Synthetic Data-Based Algorithm Selection for Medical Image Classification Under Limited Data Availability by Maxim Zhabinets, Benjamin Tyler, Martin Lukac, Shinobu Nagayama, Ferdinand Molnár, Michitaka Kameyama

“…The Algorithm selection approach improves performance by dynamically choosing the optimal Algorithm for each input instance. …”
Get full text

Investigating the Performance of Open-Vocabulary Classification Algorithms for Pathway and Surface Material Detection in Urban Environments by Kauê de Moraes Vestena, Silvana Phillipi Camboim, Maria Antonia Brovelli, Daniel Rodrigues dos Santos

“…Our approach uses large language models (LLMs) to improve the accuracy of classifying different pavement types. …”
Get full text

Research on Adaptive Education Path Dynamic Programming Algorithm Based on Reinforcement Learning and Cognitive Graphs by Hongli Lou, Pin Yue, Jianwen Chen

“…By employing reinforcement learning algorithms, the system continuously refines its model based on learner feedback and past interactions. …”
Get full text

Optimal Computation Offloading Decisions Based on System Utility and Cost Balance by Bingxue Zhang, Xisheng Li, Jia You

“…Based on the new evaluation model, an objective function is constructed to minimize the system’s cost-utility ratio, and an improved particle swarm optimization algorithm with enhanced search capabilities is proposed to solve it by designing a computation offloading strategy. …”
Get full text

A algorithm for low light image enhancement in coal mine underground based on illumination constraints by Yuchen BAI, Zuohua MIAO, Houyou XU, Mengting WANG

“…Compared to the original model, it showed improvements of approximately 23.40%, 16.07%, and 20.45% in these metrics, demonstrating optimal image enhancement effectiveness.…”
Get full text

Improving SLICES crystal representation through CHGNet integration and parameter tuning by Bizhu Zhang, Kedeng Wu, Chang Zhang, Hang Xiao, Liangliang Zhu

“…To bridge this gap, we present an enhanced approach to the simplified line-input crystal-encoding system (SLICES) representation by incorporating the Crystal Hamiltonian Graph Neural Network (CHGNet) machine learning force field model. Comprehensive evaluations across multiple datasets (MP-20, MP21-40, and MOF) using different neighbor recognition algorithms (EconNN and CrystalNN) show that our approach outperforms the original in reconstructing structures with fewer than 20 atoms per unit cell, achieving up to a 1.34% improvement in reconstruction rate (from 92.55% to 93.89%). …”
Get full text

Multi-Attribute Collaborative Optimization for Multimodal Transportation Based on User Preferences by Youpeng Lu, Gang Gao

“…In terms of solution methods, an improved Genetic Algorithm (GA) and Aptenodytes Forsteri Optimization (AFO) hybrid algorithm (GA-AFO) is proposed, which introduces GA to generate a high-quality initial population to accelerate convergence. …”
Get full text

Adaptive Q-Learning Grey Wolf Optimizer for UAV Path Planning by Golam Moktader Nayeem, Mingyu Fan, Golam Moktader Daiyan

“…Grey Wolf Optimization (GWO) is one of the most popular algorithms for solving such problems. …”
Get full text

Distributed hybrid energy storage photovoltaic microgrid control based on MPPT algorithm and equilibrium control strategy by Yanlong Qi, Rui Liu, Haisheng Lin, Junchen Zhong, Zhen Chen

“…The above results indicate that The proposed algorithm and the improved algorithm of the PV microgrid control model can not only improve the steady-state tracking accuracy, but also have better dynamic performance and improve the tracking speed. …”
Get full text

Using 'sentinel' plants to improve early detection of invasive plant pathogens. by Francesca A Lovell-Read, Stephen Parnell, Nik J Cunniffe, Robin N Thompson

Get full text

Dimensionality Reduction Optimization of High Subsonic Unmanned Aerial Vehicles Intake by Zeqi QI, Zheng GUO, Suqi CHEN, Ke YU

“…A Kriging model was then used for fitting, and a genetic algorithm was employed to search for optimal solutions with total pressure recovery coefficient and steady-state outlet distortion index as the objectives. …”
Get full text

