Intelligent Evaluation of Classroom Teaching Language: Effectiveness, Application, and Optimization by FENG Xiumei, JIANG Yuchen, WANG Yiting

“…Then, an automated encoding model was constructed and tested for feasibility and effectiveness in language coding tasks. …”
Get full text

Simplified models for describing multitasking modes in living recognition systems by Golovina, Alina Andreevna, Yakhno, Vladimir Grigorevich

“…The purposeof this study is to explore the possibilities and create versions of simplified languages that describe the variety of dynamic modes during the alternating execution of multiple tasks. These languages can be used for an adequate description of experimentally recorded variants of behavior in living systems under such conditions. …”
Get full text

A New Realm of Human-AI Co-Creative Learning: AI Empowered Science and Innovation Education by WU Bian, HE Yutong

“…Additionally, the learning model can refer to the hackathon model, completing specific creative tasks through teamwork in a short time. Finally, the study takes "Digital Game Production" as a case to analyze the practical application of this model in detail, aiming to provide a new path for the future human-AI co-creative learning model.…”
Get full text

Optimal Computation Offloading Decisions Based on System Utility and Cost Balance by Bingxue Zhang, Xisheng Li, Jia You

“…In this study, we address the offloading problem of partitionable tasks in collaborative edge computing systems and propose a new evaluation model that jointly optimizes the time and energy costs along with the system utility. …”
Get full text

Leveraging AI in academia: university students’ adoption of ChatGPT for writing coursework (take home) assignments through the lens of UTAUT2 by Afulah Namatovu, Mahadih Kyambade

“…The rapid growth of artificial intelligence (AI) is transforming education, with tools like ChatGPT offering innovative support for university students in tasks such as essay writing and problem-solving. …”
Get full text

Sparse Regularization With Reverse Sorted Sum of Squares via an Unrolled Difference-of-Convex Approach by Takayuki Sasaki, Kazuya Hayase, Masaki Kitahara, Shunsuke Ono

“…In experiments, we apply the RSSS regularization method to image deblurring and super-resolution tasks and confirmed its superior performance compared to conventional methods, all with feasible computational complexity.…”
Get full text

Vision transformer-based diagnosis of lumbar disc herniation with grad-CAM interpretability in CT imaging by Qingsong Chu, Xingyu Wang, Hao Lv, Yao Zhou, Ting Jiang

“…We compared the performance of the ViT model with that of several convolutional neural networks (CNNs), including ResNet18, ResNet50, LeNet, AlexNet, and VGG16, across two primary tasks: vertebra localization and disc abnormality classification. …”
Get full text

Modeling of maintenance systems for railway infrastructure facilities based on the theory of mass service by A. N. Shabel’Nikov, Yu. V. Shapovalova

“…It port infrastructure into the practice of the transportation process. was also proposed to use the mathematical apparatus of queuing The functions of object monitoring, diagnostics of their condition theory to implement the tasks of analyzing and synthesizing the structure and functions of the system for organizing maintenance of transport infrastructure facilities. …”
Get full text

Investigation of an Optimized Linear Regression Model with Nonlinear Error Compensation for Tool Wear Prediction by Lihua Shen, Baorui Du, He Fan, Hailong Yang

“…By combining linear modeling with nonlinear error compensation, this method provides an integrated optimization approach to prediction tasks in complex industrial scenarios.…”
Get full text

Blockchain-Based Intelligent Transportation: A Sustainable GCU Application System by Xiaomin Du, Yang Gao, Chia-Huei Wu, Rong Wang, Datian Bi

“…The results show that (1) solving social problems is the primary link, (2) economic tasks are mainly focused on smart contracts and affected by the social problems, (3) the continuous improvement of environmental issues requires a solution to social problems, and (4) the application system of blockchain in intelligent transportation needs to be built from three levels including the government layer, the company layer, and the user layer. …”
Get full text

VET leaders’ collaborative problem-solving skills: insights from a professionals’ master’s degree program by Anna Trikoili, Despoina Georgiou, Daniel Pittich

“…This single case study investigates the CPS skills that VET leaders use in addressing tasks and challenges in an educational setting. Postgraduate students in a professional master’s degree program with several years of work experience in VET leadership positions served as study participants. …”
Get full text

Lightweight interactive feature inference network for single-image super-resolution by Li Wang, Xing Li, Wei Tian, Jianhua Peng, Rui Chen

“…Abstract The emergence of convolutional neural network (CNN) and transformer has recently facilitated significant advances in image super-resolution (SR) tasks. However, these networks commonly construct complex structures, having huge model parameters and high computational costs, to boost reconstruction performance. …”
Get full text

A contrast enhanced representation normalization approach to knowledge distillation by Zhiqiang Bao, Di Zhu, Leying Du, Yang Li

“…Meanwhile, drawing on the idea of the Triplet Loss function in contrastive learning, we constructed a loss function and integrated it into the Contrastive Representation Distillation Loss to form the Contrast Enhanced Representation Normalization Distillation Loss. …”
Get full text

Analyzing Diagnostic Reasoning of Vision–Language Models via Zero-Shot Chain-of-Thought Prompting in Medical Visual Question Answering by Fatema Tuj Johora Faria, Laith H. Baniata, Ahyoung Choi, Sangwoo Kang

“…The results demonstrate that chain-of-thought prompting significantly improves both reasoning transparency and performance in MedVQA tasks.…”
Get full text

Pedagogical Projecting of the Model of a Future Specialist by Oleksandr Mozolev

“…Training future specialist to professional activity is one of the main tasks of higher and professional education. Pedagogical modeling of professional activity is used to determine the content of quantitative and qualitative information, which is necessary for modern researchers to further work, and also directs them to the prospects of career growth. …”
Get full text

Monitoring of the state of electromagnetic fuel injectors of gasoline engines with distributed fuel injection systems by G. N. Votinov, D. V. Maltsev, D. S. Repetsky

“…Ensuring the trouble-free operation of road transport is one of the priority tasks. The functioning of the internal combustion engine, the most important unit, is impossible without the correct operation of the fuel injectors. …”
Get full text

Multi-View Graph Contrastive Neural Networks for Session-Based Recommendation by Pengbo Huang, Chun Wang

“…These results validate the effectiveness of multi-view graphs and contrastive learning in improving both accuracy and robustness for session-based recommendation tasks.…”
Get full text

Registrars’ experience with research in family medicine training programmes in South Africa by Emcy Louw, Robert J. Mash

“…Teaching modules should be more standardised and focussed on the practical tasks and skills, rather than didactic theory. Lengthy provincial and ethics processes, and lack of institutional support, such as scholarly services and financial support, caused delays. …”
Get full text

Application of Reinforcement Learning in Controlling Quadrotor UAV Flight Actions by Shang-En Shen, Yi-Cheng Huang

“…The simulation environment is constructed using AirSim and Unreal Engine, with onboard camera footage serving as the state input for reinforcement learning. …”
Get full text

Enhanced-Similarity Attention Fusion for Unsupervised Cross-Modal Hashing Retrieval by Mingyong Li, Mingyuan Ge

“…The findings show that on these datasets, ESAFH performs satisfactorily in cross-modal retrieval tasks. In conclusion, by boosting text features, improving the similarity matrix, and utilizing an attention fusion mechanism, ESAFH solves the shortcomings of current methods.…”
Get full text