International Journal of Ad Hoc and Ubiquitous Computing (26 papers in press)
Room measurement tool combining ultrasonic and inertial sensors in smartphones
by Yukitoshi Kashimoto, Yutaka Arakawa, Keiichi Yasumoto
Abstract: Obtaining accurate floor plans of buildings is critical for optimising indoor geographic information system (GIS) applications. In this paper, we present a room measurement tool that utilises a smartphone equipped with an ultrasonic sensor. To take measurements, users complete a lap along thewalls of all of the rooms. Then the tool accurately estimates the shape and size of them by tracking the walking paths of users and measuring the distance from the path to the walls with ultrasonic sensors. To track walking paths, we utilise inertial sensors embedded in the smartphone to estimate walking steps and turns, and the ultrasonic sensors to estimate the stride length when walking toward the wall. To account for such adjacent objects as bookshelves that decrease the accuracy of room size estimation, we used a mixed Gaussian filter. Our experimental results show that our tool considerably improved the estimation accuracy of the room shape and size.
Keywords: Room measurement tool; pedestrian dead reckoning; inertial sensor; smartphone;
Nash Bargaining and Policy Impact in Emerging ISP-CP Relationships
by Hamid Garmani, Driss AIT OMAR, Mohamed El Amrani, Mohamed Baslam, Mostafa Jourhmane
Abstract: "Net neutrality" is the subject of raging debates for several years now, with various viewpoints put forth by stakeholders (Internet Service Providers, Content Providers, and end-users) seeking to influence how the Internet is regulated. With the network neutrality debate, the revenue sharing between Internet service providers (ISPs) and content providers (CPs) has been received attentions. In this paper, we study the revenue sharing of them through economic modeling, illustrating how monetary flows among providers are determined. There are generally two ways for CPs to get revenue: (i) charge users for the contents they view or download; (ii) get revenue from advertisers. On the other hand, Internet service providers (ISPs) are investing in network infrastructure to provide better quality of service (QoS). We investigate the mutual interaction of the service provider and content provider in two cases: (i) competitive case, where the ISP charge CPs for delivering content to end-users; and (ii) cooperative case, where the two providers (CP, ISP) jointly optimize their strategies, with the purpose of maximizing their aggregate profits. We formulate the interactions between the ISPs and between the CPs as a non-cooperative game in which the ISP and CP determine how much they will charge the end-users. In turn, the subscribers demand for the service of a provider depends not only on their strategies, but also upon those proposed by all of its competitors. We utilize bargaining games to analyze how the side payment between CP and ISP is determined. The sufficient and necessary condition for the existence and uniqueness of Nash equilibrium are derived. Based on the best response dynamics method, we propose a distributed iterative algorithm, starting from any initial strategies vector and converge to that Nash equilibrium. Finally, through extensive simulations, it has been verified that the cooperation is the best choice for three entities, i.e., the service provider, content provider and end-users.
Keywords: Network Neutrality; Nash Bargaining; ISP; CP; Nash equilibrium; game theory.
Popularity Prediction Caching Based on Logistic Regression in Vehicular Content Centric Networks
by Kai Yao, Zhaoyang Li, Lin Yao, Kuijun Lang
Abstract: To improve the network performance caused by mobility and sporadic connectivity in the vehicular network, Vehicular Content Centric Network(VCCN) is proposed by applying CCN into the vehicular network. The open in-network caching of CCN makes nodes cache contents cooperatively to facilitate information access. Tornimprove the network performance such as access delay and hit ratio, Road Side Units (RSUs) should try to cache more popular contents and provide better service for mobile users. This paper aims to propose a novel cache replacement policy - Popularity Prediction Content Caching (PPCC) for VCCN. In PPCC, we incorporate the future popularity of contents into our decision making. By learning the popularity of contents, we propose a cache replacement method based on logistic regression for RSUs in order to store those frequently access contents. The input data are related to the inherent characters of the received interests and the output is the predicted content popularity which guarantees that only popular contents are cached in the network infrastructures (i.e.RSUs). Simulation evaluations demonstrate that our scheme is very eective with higherrncache hit, lower access latency and higher caching eciency compared to other state-of-the-art schemes.
Keywords: VCCN; Cache Policy; Logistic Regression; Popularity Prediction.
