Journal of Intelligent & Fuzzy Systems - Volume 36, issue 3

Authors: Majhi, Santosh Kumar | Bhatachharya, Subho | Pradhan, Rosy | Biswal, Shubhra

Article Type: Research Article

Abstract: In this paper, a hybrid fuzzy clustering techniques using Salp Swarm Algorithm (SSA) is proposed. The proposed fuzzy clustering method is used to optimize the cluster centroids obtained as an under sampling method. The performance of the proposed fuzzy clustering method is compared with some well-known clustering algorithms to shows the superiority of the proposed clustering algorithm. In addition, a novel hybrid Automobile Insurance Fraud Detection System is proposed in which undersampling of the majority class is performed by using the proposed fuzzy clustering algorithm which eliminates the outliers from the majority class samples. The balanced dataset for automobile fraud …detection obtained after undersampling undergoes classification. Different classifiers used for this purpose are Random Forest Classifier, Logistic Regression Classifier and XGBoost Classifier. The performance of each of the three classifiers is evaluated by considering different performance metrics such as sensitivity, accuracy and specificity. The proposed fuzzy clustering method along with XGBoost outperforms the other methods presented. Show more

Keywords: Fuzzy C-means, salp swarm algorithm, random forest classifier, logistic regression classifier, XGBoost classifier

DOI: 10.3233/JIFS-169944

Citation: Journal of Intelligent & Fuzzy Systems, vol. 36, no. 3, pp. 2333-2344, 2019

Authors: Rajagopalan, Anand K. | Shyamala, C.K.

Article Type: Research Article

Abstract: Automatic identification systems represent a wide classification of devices used primarily in commercial settings for inventory/logistics control. Familiar examples of such devices are bar codes, magnetic strips, smart cards, RFID (Radio-frequency identification) and biometric and voice recognition. Security is especially lax in low powered radio frequency systems communicating through an unsecured radio wave channel. Security represents a critical component for enabling the large scale adoption of automatic identification systems. Providing an effective security solution for low powered systems is a major area of concern; it directs research towards ‘power consumption aware’ computations in security solutions. This paper proposes a lightweight …inter-zonal authentication Protocol for moving objects in low powered radio frequency systems. Formal validation and a thorough analysis of the protocol in SPAN security tool reveal its effectiveness and resiliency to attacks – eavesdropping, reader and tag impersonation, replay and desynchronization. Show more

Keywords: Lightweight radio frequency systems, authentication, RFID, eavesdropping

DOI: 10.3233/JIFS-169945

Citation: Journal of Intelligent & Fuzzy Systems, vol. 36, no. 3, pp. 2345-2354, 2019

Authors: Madhawa, Surendar | Balakrishnan, P. | Arumugam, Umamakeswari

Article Type: Research Article

Abstract: Data Integrity attack is a major hindrance to the evolution of Industrial Internet of Things (IIoT) as it leads to immense financial loss or even human fatality. The existing security features in Software Defined Networking (SDN), which is emphatically superior to the traditional networks mitigate the integrity attacks to some extent. However, a generic, robust, secure and resilient Intrusion Detection System (IDS) for IIoT is still lacking in the literature. Towards this goal, a generic IDS is already proposed in our earlier research work which combines both anomaly as well as rule-based intrusion detection techniques and successfully tested against the …real-time dataset obtained from the water purification process in a test bed at the Singapore University of Technology and Design (SUTD). This research work proposes a supervised learning approach that utilizes Roll-forward technique for validation and Classification and Regression Trees (CART) with invariants for categorization to find anomalousness in the water treatment process. The proposed work incorporates the capability to substantiate time-series data through Roll-forward validation which is then succeeded by utilization of the CART with invariants for classification. The proposed work is simulated using Mininet tool and the train and test accuracies are 99.9% and 98.1% respectively. Show more

Keywords: Industrial internet of things, software defined networking, IDS, roll-forward validation, decision tree

DOI: 10.3233/JIFS-169946

Citation: Journal of Intelligent & Fuzzy Systems, vol. 36, no. 3, pp. 2355-2366, 2019

Authors: Das, Anjana P. | Thampi, Sabu M.

