International Journal of Intelligent Systems Technologies and Applications (11 papers in press)
An Ant Colony Optimization based Framework for the Detection of Suspicious Content and Profile from Text Corpus
by Asha Kumari, Balkishan
Abstract: The technical advancements in the field of short message communication have swiftly raised the menace of suspiciousness along with human communication means. This uncontrolled enhancement of unsolicited suspicious content has become the motivation for the researchers to work and control this peril. Suspicious content can be related to any uninvited message that can lead to rumors, fake news, spam, malicious, and threatening activities. Although there are numerous classical content-based methods for the detection of suspicious activities, these methods lack in case of short messages such as SMS and microblogs. This research work addresses the problem of suspicious content and profile identification from SMS and Twitter Microblogs. A framework based on Ant Colony Optimization is presented for the Detection of Suspicious Content and Profile (ACODSCP). In this study, one twitter Microblogs based text dataset and two SMS based text corpora are utilized. The global optimization behavior of ant colony optimization (ACO) concept incorporates to determine the suspicious activities and profiles effectively with the minimal feature set. The performance of the proposed ACODSCP system is assessed in terms of precision, recall, and f-measure. The evaluated results in terms of mentioned parameters indicate the promising results of the proposed concept in comparison with existing concepts.
Keywords: Suspicious Content; Swarm Intelligence; Ant Colony Optimization; Short Message Service (SMS); Twitter Microblogs; Spam; Social Communication Means.
An ECC Based Authentication Protocol for Fog-IoT Enabled Smart Home Environment
by Bhabendu Kumar Mohanta, Debasish Jena, Srikanta Patnaik
Abstract: Internet of Things(IoT) enabled smart home means all the home
appliances are connected to the internet.All these devices are monitored and
controlled using a mobile device, iPhone, or iPad regardless of location or time
constraint. In an IoT based smart home network, associated users and devices
need to be recognized otherwise unauthorized access reduce the security and
privacy of the smart environment. In this paper, contributions are first proposed
an Elliptical curve cryptography based authentication protocol for Fog nodes and
users in the IoT-based smart home environment. Secondly, the simulation for
security analysis of the proposed authentication protocol using AVISPA tools has
been done. Thirdly, BAN logic is used to verify that the devices in the smart
home environment are achieved security goals. Finally, a comparison with some
existingworks has been done and it has been seen that proposed protocol achieved
better security goals in a smart home environment.
Keywords: Authentication,IoT; Smart Home Environment,Security,Elliptic
Model to enhance Security posture of IoT devices and components with Private APN
by Akashdeep Bhardwaj, Bharat Bhushan
Abstract: Internet is a dangerous place for the countless devices connected to the Internet. These devices or Things on Internet connect from remote locations at the network edge provide various services that makes our lives easy. With little or no security protection, IoT vendors use low-grade virtual private network solutions for devices linked on public, insecure circuits, specifically the Internet. This enables protection of sensitive data in transit when logs traverse from sensors and edge devices to business systems and cloud infrastructure. However, the rise of new vulnerabilities and attack methodologies more often than not, end up compromising these devices. The reality is such devices face an unprecedented risk of exposure to Botnets, Malware, man in the middle, remote execution and session hijacking cyber-attacks. The impact not just disrupts the functioning of IoT deployment; it can disable services, turn into Bots but also, damages the business reputation and brand value. The authors strongly believe that industrial, commercial business operations and end user devices should never be at risk or have a chance of exposure to cyber-attacks. This paper presents a secure IoT architecture using private Access Point Name model. The authors discuss the proposed model presenting superior security, visibility and regulation over data traffic flows originating from the IoT device to the cloud infrastructure. This architecture has been successfully tested and implemented for one of the utility companies in India for real time monitoring of their critical infrastructure elements.
Keywords: IoT; IoT Security; Private APN; Mobile; Private IP.
A reliability-aware scheduling algorithm for parallel task executing on cloud computing system
by Jie Cao, Zhifeng Zhang, Bo Wang, Xiao Cui, Jinchao Xu
Abstract: As cloud computing is established on the massive cheap server clusters, which causes compute nodes software and hardware to go wrong. Different computing nodes and communications links have different failure rate. For the parallel task scheduling problem that cloud users have requirements for deadlines and executing reliability, we put forward to generate all possible execution schemes of a parallel task on a cloud computing system. All the execution schemes are constructed into an execution scheme graph (ESG), in which a path from the start point to end point corresponds to an execution scheme of a parallel task. Based on ESG, we propose the maximum reliability execution scheme solving algorithm MRES that searches the execution schemes which have maximum reliability cost while meeting the parallel tasks deadline requirement. The experimental results show that MRES algorithm can effectively improve the executing success rate.
Keywords: Cloud computing;Reliability;Directed acyclic graph;Task scheduling.
