Integrating feedback control for improved human-structure interaction analysis by Santiago A. Lopez, Daniel Gomez, Albert R. Ortiz, Sandra Villamizar

Get full text

A dereverberation beamforming algorithm for noise source localization in anechoic and semi-reverberant environments by R. Singh, A. Mimani, R. Kumar

“…Additionally, the CLEAN-SC deconvolution applied to the DBF maps of the mixer-grinder significantly improved the source resolution. • DBF algorithm is presented based on CCM filtering using an optimized Hanning window to significantly improve the localization accuracy of noise sources within λ/20 uncertainty. • Trial-and-error method is used to determine the optimal Hanning window width, which depends on frequency, noise source and surroundings. • It was necessary to implement DBF even in an anechoic chamber to accurately localize noise sources generated by engineering applications.…”
Get full text

Small Object Detection Algorithm Based on Partial Convolution and Attention Fusion Detection Head by Peng Sheng, Zhu Fenghua, Zhou Jin, Zhu Gaofeng, Wang Yingxu, Chen Yuehui

“…Additionally, a Dynamic Head is incorporated into the detection head, effectively applying attention mechanism to improve overall detection performance. Finally, the bounding box loss function is optimized as Inner-ShapeIoU, focusing on shape and scale of the bounding box to improve the accuracy for bounding box regression calculation while utilizing auxiliary bounding boxes to expedite convergence speed. …”
Get full text

Metrics and Algorithms for Identifying and Mitigating Bias in AI Design: A Counterfactual Fairness Approach by Dongsoo Moon, Seongjin Ahn

Get full text

Risk of AI Algorithmic Discrimination Embedded in Government Data Governance and Its Prevention and Control by PENG Lihui, ZHANG Qiong, LI Tianyi

“…To address this issue, this study proposed a series of targeted prevention and control measures, including clarifying the principle of algorithmic fairness, formulating industry norms and standards, improving the accountability mechanism and regulatory system, and optimizing the data collection and processing environment, so as to effectively curb the phenomenon of algorithmic discrimination while making full use of the advantages of AI technology, so that AI technology in government data governance can truly benefit the people, and promote social fairness and justice.…”
Get full text

Multi-Strategy Fusion Path Planning Algorithm for Autonomous Surface Vessels with Dynamic Obstacles by Yongshun Xie, Chengyong Liu, Yixiong He, Yong Ma, Kang Liu

“…Through a comprehensive analysis of its control output, the proposed integrated algorithm accomplishes efficient obstacle avoidance via agile control of angular velocity while preserving navigational stability and achieves path optimization through consistent acceleration adjustments, thereby asserting its superiority and practical worth in challenging maritime environments.…”
Get full text

Green logistics optimization for coal supply in a power plant connecting maritime port by Mingsheng Qiu, Liping Gao, Zhouyong Lin, Minghong Zheng, Qingzhong Lin

“…This paper introduces an integrated optimization model grounded in green logistics and employs an Improved Particle Swarm Optimization (IPSO) algorithm to efficiently manage the coal supply chain from unloading at ports to loading into generators. …”
Get full text

Automated Calibration of SWMM for Improved Stormwater Model Development and Application by Hossein Ahmadi, Durelle Scott, David J. Sample, Mina Shahed Behrouz

“…During multi-objective optimization calibration, the model achieved NSE, PBIAS, and RSR values of 0.73, 17.1, and 0.52, respectively; while the validation period recorded values of 0.86, 13.1, and 0.37, respectively. …”
Get full text

Big Data and AI Algorithms for Sustainable Development Goals: A Topic Modeling Analysis by Prema Nedungadi, Simi Surendran, Kai-Yu Tang, Raghu Raman

“…In energy, AI-driven solutions optimize forecasting, grid management, and renewable integration, while in industry, they bolster infrastructure resilience through innovations like predictive maintenance and automated quality control within Industry 4.0 frameworks. …”
Get full text

Stress management with HRV following AI, semantic ontology, genetic algorithm and tree explainer by Ayan Chatterjee, Michael A. Riegler, K. Ganesh, Pål Halvorsen

“…Various techniques like feature selection and dimensionality reduction are explored to improve classification accuracy while minimizing bias. …”
Get full text

DScanNet: Packaging Defect Detection Algorithm Based on Selective State Space Models by Yirong Luo, Yanping Du, Zhaohua Wang, Jingtian Mo, Wenxuan Yu, Shuihai Dou

“…Through experiments on its own dataset, BIGC-LP, DScanNet achieves a high accuracy of 96.8% on the defect detection task compared with the current mainstream detection algorithms, while the number of model parameters and the computational volume are effectively controlled.…”
Get full text

A multi strategy bidirectional RRT* algorithm for efficient mobile robot path planning by Yourui Huang, Wenxin Jiang, Shanyong Xu

“…During the parent node rewiring phase, a multi-factor path cost function is constructed to optimize parent node selection, thereby improving path quality. …”
Get full text

DP-YOLO: A Lightweight Real-Time Detection Algorithm for Rail Fastener Defects by Lihua Chen, Qi Sun, Ziyang Han, Fengwen Zhai

“…To enable accurate and efficient real-time detection of rail fastener defects under resource-constrained environments, we propose DP-YOLO, an advanced lightweight algorithm based on YOLOv5s with four key optimizations. …”
Get full text

Retrieval Augmented Therapy Suggestion for Molecular Tumor Boards: Algorithmic Development and Validation Study by Eliza Berman, Holly Sundberg Malek, Michael Bitzer, Nisar Malek, Carsten Eickhoff

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. …”
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