Article
Cardiac & Cardiovascular Systems
Xiehui Chen, Wenqin Guo, Lingyue Zhao, Weichao Huang, Lili Wang, Aimei Sun, Lang Li, Fangrui Mo
Summary: In this study, a neural network algorithm was developed to automatically diagnose AMI from 12-lead ECGs, with high AUC and performance metrics in the training, validation, and testing sets. The algorithm was also able to accurately diagnose MI location. The residual network-based algorithm showed effectiveness in automatic AMI and MI location diagnosis.
FRONTIERS IN CARDIOVASCULAR MEDICINE
(2021)
Article
Computer Science, Artificial Intelligence
Xingdong Wu, Chao Liu, Lijun Wang, Muhammad Bilal
Summary: Smart healthcare monitoring systems, enabled by the Internet of Things and deep learning, have facilitated telemedicine and disease prevention. This research introduces an IoT-based real-time health monitoring system utilizing deep learning algorithms and wearable medical devices. By studying Sanda athletes, the proposed system enables doctors to properly analyze athletes' conditions and provide appropriate treatment remotely. The system's performance is evaluated using various statistical-based metrics, proving its effectiveness in diagnosing diseases among athletes.
NEURAL COMPUTING & APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Vidit Jain, Rohit Kumar Kaliyar, Anurag Goswami, Pratik Narang, Yashvardhan Sharma
Summary: In the current era of social media, the prevalence of fake news is rapidly increasing, making it difficult to distinguish between real and fake news. This paper aims to design an efficient deep learning model to detect the degree of fakeness in news statements, proposing a simple network architecture that has shown efficacy and efficiency on various real-world datasets.
NEURAL COMPUTING & APPLICATIONS
(2022)
Article
Environmental Sciences
T. Daniya, S. Vigneshwari
Summary: In this paper, a hybrid optimization algorithm is proposed for categorizing plant diseases, and deep learning algorithms are applied for image processing and feature extraction. The proposed method achieves high accuracy and sensitivity in the identification and classification of plant diseases.
JOURNAL OF ENVIRONMENTAL INFORMATICS
(2023)
Article
Computer Science, Information Systems
Mohammad Hashem Haghighat, Jun Li
Summary: The novel voting-based deep learning framework VNN proposed in this paper effectively increases system performance and accuracy, helping security specialists to detect more complicated attacks. Experimental results showed a significant reduction in false alarms by up to 75% compared to original deep learning models.
TSINGHUA SCIENCE AND TECHNOLOGY
(2021)
Review
Chemistry, Analytical
Qaisar Abbas, Abdullah Alsheddy
Summary: The paper reviews state-of-the-art approaches for predicting unsafe driving styles using IoT-based architectures, focusing on the major differences among multi-sensors, smartphone-based, and cloud-based systems. It discusses the challenges faced by machine learning techniques, particularly the deep learning model, in predicting driver hypovigilance. State-of-the-art comparisons using driving simulators are conducted to evaluate the performance of these architectures for detecting driver fatigue.
Article
Computer Science, Hardware & Architecture
Safi Ullah, Jawad Ahmad, Muazzam A. Khan, Mohammed S. Alshehri, Wadii Boulila, Anis Koubaa, Sana Ullah Jan, Munawwar Iqbal Ch
Summary: The Internet of Things (IoT) is vulnerable to security breaches and attacks, and there is a need for advanced intrusion detection systems (IDS). This study proposes a transformer neural network-based IDS (TNN-IDS) specifically designed for MQTT-enabled IoT networks, which outperforms other systems in detecting malicious activities with an accuracy of 99.9%.
Article
Computer Science, Hardware & Architecture
Kutub Thakur, Hamed Alqahtani, Gulshan Kumar
Summary: The intelligent system IDGADS is capable of quickly detecting algorithmically generated domains with 99% accuracy based on easy-to-compute features of real domain name system (DNS) traffic. It can serve as the first line of defense in a security stack for validating DNS queries.
COMPUTERS & ELECTRICAL ENGINEERING
(2021)
Article
Nuclear Science & Technology
JaeKwan Park, TaekKyu Kim, SeungHwan Seong
Summary: This study proposes a mechanism for aging detection using LSTM, which consists of three phases including input preprocessing, LSTM network training, and output evaluation. The experiment results demonstrate the stable detection capability of the proposed approach.
