·         Table of Contents (Volume #6, Issue #2)

·         Cover Page (Volume #6, Issue #2)

·         Editorial (Volume #6, Issue #2)

Paper #1

High Synthetic Audio Compression Model Based on Fractal Audio Coding and Error-Compensation

Ahmed Hussain Ali and Loay Edwar George

Abstract: This study presented a model for improving audio files quality using fractal coding specifically when a high compression ratio is required. The proposed high synthetic audio compression model which can be called (HSACM) is based on conventional fractal coding and lifting wavelet transform. Various lifting wavelet transform families and levels are used and their effects on the reconstructed audio files are discussed as well. Audio files from GTZAN dataset and standard measurements for data compression are used in the evaluation of the proposed model. The results reveal that using block length 50 samples which is the worst case, PSNR is increased, on average, from 34.1 to 44.8 dB and from 34.1 to 40.5 dB using lifting wavelet transform with 3 and 2 levels, respectively. Thus, the PSNR is improved by 10 and 5 dB with slightly reducing the compression ratio by 6.2 and 12.5%, respectively. Moreover, it can be noticed that adopting lifting wavelet transform with basis Haar, db1, db4, db5, cdf1.1 and cdf2.2 provide higher audio quality while db6, db8, sym7 and sym8 give the worst audio quality. Furthermore, the performance of HSACM is compared with that of existing work to highlight its performance.

Keywords: Audio Compression; Audio Quality; Fractal Audio Coding; Lifting Wavelet Transform.

Download Full Text

Paper #2

Machine Learning and Artificial Intelligence in Circular Economy: A Bibliometric Analysis and Systematic Literature Review

Abdulla All Noman, Umma Habiba Akter, Tahmid Hasan Pranto and AKM Bahalul Haque

Abstract: With unorganized, unplanned and improper use of limited raw materials, an abundant amount of waste is being produced, which is harmful to our environment and ecosystem. While traditional linear production lines fail to address far-reaching issues like waste production and a shorter product life cycle, a prospective concept, namely circular economy (CE), has shown promising prospects to be adopted at industrial and governmental levels. CE aims to complete the product life cycle loop by bringing out the highest values from raw materials in the design phase and later on by reusing, recycling, and remanufacturing. Innovative technologies like artificial intelligence (AI) and machine learning(ML) provide vital assistance in effectively adopting and implementing CE in real-world practices. This study explores the adoption and integration of applied AI techniques in CE. First, we conducted bibliometric analysis on a collection of 104 SCOPUS indexed documents exploring the critical research criteria in AI and CE. Forty papers were picked to conduct a systematic literature review from these documents. The selected documents were further divided into six categories: sustainable development, reverse logistics, waste management, supply chain management, recycle & reuse, and manufacturing development. Comprehensive research insights and trends have been extracted and delineated. Finally, the research gap needing further attention has been identified and the future research directions have also been discussed.

Keywords: Artificial Intelligence; Bibliometric Analysis; Circular Economy; Machine Learning; Systematic Literature Review.

Download Full Text

Paper #3

Soft Voting-based Ensemble Model for Bengali Sign Gesture Recognition

Md Abdur Rahim, Jungpil Shin and Keun Soo Yun

Abstract: Human hand gestures are becoming one of the most important, intuitive, and essential means of recognizing sign language. Sign language is used to convey different meanings through visual-manual methods. Hand gestures help the hearing impaired to communicate. Nevertheless, it is very difficult to achieve a high recognition rate of hand gestures due to the environment and physical anatomy of human beings such as light condition, hand size, position, and uncontrolled environment. Moreover, the recognition of appropriate gestures is currently considered a major challenge. In this context, this paper proposes a probabilistic soft voting-based ensemble model to recognize Bengali sign gestures. We have divided this study into pre-processing, data augmentation and ensemble model-based voting process, and classification for gesture recognition. The purpose of pre-processing is to remove noise from input images, resize it, and segment hand gestures. Data augmentation is applied to create a larger database for in-depth model training. Finally, the ensemble model consists of a support vector machine (SVM), random forest (RF), and convolution neural network (CNN) is used to train and classify gestures. Whereas, the ReLu activation function is used in CNN to solve neuron death problems and to accelerate RF classification through principal component analysis (PCA). A Bengali Sign Number Dataset named “BSN-Dataset” is proposed for model performance. The proposed technique enhances sign gesture recognition capabilities by utilizing segmentation, augmentation, and soft-voting classifiers which have obtained an average of 99.50% greater performance than CNN, RF, and SVM individually, as well as significantly more accuracy than existing systems.

Keywords: Augmentation; Convolutional Neural Network (CNN); Deep ensemble; Hand gesture; Sign Language; Support Vector Machine (SVM); Random Forest (RF).

Download Full Text

Paper #4

Speeding Up Fermat’s Factoring Method using Precomputation

Hatem M. Bahig

Abstract: The security of many public-key cryptosystems and protocols relies on the difficulty of factoring a large positive integer n into prime factors. The Fermat factoring method is a core of some modern and important factorization methods, such as the quadratic sieve and number field sieve methods. It factors a composite integer n=pq in polynomial time if the difference between the prime factors is equal to ?=p-q=n^(0.25) , where p>q. The execution time of the Fermat factoring method increases rapidly as ? increases. One of the improvements to the Fermat factoring method is based on studying the possible values of (n mod 20). In this paper, we introduce an efficient algorithm to factorize a large integer based on the possible values of (n mod 20) and a precomputation strategy. The experimental results, on different sizes of n and ?, demonstrate that our proposed algorithm is faster than the previous improvements of the Fermat factoring method by at least 48%.

Keywords: Fermat’s Factoring Method; Integer Factorization; Precomputation; Public-key Cryptosystem; RSA.

Download Full Text

Paper #5

Examining Mental Disorder/Psychological Chaos through Various ML and DL Techniques: A Critical Review

Afra Binth Osman, Faria Tabassum, Muhammed J. A. Patwary, Ahmed Imteaj, Touhidul Alam, Mohammad Arif Sobhan Bhuiyan and Mahdi H. Miraz

Abstract: Mental health is a state of well-being where a person understands his/her potential, participates in his or her community and is able to deal effectively with the challenges and obstacles of everyday life. It circumscribes how an individual thinks, feels and responds to any circumstances. Mental stress has now become a social issue and it has the potential to create functional incapacity at work. Chronic stress may also be linked with several physiological illnesses. The purpose of this study is to review existing research of mental health outcomes where various machine learning (ML) and deep learning (DL) algorithms have been applied. Applying our exclusion and inclusion criteria, 46 articles were finally selected from the search results obtained from various research databases and repositories. This literature on ML and mental health outcomes provides an account of the state-of-the-art techniques developed and used in this domain. The review also compares and contrasts amongst various models based on deep learning that can predict a user’s mental condition based on different types of data such as social media data, clinical data, etc. Finally, the open issues and future challenges of utilising deep learning algorithms to better understand and diagnose mental health of any individual were discussed. From the literature survey, this is evident that the use of ML and DL in mental health has yielded a number of benefits in the areas of diagnosis, therapy, support, research and clinical administration.

Keywords: DL; Mental Disorders; ML; Social Media; Stress; Suicide.

Download Full Text