Article
Medicine, General & Internal
Soham Chattopadhyay, Arijit Dey, Pawan Kumar Singh, Zong Woo Geem, Ram Sarkar
Summary: The COVID-19 virus is spreading rapidly worldwide and early detection is crucial. Currently, there are three main detection methods including RT-PCR, CT, and X-ray. A computational model for automatic COVID-19 detection has been proposed, achieving high accuracies on publicly available datasets.
Article
Biochemistry & Molecular Biology
Yang Xia, Weixiang Chen, Hongyi Ren, Jianping Zhao, Lihua Wang, Rui Jin, Jiesen Zhou, Qiyuan Wang, Fugui Yan, Bin Zhang, Jian Lou, Shaobin Wang, Xiaomeng Li, Jie Zhou, Liming Xia, Cheng Jin, Jianjiang Feng, Wen Li, Huahao Shen
Summary: This study demonstrated the efficiency of a classifier combining chest X-ray and clinical features in distinguishing COVID-19 from influenza A/B pneumonia. The combined classifier showed significantly improved diagnostic efficacy compared to using clinical features or CXR alone, with high sensitivity and specificity. Additionally, the AI system exhibited superiority in turn-around time and diagnostic accuracy compared to experienced pulmonary physicians in the reader study.
INTERNATIONAL JOURNAL OF BIOLOGICAL SCIENCES
(2021)
Article
Biology
Ali Narin
Summary: COVID-19 is a severe global epidemic with high mortality rates, impacting health systems and economies. Automatic diagnosis and detection systems are crucial for controlling the epidemic. A study implemented high-performance detection systems using various algorithms, achieving high accuracy post feature selection. The research is expected to benefit radiologists as a decision support system.
COMPUTERS IN BIOLOGY AND MEDICINE
(2021)
Article
Computer Science, Information Systems
Ganesh Yenurkar, Sandip Mal
Summary: This research analyzes the spread of COVID-19 globally and proposes an AI-based deep learning algorithm that uses real-world datasets to identify COVID-19 cases and predict mortality and recovery rates. The proposed method achieves higher accuracy compared to other machine learning models.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Rahul Kumar, Ridhi Arora, Vipul Bansal, Vinodh J. Sahayasheela, Himanshu Buckchash, Javed Imran, Narayanan Narayanan, Ganesh N. Pandian, Balasubramanian Raman
Summary: COVID-19 is a viral disease that can be detected using chest X-ray images. This study proposes a new model that utilizes machine learning and deep learning techniques to classify COVID-19, pneumonia, and normal cases, achieving promising results.
MULTIMEDIA TOOLS AND APPLICATIONS
(2022)
Article
Automation & Control Systems
Thing-Yuan Chang, Cheng-Kui Huang, Cheng-Hsiung Weng, Jing-Yuan Chen
Summary: In this study, we integrate deep neural network (DNN) with hybrid approaches (feature selection and instance clustering) to build prediction models for predicting mortality risk in patients with COVID-19. Cross-validation methods are used to evaluate the performance of these prediction models. The experimental results showed that the proposed feature based DNN model outperforms the original prediction model in terms of prediction performance.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Computer Science, Information Systems
Noha E. El-Attar, Sahar F. Sabbeh, Heba Fasihuddin, Wael A. Awad
Summary: This study proposes a method to predict COVID-19 positive cases based on patients' symptoms and features, using feature selection technique to improve the accuracy and learning speed of the model. The experiments show that this method outperforms other models in feature reduction, classification results, and time.
CMC-COMPUTERS MATERIALS & CONTINUA
(2022)
Article
Medicine, General & Internal
Asif Hassan Syed, Tabrej Khan, Nashwan Alromema
Summary: This study utilizes blood sample data from COVID-19 patients in Wuhan, China to identify informative blood biomarkers and train a RF-based machine learning model that accurately predicts in-hospital mortality of COVID-19 patients.
