Efficient coding in biophysically realistic excitatory-inhibitory spiking networks by Veronika Koren, Simone Blanco Malerba, Tilo Schwalger, Stefano Panzeri

“…Here, we derive the structural, coding, and biophysical properties of excitatory-inhibitory recurrent networks of spiking neurons that emerge directly from imposing that the network minimizes an instantaneous loss function and a time-averaged performance measure enacting efficient coding. …”
Get full text

Research on X-Ray Weld Defect Detection of Steel Pipes by Integrating ECA and EMA Dual Attention Mechanisms by Guanli Su, Xuanhe Su, Qunkai Wang, Weihong Luo, Wei Lu

Get full text

An Improved YOLOv9s Algorithm for Underwater Object Detection by Shize Zhou, Long Wang, Zhuoqun Chen, Hao Zheng, Zhihui Lin, Li He

“…Finally, we employ Wise-IoU version 3 (WIoU v3) as the loss function to balance the loss weights for targets of different sizes. …”
Get full text

An Improved Small Target Detection Algorithm Based on YOLOv8s by G. Ma, C. Xu, Z. Xu, X. Song

Get full text

Toward model-based individualized fitting of hip-flexion exosuits for persons with unilateral transfemoral amputation by Finn G. Eagen, Nicholas P. Fey

“…The muscular restructuring and loss of function that occurs during a transfemoral amputation surgery has a great impact on the gait and mobility of the individual. …”
Get full text

Marine fish species recognition based on improved YOLOv5s by ZHANG Haifeng, LU Xinchun, FENG Bo, YANG Jin

“…ObjectiveIn order to improve the recognition accuracy of different kinds of marine fish, an improved YOLOv5s marine fish species recognition method was proposed.MethodsK⁃means++algorithm was used to cluster the real frames of marine fish, and more matching anchor frames were obtained with the self built data set. CIoU Loss function was replaced by SIoU Loss function as the boundary box regression algorithm to improve the accuracy and rate of convergence of the boundary box regression. …”
Get full text

AHN-YOLO: A Lightweight Tomato Detection Method for Dense Small-Sized Features Based on YOLO Architecture by Wenhui Zhang, Feng Jiang

“…The key innovations of AHN-YOLO include (1) the introduction of an ADown module to reduce model parameters; (2) the adoption of a Normalized Wasserstein Distance (NWD) loss function to stabilize small-feature detection; and (3) the proposal of a lightweight hybrid attention mechanism, Light-ES, to enhance focus on disease regions. …”
Get full text

CSCP-YOLO: A Lightweight and Efficient Algorithm for Real-Time Steel Surface Defect Detection by Chenglong Wang, Heng Wang, Yimin Jiang, Lei Yu, Xueting Wang

“…Finally, the Powerful-IoU loss function is employed to address optimization limitations in the original objective formulation. …”
Get full text

Toward improving precision and complexity of transformer-based cost-sensitive learning models for plant disease detection by Manh-Tuan Do, Manh-Hung Ha, Duc-Chinh Nguyen, Oscal Tzyh-Chiang Chen, Oscal Tzyh-Chiang Chen

“…Furthermore, we adopted the SIoU loss function, a modified version of CIoU, applied to the YOLOv8s model, demonstrating a substantial improvement in accuracy. …”
Get full text

Simultaneous Optimal Network Reconfiguration, DG and Fixed/Switched Capacitor Banks Placement in Distribution Systems using Dedicated Genetic Algorithm by Davar Esmaeili, Kazem Zare, Behnam Mohammadi-ivatloo, Sayyad Nojavan

“…The considered objective function encompasses the total cost of power loss, the investment and operation costs of DG units, the installation cost of fixed/switched capacitor banks and cost of purchased active power demand from upstream network. …”
Get full text

Construction and scheduling optimization of renewable energy consumption forecasting system for twisted tire porcelain manufacturing industry based on deep learning by Fangrong Liao, Runlin Ran, Jiayi Zhang

“…At the same time, based on the convolutional neural network model Alexnet, the cross-entropy loss function is selected as the training loss, and the twisted tire porcelain pattern classification algorithm under the deep learning framework is designed. …”
Get full text

Analysing the loss of embryogenic competence in long-term cell lines of Solanum betaceum Cav.: involvement of miR827, phosphate and sugar by Daniela Cordeiro, Jorge Canhoto, Sandra Correia

Get full text

Analysis of Power Enhancement in Facade-BIPV Systems Through Module-Level Power Optimizer: Evaluating Performance Under Shading Conditions by Jiyoung Eum, Hyun-Jung Choi

“…This confirms the optimizer function in enabling shaded and non-shaded modules to operate independently at maximum power. …”
Get full text

Non-convex optimization with using positive-negative moment estimation and its application for skin cancer recognition with a neural network by P.A. Lyakhov, U.A. Lyakhova, R.I. Abdulkadirov

“…These approaches allow the loss function to more accurately converge in the neighborhood of the global minimum in a smaller number of iterations. …”
Get full text

Design and Optimization of a Fan-Out Wafer-Level Packaging- Based Integrated Passive Device Structure for FMCW Radar Applications by Jiajie Yang, Lixin Xu, Ke Yang

“…Using this metric as a loss function, we apply the support vector machine (SVM) for electromagnetic simulation and the genetic algorithm (GA) for optimization. …”
Get full text

Model-Free Optimal Volt-VAR Control of Wind Farm Based on Data-Driven Lift-Dimension Linear Power Flow by Li Guo, Zhaoning Liu, Zhongguan Wang, Xialin Li, Yixin Liu, Yuxuan Zhang, Xiaodi Zang, Chengshan Wang

“…Considering reactive power devices such as wind turbines and static var generator (SVG) in wind farms, a global sensitivity-based reactive power and voltage linear optimization control model is proposed. Taking minimum reactive power adjustment of wind turbines and SVG as the objective function, combined with the sensitivity relationship between node voltage and reactive power injection, the proposed model-free voltage control method can realize optimal reactive power distribution, effectively reduce active power loss, and satisfy the requirement of rapid voltage control response of wind farms. …”
Get full text

A ROS-Based Online System for 3D Gaussian Splatting Optimization: Flexible Frontend Integration and Real-Time Refinement by Li’an Wang, Jian Xu, Xuan An, Yujie Ji, Yuxuan Wu, Zhaoyuan Ma

“…With the help of a dynamic sliding-window strategy and a rendering-quality loss function that combines L1 and SSIM, it achieves online optimization of the 3DGS map. …”
Get full text

Metaheuristic optimization of extreme gradient boosting machine for enhanced prediction of lateral strength of reinforced concrete columns under cyclic loadings by Phu-Anh-Huy Pham, Nhat-Duc Hoang

“…Additionally, an asymmetric squared error loss function is utilized to reduce overestimations by 12 %. …”
Get full text

Optimization of a multi-environmental detection model for tomato growth point buds based on multi-strategy improved YOLOv8 by Jiang Liu, Jingxin Yu, Changfu Zhang, Huankang Cui, Jinpeng Zhao, Wengang Zheng, Fan Xu, Xiaoming Wei

“…Three key innovations address YOLOv8’s limitations: (1) an SE attention module boosts feature representation in cluttered environments, (2) GhostConv replaces standard convolution to reduce computational load by 19% while preserving feature discrimination, and (3) a scale-adaptive WIoU_v2 loss function optimizes gradient allocation for variable-quality data. …”
Get full text

Research into Robust Federated Learning Methods Driven by Heterogeneity Awareness by Junhui Song, Zhangqi Zheng, Afei Li, Zhixin Xia, Yongshan Liu

Get full text