Efficient Integration of Reinforcement Learning in Graph Neural Networks-Based Recommender Systems by Abdurakhmon Sharifbaev, Mikhail Mozikov, Hakimjon Zaynidinov, Ilya Makarov

“…Models are typically trained to minimize a loss function, while their effectiveness during testing is assessed using different ranking metrics, leading to suboptimal recommendation quality. …”
Get full text

A YOLOv8n-T and ByteTrack-Based Dual-Area Tracking and Counting Method for Cucumber Flowers by Liyang Su, Shujuan Zhang, Hongtu Zhang, Xiangsen Meng, Xiongkui He

“…The YOLOv8n-T incorporates a Coordinate Attention (CA) mechanism and lightweight modules while optimizing the loss function, thereby improving floral feature extraction capabilities and reducing computational complexity. …”
Get full text

A Transformer-Based Symmetric Diffusion Segmentation Network for Wheat Growth Monitoring and Yield Counting by Ziyang Jin, Wenjie Hong, Yuru Wang, Chenlu Jiang, Boming Zhang, Zhengxi Sun, Shijie Liu, Chunli Lv

“…By introducing an aggregated loss function, the model effectively optimizes both segmentation accuracy and growth measurement performance. …”
Get full text

A Multi-Task Learning Framework with Enhanced Cross-Level Semantic Consistency for Multi-Level Land Cover Classification by Shilin Tao, Haoyu Fu, Ruiqi Yang, Leiguang Wang

“…MTL-SCH employs a shared encoder combined with a feature cascade mechanism to boost information sharing and collaborative optimization between two levels. A hierarchical loss function is also embedded that explicitly models the semantic dependencies between levels, enhancing semantic consistency across levels. …”
Get full text

The effect of pore structure on the erosion resistance of air plasma sprayed thermal barrier coatings on finite element simulation by Y. Wang, S. Y. Cui, Q. M. Yu, G. Cheng, X. F. Li, Q. Y. Li, J. Yan, X. Zhao

“…In general, the relationship between crack propagation length and particle erosion velocity satisfies an exponential function. In addition, the material loss (Δm) of the coatings exhibits significant fluctuations with the increasing pore radius (0–1 μm), and the optimal pore radius is 0.3 μm for superior erosion resistance; The Δm is achieved around 4% porosity, after which the Δm tends to stabilize with increasing porosity. …”
Get full text

A deep learning-orchestrated garlic routing architecture for secure telesurgery operations in healthcare 4.0 by Kavit Shah, Nilesh Kumar Jadav, Rajesh Gupta, Sucheta Gupta, Sudeep Tanwar, Joel J.P.C. Rodrigues, Fayez Alqahtani, Amr Tolba

“…The proposed architecture is evaluated using different evaluation metrics, such as statistical analysis (training accuracy, training loss, optimizer performance, activation function performance), data compromisation rate (0.346), network throughput (1.44 Mbps), error rate, and latency comparison.…”
Get full text

YOLOX-LS: Strong Gravitational Lenses Detection in the DECaLS with Deep Learning by Yangyang Liu, Liangping Tu, Jianxi Li, Jiawei Miao, Gengqi Lin, Chenying Zhao

“…We apply the YOLOX algorithm as the basic framework and improve it by selecting the optimal optimizer, activation function, attention mechanism, and loss function. …”
Get full text

Crack Detection Method of Sleeper Based on Cascade Convolutional Neural Network by Liming Li, Shubin Zheng, Chenxi Wang, Shuguang Zhao, Xiaodong Chai, Lele Peng, Qianqian Tong, Ji Wang

“…The prediction graph is inputted into CRRNet to improve its edge information and local region to achieve optimization. The accuracy of the crack identification model is improved by using a mixed loss function of binary cross-entropy (BCE), structural similarity index measure (SSIM), and intersection over union (IOU). …”
Get full text

Numerical simulation of the effect of installation height on self-priming performance of a prototype self-priming pump by Ying-Yu Ji, Shao-Han Zheng, Yu-Liang Zhang, Kai-Yuan Zhang, Zu-Chao Zhu

“…Throughout the self-priming process, the regions of significant hydraulic loss are primarily located at the outer edge of the impeller and the impeller inlet. …”
Get full text

Index-Based Neural Network Framework for Truss Structural Analysis via a Mechanics-Informed Augmented Lagrangian Approach by Hyeonju Ha, Sudeok Shon, Seungjae Lee

