Model and training method for aerial image object detector with optimization of both robustness and computational efficiency by Alona Moskalenko, Mykola Zaretskyi, Maksym Vynohradov, Vladyslav Babych

“…A novel method for training the detector was developed, combining the RetinaNet loss function with the loss function of gate blocks and applying meta-learning on the adaptation results for various types of synthetic perturbations. …”
Get full text

FM‐YOLOv8:Lightweight gesture recognition algorithm by Fanghai Li, Xitai Na, Jinshuo Shi, Qingbin Sun

“…Recombination convolution can reduce the computation and make up for the loss of precision to some extent. Finally, the MDPIoU loss function is used to optimize target location and prediction, to improve the accuracy of the model. …”
Get full text

Path Planning Method of Mobile Robot Using Improved Deep Reinforcement Learning by Wei Wang, Zhenkui Wu, Huafu Luo, Bin Zhang

“…Experiments show that compared with the classical DQN method, the average loss function value is reduced by 36.87% and the average reward value is increased by 12.96%, which can effectively improve the working efficiency of mobile robot.…”
Get full text

Exploring feature sparsity for out-of-distribution detection by Qichao Chen, Kuan Li, Zhiyuan Chen, Tomas Maul, Jianping Yin

“…One key drawback, however, is that the loss function parameters are highly dependent on involved datasets, which means it cannot be dynamically adapted and implemented in others settings; in other words, the general ability of the energy score is considerably limited. …”
Get full text

Coordinate-Corrected and Graph-Convolution-Based Hand Pose Estimation Method by Dang Rong, Feng Gang

“…Finally, the skeletal constraint loss function is used to impose constraints on the joints, and a natural and undistorted hand skeleton structure is generated. …”
Get full text

Adaptive electricity consumption forecasting approach for universal environments by Shiqi Zhou, Saisai Ni, Yifeng Han, Zhekang Dong, Chun Sing Lai

“…Our model incorporates a joint loss function combining point and probability forecasting evaluations to accurately quantify online batch errors. …”
Get full text

Analysis and Design of Gap-Coupled Annular Ring Microstrip Antenna by Binod Kumar Kanaujia, Anil Kumar Singh

“…The various parameters of the antenna such as input impedance, VSWR, return loss, and radiation pattern have been investigated as a function of gap length and feed point. …”
Get full text

Dominant cone-rod dystrophy: a mouse model generated by gene targeting of the GCAP1/Guca1a gene. by Prateek K Buch, Marija Mihelec, Phillippa Cottrill, Susan E Wilkie, Rachael A Pearson, Yanai Duran, Emma L West, Michel Michaelides, Robin R Ali, David M Hunt

“…The role of GCAP1 in controlling cyclic nucleotide levels in photoreceptors has largely been elucidated using knock-out mice, but the disease pathology in these mice cannot be extrapolated directly to COD3 as this involves altered, rather than loss of, GCAP1 function. Therefore, in order to evaluate the pathology of this dominant disorder, we have introduced a point mutation into the murine Guca1a gene that causes an E155G amino acid substitution; this is one of the disease-causing mutations found in COD3 patients. …”
Get full text

Small target detection in UAV view based on improved YOLOv8 algorithm by Xiaoli Zhang, Guocai Zuo

“…This mechanism helps in filtering out unimportant information and enhancing the recognition of key features. The MPDIoU (Minimum Point Distance based IoU) loss function is improved, and the idea of inner-IoU loss function is adopted as a way to improve the model’s learning ability for difficult samples. …”
Get full text

Eg5 and Diseases: From the Well-Known Role in Cancer to the Less-Known Activity in Noncancerous Pathological Conditions by Alessia Ricci, Simone Carradori, Amelia Cataldi, Susi Zara

“…In conclusion, this review highlights the double impact that overexpression or loss of function of Eg5 could have in the onset and progression of different pathological situations. …”
Get full text

Water-Adapted 3D Gaussian Splatting for precise underwater scene reconstruction by Xinnan Fan, Xiaotian Wang, Haonan Ni, Yuanxue Xin, Pengfei Shi

“…To address these challenges, we propose an improved underwater 3D Gaussian Splatting method combining complexity-adaptive point distribution, depth-adaptive multi-scale radius rendering, and a tailored loss function for underwater environments. …”
Get full text

