Journal of Intelligent Systems and Internet of Things

Journal DOI

Submit Your Paper

2690-6791ISSN (Online) 2769-786XISSN (Print)

Trust Aware Moth Flame Optimization based Secure Clustering for Wireless Sensor Networks

Abdul Rahaman Wahab Sait , M. Ilayaraja

Wireless sensor networks (WSN) encompass numerous sensor nodes deployed in the physical environment to sense parameters and transmit to the base station (BS). Since the nodes in WSN communicate via a wireless channel, security remains a significant issue that needs to be resolved. The choice of cluster heads (CHs) is critical to achieving secure data transmission in WSN. In this aspect, this article presents a novel trust-aware mothflame optimization-based secure clustering (TAMFO-SC) technique for WSN. The goal of the TAMFO-SC technique is to determine the trust level of the nodes and determine the secure CHs. The proposed TAMFO-SC technique initially determines the nodes' trust level, and the node with maximum trust factor can be chosen as CHs. In addition, the TAMFO-SC technique derives a fitness function using two parameters, namely residual energy and trust level. The inclusion of trust level in the CH selection process helps to accomplish security in WSN. A comprehensive experimental analysis exhibits the promising performance of the TAMFO-SC technique over the other compared methods. 

Read More


Vol. 0 Issue. 2 PP. 54-64, (2019)

MSJEP Classifier: “Modified Strong Jumping Emerging Patterns” for Fast Efficient Mining and for handling attributes whose values are associated with taxonomies

Mohammed K. Hassan , Ahmed K. Hassan , Ali I. Eldesouky

Modified Strong Jumping Emerging Patterns (MSJEPs) are those itemsets whose support increases from zero in one data set to non-zero in the other dataset with support constraints greater than the minimum support threshold (ζ). The support constraint of MSJEP removes potentially less useful JEPs while retaining those with high discriminating power. Contrast Pattern (CP)-tree-based discovery algorithm used for SJEP mining is a main-memory-based method. When the data set is large, it is unrealistic to assume that the CP-tree can fit in the main memory. The main idea to handle this problem is to first partition the data set into a set of projected data sets and then for each projected data set, we construct and mine its corresponding CP-tree. Trees of the projected data sets are called Separated Contrast Pattern Tree “SCP-trees”  and Patterns generated from it are Called MSJEPs” Modified Strong Jumping Emerging Patterns”.  Our proposal also investigates the weakness of emerging patterns in handling attributes whose values are associated with taxonomies and proposes using an MSJEP classifier to achieve better accuracy, better speed, and also handling attributes in taxonomy.

Read More


Vol. 0 Issue. 2 PP. 37-53, (2019)

Intelligent Differential Evolution based Feature Selection with Deep Neural Network for Intrusion Detection in Wireless Sensor Networks

Ibrahim M. EL-Hasnony

Wireless sensor network (WSN) is mainly utilized for data gathering and surveillance applications. As WSN is majorly deployed in harsh and hostile environments, security remains a critical issue which needs to be resolved. An intrusion detection system (IDS) is one of the proficient ways used to determine the presence of abnormal behaviors (i.e. intrusions) in the network. Earlier studies have focused on the design of machine learning (ML) and deep learning (ML) models to design IDS. With this motivation, this paper presents an intelligent differential evolution based feature selection with deep neural network (IDEFS-DNN) for intrusion detection in WSN. The proposed IDEFS-DNN model aims to select optimum set of features and classify the intrusions in the network. In addition, the IDEFS-DNN technique involves the design of IDEFS technique to choose a subset of optimum features. Moreover, the chosen features are fed into the DNN technique for classification purposes. The usage of IDEFS technique helps to reduce the complexity and increase the classifier outcome. In order to portray the improved performance of the IDEFS-DNN technique, wide ranging experiments take place on benchmark datasets and the results are inspected under varying aspects. The simulation results ensured the enhanced intrusion detection performance of the IDEFS-DNN technique over the other IDS models.

Read More


Vol. 0 Issue. 2 PP. 78-89, (2019)

IoT-Based Health Monitoring System with Real-Time Analytics

Salah-ddine Krit

Thanks to advances in nanodevices and internet technology, it is now possible for devices from different manufacturers to be connected and communicate with one another. Among the fields that benefited from this technology integration were healthcare and general well-being. Healthcare had been established to lower healthcare expenses and offer enhanced and dependable services. Nevertheless, the primary difficulty in building such systems has continually been ensuring a high quality of service (QoS) in terms of quicker reaction and complicated analysis of data, given the sensitive and medical data. To solve these problems, this article suggests a heterogeneous Health Monitoring System built on mist, fog, and the cloud that can process and route data in both immediately and in form of a batch. In addition, the proposed system uses software-defined networking and load-stabilizing method to make sure that all available resources are being used effectively and efficiently.  Experimental simulations validated that our system could achieve excellent QoS, with acceptable delay and packet delivery rate, which is crucial for the creation of sustainable healthcare solutions.

Read More


Vol. 0 Issue. 2 PP. 90-99, (2019)