Improved GOA-based fuzzy PI speed control of PMSM with predictive current regulation. by Taochang Li, Ang Li, Limin Hou

“…Subsequently, the fusion of Cauchy mutation and opposition-based learning, along with modifications to the optimal position, further improves the algorithm's ability to escape local optima. …”
Get full text

A Review of Smart Camera Sensor Placement in Construction by Wei Tian, Hao Li, Hao Zhu, Yongwei Wang, Xianda Liu, Rongzheng Yang, Yujun Xie, Meng Zhang, Jun Zhu, Xiangyu Wang

“…Simultaneously, Building Information Modeling is employed to consider the progress of construction and visualize optimized layouts, improving the effect of CSP. …”
Get full text

Optimal Control of a Fed-Batch Fermentation Involving Multiple Feeds by Chongyang Liu, Zhaohua Gong, Zhaoyi Huo, Bangyu Shen

“…To maximize the 1,3-PD concentration at the terminal time, a constrained optimal control model is then presented. A solution approach is developed to seek the optimal feed rates based on control vector parametrization method and improved differential evolution algorithm. …”
Get full text

Optimized Offloading in Vehicular Edge Computing: A Game Theoretic Analysis by Abdelkarim Ait Temghart, Mbarek Marwan, Mohamed Baslam

Get full text

A self-learning method with domain knowledge integration for intelligent welding sequence planning by Weidong Shen, Xuewen Wang, Juanli Li, Yong Wang, Xiaojun Qiao

“…To improve the interpretability of the results, domain knowledge was integrated into the construction and training processes of a self-learning model. …”
Get full text

RIS-assisted terahertz frequency band vehicle network capacity optimization by Fatang CHEN, Xiaoling LIU, Dan WANG, Ruofan ZHANG

“…In order to alleviate the spectrum scarcity and capacity limitation of the current wireless system, the terahertz frequency band was introduced and the reconfigurable intelligent surface (RIS) was used for auxiliary communication to construct a downlink vehicle network.Considering the constraints of limited total system power, QoS constraints of cellular mobile users, and randomness constraints of vehicle and user locations, a hybrid optimization model was established for optimal power allocation and optimal deployment of RIS with the aim of maximizing the total rate of vehicle users.Based on the balance method, linear transformation method, and element elimination method, the original NP-hard problem was transformed into a convex optimization problem with complex correlation constraints and multivariate coupling.The inner layer iteration was based on the Lagrange multiplier method to solve the optimal power allocation, and the outer layer iteratively solved the optimal deployment of RIS based on a improved genetic algorithm.The simulation results show that rationally deploying the number and distribution density of RIS nodes based on optimal power allocation can save costs while achieving a higher target total capacity.…”
Get full text

Optimization Design and Simulation of Single Degree of Freedom Legs of Quadruped Robots by Shi Huiwen, He Jing, Wang Zhijun

“…The optimal motion size and initial position of each component of the mechanism are optimized by using the genetic algorithm and the general nonlinear optimization method with the approximation degree of non-impact foot trajectory as the objective. …”
Get full text

Optimized YOLOv8 framework for intelligent rockfall detection on mountain roads by Peng Peng, Langchao Gao, Jiachun Li, Hongzhen Zhang

“…To enable efficient detection, this study proposes a rockfall detection system based on embedded technology and an improved Yolov8 algorithm, termed Yolov8-GCB. The algorithm enhances detection performance through the following optimizations: (1) integrating a lightweight DeepLabv3+ road segmentation module at the input stage to generate mask images, which effectively exclude non-road regions from interference; (2) replacing Conv convolution units in the backbone network with Ghost convolution units, significantly reducing model parameters and computational cost while improving inference speed; (3) introducing the CPCA (Channel Priori Convolution Attention) mechanism to strengthen the feature extraction capability for targets with diverse shapes; and (4) incorporating skip connections and weighted fusion in the Neck feature extraction network to enhance multi-scale object detection. …”
Get full text

SVR Data-Driven Optimization of Generator Leading Phase Operation Limit by Dengfeng LI, Mincai YANG, Yuming LIU, Ruilin XU, Xia YU, Zhaojiong LI

“…The improved second-order oscillation particle swarm optimization algorithm is then applied to solve the optimization model. …”
Get full text