Journal of Intelligent & Fuzzy Systems - Volume 39, issue 6

Authors: Revathy, P. | Mukesh, Rajeswari

Article Type: Research Article

Abstract: Like many open-source technologies such as UNIX or TCP/IP, Hadoop was not created with Security in mind. Hadoop however evolved from the other tools over time and got widely adopted across large enterprises. Some of Hadoop’s architectural features present Hadoop its unique security issues. Given this security vulnerability and potential invasion of confidentiality due to malicious attackers or internal customers, organizations face challenges in implementing a strong security framework for Hadoop. Furthermore, given the method in which data is placed in Hadoop Cluster adds to the only growing list of these potential security vulnerabilities. Data privacy is compromised when these …critical and data-sensitive blocks are accessed either by unauthorized users or for that matter even misuse by authorized users. In this paper, we intend to address the strategy of data block placement across the allotted DataNodes. Prescriptive analytics algorithms are used to determine the Sensitivity Index of the Data and thereby decide on data placement allocation to provide impenetrable access to an unauthorized user. This data block placement strategy aims to adaptively distribute the data across the cluster using innovative ML techniques to make the data infrastructure extra secured. Show more

Keywords: Big data, Hadoop security, data placement strategy for sensitive data, sensitivity in Hadoop, prescriptive analytics

DOI: 10.3233/JIFS-189165

Citation: Journal of Intelligent & Fuzzy Systems, vol. 39, no. 6, pp. 8477-8486, 2020

Authors: Devarajan, Malathi | Sasikaladevi, N.

Article Type: Research Article

Abstract: With ever growing popularity, wireless communication system also vulnerable to various security attacks. To provide high level security, many cryptographic solutions have been proposed. One such solution is signcryption, where authenticity and confidentiality provided by single logical step. Therefore, signcryption scheme helps to reduce computational cost, but it is not feasible for resource constraint environments. Because, most of the existing approaches were based on El-Gamal, bilinear pairing, Rivest-Shamir-Adleman (RSA), and Elliptic curve Cryptography (ECC). They consume more energy due to their increased key size. Hence, the new signcryption approach is proposed based on Hyper Elliptic Curve Cryptosystem (HECC) whose key …size is much lesser than ECC. It significantly reduces the cost of computation and communication overhead by half the amount of ECC which suits well for resource constraint environments. Further, the proposed scheme attains necessary security features along with forward secrecy and public verifiability. On the other hand, the security of the approach is validated through an automated protocol validation tool – AVISPA. Show more

Keywords: Hyper elliptic curve, signcryption, mutual authentication, security analysis, AVISPA

DOI: 10.3233/JIFS-189166

Citation: Journal of Intelligent & Fuzzy Systems, vol. 39, no. 6, pp. 8487-8498, 2020

Authors: Varela, Noel | Pineda Lezama, Omar Bonerge | Neira, Harold

Article Type: Research Article

Abstract: The principle assaults on a Wireless Sensor Network (WSN) essentially influence the uprightness and accessibility of the data gathered, for example, Deni-al of Service, Blackhole, Wormhole, and assault on the data being transmitted. Privacy is not an important security objective because the data caught by the sensors are typically not delicate or mystery from individuals. A remote sensor organizes applied to shrewd metering frameworks might be adequately powerful as far as robotization and adjustment of the information that is gathered, however, if the system doesn’t have satisfactory security, both the client and the organization offering the support might be influenced …by assaults on the respectability and accessibility of the data transmitted. This research proposes the use of MESH encryption techniques and Star topology to find the best combination that meets the requirements of a Smart Metering System. Show more

Keywords: Security, encryption, topology, WSN, smart metering networks, cryptographic techniques

DOI: 10.3233/JIFS-189167

Citation: Journal of Intelligent & Fuzzy Systems, vol. 39, no. 6, pp. 8499-8506, 2020

Authors: Varghese, Lijo Jacob | Sira Jacob, Suma | Banumathi, S. | Ravi, Logesh | Vairavasundaram, Subramaniyaswamy | Jacob Raglend, I.

