·         Table of Contents (Volume #6, Issue #3)

·         Cover Page (Volume #6, Issue #3)

·         Editorial (Volume #6, Issue #3)

Paper #1

Performance Limits of 433 MHz Quarter-wave Monopole Antennas due to Grounding Dimension and Conductivity

Jinfeng Li

Abstract: Among antennas for Industrial, Scientific and Medical (ISM band) applications at 433 MHz, quarter-wave monopole is a reasonably good trade-off between size, gain, and cost. The electrical performance of the monopole is largely dependent on the quality of the ground plane (size and conductivity), which exhibits a practical limit on the achievable gain as most industrial user environments can provide only a finite ground plane of finite electrical conductivity. Establishing traceability in understanding the performance degradation due to such limits due to the grounding dimension and conductivity is becoming mandatory. To this end, this work leverages universal MATLAB in place of off-the-shelf software (HFSS or CST) for the quarter-wave monopole antenna simulation at 433 MHz parametrised with the ground plane’s dimension with respect to the wavelength (λ). Results indicate that by enlarging the ground plane’s size from 0.14 λ to 14 λ, the gain (directivity for PEC) from the 3D radiation pattern rises from 1.79 dBi, then starts levelling off at 6.7 dBi (5.78 λ), until saturating at 7.49 dBi (13 λ). The radiation efficiency and gain of various grounding conductivity scenarios (e.g., gold, aluminium, steel) are also quantified to inform antenna designers and engineers for commercial, industrial, defence and space applications.

Keywords: antenna gain; antenna grounding; antenna modelling; antenna simulation; antenna optimisation; ISM band; MATLAB; monopole antenna; 433 MHz.

Download Full Text

Paper #2

Analysis of Intelligent English Chunk Recognition based on Knowledge Corpus

Mei Zhang

Abstract: Chunks play an important role in applied linguistics, such as Teaching English as a Second Language (TESL) and Computer-Aided Translation (CAT). Although corpora have already been widely used in the areas mentioned above, annotation and recognition of chunks are mainly done manually. Computer- and linguistic-based chunk recognition is significant in natural language processing (NLP). This paper briefly introduced the intelligent recognition of English chunks and applied the Recurrent Neural Network (RNN) to recognise chunks. To strengthen the RNN, it was improved by Long Short Term Memory (LSTM) for recognising English chunk. The LSTM-RNN was compared with support vector machine (SVM) and RNN in simulation experiments. The results suggested that the performance of the LSTM-RNN was always the highest when dealing with English texts, no matter whether it was trained using a general corpus or a corpus of specialised domain knowledge.

Keywords: applied linguistics; chunk recognition; corpus; recurrent neural network.

Download Full Text

Paper #3

Comparative Analysis of Intrusion Detection System Using Machine Learning and Deep Learning Algorithms

Johan Note and Maaruf Ali

Abstract: Attacks against computer networks, “cyber-attacks”, are now common place affecting almost every Internet connected device on a daily basis. Organisations are now using machine learning and deep learning to thwart these types of attacks for their effectiveness without the need for human intervention. Machine learning offers the biggest advantage in their ability to detect, curtail, prevent, recover and even deal with untrained types of attacks without being explicitly programmed. This research will show the many different types of algorithms that are employed to fight against the different types of cyber-attacks, which are also explained. The classification algorithms, their implementation, accuracy and testing time are presented. The algorithms employed for this experiment were the Gaussian Naïve-Bayes algorithm, Logistic Regression Algorithm, SVM (Support Vector Machine) Algorithm, Stochastic Gradient Descent Algorithm, Decision Tree Algorithm, Random Forest Algorithm, Gradient Boosting Algorithm, K-Nearest Neighbour Algorithm, ANN (Artificial Neural Network) (here we also employed the Multilevel Perceptron Algorithm), Convolutional Neural Network (CNN) Algorithm and the Recurrent Neural Network (RNN) Algorithm. The study concluded that amongst the various machine learning algorithms, the Logistic Regression and Decision tree classifiers all took a very short time to be implemented giving an accuracy of over 90% for malware detection inside various test datasets. The Gaussian Naïve-Bayes classifier, though fast to implement, only gave an accuracy between 51-88%. The Multilevel Perceptron, non-linear SVM and Gradient Boosting algorithms all took a very long time to be implemented. The algorithm that performed with the greatest accuracy was the Random Forest Classification algorithm.

Keywords: cyber-attack; cyber defence; deep learning; intrusion detection system; machine learning.

