Article
Computer Science, Interdisciplinary Applications
Syed Inthiyaz, Baraa Riyadh Altahan, Sk Hasane Ahammad, V. Rajesh, Ruth Ramya Kalangi, Lassaad K. Smirani, Md. Amzad Hossain, Ahmed Nabih Zaki Rashed
Summary: Dermatology is a complex field that requires extensive testing to diagnose skin diseases. This research provides an automated image-based method for diagnosing and categorizing skin problems using machine learning classification. This application offers more accurate and faster results than the traditional method, and may also be used as a real-time teaching tool.
ADVANCES IN ENGINEERING SOFTWARE
(2023)
Article
Computer Science, Information Systems
Israt Jahan, K. M. Aslam Uddin, Saydul Akbar Murad, M. Saef Ullah Miah, Tanvir Zaman Khan, Mehedi Masud, Sultan Aljahdali, Anupam Kumar Bairagi
Summary: This paper explores the potential uses of eye condition classification, such as tiredness detection and psychological condition evaluation. A novel CNN model for eye state categorization is proposed using deep learning and digital image processing techniques. The system can automate drowsiness detection and alert the driver before any severe threats to road safety.
Article
Computer Science, Information Systems
Madhusudan G. Lanjewar, Jivan S. Parab, Arman Yusuf Shaikh
Summary: Alzheimer's disease, an incurable and irrecoverable brain illness, can be detected from MRI images using a combination of Convolutional Neural Network (CNN) and K-nearest neighbor (KNN) algorithm, achieving a high level of accuracy.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Alok Singh, Thoudam Doren Singh, Sivaji Bandyopadhyay
Summary: This study focuses on generating Hindi image captions using the Hindi Visual genome dataset, with an encoder-decoder architecture incorporating CNN for image encoding and sLSTM for caption generation. Experimental results demonstrate that the proposed model outperforms existing approaches in both qualitative and quantitative aspects.
MULTIMEDIA TOOLS AND APPLICATIONS
(2021)
Article
Computer Science, Information Systems
Abdullah A. Asiri, Muhammad Aamir, Ahmad Shaf, Tariq Ali, Muhammad Zeeshan, Muhammad Irfan, Khalaf A. Alshamrani, Hassan A. Alshamrani, Fawaz F. Alqahtani, Ali H. D. Alshehri
Summary: The precise diagnosis of brain tumors is crucial in the medical support for treating tumor patients. This paper proposes an improved computer-aided system using a fine-tuned Block-Wise Visual Geometry Group19 (BW-VGG19) architecture to enhance accuracy. The results demonstrate that the proposed method outperforms existing techniques.
CMC-COMPUTERS MATERIALS & CONTINUA
(2022)
Article
Instruments & Instrumentation
Saleh Albahli, Ghulam Nabi Ahmad Hassan Yar
Summary: This study aims to design and compare various deep learning models for detecting the severity of diabetic retinopathy, determining the risk of macular edema, and segmenting different disease patterns using retina images. The results show that image preprocessing plays an important role in improving the efficacy and performance of deep learning models.
JOURNAL OF X-RAY SCIENCE AND TECHNOLOGY
(2022)
Article
Computer Science, Interdisciplinary Applications
Nirmala Devi Kathamuthu, Shanthi Subramaniam, Quynh Hoang Le, Suresh Muthusamy, Hitesh Panchal, Suma Christal Mary Sundararajan, Ali Jawad Alrubaie, Musaddak Maher Abdul Zahra
Summary: COVID-19 is a highly transmissible disease that has a significant impact on the world. It is difficult to diagnose early and can be detected non-invasively using medical imaging techniques. This research developed a conceptual transfer learning enhanced CNN model, and the VGG16 model performed the best (98% accuracy). It can assist healthcare professionals in making optimal treatment decisions.
