Reinforcement learning on slow features of high-dimensional input streams. by Robert Legenstein, Niko Wilbert, Laurenz Wiskott

“…The system is composed of a hierarchical slow feature analysis (SFA) network for preprocessing and a simple neural network on top that is trained based on rewards. …”
Get full text

XSE-TomatoNet: An explainable AI based tomato leaf disease classification method using EfficientNetB0 with squeeze-and-excitation blocks and multi-scale feature fusion by Md Assaduzzaman, Prayma Bishshash, Md. Asraful Sharker Nirob, Ahmed Al Marouf, Jon G. Rokne, Reda Alhajj

“…Finally, the best model was integrated into a web-based system for practical use by tomato cultivators. • XSE-TomatoNet is an enhanced version of EfficientNetB0 which incorporates Squeeze-and-Excitation (SE) blocks and multi-scale feature fusion. • XSE-TomatoNet outperformed MobileNet (87.44%) and VGG-19 (95.50%), in terms of accuracy, achieving 99.41%. • Integration of interpretation using LIME and SHAP models gives higher level understanding of the diseases and employment of Grad-CAM and Grad-CAM++ shows visual representation of the diseased leaves.…”
Get full text

3D FACIAL LANDMARK-BASED DECEPTION DETECTION IN VIDEO USING GRU MODEL by Amira Himyari, Israa Hadi

“…In this paper, we first proposed a 3D 478 Mediapipe Face Mesh Model to extract facial landmarks that reflect facial micro expression, this is contrary to the traditional method, which relies on human judgment and the use of devices to detect facial micro expression. Second, a feature selection-based multivariate mutual information method was proposed to select facial landmarks that are most related to the deceptive cues and have critical influence on the classification task. …”
Get full text

A new machine learning approach based on spatial fuzzy data correlation for recognizing sports activities by Xu Pengru, Zhou Junhui, Kausar Nasreen, Lin Chunlei, Lu Qianqian, Ghaderpour Ebrahim, Pamucar Dragan, Zadeh Ardashir M.

Get full text

Detecting emotional disorder with eye movement features in sports watching by Wei Qiang, Wei Qiang, Lin Yang, Xucheng Zhang, Na Liu, Yanyong Wang, Jipeng Zhang, Yixin Long, Weiwei Xu, Wei Sun

“…A decision tree model trained on all significant features achieved 0.92 accuracy, 0.80 precision, and an AUC of 0.94. …”
Get full text

Sliding mode control of electronic mechanical braking system based on new power exponential by CHANG Jiujian, WANG Wenlong, ZHANG Yajie

Get full text

Test-Time Training with Adaptive Memory for Traffic Accident Severity Prediction by Duo Peng, Weiqi Yan

“…While distribution shift is a common challenge in machine learning, Transformer-based models—despite their ability to capture long-term dependencies—often lack mechanisms for dynamic adaptation during inferencing. …”
Get full text

The impact of Inter-observation variation on radiomic features of pulmonary nodules by Wenchao Zhu, Wenchao Zhu, Fangyi Xu, Fangyi Xu, Kaihua Lou, Kaihua Lou, Xia Qiu, Xia Qiu, Dingping Huang, Dingping Huang, Shaoyu Huang, Shaoyu Huang, Dong Xie, Dong Xie, Hongjie Hu, Hongjie Hu

Get full text

Research on Design of Intelligent Background Differential Model for Training Target Monitoring by Ya Liu, Fusheng Jiang, Yuhui Wang, Lu OuYang, Bo Gao, Jinling Jiang, Bo Zhang

“…Aiming at the problem of high failure rate in the detection of sports targets under complex backgrounds, this paper proposes a research on the design of an intelligent background differential model for training target monitoring. This paper proposes a background difference method based on RGB colour separation. …”
Get full text

The effects of fitness training on physical preparedness of highly qualified football players by Gennadii Lisenchuk, Irene Khmelnitska, Konstantin Bogatyrev, Borys Kokarev, Svitlana Kokareva, Viktor Derkach, Igor Martsinkovsky, Svitlana Krupenya, Miroslava Cieślicka

