Multi-Task Water Quality Colorimetric Detection Method Based on Deep Learning by Shenlan Zhang, Shaojie Wu, Liqiang Chen, Pengxin Guo, Xincheng Jiang, Hongcheng Pan, Yuhong Li

“…Experimental results demonstrate that the optimized deep learning algorithm excels in precision (96.4%), recall (96.2%), and mAP50 (98.3), significantly outperforming other mainstream models. …”
Get full text

Review: the application of deep reinforcement learning to quantitative trading in financial market by XU Bo, HE Yijun, WEN Jiancheng, LI Xiangxia

“…It is believed that with the continuous optimization of algorithms and the improvement of computing power, DRL will play a more important role in the field of quantitative trading in financial market, providing more accurate and reliable support for investment decisions.…”
Get full text

Research on the Control Method of Force Servo System of Liquid Hydrostatic Guide Oil Film Thickness Test Bench for Machine Tools by Xu Fang, Youmin Wang, Bo Zhu

“…And based on the fast overshoot of the classical PID control, introducing the self-antidisturbance control algorithm, this study established a mathematical model of the test bench electro-hydraulic servo control system. …”
Get full text

Adaptive Anomaly Detection in Network Flows With Low-Rank Tensor Decompositions and Deep Unrolling by Lukas Schynol, Marius Pesavento

“…We first propose a novel block-successive convex approximation algorithm based on a regularized model-fitting objective where the normal flows are modeled as low-rank tensors and anomalies as sparse. …”
Get full text

Statistical Evaluation of Smartphone-Based Automated Grading System for Ocular Redness Associated with Dry Eye Disease and Implications for Clinical Trials by Rodriguez JD, Hamm A, Bensinger E, Kerti SJ, Gomes PJ, Ousler III GW, Gupta P, De Moraes CG, Abelson MB

“…The optimal generalized model improved predictive accuracy with horizontality such that 93.0% of images were predicted with an absolute error less than one unit difference in grading.Conclusion: This study demonstrates that fully automating image analysis allows thousands of images to be graded efficiently. …”
Get full text

Experimental Study on Evaluation of Organization Collaboration in Prefabricated Building Construction by Dingjing Bao, Yuan Chen, Shuai Wan, Jinlai Lian, Ying Lei, Kaizhe Chen

“…The knowledge-driven part of this evaluation system used an evaluation model based on the analytic hierarchy process (AHP), while the data-driven part used a prediction model based on the BO-XGBoost algorithm to verify the validity of the AHP-based model. …”
Get full text

Data-driven approach to mid-latitude coherent scatter radar data classification by Berngardt Oleg

“…Based on 2021 data, a solution of the problem of automatic data classification is presented without their labeling by an expert and without postulating the number of classes. The algorithm automatically labels the data, determines the optimal number of signal classes observed by the radars, and trains a two-layer classifying neural network of an extremely simple structure. …”
Get full text

Enhancement Ear-based Biometric System Using a Modified AdaBoost Method by Abdulkareem Merhej Radhi, Subhi Aswad Mohammed

“…The proposed model is a new scenario for enhancing ear recognition accuracy via modifying the AdaBoost algorithm to optimize adaptive learning. …”
Get full text

Beyond Linearity: Uncovering the Complex Spatiotemporal Drivers of New-Type Urbanization and Eco-Environmental Resilience Coupling in China’s Chengdu–Chongqing Economic Circle with... by Caoxin Chen, Shiyi Wang, Meixi Liu, Ke Huang, Qiuyi Guo, Wei Xie, Jiangjun Wan

“…The results reveal the following: (1) NTU and EER levels steadily improved from 2004 to 2022, although coordination between cities still requires enhancement; (2) CCD exhibited a temporal pattern of “progressive escalation and continuous optimization,” and a spatial pattern of “dual-core leadership and regional diffusion,” with most cities shifting from NTU-lagged to synchronized development; (3) environmental regulations (MAR) and fixed asset investment (FIX) emerged as the most influential CCD drivers, and significant nonlinear interactions were observed, particularly those involving population size (HUM); (4) CCD drivers exhibited complex spatiotemporal heterogeneity, characterized by “stage dominance—marginal variation—spatial mismatch.” …”
Get full text

A long-term localization and mapping system for autonomous inspection robots in large-scale environments using 3D LiDAR sensors. by Wandeng Mao, Liang Jiang, Shanfeng Liu, Shengzhe Xi, Hua Bao

“…Then, to address drift errors, we formulate the global map as a graph of local submaps that undergo global optimization. Furthermore, we utilize marching cubes to generate a mesh model of the map. …”
Get full text

IoT intrusion detection method for unbalanced samples by ANTONG P, Wen CHEN, Lifa WU

