xAAD–Post-Feedback Explainability for Active Anomaly Discovery by Damir Kopljar, Vjekoslav Drvar, Jurica Babic, Vedran Podobnik

“…Anomaly detection algorithms are widely used across various domains, but they often suffer from high false positive rates and lack of interpretability. …”
Get full text

Bottlenose dolphin identification using synthetic image-based transfer learning by Changsoo Kim, Byung-Yeob Kim, Dong-Guk Paeng

“…Despite recent developments in learning-based photo-ID algorithms, the lack of training data for these models has become a bottleneck for improving the accuracy of these algorithms. …”
Get full text

A hybrid AI-CFD framework for optimizing heat transfer of a premixed methane-air flame jet on inclined surfaces by Panit Kamma, Kittipos Loksupapaiboon, Juthanee Phromjan, Chakrit Suvanjumrat

“…To reduce the computational expense of these simulations, a hybrid Artificial Neural Network-Genetic Algorithm (ANN-GA) model was developed. The ANN accurately predicted thermal efficiency based on operational parameters, while the GA optimized these inputs to achieve maximum thermal efficiency of 76.9955 %, closely matching the CFD-predicted value of 70.86 % (discrepancy:6.1355 %). …”
Get full text

Synchrony Vision: Capturing Body Motion Synchrony Through Phase Difference Using the Kinect by Jinhwan Kwon

“…To enhance its accuracy, potential improvements include algorithmic refinements, hardware upgrades, and AI-driven models to adaptively refine motion detection.…”
Get full text

Tissue Puncture Event Detection in Needle Procedures using Vibroacoustic Signals - ResNet optimised Phantom Results by Serwatka Witold, Rzepka Dominik, Oran Hamza, Steeg Katharina, Krombach Gabriele, Stefanski Juliusz, Heryan Katarzyna, Friebe Michael

“…This result is very encouraging, as several possible improvements have been identified that will be implemented in the next research steps together with a robot assisted insertion and an automatic video annotation algorithm.…”
Get full text

Energy management system design for high energy consuming enterprises integrating the Internet of Things and neural networks by Zhaolin Wang, Zhiping Zhang

“…The combination of neural network model prediction and optimization algorithms can achieve real-time monitoring, prediction, and optimization control of energy consumption. …”
Get full text

Application of artificial intelligence in the diagnosis of malignant digestive tract tumors: focusing on opportunities and challenges in endoscopy and pathology by Yinhu Gao, Peizhen Wen, Yuan Liu, Yahuang Sun, Hui Qian, Xin Zhang, Huan Peng, Yanli Gao, Cuiyu Li, Zhangyuan Gu, Huajin Zeng, Zhijun Hong, Weijun Wang, Ronglin Yan, Zunqi Hu, Hongbing Fu

“…Results In the field of endoscopy, multiple deep learning models have significantly improved detection rates in real-time polyp detection, early gastric cancer, and esophageal cancer screening, with some commercialized systems successfully entering clinical trials. …”
Get full text

Human face localization and detection in highly occluded unconstrained environments by Abdulaziz Alashbi, Abdul Hakim H.M. Mohamed, Ayman A. El-Saleh, Ibraheem Shayea, Mohd Shahrizal Sunar, Zieb Rabie Alqahtani, Faisal Saeed, Bilal Saoud

“…Unconstrained face identification has been significantly improved by the advancements in Deep Learning algorithms (DL). …”
Get full text

Development and validation of a nomogram for predicting low Kt/Vurea in peritoneal dialysis patients by Danfeng Zhang, Tian Zhao, Liting Gao, Huan Zhu, Haowei Jin, Guiling Liu, Deguang Wang

“…Conclusions We developed a nomogram that accurately predicts PD total Kt/Vurea in incident PD patients. This model can be a valuable tool for identifying patients at risk of low PD total Kt/Vurea, facilitating timely interventions to improve patient outcomes.…”
Get full text

A Machine Learning Approach for Predicting Maternal Health Risks in Lower-Middle-Income Countries Using Sparse Data and Vital Signs by Avnish Malde, Vishnunarayan Girishan Prabhu, Dishant Banga, Michael Hsieh, Chaithanya Renduchintala, Ronald Pirrallo

“…Observations from our study demonstrate the feasibility of using sparse data and features for maternal health risk prediction using algorithms. By focusing on data from resource-constrained settings, we show that machine learning offers a convenient and accessible solution to improve prenatal care and reduce maternal deaths in LMICs.…”
Get full text

Trust-driven approach to enhance early forest fire detection using machine learning by Tayyab Khan, Karan Singh, Bhoopesh Singh Bhati, Khaleel Ahmad, Amal Al-Rasheed, Masresha Getahun, Ben Othman Soufiene

“…Our method seeks to reduce fire detection time and improve the reliability of the detection process. …”
Get full text