Special Issue on: Exploration of Intelligent Techniques for Computer Vision Applications
Investigating the Population Dynamics of Differential Evolution Algorithm for Solving Multi-Objective RFID Reader Placement Problem
by K. Devika, Gurusamy Jeyakumar
Abstract: Evolutionary Algorithms (EAs) are the most commonly used bio-inspired algorithms to solve complex real-world optimization problems. Numerous research works are in pipeline for studying the behavior, improving the performance and testing the applicability of EAs on complex real world optimization problems. Matching to this trend, this research work is carried out in three phases. In Phase-I, a comparative performance analysis of two popular Population Initialization (PI) techniques of EAs was carried out. The experimental set up of this phase included four variants of the classical Differential Evolution (DE) algorithm and a set with four standard benchmarking functions of different categories. The comparative results showed that DE performs better with Opposition Based Learning PI (OBLPI) than with the Random PI (RPI) technique, for larger population sizes with increased chromosome length. The Phase-II of this work analyzed the performance of DE in solving the Multi-Objective Optimization Problems (MOOP) with these RPI and OBLPI techniques. The experimental analysis revealed that DE with OBLPI technique could perform well only for problems with lower population size and with less number of objectives. The DE with RPI technique performed well for MOOPs with larger population sizes and with more number of objectives. In Phase - III, the applicability of DE was demonstrated on the Radio Frequency Identification (RFID) reader placement problem with multiple-objectives. This phase included experiments to optimize the RFID reader placement problem in single room as well as in multiple rooms of different sizes. Respectively, the concept of population with Fixed Length Chromosomes (FLC) and Variable Length Chromosomes (VLC) were experimented. A carefully designed simulation environment was used for phase III. The design of experiment, the results obtained and the inferences, in all the phases, are presented in this paper.
Keywords: Evolutionary Algorithms; Differential Evolution; Population Initialization; Multi-objective optimization problem; RFID Reader Placement problem; Variable Length Chromosomes;.
Empirical Investigations on Evolution Strategies to Self-adapt the Mutation and Crossover Parameters of Differential Evolution Algorithm
by Dhanya M. Dhanalakshmy, Gurusamy Jeyakumar, C. Shunmuga Velayutham
Abstract: Differential Evolution (DE) is an instance under the repository of Evolutionary Algorithms (EAs). DE is popular for its simplicity and robustness. Numerous researches have been underway towards improvement of the performance of DE. Incorporation of parameter control mechanisms to DE is one such avenue. There exist many strategies for parameter control. One such strategy is to evolve the parameters along with the candidate solutions in the population being probed by DE. This paper proposes to investigate different parameter evolution strategies, applicable for DE, for two of its control parameters: mutation step size (F) and crossover probability (CR). The experimental set up used for this investigation includes a well-defined set of four benchmarking problems with diverse characteristics and two performance metrics: mean of objective function values (mOV) and mean of number of function evaluations (mFE). This study initially discusses the influence of F and CR on the performance of DE, with empirical evidences of the obtained results. Then, the study proceeds to implement 25 difference instances of self-adaptive strategy for F and CR. The best performing instance among these 25 instances is declared as the proposed self-adaptive strategy for F and CR. The superiority of the proposed strategy was tested and validated on solving the RFID reader placement problem. The experimental setups, the results obtained, and the inferences found at all the phases of this research work are presented in this paper. The study found that the proposed strategy could solve the benchmarking functions and the chosen real world problem faster than the classical DE algorithm.
Keywords: Differential Evolution; Self-Adaptation; Scale Factor; Crossover Rate; Evolving Parameters.
Trajectory based Fast Ball Detection and tracking for an Autonmous Industrial Robot System
by Youssef M. AbdElKhalek, Mohammed Ibrahim Awad, Hossam E. Abd El Munim, Shady A. Maged
Abstract: Autonomizing industrial robots is the main goal in this paper, imagine humanoid robots that have several D.O.F (Degrees of freedom) mechanisms as their arms. What if the humanoid's arms could be programmed to be responsive to their surrounding environment, without any hard-coding assigned. This paper presents the idea of an autonomous system, where the system observes the surrounding environment, and takes action on its observation. The application here is that of rebuffing an object that is thrown towards a robotic arm's work space. This application mimics the idea of high dynamic responsiveness of a robot's arm. This paper will present a trajectory generation framework for rebuffing incoming flying objects. The framework bases its assumptions on inputs acquired through image processing and object detection. After extensive testing, it can be said that the proposed framework managed to fulfill the real-time system requirements for this application, with an 80% percent successful rebuffing rate.
Keywords: object detection: stereo vision: object tracking: ping-pong ball: trajectory prediction; table tennis; real-time; depth image processing; infrared image processing; serial robot.
