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. …”
Get full text

Traffic environment perception algorithm based on multi-task feature fusion and orthogonal attention by Zhengfeng LI, Mingen ZHONG, Yihong ZHANG, Kang FAN, Zhiying DENG, Jiawei TAN

“…Both these metrics surpass those of existing mainstream multi-task perception algorithms with comparable parameter scales. Furthermore, the lane line segmentation accuracy, measured by IoU, reached a sub-optimal value of 27.2%. …”
Get full text

Mode selection and resource optimization for UAV-assisted cellular networks by Daquan FENG, Canjian ZHENG, Xiangqi KONG

“…The resource allocation and optimization scheme was studied in a coexistence scenario of unmanned aerial vehicle (UAV) and cellular communication network.To improve spectrum efficiency of the system, UAV users could reuse the cellular spectrum resources to access the network through full duplex or half duplex device-to-device technique.Additionally, a joint access control, mode selection, power control and resource allocation optimization problem was formulated to maximize the overall throughput of the network while ensuring quality of service requirements for both UAV users and ground cellular users.Specifically, the phase 1 method in the convex optimization was adopted for access control and feasibility check, and then the convex and concave procedure (CCCP) iterative algorithm was used to solve the power control problem for feasible UAV user pairs.By using this local optimum value, the original optimization problem can be simplified into a weighted maximization problem.Finally, the Kuhn-Munkres (KM) algorithm was used to match the optimal channel resources and obtain the global optimal throughput value of the system.Numerical results show that the proposed scheme can significantly improve the performance of system.…”
Get full text

Improving Portfolio Management Using Clustering and Particle Swarm Optimisation by Vivek Bulani, Marija Bezbradica, Martin Crane

“…Particularly, this research examines different approaches for handling missing values and volatility, while examining their effects on optimal portfolios. …”
Get full text

Network slicing resource allocation strategy based on joint optimization by Zaijian WANG, Huimin GU

“…To improve network resource utilization that was decreased by different applications with different requirements in 5G networks, a network slicing resource allocation strategy based on joint optimization was proposed, which was utilized to maximize both network resource utilization and network revenue by comprehensively considering in tra-slice and inter-slice resource schedule.Firstly, the user’s average satisfaction function was defined in the inter-slicing resource allocation problem.Furthermore, in terms of the number of users, slicing schedule delay and priority, a proportional fair resource allocation algorithm based on quality of service (QoS) was proposed, which was employed to achieve the best tradeoff between fairness and the users’ requirements among slices.Secondly, after two functions (service degradation and resource migration) were introduced in the inter-slice resource schedule problem, two price models were established for internal access users and external access users respectively, where congestion and non-congestion conditions were analyzed.According to the proposed price models, a Stackelberg game between the base station and users was constructed, and a global search algorithm with low complexity was leveraged to obtain the best response of the game, where the best tradeoff between the base station revenue and user utility was obtained.Simulation results show that the proposed strategy can effectively improve resource utilization and network revenue while reducing network congestion.Therefore, it can better realize fairness in resource allocation.…”
Get full text

Improving classifier decision boundaries and interpretability using nearest neighbors by Johannes Schneider, Arianna Casanova

“…Unlike prior methods, our approach achieves improvements without introducing trade-offs or necessitating architectural adaptations, while providing actionable insights and theoretical analysis to support its efficacy.…”
Get full text

Multiobjective Optimization for Topology and Coverage Control in Wireless Sensor Networks by Seyed Mahdi Jameii, Karim Faez, Mehdi Dehghan

“…Simulation results demonstrate that the proposed algorithm can improve the network lifetime and coverage while maintaining the network connectivity.…”
Get full text

A clustering algorithm based on grids for core data and adjacency relationships for edge data by Honglei He

“…To address these issues, existing research primarily focuses on three directions: (1) optimizing the adaptive selection of grid parameters, which struggles to handle variations in cluster density; (2) improving grid division methods (e.g., multi-granularity or dynamic grids), which have limited effectiveness on complex-shaped data; and (3) integrating other clustering techniques, which enhances accuracy but increases algorithmic complexity. …”
Get full text