Leveraging ensemble convolutional neural networks and metaheuristic strategies for advanced kidney disease screening and classification by Abeer saber, Esraa Hassan, Samar Elbedwehy, Wael A. Awad, Tamer Z. Emara

“…The proposed model combines multiple DL models to improve overall performance by leveraging the strengths of different architectures, ensembles can enhance accuracy, robustness, and generalization. …”
Get full text

Vision-Based Activity Recognition for Unobtrusive Monitoring of the Elderly in Care Settings by Rahmat Ullah, Ikram Asghar, Saeed Akbar, Gareth Evans, Justus Vermaak, Abdulaziz Alblwi, Amna Bamaqa

“…The system integrates a frame differencing algorithm with adjustable sensitivity parameters and an anomaly detection model tailored to identify deviations from individual behavior patterns without relying on large volumes of labeled data. …”
Get full text

Adaptive Control Strategy for Automotive Magnetorheological Dampers Based on Artificial Neural Networks by C. Steven Diaz-Choque, Luis C. Felix-Herran, Renato Galluzzi, Riccardo Cespi, Jorge de J. Lozoya-Santos, Ricardo A. Ramirez-Mendoza

“…The formulation of the controller considers a magnetorheological damper represented through the Bouc-Wen model. A stochastic gradient descent algorithm with backward propagation is used to train the artificial neural network that then selects the controller gains in real time. …”
Get full text

Identification and Evaluation of Lipocalin-2 in Sepsis-Associated Encephalopathy via Machine Learning Approaches by Hu J, Chen Z, Wang J, Xu A, Sun J, Xiao W, Yang M

“…Subsequently, neuroinflammation-related genes were obtained to construct a neuroinflammation-related signature. The AddModuleScore algorithm was used to calculate neuroinflammation scores for each cell subpopulation, whereas the CellCall algorithm was used to assess the crosstalk between neutrophils and other cell subpopulations. …”
Get full text

Fiber-Optic Sensor Spectrum Noise Reduction Based on a Generative Adversarial Network by Yujie Lu, Qingbin Du, Ruijia Zhang, Bo Wang, Zigeng Liu, Qizhe Tang, Pan Dai, Xiangxiang Fan, Chun Huang

“…This study proposes a deep-learning-based denoising method for fiber-optic sensors, which involves pre-processing the sensor spectrum into a 2D image and training with a cycle-consistent generative adversarial network (Cycle-GAN) model. The pre-trained algorithm demonstrates the ability to effectively denoise various spectrum types and noise profiles. …”
Get full text

An optimization based framework for water quality assessment and pollution source apportionment employing GIS and machine learning techniques for smart surface water governance by Abhijeet Das

“…In addition, the study area's hydro-chemical facies were examined, and machine learning models’ hyperparameters such as Random Forest (RF), Borda Scoring Algorithm (BSA), Decision Tree (DT), Multilayer Perception (MLP), and Naïve Bayes (NB), were executed before, to training and testing the samples of surface water. …”
Get full text

A FixMatch Framework for Alzheimer’s Disease Classification: Exploring the Trade-Off Between Supervision and Performance by Al Hossain, Umme Hani Konok, MD Tahsin, Raihan Ul Islam, Mohammad Rifat Ahmmad Rashid, Mohammad Shahadat Hossain, Karl Andersson

“…Alzheimer’s Disease (AD) poses a major challenge for healthcare systems worldwide, as timely and accurate diagnosis is crucial for patient management and outcome improvement. While experienced medical professionals can often identify AD through conventional assessment methods, limited resources and growing patient populations make large-scale and rapid screening increasingly necessary. …”
Get full text

A lightweight YOLO network using temporal features for high-resolution sonar segmentation by Sen Gao, Sen Gao, Wei Guo, Wei Guo, Gaofei Xu, Gaofei Xu, Ben Liu, Ben Liu, Yu Sun, Bo Yuan

“…The model was trained and evaluated on a high-resolution sonar dataset collected using an AUV-mounted Oculus MD750d multibeam forward-looking sonar in two distinct underwater environments.ResultsImplementation on Nvidia Jetson TX2 demonstrated significant performance improvements. (1) Processing latency reduced to 87.4 ms (keyframes) and 35.3 ms (non-keyframes)(2)Maintained competitive segmentation accuracy compared to conventional methods and achieved low latency.DiscussionThe proposed architecture successfully addresses the speed-accuracy trade-off in sonar image segmentation through its innovative temporal feature utilization and computational skipping mechanism. …”
Get full text

Enhancing credit card fraud detection: the impact of oversampling rates and ensemble methods with diverse feature selection by Mohamed Akouhar, Abdallah Abarda, Mohamed El Fatini, Mohamed Ouhssini

“…The results show that the application of SMOTE significantly improves the performance of the machine learning models, with an optimal oversampling rate of 20% identified. …”
Get full text