Operational Forecasting of Wind Speed for an Self-Contained Power Assembly of a Traction Substation by P. V. Matrenin, A. I. Khalyasmaa, A. G. Rusina, S. A. Eroshenko, N. A. Papkova, D. A. Sekatski

“…A specific feature of this work is the stability investigation of the model trained on the data of long-term observations to long-term changes, as well as the analysis of the possibilities of improving the accuracy of forecasting due to regular further training of the model on newly available data. …”
Get full text

Dynamic bone recognition for robotic vertebral plate cutting via unit energy consumption and SVM optimized by PSO by Heqiang Tian, Jing Zhao, Ying Sun, Jinchang An

“…The optimized model achieved bone identification accuracy of 90.64%, compared to 83.56% using traditional feature extraction techniques. …”
Get full text

WSDC-ViT: a novel transformer network for pneumonia image classification based on windows scalable attention and dynamic rectified linear unit convolutional modules by Yu Gu, Haotian Bai, Meng Chen, Lidong Yang, Baohua Zhang, Jing Wang, Xiaoqi Lu, Jianjun Li, Xin Liu, Dahua Yu, Ying Zhao, Siyuan Tang, Qun He

“…These results highlight the model’s superior performance compared to existing automated pneumonia classification approaches, underscoring its potential clinical applicability.…”
Get full text

Cochlear Implantation in a Patient with a Novel POU3F4 Mutation and Incomplete Partition Type-III Malformation by Xiuhua Chao, Yun Xiao, Fengguo Zhang, Jianfen Luo, Ruijie Wang, Wenwen Liu, Haibo Wang, Lei Xu

“…The genetic analysis was conducted in his family, including the whole-exome sequencing combined with Sanger sequencing and bioinformatic analysis. Clinical features, preoperative auditory and speech performances, and postoperative outcomes of cochlear implant (CI) were assessed on the proband and his family. …”
Get full text

Exploring the origin of the rarest stable isotopes naturally occurring on Earth with real photon beams by Banu Adriana

“…The astrophysical phenomenon responsible for this synthesis is termed the p-process. Though modelling the p-process nucleosynthesis is a daunting task, significant progress can be made by performing key experimental studies, which can constrain Hauser-Feshbach statistical nuclear models used to calculate the many unknown astrophysically relevant stellar reaction rates. …”
Get full text

Explainable Machine Learning in the Prediction of Depression by Christina Mimikou, Christos Kokkotis, Dimitrios Tsiptsios, Konstantinos Tsamakis, Stella Savvidou, Lillian Modig, Foteini Christidi, Antonia Kaltsatou, Triantafyllos Doskas, Christoph Mueller, Aspasia Serdari, Kostas Anagnostopoulos, Gregory Tripsianis

“…The study employed four machine learning (ML) methods to assess depression: logistic regression (LR), support vector machine (SVM), XGBoost, and neural networks (NNs). These models were compared to identify the best-performing approach. …”
Get full text

Functional Connectivity Metrics in Temporal Lobe Epilepsy: A Machine Learning Perspective With MEG by M. V. Suhas, N. Mariyappa, A. Karunakar Kotegar, M. Ravindranadh Chowdary, K. Raghavendra, Ajay Asranna, L. G. Viswanathan, H. Anitha, Sanjib Sinha

“…Various machine learning models demonstrate high classification performance, with accuracies reaching up to 100% in particular frequency bands in agreement with the Chi2 feature importance analysis. …”
Get full text

Machine learning for predicting all-cause mortality of metabolic dysfunction-associated fatty liver disease: a longitudinal study based on NHANES by Xueni Wang, Huihui Chen, Luqiao Wang, Wenguang Sun

“…The data (demographic, behavioral factors and laboratory indicators) were utilized to construct machine learning models (Coxnet, RSF, GBS) after feature selection. …”
Get full text

探討強化學習演算法之素材推薦機制與AI學習履歷之學習者感知 Learner Perceptions of AI-Powered Learning Portfolios and Personalized Material Recommendation Mechanisms in Reinforcement Learning Algorithms... by 曾建維 Jian-Wei Tzeng, 黃天麒 Tien-Chi Huang, 薛承祐 Cheng-Yu Hsueh, 廖英淞 Ying-Song Liao

“…In contrast to traditional teacher-centered models, online autonomous learning courses prioritize self-directed learning. …”
Get full text

Generalization challenges in video deepfake detection: methods, obstacles, and technological advances by LI Junjie, WANG Jianzong, ZHANG Xulong, QU Xiaoyang