An Enhanced Anonymous Authentication Protocol for Wireless Sensor Networks
by Jiping Li, Tong Yu, Yunyun Wu, Xia Kong, Shouyin Liu
Abstract: As a main component of IoTs, Wireless sensor networks (WSNs) are of greatrnimportance to data collection in varieties of sectors, such as environment monitoring, health monitoring of human body, farming, commercial manufacture, reconnaissance mission in military, and calamity alert, and so on. However, the nature of its wireless communication and resource constrain make it more likely to suer various kinds of attacks. As to this problem, many authentication s have protocols been designed recently to ensure secure communication in WSNs. Among the schemes, Singh et al.'s protocol shows great novelty. Unfortunately, we nd in our current research that Singh et al.'s protocol still has the vulnerabilities to stolen/lost smart card attacks, privileged-insiderrnattacks, the session key leakage attacks, and so on. To solve these problems, we propose an ecient anonymous authentication protocol by using hash function and bitwise XOR operations based on the security analysis of Singh et al.'s protocol. Secondly, we conduct detailed analysis to our protocol's security, and then security-feature comparisons with related protocols. In addition, we give formalized security proof of our by using Burrows-Abadi-Needham (BAN) logic. Finally, we give performance comparisons in regard to computing costs and communicating costs, respectively. Comparative summaries demonstrate that our protocol is much better in security with little overheads increase,rnand more appropriate for WSNs with limited resources.
Keywords: Authentication; Anonymity; Internet of Things; Key Agreement; BAN Logic.
Fine-Grained Emotion Recognition: Fusion of Physiological Signals and Facial Expressions on Spontaneous Emotion Corpus
by Feri Setiawan, Aria Ghora Prabono, Sunder Ali Khowaja, Wangsoo Kim, Kyoungsoo Park, Bernardo Nugroho Yahya, Seok-Lyong Lee, Jin Pyo Hong
Abstract: The recognition of fine-grained emotions (i.e. happiness, sad, etc.) has shown its importance in a real-world implementation. The emotion recognition using physiological signals is a challenging task due to the precision of the labelled data while using facial expressions is less appropriate for the real environment. This work proposes a framework for fusing physiological signals and facial expressions modalities to improve classification performance. The feature-level fusion (FLF) and decision-level fusion (DLF) techniques are explored in this work to recognize 7 fine-grained emotions. The performance of the proposed framework is evaluated using 34 subjects data. Our result shows that the fusion of the multiple modalities could improve the overall accuracy compared to the unimodal system by 11.66% and 13.63% for facial expression and physiological signals, respectively. Our work achieved a 73.23% accuracy for 7 emotions which is considerable accuracy for the spontaneous emotion corpus.
Keywords: Emotion recognition; Low sampling rate; Multimodal fusion; Spontaneous facial expression.
A selective forwarding technique for data dissemination in vehicular ad hoc networks based on traffic parameters
by Rangaballav Pradhan, Tanmay De
Abstract: In this work, a novel data dissemination technique is proposed based on the selective forwarding mechanism. Various network parameters such as node density,
inter-vehicular distance and time to leave are considered for choosing the appropriate relaying node out of a set of one hop neighbouring nodes of the sender. Veins, a simulation framework combining the power of Omnet++ and SUMO, is used to simulate and test the proposed approach. Simulation results are obtained by considering various performance metrics and the effectiveness of the method is justified by comparing with two existing methods namely Selective flooding and a Unidirectional Flooding. The analysis of these results showed that the proposed method has a higher Packet Delivery Ratio and coverage rate with a throughput surplus of 15% and 29% more than that of selective and unidirectional flooding respectively. It also has a minimum delay and a lower collision rate than the two flooding based approaches.
Keywords: VANETs; data dissemination; flooding; Selective forwarding; vehicular parameters; time to leave; vehicular density; Veins.
An Adaptive and Cooperative MAC Protocol in Vehicular Adhoc Network: Design and Performance Analysis
by Duc Ngoc Minh Dang, Quynh Ngo, Quan Le Trung, Long Le
Abstract: Vehicular Adhoc Network is the key technology to enable the Intelligent Transportation System. VANET should provide reliable broadcasting to support the safety-related application. It is also required to effectively transmit service-related data. With the rapid development of the Internet of Vehicles, Medium Access Control (MAC) protocols for VANET are expected to be more adaptive and scalable to the network size; so that the MAC protocol can operate effectively in supporting the massive number of connections. This paper proposes a multi-channel MAC protocol, namely AC-MAC, that enables multi-hop transmission of safety application data leveraging cooperation among vehicles. The proposed MAC protocol ensures the reliability of safety message transmission and the effective utilization of channel resources. Moreover, the MAC mechanism also has the ability to adapt to different network conditions.
