Conformal Segmentation in Industrial Surface Defect Detection with Statistical Guarantees by Cheng Shen, Yuewei Liu

“…The latter constructs a prediction set on which a given guarantee for detection will be obtained. First, we define a loss function for each calibration sample to quantify detection error rates. …”
Get full text

A Multifeature Fusion Short-Term Traffic Flow Prediction Model Based on Deep Learnings by Chunxu Chai, Chuanxiang Ren, Changchang Yin, Hui Xu, Qiu Meng, Juan Teng, Ge Gao

“…And then, the number of neurons in the model, the loss function, and other parameters such as the optimization algorithm are discussed and set up through simulation experiments. …”
Get full text

Online ECG Biometrics for Streaming Data with Prototypes Learning and Memory Enhancement by Kuikui Wang, Na Wang

“…Furthermore, we design a novel and efficient online optimization algorithm to minimize the overall loss function. …”
Get full text

G-RCenterNet: Reinforced CenterNet for Robotic Arm Grasp Detection by Jimeng Bai, Guohua Cao

“…Finally, ResNet50 is selected as the backbone network, and a custom loss function is designed specifically for grasp detection tasks, which significantly enhances the model’s ability to predict feasible grasp boxes. …”
Get full text

The utilization of 3D-printed arthrodesis prostheses in the repair and reconstruction of malignant tumors in proximal humerus by Guolong Bin, Bin Liu, Zhenchao Yuan, Jiachang Tan

“…Therefore, there is a pressing need for advancements in both prostheses design and surgical protocols to optimize clinical outcomes.…”
Get full text

Improvement of Energy Indicators of Asynchronous Motor under the Conditions of Asymmetric Voltage Supply by Boyko A.A., Besarab A.N., Sokolov Y.A., Shapa L.N.

“…As a result, there appears the possibility to maintain the load angle equality of all the phases of asynchronous motor to an optimal value. This allows to solve the problem of power loss minimization in an asynchronous motor due to the load angle equality to the optimal value, and the problem of symmetrization due to the load angle equality in motor phases. …”
Get full text

Predictive Modeling of soil salinity integrating remote sensing and soil variables: An ensembled deep learning approach by Sana Arshad, Jamil Hasan Kazmi, Endre Harsányi, Farheen Nazli, Waseem Hassan, Saima Shaikh, Main Al-Dalahmeh, Safwan Mohammed

“…However, the ensemble of improved FFNN and LSTM outperformed with the highest R2 and NSE = 0.84, and the lowest RMSE and MAE = 1.38 and 1.01, respectively, on the testing dataset. Optimized deep learning architectures with adjustments to the learning rate, dropout rate, and activation functions achieved the highest prediction accuracy with the lowest validation loss. …”
Get full text

Hierarchical pore and polarity regulation synergistic promoting efficient CO₂ adsorption by Zeyou Meng, Xin Ye, Xiao Sun, Jiahao Li, Nan Wang, Zhen Wang, Gang Xie

“…To address the two major challenges of low active site utilization and amine loss in traditional amine-functionalized CO2 adsorbent, this study proposed a synergistic strategy of “hierarchical pore channels-polarity regulation”. …”
Get full text

Endoscopic spine surgery for obesity-related surgical challenges: a systematic review and meta-analysis of current evidence by Wongthawat Liawrungrueang, Watcharaporn Cholamjiak, Peem Sarasombath, Yudha Mathan Sakti, Pang Hung Wu, Meng-Huang Wu, Yu-Jen Lu, Lo Cho Yau, Zenya Ito, Sung Tan Cho, Dong-Gune Chang, Kang Taek Lim

“…However, limitations such as study heterogeneity and the lack of randomized controlled trials highlight the need for further high-quality research to refine ESS techniques and optimize patient care in this high-risk population.…”
Get full text

Impact of obesity on proteomic profiles of follicular fluid-derived small extracellular vesicles: A comparison between PCOS and non-PCOS women by Qiyuan Chang, Senlan Wang, Qingyun Mai, Canquan Zhou

“…These insights underscore the necessity for tailored fertility management approaches, including weight loss strategies and specific interventions for PCOS patients, to optimize reproductive outcomes and enhance pregnancy success rates.…”
Get full text

Comparison of the Properties of Cold Work Tool Steels with the Same Hardness but Different Manufacturing Processes The required important properties by L. Tóth, R.E. Fábián, P. Pinke, T.A. Kovács, M. Nabiałek, A.V. Sandu, P. Vizureanu

“…The goal of the research was to find the optimal cold work tool steel quality for special applications (as a function of wear resistance, corrosion resistance and toughness). …”
Get full text

