Forthcoming articles

 


International Journal of Ad Hoc and Ubiquitous Computing

 

These articles have been peer-reviewed and accepted for publication in IJAHUC, but are pending final changes, are not yet published and may not appear here in their final order of publication until they are assigned to issues. Therefore, the content conforms to our standards but the presentation (e.g. typesetting and proof-reading) is not necessarily up to the Inderscience standard. Additionally, titles, authors, abstracts and keywords may change before publication. Articles will not be published until the final proofs are validated by their authors.

 

Forthcoming articles must be purchased for the purposes of research, teaching and private study only. These articles can be cited using the expression "in press". For example: Smith, J. (in press). Article Title. Journal Title.

 

Articles marked with this shopping trolley icon are available for purchase - click on the icon to send an email request to purchase.

 

Articles marked with this Open Access icon are freely available and openly accessible to all without any restriction except the ones stated in their respective CC licenses.

 

Register for our alerting service, which notifies you by email when new issues of IJAHUC are published online.

 

We also offer RSS feeds which provide timely updates of tables of contents, newly published articles and calls for papers.

 

International Journal of Ad Hoc and Ubiquitous Computing (65 papers in press)

 

Regular Issues

 

  •   Free full-text access Open AccessBilateral multi-issue negotiation of execution contexts by proactive document agents
    ( Free Full-text Access ) CC-BY-NC-ND
    by Jerzy Kaczorek, Bogdan Wiszniewski 
    Abstract: A proactive document can react to its actual environment by autonomously selecting and performing actions integrated into its body and interact with its user. When migrating over a network of execution devices it may encounter diverse execution contexts, each one set up according to the temporal characteristics of a receiving device and preferences of its owner. A concept to augment proactive documents with negotiation capability is proposed to make them responsive to such dynamically changing contexts, and implemented in a system where they that can migrate as attachments to email messages, owing to a dedicated email client capable of handling them. Negotiation is based on a simple game-theoretic mechanism to minimise computation load on execution devices. Four negotiation algorithms are proposed and two of them evaluated in more detail in a series of experiments, when respectively, negotiating parties do not or do have knowledge on past encounters and negotiated contracts.
    Keywords: proactive documents; dynamic execution contexts; mobile agents; multi-issue negotiations; ad hoc collaborative processes;.
    DOI: 10.1504/IJAHUC.2019.10018357
     
  • Friend Circle Identification in Ego Network based on Hybrid Method   Order a copy of this article
    by Ma TingHuai, Fan Xing, Meili Tang, Donghai Guan 
    Abstract: The ego network, which is a network of a user with his/her friends, is large-scale and tanglesome, and nowadays it is imperative to find a suitable method to automatically administrate it. The social network analysis method has provided some methods to help users classify their friends, including manually categorizing friends into social circles or system classification. Whereas, categorizing friends manually is time consuming for users and the results are not accurate enough. In this paper, we will discuss how to realize community identification automatically and accurately. To achieve this, we propose a method which utilizes not only the similarity of user attributes but also the features of network structure and friends contact frequency. On the basis of the users' profile, we identify the relationship between them firstly. Second, we solve the problem of community identification using of the structure features while profiles losing. Third, we introduce a concept, contact frequency, which will help us identify the relationship between users and their friends more accurately. Extensive experiments on real-world data show that our approach outperforms the state-of-the-art technique, in terms of balance error rate and F1 score.
    Keywords: ego networks; communities; user attribute; network structure; contact frequency.

  • Delay-Tolerant Forwarding Strategy for Named Data Networking in Vehicular Environment   Order a copy of this article
    by Meng Kuai, Xiaoyan Hong, Qiangyuan Yu 
    Abstract: Named Data Networking (NDN) has been considered as a promising networking architecture for Vehicular Ad-Hoc Networks (VANETs). However, Interest forwarding in NDN suffers severe issues in vehicular environment. Broadcast storms result in much packet loss and huge transmission overhead. Also, link disconnection caused by highly dynamic topology leads to low packet delivery ratio and extreme long delay in data retrieval. Thus, an efficient NDN forwarding strategy to retrieve data is urgently required. In this paper, we propose the Density-Aware Delay-Tolerant (DADT) Interest forwarding strategy to retrieve traffic data in vehicular NDN. DADT specifically addresses data retrieval during network disruptions using Delay Tolerant Networking (DTN). It makes retransmission decisions based on directional network density. Also, DADT mitigates broadcast storms by using a rebroadcast deferring timer. We compared DADT against other strategies through simulation and the results show that it can achieve a higher satisfaction ratio while maintaining low transmission overhead.
    Keywords: Density-Aware; Delay-Tolerant; Interest Forwarding; Named Data Networking; Vehicular Networks.
    DOI: 10.1504/IJAHUC.2017.10013072
     
  • Link-Preserving Channel Assignment Game for Wireless Mesh Networks   Order a copy of this article
    by Li-Hsing Yen, Bo-Rong Ye 
    Abstract: To deliver user traffic in a wireless mesh network, mesh stations equipped with multiple interfaces communicate with one another utilizing multiple orthogonal channels. Channel assignment is to assign one channel to each interface to minimize co-channel interference among wireless links while preserving link connectivity. The interference and connectivity objectives are generally conflicting. This paper first analyzes the probability of link connectivity when channels are randomly assigned to interfaces. We then propose a game-theoretic approach that jointly considers the two objectives with a unified payoff function. We prove that the proposed approach is an exact potential game, which guarantees stability in a finite time. We also prove the link-preserving property of the approach. Simulation results show that the proposed approach generally outperforms counterparts in terms of network interference when a moderate number of channels are available. For fairness of link interference, both the proposed approach and its variant outperform the counterparts.
    Keywords: channel assignment; wireless mesh network; interference; connectivity; game theory.

  • Performance Analysis of truncated ARQ and HARQ I protocols for cooperative networks using Smart Amplify and Forward Relaying   Order a copy of this article
    by Nadhir Ben Halima, Hatem Boujemaa 
    Abstract: In this paper, we evaluate the theoretical performance of truncated Automatic Repeat reQuest (ARQ) and Hybrid ARQ I protocols with and without packet combining in cooperative networks using smart amplify and forward relaying. In cooperative networks, the retransmission can be done by the source or by a selected relay. The selected relay is the one which offers the best instantaneous Signal to Noise Ratio (SNR) of the relaying link. We provide a theoretical framework when there is a combination of source and relays transmission for a destination using a Maximum Ratio Combining of the received packets from the source and the relays. Smart relays are studied in this paper. These relays selected the best packet from the source. We will show that the performance is better for smart relays that continuously supervise the transmissions from the source compared to conventional relays overhearing only the first source transmission. We also suggest smart relays listening to each other.
    Keywords: HARQ; Cooperative Systems; Amplify and Forward.
    DOI: 10.1504/IJAHUC.2017.10013340
     
  • On the Parallel Programmability of JavaSymphony for Multi-cores and Clusters   Order a copy of this article
    by Muhammad Aleem 
    Abstract: This paper explains the programming aspects of a promising Java-based programming and execution framework called JavaSymphony. JavaSymphony provides unified high-level programming constructs for applications related to shared, distributed, hybrid memory parallel computers, and co-processors accelerators. JavaSymphony applications can be executed on a variety of multi-/many-core conventional and data-parallel architectures. JavaSymphony is based on the concept of dynamic virtual architectures, which allows programmers to define a hierarchical structure of the underlying computing resources and to control load-balancing and task-locality. In addition to GPU support, JavaSymphony provides a multi-core aware scheduling mechanism capable of mapping parallel applications on large multi-core machines and heterogeneous clusters. Several real applications and benchmarks (on modern multi-core computers, heterogeneous clusters, and machines consisting of a combination of different multi-core CPU and GPU devices) have been used to evaluate the performance. The results demonstrate that the JavaSymphony outperforms the Java implementations, as well as other modern alternative solutions.
    Keywords: Parallel programming; Java; Multi-core Scheduler; GPU computing.
    DOI: 10.1504/IJAHUC.2017.10006700
     
  • Acoustic Energy-based Sensor Localization With Unknown Transmit Energy Levels   Order a copy of this article
    by Xiaoping Wu 
    Abstract: When the transmit energy levels are unavailable, semidefinite programming (SDP), mixed second order cone programming and semidefinite programming (SOC/SDP) and the linear least square estimator with source-anchor measurements (LLS-SA) are proposed to estimate the source locations in the wireless sensor networks. The proposed three algorithms avoid the shortcoming of the maximum likelihood (ML) estimator which requires the initial solution guess to ensure the global convergence. By relaxing the acoustic energy-based localization model into convex optimization, the SDP, SOC/SDP algorithms provide the robust solutions to the source location estimates for the cooperative localization. The non-cooperative LLS-SA represents the source location estimates as algebraic closedform solutions which are further improved by using location refinement (LR) technique. The simulations show that the convex optimization algorithms including the SDP and SOC/SDP provide more robust solutions to the source location estimates compared with the linear estimator of LLS-SA. However the proposed LLS-SA runs faster than the SDP and SOC/SDP. The accuracy performance of the designed SOC/SDP is similar to that of the SDP, but the complexity of the SOC/SDP is greatly lower than that of the SDP for the same network configuration.
    Keywords: wireless sensor networks; sensor localization; acoustic energy-based; convex optimization.
    DOI: 10.1504/IJAHUC.2017.10006702
     