ADVANCES IN ENGINEERING SOFTWARE
(2023)
Article
Computer Science, Information Systems
Aayush Khurana, Sweta Mittal, Deepika Kumar, Sonali Gupta, Ayushi Gupta
Summary: This paper proposes an integrated methodology called TiCNN for emotion classification based on Mel-frequency spectrograms. By training and validating on multiple datasets, the proposed method achieves high accuracy and performance.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Md. Nahiduzzaman, Md. Rabiul Islam, Rakibul Hassan
Summary: In recent decades, epidemic diseases have posed challenges to doctors in terms of accurate identification. However, machines trained correctly can outperform humans in disease recognition. With the increasing amount of medical data, machines can analyze and extract knowledge from this data to assist doctors. In this study, a lightweight convolutional neural network named ChestX-ray6 was proposed to automatically detect pneumonia, COVID19, cardiomegaly, lung opacity, and pleural diseases from digital chest x-ray images. The ChestX-ray6 model achieved an 80% accuracy for the six diseases. Moreover, the pre-trained ChestX-ray6 model showed a superior performance compared to state-of-the-art models with a 97.94% accuracy and 98% recall in binary classification of normal and pneumonia patients.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Chemistry, Analytical
Rita Goel, Irfan Mehmood, Hassan Ugail
Summary: This study investigates the use of deep learning models for accurate identification of siblings through facial recognition, finding that VGGFace has the highest accuracy when comparing full-frontal-face and eyes, while FaceNet performs best when comparing noses.
Article
Computer Science, Software Engineering
Divine Senanu Ametefe, Suzi Seroja Sarnin, Darmawaty Mohd Ali, Zaigham Zaheer Muhammad
Summary: This article introduces how to develop a fingerprint pattern classifier using deep transfer learning and data augmentation to decrease the number of matching comparisons in automated fingerprint identification systems. The experimental results show that data augmentation improves the accuracy of the fingerprint pattern classifier models.
Article
Chemistry, Analytical
Sunday Ajala, Harikrishnan Muraleedharan Jalajamony, Renny Edwin Fernandez
Summary: This study combines a textile electrode-based DEP sensing system with deep learning to accurately estimate the DEP forces on micro particles. By training three deep convolutional neural networks, the researchers demonstrate that their deep learning model is capable of processing micrographs and accurately estimating the DEP forces. The method shows robustness in unfavorable real-world settings and can be used for direct estimation of dielectrophoretic force in point-of-care settings.
Article
Chemistry, Multidisciplinary
Ahmed Alwakeel, Mohammed Alwakeel, Mohammad Hijji, Tausifa Jan Saleem, Syed Rameem Zahra
Summary: Image classification is a significant task in smart city applications, and the deployment of classification models with good generalization accuracy is crucial for reliable decision-making. Decision fusion, which involves using multiple classifiers and combining their decisions, can improve generalization accuracy. This paper proposes and evaluates two methods for achieving dissimilarity in decision fusion: using dissimilar classifiers with different architectures and using similar classifiers with different batch sizes. The paper also compares various decision fusion strategies.
APPLIED SCIENCES-BASEL
(2023)
Article
Computer Science, Hardware & Architecture
Ozlem Polat, Cahfer Gungen
Summary: This study proposes a solution for classifying brain tumors in MR images using transfer learning networks and tests the performance of various neural networks under different optimization algorithms. The results show that the proposed transfer learning methods can achieve high performance in classifying the most common brain tumors.
JOURNAL OF SUPERCOMPUTING
(2021)
Article
Agronomy
Renato J. Horikoshi, Hallison Vertuan, Ancideriton A. de Castro, Kimberly Morrell, Cara Griffith, Adam Evans, Jianguo Tan, Peter Asiimwe, Heather Anderson, Marcia O. M. A. Jose, Patrick M. Dourado, Geraldo Berger, Samuel Martinelli, Graham Head
Summary: The research showed that MON 95379, expressing Cry1B.868 and Cry1Da_7 proteins, effectively protected maize plants against feeding damage by fall armyworm, providing a potential alternative for managing resistance issues in South America.
PEST MANAGEMENT SCIENCE
(2021)
Article
Ecology
Farian S. Ishengoma, Idris A. Rai, Said Rutabayiro Ngoga
Summary: This study proposes a hybrid convolutional neural network model that combines UAV technology and VGG16 with InceptionV3 models for accelerated detection of fall armyworm-infested maize leaves. Comparisons show that the proposed hybrid model outperforms four existing CNN models in terms of accuracy and training time.
ECOLOGICAL INFORMATICS
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Farian S. Ishengoma, Idris A. Rai, Ignace Gatare
Summary: Automatic plant disease detection can be achieved by deploying unmanned aerial vehicles (UAV) programmed with machine learning algorithms. Improving the contrast of captured images can aid in reducing misclassification.
DATA SCIENCE AND ALGORITHMS IN SYSTEMS, 2022, VOL 2
(2023)