Akmam Majed Mosa

Ministry of Higher Education and Scientific Research

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Trends

Author Order

Document Type

Co-Authors

Ebtehal Akeel Hamed

Galgotias University

Parvathy Lakshmanan

Galgotias University

Narayana Arun

Galgotias University

Joel Alanya-Beltrán

Universidad Tecnológica del Perú

A. Mohana Priya

Galgotias University

Adarsh Tripathi

King George's Medical University

Chitra Devi

Galgotias University

Apoorva Srivastava

Biocon (India)

Jhalak Sharma

Galgotias University

Aniket Sharma

Galgotias University

Cooperative Institutions

Galgotias University

267

Weatherford College

261

Chandigarh University

Chitkara University

Lovely Professional University

Delhi Technological University

Banaras Hindu University

All India Institute of Medical Sciences

ABES Engineering College

Institute of Engineering

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Field

Survey: A wide and deep neural network with their implementation

Turkish Journal of Computer and Mathematics Education (TURCOMAT) (2021)

Akmam Majed Mosa

The notion concerning a neural community capable concerning transcribing ethnical composition has long gone beyond a list in accordance with turning into an almost insignificant task. Neural networks started out abroad as like simply a mathematical concept, no longer something that may want to remain performed together with the technological know-how degree of the time, however above period the thoughts grew and the science eventually caught up. ANNs commenced including an assignment via McCullogh and Pitts whichever described up to expectation sets concerning easy devices (artificial neurons) could operate entire viable logic operations or hence stay capable regarding normal computation. In 1985, Rumelhart, McClelland, yet Hinton determined a powerful study regime that allowed them to educate ANNs together with various black units. Actually, flagrant neural networks (DNNs) are awfully utilized because of extraordinary features and have performed state-of-the-art performances.in it record review an overview present day concerning the research touching DNNs’ implementations are presented. As because the large awful neural networks, we showed the purpose for the appearance of this kind regarding network, the features, the architecture over these networks, the learning strategies used, as differentiates this networks beside the traditional networks. After the suggestion of an algorithm of fast learning for deep networks through 2006, the deep learning methods have induced regularly-growing study attention for the reason of their intrinsic ability to overcome the disadvantage of classical algorithms conditional on manually-prepared characteristics. Deep learning strategies have further been discovered to be proper for huge data examination with prosperous applications to computer vision, pattern recognition, etc. In this paper, we consider several architectures of widely-used deep learning with their functional applications. A modern summary is presented on some deep learning architecture, wide Deep Neural Networks Implementations, traditional neural network, embedding vector. Various kinds of deep neural networks are viewed and modern forwards are compiled. Employment of deep learning methods on remarkable chosen fields also analyzed.

Deep Neural Networks

Implementation

Disadvantage

Source

Cite

Citations (0)

Improved Smart Forecasting Model to Combat Coronavirus using Machine Learning

2022 2nd International Conference on Advance Computing and Innovative Technologies in Engineering (ICACITE) (2022)

Akmam Majed Mosa Ebtehal Akeel Hamed Zahraa Hussein Refed Adnan Jaleel

Coronavirus (COVID) is one of the world's most devastating diseases, affecting the lives of millions of people around the globe. Accurate and timely detection of the COVID virus is critical for human survival. The standard medical history of diagnosing COVID disease has been deemed unreliable in several ways. Noninvasive methods such as Machine Learning (ML) are efficient and reliable for classifying healthy persons and people with COVID disease. In this paper, we improved a Smart Forecasting Model using Machine Learning (SFML) for COVID prediction (positive, negative) by using COVID data. We applied, two algorithms of feature selection (correlation and gain ratio), two supervised ML algorithms (Random forest and support vector machine) and the technique of cross-validation was applied for evaluating the SFML, such as specificity, accuracy, F-measure, sensitivity, and running time. The proposed SFML may easily distinguish COVID infected individuals from healthy individuals. The proposed SFML has been tested on a full set of COVID features as well as a smaller set of features. The results reveal that reducing COVID features has an impact on SMFL performance measures.

Supervised Learning

Feature (linguistics)

Coronavirus

10.1109/icacite53722.2022.9823435

Cite

Citations (3)

Secure E-healthcare System Based on Biometric Approach

Data & Metadata (2023)

Amal Fadhil Mohammed Hayder A. Nahi Akmam Majed Mosa Inas O Kadhim

A secure E-health care system is satisfying by maintaining data authenticity and privacy. Authentic users only access and edit medical records, any alteration in the medical records may result in a misdiagnosis and, as a result, harm the patient's life. Biometric method and watermarking modes are utilized to satisfy goal, such as Discrete Wavelet Transform (DWT), Discrete Fourier Transform (DFT), Discrete Cosine Transform (DCT) and Least Significant Bit (LSB). In this work focused on a biometric watermarking system where the iris code of the sender programmed as a sender authentication key. The confidentiality of the patient information is safeguarded via encrypting it with an XOR algorithm and embedding the key in the DCT image. The algorithm has demonstrated which is suggested system has met earlier constraints. We used samples of original watermarked images with PSNR value, embedding time and extraction time, the lowest embedding time was 0,0709 and the PSNR value was 49,2369

10.56294/dm202356

Cite

Citations (14)

Author Index

2022 2nd International Conference on Advance Computing and Innovative Technologies in Engineering (ICACITE) (2022)

A. Ambikapathy A Shenbagharaman Aanchal Vij Abdul Sameerunnisa Abhay Bindal

10.1109/icacite53722.2022.9823739

Cite

Citations (0)