Private Stochastic Optimization with Large Worst-Case Lipschitz Parameter by Andrew Lowy, Meisam Razaviyayn

“…To do so, we develop novel algorithmic and stability-based proof techniques, which we believe will be useful for future work in obtaining optimal excess risk. …”
Get full text

SAMFA: A Flame Segmentation Algorithm for Infrared and Visible Aerial Images in the Same Scene by Jianye Yuan, Min Yang, Haofei Wang, Xinwang Ding, Song Li, Wei Gong

“…Compared to SAM, SAMFA improves the IoU by 11.94% and 6.45% on infrared and visible light images, respectively, while reducing the number of learnable parameters to 11.58 M.…”
Get full text

Mobile-YOLO: A Lightweight Object Detection Algorithm for Four Categories of Aquatic Organisms by Hanyu Jiang, Jing Zhao, Fuyu Ma, Yan Yang, Ruiwen Yi

Get full text

A two-step multiaxial racetrack filter algorithm for non-proportional load histories by Marco Antonio Meggiolaro, Jaime Tupiassú Pinho de Castro, Hao Wu

Get full text

A Heuristic Algorithm for Deploying Electric Taxi Charging Stations to Enhance Service Quality by Lingjie Li, Yu Zhang, Cheng Cheng, Hao Du, Shifu Liu

“…A heuristic algorithm, Improved K-means iterated with Queuing Theory (IKQT), is proposed. …”
Get full text

Dynamic Node Management for Energy Optimization in Cognitive Radio Systems by Tangsen Huang, Haibing Yin, Xiangdong Yin, Huijun Xiao

“…The optimal number of cooperative nodes is determined through a greedy algorithm, formulated as a constrained optimization problem. …”
Get full text

Design of performance evaluation method for higher education reform based on adaptive fuzzy algorithm by Dakun Yang, Muhammad Sheraz Arshad Malik

Get full text

Predicting the Likelihood of Operational Risk Occurrence in the Banking Industry Using Machine Learning Algorithms by Hamed Naderi, Mohammad Ali Rastegar Sorkhe, Bakhtiar Ostadi, Mehrdad Kargari

“…Specifically, the RF algorithm achieved an accuracy of 0.9690, while the SVM algorithm attained an accuracy of 0.9587 in State 1, making them the most effective models in this setting. …”
Get full text

Research on E-Commerce Inventory Sales Forecasting Model Based on ARIMA and LSTM Algorithm by Chenyang Wang, Junsheng Wang

Get full text

A hybrid evolution strategies algorithm for non-permutation flow shop scheduling problems by Bilal Khurshid, Shahid Maqsood, Muhammad Salman Habib, Muhammad Omair, Seung-June Hwang

“…The Quad swap mutation operator is employed in the IES to optimize the utilization of the solution space while minimizing computational time. …”
Get full text

Machine Learning Techniques for Heart Disease Prediction Using a Multi-Algorithm Approach by Muhammad Kunta Biddinika, Alya Masitha, Herman Herman, Vita Arfiana Nurul Fatimah

“…This analysis explores the efficiency of machine learning systems for heart disease identification through a multi-algorithm approach. The main objective is to identify the best performing algorithm for accurate disease prediction, improving clinical decision making. …”
Get full text

DLE-YOLO: An efficient object detection algorithm with dual-branch lightweight excitation network by Peitao Cheng, Xuanjiao Lei, Haoran Chen, Xiumei Wang

“…Thirdly, the localization loss utilizes SIoU loss to further optimize the accuracy of the bounding box. Our method achieves a mAP value of 46.0% on the MS-COCO dataset, which is a 2% mAP improvement compared to the baseline YOLOv5-m, while bringing a 19.3% reduction in parameter count and a 12.9% decrease in GFLOPs. …”
Get full text