Article
Multidisciplinary Sciences
Muhammed S. Hammad, Vidan F. Ghoneim, Mai S. Mabrouk, Walid I. Al-atabany
Summary: This study proposes an effective hybrid approach based on genomic image processing (GIP) techniques to rapidly detect COVID-19 while avoiding the limitations of traditional detection techniques, using whole and partial genome sequences of human coronavirus (HCoV) diseases. Results showed that extracting deep features from the fc7 layer, selecting the most significant features using the LASSO algorithm, and executing the classification process using the KNN classifier is the best hybrid approach. The proposed hybrid deep learning approach detected COVID-19, among other HCoV diseases, with 99.71% accuracy, 99.78% specificity, and 99.62% sensitivity.
SCIENTIFIC REPORTS
(2023)
Article
Engineering, Biomedical
Justino Duarte Santos, Rodrigo de M. S. Veras, Romuere R. Silva, Nayze L. S. Aldeman, Flavio H. D. Araujo, Angelo A. Duarte, Joao Manuel R. S. Tavares
Summary: This study introduces a new method for distinguishing MCD from GS in glomerulus biopsy images, achieving an accuracy of 90.3% and a Kappa index of 80.5% through a hybrid representation of deep and textural features.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2021)
Article
Computer Science, Information Systems
Dongdong Li, Yijun Zhou, Zhe Wang, Daqi Gao
Summary: Recent studies on speech signals have focused on emotional information and the importance of feature representation in speech emotion recognition (SER). Different combinations of features and models have a significant impact on SER performance, with the proposed ECFW method showing promising results in improving performance across different databases.
INFORMATION SCIENCES
(2021)
Article
Multidisciplinary Sciences
Vivek Singh, Rishikesan Kamaleswaran, Donald Chalfin, Vivek Singh, Donald Chalfin, Antonio Buno-Soto, Janika San Roman, Edith Rojas-Kenney, Ross Molinaro, Sabine von Sengbusch, Parsa Hodjat, Dorin Comaniciu, Ali Kamen
Summary: This study aimed to develop an AI-based system to predict severe manifestations of COVID-19 in patients, assisting clinicians in treatment decisions. The model, trained using patient age and nine laboratory markers, showed high prediction accuracy.
Article
Energy & Fuels
Ali Jafari, Ali Asghar Alesheikh, Fatemeh Rezaie, Mahdi Panahi, Shiva Shahsavar, Moung-Jin Lee, Saro Lee
Summary: This study utilized genetic algorithm and binary whale optimization algorithm to select influential factors, and determined optimal hyperparameter values for the convolutional neural network model using whale optimization algorithm and Laplacian whale optimization algorithm. The proposed model provided a more accurate and reliable LS susceptibility map, suitable for predicting future subsidence areas.
INTERNATIONAL JOURNAL OF COAL GEOLOGY
(2023)
Article
Nanoscience & Nanotechnology
J. Sharmila Joseph, Abhay Vidyarthi
Summary: Gastrointestinal Tract (GIT) infections are common and can lead to stomach cancers if left untreated. Wireless Capsule Endoscopy (WCE) allows medical professionals to view and capture images of the internal parts of the GIT using a pill camera. Manual detection of abnormalities from these images is time-consuming and may result in misdiagnosis. This research introduces a novel technique that combines color, texture, statistical, shape, and deep pretrained Densenet features from contrast-enhanced GI images to improve prediction accuracy. The proposed method achieves a maximum classification accuracy of 99.2% and precision of 99.1% when tested with 8000 images from the KVASIR V2 dataset.
JOURNAL OF BIOMEDICAL NANOTECHNOLOGY
(2023)
Article
Computer Science, Hardware & Architecture
Nilesh Kunhare, Ritu Tiwari, Joydip Dhar
Summary: An intrusion detection system is crucial for detecting threats and unauthorized access. This paper proposes a novel feature selection method using a genetic algorithm and hybrid classification with logistic regression and decision tree. Experimental results show that the gray wolf optimization algorithm achieves the best performance with a reduced feature set. The proposed method is compared with existing methods, demonstrating improved performance.