Article Type: Research Article

Abstract: This work aims to improve the operation of multi-level inverter with reduced switching losses, thereby propose a new structure for an MLI with a reduced component count. A 27-level asymmetric Multi Level Inverter (MLI) with a minimal number of static switches is considered as a test system. The proposed MLI is developed with three input DC sources and thirteen power electronic switches. The hardware prototype is developed for 40 V and 3.5 A output. The control logic is developed in dsPIC30F410 controller. The main objective of this work is to effectively bring down the Total Harmonic Distortion (THD) of the resulting …output voltage by analyzing the harmonic spectrum of the proposed MLI configuration with various low frequencies switching techniques and optimizing their switching angles and to choose an appropriate switching state using fuzzy logic controller (FLC). The proposed FLC covers wide range of operating conditions i.e. 10 switching states and variables 9*9 rules to predict the suitable switching angel. The performance metrics of the proposed structure of 27-level MLI has been evaluated upon simulation results and experimental results based on hardware prototype. The comparative study also carried out with the recent MLI topologies. Show more

Keywords: Asymmetric multilevel inverter, fuzzy logic, total harmonic distortion, pulse width modulation, reduced number of switches, optimum switching angles.

DOI: 10.3233/JIFS-189168

Citation: Journal of Intelligent & Fuzzy Systems, vol. 39, no. 6, pp. 8507-8519, 2020

Authors: Nagarajan, Manikandan | Sasikumar, A. | Muralidharan, D. | Rajappa, Muthaiah

Article Type: Research Article

Abstract: Approximate computing is a rapidly growing technique to speed up applications with less computational effort while maintaining the accuracy of error-resilient applications such as machine learning and deep learning. Inheritance properties of the machine and deep learning process give freedom for the designer to simplify the circuitry to speed up the computation process at the expense of accuracy of computational results. Fundamental blocks of any computation are adders. In order to optimize it for better performance, 2-bit multi-bit approximate adders (MAPX) are proposed in this work which breaks the lengthy carry chain. In contrast with other approximate larger width adders, …instead of using accurate adders for the most significant part, here proposed 2-bit MAPX-1 and MAPX-2 adders are arranged in various ways to compose most and least significant parts. Designed 8-bit and 16-bit adders are evaluated for their performance and error characteristics. Proposed 2-bit MAPX-2 shows better error characteristics whose MED is 0.250 while occupying less area and MAPX-1 consumes less power and delay at the cost of accuracy. Among the extended adders, MAPX 8-bit adder design1 outperforms the best performing APX based 8-bit adder design1. The error performance of it is improved by 14%, 42.1% and 50.4% compared to the existing well-performing APX 8-bit Design1, Design2 and Design3 respectively. Similarly, proposed MAPX 16-bit Design1 exhibits overwhelming performance compared to best performing APX 16-bit Design1, and its error performance is improved by 24.3%, 34.9% and 50.3% compared to APX 16-bit Design1, Design2 and Design3 respectively. In order to evaluate the proposed adder for a real application, extended MAPX 16-bit Design1 is fit in the convolution layer of Low Weights Digit Detector (LWDD) convolutional neural network-based digit classification system. Our modified system accelerates the computation process by 1.25 factors while exhibiting the accuracy of 91% and it best fits error-tolerant real applications. All the adders are synthesized and implemented in the Intel Cyclone IV EP4CE22F17C6N FPGA. Show more

Keywords: Approximate adders, multi-bit adders, CNN accelerator, digit classification, deep learning

DOI: 10.3233/JIFS-189169

Citation: Journal of Intelligent & Fuzzy Systems, vol. 39, no. 6, pp. 8521-8528, 2020

Authors: Martinaa, M. | Santhi, B. | Raghunathan, A.

