Multi-objective optimization of integrated energy system considering customer satisfaction by YU Wuyue, JIA Yuchen, HUO Limin, WEN Peng, GAO Liai

“…A multi-objective optimization function with improved customer satisfaction, economy and carbon emission is constructed, and MAPSO (multi-group adaptive particle swarm optimization) algorithm is used for optimization analysis, and the Pareto optimal frontier solution sets in different scenarios are obtained. …”
Get full text

A novel reinforcement learning framework-based path planning algorithm for unmanned surface vehicle by Jianhui Mou, Bo Shi, Bo Wang, Chengcheng Yu, Yangwei Wang, Fusheng Zhong, Li Zheng, Jian Wang, Junjie Li

“…Subsequently, an optimized deep neural network with a reward-averaging strategy is constructed to effectively enhance the learning and convergence speed of the algorithm, thus further improving the global search capability and interface performance of USV path planning. …”
Get full text

Reliable and efficient magnetic data inversion for resource detection using a hybrid bat algorithm by Khalid S. Essa, Mahmoud Elhussein, Omar A. Gomaa, Zein E. Diab

“…The estimated subsurface parameters closely match with well data and prior studies, emphasizing the algorithm’s practical effectiveness. This integrated approach significantly advances the interpretation of magnetic datasets by improving both the accuracy and resolution of subsurface parameters estimation within the framework of idealized geometric models.…”
Get full text

Automatic detection and classification of drill bit damage using deep learning and computer vision algorithms by Xiongwen Yang, Xiao Feng, Chris Cheng, Jiaqing Yu, Qing Zhang, Zilong Gao, Yang Liu, Bo Chen

“…The experimental results demonstrate that the proposed method significantly enhances the accuracy of bit damage detection and classification while also providing substantial improvements in processing speed and computational efficiency, offering a valuable tool for optimizing drilling operations and reducing costs.…”
Get full text

Dynamic Analysis and Efficient Numerical Algorithm for Rocking Response of Freestanding Packages Under Transportation Excitations by Zhenmin Qi, Dapeng Zhu

“…Experimental validation under sinusoidal and numerical analysis with random excitations confirms the algorithm’s effectiveness in predicting rocking behavior. …”
Get full text

Integrated deep learning for cardiovascular risk assessment and diagnosis: An evolutionary mating algorithm-enhanced CNN-LSTM by Ahmed Mohammed Ahmed Alsarori, Mohd Herwan Sulaiman

“…Cardiovascular diseases (CVD) remain the leading cause of mortality worldwide, emphasizing the urgent need for accurate and efficient predictive models. This study proposes a dual-output deep learning model based on a hybrid Convolutional Neural Network–Long Short-Term Memory (CNN-LSTM) model, optimized using the Evolutionary Mating Algorithm (EMA). …”
Get full text

Application of the joint clustering algorithm based on Gaussian kernels and differential privacy in lung cancer identification by Hang Yanping, Zheng Haixia, Yang Minmin, Wang Nan, Kong Miaomiao, Zhao Mingming

“…The algorithm enhances cancer detection while ensuring data privacy. …”
Get full text

Water Supply Scheduling for Cross-basin Reservoir Groups Based on Improved Scheduling Diagram by ZHAO Siqi, XU Wei, CHEN Si, WANG Sufan, YANG Yi

“…To exploit the scheduling potential of cross-basin reservoir groups by employing runoff information,this paper proposes an improved reservoir scheduling diagram to retain simplicity and intuitiveness.Taking the Xiajiankou,Fengyan,and Nanpeng reservoirs in Banan District of Chongqing as an example,it adopts the POA algorithm to build a joint scheduling model of water diversion and water supply for the cross-basin reservoir groups by a simulation-optimization approach.Meanwhile,three scenarios of the current situation scheduling,optimized scheduling with conventional scheduling diagrams,and optimized scheduling with improved scheduling diagrams are set up to evaluate the water diversion and supply performance of reservoirs and analyze the influence of uncertainty runoff information on the scheduling performance.The results are as follows:① The improved scheduling diagram performs best in the long series scheduling,and it can increase the annual average water supply of the reservoir group by 6.87% and reduce the abandoned water by 87.58% compared with the current situation scheduling;② In a dry year,the method can reduce 486.3×10⁴ m³ of water shortage and increase 477.6×10⁴ m³ of water for power generation based on the current situation scheduling;③ When considering the runoff information uncertainty,the water supply of the improved scheduling diagram is 3.37% lower than the ideal case but is still 5.96% more than the conventional optimization.The results are conducive to making scientific decisions and improving the water supply effect.…”
Get full text

Stability Analysis and Construction Parameter Optimization of Tunnels in the Fractured Zone of Faults by Banma Huang, Haibo Chen, Chenglong Duan, Wenhu Li

“…Finally, the actual blasting effect of tunnel construction is tested and the optimization algorithm model of tunnel fault drilling and blasting parameters is established. …”
Get full text