Download Full Text

Paper #4

Dynamic Context Driven Re-configurable Business Process

Priyanka Chakraborty and Anirban Sarkar

Abstract: The building of a re-configurable business process (BP) has gained importance in business organizations. It helps the organization to adapt to the agility in business goals. A proper context-driven re-configurable BP should be capable of integrating dynamic context information. However, this is absent in the existing studies. As a result, providing a suitable, expressive and re-configurable BP to the business organization stakeholders has become a challenging issue. The prevailing research works lack the proper consideration and suitable incorporation of the context-driven services to make a BP re-configurable. And then it can quickly respond and change its behavior to adapt to the rapid and unpredictable changing business environment. In addition, those methods hardly come up with any appropriate technique to use the set of specified goals to extract context-driven services. Those business goals are determined by the group of stakeholders of a business organization. This paper proposes a new method of re-configuring context-driven from a defined goal to sort out these vital challenges. Present context data is included in an existing BP to achieve a modified goal which immensely benefits the end-users. Thus, this approach is intrinsically highly user-centric, reusable, fast and inexpensive. To achieve this, an algorithm called Context-driven Re-configurable Business Process Achievement Algorithm (CDRBPA) is introduced and implemented. Based on Primary Context (PC), three software metrics, namely, Degree of re-usability (DRUPC), Degree of re-appropriation (DRAPC) and Degree of re-configurability (DRPC) have been proposed to measure the modifications done to the existing BP. In conclusion, various case studies with different complexities have been performed to show the strength of the proposed algorithm.

Keywords: Context-driven Re-configurable business process; Degree of re-usability; Degree of re-appropriation; Degree of re-configurability; context-driven services.

Download Full Text

Paper #5

An Edge Computing Environment for Early Wildfire Detection

Ahmed Saleem Mahdi and Sawsen Abdulhadi Mahmood

Abstract: Recently, an increasing demand is growing for installing a rapid response system in forest regions to enable an immediate and appropriate response to wildfires before they spread across vast areas. This paper introduces a multilevel system for early wildfire detection to support public authorities to immediately specify and attend to emergency demands. The presented work is designed and implemented within Edge Computing Infrastructure. At the first level; the dataset samples of wildfire represented by a set of video sequences are collected and labelled for training mode purposes. Then, YOLOv5 deep learning model is adopted in our framework to build a trained model for distinguishing the fire event against non-fire events in binary classification. The proposed system structure comprises IoT entities provided with camera sensor capabilities and NVIDIA Jetson Nano Developer kit as an edge computing environment. At the first level, a video camera is employed to assemble environment information received by the micro-controller middle level to handle and detect the possible fire event presenting in the interested area. The last level is characterized as making a decision by sending a text message and snapshot images to the cloud server. Meanwhile, a set of commands are sent to IoT nodes to operate the speakers and sprinklers, which are strategically assumed to place on the ground to give an alarm and prevent wildlife loss. The proposed system was tested and evaluated using a wildfire dataset constructed by our efforts. The experimental results exhibited 98% accurate detection of fire events in the video sequence. Further, a comparison study is performed in this research to confirm the results obtained from recent methods.

Keywords: Early Wildfire Detection System; Edge Computing; Jetson Nano; YOLOv5.

Download Full Text

Paper #6

A Novel Data Aggregation Mechanism using Reinforcement Learning for Cluster Heads in Wireless Multimedia Sensor Networks

Jia Uddin

Abstract: Wireless multimedia sensor networks (WMSNs) are getting used in numerous applications nowadays. Many robust energy-efficient routing protocols have been proposed to handle multimedia traffic-intensive data like images and videos in WMSNs. It is a common trend in the literature to facilitate a WMSN with numerous sinks allowing cluster heads (CHs) to distribute the collected data to the adjacent sink node for delivery overhead mitigation. Using multiple sink nodes can be expensive and may incur high complexity in routing. There are many single-sink cluster-based routing protocols for WMSNs that lack in introducing optimal path selection among CHs. As a result, they suffer from transmission and queueing delay due to high data volume. To address these two conflicting issues, we propose a data aggregation mechanism based on reinforcement learning (RL) for CHs (RL-CH) in WMSN. The proposed method can be integrated to any of the cluster-based routing protocol for intelligent data transmission to sink node via cooperative CHs. Proposed RL-CH protocol performs better in terms of energy-efficiency, end-to-end delay, packet delivery ratio, and network lifetime. It gains 17.6% decrease in average end-to-end delay and 7.7% increase in PDR along with a network lifetime increased to 3.2% compared to the evolutionary game-based routing protocol which has been used as baseline.

Keywords: Cluster head; Routing protocols; Reinforcement learning; Wireless multimedia sensor networks.

Download Full Text