COMPUTERS & ELECTRICAL ENGINEERING
(2022)
Article
Computer Science, Interdisciplinary Applications
A. M. Shloof, N. Senu, A. Ahmadian, M. Pakdaman, S. Salahshour
Summary: This paper proposes an artificial neural networks (ANNs) technique for solving fractal-fractional differential equations (FFDEs). The technique converts the original differential equation into a minimization problem and obtains the solution by computing the parameters with a precise neural network model. By combining the initial conditions and the performance of ANNs, a good approximate solution of FFDEs can be obtained. Examples and comparisons with existing methods are provided to demonstrate the efficiency and applicability of this approach.
ENGINEERING WITH COMPUTERS
(2023)
Article
Computer Science, Information Systems
Mainak Biswas, Saif Rahaman, Ali Ahmadian, Kamalularifin Subari, Pawan Kumar Singh
Summary: Spoken Language Identification (SLID) is a well-researched field and an important first step in multilingual speech recognition systems. This study proposes a model for Indian and foreign language recognition, which enhances data to make it robust against everyday life noise and selects relevant features through feature extraction and selection algorithms. The model achieves high accuracy on three standard datasets, indicating that these features capture language specific characteristics of speech and can be used as standard features for SLID task.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Computer Science, Software Engineering
Samir Malakar, Samanway Sahoo, Anuran Chakraborty, Ram Sarkar, Mita Nasipuri
Summary: Handwritten word recognition is an open research problem due to variations in writing style and degraded images. This paper proposes a holistic approach combined with distance calculation and feature descriptors to address the problem. The experimental results demonstrate the effectiveness of the proposed method on standard databases compared to deep learning models.
Article
Computer Science, Artificial Intelligence
Umer Ahmed Butt, Rashid Amin, Hamza Aldabbas, Senthilkumar Mohan, Bader Alouffi, Ali Ahmadian
Summary: Cloud computing refers to the on-demand availability of personal computer system assets without client's input. This paper focuses on email phishing attacks and proposes using SVM, NB, and LSTM algorithms for classification, achieving high accuracy rates. The results suggest the importance of implementing effective detection measures to combat phishing attacks in email communication.
COMPLEX & INTELLIGENT SYSTEMS
(2023)
Article
Engineering, Industrial
Subhajit Das, Md Sadikur Rahman, Ali Akbar Shaikh, Asoke Kumar Bhunia, Ali Ahmadian
Summary: The goal of this work is two-fold: (i) to theoretically develop optimality conditions for a variational problem with interval uncertainty, and (ii) to apply the established results in a production inventory model with interval uncertainty. The necessary and sufficient optimality conditions for the interval-valued variational problem (IVVP) are proposed using interval order relations. A production inventory model is formulated considering interval-valued time-dependent production and demand rates. The optimal policy of the proposed model is studied using the established optimality conditions.
INTERNATIONAL JOURNAL OF SYSTEMS SCIENCE-OPERATIONS & LOGISTICS
(2023)
Article
Computer Science, Artificial Intelligence
Souradeep Mukhopadhyay, Sabbir Hossain, Samir Malakar, Erik Cuevas, Ram Sarkar
Summary: This paper introduces a new gray-scale contrast enhancement algorithm, which improves image quality by calculating near-optimal values using the Artificial Electric Field Algorithm (AEFA). Through comparisons with other techniques using standard metrics, simulation results show that the proposed method increases image contrast and enriches image information.
Article
Computer Science, Information Systems
Anubhab Das, Arka Choudhuri, Arpan Basu, Ram Sarkar
Summary: This study proposes a GAN-based method for generating handwritten Bengali compound characters to address data scarcity. The model's performance is evaluated by assessing the quality of generated samples, showing that it outperforms basic AC-GAN architecture and some other existing GAN architectures.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Apu Sarkar, S. K. Sabbir Hossain, Ram Sarkar
Summary: This paper proposes a method for human activity recognition (HAR) from wearable sensor data. It utilizes Continuous Wavelet Transform and a Spatial Attention-aided Convolutional Neural Network (CNN) to extract features, and employs feature selection and a modified version of Genetic Algorithm (GA) for activity recognition. Experimental results show that the proposed method outperforms existing models in terms of classification performance and improves overall recognition accuracy by reducing the number of features.