Article Type: Research Article

Abstract:  An underwater acoustic sensor network (UASN) offers a promising solution for the exploration of underwater resources remotely. As the UASN acoustic channel is open and the environment is hostile, the risk of malicious activities is very high, particularly in time-critical military applications. In this paper, we propose an unsupervised anomaly detection system by learning the social behavioral correlation among nodes. The location data retrieved from sensors are learned using long short term memory (LSTM) networks to capture the anomalous nature. The network is simulated by modeling anomalies and analyzed the performance. The analysis of results indicates that the anomaly detection …system offers an acceptable accuracy with high true positive rate and F-Score by showing consistency in multiple mobility behavior. Show more

Keywords: Underwater sensor networks, time series analysis, anomaly detection, long shot term memory network

DOI: 10.3233/JIFS-169947

Citation: Journal of Intelligent & Fuzzy Systems, vol. 36, no. 3, pp. 2367-2372, 2019

Authors: Kulkarni, Swati V. | Dhage, Sudhir N.

Article Type: Research Article

Abstract:   The Credit Score is the most fascinating three digit number associated with an individual or an organization as it figures out what loans you will qualify for and the interest rate you will pay. Current credit scoring system is based on the financial history of individual or organization. This work illustrates a new credit scoring system which incorporates Legacy credit score and emotional/social credit score. The legacy credit score is based on the financial history of an individual. The emotional/social credit score is based on analysis and study of social media and other web interaction. The new system called …information trustworthiness is developed to improve the precision of social media data when compared with data from reliable sources. Finally, the proper fractions of legacy credit score and emotional/social credit score are added to get Advanced Credit Score. This score is more precise than Legacy credit score as it also incorporates personality traits of an individual which have a high impact on one’s financial behavior. However, the accuracy of the Advanced Credit Score is dependent on the fractions of legacy credit score and emotional/social credit score selected. The advance scoring system can be effectively used to distinguish people who defaulted many times and who never used loans or services like credit cards which are otherwise not possible using legacy financial credit scoring system. Show more

Keywords: Credit score, Naive Bayes, CRISP-DM, data mining, Multilayer Perceptron, Random Forest, Random Tree

DOI: 10.3233/JIFS-169948

Citation: Journal of Intelligent & Fuzzy Systems, vol. 36, no. 3, pp. 2373-2380, 2019

Authors: Casado-Vara, Roberto | Corchado, Juan

Article Type: Research Article

Abstract:  Today’s e-health system is centralized. This system obliges all users (patients and healthcare staff) to have a high level of trust in the intermediary who stores the data. Moreover, healthcare employees must trust that their patients are providing authentic medical records and are not altering them in order to obtain drugs for illegal purposes. The solution proposed in this paper is a new blockchain-based architecture for the creation of an e-health system. In this architecture, wireless sensor networks (WSN) will be used in association with a WSN controller v.2 to supervise patients and their testing by healthcare staff. Transactions between …blockchain and WSN are made through smart contracts, removing the need for intermediaries and preventing human error. This new model facilitates a distributed ledger, creating an e-health system that is much more optimized than the current one. Show more

Keywords: Blockchain, WSN, smart contract, e-health architecture, distributed ledger

DOI: 10.3233/JIFS-169949

Citation: Journal of Intelligent & Fuzzy Systems, vol. 36, no. 3, pp. 2381-2386, 2019

Authors: Saxena, Rahul | Jain, Monika | Sharma, D.P. | Jaidka, Siddharth

Article Type: Research Article

Abstract: VANET has been an area of great interest and exploration for researchers to solve several challenging issues regarding communication, topology, security etc. in the last few years. Currently, a lot of work has been done and is looked after to establish effective communication and message passing among the vehicles (V2V and V2I routing) with a number of algorithmic models developed. The paper presents a survey of the routing algorithms proposed to have communication inside a VANET among the nodes. Since V2V and V2I interactions is a complex combinatorial problem which falls under the class of NP-Complete set of problems. The …paper here presents a modified mobicast routing version using genetic algorithm with certain considerations for mutation and crossover operator for the algorithm in order to achieve more accuracy for the results. The method shows a great enhancement in the execution timing for a considerable number of vehicles where the traditional algorithms may hang up to produce a route. But still the serial version stucks up for heavy density vehicle scenarios for message passing in real time. So, the efficiency of the proposed method is enhanced using parallel processing power of multi-core and many-core processors using OpenMP and Computationally Unified Device Architecture (CUDA) API. The enhanced results show a great improvement in the performance in terms of execution time when compared with the serial algorithm, especially for the cases where the solutions cannot be obtained in real time. The results over GPU based architecture suggests that the proposed method has a huge potential to scale up with the vehicles on the road, thus, reducing the road side units for providing a larger range of coverage. Show more

Keywords: VANET, Vehicle to Vehicle (V2V), Vehicle to Infrastructure (V2I), genetic algorithm, OpenMP, CUDA

DOI: 10.3233/JIFS-169950

Citation: Journal of Intelligent & Fuzzy Systems, vol. 36, no. 3, pp. 2387-2398, 2019