Keywords: VANETs; IoTs; Multi-channel MAC; TDMA; CSMA; multi-hop; adaptive; cooperative.
A Channel Assignment Scheme for MIMO on Concentric-Hexagon-based Multi-Channel Wireless Networks
by Fang-Yie Leu, Heru Susanto, Kun-Lin Tsai, Chia-Yin Ko
Abstract: In a wireless network environment, multi-hop communication performed on a single channel may lead to hidden node and radio signal interference problems which are also the key reasons why network transmission efficiency is often not as expected. In fact, the hidden node problem is caused by radio signal interference, i.e., signal interference is the primary reason. Currently, numerous studies have used multi-channel schemes to solve the single channel interference problem. In general, Multi-channel can increase network capacity. However, it causes other problems, e.g., multi-channel hidden terminal/node problem and the issue about how to allocate channels to wireless nodes. Basically, a well-defined channel assignment can avoid radio interference and improve transmission performance. Therefore, in this study, we proposed a multiple channel assignment scheme, called Concentric-Hexagon-Oriented Multi-channel Assignment (CHOMA for short) which is suitable for use in a metropolitan-scale wireless network system with multi-input multi-output (MIMO) antenna, and the deployed eNBs are organized as concentric-hexagon (C-hexa for short). Available channels are grouped and then allocated to the C-hexas. We also arrange channels allocated to a C-hexa so as to reduce radio interference among its eNBs, consequentially improving the transmission capability and performance of a wireless network. Experimental results show that the CHOMA is really an interference-free scheme, no matter whether the target system is a network with SISO, SIMO, MISO or MIMO stations.
Keywords: wireless networks; eNB;signal/frequency interference; hidden terminal problem; multi-hidden terminal problem; channel allocation; MIMO.
Outage Probability Analysis for Relay based Cognitive Radio Network
by Perarasi Sambantham, Ganesan Nagarajan
Abstract: This paper is delineating with relay based subjective radio system (CRN) with different optional source hubs and numerous auxiliary goal nodes. The quality of service is mainly ability can be enhanced with proper resource allocation. The link value is preserved by keeping SNR above a threshold called minimum protection ratio. Uplink resource allocation based on hybrid cooperative CR network (HCCRN) is considered in which licensed radio and cognitive radio are combined. Cognitive relay is utilized for range extension to attain greater capacity. CRN stands for Cognitive Radio Network. Medium access layer network coding (MALNC) is connected with two sorts of full duplex transfer to be specific amplify and forward (AF), decode and forward (DF) for the fruitful transmission of data. Identification of data at the collector is anticipated by multiple range groups. Utilization of MALNC lessens to the quantity of vacancies required for correspondence. Log typical conveyances are utilized for divert parameter investigation within the sight of shadowing of sign because of huge hindrances in versatile radio correspondence. Blackout likelihood is portrayed for blurring channel. A variety of the estimation of mean, fluctuation and transmission rate is done to accomplish an effective framework.
Keywords: Cognitive radio network; Relay system; Amplify and forward; Decode and forward; MALNC; Log Normal Distribution.
Partition Tolerant Collaborative Gateway Architecture for Interoperable ITS Applications
by Manipriya Sankaranarayanan, Mala C, Samson Mathew
Abstract: One of the aims of Intelligent Transportation Systems (ITS) is to provide reliable and uninterrupted traffic information to travellers to improve traffic flow, safety and management. This objective can be accomplished by ensuring interoperability between independent ITS services or applications. This paper proposes a Collaborative Gateway Architecture (CGA) that addresses technological and service related issues in delivering traffic data for interoperable ITS. To ensure seamless and trustworthy operation of ITS services in CGA, this paper further proposes a Partition Tolerant Support System (PTS2) that provides the facility to reuse similar data or information originating from different sources, types and formats. The effectiveness of ITS services in CGA environment is analysed and tested through simulation of traffic Congestion Rate (CongRa) estimation processes functioning through data acquired from co-operative vehicles and computer vision technologies respectively. From the simulated results, it is seen that the CongRa estimation application, which operates under the proposed interoperable architecture along with its support framework, ensures that the application is partition tolerant and function with higher accuracy, credibility, consistency and enhanced quality of information compared to that which operates as an independent application.
Keywords: Intelligent Transportation Systems; ITS Applications; Collaborative GatewayrnArchitecture; Partition Tolerant; Interoperability; Computer Vision; Co-operative vehicles; Traffic Congestion Rate Estimation.
