Cognitive MIMO radar waveform design for multiple moving extended targets by SHEN Tingli, ZHANG Yunlei, LU Jianbin, YU Guohua

“…In order to solve the problem of boosting cognitive MIMO radar for multiple moving target detection in cluttered backgrounds, this paper constructs a multi-target optimization model based on the dual mutual information criterion, takes into account the problem of linear variation of the motion target impulse response (TIR), estimates the TIR at the next moment by using Kalman filtering algorithm. …”
Get full text

Joint Allocation of Power and Subcarrier for Low Delay and Stable Power Line Communication by Zhixiong Chen, Zhihui Yang, Zeng Dou

“…Finally, the performance of the algorithm is compared and analyzed by simulation. The results show that the proposed algorithm can reduce the rate fluctuation and improve the system delay performance and deterministic transmission ability under the condition of ensuring the average rate optimization.…”
Get full text

Optimum Design Research on the Link Mechanism of the JP72 Lifting Jet Fire Truck Boom System by Guo Tong, Wang Jiawen, Liang Yingnan, Peng Buyu, Liu Tao, Liu Yiqun

“…Through mathematical models and computer simulations, it is the current mainstream optimization direction to optimize the structure of the boom linkage mechanism and improve its strength and stability. …”
Get full text

3D craniofacial registration using thin-plate spline transform and cylindrical surface projection. by Yucong Chen, Junli Zhao, Qingqiong Deng, Fuqing Duan

“…First, the gradient descent optimization is utilized to improve a cylindrical surface fitting (CSF) for the reference craniofacial model. …”
Get full text

Broad learning system based on attention mechanism and tracking differentiator by LIAO Lüchao, ZOU Weidong, YANG Jialong, LU Huihuang, XIA Yuanqing, GAO Jianlei

“…To alleviate these problems, broad learning system based on attention mechanism and tracking differentiator (TD), abbreviated as A-TD-BLS, was proposed. In terms of model structure, A-TD-BLS introduced self-attention mechanism to the original BLS, and further fused and transformed the extracted features through attention weighting to improve the feature learning ability.In terms of model training methods, a weight optimization algorithm based on tracking differentiator was designed.This method effectively alleviates the overfitting phenomenon of the original BLS by limiting the size of the weight values, significantly reduces the influence of the number of hidden layer nodes on model performance and makes the generalization performance more stable.Moreover, the training algorithm was extended to the BLS incremental learning framework, so that the model can improve performance by dynamically adding hidden layer nodes.Multiple experiments conducted on some benchmark datasets show that compared to the original BLS, the classification accuracy of A-TD-BLS is increased by 1.27% on average on classification datasets and the root mean square error of A-TD-BLS is reduced by 0.53 on average on regression datasets.Besides, A-TD-BLS is less affected by the number of hidden layer nodes and has more stable generalization performance. …”
Get full text

基于改进Kriging模型的主动学习可靠性分析方法 by 陈哲, 杨旭锋, 程鑫

“…,the differential evolution algorithm is introduced to explore the optimal parameter of Kriging model and improve the accuracy of Kriging prediction information.As a result,the training point in each iteration is guaranteed to be the global optimal one and the efficiency of ALK model is largely improved.…”
Get full text

Real-time torque distribution simulation of parallel hybrid vehicle engine by Jing Wang

“…Validation employed the Gamma Technologies Suite simulation platform and the Next Generation Simulation dataset, with benchmark comparisons against Equivalent Consumption Minimization Strategy, Fuzzy Logic Control, and Thermostat Strategy models.ResultsThe optimized Proximal Policy Optimization algorithm achieved 93.2% accuracy and 1.0% loss rate upon convergence, with an average feedback time of 32 milliseconds. …”
Get full text

Research on caching strategy based on transmission delay in Cell-Free massive MIMO systems by Rui WANG, Min SHEN, Yun HE, Xiangyan LIU

“…To meet the ultra-low latency and ultra-high reliability requirements of users in the future mobile Internet， the wireless caching technology was combined with Cell-Free massive MIMO systems.The caching model was designed based on AP cooperative caching and regional popularity evaluation.The transmission delay expression involving AP clustering， cooperative caching， and regional popularity was derived， and the content placement problem was expressed as total content transmission delay minimization.Through the demonstration of the NP-hard and submodular monotony of the optimization problem， the greedy algorithm-based optimization strategy was proposed.Simulation results show that the proposed strategy can effectively reduce the content transmission delay and improve the cache hit rate.…”
Get full text

Research on automatic identification method for pipeline girth weld defects based on X-ray images and sparse representation by Shaohui JIA, Yaping LI, Weixin GAO, Yunchao PENG, Xinjian ZHANG, Yuxia WANG

“…To maximize the library of image features within the dictionary matrix, an optimal model was established for X-ray SDR images of welds based on orthogonal optimization, along with a dictionary matrix solving algorithm featuring orthogonal optimization. …”
Get full text

Outdoor location scheme with fingerprinting based on machine learning of mobile cellular network by Zhichao ZHOU, Yi FENG, Xiaohan XIA, Yuyao FENG, Chao CAI, Jiahui QIU, Lihui YANG, Yunxiao WU