Authors: Gogoi, Ashim Jyoti | Choudhury, Hussain Ahmed | Baishnab, Krishna Lal

Article Type: Research Article

Abstract:  The cognitive radio network provides a pioneered solution to the spectrum scarcity problem and represents a new paradigm for designing intelligent wireless networks. Energy efficient cognitive radio system maintaining reliability holds great importance in the present scenario of wireless communications. In a cognitive radio network, relays are used to enhance energy efficiency as well as to maintain the sensing reliability. Most of the works in the area of cognitive radio network focused on optimization of energy consumed during data transmission only, while neglecting the energy consumed during spectrum sensing. In this paper, an energy efficient multi-relay cognitive radio network is …designed, in which both sensing energy and data transmission energy are jointly optimized. Also, optimal values of system parameters like sensing time and amplifying gain of the relays are determined for the energy efficient system. The minimization of the energy consumed under constraints of target throughput and sensing requirements of cognitive radio network is considered as an optimization problem. Swarm intelligence based optimization techniques like particle swarm optimization (PSO), Particle Swarm Optimization with Aging Leader and Challengers (ALCPSO), Human behavior based Particle Swarm Optimization (HPSO) and Whale Optimization Algorithm (WOA) are used to optimize energy consumption in the network. The analysis reveals that the proposed scheme makes the cognitive radio network more energy efficient than conventional schemes. Show more

Keywords: Cognitive radio networks, energy efficiency, particle swarm optimization, spectrum efficiency, dynamic spectrum assignment

DOI: 10.3233/JIFS-169951

Citation: Journal of Intelligent & Fuzzy Systems, vol. 36, no. 3, pp. 2399-2407, 2019

Authors: Chandrawanshi, Veervrat Singh | Tripathi, Rajiv Kumar | Pachauri, Rahul

Article Type: Research Article

Abstract: A wireless sensor network consists of a large number of sensor nodes. The key parameters of the wireless sensor network are limited energy, network lifetime, limited ability, secure communication, quality of service, data aggregation, and synchronization. In wireless sensor network when the single base station multi-hop communication model is used, the adjacent nodes to the base station transmitted all the data to the base station. Thus the adjacent nodes deplete their energy earlier than other nodes and create the energy holes near the base station. These energy holes minimize the lifetime of the network. The primary objective in large-scale wireless …sensor networks is to increase the lifetime with limited energy resources. This can be achieved by placing the multiple base stations using an intelligent clustering technique in a wireless sensor network. In this paper, an intelligent clustering technique has been proposed to choose the optimal position of multiple base stations with the help of k-means++ clustering technique in conjunction with the local+ scheme. The simulation result shows that the proposed method provides minimum energy consumption with an extended lifetime in comparison to the two individual clustering techniques. Show more

Keywords: Wireless sensor networks, clustering, cluster head, multiple base station, optimal number, k-means, local+, energy efficient network.

DOI: 10.3233/JIFS-169952

Citation: Journal of Intelligent & Fuzzy Systems, vol. 36, no. 3, pp. 2409-2418, 2019

Authors: Ezhilarasie, R. | Umamakeswari, A. | Reddy, Mandi Sushmanth | Balakrishnan, P.

Article Type: Research Article

Abstract:  Generally, several IoT (Internet of Things) applications employ cloud data centre for processing the data generated by edge devices like smartphones and tablets. Due to the increasing use of the IoT devices, the demand for higher computational and communication capabilities are also increasing. With the advent of Edge Computing and given the fact that computational capabilities are currently untapped, a part of the computational load can be offloaded to the edge nodes. In this paper, a Grefenstette bias based Genetic Algorithm for MultiSite Offloading (GGA-MSO) is proposed. This algorithm decides the schedule of the application that could be offloaded. The proposed …algorithm provides a solution which has convergence in lesser time by employing diversification of initial population using the Grefenstette’s Bias method. Besides, the container based lightweight virtualization is analyzed for offloading code and data to the nearby devices. The evaluation of the proposed work on random graphs shows that the proposed method starts to converge with significantly lesser iterations than its counterpart with undiversified population. The test bed results on Single Board Computers (SBC) like Raspberry Pi setup indicates that by adapting container virtualization in the edge environment, the performance of the IoT devices is improved and the communication overhead is reduced. Show more

Keywords: Internet of things (IoT), edge computing, computation offloading, application partitioning, Docker container, raspberry Pi

DOI: 10.3233/JIFS-169953

Citation: Journal of Intelligent & Fuzzy Systems, vol. 36, no. 3, pp. 2419-2429, 2019