  • A Hybrid Intelligent Control based Cyber-Physical System for Thermal Comfort in Smart Homes   Order a copy of this article
    by Jiawei ZHU 
    Abstract: With the fast development of human society, as environmental issues have drawn incomparable attention, energy efficiency is playing a significant role in residential buildings. Meanwhile, spending more time in homes leads people to constantly improve comfort there. Considering the fact that space heating makes a great contribution to residential energy consumption and thermal comfort, this paper presents a novel hybrid intelligent control system to manage space heating devices in a smart home with advanced technologies to save energy while to increase thermal comfort level. The approach combines a meta-heuristic algorithm used to compute a setpoint from the Predicted Mean Vote model with a Proportional-Integral-Derivative controller for indoor temperature regulation. In order to validate the system, computer simulations are conducted and analyzed. The results indicate the proposed control system can provide better thermal comfort comparing with other conventional and intelligent control methods, and consume less energy when demand response is considered.
    Keywords: thermal comfort; demand response; smart home; cyber-physical system; particle swarm optimization.
    DOI: 10.1504/IJAHUC.2017.10006704
     
  • A Smart Proactive Routing Protocol in Cognitive Radio Networks   Order a copy of this article
    by Mahsa Soheil Shamaee, Mohammad Ebrahim Shiri, Masoud Sabaei 
    Abstract: In this paper, we propose a smart proactive routing protocol based on Q-learning to find the most stable routes which impose minimum interference on the primary users. Unlike the traditional proactive routing protocols, in our proposed method, control packets are not broadcast whenever the network topology changes. Indeed, we apply a generalized version of Q-learning to predict the model of the routes stability. This model is used to prevent the floods of state information that is ineffective for routing decisions. The frequency of changes in the model is much less than that in the network topology. In our protocol, secondary users broadcast control packets with any changes in the model which reduces the routing overhead. The simulation results show that our routing protocol outperforms the existing ones in terms of throughput and the imposed interference on the primary users' spectrum as well as overhead.
    Keywords: Proactive Routing; Routes Stability; Control Overhead; Q-learning; Reinforcement Learning; Cognitive Radio; Primary Users; Secondary Users; Opportunistically Access; Channel Availability.

  • A Scalable Middleware for Context-aware Mobile Applications   Order a copy of this article
    by Loris Belcastro, Fabrizio Marozzo, Paolo Trunfio 
    Abstract: A core functionality of context-aware mobile applications is storing, indexing, and retrieving information about users, places, events and other resources. The goal of this work is to design and provide a service-oriented middleware, called Geocon, which can be used by mobile developers to implement such functionality. To represent information about users, places, events and resources of context-aware applications, Geocon defines a metadata model that can be extended to match specific application requirements. The middleware includes a geocon-service for storing, searching and selecting metadata about users, resources, events and places of interest, and a geocon-client library that allows mobile applications to interact with the service through the invocation of local methods. The paper describes the Geocon middleware and presents an experimental evaluation of its scalability on a cloud platform with a real-world mobile application.
    Keywords: Context-aware; Mobile applications; Middleware; Scalability; Cloud computing.

  • Automatic String Deobfuscation Scheme for Mobile Applications Based on Platform-level Code Extraction   Order a copy of this article
    by WooJong Yoo, Minkoo Kang, Myeongju Ji, Jeong Hyun Yi 
    Abstract: The Android operating system is vulnerable to various security threats owing to structural problems in Android applications. String obfuscation is one of the required protection schemes developed to protect Android application code. However, string obfuscation is being thwarted by malware makers and malware analysis is becoming more difficult and time-consuming. This paper proposes an automatic string deobfuscation and application programming interface (API) hiding neutralisation scheme that requires no encryption algorithm analysis or encryption key information. The proposed scheme has its own independent obfuscation tool. Further, it extracts and analyses code from the Android platform while the application is being executed and inserts only a return string value from the extracted code into the DEX file. The results of experiments conducted, in which commercial obfuscation tools Allatori, DexGuard, and DexProtector were applied to sample applications, verify the efficacy of the proposed method.
    Keywords: Reverse Engineering; Deobfuscation; Mobile Malware; Android;.

  • ACFC: Ant Colony with Fuzzy Clustering Algorithm for Community Detection in Social Networks   Order a copy of this article
    by Marjan Naderan, Marjan Naderan, Seyed Enayatollah Alavi 
    Abstract: In this paper, we suggest a bipartite algorithm, namely ACFC, for finding communities in social networks. First, we use artificial ants to traverse the network modeled by a graph based on a set of rules to find a "good region" of edges. Next, we construct the communities after which local optimization methods are used to further improve the solution quality. Finally, we use the Fuzzy C-Means (FCM) clustering algorithm to fine tune the result. In our method ants are only used to identify good regions of the search space and construction methods are used to build the final solution. Experimental results on several synthetic graphs and four real world social networks compared to six other well-known methods show that our ACFC algorithm is very competitive against current state-of-the-art techniques for community detection and it is more accurate than existing algorithms as it performs well across many different types of networks.
    Keywords: Community Detection; Social Networks; Ant Colony; Q modularity; Fuzzy Clustering.
    DOI: 10.1504/IJAHUC.2017.10008798
     
  • An Adaptable CS-Based Transmission Scheme in Wireless Sensor Network   Order a copy of this article
    by Hao Yang, Keming Tang 
    Abstract: As the essential requirement of wireless sensor network, energy-efficient data transmission has been paying a lot attention. Compressive Sensing(CS) has been currently utilized to save consumption of sensors. However, a vital problem still remains unclear that whether the execution costs of sensors employing CS is not worth being considered, motivating us to explore the answer from a point of real deployment platform view. Presenting observations from our operating sensor network, we verify two important facts: 1) The power costs of measure processing of sensors cannot be negligible as the increasing of samplings. 2) Measurements will constantly change along the routing and force relay sensors to consume more. Based on our findings, we propose an adaptable CS-based transmission scheme, ACS. With our experiments, energy is economized at least 15%. Our work gives a potential guideline for future designs of WSN in practice.
    Keywords: Compressive sensing; Data transmission; Adaptable transmission; Wireless sensor network.

  • Energy Aware Optimal Slot Allocation Scheme for Wearable Sensors in First Responder Monitoring System   Order a copy of this article
    by Mahin K. Atiq, Kashif Mehmood, Muhammad Tabish Niaz, Hyung Seok Kim 
    Abstract: In recent advances in first response techniques, the uniform of each first responder working at the emergency field may be equipped with sensors and a gateway. These wearable sensors in conjunction with the gateway constitute a first responder monitoring system (FRMS). FRMS gathers data about the first responders's vitals and the surrounding environment, which is then transmitted to the incident commander. For the energy-constrained nature of the FRMS, an energy-ecient slot allocation scheme is proposed. The energy-ecient scheme involves the design of an optimal slot allocation scheme based on Hungarian algorithm for sensor data collection and an energy-aware sensing and transmission scheme for sensor nodes. Simulation results demonstrate the superiority of proposed scheme in terms of lifetime, residual energy, and energy delay product as compared to greedy and first-in-first-out (FIFO) slot allocation schemes.
    Keywords: Slot allocation; Hungarian algorithm; Sensing and transmission scheme; Wearable sensor systems; First responder monitoring.
    DOI: 10.1504/IJAHUC.2017.10017734
     
  • A Statistical Detection Mechanism for Node Misbehaviors in Wireless Mesh Networks (WMNs)   Order a copy of this article
    by Rida Khatoun 
    Abstract: Wireless mesh networks (WMNs) have become an increasingly popular wireless networking technology for establishing the last-mile connectivity for home and neighbourhood networkings. In such networks, packet dropping may be due to either an attack, or normal loss events such as bad channel quality. Furthermore, in the route discovery phase, path stability is not always considered. We consider a special case of denial of service (DoS) attack in WMNs known as the greyhole attack. In this attack, a node selectively drops some packets which it has to forward along the path. To mitigate this attack, we propose a dropping detection mechanism allowing a mobile node to select a most reliable route to the destination. Our detection module detects misbehaving nodes by comparing the observed packet loss distribution of nodes to the expected ones when they are well-behaved. We validate the proposed approach via extensive simulations through R software and Matlab.
    Keywords: Wireless Mesh Networks; Misbehavior; Detection.
    DOI: 10.1504/IJAHUC.2017.10009416
     
  • Malicious User Detection with Local Outlier Factor during Spectrum Sensing in Cognitive Radio Network   Order a copy of this article
    by Suchismita Bhattacharjee 
    Abstract: In collaborative sensing, multiple secondary users (SUs) cooperate for a more accurate sensing decision to detect spectrum holes in cognitive radio networks (CRNs). This technique, however, can be adversely affected by malicious users (MUs) who route falsified spectrum sensing data to the fusion centre (FC). This attack is known as the spectrum sensing data falsification (SSDF) attack. The task of the FC is to aggregate local sensing reports and is thereby responsible for making the final sensing decision. In this paper, we propose a detection and isolation scheme based on local outlier factor (LOF) to detect and reduce the unfavourable effects of SSDF attack. The key feature of this scheme is that for each SU a metric is calculated, which is called the LOF. Based on the LOF, a decision is made about whether an SU is an attacker or not. We support the validity of the proposed scheme through extensive simulation results.
    Keywords: Cognitive Radio Networks; Local Outlier Factor; Collaborative Spectrum Sensing; SSDF Attack; Independent Attack; Colluding Attack; Fusion Center.
    DOI: 10.1504/IJAHUC.2017.10009417
     
  • A Critical Review of Quality of Service Models in Mobile Ad hoc Networks   Order a copy of this article
    by Nadir Bouchama, Djamil Aïssani, Natalia Djellab, Nadia Nouali-Taboudjemat 
    Abstract: Quality of service (QoS) provisioning in mobile ad hoc networks (MANETs) consists of providing a complex functionality in a harsh environment where resources are scarce. Thus, it is very challenging to build an efficient solution to address this issue. The proposed solutions in the literature are broadly classified into four categories, namely: QoS routing protocols, QoS signalling, QoS-aware MAC protocols and QoS models, which are the main concern of our study. The contribution of this paper is threefold: Firstly,wepropose a set of guidelines to deal with the challenges facing QoS models design in ad hoc networks. Secondly, we propose a new taxonomy for QoS models in ad hoc networks. Finally, we provide an in-depth survey and discussion of the most relevant proposed frameworks.
    Keywords: Mobile ad hoc networks; Quality of service; IntServ; DiffServ; QoS models; QoS routing; Hard QoS; Soft QoS.
    DOI: 10.1504/IJAHUC.2017.10009418
     