Article Type: Research Article

Abstract: Wireless Sensor Networks (WSNs) is created, stemming from their applications in distinct areas. Huge sensor nodes are deployed in geographically isolated regions in WSN. As a result of uninterrupted transmission, the energy level of the nodes gets rapidly depleted. Sensor node batteries cannot be replaced or recharged often and maintaining the energy level is a crucial issue. Thus energy efficiency is the significant factor to be consider in WSN. This paper focuses to implement an efficient clustering and routing protocols for maximized network lifetime. Clustering has been confirmed as a successful approach in network organization. The fundamental responsibilities of the …clustering mechanism include improved energy efficiency and extended network lifespan. In this work, energy efficiency is improved to maximize lifespan of the WSN by proposing a novel method known as the Populated Cluster aware Routing Protocol (PCRP). The proposed method comprises three different steps: cluster formation, cluster head selection, and multi-hop data transmission. All sensor nodes are joined to a Cluster Head in a single hop in the cluster formation phase. Node distance is calculated and from which cluster head is selected. Then, cluster head aggregates the data from sensor nodes and transfer to the Base Station (BS). The shortest pathway is estimated by the Energy Route Request Adhoc On-demand Distance Vector (ERRAODV) algorithm. The proposed method considers the residual energy involved to attain high energy efficiency and network stability. The experimental analysis is demonstrated to validate the proposed method with existing, which improves the network lifespan. Vital parameters are validated using Network Simulator (NS2). Show more

Keywords: Energy consumption, clustering, routing protocol, network lifetime, wireless sensor networks

DOI: 10.3233/JIFS-189170

Citation: Journal of Intelligent & Fuzzy Systems, vol. 39, no. 6, pp. 8529-8542, 2020

Authors: Nourbakhsh, Azamossadat | Moin, Mohammad-Shahram | Sharifi, Arash

Article Type: Research Article

Abstract: Face is the most important and most popular biometric used in many identification and verification systems. In these systems, for reducing recognition error rate, the quality of input images need to be as high as possible. Face Image Compliancy verification (FICV) is one of the most essential methods for this purpose. In this research, a brain functionality inspired model is presented for FICV using Haxby model, which is a face visual perception consistent model containing three bilateral areas for three different functionalities. As a result, contribution of this work is presenting a new model, based on human brain functionality, improving …the compliancy verification of face images in FICV context. Perceptual understanding of an image is the motivation of most of the quality assessment methods, i.e., the human quality perception is considered as a gold standard and a perfect reference for recognition and quality assessment. The model presented in this work aims to make the operational process of face image quality assessment system closer to the performance of a human expert. Three basic modules have been introduced. Face structural information, for initial information encoding, is simulated by an extended Viola-Jones model. Face image quality assessment is presented by International Civil Aviation Organization (ICAO), in ICAO (ISO / IEC19794 -11) requirements’ compliancy assessment document. Like Haxby model, perception is performed through two distinct functional and neurological pathways, using Hierarchical Maximum pooling (HMAX) and Convolutional Deep Belief Networks (CDBN). Information storing and fetching for training are similar to their corresponding modules in brain. For simulating the brain decision making, the final results of two separate paths are integrated by weighting sum operator. Nine ISO / ICAO requirements were used for testing the model. The simulation results, using AR and PUT databases, shows improvements in six requirements using the proposed method, in comparison with the FICV benchmark. Show more

Keywords: Haxby model, ICAO, facial images quality verification, HMAX model, CDBN

DOI: 10.3233/JIFS-189171

Citation: Journal of Intelligent & Fuzzy Systems, vol. 39, no. 6, pp. 8543-8555, 2020

Authors: Jagdish, Mukta | Viloria, Amelec | Vargas, Jesus | Pineda Lezama, Omar Bonerge | Ovallos-Gazabon, David

Article Type: Research Article

Abstract: Cloud-based computation is known as the source architecture of the upcoming generation of IT enterprise. In context to up-coming trade solutions, the Information Technology sections are established under logical, personnel, and physical control, it transfers application software and large database to appropriate data centers, where security and management of database with services are not trustworthy fully. So this process may face many challenges towards society and organizations and that not been well understood over a while duration. This becomes one of the major challenges days today. So in this research, it focuses on security-based data storage using cloud, which plays …one of the important aspects bases on qualities of services. To assure user data correctness in the cloud system, a flexible and effective distributed technique with two different salient features was examined by utilizing the token called homomorphic with erasure-coded data for distributed verification, based on this technique it achieved error data localization and integration of storage correctness. Also, it identifies server misbehaving, efficient, and security-based dynamic operations on data blocking such as data append, delete, and update methods. Performance analysis and security show the proposed method is more effective resilient and efficient against Byzantine failure, even server colluding attacks and malicious data modification attacks. Show more

Keywords: Cloud security, architecture design, data storage, homomorphic token, dynamic operation

DOI: 10.3233/JIFS-189172

Citation: Journal of Intelligent & Fuzzy Systems, vol. 39, no. 6, pp. 8557-8564, 2020

Authors: Quadir, Md Abdul | Christy Jackson, J. | Prassanna, J. | Sathyarajasekaran, K. | Kumar, K. | Sabireen, H. | Ubarhande, Shivam | Vijaya Kumar, V.