Energy-efficient fault-tolerant scheduling in a Fog-based smart monitoring application
by Ahmad Sharif, Mohsen Nickray, Ali Shahidinejad
Abstract: Fog environment is a distributed system model that can utilise the processing abilities of Fog Devices (FDs) and is growing as an essential platform for IoT. Network failures become inevitable, with the growing scale of IoT. To achieve high performance, should attend to communication reliability. Fault tolerance becomes a necessary matter to enhance the reliability of the Fog. Notably, fault tolerance studies have been performed only on the Cloud system. To counter this issue, we propose a novel fault-tolerant scheduling algorithm for hybrid modules in Fog. One of the main innovations of this approach is a classification method for different modules by the side of computing the energy consumption of all Fog nodes and finding minimal Fog nodes energy consumption. Proposing ECRBC model, which composes the profits of Extended Checkpoint-Restart and Primary Back up model with Classification, is leading to superior energy-efficiency and reliability. We evaluate the performance of the proposed method by comparing it with four methods in terms of delay, energy consumption, execution cost, network usage, and total executed modules. Analysis and simulation results show, our method augments high reliability and efficiency to the system.
Keywords: Fog Computing; Fault-tolerant scheduling; Checkpointing; Energy efficiency.
Approximation Algorithms for Profit Maximization in Multicast D2D Networks
by Jagadeesha R. Bhat, Jang-Ping Sheu, Wing-Kai Hon, Cian You Yang
Abstract: As the demand for mobile data services increases, telecom companies need to develop wise strategies to retain existing customers. For instance, in a multicast scenario, satisfying individual users quality of service (QoS), data demand at varying rates, etc. are complicated tasks. Earlier works on device-to-device (D2D) multicast have majorly discussed the cases of throughput maximization without considering the individual users data request rates. In this paper, we propose two algorithms to maximize the telecom operators profit collected from the users in a two-hop D2D multicast network, when users have different channel qualities and data request rates while receiving multicast data through a single transmission session. First, we model our multicast scheme for the proposed scenario as a budgeted maximum coverage problem. Later, we propose two approximation algorithms that guarantee approximation ratios of 1-1/?e and 1-1/e, respectively, where e denotes the base of the natural logarithm. Numerical results show that the proposed algorithms perform better than the other candidate algorithms and nearly approximates the optimal solution.
Keywords: Mobile data; multicast; approximation algorithm; device-to-device.
An intrusion detection model using improved convolutional deep belief networks for wireless sensor networks
by Weimin Wen, Cuijuan Shang, Zaixiu Dong, Huan-Chao Keh, Diptendu Sinha Roy
Abstract: Intrusion detection is a critical issue in the wireless sensor networks (WSNs), especially for security application. In literature, many classification algorithms have been applied to address the intrusion detection problems. However, their efficiency and scalability still need to be improved. One challenge is that the prior samples cannot be timely obtained when applying the previous supervision classification algorithms, due to the indefinite features of attack behaviors. Another challenge is that the redundant nodes and data consume the limited energy of sensor nodes, reducing the network lifetime of the WSN. This paper proposes an Improved Convolutional Deep Belief Network-based Intrusion Detection Model (ICDBN_IDM). The model consists of a redundancy detection algorithm, an improved intruder detection algorithm based on convolutional deep belief network as well as a performance evaluation strategy. The redundancy detection can remove non-effective nodes connections and data, reduce the number of data transmissions and hence save the energy consumption of the whole network. The improved CDBN algorithm extracts features from normal and abnormal behavior samples by using unsupervised learning and overcomes the problem of self-learning and automatic detection of abnormal behaviors under the condition of unknown or less prior samples. The performance evaluation is an indispensability part of the ICDBN_IDM, which verifies the correctness, accuracy, and efficiency of the mentioned algorithms. Compared with the commonly used machine learning mechanisms, the ICDBN_IDM achieves high intrusion detection accuracy, reduces the ratio of false alarm while saving the energy consumption of sensor nodes. In comparison, the average intrusion detection ratio of the ICDBN_IDM is 96.82% for five types of attack in a WSN.
Keywords: Intrusion detection; improved convolutional deep belief network; redundancy detection; deeply compressed algorithm; wireless sensor network.