Alpha-actinin-4-mediated FSGS: an inherited kidney disease caused by an aggregated and rapidly degraded cytoskeletal protein. by June Yao, Tu Cam Le, Claudine H Kos, Joel M Henderson, Phillip G Allen, Bradley M Denker, Martin R Pollak

“…Comparison of the phenotype in wild-type, heterozygous, and homozygous Actn4 "knockin" and "knockout" mice, together with our in vitro data, suggests that the phenotypes in mice and humans involve both gain-of-function and loss-of-function mechanisms.…”
Get full text

A Modified Approach by Using Prediction to Build a Best Threshold in ARX Model with Practical Application by Juma et al.

“…Then they are compared with the obtained models from two methods that mentioned above of the two approaches within a group of the criteria as AIC, MDL, Loss Function, BIC, FPE, MSE, in addition the proposed weighted comparison criteria to determine the best model for representing the wind speed data as input variable, soil and dust as an output variable, in Baghdad Station from January 1956 to December 2012.…”
Get full text

Detection of Maize Pathogenic Fungal Spores Based on Deep Learning by Yijie Ren, Ying Xu, Huilin Tian, Qian Zhang, Mingxiu Yang, Rongsheng Zhu, Dawei Xin, Qingshan Chen, Qiaorong Wei, Shuang Song

“…To improve the recognition accuracy of various maize disease spores, this study introduced the YOLOv8s-SPM model by incorporating the space-to-depth and convolution (SPD-Conv) layers, the Partial Self-Attention (PSA) mechanism, and Minimum Point Distance Intersection over Union (MPDIoU) loss function. …”
Get full text

Campus risk detection using the S-YOLOv10-SIC network and a self-calibrated illumination algorithm by Qiang Zhao, Sha Liu, Shihao Zhang, Baijuan Wang

“…The algorithm optimizes the loss function by introducing an auxiliary bounding box, and accelerates model convergence. …”
Get full text

Research on Satellite Power System Based on MPPT Technology by Wenshuang ZHANG, Wentao YU, Qiang WEI

“…According to the need of power system for GEO satellite,the plan design and simulation based on Maximum Power Point Tracking (MPPT) technology were designed and simulated.It could reduce the power loss in power transport line and made full use of the output power of solar array.Based on the research and simulation for solar array,the simulation of all the power system was fi nished.The result of simulation provides that it can complete the MPPT function and stabilize the bus voltage.Last,the new plan and the traditional one were compared,which shows the advantage of the new plan and lays a foundation for next power system.…”
Get full text

Single-port robot-assisted pyeloplasty through supine anterior retroperitoneal access by Sina Sobhani, Sij Hemal

“…At 4-months follow-up, on the renal scan, the right kidney showed stable function with improved drainage.…”
Get full text

Scoop: An Optimization Algorithm for Profiling Attacks against Higher-Order Masking by Nathan Rousselot, Karine Heydemann, Loïc Masure, Vincent Migairou

“…Scoop combines second-order derivative of the loss function in the optimization process, with a sparse stochastic mirror descent. …”
Get full text

Smart Agricultural Pest Detection Using I-YOLOv10-SC: An Improved Object Detection Framework by Wenxia Yuan, Lingfang Lan, Jiayi Xu, Tingting Sun, Xinghua Wang, Qiaomei Wang, Jingnan Hu, Baijuan Wang

“…Additionally, Shape Weights and Scale Adjustment Factors are introduced to optimize the loss function. The experimental results show that compared with the original YOLOv10, the model generated by the improved algorithm improves the accuracy by 5.88 percentage points, the recall rate by 6.67 percentage points, the balance score by 6.27 percentage points, the mAP value by 4.26 percentage points, the bounding box loss by 18.75%, the classification loss by 27.27%, and the feature point loss by 8%. …”
Get full text

Fast and Accurate Density Estimation of Hybrid Rice Seedlings Using a Smartphone and an Improved YOLOv8 Model by Zehua Li, Yongjun Lin, Yihui Pan, Xu Ma, Xiaola Wu

“…A dynamic head module was added to the head network to enhance the capability of the model to identify seedlings. The CIoU loss function was replaced by the EIoU loss function, enhancing the convergence speed of the model. …”
Get full text