Translational Application of Microfluidics and Bioprinting for Stem Cell-Based Cartilage Repair by Silvia Lopa, Carlotta Mondadori, Valerio Luca Mainardi, Giuseppe Talò, Marco Costantini, Christian Candrian, Wojciech Święszkowski, Matteo Moretti

“…Cartilage defects can impair the most elementary daily activities and, if not properly treated, can lead to the complete loss of articular function. The limitations of standard treatments for cartilage repair have triggered the development of stem cell-based therapies. …”
Get full text

Computerised Method of Multiparameter Optimisation of Predictive Control Algorithms for Asynchronous Electric Drives by Grygorii Diachenko, Serhii Semenov, Katarzyna Marczak, Gernot Schullerus, Ivan Laktionov

“…A series of simulation experiments were carried out by varying the sampling step, number of iterations, prediction horizon, loss function parameters, and maximum linear search step to identify their impact on the control quality indicators. …”
Get full text

Clinical Application of 3D‐Printed Custom Hemipelvic Prostheses With Negative Poisson's Ratio Porous Structures in Reconstruction After Resection of Pelvic Malignant Tumors by Xin Hu, Chuang Li, Xiaodi Tang, Yitian Wang, Yi Luo, Yong Zhou, Chongqi Tu, Xiao Yang, Li Min

“…Conclusions 3D‐printed custom hemipelvic prostheses with auxetic biomaterials offer an effective solution for pelvic reconstruction, providing promising oncological, functional, and radiographic outcomes. These findings support the use of 3D printing in complex pelvic defect reconstruction, optimizing both osteointegration and mechanical strength.…”
Get full text

An Efficient Model for Leafy Vegetable Disease Detection and Segmentation Based on Few-Shot Learning Framework and Prototype Attention Mechanism by Tong Hai, Yuxin Shao, Xiyan Zhang, Guangqi Yuan, Ruihao Jia, Zhengjie Fu, Xiaohan Wu, Xinjin Ge, Yihong Song, Min Dong, Shuo Yan

“…Furthermore, the prototype loss function, which optimizes the distance relationship between samples and category prototypes, significantly improves the model’s ability to discriminate between categories. …”
Get full text

Lightweight UAV Detection Method Based on IASL-YOLO by Huaiyu Yang, Bo Liang, Song Feng, Ji Jiang, Ao Fang, Chunyun Li

“…Second, we introduce the SIoU loss function to address the orientation mismatch issue between predicted and ground truth bounding boxes. …”
Get full text

GeoMM-SSL: Integrating Geospatial Object Relations in Multimodal Self-Supervised Learning for Semantic Segmentation of Remote Sensing Images by Yang Liu, Tong Zhang, Yanru Huang

“…The proposed framework includes a teacher-student framework with residual gated guidable attention units as the backbone, a multihead graph attention network that encodes prior knowledge of geospatial object relations, a multimodal representation fusion module that facilitates mutual learning between visual features of remote sensing images and topological features of geospatial object relations, and a multilevel loss function that performs multiple levels of evaluation, enabling the model to learn the data representation at the pixel, object, and global levels. …”
Get full text

TCE-YOLOv5: Lightweight Automatic Driving Object Detection Algorithm Based on YOLOv5 by Han Wang, Zhenwei Yang, Qiaoshou Liu, Qiang Zhang, Honggang Wang

“…Secondly, the C3 module in the neck is replaced by the Res2Net module, which extracts features at different scales through multiple branches, not only ensuring rich details, but also enhancing the generalization ability of the network. Finally, the EIOU loss function is introduced to measure the overlap between the predicted box and the real box more accurately and improve the detection accuracy. …”
Get full text

The Influence of Si(C,N) Layer Composition on the Corrosion of NiCr Prosthetic Alloy by Zofia Kula, Barbara Burnat, Katarzyna Dąbrowska, Leszek Klimek

“…The results indicate that Si(C,N) coatings deposited via magnetron sputtering exhibit relatively low porosity (approximately 3%), enabling them to function effectively as barrier coatings. Among the tested coatings, the Si(39.6C/25.2N) layer demonstrated the highest polarization resistance (R_p) value and the lowest corrosion current density (i_cor), corrosion rate (CR), and mass loss rate (MR), suggesting that this composition achieves an optimal balance between carbon and nitrogen content. …”
Get full text

Tca4rec: contrastive learning with popularity-aware asymmetric augmentation for robust sequential recommendation by Yanan Bai, Liji Xiao, Chongjun Xia, Kexiang Zeng, Xiaoyu Shi

“…To mitigate popularity bias, we derive an Asymmetric Multi-instance Noise Contrastive Estimation (AMINCE) loss function that supplies rich, bias-aware training signals, while our two-stage training strategy significantly reduces the over-dominance of popular items during optimization. …”
Get full text