“…In recent years, network traffic increases exponentially with the iteration of devices, while more and more attacks are launched against various applications.It is significant to identify and classify attacks at the traffic level.At the same time, with the explosion of Internet of Things (IoT) devices in recent years, attacks on IoT devices are also increasing, causing more and more damages.IoT intrusion detection is able to distinguish attack traffic from such a large volume of traffic, secure IoT devices at the traffic level, and stop the attack activity.In view of low detection accuracy of various attacks and sample imbalance at present, a random forest based intrusion detection method (Resample-RF) was proposed, which consisted of three specific methods: optimal sample selection algorithm, feature merging algorithm based on information entropy, and multi-classification greedy transformation algorithm.Aiming at the problem of unbalanced samples in the IoT environment, an optimal sample selection algorithm was proposed to increase the weight of small samples.Aiming at the low efficiency problem of random forest feature splitting, a feature merging method based on information entropy was proposed to improve the running efficiency.Aiming at the low accuracy problem of random forest multi-classification, a multi-classification greedy transformation method was proposed to further improve the accuracy.The method was evaluated on two public datasets.F1 reaches 0.99 on IoT-23 dataset and 1.0 on Kaggle dataset, both of which have good performance.The experimental results show that the proposed model can effectively identify the attack traffic from the massive traffic, better prevent the attack of hackers on the application, protect the IoT devices, and thus protect the related users.…”
Get full text

Predicting Employee Turnover Using Machine Learning Techniques by Adil Benabou, Fatima Touhami, My Abdelouahed Sabri

“…This study aims to identify the most effective machine learning model for predicting employee attrition, thereby providing organizations with a reliable tool to anticipate turnover and implement proactive retention strategies.Objective: This study aims to address the challenge of employee attrition by applying machine learning techniques to provide predictive insights that can improve retention strategies.Methods: Nine machine learning algorithms are applied to a dataset of 1,470 employee records. …”
Get full text

Adaptive zero velocity correction method for fiber optic inertial navigation system in coal mining roadheader by Qinghua MAO, Qing ZHOU, Jianquan CHAI, Yanzhang CHEN, Wenjuan YANG, Xusheng XUE

“…Secondly, the time-frequency domain features of IMF components are extracted, and the principal component analysis method is used to reduce the dimension to reduce the complexity of the diagnostic model and the difficulty of data analysis. Finally, the accuracy of zero-speed detection is improved by introducing the sandcat swarm optimization algorithm to optimize the kernel function and penalty parameters.Aiming at the problem of high cost and error accumulation with time of high-precision fiber-optic inertial navigation, an adaptive zero-speed correction method is proposed. …”
Get full text

Transient stability assessment of wind turbine grid-connected systems using ISSA-MSVR by FAN Hong, XU Yongjie, XU Tao

“…To address the issue of inaccurate transient stability analysis in power systems after wind farm integration， this paper proposes a method combining improved sparrow search algorithm （ISSA）-optimized multi-output support vector regression （MSVR）. …”
Get full text

Multi-Modal Federated Learning Over Cell-Free Massive MIMO Systems for Activity Recognition by Seyed Mohammad Sheikholeslami, Pai Chet Ng, Jamshid Abouei, Konstantinos N. Plataniotis

“…Extensive experiments validate our framework, demonstrating substantial reductions in training time and significant improvements in model performance, particularly an average improvement of 15% and 23% in test accuracy compared to the other fusion models when missing one and two modalities in the inference phase.…”
Get full text

Anti-packet-loss joint encoding for voice-over-IP steganography by Zhan-zhan GAO, Guang-ming TANG, Wei-wei ZHANG

“…Furthermore, the influences of key parameters on the performance of joint coding were studied. The selection algorithm for optimal parameters was also given. Experimental results show that the proposed joint coding can effectively improve steganographic resistance to packet loss, and decrease the number of modifications to the voice stream.…”
Get full text

Monitoring of Transformer Hotspot Temperature Using Support Vector Regression Combined with Wireless Mesh Networks by Naming Zhang, Guozhi Zhao, Liangshuai Zou, Shuhong Wang, Shuya Ning

“…Subsequently, this study employed a Support Vector Regression (SVR) algorithm to train the sample dataset, optimizing the SVR model using a grid search and cross-validation to enhance the predictive accuracy. …”
Get full text

Research on Active–Passive Training Control Strategies for Upper Limb Rehabilitation Robot by Yongming Yang

“…By utilizing neural networks to train sample data during rehabilitation training, the fuzzy rules and membership functions in fuzzy intention recognition algorithm are optimized to improve the accuracy of intention recognition during training. …”
Get full text

RRBM-YOLO: Research on Efficient and Lightweight Convolutional Neural Networks for Underground Coal Gangue Identification by Yutong Wang, Ziming Kou, Cong Han, Yuchen Qin

“…The lightweight module RepGhost, the repeated weighted bi-directional feature extraction module BiFPN, and the multi-dimensional attention mechanism MCA were integrated, and different datasets were replaced to enhance the adaptability of the model and improve its generalization ability. The findings from the experiment indicate that the precision of the proposed model is as high as 0.988, the mAP@0.5(%) value and mAP@0.5:0.95(%) values increased by 10.49% and 36.62% compared to the original YOLOv8 model, and the inference speed reached 8.1GFLOPS. …”
Get full text

Few-Shot Intelligent Anti-Jamming Access with Fast Convergence: A GAN-Enhanced Deep Reinforcement Learning Approach by Tianxiao Wang, Yingtao Niu, Zhanyang Zhou

“…Furthermore, it screens qualified samples using the Pearson correlation coefficient to form a sample set, which is input into the DQN network model for pre-training to expand the experience replay buffer, effectively improving the convergence speed and decision accuracy of DQN. …”
Get full text