PROGRESS IN NUCLEAR ENERGY
(2021)
Article
Chemistry, Analytical
Muhammad Husnain, Khizar Hayat, Enrico Cambiaso, Ubaid U. Fayyaz, Maurizio Mongelli, Habiba Akram, Syed Ghazanfar Abbas, Ghalib A. Shah
Summary: In this paper, a MQTT parsing engine is designed and developed to serve as an initial layer in network-based IDS for extensive checking of IoT protocol vulnerabilities and improper usage. By rigorously validating packet fields, the proposed solution effectively detects and prevents the exploitation of vulnerabilities on IoT protocols.
Article
Automation & Control Systems
Neeru Mago, Satish Kumar, Lalit Mohan Goyal
Summary: This study proposes an ensemble model based on deep learning to tackle weather condition effects by training CNN's network considering five techniques, achieving significant improvement in terms of accuracy compared with existing state-of-art methods for parking slot status detection.
INTERNATIONAL JOURNAL OF FUZZY SYSTEMS
(2022)
Article
Computer Science, Interdisciplinary Applications
G. S. R. Emil Selvan, M. Azees, CH. Rayala Vinodkumar, G. Parthasarathy
Summary: This paper proposes a hybrid optimization-based deep learning technique for multi-level intrusion detection, which improves the accuracy and timeliness of detection. The method shows good performance in experiments.
ADVANCES IN ENGINEERING SOFTWARE
(2022)
Review
Computer Science, Artificial Intelligence
Luis Guarda, Juan E. Tapia, Enrique Lopez Droguett, Marcelo Ramos
Summary: This paper presents a Deep Learning-based method for drowsiness detection using CapsNet and spectrogram images of EEG signals. The proposed CapsNet model outperforms the traditional Convolutional Neural Network in terms of accuracy and sensitivity. This method is effective for handling small amounts of data and biomedical signals.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Food Science & Technology
R. Nithya, B. Santhi, R. Manikandan, Masoumeh Rahimi, Amir H. Gandomi
Summary: The article highlights the importance of machine learning techniques in agricultural applications, specifically in developing a computer-assisted system for mango quality grading and defect detection. Efficient classification results were achieved using deep learning methods, particularly CNN.
Article
Engineering, Civil
Xinyu Wu, Zhiyong Chen, Chuntian Cheng, Shuai Yin, Huaying Su
Summary: A deep neural network SSDP (DNN-SSDP) method is proposed to solve the problem of multiple reservoir operations. The method combines DNN, SSDP, and simulation to improve the efficiency of the solution by using a small-scale and irregularly distributed state set.
JOURNAL OF HYDROLOGY
(2022)
Review
Biochemistry & Molecular Biology
Hangfei Chen, Dheerendranath Battalapalli, Mohamed S. Draz, Pengfei Zhang, Zhi Ruan
Summary: This review discusses the characteristics, designing strategies, and recent progress in the development and application of antimicrobial CPPs as potent antibacterial agents against multidrug-resistant bacteria, providing a new approach to combating multidrug-resistant bacteria.
CURRENT MEDICINAL CHEMISTRY
(2021)
Article
Genetics & Heredity
V. W. Fitz, M. K. Kanakasabapathy, P. Thirumalaraju, H. Kandula, L. B. Ramirez, L. Boehnlein, J. E. Swain, C. L. Curchoe, K. James, I Dimitriadis, I Souter, C. L. Bormann, H. Shafiee
Summary: Incorporating an AI framework improved the performance of trained embryologists in selecting euploid embryos destined to implant, with an average increase of 11.1% in successful selection rate. All embryologists showed improvement in selecting embryos with the aid of the AI algorithm, regardless of their level of experience.
JOURNAL OF ASSISTED REPRODUCTION AND GENETICS
(2021)
Article
Materials Science, Multidisciplinary
Filipe S. R. Silva, Eda Erdogmus, Ahmed Shokr, Hemanth Kandula, Prudhvi Thirumalaraju, Manoj K. Kanakasabapathy, Joseph M. Hardie, Luis G. C. Pacheco, Jonathan Z. Li, Daniel R. Kuritzkes, Hadi Shafiee
Summary: This study introduces an amplification-free CRISPR/Cas12a-based technology for SARS-CoV-2 RNA detection, with results readout using a smartphone camera. The method achieves high analytical sensitivity and accuracy, with results obtained in approximately 71 minutes.
