+48 22 5128 100  

Szachowa 1,
04-894 Warszawa

Journal of Telecommunications and Information Technology (JTIT) - 1/2022

Kang Leng Chiew, Josef Pieprzyk
Inspiring Technologies for Digital Inclusivity
[ Bibtex Plain ]
Wan Nural Jawahir Hj Wan Yussof, Mustafa Man, Roslan Umar, Ahmad Najmuddin Zulkeflee, Ezmahamrul Afreen Awalludin and Nazhatulshima Ahmad
Enhancing Moon Crescent Visibility Using Contrast-Limited Adaptive Histogram Equalization and Bilateral Filtering Techniques
Image enhancement is becoming increasingly important with the advancement of space exploration techniques and the technological development of more durable and scientifically sound observatories equipped with more powerful telescopes. The enhancement of images helps astronomers analyze the results and act toward determining the dates of religious festivals. This work describes a technique known as contrast-limited adaptive histogram equalization (CLAHE) with grayscale contrast enhancement and bilateral filtering. We apply CLAHE on the L component of the CIE-Lab color space to adjust lightness contrast. Subsequently, grayscale contrast enhancement is performed to increase the visibility of the moon crescent. Noise caused by grayscale contrast enhancement is reduced using bilateral filtering. Two quantitative measures are selected (PSNR and MSE) to show the visual improvement achieved by the proposed algorithm.
[ Bibtex Plain ]
Hui Hui Wang and Sze Ye Chai
Novel Feature Extraction for Pineapple Ripeness Classification
A novel feature extraction method has been proposed to improve the accuracy of the pineapple ripeness classification process. The methodology consists of six stages, namely: image acquisition, image pre-processing, color extraction, feature selection, classification and evaluation of results. The red element in the RGB model is selected as the threshold value parameter. The ripeness of pineapples is determined based on the percentage share of yellowish scales visible in images presenting the front and the back side of the fruit. The prototype system is capable of classifying pineapples into three main groups: unripe, ripe, and fully ripe. The accuracy of 86.05% has been achieved during experiments.
[ Bibtex Plain ]
Ezmahamrul Afreen Awalludin, Tengku Noorfarahana T. Arsad, Wan Nural Jawahir Hj Wan Yussof, Zainudin Bachok and Muhammad Suzuri Hitam
A Comparative Study of Various Edge Detection Techniques for Underwater Images
Nowadays, underwater image identification is a challenging task for many researchers focusing on various applications, such as tracking fish species, monitoring coral reef species, and counting marine species. Because underwater images frequently suffer from distortion and light attenuation, pre-processing steps are required in order to enhance their quality. In this paper, we used multiple edge detection techniques to determine the edges of the underwater images. The pictures were pre-processed with the use of specific techniques, such as enhancement processing, Wiener filtering, median filtering and thresholding. Coral reef pictures were used as a dataset of underwater images to test the efficiency of each edge detection method used in the experiment. All coral reef image datasets were captured using an underwater GoPro camera. The performance of each edge detection technique was evaluated using mean square error (MSE) and peak signal to noise ratio (PSNR). The lowest MSE value and the highest PSNR value represent the best quality of underwater images. The results of the experiment showed that the Canny edge detection technique outperformed other approaches used in the course of the project.
[ Bibtex Plain ]
Adriana Ganum, D. N. F. Awang Iskandar, Lim Phei Chin and Ahmad Hadinata Fauzi
Detection of Monocrystalline Silicon Wafer Defects Using Deep Transfer Learning
Defect detection is an important step in industrial production of monocrystalline silicon. Through the study of deep learning, this work proposes a framework for classifying monocrystalline silicon wafer defects using deep transfer learning (DTL). An existing pre-trained deep learning model was used as the starting point for building a new model. We studied the use of DTL and the potential adaptation of MobileNetV2 that was pre-trained using ImageNet for extracting monocrystalline silicon wafer defect features. This has led to speeding up the training process and to improving performance of the DTL-MobileNetV2 model in detecting and classifying six types of monocrystalline silicon wafer defects (crack, double contrast, hole, microcrack, saw-mark and stain). The process of training the DTL-MobileNetV2 model was optimized by relying on the dense block layer and global average pooling (GAP) method which had accelerated the convergence rate and improved generalization of the classification network. The monocrystalline silicon wafer defect classification technique relying on the DTL-MobileNetV2 model achieved the accuracy rate of 98.99% when evaluated against the testing set. This shows that DTL is an effective way of detecting different types of defects in monocrystalline silicon wafers, thus being suitable for minimizing misclassification and maximizing the overall production capacities.