Article Type: Research Article

Abstract: Domain name system (DNS) plays a critical part in the functioning of the Internet. But since DNS queries are sent using UDP, it is vulnerable to Distributed Denial of Service (DDoS) attacks. The attacker can take advantage of this and spoof the source IP address and direct the response towards the victim network. And since the network does not keep track of the number of requests going out and responses coming in, the attacker can flood the network with these unwanted DNS responses. Along with DNS, other protocols are also exploited to perform DDoS. Usage of Network Time Protocol (NTP) …is to synchronize clocks on systems. Its monlist command replies with 600 entries of previous traffic records. This response is enormous compared to the request. This functionality is used by the attacker in DDoS. Since these attacks can cause colossal congestion, it is crucial to prevent or mitigate these types of attacks. It is obligatory to discover a way to drop the spoofed packets while entering the network to mitigate this type of attack. Intelligent cybersecurity systems are designed for the detection of these attacks. An Intelligent system has AI and ML algorithms to achieve its function. This paper discusses such intelligent method to detect the attack server from legitimate traffic. This method uses an algorithm that gets activated by excess traffic in the network. The excess traffic is determined by the speed or rate of the requests and responses and their ratio. The algorithm extracts the IP addresses of servers and detects which server is sending more packets than requested or which are not requested. This server can be later blocked using a firewall or Access Control List (ACL). Show more

Keywords: Amplification attacks, DRDoS, domain name system, network time protocol

DOI: 10.3233/JIFS-189173

Citation: Journal of Intelligent & Fuzzy Systems, vol. 39, no. 6, pp. 8565-8572, 2020

Authors: Sengan, Sudhakar | Priya, V. | Syed Musthafa, A. | Ravi, Logesh | Palani, Saravanan | Subramaniyaswamy, V.

Article Type: Research Article

Abstract: Breast cancer should be diagnosed as early as possible. A new approach of the diagnosis using deep learning for breast cancer and the particular process using segmentation strategies presented in this article. Medical imagery is an essential tool used for both diagnosis and treatment in many fields of medical applications. But, it takes specially trained medical specialists to read medical images and make diagnoses or treatment decisions. New practices of interpreting medical images are labour exhaustive, time-wasting, expensive, and prone to error. Using a computer-aided program which can render diagnosis and treatment decisions automatically would be more beneficial. A new …computer-based detection method for the classification between compassionate and malignant mass tumours in mammography images of the breast proposed. (a) We planned to determine how to use the challenging definition, which produces severe examples that boost the segmentation of mammograms. (b) Employing well designing multi-instance learning through deep learning, we validated employing inadequately labelled data of breast cancer diagnosis using a mammogram. (c) The study is going through the Deep Lung method incorporating deep multi-dimensional automated identification and classification of the lung nodule. (d) By combining a probabilistic graphic model in deep learning, it authorizes how weakly labelled data can be used to improve the existing breast cancer identification method. This automated system involves manually defining the Region Of Interest (ROI), with the region and threshold values based on the next region. The High-Resolution Multi-View Deep Convolutional Neural Network (HRMP-DCNN) mainly developed for the extraction of function. The findings collected through the subsequent in available public databases like mammography screening information database and DDSM Curated Breast Imaging Subset. Ultimately, we’ll show the VGG that’s thousands of times quicker, and it is more reliable than earlier programmed anatomy segmentation. Show more

Keywords: Deep convolutional neural network, computer-based automated detection, breast cancer screening, deep learning, machine learning, mammography, fuzzy logic.

DOI: 10.3233/JIFS-189174

Citation: Journal of Intelligent & Fuzzy Systems, vol. 39, no. 6, pp. 8573-8586, 2020