ADVANCED MATERIALS TECHNOLOGIES
(2021)
Article
Genetics & Heredity
Karissa C. Hammer, Victoria S. Jiang, Manoj Kumar Kanakasabapathy, Prudhvi Thirumalaraju, Hemanth Kandula, Irene Dimitriadis, Irene Souter, Charles L. Bormann, Hadi Shafiee
Summary: This study shows that convolutional neural networks can accurately identify patient identity of embryos based on image data alone. The technology achieves 100% accuracy in identifying embryos on day 3 and day 5, and can be integrated into existing imaging systems and laboratory protocols to improve specimen tracking.
JOURNAL OF ASSISTED REPRODUCTION AND GENETICS
(2022)
Article
Genetics & Heredity
Panagiotis Cherouveim, Victoria S. Jiang, Manoj Kumar Kanakasabapathy, Prudhvi Thirumalaraju, Irene Souter, Irene Dimitriadis, Charles L. Bormann, Hadi Shafiee
Summary: This study evaluated the utility of an AI-QA tool in monitoring the performance of ART staff. The results showed that AI could accurately predict the implantation rates of embryo transfers and embryo thawing procedures, and in some cases, the actual performance of certain providers was lower than the AI predictions. This indicates that AI-based QA tools can provide accurate, reproducible, and efficient staff performance monitoring.
JOURNAL OF ASSISTED REPRODUCTION AND GENETICS
(2023)
Article
Genetics & Heredity
Victoria S. Jiang, Deeksha Kartik, Prudhvi Thirumalaraju, Hemanth Kandula, Manoj Kumar Kanakasabapathy, Irene Souter, Irene Dimitriadis, Charles L. Bormann, Hadi Shafiee
Summary: This study investigates the use of deep learning artificial intelligence algorithms to accurately identify key morphologic landmarks on oocytes and cleavage stage embryo images for micromanipulation procedures. Two convolutional neural network models were trained and tested, demonstrating the potential of deep CNN models in accurately identifying these landmarks. These findings are important for the automation of micromanipulation procedures.
JOURNAL OF ASSISTED REPRODUCTION AND GENETICS
(2023)
Article
Immunology
Doaa Waly, Aradana Muthupandian, Chia-Wei Fan, Harrison Anzinger, Brad G. G. Magor
Summary: This study reveals the existence of Aicda(+) cell clusters in fish that functionally resemble germinal centers in mammals. These clusters undergo B-cell clonal expansion and VDJ somatic hypermutation to achieve antibody affinity maturation. The study also provides evidence for positive selection for replacement mutations in regions encoding the antigen contact loops, leading to functional antibody modification. Additionally, melano-macrophages in the clusters trap antigens used for post-mutation B-cell selection, serving a role similar to follicular dendritic cells in mammalian germinal centers.
FRONTIERS IN IMMUNOLOGY
(2022)
Article
Agriculture, Dairy & Animal Science
Aridany Suarez-Trujillo, Hemanth Kandula, Jasmine Kumar, Anjali Devi, Larissa Shirley, Prudhvi Thirumalaraju, Manoj Kumar Kanakasabapathy, Hadi Shafiee, Liane Hart
Summary: The study aimed to validate the use of a smartphone-based device, Fertile-Eyez (FE), for measuring sperm concentration, total motility, and morphology in boar semen samples. The results of the experiment demonstrate that FE is capable of assessing concentration, motility, and morphology of boar semen samples.
TRANSLATIONAL ANIMAL SCIENCE
(2022)
Meeting Abstract
Obstetrics & Gynecology
V. Jiang, C. Bormann, I. Souter, I. Dimitriadis, M. K. Kanakasabapathy, P. Thirumalaraju, H. Shafiee
HUMAN REPRODUCTION
(2022)
Meeting Abstract
Obstetrics & Gynecology
Caitlin R. Sacha, Stylianos Vagios, Irene Souter, Manoj Kumar Kanakasabapathy, Prudhvi Thirumalaraju, Hadi Shafiee, Charles L. Bormann
FERTILITY AND STERILITY
(2021)
Meeting Abstract
Obstetrics & Gynecology
C. Bormann, M. Kanakasabapathy, P. Thirumalaraju, I. Dimitriadis, I. Souter, K. Hammer, H. Shafiee
HUMAN REPRODUCTION
(2021)
Article
Multidisciplinary Sciences
Prudhvi Thirumalaraju, Manoj Kumar Kanakasabapathy, Charles L. Bormann, Raghav Gupta, Rohan Pooniwala, Hemanth Kandula, Irene Souter, Irene Dimitriadis, Hadi Shafiee
Summary: The quality of the transferred embryo significantly impacts the success of IVF cycles, and utilizing convolutional neural networks to differentiate embryo morphology quality was evaluated across various deep learning architectures, with Xception performing the best.