Botnet Detection Used Fast-Flux Technique, Based on Adaptive Dynamic Evolving Spiking Neural Network Algorithm
by Ammar Almomani, Ahmad Al-Nawasrah, Mohammad Alauthman, Mohammed Azmi Al-Betar, Farid Mezian
Abstract: A botnet refers to a group of machines. These machines are controlled distantly
by a speci?c attacker. It represents a threat facing the web and data security. Command and Control C&C service is deemed as the pillar of botnet communications at which the botmasters and bots send a report and orders to one another. It should be noted that botnets are usually categorized based on C&C protocols. Fast-Flux Service Network(FFSN) has been engaged by bot herders for cover malicious botnet activities. Its been engaged by bot herders for increasing the lifetime of malicious servers through changing the IP addresses of the domain name quickly. There are several methods for detecting FFSNs. However, these methods show a low level of detection accuracy. In the present research, the researchers aimed to propose a new system. This system is named Fast Flux Botnet catcher system (FFBCS). This system can detect FF-Domains in an online mode using an Adaptive dynamic evolving spiking neural network algorithm. Comparing with two other related approaches the proposed system shows a high level of detection accuracy,a low false positive and negative rates, respectively. It shows a high performance. The algorithms proposed adaptation increased the accuracy of the detection. For instance, this accuracy reached (98.76%) approximately.
Keywords: Dynamic evolving spiking neural network; Fast-flux techniques detection;Network security; Botnet.
Detection of Phishing Attacks using Probabilistic Neural Network with a Novel Training Algorithm for Reduced Gaussian Kernels and Optimal Smoothing Parameter Adaptation for Mobile Web Services
by Priya Saravanan, Selvakumar Subramanian
Abstract: The rapid escalation of smartphones and online transactions increases the rate of semantic attacks such as phishing that exploit the user credentials for fraudulent financial gains in online social networks. The existing detection methods suffer from low detection accuracy and high False Positive Rate (FPR) due to the lack of generalized algorithms for accurate prediction. The neural network classifiers have shown promising results for detecting such kinds of semantic attacks. Hence, this study focused on the use of Probabilistic Neural Network (PNN) for proposing an effective solution for detecting the phishing attacks. In contrast to conventional PNN, in this study, the perception of PNN is enhanced with a novel training process. A novel Fuzzy Dense K-Modes (FDKM) clustering algorithm is proposed to achieve the objectives. The number of Gaussian kernels used in the pattern layer is reduced by the cluster centers or K-Modes obtained from the FDKM clustering algorithm. In FDKM clustering, a novel dissimilarity measure is introduced to improve the intracluster similarity. Moreover, the performance of PNN is further enhanced by the proposed optimization procedure called Modified Harmony Search with Generation Regrouping (MHS_GR) which finds the optimal smoothing parameter for training the network. In MHS_GR, the diverse population is maintained by generating the initial seeds using the Generalized Opposition Based Learning (GOBL) method. Also, the problem of stagnation in which the searching of global optimum stagnates before finding a globally optimal solution is overcome by the proposed entropy-based generation regrouping strategy. The efficiency of the proposed approach was evaluated on two benchmark phishing datasets obtained from the University of California Irvine (UCI) machine learning repository and on our Phish_Net dataset collected from PhishTank and starting point directory. The experimental results reveal that the proposed PNN with MHS_GR technique (PNN_HS3) achieves higher detection accuracy with lesser FPR when compared to the existing phishing detection techniques. Specifically, PNN_HS3 obtained 98.53\%, 96.92\%, and 97.12\% of detection accuracy and 2.02\%, 3.39\%, and 3.12\% of FPR for UCI_1, UCI_2, and Phish_Net dataset respectively.
Keywords: Mobile web services; Phishing attacks; Online security; Gaussian kernels reduction; Probabilistic Neural Network; Personal privacy.
Mobility Modeling for Urban Traffic Surveillance by a Team of Unmanned Aerial Vehicles
by Farooq Ahmed, Haroon Mahmood, Yasir Niaz
Abstract: Use of Unmanned Aerial Vehicles (UAVs) for road traffic surveillance, within the context of Intelligent Transportation Systems and Smart Cities, is an exciting idea for improving surveillance quality, with several interesting usecases. To study its applicability in large urban environments, calibrated mobility models have a significant role to play as they help analyze several mobility related issues, before as well as after deployment. Although mobility models for general surveillance scenarios, using UAVs, have been studied earlier; a model optimized for urban traffic surveillance has been missing. This paper addresses this problem with the discussion of an energy-aware and scalable mobility model for a team of cooperative Unmanned Aerial Vehicles (UAVs), for monitoring road traffic in an urban area. It also accompanies an extensible framework for territory distribution, to optimize the number of UAVs required for maximizing coverage, without compromising operational performance. Since the problem of territory distribution in general is NP-hard, a Genetic Algorithm based strategy is recommended, using the idea of edge-disjoint paths. Simulation results show that proposed model performs considerably better in terms of area coverage when compared with other mobility models proposed in literature. Scalability of the model to realistic urban territories is also ascertained, using a published dataset simulating vehicular traffic for a mid-size urban city.