A Comparison of AutoML Hyperparameter Optimization Tools For Tabular Data by Prativa Pokhrel, Alina Lazar

“…Therefore, finding the optimal values of these hyperparameters is integral in improving the prediction accuracy of an ML algorithm and the model selection. …”
Get full text

Optimal control strategy for trains in emergency self-propelled running conditions by ZHU Yutong

“…In conclusion, the designed coasting algorithm based on the optimal constant speed can effectively reduce the total energy consumption of emergency self-propelled train operation, thereby improving the self-rescue success rate of high-speed trains.…”
Get full text

Solution Approach to the Minimum Spanning Tree Problem in Tsukamoto Fuzzy and Fermantean Fuzzy Environments by Desli de Haas, Citra Palembang, Aziz Rumakefing

“…With the help of Numerical examples, the solution technique for the proposed FFMST model is explained. It aims to modify the Prims algorithm for oriktade graphing and the optimal result processing algorithm for re-graphing in Fuzzy Fermatean ( FFN )-miljö. …”
Get full text

Bi-Objective Optimization of Product Selection and Ranking Considering Sequential Search by Yuyang Tan, Hao Gong, Chunxiang Guo

“…To address this gap, we study a bi-objective product selection and ranking (BP-SS) problem considering sequential search, aiming to jointly optimize the expected revenue and market share. We first develop a two-stage choice model with consideration sets to capture how sequential search influences customer decision-making. …”
Get full text

Collaborative Optimization Strategy for Dependent Task Offloading in Vehicular Edge Computing by Xiting Peng, Yandi Zhang, Xiaoyu Zhang, Chaofeng Zhang, Wei Yang

“…The task-offloading problem is modeled as a Markov Decision Process, and an improved twin-delayed deep deterministic policy gradient algorithm, LT-TD3, is introduced to enhance the decision-making process. …”
Get full text

Tool wear monitoring method based on AMIDBOAB and imbalanced data optimization by Guan-Hua Xu, Hong-Yu Wu, Bo Tang, Jun-Long Xu

“…Introducing circle chaotic mapping, Levy flight strategy, and adaptive variable inertia weight, a multiple improvement dung beetle optimizer algorithm is proposed to optimize the parameters of the base classifier in the adaptive boosting model. …”
Get full text

Machine learning to improve HIV screening using routine data in Kenya by Jonathan D. Friedman, Jonathan M. Mwangi, Kennedy J. Muthoka, Benedette A. Otieno, Jacob O. Odhiambo, Frederick O. Miruka, Lilly M. Nyagah, Pascal M. Mwele, Edmon O. Obat, Gonza O. Omoro, Margaret M. Ndisha, Davies O. Kimanga

“…We generated a stratified 60‐20‐20 train‐validate‐test split to assess model generalizability. We trained four machine learning algorithms including logistic regression, Random Forest, AdaBoost and XGBoost. …”
Get full text

Optimization of train obstacle detection based on zone media controller unit by ZHOU Liming, HU Jiaqiao, SHEN Tuo

Get full text

Improving the Integrity of a Voting Process with Biometric Authentication and Data Encryption by Walter M. Molina, Lino R. Mac Kay, Daniel Subauste

Get full text

Optimization mechanism of attack and defense strategy in honeypot game with evidence for deception by Lihua SONG, Yangyang JIANG, Changyou XING, Guomin ZHANG

“…Using game theory to optimize honeypot behavior is an important method in improving defender’s trapping ability.Existing work tends to use over simplified action spaces and consider isolated game stages.A game model named HoneyED with expanded action spaces and covering comprehensively the whole interaction process between a honeypot and its adversary was proposed.The model was focused on the change in the attacker’s beliefs about its opponent’s real identity.A pure-strategy-equilibrium involving belief was established for the model by theoretical analysis.Then, based on the idea of deep counterfactual regret minimization (Deep-CFR), an optimization algorithm was designed to find an approximate hybrid-strategy-equilibrium.Agents for both sides following hybrid strategies from the approximate equilibrium were obtained.Theoretical and experimental results show that the attacker should quit the game when its belief reaches a certain threshold for maximizing its payoff.But the defender’s strategy is able to maximize the honeypot’s profit by reducing the attacker’s belief to extend its stay as long as possible and by selecting the most suitable response to attackers with different deception recognition abilities.…”
Get full text

A Crash Severity Prediction Method Based on Improved Neural Network and Factor Analysis by Chen Zhang, Jie He, Yinhai Wang, Xintong Yan, Changjian Zhang, Yikai Chen, Ziyang Liu, Bojian Zhou

“…The results showed that although the algorithms produced almost the same accuracy in their predictions, a backpropagation method combined with a nonlinear inertial weight setting in PSO produced fast global and accurate local optimal searching, thereby demonstrating a better understanding of the entire model explanation, which could best fit the model, and at last, the factor analysis showed that non-road-related factors, particularly vehicle-related factors, are more important than road-related variables. …”
Get full text