Application of Deep Learning for Detection and Analysis of COVID-19 Outcomes: Deep-COVID | Chapter 7 | Science and Technology - Recent Updates and Future Prospects Vol. 1

 

The COVID-19 epidemic, which began on December 31, 2019, with the revelation of nonspecific pneumonia indications in Wuhan, China, swiftly became a significant outbreak, with great ramifications worldwide. The coronavirus epidemic (COVID-19) was growing quickly around the globe. The first acute atypical respiratory illness was reported in December 2019, in Wuhan, China. This quickly spread from Wuhan city to other locations. Deep learning (DL) algorithms are one of the greatest solutions for consistently and readily recognizing COVID-19. Previously, many researchers used state-of-the-art approaches for the classification of COVID-19. In this paper, we present a deep learning approach with the Efficient netB4 model, centered on transfer learning, for the classification of COVID-19. Transfer learning is a popular technique that uses pre-trained models that have been trained on the ImageNet database and employed on a new problem to increase generalization. We presented an in-depth training approach to extract the visual properties of COVID-19 in exchange for providing a medical assessment before infection testing. The proposed methodology is assessed on a publicly accessible X-ray imaging dataset. The experimentation work was conducted at the university using the Anaconda 3 software environment. Performance measurements were employed on the COVID-19 dataset to evaluate and verify our proposed approach. The proposed framework achieves an accuracy of 97%. Our model’s experimental findings demonstrate that it is extremely successful at identifying COVID-19 and that it may be supplied to health organizations as a precise, quick, and successful decision support system for COVID-19 identification. More data may be integrated into future work for improved outcomes, which would enhance the proposed framework even more.

Author(s) Details:

Muhammad Ibrahim Khalil,
University Institute of Information Technology, PMAS Arid Agriculture University, Rawalpindi-46000, Pakistan.

Mahwish Kundi
International Engineering Collage, Maynooth University, W23 F2H6, Irland.

Saif Ur Rehman
University Institute of Information Technology, PMAS Arid Agriculture University, Rawalpindi-46000, Pakistan.

Dr. Tahani Brarakah Alsaedi
Department of Computer Science and Information, Taibah University, 42377, Saudi Arabia.

Please see the link here: https://stm.bookpi.org/STRUFP-V1/article/view/14344

Study on Fuzzy Logic Decision Support System for Hypovigilance Detection Based on CNN Feature Extractor and WN Classifier | Chapter 13 | Recent Advances in Mathematical Research and Computer Science Vol. 1

Excessive speed and drinking are the leading causes of road accidents, followed by fatigue and drowsiness. It is critical to regularly check the driver's alertness level in order to improve their capacity to drive safely and efficiently. This paper is about the issue of road safety. It makes an attempt to present a video-based driver vigilance monitoring system. The goal of this project is to develop an assistance driving application that uses eye closure length and head position estimate as effective indicators of alertness control. The suggested system may be broken down into three steps: video eye recognition and tracking, categorization of eye states, and integration of both sub-systems based on blinking and head position. Because of its efficiency in real-time applications, we employed the Viola and Jones algorithm for interest area recognition to complete the prior tasks. We used two innovative architectures of transfer learning classifiers based on fast wavelet transform and separator wavelet networks for the classification stage, which is the paper's key contribution. This unique design outperforms the standard version of transfer learning based on SVM classifiers as well as our previous classifier based solely on fast wavelet networks without a deep learning component. The goal of our research is to compare the performance of CNNs with wavelet networks in the classification phase. We also want to highlight the value of fuzzy logic as a tool for combining multiple inputs, allowing us to create a more accurate vigilance control system.

Author (S) Details

Ines Teyeb
RTIM: Research Team in Intelligent Machines, University of Gabes, National Engineering School of Gabes (ENIG), Tunisia.

Ahmed Snoun
RTIM: Research Team in Intelligent Machines, University of Gabes, National Engineering School of Gabes (ENIG), Tunisia.

Olfa Jemai
RTIM: Research Team in Intelligent Machines, University of Gabes, National Engineering School of Gabes (ENIG), Tunisia.

Mourad Zaied
RTIM: Research Team in Intelligent Machines, University of Gabes, National Engineering School of Gabes (ENIG), Tunisia.

View Book :-  https://stm.bookpi.org/RAMRCS-V1/article/view/4343

Study on Identifying the Cattle Diseases Using Artificial Intelligence Techniques | Chapter 10 | New Visions in Science and Technology Vol. 4

Livestock is one of India's most important industries. There are 56.7 percent buffaloes, 12.5 percent cattle, 20.4 percent small ruminants, 2.4 percent camels, 1.4 percent equestrian, 1.5 percent pigs, and 3.1 percent poultry in the country. The average production of milk or meat from animals in the United States is 20-60% lower than the global average. Due to a lack of breeding, feeding, health, and management concerns, their output potential is not fully realised. Also, infections such as Brucellosis, Swine Fever, and others affect the animals. There is insufficient veterinarian support for this. This research focuses on applying Artificial and Machine Learning techniques to identify these diseases in cattle. Four important diseases are discussed in this paper: FMD (Foot and Mouth Disease), HS, BQ (Black Quarter), and Anthrax. A camera-based mobile app is being developed to detect illnesses. To detect, store, and predict the sickness, data science and deep learning technology are applied. Once the data has been analysed, the results can be communicated with clinicians in the area through cell phone. Some drugs could be provided by farmers themselves, based on doctor's advise. As a result, a single doctor may virtually serve a larger number of patients..

 

Author (S) Details

H. S. Anupama
Department of Artificial Intelligence and Machine Learning, BMS Institute of Technology and Management, Bangalore, India.

B. A. Usha
Department of Computer Science and Engineering, BMS Institute of Technology and Management, Bangalore, India.

M. Aishwarya
Department of Computer Science and Engineering, BMS Institute of Technology and Management, Bangalore, India.

View Book https://stm.bookpi.org/NVST-V4/article/view/3999

Modelling and Simulation of Microstructural Evolution for Extra-terrestrial Planetary Chemistry Mapping Using Artificial Intelligence – A NASA Mars Rover Study | Chapter 11 | Recent Developments in Engineering Research Vol. 6

Recently, the creation of rovers and infrastructure development that allows them to test other planets (such as Mars) have sparked a lot of interest, particularly with growing public attention by the National Aeronautics and Space Administration in the Moon and Mars Program. This is intended to be done by various means, such as advanced spectroscopy and artificial intelligent techniques, such as deep learning and transfer learning, to allow the rover not only to map the planet's surface, but also to obtain detailed information on its chemical composition in layers below (deep learning) and in areas around the point of observation (transfer learning). The later method is discussed in this work, which is part of a proposal. A systematic strategy is proposed that uses the aforementioned techniques developed as a benchmark for metallic glass matrix composites and helps develop chemistry mapping algorithms on Perseverance Rover launched shortly for the real Martian surface.

Author (s) Details

Muhammad Musaddique Ali Rafique
Eastern Engineering Solutions LLC, Detroit MI 48202, USA and Law Chamber, Muhammad Rafique Advocate (High Court Lahore, Supreme Court of Pakistan), H 15/B, St. 23, Nizamabad Kot Khawaja Saeed, Lahore, Pakistan.

View Book :- https://bp.bookpi.org/index.php/bpi/catalog/book/285