Article
Automation & Control Systems
Shanjiang Tang, Chunjiang Wang, Jiangtian Nie, Neeraj Kumar, Yang Zhang, Zehui Xiong, Ahmed Barnawi
Summary: Efficient screening of COVID-19 cases is crucial to prevent the rapid spread of the disease, and the EDL-COVID model, combining deep learning and ensemble learning, shows promising results in COVID-19 case detection with a higher accuracy compared to the COVID-Net model.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2021)
Article
Health Care Sciences & Services
Mana Saleh Al Reshan, Kanwarpartap Singh Gill, Vatsala Anand, Sheifali Gupta, Hani Alshahrani, Adel Sulaiman, Asadullah Shaikh
Summary: Pneumonia causes a large number of deaths worldwide and can be difficult to distinguish from other respiratory diseases. The variability in chest X-ray image acquisition and processing affects the quality and consistency of the images, making it challenging to develop accurate algorithms. This research demonstrates a deep-learning-based model for distinguishing between normal and severe cases of pneumonia.
Article
Computer Science, Interdisciplinary Applications
Shadi A. Aljawarneh, Romesaa Al-Quraan
Summary: The aim of this study was to develop models to evaluate large X-ray images of the chest and determine whether the images show signs of pneumonia. The enhanced CNN model showed the highest accuracy for pneumonia detection.
Article
Computer Science, Artificial Intelligence
Nilanjan Dey, Yu-Dong Zhang, V. Rajinikanth, R. Pugalenthi, N. Sri Madhava Raja
Summary: The research aims to develop a Deep-Learning System for diagnosing lung abnormalities, using a combination of VGG19 and Random-Forest classifier showing the highest accuracy when dealing with chest X-ray images.
PATTERN RECOGNITION LETTERS
(2021)
Article
Medicine, General & Internal
Muhammad Mujahid, Furqan Rustam, Roberto Alvarez, Juan Luis Vidal Mazon, Isabel de la Torre Diez, Imran Ashraf
Summary: Pneumonia is a leading cause of death in infants and elderly people, and accurate diagnosis systems are needed. This study uses X-ray images for pneumonia detection and experiments with pre-trained convolutional neural networks and ensemble models. The results show that the model using Inception-V3 and CNN achieves the highest accuracy and recall score.
Article
Computer Science, Information Systems
Megha Trivedi, Abhishek Gupta
Summary: This paper proposes a method for automatic detection of pneumonia using the deep learning architecture 'MobileNet'. By training on a dataset of 5856 chest X-ray images, the method achieves high accuracy in a short training time, with good specificity, precision, and recall rates.
MULTIMEDIA TOOLS AND APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Pranab Sahoo, Sriparna Saha, Saksham Kumar Sharma, Samrat Mondal, Suraj Gowda
Summary: This study proposes an end-to-end multi-stage architecture for COVID-19 diagnosis and severity assessment. The architecture identifies relevant lung regions by eliminating irrelevant portions and combines predictions using multiple models and a fuzzy ensemble method. The method achieves good performance in infection region identification and COVID-19 classification tasks.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Information Systems
Roaa Alsharif, Yazan Al-Issa, Ali Mohammad Alqudah, Isam Abu Qasmieh, Wan Azani Mustafa, Hiam Alquran
Summary: Pneumonia is an inflammatory disease of the lung parenchyma caused by various infectious microorganisms and non-infective agents. Radiological images, such as Chest X-ray, provide early detection and prompt action. Early and accurate detection is crucial to prevent fatal consequences, especially in children and seniors.
Article
Mathematics, Interdisciplinary Applications
Emtiaz Hussain, Mahmudul Hasan, Md Anisur Rahman, Ickjai Lee, Tasmi Tamanna, Mohammad Zavid Parvez
Summary: A novel CNN model called CoroDet was proposed for automatic detection of COVID-19 using raw chest X-ray and CT scan images in this study. The model outperformed existing techniques in terms of classification accuracy, providing a solution to the issue of scarcity of COVID-19 testing kits.
CHAOS SOLITONS & FRACTALS
(2021)
Article
Computer Science, Information Systems
Gurmail Singh, Kin-Choong Yow
Summary: The study introduced an interpretable deep learning model Gen-ProtoPNet, which achieves accuracy comparable to the best performing non-interpretable models. The model utilizes a generalized version of the distance function L2 and prototypes of different spatial dimensions for image classification.