“…Regarding the challenges of cross-dataset detection, the paper analyzes how differences in feature distributions between datasets lead to the performance degradation of traditional deep learning models in cross-domain applications. …”
Get full text

Generalization challenges in video deepfake detection: methods, obstacles, and technological advances by LI Junjie, WANG Jianzong, ZHANG Xulong, QU Xiaoyang

“…Regarding the challenges of cross-dataset detection, the paper analyzes how differences in feature distributions between datasets lead to the performance degradation of traditional deep learning models in cross-domain applications. …”
Get full text

Pest detection in dynamic environments: an adaptive continual test-time domain adaptation strategy by Rui Fu, Shiyu Wang, Mingqiu Dong, Hao Sun, Mohammed Abdulhakim Al-Absi, Kaijie Zhang, Qian Chen, Liqun Xiao, Xuewei Wang, Ye Li

“…The MT-DAM integrates an object detection model with an image segmentation model, exchanging information through feature fusion at the feature extraction layer. …”
Get full text

Land use classification using multi-year Sentinel-2 images with deep learning ensemble network by J. Jagannathan, M. Thanjai Vadivel, C. Divya

“…While the data spans multiple years, each year is treated as an independent input without modeling temporal sequences. The proposed method demonstrates superior performance over UNet, ResUNet, and Attention-UNet models, achieving an accuracy of 98.21% and Dice similarity coefficient (DSC) of 88.96%. …”
Get full text

High-Relative-Bandwidth Multiband LNA Distortion Elimination With Neural Network by Zheng Xiang Li, Rui Lv

“…Additionally, by utilizing mathematical characteristics of LNA output signals, such as instantaneous rate of change, magnitude, and non-uniformly sampled memory points, it performs feature engineering to simultaneously reduce the complexity of the NN and enhance its generalization capabilities. …”
Get full text

A Novel Approach for Enhancing Code Smell Detection Using Random Convolutional Kernel Transform by Mostefai Abdelkader, Mekour Mansour

“…Objective: Despite numerous deep learning approaches for code smell detection, many still heavily rely on feature engineering processes (metrics) and exhibit limited performance. …”
Get full text

A novel theta-shaped slotted patch antenna with a unique DGS for Sub-6 GHz 5G communication by Nafis Almas Nafi, Chowdhury Tasmia Israt, K.M. Ashikur Rahman, Niloy Dutta Anik, Aminur Rahman

“…A conventional DGS for the TSPA is also modeled and fabricated to facilitate comparison. A thorough comparison of the two designs is made to show that the proposed antenna performs better than conventional DGS single-band patch antenna. …”
Get full text

Inverted-L wideband quad-port MIMO antenna with intersecting strip parasitic for 5G new radio (n77) network systems by Phakpoom Sritongnuan, Phatsakul Thitimahatthanakusol, Nathapat Supreeyatitikul, Jessada Konpang

“…The proposed antenna is distinguished using the characteristic mode (CM) technique, providing a unique method to analyze and optimize the antenna performance. The antenna is fabricated on a single-layer FR-4 substrate, with the upper layer consisting of a quad-port inverted-L monopole antenna and the lower layer featuring a partial ground plane. …”
Get full text

A Machine-Learning-Based Approach for the Detection and Mitigation of Distributed Denial-of-Service Attacks in Internet of Things Environments by Sebastián Berríos, Sebastián Garcia, Pamela Hermosilla, Héctor Allende-Cid

“…This study proposes a machine-learning-based framework to enhance DDoS attack detection and mitigation, employing Random Forest, XGBoost, and Long Short-Term Memory (LSTM) models. Two well-established datasets, CIC-DDoS2019 and N-BaIoT, were used to train and evaluate the models, with feature selection techniques applied to optimize performance. …”
Get full text

Convolutional neural networks and vision transformers for Plankton Classification by Loris Nanni, Alessandra Lumini, Leonardo Barcellona, Stefano Ghidoni

“…Such ensembles were tested together with transformer-based models in a detailed comparative analysis considering feature extraction efficiency, computational cost, and robustness to species imbalances. …”
Get full text

Comprehensive evaluation of new sorghum varieties and their light-simple and efficient production technology: a case study of Ji Niang No. 2 by Meng Liu, Huijing Liu, Han Zhang, Wenqing Zhao, Yu Zhao, Zhi Zheng, Shunguo Li

Get full text