“…The positioning scheme based on mobile cellular network technology is one of the important technical approaches to provide network optimization, emergency rescue, police patrol and location services.The traditional positioning scheme based on cell base station location information has low positioning accuracy and large positioning error, so it cannot meet the requirements of some positioning applications.The scheme based on fingerprint location can greatly improve the location accuracy, save computational cost and enhance the usability based on the coarse location scheme of the cell and become the hotspot of the research.Rasterization and non-rasterization of outdoor fingerprint location scheme based on machine learning were studied and analyzed to meet the business requirements of outdoor fingerprint location.By means of parameter weighting, data fitting and other methods, large-scale fingerprint data were cleaned to improve the effectiveness of data sources.Through the realization of sub-modules such as demarcating research area, rasterizing, constructing fingerprint database, training model, correcting model, non-rasterizing, rough positioning coupling, matching parameter and training parameter, the operation efficiency and positioning accuracy of the algorithm were analyzed and optimized, and the key indexes affecting the algorithm performance were determined.Then, the performance of two fingerprint-based localization schemewas analyzed based on the simulation results.Finally, the typical scenarios of the fingerprint location scheme based on machine learning in practical application were presented.…”
Get full text

Soft Measurement of Wastewater Treatment System Based on PSOGA-WNN by LIU Yuhui, MAI Wenjie, LI Xiaoyong, ZHAO Yinzhong, HE Xinzhong, HUANG Mingzhi

“…To accurately predict the SS_eff (effluent SS) content and COD_eff (effluent COD) concentration in water quality parameters and further improve the water quality early warning mechanism,this paper proposes the PSOGA-WNN soft measurement model of paper wastewater effluent quality to obtain the main water quality technical parameters,COD_inf (influent COD),Q (influent flow),pH (influent pH),SS_inf (influent SS),T (influent temperature),DO (influent dissolved oxygen),COD_eff,and SS_eff, for predicting the quality of wastewater from the wastewater treatment plant.Among them,the prediction results of PSOGA-WNN are compared with the neural networks of PSO-WNN,GA-WNN,and PSOGA-BP.The results show that the PSOGA-WNN neural network has the highest prediction accuracy,which indicates that the PSOGA hybrid parameter optimization algorithm based on the genetic algorithm and particle swarm algorithm has obvious superiority in optimizing the prediction accuracy of the model.The WNN neural network has certain advantages over BP neural network in terms of fitting degree as well as error accuracy and is an effective means of simulation prediction.…”
Get full text

Energy Harvesting for Throughput Enhancement of Cooperative Wireless Sensor Networks by Van-Dinh Nguyen, Chuyen T. Nguyen, Oh-Soon Shin

“…We then propose an iterative power allocation algorithm which converges to a locally optimal solution at a Karush-Kuhn-Tucker point. …”
Get full text

Classification Prediction of Rockburst in Railway Tunnel Based on Hybrid PSO-BP Neural Network by Min Zhang

“…Then, the BP neural network is improved by using particle swarm optimization (PSO) combined with the simulated annealing algorithm. …”
Get full text

Flight Endurance Increasing Technology of New Energy UAV Based on a Strut-Braced Wing by Li Liu, Wencan Bai, Dun Yang

“…Surrogate model technology and multiobjective genetic algorithm are used to optimize the SBW configuration. …”
Get full text

Research on management mode of talent team in E-government based on big data analysis by Shixuan Hao

“…The performance analysis of the Apriori algorithm before and after improvement shows that the optimized Apriori algorithm can significantly reduce the number of scans of the data transaction database and the system running time, and the algorithm efficiency has increased by 48.26 %. …”
Get full text

Green Energy Strategic Management for Service of Quality Composition in the Internet of Things Environment by Jianhao Gao

“…The simulation results reveal that MFO has good optimization effect in the abovementioned models, and the optimization effect of MFO is improved by 8% and 6% compared with the genetic algorithm and particle swarm optimization, so as to realize the green energy strategic management of QoS composition in the environment of IoT.…”
Get full text

Research on deep reinforcement learning in Internet of vehicles edge computing based on Quasi-Newton method by ZHANG Jianwu, LU Zetao, ZHANG Qianhua, ZHAN Ming

“…Additionally, system transmission time allocation in the vehicular network model was considered, enhancing the practicality of the algorithm. …”
Get full text

Research on action matching of skeletal point coordinates and sports teaching application based on Open-pose by Shunmin Su

“…This study addresses the challenges of high matching errors and low recognition rates in traditional skeletal point-based human action matching methods, a skeleton point coordinate and human posture action matching technology is studied based on Open-pose open-source model. Based on the Open-pose open source model, we construct a skeletal point coordinate action matching network model, use the feed-forward network for 2D confidence mapping, test it through the loss function, calculate the shortest distance to identify the association affinity domain, and introduce the greedy relaxation algorithm to optimize the accuracy rate of the association matching of multi-body skeletal points; we obtain the skeletal point coordinate parameters through the two-dimensional spatial mapping and use the k-means algorithm to quantify the features of the skeletal point coordinates, and the residuals of the skeletal point coordinates are quantized. …”
Get full text

Based on PCA and SSA-LightGBM oil-immersed transformer fault diagnosis method. by Jizhong Wang, Jianfei Chi, Yeqiang Ding, Haiyan Yao, Qiang Guo

“…The experimental results show that the SSA-LightGBM model proposed in this paper has an average fault diagnosis accuracy of 93.6% after SSA algorithm optimization, which is 3.6% higher than before optimization. …”
Get full text

基于分层模糊优化的湿式多片离合器起步控制研究 by 闫光辉, 关志伟, 童敏勇

“…According to the control theory of wet multi-plate clutch and starting process,taking full account of starting impact and sliding friction works,the starting process is analyzed and the control parameters of each starting process are selected.And then the hierarchical fuzzy optimization control strategy of clutch engagement occupation-empty ratio is proposed,which means the first analysis of starting intention,followed by initial occupation-empty ratio control,and finally to optimize occupation-empty ratio.Based on the control strategy,the control model and algorithm of hierarchical fuzzy optimization is designed.After vehicle simulation and compare with other control strategies,the results show that the strategy can effectively identify the driver’s starting intention,improve the smoothness of the wet clutch and reduce the starting impact and sliding friction works.…”
Get full text