  • Detection of Malicious Packet Dropping Attacks in RPL-based Internet of Things   Order a copy of this article
    by Sooyeon Shin, Kyounghoon Kim, Taekyoung Kwon 
    Abstract: The Internet of Things (IoT) may involve a large number of devices highly constrained in their resources in terms of power, memory, computation, and communication. To cover an increasing number of IoT devices, the IPv6 paradigm is essentially required. RPL (Routing Protocol for Low-Power and Lossy Networks) is an IPv6-based routing protocol optimized for IoT environments and it supports a powerful and flexible routing framework for a variety of application scenarios of IoT. However, it is susceptible to various security threats including a malicious packet dropping attack, which uses internal compromised nodes to threaten the operation of network. If a node with a lower rank closer to the root node attempts a malicious packet dropping, it may disrupt basic data transmission, or even the entire IoT application service. In this paper, we present a novel detection method for malicious packet dropping attacks against RPL-based networks. The proposed method is based on the anomaly IDS approach and detects a malicious packet dropping in the presence of normal packet losses caused by collisions or channel errors. We evaluate the performance of the proposed method on Contiki's network simulator, Cooja. The evaluation results show that it has good performance to detect malicious packet dropping attacks in the RPL-based networks. In every case, the successful detection rate is more than 94% and the false alarm rate is less than 3%.
    Keywords: Internet of Things; IPv6; RPL; 6LowPAN; Packet Dropping; Detection; ContikiOS; Cooja simulator.

  • GPU-based distributed bee swarm optimization for dynamic vehicle routing problem   Order a copy of this article
    by Maroua Grid, Noureddine Djedi, Salim Bitam 
    Abstract: Nowadays, there is still a large gap between the requirements and the performance of decision support systems for many problems such as the vehicle routing problem, consists in conceiving a set of optimal routes for a fleet of vehicles, aiming at serving a given number of customers. Nevertheless, new customer orders could be introduced while a prior plan is in progress. Therefore, routes should be recalculated in a dynamic way. In this paper, we propose a new parallel combinatorial optimization method based on Graphic Processing Unit (GPU) called Parallel Bees Life Algorithm (P-BLA) to solve efficiency the Dynamic Capacitated vehicle routing problem (DCVRP) in terms of execution time, and to reduce computational complexity often considered as the major drawback of conventional optimization methods. P-BLA is developed using CUDA framework performed on island-based GPU. After a set of comparisons against conventional methods namely; genetic algorithm, ant system, Tabu search and sequential BLA, P-BLA has provided efficient results reached from the most tested DCVRP benchmarks.
    Keywords: DCVRP; k-means; P-BLA; Parallel optimization; GPGPU.

  • Linear Closed-Form Estimator for Sensor Localization Using RSS and AOA Measurements   Order a copy of this article
    by Jian Zhang 
    Abstract: Using the hybrid received signal strength (RSS) and angle of arrival (AOA) measurements, a position estimation model is proposed for senor localization in three-dimensional plane. Then the unconstraint linear least square (ULLS) estimator is designed to obtain a closed-form solution to the positions of source nodes by considering the known transmit power. To improve the accuracy performance of the ULLS estimator, the constraint linear least square (CLLS) estimator is introduced by utilizing the constraint condition. When the transmit power is unavailable, a global linear least square (GLLS) estimator is also put forward to estimate the positions of source nodes along with the transmit power. The simulations show that the computational complexity of the proposed linear estimators is greatly lower than that of the convex semidefinite programming (SDP) method. When the measurement noises are small, the linear ULLS, CLLS and GLLS estimators perform better than that of the SDP method. Due to the exploiting of constraint condition, the accuracy performance of the CLLS estimator can approach the Cram'{e}r-Rao Lower Bound (CRLB) of position estimation.
    Keywords: Wireless sensor networks (WSNs); localization; received signal strength (RSS); angle of arrival (AOA); linear least square.

  • Reverse-biform Game based Resource Sharing Scheme for Wireless Body Area Networks   Order a copy of this article
    by Sungwook Kim 
    Abstract: Current advances in wireless sensor technologies have contributed to the development of Wireless Body Area Network (WBAN). It has been considered for applications in medical, healthcare and sports fields. Due to specific features and reliability requirements in WBAN, a number of new challenges have been introduced to design novel WBAN protocols. In order to cope with these challenges, game theoretic approach can allow WBANs to improve their performance while increasing their flexibility and adaptability. In this paper, we develop a new WBAN resource sharing scheme based on the reverse-biform game model. Based on the dual-level phases, the limited WBAN resource is effectively shared by employing a coordinate-and-competitive game manner. In particular, we consider the unique features of WBAN applications, and provide a generalized solution for the resource sharing problem. The simulation results demonstrate that our game-theoretic framework can provide the ability to practically respond to current WBSN conditions. This approach is suitable for real WBAN operations, particularly for the energy efficiency, network throughput, and QoS provisioning.
    Keywords: Wireless body area networks; Power control algorithm; Data-tuning mechanism; Quality of Service; Reverse-biform game.

  • Implementation of an Autonomous Intelligent Mobile Robot for Climate Purposes   Order a copy of this article
    by Mohammad Samadi Gharajeh 
    Abstract: One of the main requirements in humans lifecycle is to predict environmental situations (e.g., pollution density) over various areas. Since determining the climate information by using traditional electromechanical devices is very expensive, autonomous robots can be used to organize this mission. This paper proposes an autonomous intelligent mobile robot for climate purposes, called ClimateRobo, to notify the weather condition based on environmental data. An ATmega32 microcontroller is used to measure temperature, gas, light intensity, and distance to obstacles using the LM35DZ, MQ-2, photocell, and infrared (IR) sensors. A utility function is proposed to calculate the weather condition according to the temperature and gas data. Afterwards, the weather condition will be monitored on a liquid crystal display (LCD), an appropriate light-emitting diode (LED) will be illuminated, and an audio alarm would be enabled when weather condition is emergency as well as ambient brightness is high. The ambient brightness is calculated by a proposed supervised machine learning using sensed data of the photocell sensor. A fuzzy decision system is proposed to adjust the speed of DC motors based on weather condition and light intensity. The robot can detect and pass stationary obstacles with the six reflective sensors installed in the left, front, and right sides under six detection scenarios. Simulation results show performance of the proposed supervised machine learning, fuzzy decision system, and obstacle detection mechanism under various simulation parameters. The robot, initially, is simulated in the Proteus simulator and, then, is implemented by electronic circuits and mechanical devices. It would be used in the future by bureau organizations, rescue teams, etc.
    Keywords: Autonomous Intelligent Robot; Weather Condition; Utility Function; Supervised Machine Learning; Fuzzy Decision System; Sensor.

  • Trust Management in Vehicular Ad hoc Networks: a survey   Order a copy of this article
    by Ilhem Souissi, Nadia Ben Azzouna, Tahar Berradia 
    Abstract: The vehicular ad hoc networks (VANETs) provide a variety of applications that aim to ensure a safe and comfort driving experience. These applications rely on the communication and the exchange of data between vehicles. These entities are exposed to many security threats that may affect the reliability of the provided applications. Accordingly, there is a need for a trust management scheme that has to cope with the security threats and the high dynamicity of the network topology. In this paper, we survey the recent advances in trust management for VANETs. The aim of this paper is to show the importance of an adaptive trust model that can deal with the requirements of each class of applications. Therefore, we have presented well-defined criteria to point out the key issues of the existing studies and to set up some insights for research within this scope.
    Keywords: VANET; security; trust management; attacks; reputation; similarity; behavior; utility.

  • Multi-constraint Zigbee Routing to Prolong Lifetime of Mobile Wireless Sensor Networks   Order a copy of this article
    by Chhagan Lal, Pallavi Kaliyar, Chotmal Choudhary 
    Abstract: Due to the recent developments in hardware technology and deployment techniques, Mobile Wireless Sensor Networks (MWSNs) are attracting a large array of real-world applications. However, practical realization of these applications is still constrained due to inherent characteristics of MWSNs such as highly dynamic topology, low bandwidth, and finite energy of nodes. These characteristics causes threat to MWSNs basic functionalities, which includes network formation, self-organization, route discovery, and communication management. Hence, improving the lifetime of MWSNs, and minimizing the mobility induced route breaks are the key issues in MWSNs. Zigbee is an advanced technology that works on IEEE standard 802.15.4 and it is suitable for contrainted networks such as MWSNs as well. The main features of Zigbee such as low energy and network bandwidth consumption, and lower deployment cost greatly helps to prolong network lifetime in MWSNs. To this end, in this paper, we propose a multi-constraint Zigbee based Reactive Routing (MZRR) protocol for MWSNs to prolong the network lifetime. Our MZRR protocol uses node energy and hop-to-hop transmission efficiency along with network mobility as metrics during its route discovery process to discover highest remaining lifetime routes. MZRR protocol ensures that the discovered routes has high transmission efficiency which leads to low energy and link bandwidth consumption in the network. By keeping the energy utilization of sensors balanced, MZRR protocol avoids the dead zones in the surveillance areas, this could be very important in data-critical applications. We fully implement MZRR protocol on NS-3 simulator, and the results obtained are compared with traditional AODV and state-of-the-art routing algorithms in terms of relevant parameters such as energy consumption, end-to-end delay, packet delivery ratio, network life-time and network routing overhead.
    Keywords: Wireless Sensor Network; Zigbee; Energy Efficiency; Network Mobility; Link Lifetime; IEEE 802.15.4.

