Shamim Al Mamun

Bio: Shamim Al Mamun is an academic researcher from Jahangirnagar University. The author has contributed to research in topics: Wheelchair & Cloud computing. The author has an hindex of 10, co-authored 44 publications receiving 428 citations. Previous affiliations of Shamim Al Mamun include Saitama University.

Application of deep learning in detecting neurological disorders from magnetic resonance images: a survey on the detection of Alzheimer’s disease, Parkinson’s disease and schizophrenia

Abstract: Neuroimaging, in particular magnetic resonance imaging (MRI), has been playing an important role in understanding brain functionalities and its disorders during the last couple of decades. These cutting-edge MRI scans, supported by high-performance computational tools and novel ML techniques, have opened up possibilities to unprecedentedly identify neurological disorders. However, similarities in disease phenotypes make it very difficult to detect such disorders accurately from the acquired neuroimaging data. This article critically examines and compares performances of the existing deep learning (DL)-based methods to detect neurological disorders—focusing on Alzheimer’s disease, Parkinson’s disease and schizophrenia—from MRI data acquired using different modalities including functional and structural MRI. The comparative performance analysis of various DL architectures across different disorders and imaging modalities suggests that the Convolutional Neural Network outperforms other methods in detecting neurological disorders. Towards the end, a number of current research challenges are indicated and some possible future research directions are provided.

Detecting Neurodegenerative Disease from MRI: A Brief Review on a Deep Learning Perspective

Abstract: Rapid development of high speed computing devices and infrastructure along with improved understanding of deep machine learning techniques during the last decade have opened up possibilities for advanced analysis of neuroimaging data. Using those computing tools Neuroscientists now can identify Neurodegenerative diseases from neuroimaging data. Due to the similarities in disease phenotypes, accurate detection of such disorders from neuroimaging data is very challenging. In this article, we have reviewed the methodological research papers proposing to detect neurodegenerative diseases using deep machine learning techniques only from MRI data. The results show that deep learning based techniques can detect the level of disorder with relatively high accuracy. Towards the end, current challenges are reviewed and some possible future research directions are provided.

A Neuro-Fuzzy Control System Based on Feature Extraction of Surface Electromyogram Signal for Solar-Powered Wheelchair

Abstract: This paper presents the design and implementation of a low-cost solar-powered wheelchair for physically challenged people. The signals necessary to maneuver the wheelchair are acquired from different muscles of the hand using surface electromyography (sEMG) technique. The raw sEMG signals are collected from the upper limb muscles which are then processed, characterized, and classified to extract necessary features for the generation of control signals to be used for the automated movement of the wheelchair. An artificial neural network-based classifier is constructed to classify the patterns and features extracted from the raw sEMG signals. The classification accuracy of the extracted parameters from the sEMG signals is found to be relatively high in comparison with the existing methods. The extracted parameters used to generate control signals that are then fed into a microcomputer-based control system (MiCS). A solar-powered wheelchair prototype is developed, and the above MiCS is introduced to control its maneuver using the sEMG signals. The prototype is then thoroughly tested with sEMG signals from patients of different age groups. Also, the life cycle cost analysis of the proposed wheelchair revealed that it is financially feasible and cost-effective.

Cloud based healthcare application architecture and electronic medical record mining: An integrated approach to improve healthcare system

Abstract: Healthcare system can be enhanced vastly with the use of modern information technology. Still now in underdeveloped and developing countries, traditional paper based system is being used in healthcare. Although very few organizations use computer based system, they could not establish a ubiquitous network among patients, physicians and government. Cloud computing is the emerging technology which can be used to develop a heterogeneous network to improve the system. In this article, a three tier cloud based application “eHealth Cloud” has been developed which will involve different parties to improve old-fashioned healthcare system. RIA (Rich Internet Application) based client, SimpleDB based server and a logic layer have been designed to build an easily accessible network. By using the “eHealth Cloud”, enormous electronic medical record (EMR) will be stored everyday. This huge size of data can lead us with new research opportunities. Data mining from the large amount of EMR has been proposed. The process of data mining, a standard for exchanging data and a mining model is described. Finally, the challenges and future research options are directed.

An XAI Based Autism Detection: The Context Behind the Detection

Abstract: With the rapid growth of the Internet of Healthcare Things, a massive amount of data is generated by a broad variety of medical devices. Because of the complex relationship in large-scale healthcare data, researchers who bring a revolution in the healthcare industry embrace Artificial Intelligence (AI). In certain cases, it has been reported that AI can do better than humans at performing healthcare tasks. The data-driven black-box model, on the other hand, does not appeal to healthcare professionals as it is not transparent, and any biasing can hamper the performance the prediction model for the real-life operation. In this paper, we proposed an AI model for early detection of autism in children. Then we showed why AI with explainability is important. This paper provides examples focused on the Autism Spectrum Disorder dataset (Autism screening data for toddlers by Dr Fadi Fayez Thabtah) and discussed why explainability approaches should be used when using AI systems in healthcare.

Space-Time Block Coding for Wireless Communications

Abstract: II

6G Internet of Things: A Comprehensive Survey

Abstract: The sixth generation (6G) wireless communication networks are envisioned to revolutionize customer services and applications via the Internet of Things (IoT) towards a future of fully intelligent and autonomous systems. In this article, we explore the emerging opportunities brought by 6G technologies in IoT networks and applications, by conducting a holistic survey on the convergence of 6G and IoT. We first shed light on some of the most fundamental 6G technologies that are expected to empower future IoT networks, including edge intelligence, reconfigurable intelligent surfaces, space-air-ground-underwater communications, Terahertz communications, massive ultra-reliable and low-latency communications, and blockchain. Particularly, compared to the other related survey papers, we provide an in-depth discussion of the roles of 6G in a wide range of prospective IoT applications via five key domains, namely Healthcare Internet of Things, Vehicular Internet of Things and Autonomous Driving, Unmanned Aerial Vehicles, Satellite Internet of Things, and Industrial Internet of Things. Finally, we highlight interesting research challenges and point out potential directions to spur further research in this promising area.