Article
Engineering, Biomedical
Emine Ucar, Umit Atila, Murat Ucar, Kemal Akyol
Summary: The study proposes a deep learning approach for rapid and accurate detection of Covid-19 on X-ray images, extracting deep features using pre-trained architectures and employing a two-stage classifier method for binary classification. The Bi-LSTM network showed superior performance with 92.489% accuracy compared to other classifiers, including well-known ensemble approaches.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2021)
Article
Computer Science, Artificial Intelligence
R. Karthik, R. Menaka, M. Hariharan
Summary: Automatic diagnosis of COVID-19 from medical imaging enables precise medication, helps to control community outbreak, and strengthens coronavirus testing methods. A custom CNN architecture has been proposed in this research to learn unique convolutional filter patterns for each kind of pneumonia, showing significant potential in augmenting current testing methods for COVID-19.
APPLIED SOFT COMPUTING
(2021)
Article
Computer Science, Artificial Intelligence
Subhrajit Dey, Rajarshi Roychoudhury, Samir Malakar, Ram Sarkar
Summary: Early detection of Tuberculosis is crucial in reducing mortality rates by preventing its spread to other body parts, and researchers are working on developing a computerized decision support system for efficient diagnosis.
APPLIED SOFT COMPUTING
(2022)
Article
Engineering, Biomedical
Wassim Zouch, Dhouha Sagga, Amira Echtioui, Rafik Khemakhem, Mohamed Ghorbel, Chokri Mhiri, Ahmed Ben Hamida
Summary: This article introduces a novel method for automatically detecting COVID-19 using tomographic images and radiographic images, utilizing the VGG and ResNet deep learning models, achieving high accuracy.
ANNALS OF BIOMEDICAL ENGINEERING
(2022)
Article
Computer Science, Information Systems
Vinayakumar Ravi, Vasundhara Acharya, Mamoun Alazab
Summary: This paper proposes a multichannel deep learning approach for lung disease detection using chest X-rays. The proposed method shows better performance in detecting various lung diseases and is robust and generalizable on unseen chest X-ray data samples.
CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Erik Cuevas, Hector Escobar, Ram Sarkar, Heba F. Eid
Summary: This paper proposes a new population initialization method for metaheuristic algorithms, where the initial set of candidate solutions is obtained through the sampling of the objective function. The method aims to find initial solutions that are close to the prominent values of the objective function, and these initial points represent promising regions of the search space. The proposed approach shows faster convergence and improved quality of solutions compared to other similar approaches.
APPLIED INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Rishav Pramanik, Payel Pramanik, Ram Sarkar
Summary: Breast cancer is a leading cause of premature death among women globally, but early detection and diagnosis can save lives. Hence, computer scientists are working to develop reliable models to tackle this disease. A proposed lightweight model combines transfer learning-based deep learning (DL) with feature selection to detect abnormalities in breast thermograms. This model performs well in detecting and differentiating malignant and healthy breasts.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Engineering, Biomedical
Agnish Bhattacharya, Biswajit Saha, Soham Chattopadhyay, Ram Sarkar
Summary: Cancer is a frightening disease that is extensively researched worldwide. This study presents a framework that utilizes deep learning and meta-heuristic approaches to accurately predict colon or lung cancer from histopathological images. By combining these methods, the proposed approach achieves near-perfect precision in cancer detection.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2023)
Article
Energy & Fuels
Mahmoud Aref, Almoataz Y. Abdelaziz, Zong Woo Geem, Junhee Hong, Farag K. Abo-Elyousr
Summary: The main goal of this study is to suppress low-frequency oscillations caused by disruptive faults and heavy load disturbance through appropriate power oscillation damping controllers. FACTs technology, such as the static synchronous series compensator, can effectively dampen power frequency oscillations in power systems with heavy solar energy penetrations. By developing neural controllers based on optimized particle swarm optimization (PSO) and adaptive neuro-fuzzy algorithms, the obtained results demonstrate that the PSO-based neural network controller outperforms other controllers in terms of execution time and system performance.