  • Reliable Sense Maintenance Scheme by Sense Holes Recognized and Self-healing in Sensor Networks of Internet of Things   Order a copy of this article
    by J.U.N. LIU, Xu Lu, Tao Wang 
    Abstract: Sense holes recognized and repaired in sensor networks have important significance for sense performance. Most of the existing researches are based on the assumption that the sensor can provide the location or other ideal condition. In this paper, a distributed reliable sense maintenance scheme by sense holes recognized and self-healing was presented. Firstly, it reduced the required nodes density limit to maintain a reliable sense by mathematical analysis. Then, sense holes recognized algorithm based on the Hamiltonian graph and computation geometry was proposed in this paper. It could identify triangular holes and realize a good recognition rate without an accurate position. Based on virtual forces strategy, sense holes self-healing algorithm was presented. Simulation results showed the algorithm was superior to others in energy-balancing. The sense holes recognized algorithm could efficiently and quickly detect sense holes in sensor networks as shown in simulations.
    Keywords: Sensor networks; Sense hole recognized; Self-healing; Nodes deployment.

  • Application of Congestion Avoidance Mechanism in Multimedia Transmission over Mesh Networks   Order a copy of this article
    by Biaokai Zhu, Jumin Zhao, Deng-ao Li, Ruiqin Bai 
    Abstract: The unreliable nature and shared multi-media of multi-hop communications cause the deployment of multi-media applications in wireless mesh network a thorny problem. For instance, video is usually compressed into a group of frames before transmission, resulting in unrecoverable destruction during the display process. The importance of different frames' type is quite different. However, they are considered as same in most existing wireless mesh networks. In this paper, we propose a novel Congestion Avoidance Mechanism for multimedia transmission over 802.11e mesh networks. In our mechanism, we added priority for video packets. According to the significance of frames, we proposed an adaptive mechanism involves the mapping of H.264 video packets to appropriate access categories in IEEE 802.11e standard. Simulation results show that our mechanism improves Quality of Service (QoS) of multimedia transmission.rn
    Keywords: Multimedia transmission; 802.11e; wireless mesh network.

  • Efficient Data Dissemination Approach For QoS Enhancement in VANETs   Order a copy of this article
    by Sachin Khurana, Gaurav Tejpal, Sonal Sharma 
    Abstract: Vehicular ad hoc networks (VANETs) have seen tremendous growth in the last decade, providing a vast range of applications in both military and civilian activities. The temporary connectivity in the vehicles can also increase the driver's capability on the road. However, such applications require heavy data packets to be shared on the same spectrum without the requirement of excessive radios. Thus, efficient approaches are required which can provide improved data dissemination along with the better quality of services to allow heavy traffic to be easily shared between the vehicles. In this paper, an efficient data dissemination approach is proposed which not only improves the vehicle to vehicle connectivity but also improves the QoS between the source and the destination. The proposed approach is analyzed and compared with the existing state-of-the-art approaches. The effectiveness of the proposed approach is demonstrated in terms of the significant gains attained in the parameters namely, end to end delay, packet delivery ratio, route acquisition time, throughput, and message dissemination rate in comparison with the existing approaches.
    Keywords: VANETs; delay; QoS; Data Dissemination; Fuzzy sets.

  • A Challenge-Response Mechanism for Securing Online Social Networks against Social Bots   Order a copy of this article
    by Mohamed Torky, Ali Meligy, Hani Ibrahim 
    Abstract: Social bots is fast becoming a serious security threat to Online Social Networks (OSNs). Social bots are automated software tools able to execute malicious activities in OSNs systems in an automated fashion. It can perform auto-sharing and posting, sending fake friend requests, harvesting private information, etc. There is evidence that social bots play a crucial role in penetrating privacy and security of social networks. Hence, these malicious software tools represent a big security challenge against Social Network Service Provider (SNSP). In this paper, we introduce a novel anti-bot mechanism called Necklace CAPTCHA for securing OSNs platforms against the automated behaviors of social bots. Necklace CAPTCHA is an Image-based CAPTCHA, which utilizes the functionality of Necklace Graph approach to generate its challenge-response tests in a novel fashion. The results demonstrated that Necklace CAPTCHA is an effective and secure anti-bot mechanism compared with other CAPTCHAs in the literature with respect to the usability and security metrics.
    Keywords: Online Social Networks (OSNs); Security and Privacy; System Usability; Social Bots ; CAPTCHA; Necklace Graph.

  • Design of a Monitoring and Safety System for Underground Mines Using Wireless Sensor Networks   Order a copy of this article
    by Coert Jordaan, Reza Malekian 
    Abstract: A mine safety system using a wireless sensor network is implemented. Sensor nodes and a monitoring system are developed to be used in the underground mining environments. Investigations are done into sensor design for underground mines, as well as the use of sensors to profile the underground mining environment and the use of wireless communication in the underground mining environment. The information is used to design and implement a robust hardware-based sensor node with standalone microcontrollers that sample data from six different sensors, namely temperature, humidity, airflow speed, noise, dust and gas level sensors, and transmit the processed data to a graphical user interface, developed using Qt Creator. The system reliability and accuracy is tested in a simulated mine. The wireless mine profiling sensor node, with its monitoring software and receiver unit was successfully implemented. It provided linear and accurate results over nearly a month of daily testing in the simulated mine. It is observed that critical success factors for the wireless sensor node is its robust design, which does not easily fail or degrade in performance. The node also has strong, self-adaptive networking functionality, to recover in the case of a node failure.
    Keywords: Mine safety system; wireless sensors; temperature sensor; humidity sensor; airflow speed sensor; noise sensor; dust sensor; gas sensor; error detection.

  • Signal Technique for Friend or Foe Detection of Intelligent Malicious User in Cognitive Radio Network   Order a copy of this article
    by Saifur Rahman Sabuj, Masanori Hamamura 
    Abstract: To address spectrum scarcity, cognitive radio networks have been proposed as a means to improve spectrum utilization and effciency. In regulation policy for cognitive radio networks, unlicensed users (secondary users) are allowed to utilize unoccupied spectrum when it is not being used by licensed users (primary users). In point of fact, security issues arise when intelligent malicious users can attack cognitive radio networks and decrease the permitted channel for secondary users. In this paper, we propose a novel scheme, based on friend or foe (FoF) detection technique with physical layer network coding, to enable discrimination between secondary users and intelligent malicious users. Theoretical expressions are derived for probabilities of detection of secondary user, miss detection, and false alarm. In addition, the effectiveness of the proposed approach is evaluated by theoretical analysis and Monte Carlo simulation. Furthermore, an algorithm is proposed for distinguishing between secondary user and intelligent malicious user. Finally, based on the outcome of simulation of probabilities and normalized cross- correlation, it is determined that the proposed scheme outperforms in terms of OFDM signal compared with QPSK signal over cognitive radio network.
    Keywords: Cognitive radio network; Friend or foe detection; Physical-layer network coding; Cross-correlation.

  • Designing Secure and Reliable Mobile Agent Based System for Reliable MANET   Order a copy of this article
    by Moumita Roy, Chandreyee Chowdhury, Munshi Navid Anjum, Sarmistha Neogy 
    Abstract: Mobile Adhoc NETwork (MANET) provides a promising platform for pervasive computing applications. Mobile agents are found to be effective for executing such pervasive computing applications. The motivations behind this are advancement in technology, wireless networking, sensor network, ambient intelligence etc. However, since MANET is inherently more vulnerable to security threats and prone to topology changes, reliability and security issues must be addressed before mobile agents are commercially deployed. There are few works on securing mobile agents but even fewer focuses on MANET. This work is our attempt to design a lightweight trust based reputation scheme to protect the agents against network layer threats. The scheme is based on Dempster-Shafer belief theory. Performance of the trust based reputation scheme with respect to network and system reliability is analyzed. The work is simulated and the results show that even for a fairly hostile MANET, the effective reliability of distributed application can be increased using mobile agent based system.
    Keywords: Reputation; Trust; Demster-Shafer Belief Theory; Reliability; Monte Carlo Simulation.

  • Energy Efficient Hierarchical Multi-Path Routing Protocol to Alleviate Congestion in WSN   Order a copy of this article
    by Sunitha GP, Dilip Kumar S M, Vijay Kumar B P 
    Abstract: Congestion easily occurs in wireless sensor networks (WSN) due to it's centralized traffic pattern. It has a negative impact on the network performance in terms of decreasing throughput and increasing energy consumption. %In WSN, the main concern is to control congestionrnIn order to achieve high energy efficiency, network longevity, better fairness and quality of service, it is important to detect congestion in (WSN) in a timely manner. In this paper, an energy efficient hierarchical multi-path routing protocol to alleviate congestion and energy balancing problems is proposed.rn The algorithm is designed by partitioning the network into equal sized zones to achieve complete network connectivity and to reduce packet transmissions. The zone leaders ((ZL's)) selected are shifted on different nodes on network dynamic conditions to avoid hotspots and to provide energy balancing. For efficient data transmission quicker and optimal multiple paths are established using merged zone and Hierarchical network ((HiNet)) topology structure. The proposed algorithm detects the congestion by monitoring the path quality. The detected congestion is a result of overloaded links or nodes on the path. In addition, the algorithm proactively controls the congestion by dynamically shifting the transmission paths on their quality and alleviate it reactively using traffic splitting approach. The goal of this approach is to control resources instead of controlling the network load. The simulation results demonstrate that the proposed algorithm performs better as compared to other congestion control algorithms in terms of throughput, energy consumption and packet delivery ratio in a resource constraint wireless sensor network
    Keywords: Congestion control; Multi-path routing; Energy efficiency; Load balancing; WSN.