[ Bibtex Plain ]
Steve Olsen Michael, Sarah Samson Juan and Edwin Mit
Preliminary Evaluation of Convolutional Neural Network Acoustic Model for Iban Language Using NVIDIA NeMo
For the past few years, artificial neural networks (ANNs) have been one of the most common solutions relied upon while developing automated speech recognition (ASR) acoustic models. There are several variants of ANNs, such as deep neural networks (DNNs), recurrent neural networks (RNNs), and convolutional neural networks (CNNs). A CNN model is widely used as a method for improving image processing performance. In recent years, CNNs have also been utilized in ASR techniques, and this paper investigates the preliminary result of an end-to-end CNN-based ASR using NVIDIA NeMo on the Iban corpus, an under-resourced language. Studies have shown that CNNs have also managed to produce excellent word error (WER) rates for the acoustic model on ASR for speech data. Conversely, results and studies concerned with under-resourced languages remain unsatisfactory. Hence, by using NVIDIA NeMo, a new ASR engine developed by NVIDIA, the viability and the potential of this alternative approach are evaluated in this paper. Two experiments were conducted: the number of resources used in the works of our ASR’s training was manipulated, as was the internal parameter of the engine used, namely the epochs. The results of those experiments are then analyzed and compared with the results shown in existing papers.
[ Bibtex Plain ]
Syazwanie Filzah binti Zulkifli, Cheah Waishiang, Muhammad Asyraf bin Khairuddin, Nurfauza binti Jali and Yanti Rosmunie binti Bujang
How to Model an Engaging Online Quiz? The Emotion Modeling Approach
The article focuses on software technology used to provide a more engaging and exciting learning environment for students by introducing a variety of quizzes. Presently, quiz development can range from simple multiple-choice questions, true or false, drag-and-drop, dropdown menu selections, to 3D interactive techniques. This study introduces a systematic way of creating an engaging application using emotion modeling. Emotion models are being introduced in order to collect and model the systems’ meaningful emotional needs. According to the findings, agent-oriented modeling is capable of modeling the emotional requirements of a system and of transforming these into a specific solution enabling to rapidly prototype an engaging system. A quantitative study has been performed on the novel approach to determine the feasibility of the proposed methodology in terms of analyzing, designing, and developing engaging applications.
[ Bibtex Plain ]
Rafia Afzal and Raja Kumar Murugesan
Implementation of a Malicious Traffic Filter Using Snort and Wireshark as a Proof of Concept to Enhance Mobile Network Security
In the 1970s, roaming interconnections for cellular networks were designed for a few trusted parties. Hence, security was not a major concern. Today, the SS7 (Signaling System no. 7) solution that is several decades old is still used for many roaming interconnections. SS7 has been proven vulnerable to serious threats due to deregulation, expansion, and convergence with IP-based Long Term Evolution (LTE) networks. The limitations of the SS7 network that it is unable to check the subscriber’s authentic location, verify their identity and filter illegitimate messages, makes the system vulnerable to attacks. Adversaries taking advantage of these shortcomings can inflict threats such as interception of calls and text messages, subscriber tracking and denial of service attacks. Although LTE and Diameter signaling protocols promise enhanced security keeping up with the latest attack vectors, their inherent flaws related to roaming interconnections are still there and continue to make the networks vulnerable. Hence, a highly secure signaling network is required to protect the operators and the subscribers from a diverse range of security attacks. SS7 network protocol layers, such as signaling connection control part (SCCP), transaction capabilities application part (TCAP), and global system for mobile Communications – mobile application part (GSM MAP), manage connectivity between networks and subscribers. An analysis of the parameters of these layers may provide a clear insight into any anomalies present. Unfortunately, these parameters are not validated and verified at the network’s edge. The major contribution of this research is a methodology for detecting anomalies by checking malformed parameters and intra-layer parameter discrepancies at the abovementioned protocol layers. This paper provides an insight into the severity of SS7 network security vulnerabilities. Furthermore, it provides a proof of concept for the analysis of SS7 network traffic using the Wireshark packet capture tool and the Snort intrusion detection system (IDS) capable of detecting malicious traffic patterns.