Keywords: Mobility modeling; Unmanned Aerial Vehicles; Flying Ad hoc Networks; Intelligent Transportation System.
A robust Guaranteed Time Slots allotment scheme for real-time and reliable communication in WBANs
by Gulshan Soni, Kandasamy Selvaradjou
Abstract: The ever increasing aging population and expenditure related to healthcare, consequently demand the requirement for a state-of-the-art healthcare system, which should be capable enough to handle the existing and near future challenges in health-care systems. Wireless Body Area Networks (WBANs) are the potential contender for this requirement. In the recent past, a substantial amount of research interest has been diverted towards the development of WBANs by the various research communities from academia and industries. The IEEE 802.15.4 standard is an appropriate communication protocol for the requirement of WBANs because of its low-power and low-cost features. In beacon-enabled mode, IEEE 802.15.4 standard supports real-time traffic through Guaranteed Time Slots (GTSs) feature. Nevertheless, it suffers from the reliability and timeliness guarantees. To address this issue, this work advocates a Robust Guaranteed time slots Allotment Scheme (RGAS) that consists two phases, viz. (i) determine the severity of sensor data and (ii) dynamic allocation of available GTS slots to the contending sensor nodes. A Fuzzy Inference System (FIS) is devised in the first phase to evaluate the merit of the sensor nodes which in turn decides the GTS slots to be demanded based on their severity level. On the other hand, the second phase ensures that the high severity sensor nodes always get GTS slots allocated with top most priority in order to enable them to transmit real-time data without any undue delay. Through simulation results we demonstrate that the proposed RGAS significantly outperforms the existing GTS mechanism specified in the IEEE 802.15.4 in terms of various performance metrics such as packets transmission, packet reception rate, packet loss rate, and effective utilization of Contention Free Period (CFP).
Keywords: Wireless Body Area Networks; Guaranteed Time Slot allocation; Contention Free Period; Fuzzy Inference System.
Enhancing Data Privacy through Decentralized Predictive Model with Blockchain-based Revenue
by Sandi Rahmadika, Kyung-Hyune Rhee
Abstract: Federated learning (FL) permits a vast number of connected to construct deep learning models while keeping their private training data on the device. Rather than uploading the training data and model to the server, FL only sends the local gradients gradually. Hence, FL preserves data privacy by design. FL leverages a decentralized approach where the training data is no longer concentrated. Similarly, blockchain uses the same approach by providing a digital ledger that can cover the flaws in the centralized system. Motivated by the merits of a decentralized approach, we construct a collaborative model of simultaneous distributed learning by employing multiple computing devices over shared memory with blockchain smart contracts as a secure incentive mechanism. The collaborative model preserves a value-driven of distributed learning in enhancing users' privacy. It is supported by blockchain with a secure decentralized incentive technique without having a single point of failure. Furthermore, potential vulnerabilities and plausible defenses are also outlined. The experimental results positively recommend that the collaborative model satisfies the design goals.
Keywords: Blockchain; Decentralized Revenue; Decentralized Training; Federated Learning; Predictive Model; User Privacy.
Provably secure authenticated content key distribution framework for IoT enabled enterprise digital rights management systems
by Dheerendra Mishra, Saurabh Rana
Abstract: The Internet of Things (IoT) is one of the fastest-growing technology, which is helping the enterprise industry.
Keywords: Multimedia; Enterprise digital rights management systems; Key agreement; Security; anonymity.