  • An Adaptive Wi-Fi Indoor Localization Scheme using Deep Learning   Order a copy of this article
    by Chih-Shun Hsu, Yuh-Shyan Chen, Tong-Ying Juang, Yi-Ting Wu 
    Abstract: Indoor localization is an important issue for many indoor applications. Many deep learning-based indoor localization schemes have been proposed. However, these existing schemes cannot adjust according to different environment. To improve the existing schemes, a novel indoor localization scheme, which can adaptively adopt the proper fingerprint database according to the collected signals, is proposed in this paper. The proposed scheme consists of the off-line and the on-line phases. A deep learning architecture with seven hidden layers is designed for the off-line phase. Two consecutive hidden layers form a Restricted Boltzmann Machine, which uses the ${k}$-step contrastive divergence algorithm for the layer-by-layer training. The proposed Wi-Fi indoor localization scheme uses two fine-tuning algorithms, namely the cross entropy and the mean squared algorithms, to build the corresponding fingerprint databases. As for the on-line phase, the Bayesian probability algorithm is used for position estimation. The fingerprint databases built during the off-line phase are adaptively adopted during the on-line phase. When the standard deviation of the collected signals does not exceed the threshold, the fingerprint database built by the cross entropy algorithm is adopted; when the standard deviation of the collected signals exceed the threshold, the fingerprint database built by the mean squared algorithm is adopted. The experiments were implemented and validated in a noisy and noise free indoor environment. The experimental results show that the proposed scheme can improve the accuracy of the training data and reduce the localization error.
    Keywords: deep belief network; deep learning; indoor positioning; Wi-Fi; fingerprinting localization.

  • A Novel Faster Failure Detection Strategy for Link Connectivity using Hello Messaging in Mobile Ad Hoc Networks   Order a copy of this article
    by Alamgir Naushad, Ghulam Abbas, Ziaul Haq Abbas, Lei Jiao 
    Abstract: Faster failure detection is one of the main steps responsible for efficient link connectivity in mobile ad hoc networks (MANETs). Under a random behavior of network nodes and link/node failure, there must be a unified approach to describe an adequate Hello messaging strategy for link connectivity in MANETs. In order to tackle this issue, we present a strategy for achieving faster failure detection, and derive algorithmic attributes of the proposed strategy on the basis of multiple parameters of interest after modelling it as a Markov process. We also present novel algorithms to minimize the biggest chunk of delay incurred as a result of link re-connectivity and, thus, improve network connectivity in MANETs. Simulation and analytical results indicate efficacy of the proposed strategy in achieving faster failure detection and efficient link re-connectivity.
    Keywords: Faster failure detection; Hello messages; MANETs; Stochastic processes; Link connectivity.

  • Mitigating SSDF Attack using Distance-based Outlier approach in Cognitive Radio Networks   Order a copy of this article
    by Wangjam Niranjan Singh, Ningrinla Marchang, Amar Taggu 
    Abstract: Collaborative spectrum sensing is employed in cognitive radio networks for improving the spectrum sensing accuracy. The collaborating cognitive radios send their individual sensing results to the fusion center (FC) which aggregates the results to come to a final sensing decision. Malicious radios may adversely influence the final sensing decision by transmitting false spectrum sensing results to the FC. This attack is commonly known as the spectrum sensing data falsification (SSDF) attack. Hence, in the light of such a threat, it is pertinent for the FC to identify any such malicious radios, if any and isolate them from the decision process. In this paper, a distance-based outlier detection approach is proposed which mines the sensing reports at the FC for detection and isolation of such malicious users. Numerical simulations results support the validity of the proposed approach.
    Keywords: SSDF attack; distance-based outlier detection; cognitive radio network; data mining.
    DOI: 10.1504/IJAHUC.2018.10015628
     
  • IOT Enabled Adaptive Clustering based Energy Efficient Routing Protocol For Wireless Sensor Networks   Order a copy of this article
    by Muhammad Asad, Aslam Hayat, Yao Nianmin, Naeem Ayoub, Khalid Ibrahim Qureshi, Ehsan Ullah Munir 
    Abstract: Wireless Sensor Networks (WSNs) consists of hundreds and thousands of micro-sensor nodes which are distributed in the sensing field to sense the uncertain events. These sensor nodes plays an important role in Internet of Things (IoT). Energy consumption has been a major issue in WSNs, various energy efficient conventional routing protocols are proposed to minimize the communication energy cost of sensor nodes. In IoT enabled WSNs, these sensor nodes are resource controlled in various ways, such as energy, storage, computing, communication and so on. In conventional routing protocols clustering technique is performing superiorly but due to the limited characteristics, suggested routing protocols are not as much smart and flexible to generate a perfect Cluster-Head (CH) because these routing protocols are limited to centralized and distributed or homogeneous and heterogeneous networks. In this paper, we propose a new IoT enabled Multi Adaptive Clustering (MAC) energy efficient routing protocol for WSNs to minimize the energy dissipation and improve the network performance. This new technique holds the hybrid cluster formation algorithm in which the network topology is divided into two regions the first region is centralized and the second region is distributed. Both regions contains homogeneous and heterogeneous nodes while the sink is static and located in the center of both networks. Specifically, proposed IoT enabled MAC routing protocol holds the major three properties: Enabling of resources to sensor nodes through IoT, hybrid cluster formation to distribute the network load evenly among sensor nodes and a new mechanism to minimize the energy consumption in long range data transmission. Our simulation results give significant proof that MAC performs better than state-of-the-art routing protocols such as LEACH-C, DEEC, D-DEEC and E-DEEC. In addition, performance evaluation proofs that MAC is suitable for the network which requires longer network lifetime.
    Keywords: Internet of Things; Wireless Sensor Networks; Energy Efficient; Routing Protocols.

  • A new approach for the recognition of human activities   Order a copy of this article
    by SALIMA SABRI, AlOUI Abdelouhab 
    Abstract: The evaluation of a patient\'s functional ability to perform daily living activities is an essential part of nursing and a powerful predictor of a patient\'s morbidity, especially for the elderly. In this article, we describe the use of a machine learning approach to address the task of recognizing activity in a smart home.We evaluate our approach by comparing it to aMarkov statistical approach and using several performance measures over three datasets. We show how our model achieves signi cantly better recognition performance on certain data sets and with different representations and discretisation methods with an accuracy measurement that exceeds 92%and accuracy of 68%. The experiments also showa signi cant improvement in the learning time which does not exceed one second in the totality of the experiments reducing the complexity of the approach.
    Keywords: Ubiquitous applications; automatic learning; Katz ADL; activity recognition; probabilistic models; wireless sensor network.

  • A Novel Method for Time Delay Prediction in Networked Control Systems   Order a copy of this article
    by Pei XU, Jianguo WU 
    Abstract: Time delay prediction is a crucial issue of networked control systems. Previous methods mainly use individual model to predict time delay, which causes the limitation that the proposed model can only be suitable applied to either linear or nonlinear data. This paper proposed a novel method to predict time delay in networked control systems which considers several different individual models as the component models to form a combined model and takes full advantages of these component models. By applying Lagrange multiplier method to minimize prediction error, the proposed OW (optimal weight) algorithm is able to calculate the proper weight coefficients of component models in order to improve the prediction performance. Compared with the existing methods, the proposed combined model can improve the prediction accuracy and support robustness, variability and scalability. The simulation experiments verify the effectiveness of the proposed method.
    Keywords: networked control systems; time delay prediction; RBF neural network; ARMA model; optimal weight; combined model.

  • A reputation-based truthfulness paradigm for multi-hop transmission in cognitive radio networks   Order a copy of this article
    by Trupil Limbasiya, Debasis Das, Ramnarayan Yadav 
    Abstract: Cognitive radio networks (CRNs) consist of numerous intellectual users with the capability of sensing and sharing underutilized spectrum, and they are called as cognitive users (CUs). The spectrum is allocated to licensed users or primary users (PUs) but, generally, they do not utilize it completely. To overcome the ever-increasing spectrum demand and utilize the underutilized licensed spectrum, the cognitive radio plays a major role. In this distributed environment, the communication among CUs becomes more challenging due to channel heterogeneity, uncontrolled environment, a need of cooperative sensing for accurate sensing result, etc. Additionally, there are different attacks, e.g., primary user emulation (PUE), control channel saturation DoS (CCSD), selfish channel negotiation (SCN), spectrum sensing data falsification (SSDF), modification, and man-in-the-middle. Then, this affects and degrades system and CRN performance, which creates an opportunity for a trust management model to manage the CRNs properly. In this paper, we propose an efficient trust management protocol for centralized and distributed CRNs that are to build a trust-based system over the complete cognitive cycle to protect against security attacks brought by the unreliable individuals. To address the security issues, a clustering scheme is used in the distributed environment for effective cooperation among CUs. The security analysis and simulation results represent that the proposed protocol can identify malicious behavior and enhance fairness and powerfulness of the network in centralized and distributed circumstances.
    Keywords: Attacks; Cognitive radio networks; Integrity; Trust management.