“…The main feature of this program was the use of innovative methods of modern fitness training: TRX/TRX-Rip, MAX®, Tabata, High-Intensity Interval Training (HIIT), Strenflex, 6D Sliding, myo-fascial release, in addition to the classic methods of exercises. …”
Get full text

The implementation of the situational control concept of information security in automated training systems by A. M. Chernih, S. V. Fedoseev

“…Developed method of situational control of information security in automated learning systems, involves the participation of the operator in the development and decision-making (dialogue procedures statement of objectives situational control, the formation of the base of alternative sets of control actions, etc.).Another important feature of this technique is the necessity of using previously developed models (models of decision-making situation, a model of coordination and planning of operation of a subsystem of the control and protection of information, models of information processing about the status of the subsystem analysis models and evaluation of results) and the database obtained on the basis of operating experience of information protection systems in the automated learning systems.The implementation of the concept of situational control of information security ensures the timely adaptation of the algorithms and parameters of the information security system to changes in the external environment and the nature of tasks within the education systems and on this basis allows to improve the characteristics of the information protection system in the automated learning systems.…”
Get full text

NBDNet: A Self-Supervised CNN-Based Method for InSAR Phase and Coherence Estimation by Hongxiang Li, Jili Wang, Chenguang Ai, Yulun Wu, Xiaoyuan Ren

Get full text

Comparative analysis of multi-zone peritumoral radiomics in breast cancer for predicting NAC response using ABVS-based deep learning models by Minfang Wang, Wanjun Chen, Ruiping Ren, Yuanwei Lin, Jiawen Tang, Meng Wu

“…The study cohort was divided into training and testing cohorts. ROI-specific TabNet models were developed using the training cohort data. …”
Get full text

Evaluation of a fusion model combining deep learning models based on enhanced CT images with radiological and clinical features in distinguishing lipid-poor adrenal adenoma from me... by Shao-Cai Wang, Sheng-Nan Yin, Zi-You Wang, Ning Ding, Yi-Ding Ji, Long Jin

“…Patients were randomly divided into training and testing sets in a 7:3 ratio. Six convolutional neural network (CNN)-based deep learning models were employed, and the model with the highest diagnostic performance was selected based on the area under curve(AUC) of the ROC. …”
Get full text

PI-ADFM: Enhancing Multimodal Remote Sensing Image Matching Through Phase-Integrated Aggregated Deep Features by Haiqing He, Shixun Yu, Yongjun Zhang, Yufeng Zhu, Ting Chen, Fuyang Zhou

“…Subsequently, an attention-based multilevel feature interaction and aggregation module is crafted to encapsulate a comprehensive representation of both local and global features of keypoints. …”
Get full text

Perceptions of TPACK in genre-based pedagogy: the role of socio-demographics and ICT competence among pre-service Indonesian language teachers by   Sultan, Muhammad Rapi, Suardi, Asri Ismail

“…The findings concluded that, information and communication technology competence shape pre-service Indonesian language teachers’ perceptions of TPACK in genre-based pedagogy. The results underscore the need for teacher training institution curricula and learning designs to consider the social and individual characteristics of the students.…”
Get full text

An Accurate Deep Key-Point Prediction Model With Low-Level Texture Refinement and High-Level Semantic Enhancement for Bolt Vertex Detection in Industrial Machine Systems by Jiaqi Liu, Yingbo Wang, Mingyue Lang, Fengyuan Zuo

“…In addition, we introduced a masked-based unsupervised pre-training paradigm based on convolutional structure to enhance the feature representation ability of the above model. …”
Get full text

Modified LSTM based skin lesion segmentation and classification using optimization concept by S. Gomathi, N. Arunachalam

Get full text

A Method for the Automatic Selection of Training Tasks in Learning Environment for IT Students by S. U. Rzheutskaya, M. V. Kharina

“…The learning phase of the model consists of building a decision tree based on a training sample containing data on precedents for students to complete tasks. …”
Get full text

Hybrid PI and Fuzzy Logic Control for Energy Optimization in Train Operations by Hwan-Hee Cho, Jae-Won Kim, Min-Sup Song, Chi-Myeong Yun, Gyu-Jung Cho, Zhongbei Tian

“…This paper presents a Fuzzy logic-based train control algorithm designed to enhance energy efficiency across a complete railway route. …”
Get full text