Non-end-to-end adaptive graph learning for multi-scale temporal traffic flow prediction. by Kang Xu, Bin Pan, MingXin Zhang, Xuan Zhang, XiaoYu Hou, JingXian Yu, ZhiZhu Lu, Xiao Zeng, QingQing Jia

“…Existing methods, however, have the following limitations: (1) insufficient exploration of interactions across different temporal scales, which restricts effective future flow prediction; (2) reliance on predefined graph structures in graph neural networks, making it challenging to accurately model the spatial relationships in complex road networks; and (3) end-to-end training, which often results in unclear optimization directions for model parameters, thereby limiting improvements in predictive performance. …”
Get full text

Efficient and accurate determination of the degree of substitution of cellulose acetate using ATR-FTIR spectroscopy and machine learning by Frank Rhein, Timo Sehn, Michael A. R. Meier

“…By applying a n-best feature selection algorithm based on the F-statistic of the Pearson correlation coefficient, several relevant areas were identified and the optimized model achieved an improved MAE of 0.052. …”
Get full text

Research on Dynamic Storage Location Assignment of Picker-to-Parts Picking Systems under Traversing Routing Method by Xiangbin Xu, Chenhao Ren

“…Then, the adjustment gain model of dynamic storage location assignment is built, and a genetic algorithm is designed to find the final adjustment solution. …”
Get full text

Real-time prediction of HFNC treatment failure in acute hypoxemic respiratory failure using machine learning by Xiaojie Li, Chunliang Jiang, Qingyan Xie, Huiquan Wang, Jiameng Xu, Guanjun Liu, Panpan Chang, Guang Zhang

“…The soft-voting ensemble algorithm achieved an optimal predictive performance with an AUC of 0.839 (95% CI 0.786–0.889) for the all-features model, while logistic regression using common features achieved an AUC of 0.767 (95% CI 0.704–0.825), outperforming ROX and mROX indices. …”
Get full text

Energy-Balanced Data Gathering and Aggregating in WSNs: A Compressed Sensing Scheme by Xiaofei Xing, Dongqing Xie, Guojun Wang

“…In WSNs, data aggregating can reduce data transmission cost and improve energy efficiency. Existing CS-based data gathering work in WSNs utilizes the centralized method to process the data by a sink node, which causes the load imbalance and “coverage hole” problems, and so forth. …”
Get full text

Hyperspectral Detection of Pesticide Residues in Black Vegetable Based on Multi-Classifier Entropy Weight Method by Rongchang Jiang, Guoqiang Zhuang, Shijie Xie, Yang Wang, Guoqi Zhang, Dandan Qu, Wanzhi Wen

“…The entropy weight method was then used to optimize model weights, developing the multi-classifier entropy weighted method algorithm to improve detection accuracy and robustness. …”
Get full text

A Reputation Value-Based Task-Sharing Strategy in Opportunistic Complex Social Networks by Jia Wu, Fangfang Gou, Wangping Xiong, Xian Zhou

“…The two submodels apply an improved particle swarm algorithm and a Lagrange multiplier, respectively. …”
Get full text

Building construction crack detection with BCCD YOLO enhanced feature fusion and attention mechanisms by Wenhao Ren, Zuowei Zhong

“…Firstly, this model optimizes the Path Aggregation Network (PAN) by introducing lateral skips and weighted feature fusion mechanisms, improving the multi-scale fusion capability of bare concrete crack features. …”
Get full text

Privacy-preserving federated learning framework with dynamic weight aggregation by Zuobin YING, Yichen FANG, Yiwen ZHANG

“…There are two problems with the privacy-preserving federal learning framework under an unreliable central server.① A fixed weight, typically the size of each participant’s dataset, is used when aggregating distributed learning models on the central server.However, different participants have non-independent and homogeneously distributed data, then setting fixed aggregation weights would prevent the global model from achieving optimal utility.② Existing frameworks are built on the assumption that the central server is honest, and do not consider the problem of data privacy leakage of participants due to the untrustworthiness of the central server.To address the above issues, based on the popular DP-FedAvg algorithm, a privacy-preserving federated learning DP-DFL algorithm for dynamic weight aggregation under a non-trusted central server was proposed which set a dynamic model aggregation weight.The proposed algorithm learned the model aggregation weight in federated learning directly from the data of different participants, and thus it is applicable to non-independent homogeneously distributed data environment.In addition, the privacy of model parameters was protected using noise in the local model privacy protection phase, which satisfied the untrustworthy central server setting and thus reduced the risk of privacy leakage in the upload of model parameters from local participants.Experiments on dataset CIFAR-10 demonstrate that the DP-DFL algorithm not only provides local privacy guarantees, but also achieves higher accuracy rates with an average accuracy improvement of 2.09% compared to the DP-FedAvg algorithm models.…”
Get full text

Research on Cognitive Radio Non-orthogonal Multiple Access System in 5G Communications Oriented to Ubiquitous Power Internet of Things by Rui SHE, Ningchi ZHANG, Yanru WANG, Dandan GUO, Wenjie MA, Hui LIU, Jie ZHANG

“…The closed expressions of spectrum access probability and throughput are derived; in order to further increase the accuracy of the classification results, an improved K-means algorithm is proposed. The alternate iterative algorithm is implemented to jointly optimize the detection time, node power and the number of user clusters such that the system throughput can be maximized eventually. …”
Get full text