[ Bibtex Plain ]
Jyoti P. Patra, Bibhuti Bhusan Pradhan and Poonam Singh
A DFT-based Low Complexity LMMSE Channel Estimation Technique for OFDM Systems
The linear minimum mean square error (LMMSE) channel estimation technique is often employed in orthogonal frequency division multiplexing (OFDM) systems because of its optimal performance in the mean square error (MSE) performance. However, the LMMSE method requires cubic complexity of order O(N 3 p ), where Np is the number of pilot subcarriers. To reduce the computational complexity, a discrete Fourier transform (DFT) based LMMSE method is proposed in this paper for OFDM systems in the frequency selective channel. To validate the proposed method, the closed form mean square error (MSE) expression is also derived. Finally, a computer simulation is carried out to compare the performance of the proposed LMMSE method with the classical LS and LMMSE methods in terms of bit error rate (BER) and computational complexity. Results of the simulation show that the proposed LMMSE method achieves exactly the same performance as the conventional LMMSE method, with much lower computational complexity.
[ Bibtex Plain ]
Ravi Shankar, V. V. Raghava Raman, Kantilal Pitamber Rane, Sarojini B. K. and Rahul Neware
An Investigation of the MIMO Space Time Block Code Based Selective Decode and Forward Relaying Network over η–µ Fading Channel Conditions
In this paper, we examine the end-to-end average pairwise error probability (PEP) and output probability (OP) performance of the maximum ratio combining (MRC) based selective decode and forward (S-DF) system over an η–µ scattering environment considering additive white Gaussian noise (AWGN). The probability distribution function (PDF) and cumulative distribution function (CDF) expressions have been derived for the received signal-to-noise (SNR) ratio and the moment generating function (MGF) technique is used to derive the novel closed-form (CF) average PEP and OP expressions. The analytical results have been further simplified and are presented in terms of the Lauricella function for coherent complex modulation schemes. The asymptotic PEP expressions are also derived in terms of the Lauricella function, and a convex optimization (CO) framework has been developed for obtaining optimal power allocation (OPA) factors. Through simulations, it is also proven that, depending on the number of multi-path clusters and the modulation scheme used, the optimized power allocation system was essentially independent of the power relation scattered waves from the source node (SN) to the destination node (DN). The graphs show that asymptotic and accurate formulations are closely matched for moderate and high SNR regimes. PEP performance significantly improves with an increase in the value of η for a fixed value of µ. The analytical and simulation curves are in close agreement for medium-to-high SNR values.
[ Bibtex Plain ]
Ali Djebbari and Sid Ahmed Elahmar
Improved CSE with DLS-MMSE Criteria in TH-UWB System
This article presents a study on the use of deterministic least squares criteria combined with the minimum mean square error method for the purpose of computing filter coefficients of the channel shortening equalizer. This method is well known to alleviate inter-symbol interference in time hopping UWB systems. The validity of this method is applied to shorten the impulse response of the effective UWB channels and, therefore, reduce the complexity of the rake receiver. Results show a very promising advantage compared to partialrake (P-Rake), selective-rake (S-Rake) and optimal maximum shortening signal-to-noise ratio methods.
[ Bibtex Plain ]
Prasanna K. Kumar, Lakshman Pappula, B. T. P. Madhav and V. S. V. Prabhakar
Unequally Spaced Antenna Array Synthesis Using Accelerating Gaussian Mutated Cat Swarm Optimization
Low peak sidelobe level (PSLL) and antenna arrays with high directivity are needed nowadays for reliable wireless communication systems. Controlling the PSLL is a major issue in designing effective antenna array systems. In this paper, a nature inspired technique, namely accelerating Gaussian mutated cat swarm optimization (AGMCSO) that attributes global search abilities, is proposed to control PSLL in the radiation pattern. In AGM-SCO, Gaussian mutation with an acceleration parameter is used in the position-updated equation, which allows the algorithm to search in a systematic way to prevent premature convergence and to enhance the speed of convergence. Experiments concerning several benchmark multimodal problems have been conducted and the obtained results illustrate that AGMCSO shows excellent performance concerning evolutionary speed and accuracy. To validate the overall efficacy of the algorithm, a sensitivity analysis was performed for different AGMCSO parameters. AGMCSO was researched on numerous linear, unequally spaced antenna arrays and the results show that in terms of generating low PSLL with a narrow first null beamwidth (FNBW), AGMCSO outperforms conventional algorithms.
[ Bibtex Plain ]