NEURAL COMPUTING & APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Sk Mohiuddin, Khalid Hassan Sheikh, Samir Malakar, Juan D. Velasquez, Ram Sarkar
Summary: Digital face manipulation has become a significant concern recently due to its harmful effects on society, particularly for high-profile celebrities who can easily be targeted using apps like FaceSwap and FaceApp. Detecting deepfake images or videos is challenging, and existing models often fail to check for irrelevant or redundant features. In this study, a hierarchical feature selection (HFS) method using a hybrid population-based meta-heuristic model and a single solution-based meta-heuristic model was proposed. The model achieved high AUC scores on three publicly available datasets and outperformed most state-of-the-art methods.
NEURAL COMPUTING & APPLICATIONS
(2023)
Article
Mathematics, Applied
Muhammad Junaid Saeed, Madeeha Tahir, Muhammad Imran Asjad, Zain Ul Aabedin, Muhammad Maqsood, Ali Ahmadian, Mehdi Salimi
Summary: This study investigates the steady mixed convection solute transfer in a two-dimensional viscous fluid. The effects of joule heating in an inclined stretching cylinder and double stratification on Jeffrey Nanofluid are analyzed. By utilizing approximation transformation and numerical techniques, the skin friction, Nusselt number, and Sherwood number are calculated and analyzed. The results show that various parameters, such as M, gamma, alpha, Deborah number, magnetic factor, Brownian motion, have different effects on the velocity, temperature, and concentration.
ZAMM-ZEITSCHRIFT FUR ANGEWANDTE MATHEMATIK UND MECHANIK
(2023)
Article
Mathematics, Applied
Mohd Rashid Admon, Norazak Senu, Ali Ahmadian, Zanariah Abdul Majid, Soheil Salahshour
Summary: A new numerical technique is developed in this paper to solve the fractional relaxation-oscillation equation in Hilfer sense. By transforming the equation into an equivalent Volterra integral equation, the problem is greatly simplified, and the accuracy of the method is verified numerically.
COMPUTATIONAL & APPLIED MATHEMATICS
(2023)
Article
Medicine, General & Internal
Arnab Bagchi, Payel Pramanik, Ram Sarkar
Summary: Breast cancer is a deadly disease that affects women worldwide. Early diagnosis and proper treatment can save lives. Breast image analysis, including histopathological image analysis, and computer-aided diagnosis, can help improve efficiency and accuracy in breast cancer detection. In this study, a deep learning-based method was developed to classify breast cancer using histopathological images, achieving high classification accuracy.
Article
Computer Science, Theory & Methods
Nik Amir Syafiq, Mohamed Othman, Norazak Senu, Fudziah Ismail, Nor Asilah Wati Abdul Hamid
Summary: This research investigates the multi-core architecture for solving the fractional Poisson equation using the modified accelerated overrelaxation (MAOR) scheme. The feasibility of the scheme in a parallel environment was tested through experimental comparisons and measurements. The results showed that the scheme is viable in a parallel environment.
JOURNAL OF PARALLEL AND DISTRIBUTED COMPUTING
(2024)
Article
Engineering, Multidisciplinary
Abdul Alamin, Mostafijur Rahaman, Sankar Prasad Mondal, Shariful Alam, Mehdi Salimi, Ali Ahmadian
Summary: In this article, a logistic fixed effort harvesting model is constructed using a fuzzy difference equation framework, which explores the philosophy behind the underflowing discrete behavior and uncertainty associated with modeling. The merits of the proposed theory are validated through numerical simulation and graphical visualization.
INTERNATIONAL JOURNAL OF MODELLING AND SIMULATION
(2023)
Article
Multidisciplinary Sciences
Lee Khai Chien, Norazak Senu, Ali Ahmadian, Siti Nur Iqmal Ibrahim
Summary: This study proposes sixth-order two-derivative improved Runge-Kutta type methods for integrating a special type of third-order ordinary differential equation. The methods are adopted with exponentially-fitting and trigonometrically-fitting techniques. The proposed methods are developed through the idea of integrating initial value problems exactly and show improved computational efficiency compared to other existing numerical methods.
PERTANIKA JOURNAL OF SCIENCE AND TECHNOLOGY
(2023)