Detection of Critical Parts of River Crab Based on Lightweight YOLOv7-SPSD by Guoai Fang, Yu Zhao

“…These additions help achieve an initial reduction in model size while preserving detection accuracy. Furthermore, we optimize the model by removing redundant parameters using the DepGraph pruning algorithm, which facilitates its application on edge devices. …”
Get full text

Two-stage denoising method for complex underground tunnel scene three-dimensional point clouds by Zhuli REN, Ruifu YUAN, Liguan WANG, Haokun DENG, Wen WANG, Jinlong ZHANG

“…When the angle threshold is less than 1°, the optimal denoising effect can be achieved. Through the two-stage optimization algorithm, effective repair of surface holes on the tunnel is achieved. …”
Get full text

YOLOv8-Based Estimation of Estrus in Sows Through Reproductive Organ Swelling Analysis Using a Single Camera by Iyad Almadani, Mohammed Abuhussein, Aaron L. Robinson

“…We then harnessed the power of machine learning to train our model using annotated images, which facilitated keypoint detection and segmentation with the state-of-the-art YOLOv8 algorithm. …”
Get full text

From Tables to Computer Vision: Transforming HPDC Process Data into Images for CNN-Based Deep Learning by A. Burzyńska

“…Utilizing a combination of statistical pre-processing, intelligent generative models, visual data transformations and deep learning, the methodology offers a comprehensive approach to enhancing production efficiency, ensuring superior process control and improving the quality of HPDC products. …”
Get full text

Adaptive robust self‐scheduling for a wind‐based GenCo equipped with power‐to‐gas system and gas turbine to participate in electricity and natural gas markets by Mojtaba Fereydani, Mohammad Amin Latify

“…A column & constraint generation (C&CG) algorithm is used to solve the model. Numerical results demonstrate the model’s effectiveness in various case studies, showing that the GenCo can manage wind uncertainties, benefit from arbitrage opportunities in electricity and gas markets, and improve economic outcomes. …”
Get full text

DLML-PC: an automated deep learning and metric learning approach for precise soybean pod classification and counting in intact plants by Yixin Guo, Jinchao Pan, Xueying Wang, Hong Deng, Hong Deng, Mingliang Yang, Mingliang Yang, Enliang Liu, Qingshan Chen, Qingshan Chen, Rongsheng Zhu, Rongsheng Zhu

“…By improving the Siamese Network in metric learning, the optimal Siamese Network model was obtained. …”
Get full text

Large-scale S-box design and analysis of SPS structure by Lan ZHANG, Liangsheng HE, Bin YU

“…A class of optimal linear transformation P over a finite field<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML"> <mrow> <msup> <mrow> <mrow><mo>(</mo> <mrow> <msubsup> <mi>F</mi> <mn>2</mn> <mi>m</mi> </msubsup> </mrow> <mo>)</mo></mrow></mrow> <mn>4</mn> </msup> </mrow></math></inline-formula> was constructed based on cyclic shift and XOR operation.Using the idea of inverse proof of input-output relation of linear transformation for reference, a proof method was put forward that transformed the objective problem of optimal linear transformation into several theorems of progressive relation, which not only solved the proof of that kind of optimal linear transformation, but also was suitable for the proof of any linear transformation.By means of small-scale S-box and optimal cyclic shift-XOR linear transformation P, a large-scale S-box model with 2-round SPS structure was established, and a series of lightweight large-scale S-boxes with good cryptographic properties were designed.Only three kind of basic operations such as look-up table, cyclic shift and XOR were used in the proposed design scheme, which improved the linearity and difference uniformity of large-scale S-boxes.Theoretical proof and case analysis show that, compared with the existing large-scale S-box construction methods, the proposed large-scale S-box design scheme has lower computational cost and better cryptographic properties such as difference and linearity, which is suitable for the design of nonlinear permutation coding of lightweight cryptographic algorithms.…”
Get full text

Sparse Temporal Data-Driven SSA-CNN-LSTM-Based Fault Prediction of Electromechanical Equipment in Rail Transit Stations by Jing Xiong, Youchao Sun, Junzhou Sun, Yongbing Wan, Gang Yu

“…When predicting the fault rate data of the screen doors on a single line, the performance of the model was better than that of the CNN-LSTM model optimized with the PSO algorithm.…”
Get full text

Joint Event Density and Curvature Within Spatio-Temporal Neighborhoods-Based Event Camera Noise Reduction and Pose Estimation Method for Underground Coal Mine by Wenjuan Yang, Jie Jiang, Xuhui Zhang, Yang Ji, Le Zhu, Yanbin Xie, Zhiteng Ren

“…The attitude estimation framework adopts the noise reduction event and global optimal perspective-n-line (OPNL) methods to obtain the initial target attitude, and then establishes the event line correlation model through the robust estimation, and achieves the attitude tracking by minimizing the event line distance. …”
Get full text

A Full-Profile Measurement Method for an Inner Wall with Narrow-Aperture and Large-Cavity Parts Based on Line-Structured Light Rotary Scanning by Zhengwen Li, Changshuai Fang, Xiaodong Zhang

“…Considering the structural constraints in the measurement of narrow-aperture and large-cavity parts, a structural optimization algorithm is designed to enable the sensor to achieve a high theoretical measurement resolution while satisfying the geometric constraints of the measured parts. …”
Get full text