Heuristic Hidden Markov Model for Fuzzy Time Series Forecasting
by Ahmed Tijani Salawudeen, Maryam Lami Imam
Abstract: This paper presents FTS forecasting model using Hidden Markov Model (HMM) and Genetic algorithm (GA). One of the major limitations of HMM has been the lack of an efficient method for parameter estimation. Over the years, traditional methods such as Baum Welch Algorithm (BWA) have been employed significantly for this purpose. This method does not usually capture effectively the fuzziness in natural data leading the HMM algorithm into local minima. To address this challenge, this paper presents an optimization method of estimating the HMM model parameters using GA. In order to address the insufficiency in data associated with the HMM model, we adopted a method called smoothing. Monte Carlo simulation was employed at the end of the forecast to ensure the stability and efficiency of the developed approach. The developed model was used to forecast the daily average temperature and cloud density of Taipei Taiwan and Internet traffic data of Ahmadu Bello University (ABU). Results showed that the model obtained MSE values of 0.0725 and 0.0893 and AFEP values of 0.7952 and 0.8493 for July 1996 and September 1996 respectively. The model also performed efficiently on the ABU internet traffic with a mean absolute percentage error of 0.086%
Keywords: GA; HMM; FTS; Monte Carlo Simulation; Baum Welch Algorithm.
Special Issue on: Recent Advancements in Artificial Intelligence Systems and Their Applications
An Improved Henry Gas Solubility Optimization-based Feature Selection Approach for Histological Image Taxonomy
by Susheela Vishnoi, Ajit Kumar Jain
Abstract: Classification of histopathological images is one of the important areas of research in the field of medical imaging. However, the complexities available in histopathological images make the classification process difficult. For such complex images, selection of prominent features for image classification is also a challenging task and is still an open research area for computer vision researchers. Therefore, an effective method for the selection of prominent features of images has been introduced in this work. For the same, an improved henry gas solubility optimization has been introduced in which a new position update equation has been used to balance the global and local search. The selected features are then input to classifiers to identify histopathological images. For the performance analysis of improved henry gas solubility optimization, 23 benchmark functions are used. The proposed feature selection method has been analysed over two datasets, namely breast cancer cell dataset and ICIAR grand challenge dataset. The proposed feature selection method eliminates the maximum 60% average features from both the datasets. To validate usefulness of selected features, results of different classifiers are compared. Experimental results show that the presented method outperforms other methods.
Keywords: Feature selection; Henry gas solubility optimization algorithm; Histology images; Image classification.
Clustering based hybrid resampling techniques for social lending data
by Pankaj Kumar Jadwal, Sonal Jain, Basant Agarwal
Abstract: Social lending is the most popular and emerging loan disbursement process where an individual can act as a borrower or lender. Credit risk evaluation of the borrowers in an effective way is a crucial task, especially in social lending, where chances of being defaulted are more than the traditional models. Social lending datasets are imbalanced in nature due to the low number of defaulters than successful borrowers. Machine learning models based on such datasets contain biasing towards the class representing the majority of samples (Majority class). Therefore, the probability of accurate prediction of minority class samples is decreased due to biasing towards majority class samples. In this paper, we propose a novel Clustering based Hybrid Sampling algorithm (CBHS), where multi-phase K-means clustering is applied on the minority class samples to perform oversampling (KMBOS), and Fuzzy c -means clustering is used on the majority class samples to perform undersampling (FCBU). Experiments results show that KMBOS and FCBU algorithms outperform state of the art techniques of oversampling and undersampling.
Keywords: Credit risk; Clustering; Classification; Hybrid model; Oversampling; Undersampling; Class Imbalance.
ADAPTIVE FUZZY LOGIC CONTROL FOR A ROBOTIC GAIT TRAINING ORTHOSIS
by Deepa Mathur, Deepak Bhatia, Prashant K. Jamwal, Shahid Hussain, Mergen H. Ghayesh
Abstract: This paper aims to develop an adaptive control strategy for a fuzzy logic system to be implemented in a robotic gait training orthosis. The robotic orthosis has a bio-inspired design which has evolved after a careful study of the biomechanics of human gait. Ambulatory requirements of the robot have been achieved by employing light weight but powerful pneumatic muscle actuators (PMA). The sagittal plane rotations achieved by the robotic orthosis at the hip and knee are achieved by implementing a Pneumatic Muscle Actuator (PMA) for actuation. The PMA of the Robotic orthosis was controlled by a fuzzy logic controller based on the Mamdani inference in order to obtain the necessary rotational degrees of freedom. To cope with the nonlinear behavior of PMA towards external disturbances, a second instance of fuzzy based controller has been developed. The PMA is infamous for its time dependent characteristics hence an adaptive control mechanism has been introduced in an attempt to compensate for it. Healthy subjects were employed for performing experiments in order to understand and estimate the performance of the adaptive fuzzy logic controller as well as the entire adaptive robotic design. The human-robot interaction was mainly maintained passive-active, while the paths used for the robot were strictly predefined trajectories which were usually employed by physical therapists during rehabilitation sessions.
Keywords: Adaptive fuzzy logic control; robotic orthosis; gait training; PMA; neurological impairments.