  • Throughput of Cooperative HARQ protocols for Underlay Cognitive Radio Networks using Adaptive and Fixed Transmit Power   Order a copy of this article
    by Nadhir Ben Halima, Hatem Boujemaa 
    Abstract: In this paper, we study theoretically and by simulations the throughput of cooperative Hybrid Automatic Repeat reQuest protocolsrnfor underlay cognitive radio networks. Both fixed and adaptive power transmission are studied. Different relay selection techniques with Amplify and Forward (AF) and Decode and Forward (DF) relaying are investigated.rnFor fixed transmit power, some relays are not available since they generate an interference to primary receiver larger than a predefined value T.rnThe best relay is selected among the available ones.rnFor adaptive transmit power, all relays adapt their power so that interference to primary receiver is always lower than a predefined threshold $T$. In this case, all relays will be available for retransmitting the secondary source packet.rnBoth Average Interference Power (AIP) and Peak Interference Power Constraints (PIP) are studied. We also analyze the effect of primary interference on secondary throughput.
    Keywords: Cognitive Radio Networks; HARQ.
    DOI: 10.1504/IJAHUC.2018.10016902
     
  • GOOSE: Goal Oriented Orchestration for Smart Environments   Order a copy of this article
    by Vincenzo Catania, Gaetano La Delfa, Giuseppe La Torre, Salvatore Monteleone, Davide Patti, Daniela Ventura 
    Abstract: Smart environment scenarios are characterized by the presence of users, with different needs and preferences, and everyday life objects exploited to meet the expectations of users themselves. Connecting objects to the Internet and making them accessible from remote is not sufficient to make an environment "smart" since such ecosystems should also be able to enable context-sensitive actions along with a management of the interaction between objects and users. In this work, we propose GOOSE, a platform which aimed at interpreting users goals expressed in natural language in order to generate, select, and safely enforce a set of plans to be executed to fulfill target goals. After highlighting the main challenges affecting typical Machine to Machine (M2M) communication scenarios, we show how the use of a semantic reasoner can be used to allow the composition of plans consisting of sequences of services to be called on the smart environment objects. Finally, we address the issue of secure communications between platform and objects, and the management of potentially inconsistent goals.
    Keywords: Machine to Machine; RESTful services; Goal-oriented Architecture; User-object interactions; Semantic descriptions; Indoor localization;.

  • Radio Characteristics and Mobility based Routing for Multimedia Services over MANETs   Order a copy of this article
    by Lokesh Sharma, Chhagan Lal 
    Abstract: Providing an adequate level of Quality-of-Experience (QoE) for multimedia applications in Mobile Ad-hoc Networks (MANETs) is a challenging task due to its environmental characteristics, such as dynamic network topology, variable bit-rates of transmitting traffic, and fluctuating link conditions. In this paper, we propose a QoS-aware Radio Characteristics and Network Mobility (Q-RCNM) based routing protocol, and its multipath variant (i.e., Q-RCNMM). Our protocols ensure adequate QoE to the end users while receiving the multimedia traffic. Q-RCNM uses link-bandwidth, link-delay, and link-transmission efficiency ratio as QoS metrics along with the node mobility during its QoS-aware route discovery phase. We propose novel techniques for accurately estimating the aforementioned QoS metrics. Additionally, we design a joint analytical model that simultaneously considers the dynamic values of the aforementioned metrics to generate a single link-QoS value. Simulation results in terms of Peak Signal-to-Noise Ratio (PSNR), delay, route throughput, transmission efficiency, and route lifetime, shows the efficiency of our proposal when compared with similar state-of-the-art techniques.
    Keywords: Link stability; Emulation; Bi-directional link loss factor; Video streaming; QoS-aware routing; Quality of Experience; Cross–layer communication.

  • Type-2 Fuzzy Logic based Energy-Efficient Transceiver Resource Schedule in Multi-radio WSNs   Order a copy of this article
    by Wei Peng, Dongyan Chen, Wenhui Sun 
    Abstract: Inspired by the type-2 fuzzy logic (T2FL), the energy-efficient radio resource schedule mechanism is proposed to deal with the multi-radio resources management problem in MRWSNs. Firstly, three important models, including channel quality estimation model, radio energy dissipation model and residual energy model, are established and analyzed. Then using the three important factors as the input variables, the selection probability of each transceiver as output variable, the T2FL based energy-efficient radio resource schedule scheme is designed. Moreover, both experimental and simulation results indicate that the proposed schedule mechanism can effectively improve the network performance, such as throughput, energy efficiency, the success rate of data transmission etc.
    Keywords: multi radio resource; wireless sensor network; type-2 fuzzy; energy-efficient; transceiver schedule.

  • Data gathering maximization for wireless sensor networks with a mobile sink   Order a copy of this article
    by Zongyuan Han, Tianyun Shi, Xiaojun Lv, Xinchun Jia, Zhongying Wang, Dong Zhou 
    Abstract: Recent studies have demonstrated that the significant benefit can be achieved by using mobile sinks for data gathering in wireless sensor networks (WSNs). However, most of them employed a typical scheme that the mobile collector pauses at the anchor points on its moving tour for a period time to collect the data from nearby sensors. In this paper, the data gathering process is divided into two stages named parking communication (PC) and moving communication (MC). We focus on maximizing the total amount of data gathering by the mobile sink, and formulate the problem as two different optimization models under several constraints for these two different communication stages. Accordingly, dual decomposition and simplex methods are dexterously exploited to derive the optimal communication time and flow rates allocation schemes. Computational results demonstrate the efficiency of the proposed algorithms.
    Keywords: Wireless sensor networks; Mobile data gathering; dual decomposition; nonlinear programming.

  • A Multi-channel Distributed Routing Scheme for Smart Grid Real-time Critical Event Monitoring Applications in the Perspective of Industry 4.0   Order a copy of this article
    by Muhammad Faheem, Rizwan Aslam But, Basit Raza, Md Asri Bin Ngadi, Cagri Gungor 
    Abstract: Recently, the 4th industrial revolution known as Industry 4.0 has paved way for a systematical deployment of the modernized power grid to fulfill the continuously growing energy demand of the 21st century. This industrial revolution in the power sector is known as the smart grid industry (SGI) 4.0. In SGI 4.0, the industrial wireless sensor network (IWSN) and the internet of things (IoT) are envisioned as key promising communication technologies for monitoring various SG applications. In addition, the ubiquitous computing using these communication technologies connects various smart grid devices to carry out monitoring and control logic intelligently from any remote location, worldwide. However, the highly dynamic nature of the SG environments brings several unique challenges to their reliable communication in the smart grid. As a result, the quality of service (QoS) communication is hampering for cognitive radio sensor networks (CRSNs)-based SG applications. Thus, a sophisticated, reliable and QoS-aware multi-hop communications network architecture enabling a real-time exchange of data for various CRSNs-based applications is essential in the SGI 4.0. Hence, this paper proposes a novel channel-aware distributed routing protocol named CARP for CRSNs-based SG applications. In CARP, the proposed cooperative channel assignment mechanism significantly improves the detection reliability and mitigates the noise and congested spectrum bands resulting in reliable and high capacity links for CRSNs-based SG applications. Moreover, to support higher capacity data requirements and to maximize the spectrum utilization, the proposed multi-hop routing mechanism selects a secondary user relay node rich in spectrum information with longer ideal probability at low interference in the network. The extensive simulation results conducted through EstiNet9.0 reveal that the proposed scheme achieves its defined goals compared to existing routing schemes designed for CRSNs-based applications.
    Keywords: Industry 4.0; Smart grid; Cognitive radio; Internet of thing; Wireless sensor networks.

  • Embedded Systems Codesign under Artificial Intelligence perspective: a review   Order a copy of this article
    by Fateh Boutekkouk 
    Abstract: Intelligent Embedded Systems (IES) and their distributed versions, represent a novel and promising generation of embedded systems. IES have the capacity of reasoning about their external environments and adapt their behavior accordingly. Such systems are situated in the intersection of two different branches that are the embedded computing and the intelligent computing. On the other hand, intelligent embedded software (IESo) is becoming a large part of the engineering cost of intelligent embedded systems. IESo can include some Artificial Intelligence-based systems such as expert systems, neural networks and other sophisticated Artificial Intelligence (AI) models to guarantee some important characteristics such as self-learning, self-optimizing and self-adaptation. Despite, the wide spread of such systems, some design challenging issues are arising. Designing a resource constrained software and at the same time intelligent is not a trivial task especially in a real time context. To deal with this dilemma, embedded systems researchers have profited from the progress in Semiconductor technology to develop specific hardware to support well AI models and render the integration of AI with the embedded world a reality.
    Keywords: embedded systems; Codesign; Artificial Intelligence; Intelligent Embedded Systems.

  • Enhancing the Dependability of Wireless Sensor Networks under Flooding Attack: A Machine Learning Perspective   Order a copy of this article
    by Jasminder Kaur Sandhu, Anil Kumar Verma, Prashant Singh Rana 
    Abstract: Wireless Sensor Networks (WSNs) are gaining paramount importance due to its application in real-time monitoring of geographical regions. Its deployment paradigm encompasses myriad of applications in terrestrial, underground and underwater WSNs. Nowadays the paradigm shift is taking place from mobile computing to Internet of Things. Bridging the two technologies result in the development of new applications with security as an essential feature. The discussion of applications without incorporating dependability and security features would be incompetent in a hostile environment. Extensive features such as traffic monitoring, proper resource utilization, security must be added to networks to assure quality transmission of data and enhance dependability. Security deals with detection and mitigation of various attacks. In flooding attack, an attacker repeatedly sends packets at higher rates, thereby causing packet drop and exhaustion of the link capacity. Thus, any further legitimate communication is ignored. To protect the network against the flooding attack, an Intrusion Detection System based on novel randomized and normalized deployment approach is proposed. We have found that Machine Learning models play a significant role in the prediction of Data Flow in WSNs. Network simulator is used to generate the dataset and Machine Learning techniques are used to enhance the dependability against flooding attack.
    Keywords: Wireless Sensor Networks; Dependability; Machine Learning; Data Flow; Flooding.

  • H-LPS: A Hybrid Approach for Users Location Privacy in Location Based Services   Order a copy of this article
    by Sonia Sabir, Inayat Ali, Eraj Khan 
    Abstract: Applications providing Location-Based Services (LBS) have gained much attention and importance with the notion of the Internet of Things (IoT). Users are utilizing LBS by providing their location information to third-party service providers. However, location data is very sensitive that can reveal users private life to adversaries. The passive and pervasive data collection in IoT upsurges serious issues of location privacy. Privacy-preserving location-based services is a hot research topic. Many anonymization and obfuscation techniques have proposed to overcome location privacy issue. In this paper, we have proposed a Hybrid Location Privacy Scheme (H-LPS), a hybrid scheme mainly based on obfuscation and collaboration for protecting users location privacy while using location-based services. Obfuscation naturally degrades the quality of service, but provides more privacy as compared to anonymization. Our proposed scheme, H-LPS, provides a very high level privacy yet providing a good accuracy for most of the users. Privacy level and service accuracy of H-LPS is compared with state of the art location privacy schemes and it is showed that H-LPS could be a candidate solution for preserving users location privacy in location based services.rn
    Keywords: Location privacy; Location Based Services; Obfuscation; Anonymization; Mobile location privacy.