Special Issue on: Artificial Intelligence for Edge Computing in the Internet of Things
Application of Artificial Intelligence Technology in CNC System
by Chunhui Dong, Cheng Zhong
Abstract: Since the development of computer numerical control technology from hardware numerical control to software numerical control, computer numerical control technology is still in a period of continuous improvement of functions. Although some novel numerical control technologies have been proposed, on the whole, it has not yet broken through the traditional framework. And because of the reliability research process of CNC machine tools, it is difficult to collect reliability data, which makes the reliability distribution model not unique. Based on the above background, the purpose of this article is to study the application of artificial intelligence technology in numerical control systems. The main method is to use the ANN model to expand the small amount of reliability data collected, and then use the Since the development of computer numerical control technology from hardware numerical control to software numerical control, computer numerical control technology is still in a period of continuous improvement of functions. Although some novel numerical control technologies have been proposed, on the whole, it has not yet broken through the traditional framework. And because of the reliability research process of CNC machine tools, it is difficult to collect reliability data, which makes the reliability distribution model not unique. Based on the above background, the purpose of this article is to study the application of artificial intelligence technology in numerical control systems. The main method is to use the ANN model to expand the small amount of reliability data collected, and then use the KS test to analyze the expanded data to determine the reliability data model. At the same time, in the process of determining the parameters of the reliability distribution model, the mixed Particle Swarm Optimization (HPSO) algorithm is introduced into the maximum likelihood estimation to solve the problems of easy to fall into the local optimal solution and low efficiency when solving some complex distribution models with small sample data. The experimental results show that the reliability distribution model of CNC machine tools is not unique in the case of a small sample. The reliability model of CNC machine tools can be uniquely determined after analyzing the data using the ANN model and the KS test method. Achieve a good balance between solution efficiency and convergence performance. Comparing the results of all the solving models, the relative mean square error of the 2-fold 3-parameter Weibull distribution after the ANN model expansion is the smallest, with a value of 0.0428, which shows that using this method to solve the reliability distribution model of CNC machine tools is feasible and can obtain More accurate results.
Keywords: CNC Machine Tools; Artificial Intelligence; ANN Model; HPSO Algorithm.
Functional feature-aware APP recommendation with personalized PageRank
by Yueyue Xia, Xiangliang Zhong, Yiwen Zhang, Yuanting Yan
Abstract: With the explosive growth of mobile Apps and the widespread deployment of Internet of Things (IoT) services, how to recommend applications that users are interested in has become an urgent problem to be solved. And most of the current mobile APP recommendation methods are based on the user\'s behaviour data or context-aware information, to some extent, ignoring the user\'s preference for APP functional features. Therefore, a functional feature-aware mobile APP recommendation method, named S-AppRank, is proposed in this paper. S-AppRank first extracts the functional features of mobile applications and their internal association through weight calculations, then constructs a directed graph of user functional features with the association rules, and then adds user ratings to the traditional PageRank algorithm, incorporating explicit feedback into recommendation personally. Finally, the user\'s interests in the overall APP is predicted, and a recommendation list is generated. The experiments on the real dataset of Huawei application market show that the S-AppRank proposed in this paper is better than other comparison methods.
Keywords: functional feature-aware; APP recommendation; PageRank; user preference.
Special Issue on: Distributed Secure Computing for Smart Mobile IoT Networks
Privacy-Preserving smart contracts for Fuzzy WordNet Based Document Representation and Clustering using Regularized K-Means Method
by Venkata Nagaraju Thata, Sudhir Babu A, Haritha D
Abstract: Key technology for unsupervised intelligent classification of any textual content is the clustering of documents. Prior document knowledge is not required for document clustering, which is an unsupervised method of learning as compare with document classification. For clustering rather than classification, little prior knowledge of the data is needed. The crucial challenges of document clustering are the high dimensionality, measurability, preciseness, extraction of semantic relationships from texts, and meaningful cluster labels. Fuzzy wordnet based document representation and clustering using the regularized k-means method as an efficient framework is introduced in the present paper with the purpose of improving the quality of document clustering.To estimate the performance of this framework we carried out experiments on different datasets. Experimental results show that this framework improves the quality of document clustering when compared to other existing methods. Furthermore, this system gives generalized and concrete labels for documents and improves the speed of clustering by reducing their size.
Keywords: Document Clustering; Regularized K-Means; WordNet; Fuzzy Weighting Score,TF-IDF.
Special Issue on: Machine Learning and Deep Learning Methods for the Applications in Ad Hoc and Ubiquitous Computing
An Adaptive Stochastic Central Force Optimization Algorithm for Node Localization in Wireless Sensor Networks
by Pei-Cheng Song, Shu-Chuan Chu, Jeng-Shyang Pan, Tsu-Yang Wu
Abstract: Node localization in wireless sensor networks is a common and important practical application problem. Among the many localization algorithms, the MDS-MAP algorithm is a more effective one. However, the positioning effect of the MDS-MAP algorithm is not accurate in some cases, so the metaheuristic algorithm is implemented to further optimize the estimation results of the MDS-MAP algorithm in this paper. The improved central force optimization algorithm uses adaptive parameters to achieve randomness, while adding the restart strategy and accelerate strategy so as to avoid getting stuck in a local optimum. The CEC2013 and CEC2014 benchmark test suites used to verify the proposed algorithm are more competitive than some other existing algorithms. The improved central force optimization algorithm is applied to the MDS-MAP localization algorithm. The experimental results show that the improved central force optimization algorithm has a further optimization effect on the position estimation results of MDS-MAP.
