A contrast enhanced representation normalization approach to knowledge distillation by Zhiqiang Bao, Di Zhu, Leying Du, Yang Li

“…Meanwhile, drawing on the idea of the Triplet Loss function in contrastive learning, we constructed a loss function and integrated it into the Contrastive Representation Distillation Loss to form the Contrast Enhanced Representation Normalization Distillation Loss. …”
Get full text

A Federated Learning Model for Detecting Cyberattacks in Internet of Medical Things Networks by Abdallah Ghourabi, Adel Alkhalil

“…The XGBoost models are further optimized using a Bayesian method and integrated with an aggregation algorithm to construct an adaptive global model. …”
Get full text

Intelligent policy framework: Natural resource conservation, knowledge and big data analytics by Nina Xiao, Xianhe Qu

“…To enhance the reliability of the results, this study employed two algorithms: Bayesian inference and a weighted Support Vector Machine (SVM) algorithm based on the grey relational analysis. …”
Get full text

HybridFormer: a convolutional neural network-Transformer architecture for low dose computed tomography image denoising by Shanaz Sharmin Jui, Zhitao Guo, Rending Jiang, Jiale Liu, Bohua Li

“…Firstly, this algorithm constructs residual convolution for local feature extraction and Swin Transformer for global feature extraction, boosting denoising efficacy. …”
Get full text

Leveraging ensemble learning-based stock preselection with multiobjective investment optimization for stepwise decision-supported portfolio management by Jui-Sheng Chou, Tran-Bao-Quyen Pham

“…The AID-MOFBI-XGB model combines the MOFBI optimization algorithm, XGB machine learning technique, and an expanded mean–variance strategy. …”
Get full text

A Knowledge-Driven Smart System Based on Reinforcement Learning for Pork Supply-Demand Regulation by Haohao Song, Jiquan Wang

“…By harnessing dynamic decision-making capabilities of reinforcement learning (RL), we design an optimization architecture centered on the Q-learning mechanism and dual-strategy pools, which is integrated into the honey badger algorithm to form the RL-enhanced honey badger algorithm (RLEHBA). …”
Get full text

Hazard Assessment of Extreme Compound Flood Hazards in Coastal Cities under Climate Change: A Case Study of Haikou City by Liu Qing, Wu Guofeng, Yao Qian, Xu Hanqing, Niu Yiying, Wei Xuchen, Wang Jun, Li Mengya

“…This study applied a high-resolution MRI-AGCM3-2-S climate model and the TempestExtremes tracking algorithm to construct a 6-hourly Tropical Cyclone (TC) track dataset affecting Haikou from 1960 to 2099. …”
Get full text

Bioinformatics-based screening and validation of PANoptosis-related biomarkers in periodontitis by Qing Sun, Qing Sun, JinYue Hu, JinYue Hu, RuYue Wang, RuYue Wang, ShuiXiang Guo, ShuiXiang Guo, GeGe Zhang, GeGe Zhang, Ao Lu, Ao Lu, Xue Yang, Xue Yang, LiNa Wang, LiNa Wang

“…Machine learning algorithms were then applied to screen for potential biomarkers. …”
Get full text

Systematic elucidation of the effective constituents and potential mechanisms of Scrophulariae Radix against neoplasm based on LC-MS, network pharmacology, and molecular docking ap... by Shu-jie Yu, Xiao-bin Kong, Xin Jin, Meng-yi Shan, Gang Cheng, Pei-lu Wang, Wen-long Li, Pei-yuan Zhao, Yun-jie Sheng, Bing-qian He, Qi Shi, Hua-qiang Li, Qi-ming Zhao, Lu-ping Qin, Lu-ping Qin, Xiong-yu Meng, Xiong-yu Meng

“…KEGG pathway enrichment primarily involved pathways in cancer and the cAMP signaling pathway in cancer. Overall, this integration method provided guiding significance for the exploration of TCM treatment.…”
Get full text

On the determination of the calculated runoff characteristics in conditions of time series homogeneity violation by Mikhail V. Bolgov, Irina A. Filippova

Operational Decision Model for Demand Response Considering Carbon Reduction Value of Adjustable Loads by Xiaoxuan ZHANG, Song XUE, Ye XU, Yi XU, Zeyu DING, Qingkai SUN