  • Secure and remote firmware update of cellular IoT micro devices with limited resources   Order a copy of this article
    by Ahmet Cezayirli 
    Abstract: Typically, cellular IoT (Internet of Things) devices are spread over very large areas, usually countrywide or even worldwide. This makes the firmware update operation a troublesome and costly task, and it is usually avoided as long as possible. However, due to some bugs detected in the core software and/or some significant performance enhancements developed after the release of the device, the need for a firmware update becomes inevitable. We propose a new methodology in order to fulfil the firmware update remotely in an easy and secure way for especially the devices with quite limited resources, such as very small RAM and low processing power. We utilize MMS (Multimedia Messaging Service) functions, and send the firmware to the remote cellular IoT devices as encrypted attachment. The preparation steps of the attachment are explained in detail, a handshaking mechanism is established and all are tested on a particular hardware. Some important remarks are also provided, so that major practical aspects of the methodology would be readily available in implementing it on hardware/software architectures of new IoT devices.
    Keywords: Firmware update; cellular IoT; remote device; MMS attachment; code encryption.

  • Using ubiquitous data to improve smartwatches context awareness: A case study applied to develop wearable products   Order a copy of this article
    by Qing-Xing Qu, Yuankun Song 
    Abstract: Most recently, a large amount of data is being generated by various applications on smart devices, which could contain abundant information related to the users daily lives. This study aims to investigate whether the use of ubiquitous data could effectively improve smartwatches context awareness. A prototype of a context-aware system consisting of an Android application and a web application was developed, and an experiment in which 20 participants were recruited to complete several tasks with a smartwatch was conducted. The results showed that the smartwatch with the prototype application successfully decreased the effort cost (operations), task completion time, and error rate by making use of ubiquitous data to capture users real-time contexts and automatically execute corresponding operations. Moreover, users with a proposed context-aware system could have better user experience and more positive affective responses than the non context-aware system. Furthermore, findings in this study could give a better understanding and suggestions to designers when they intend to design a new smartwatch or improve an existing application on a smartwatch with the use of ubiquitous data.
    Keywords: Ubiquitous data; Context awareness; Smartwatch; Location-based service; Context-aware recommendation system; Ubiquitous computing.

  • Incentive Mechanism based Influential Maximization Scheme for Social Cloud Service Networks   Order a copy of this article
    by Sungwook Kim 
    Abstract: An effective interaction between the Social Network Services (SNS) and Cloud Computing (CC) enables the connection of people to the ubiquitous computing universe. The integration of SNS and CC is a technological revolution that presents the future of connectivity and reachability. This paper explores the novel paradigm for future Internet of Things (IoT). Although there have been some studies in social-driven IoT, they merely consider the CC technique to improve service qualities and influences. In this study, we develop a novel social cloud control scheme based on the Incentive Mechanism (IM) approach. To maximize the total SNS system performance, SNSs have been adaptively executed in the CC system while taking into account the social welfare. In addition, we protect each users privacy according to the Differential Privacy (DP) method. Therefore, our study can capture the properties of SNS and CC, and provides an effective solution for the social cloud system while ensuring privacy. Finally, we have conducted extensive simulations. The experimental results demonstrate the efficiency and effectiveness of the proposed scheme for the real world social cloud services. The main contribution of our work lies in the fact that we shed some new light on the relationship among SNS, CC and privacy for the future social cloud system. To the best of our knowledge, there is few previous work about this issue.
    Keywords: Social network services; Social cloud computing; Influential maximization; Incentive mechanism; Differential privacy.

  • Base Station Assisted Relay Selection in Device-to-Device Communications   Order a copy of this article
    by Ushik Shrestha Khwakhali, Prapun Suksompong, Steven Gordon 
    Abstract: The performance of cooperative cellular networks can be enhanced by using social information of users in the network. This paper presents a social-aware midpoint relay selection scheme that increases average throughput of D2D communication between users in the network leveraging social trust among nodes while selecting a relay node. The selection of a relay node is such that it has strong social link with the source and also located near to the midpoint of the distance between the source and the destination. Calculation of average throughput via simulation shows that our proposed scheme outperforms existing hybrid relay selection scheme by Pan and Wang by upto 14%. In addition, our proposed introduction of probe limit and wise selection of social threshold value can further enhance the throughput when social trust among nodes are high.
    Keywords: Cooperative networks; device-to-device (D2D) communications; social networks; social-aware relay selection; data rate; throughput.

  • Cost Efficient Hybrid Techniques for DSM in Smart Homes   Order a copy of this article
    by Rasool Bukhsh, Nadeem Javaid, Majid Iqbal Khan, Zahoor Ali Khan, Imran Usman 
    Abstract: In smart grid, the minimum cost for power consumption is attained by scheduling the appliances load. Shifting the appliances load from on-peak to off-peak time reduces the cost in users bill without compromising the load demand. In this paper, four scheduling algorithms are proposed by hybridizing Elephant Herding Optimization (EHO) with genetic, firefly, bacterial foraging and binary particle swarm optimization algorithms. Extensive simulations are performed to schedule the home appliances using proposed algorithms with three pricing tariffs: day ahead real time pricing, inclined block rates and critical peak pricing. The cost efficiency of optimized power consumption is analyzed. Results show that more cost is reduced with proposed hybrid algorithms as compared to the unscheduled and state-of-the-art algorithms.
    Keywords: Smart Meter; Smart Home; Operation Time Interval; Cost Efficiency; Appliances Schedule.

  • Prefetching and Caching Schemes for IoT Data in Hierarchical Edge Computing Architecture   Order a copy of this article
    by Tzu-Jung Chen, Jang Ping Sheu, Yung Ching Kuo 
    Abstract: With the growing number of the Internet of Things (IoTs) devices and mobile devices, the data traffic produced by these devices causes high network load, and these devices endure long access latencies to communicate with the cloud. The emergence of Edge Computing, caching and prefetching at the edge of the networks are promising solutions to these problems. Therefore, we propose caching and prefetching schemes for the Internet of Things data based on a four-tier hierarchical Edge Computing architecture, and our goal is to reduce data access latency. In our architecture, caches are deployed at 1st- and 2nd-tier edge nodes and the caching scheme is designed especially for the IoTs data. We analyze the relations of all users access requests and prefetch popular data among all users to the cache based on the predictions of user preferences. The experimental results show that the proposed schemes can effectively reduce user access latencies. Comparing with the average latencies under Cloud Computing architecture, the rate of improvement is up to 95%.
    Keywords: cache; edge computing; association rule mining; Internet of Things; prefetching.

  • A Note on Cloud Computing Security   Order a copy of this article
    by Deepak Garg, Jagpreet Sidhu 
    Abstract: Cloud computing has become an emerging technology which has huge impact. Existing security algorithms cannot meet the needs of cloud computing users as security issues have become increasingly prominent, becoming an important factor restricting the development of cloud computing. Reports reveals that organizations have experienced various attacks in past year. Research community has immensely focused on developing and optimizing security techniques to overcome this hurdle in cloud. Due to huge literature it becomes difficult to comprehend overall structure and advancements. This domain needs an analytic approach to completely understand the problem domain that is why this article represents same in specific context of security. Further a notion on security issues in cloud computing with respect to vulnerabilities, threats and attacks is discussed. Paper also proposed two research evaluation parameters that are effective citation and effective impact factor for better appreciation. Article also analyses patterns, trends and other factors for directing research activities. Finally, a global research trends on security domain are evaluated and analysed.
    Keywords: Cloud Computing; Security; Survey; Effective Citation (EC); Effective Impact Factor (EIF); Vulnerabilities; Threats; Attacks.

  • Activity Recognition Approach based on Spatial-Temporal constraints for Aged-care in Smart Home   Order a copy of this article
    by Haibao Chen, Shenghui Zhao, Cuijuan Shang, Guilin Chen, Chih-Yung Chang 
    Abstract: Activity recognition plays an important role in smart homes for aged-care. In this paper, we formulate the problem of activity recognition and propose a new method based on spatial-temporal constraints to carry out activity recognition, which consists of five phases: Initialization, Segmentation, Sensor Data Representation, Activity Exploration as well as Activity Identification. Besides, we analyze the time complexity and space complexity of our approach in theory.To evaluate our approach, we carried out experiments on real dataset from Wireless & Mobile Network Laboratory, Tamkang University. The experimental results demonstrate an improvement of 5.6% in the accuracy on average of recognized activities in comparison to the method of support vector machine (SVM).
    Keywords: Activity recognition; smart home; wireless sensor network;Aged-care.