Keywords: Central Force Optimization; Restart strategy; Adaptive; Stochastic; MDS-MAP; WSN.
A Compact GBMO Applied to modify DV-Hop based on layers in wireless sensor network
by Jeng-Shyang Pan, Min Gao, Jian-po Li, Shu-Chuan Chu
Abstract: Gases Brownian Motion Optimization (GBMO) has been shown a useful optimization method. The compact concept is implemented to the GMBO named Compact Gases Brownian Motion Optimization (CGMBO) so as to improve the efficiency and effectiveness of the GMBO. Simulation results based on the 23 test functions consisting of the unimodal, multimodal, fixed-dimensional functions and composite multimodal functions demonstrate the superior of the proposed CGMBO. The idea of layer concept is also proposed to implement the Distance Vector-Hop (DV-Hop) by modifying the original average distance of each hop called Layer DV-Hop (LDV-Hop), experimental results also show the proposed LDV-Hop really improve the average positioning accuracy of each node for wireless sensor network. Finally, the proposed CGMBO is combined with the proposed LDV-Hop so as to greatly reduce the position error compared with the DV-Hop. The actual error per-hop distance between nodes is large. When the calculated average hop distance of the nodes does not reach the ideal value, the actual distance between the nodes and the calculated distance will have a large deviation.
Keywords: Gases Brownian Motion Optimization; Wireless Sensor Network; Compact Gases Brownian Motion Optimization; LDV-Hop.
Auto Insurance Fraud Identification Based on CNN-LSTM Fusion Deep Learning Model
by Huosong Xia, Yanjun Zhou, Zuopeng (Justin) Zhang
Abstract: The traditional auto insurance fraud identification method relies heavily on feature engineering and domain knowledge, making it difficult to accurately and efficiently identify fraud when the amount of claim data is large and the data dimension is high. Deep learning models have strong generalization abilities and can automatically complete feature extraction. This paper proposes a deep learning model for auto insurance fraud identification by combining Convolutional Neural Network (CNN), Long Short Term Memory (LSTM), and Deep Neural Network (DNN). Our proposed method can extract more abstract features and help avoid the complex feature extraction process that is highly dependent on domain experts in traditional machine learning algorithms. Experiments demonstrate that our method can effectively improve the accuracy of auto risk fraud identification.
Keywords: auto insurance fraud; deep learning; CNN-LSTM.
Optimal Dense Convolutional Network Model for Image Classification in Unmanned Aerial Vehicles based Adhoc Networks
by Hephzi Punithavathi, Dhanasekaran S, Duraipandy P, Laxmi Lydia E, Sivaram M, K. Shankar
Abstract: Unmanned aerial vehicles (UAVs) has the potential of generating an ad hoc communication network on the fly. They are presently employed in different application areas like security, surveillance, rescue operations, and so on. Aerial image classification gains more importance in the remote sensing community and several studies have been carried out in recent days. On the other hand, deep learning (DL) is currently exhibiting excellent performance in several processes namely object detection, tracking, image classification, and so on. In this view, this paper presents an optimal Dense Convolutional Network (DenseNet) with bidirectional long short term memory (Bi-LSTM) based image classification model called optimal DenseNet (ODN)-BiLSTM for UAV based adhoc networks. The proposed model involves two major processes namely feature extraction and classification. Firstly, DenseNet model is applied as a feature extractor, where the hyperparameters of DenseNet are tuned by the use of Adagrad optimizer. Secondly, the Bi-LSTM model is applied as a classifier, which classifies the aerial images captured by UAV. Detailed performance analysis of the proposed model takes place using UCM aerial dataset and the results are investigated under several dimensions. The experimental outcome ensured the goodness of the presented ODN-BiLSTM model on the applied UCM aerial dataset over the compared methods. The ODN-BiLSTM model has provided effective image classification results over the other methods with the maximum accuracy of 98.14% and minimum execution time of 80s.
Keywords: Adhoc networks; Deep learning; Image classification; Unmanned aerial vehicle;.