“…Demand response is one of the important adjustable load resources, which plays an important role in promoting carbon reduction and new energy consumption in new power systems. This article integrated carbon flow theory, intelligent optimization algorithm, and multi-attribute evaluation methods into adjustable load operation strategy decision-making for demand response. …”
Get full text

Schur Complement Optimized Iterative EKF for Visual–Inertial Odometry in Autonomous Vehicles by Guo Ma, Cong Li, Hui Jing, Bing Kuang, Ming Li, Xiang Wang, Guangyu Jia

“…It then integrates visual information and Inertial Measurement Unit (IMU) data through IEKF, constructing a complete residual model. …”
Get full text

GA-Based Early Warning Method for Rock Burst with Microseismic and Acoustic Emission in Steeply Inclined Coal Seam by Yarong Xue, Dazhao Song, Zhenlei Li, Jianqiang Chen, Xueqiu He, Shengquan He, Donghui Li

“…Aiming at problem of low efficacy of early warning of rock burst in coal mine, a multisystem and multiparameter integrated early warning method based on genetic algorithm (GA) is proposed. …”
Get full text

Low-Carbon Dispatch Method for Active Distribution Network Based on Carbon Emission Flow Theory by Jiang Bian, Yang Wang, Zhaoshuai Dang, Tianchun Xiang, Zhiyong Gan, Ting Yang

“…We improve the Soft Actor–Critic (SAC) algorithm by adopting a Gaussian-distribution-based reward function to train and deploy agents for optimal low-carbon dispatch. …”
Get full text

SynthSoM: A synthetic intelligent multi-modal sensing-communication dataset for Synesthesia of Machines (SoM) by Xiang Cheng, Ziwei Huang, Yong Yu, Lu Bai, Mingran Sun, Zengrui Han, Ruide Zhang, Sijiang Li

“…Abstract Given the importance of datasets for sensing-communication integration research, a novel simulation platform for constructing communication and multi-modal sensory dataset is developed. …”
Get full text

Research on the Day-Ahead Operation Decision Making Method for the Electric-Thermal System Based on Grey Fuzzy Evaluation by Zhe WANG, Xu YANG, Di ZHU, Xianglong LI, Qijing XING, Liyong WANG, Linyu WANG

Get full text

A student academic performance prediction model based on the interval belief rule base by Wenkai Zhou, Yunsong Li, Jiaxing Li, Tianhao Zhang, Xiping Duan, Ning Ma, Yuhe Wang

“…The parameters of the IBRB-C model are determined by combining the expert knowledge and the Kmeans++ algorithm. Subsequently, the P-CMA-ES algorithm is applied to optimize the initial model. …”
Get full text

Stability analysis and controller parameter optimization method for ship power electronic propulsion system based on Middlebrook criterion by Chenghu XU, Weibo LI, Hao ZHANG, Zhiming PENG, Hualiang FANG

“…Finally, a simulation model of the DC propulsion system is constructed to simulate and analyze the influence of the support capacitance and equivalent resistance and inductance of the DC bus on the stability of the system.ResultsThe simulation results show that the system's stability margin is obviously improved after the controller parameters are optimized by the particle swarm algorithm, which in turn lowers the value of support capacitance and reduces the overall size of the DC propulsion system's converter.ConclusionThe findings of this study can provide useful references for research on voltage oscillations and their suppression in integr-ated power systems with a significant proportion of power electronic devices.…”
Get full text

Open-access ultrasonic diaphragm dataset and an automatic diaphragm measurement using deep learning network by Zhifei Li, Lin Mao, Fan Jia, Shaohui Zhang, Cuiping Han, Shuiqiao Fu, Yueying Zheng, Yonghua Chu, Zuobing Chen, Daming Wang, Huilong Duan, Yinfei Zheng

“…Overall, the proposed diaphragm ultrasound segmentation algorithm demonstrated high segmentation performance and efficiency. …”
Get full text

Geological disaster risk assessment based on remote sensing, GIS, and a multi-strategy improved GWO-optimized Elman neural network by Kuayue Chen, Fuhong Bai, Ting Wang, Yingmei Su, Baoyun Wang

“…A regional feature database is constructed using GIS techniques. In the model design, strategies including chaotic reverse learning, nonlinear convergence control, Levy flight perturbation, and self-history best are introduced to enhance the global search capability and convergence stability of the algorithm. …”
Get full text