  • Amazon cloud computing platform EC2 and VANET simulations   Order a copy of this article
    by Muhammad Azhar Iqbal, Muhammad Aleem, Muhammad Ibrahim, Saleem Anwar, Muhammad Arshad Islam 
    Abstract: Network simulations are resource and time intensive tasks due to the involvement of a number of factors attributable to scalability with respect to computation time, cost, and energy. Academic clouds are employed for large-scale network simulations, which require extensive capacity and intelligent resource management. This paper explores the performance efficiency of cloud solution to facilitate network researchers by proposing the utilisation of network simulator configured virtual machines. The prototype framework is executed using Amazon elastic computing cloud (EC2) Windows' instances configured with OPNET simulator. Simulation results show three significant benefits i.e., i) for scalable network simulations, consumption of considerably fewer resources in terms of simulation elapsed time, hardware resources and usage costs; ii) reduction of carbon emission leading towards sustainable IT; iii) promotion of network research by making complicated issues like simulation scalability and setup (installation or configuration) of network simulators to facilitate researchers and students.
    Keywords: academic clouds; VANET simulations; Amazon EC2; large-scale simulations.
    DOI: 10.1504/IJAHUC.2017.10006703
     
  • On the performance analysis of wireless communication systems over α - μ/α - μ composite fading channels   Order a copy of this article
    by Osamah S. Badarneh, Fares S. Almehmadi, Taimour Aldalgamouni 
    Abstract: The α - μ/α - μ fading channel model is the result of the product of two independent and non-identically distributed (i.n.i.d.) α - μ variates. As such, in order to study the performance of wireless communication systems in such fading model, the envelopes of the probability density function (pdf) and cumulative distribution function (cdf) must be obtained. To this end, simple and the general closed-form expressions for the pdf and cdf of the product of two independent and non-identically distributed (i.n.i.d.) α - μ variates are obtained. Then based on these expressions, we derive closed-form expressions for the outage probability, the average symbol error probability (SEP) and the nth moment of the signal-to-noise ratio (SNR), and the ergodic channel capacity. The derived expressions are then used to analyse the performance of a wireless communication system. Analytical results are sustained through Monte-Carlo simulations, and a perfect match is reported over a wide range of SNR values and for several values of fading parameters.
    Keywords: composite fading channels; multi-path fading; shadowing; α - μ distribution.
    DOI: 10.1504/IJAHUC.2017.10006698
     
  • TLS: traffic load based scheduling protocol for wireless sensor networks   Order a copy of this article
    by Prasan Kumar Sahoo, Hiren Kumar Thakkar 
    Abstract: In wireless sensor networks (WSNs), nodes are usually deployed in the monitoring region randomly and densely and are supposed to monitor the region for a longer duration. These sensors are normally powered by a battery and therefore it is essential to regulate the power utilisation of the nodes efficiently. Although most of the current protocols reduce the power utilisation by regulating the sleep and wake-up schedules, they fail to make an adaptive sleep or wake up schedule for the nodes based on their traffic load. This paper proposes a traffic load based adaptive node scheduling protocol to determine the active and sleep schedules of the nodes. The entire network is partitioned into a set of virtual zones and a routing path selection algorithm is proposed considering the residual power of the next hop nodes. Simulation results show that the energy consumption and packet overhead of our protocol are considerably less as compared to similar quorum-based medium access control (MAC) protocols.
    Keywords: WSNs; wireless sensor networks; MAC protocol; scheduling.
    DOI: 10.1504/IJAHUC.2019.10019921
     
  • EFF-FAS: enhanced fruit fly optimisation based search and tracking by flying ad hoc swarm   Order a copy of this article
    by Vishal Sharma, Roberto Sabatini, Subramanian Ramasamy, Kathiravan Srinivasan, Rajesh Kumar 
    Abstract: Flying ad hoc swarms are networks formed by autonomously operated aerial nodes. These nodes can be simple high altitude platforms or specifically configured unmanned aircraft (UA). Such networks are autonomous, temporary and mission dependent. One of the major applications of this ad hoc swarm formations is the efficient search and tracking of an area without any redundancy and overlapping. Non-redundant cell tracking is a computationally expensive task, which requires optimisation strategies to be adopted during a search process. Incorporating fruit fly optimisation (FOA) algorithm to a strategic search and track operation simplifies the complexity of the overall system. In this paper, FOA is extended in terms of its applicability by modifying the procedures of the algorithm to allow its applicability to an aerial swarm for non-redundant search over a predefined area with lower complexity. Network simulations demonstrate the effectiveness of the proposed approach towards search and track operations.
    Keywords: ad hoc swarms; unmanned aircraft; searching; tracking; data acquisition; FOA; fruit fly optimisation.
    DOI: 10.1504/IJAHUC.2019.10019922
     
  • A new scheme for RPL to handle mobility in wireless sensor networks   Order a copy of this article
    by Fatma Gara, Leila Ben Saad, Rahma Ben Ayed, Bernard Tourancheau 
    Abstract: Mobile wireless sensor networks (WSNs) are characterised by dynamic changes in the network topology leading to route breaks and disconnections. The IPv6 routing protocol for low power and lossy networks (RPL), which has become a standard, uses the Trickle timer algorithm to handle changes in the network topology. However, neither RPL nor Trickle timer are well adapted to mobility. This paper investigates the problem of supporting mobility when using RPL. It enhances RPL to fit with sensors' mobility by studying two cases. Firstly, it proposes to modify RPL in order to fit with a dynamic and hybrid topology in the context of medical applications. Secondly, it investigates a more general case and introduces a new adaptive timer for RPL. The proposed approach is validated through extensive simulations and compared with existing protocols in the literature. Results show that our proposal significantly reduces disconnections and increases packet delivery ratio while maintaining low overhead.
    Keywords: WSNs; wireless sensor networks; RPL protocol; node mobility; trickle timer.
    DOI: 10.1504/IJAHUC.2017.10008392
     
  • An incentive mechanism with privacy protection and quality evaluation in mobile crowd computing   Order a copy of this article
    by Hao Long, Shukui Zhang, Li Zhang, Jin Wang 
    Abstract: In order to achieve good service quality for mobile crowd computing (MCC), incentive mechanism need to attract more users to participate in the task while avoiding leakage of privacy. We proposed an incentive mechanism with privacy protection and quality evaluation (IMPPQE). Combining the advantages of offline and online incentive mechanisms, we design improved two-stage auction to select the winners, while protecting participants 'privacy. Finally, the sensing reports are evaluated by quantitative calculation to ensure the objectivity of evaluation. Extensive simulations show that our proposed method can improve the efficiency and utility of MCC and obtain higher satisfaction rate of data quality.
    Keywords: mobile crowd computing; privacy protection; quality evaluation; incentive mechanism; two-stage auction; offline; online; incentive mechanisms; service quality; sensing reports; crowdsourcers.
    DOI: 10.1504/IJAHUC.2019.10019942
     

Special Issue on: ICSSE 2018 Innovative Services and Emerging Technologies of Smart Cities

  • Sensor-Based Detection of Abnormal Events for Elderly People Using Deep Belief Networks   Order a copy of this article
    by Yo-Ping Huang, Haobijam Basanta, Hung-Chou Kuo, Hsin-Ta Chiao 
    Abstract: Various technological developments in home-care systems have allowed elderly people to live independently without compromising their safety. A pilot study employing deep learning algorithm was conducted to study the daily routines of elderly people. We monitored unsupervised, diverse daily activities of elderly people such as household chores, sleeping, cooking, cleaning, using the bathroom, watching television, and meditating. The activities were monitored to track humanenvironment interactions by using motion sensors, actuators, and surveillance systems that were mounted inside living rooms, bedrooms, and kitchens and on bathroom doorways to detect safety hazards in the environment for elderly people. Such collected data were used in deep belief networks to ascertain and identify activities that are related to various health and self-care problems. Simulation results show that the proposed system outperforms the support vector machines in terms of F1 score and accuracy in identifying daily activities.
    Keywords: sensors; deep belief network; daily activities; abnormal events.

  • Random Forest, Gradient Boosted Machines and Deep Neural Network for Stock Price Forecasting: A Comparative Analysis on South Korean Companies   Order a copy of this article
    by Sanjiban Sekhar Roy, Rohan Chopra, Kun Chang Lee, Concetto Spampinato, Behnam Mohammadi-ivatloo 
    Abstract: Predicting the final closing price of a stock is a challenging task and even modest improvements in predictive outcome can be very profitable. Many computer-aided techniques based on either machine learning or statistical models have been adopted to estimate price changes in the stock market. One of the major challenges with traditional machine learning models is the feature extraction process. Indeed, extracting relevant features from data and identifying hidden nonlinear relationships without relying on econometric assumptions and human expertise is extremely complex and makes deep learning particularly attractive. In this paper, we propose a deep neural network-based approach to predict if the stock price will increase by 25% for the following year, same quarter or not. We also compare our deep learning method against shallow approaches, random forest and gradient boosted machines. To test the proposed methods, KIS-VALUE database consisting of the Korea Composite Stock Price Index (KOSPI) of companies for the period 2007 to 2015 was considered. All the methods yielded satisfactory performance, namely, deep neural network achieved an AUC of 0.806, random forest, 0.850 and gradient boosted machine, 0.853. Interestingly, deep learning achieved the lowest performance, which although marginal can be explained by the lack of enough training data.
    Keywords: Deep neural network; random forest; gradient boosted machine; KOSPI; financial markets.

  • Task Allocation for Crowd Sensing Based on Submodular Optimization   Order a copy of this article
    by Zhiyong Yu, Weiping Zhu, Longkun Guo, Wenzhong Guo, Zhiwen Yu 
    Abstract: Crowd sensing is becoming a hot topic because of its advantages in the field of smart city. In crowd sensing, task allocation is a primary issue which determines the data quality and the cost of sensing tasks. In this paper, on the basis of the sweep covering theory, a novel coverage metric called t-sweep k-coverage is defined, and two symmetric problems are formulated: Minimize user set under fixed coverage rate constraint (MinP) (MinP) and Maximize coverage rate under user set constraint (MaxC). Then based on their submodular property, two task allocation methods are proposed, namely double greedy (dGreedy) and submodular optimization (SMO). The two methods are compared with the baseline method linear programming (LP) in experiments. The results show that, regardless of the size of the problems, both two methods can obtain the appropriate participant set, and overcoming the shortcomings of linear programming.
    Keywords: crowd sensing; task allocation; participant selection; submodular optimization.