“…The IBNN framework approximates member forces and nodal displacements using separate neural networks and incorporates structural equations derived from the force method as mechanics-informed constraints within the loss function. Training was conducted using the Augmented Lagrangian Method (ALM), which improves the convergence stability and learning efficiency through a combination of penalty terms and Lagrange multipliers. …”
Get full text

Deep Learning Approach for Pneumonia Prediction from X-Rays using A Pretrained Densenet Model by Ahmad Zein Al Wafi, Febry Putra Rochim, Aisya Fathimah

“…The models were trained for 20 epochs using the Adam optimizer and binary cross-entropy loss function. Performance evaluation revealed that DenseNet201 outperformed the other models, achieving a precision of 0.99 and a recall of 0.61 for normal cases (F1-score of 0.75) and a precision of 0.81 with a recall of 0.99 for pneumonia cases (F1-score of 0.89). …”
Get full text

The NSL complex regulates housekeeping genes in Drosophila. by Kin Chung Lam, Friederike Mühlpfordt, Juan M Vaquerizas, Sunil Jayaramaiah Raja, Herbert Holz, Nicholas M Luscombe, Thomas Manke, Asifa Akhtar

“…The observed Pol II reduction coincides with compromised binding of TBP and TFIIB to target promoters, indicating that the NSL complex is required for optimal recruitment of the pre-initiation complex on target genes. …”
Get full text

DAHD-YOLO: A New High Robustness and Real-Time Method for Smoking Detection by Jianfei Zhang, Chengwei Jiang

“…The wise–powerful intersection over union (Wise-PIoU) is adopted as the new bounding box regression loss function, resulting in quicker convergence speed and improved detection outcomes. …”
Get full text

Hybrid chaotic firefly decision making model for Parkinson’s disease diagnosis by Sujata Dash, Ajith Abraham, Ashish Kr Luhach, Jolanta Mizera-Pietraszko, Joel JPC Rodrigues

“…Parkinson’s disease is found as a progressive neurodegenerative condition which affects motor circuit by the loss of up to 70% of dopaminergic neurons. Thus, diagnosing the early stages of incidence is of great importance. …”
Get full text

YOLO-MARS: An Enhanced YOLOv8n for Small Object Detection in UAV Aerial Imagery by Guofeng Zhang, Yanfei Peng, Jincheng Li

“…Thirdly, a multi-scale SGCS-FPN fusion architecture is proposed, adding a shallow feature guidance branch to establish cross-level semantic associations, thereby effectively addressing the issue of small target loss in deep networks. Finally, a dynamic WIoU evaluation function is implemented, constructing adaptive penalty terms based on the spatial distribution characteristics of predicted and ground-truth bounding boxes, thereby optimizing the boundary localization accuracy of densely packed small targets from the UAV viewpoint. …”
Get full text

Dynamic Assessment of Road Network Vulnerability Based on Cell Transmission Model by Yu Sun, Binglei Xie, Shan Wang, Dazhuang Wu

“…The road network maintaining stability is critical for guaranteeing urban traffic function. Therefore, the vulnerable links need to be identified accurately. …”
Get full text

Detection of power theft in sensitive stations based on generalized robust distance metric and multi-classification support vector machine by Wei Zhang, Qiong Cao, Shuai Yang, Hao Guo

“…Through training and optimization, the support vector machine outputs the detection results of electricity stealing behavior according to the decision function, and realizes the accurate detection of electricity stealing behavior. …”
Get full text

Federated Learning for Frequency-Modulated Continuous Wave Radar Gesture Recognition for Heterogeneous Clients by Tobias Sukianto, Matthias Wagner, Sarah Seifi, Maximilian Strobel, Cecilia Carbonelli

“…Moreover, regularization terms are included in the loss function to prevent client drift and overconfidence in the client’s NN prediction. …”
Get full text

Mathematical model of data collection and processing for a recommendation system for forming an individualized educational program by O.H. Hlazunova, Y.Y. Ponzel

“…In the current implementation, ML.NET tools are used, which automate the process of matrix factorization and loss function minimization, simplifying the development and tuning of the model. …”
Get full text

Long-term storage, cryopreservation, and culture of isolated human islets: a systematic review by Austin R. Chen, Austin R. Chen, Joshua Chansky, Jacqueline A. Burke

“…Developing techniques like cryopreservation and culture for long-term islet storage, or islet banking, with minimal functional loss would strengthen this supply chain. …”
Get full text