Article
Automation & Control Systems
Debjit Sarkar, Sourodeep Roy, Samir Malakar, Ram Sarkar
Summary: Graph neural networks (GNN) maintain the essence of irregularly structured information in a graph through message passing and feature aggregation. A weighting scheme called VecGNN is proposed to incorporate inter-node feature-level correlational information, considering the relative position of nodes in the feature space. VecGNN outperforms baseline models GCN, GAT, and JKNets by 2%-4% on citation datasets.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Samriddha Majumdar, Payel Pramanik, Ram Sarkar
Summary: Breast cancer is the second deadliest disease among women globally. Histopathology image analysis is an effective method for detecting tumor malignancies. Computer-aided diagnosis (CAD) using convolutional neural network (CNN) models has shown potential in breast histopathological image classification, but there is room for improvement. This paper proposes a novel rank-based ensemble method that combines multiple CNN models to enhance classification accuracy.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Pratik Bhowal, Subhankar Sen, Jin Hee Yoon, Zong Woo Geem, Ram Sarkar
Summary: This article studies the high complexity of calculating fuzzy measures and proposes a low-complexity method for implementing fuzzy measures in the fusion of deep learning models. It shows that the Dempster-Shafer belief structure provides partial information about fuzzy measures associated with a variable and devises a method to use this information for calculation. The article also proposes a theorem to calculate a specific set of fuzzy measures associated with the DS belief structure and expresses them as a weighted summation of the basic assignment function.
IEEE TRANSACTIONS ON FUZZY SYSTEMS
(2023)
Article
Automation & Control Systems
Cinthia Peraza, Oscar Castillo, Patricia Melin, Juan R. Castro, Jin Hee Yoon, Zong Woo Geem
Summary: The use of metaheuristics is increasing due to their ability to handle complex and uncertain real-world problems. However, most current metaheuristic algorithms suffer from local minima and fixed parameters. Fuzzy logic has been shown to effectively address this issue by using type-1 and type-2 fuzzy theory for parameter adaptation. The uncertainty management provided by fuzzy theory offers significant improvement in finding solutions.
INTERNATIONAL JOURNAL OF FUZZY SYSTEMS
(2023)
Article
Computer Science, Information Systems
S. k Mohiuddin, Samir Malakar, Ram Sarkar
Summary: Video forgery has become more common due to the easy availability of tools. This study proposes an ensemble based method to detect duplicate frames in a video. By extracting different types of features and applying lexicographical sorting, the method achieves high detection accuracy and outperforms state-of-the-art methods.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Sk Mohiuddin, Samir Malakar, Munish Kumar, Ram Sarkar
Summary: Video plays a critical role in conveying authenticity in various fields such as surveillance, medicine, journalism, and social media. However, the trust in videos is diminishing due to the ease of video forgery using accessible editing tools. This article comprehensively discusses the initiatives and recent trends in video forgery detection research worldwide.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Avirup Bhattacharyya, Avigyan Bhattacharya, Sourajit Maity, Pawan Kumar Singh, Ram Sarkar
Summary: Designing an automatic vehicle detection system that caters to the requirements of the traffic management system is important. This research develops a still image database, JUVDsi v1, for designing an automated traffic management system in India. The database addresses the shortcomings of existing databases and is evaluated using state-of-the-art deep learning architectures.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Green & Sustainable Science & Technology
Gebrail Bekdas, Yaren Aydin, Umit Isikdag, Aidin Nobahar Sadeghifam, Sanghun Kim, Zong Woo Geem
Summary: The study aimed to develop models to predict the cooling load of low-rise tropical buildings based on their basic characteristics. Different machine learning algorithms were tested and the results showed that Histogram Gradient Boosting and Stacking models were the most accurate for predicting the cooling load.
Article
Green & Sustainable Science & Technology
Gebrail Bekdas, Celal Cakiroglu, Sanghun Kim, Zong Woo Geem
Summary: The optimal design of prestressed concrete cylindrical walls has significant economic and environmental benefits. The lack of sufficient training datasets for robust machine learning models has hindered the widespread use of machine learning techniques in structural design. This study demonstrates the application of the harmony search methodology to create a large database of optimal design configurations, and trains ensemble learning models to accurately predict the optimum wall thickness in prestressed concrete cylindrical wall design.
Editorial Material
Chemistry, Multidisciplinary
Zong Woo Geem, Seokwon Yeom, Euntai Kim, Myung-Geun Chun, Young-Jae Ryoo
APPLIED SCIENCES-BASEL
(2023)
Article
Chemistry, Physical
Celal Cakiroglu, Yaren Aydin, Gebrail Bekdas, Zong Woo Geem
Summary: This study applies ensemble learning techniques to predict the splitting tensile strength of concrete reinforced with basalt fibers. The XGBoost algorithm achieves a coefficient of determination greater than 0.9, and the impact of input features on the prediction is visualized using the SHAP algorithm and ICE plots.