检索结果-内蒙古大学图书馆

33rd British Machine Vision Conference Proceedings, BMVC 2022

作者： Liu, Mengyuan Wang, Yuelong Sun, Qiangyu Li, Shuiwang Guilin University of Technology China Hubei Enshi College China Guangxi Key Laboratory of Embedded Technology and Intelligent System China

Unmanned aerial vehicle (UAV)-based tracking has wide perspective applications, however, due to the limitations of computing resources, battery capacity, and maximum load of UAVs, efficiency seems more thorny and imperative as an issue than precision in UAV tracking, which explains why discriminative correlation filters (DCF)- instead of deep learning (DL)- based trackers are usually preferred in this field, as the former are known for high efficiency, whereas, the latter hardly achieve real-time tracking on a single CPU. However, without deep representation learning the precision of DCF-based trackers is extremely limited. This paper dedicates to boost the efficiency of DL-based trackers for UAV tracking by presenting a global filter pruning and proposes a self-attention module, which seeks to learn backbone features that highlight meaningful visual inter-dependencies, in order to combat the precision drop, and, importantly, to avoid the arduous process of determining layer-wise pruning ratios in the original ranked-based filter pruning method. Remarkably, self-attention is utilized here to guide the training without introducing any extra computational burden into the inference phase. Extensive experiments on four UAV benchmarks show that the proposed tracker strikes a remarkable balance between efficiency and precision and achieves state-of-the-art performance in UAV tracking. © 2022. The copyright of this document resides with its authors. It may be distributed unchanged freely in print or electronic forms.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Integrating spectral-CF and FP-growth for recommendation 2

Integrating spectral-CF and FP-growth for recommendation

引用

2nd International Conference on E-Business, Information Management and Computer Science, EBIMCS 2019

作者： Zhang, Huaxin Liu, Yu Cao, keyin College of Information Science and Engineering Guangxi Key Laboratory of Embedded Technology and Intelligent System Guilin University of Technology Guilin China

ISBN: (纸本)9781450366496

In the era of information overload, both information consumers and information producers have encountered great challenges: for information consumers, it is very difficult to find information of interest from a large amount of information. The recommendation system is an important tool to resolve this contradiction. Despite the popularity of Collaborative Filtering (CF), CF-based methods are haunted by the cold-start and data sparseness problems. This paper took commodity recommendation as to the research object and proposed a recommendation algorithm that combines Spectral-CF and FP-Growth. Firstly, Firstly, the association rule algorithm FP-Growth is mine the association rules of the target user and the target item directly, and recommend the collection of items with higher similarity for the user. Secondly, using a spectral collaborative filtering algorithm Perform convolution operations in the spectral domain. Finally, providing the final result by combining the Spectral-CF and FP-Growth recommendation. The experimental results on the MovieLens dataset show that the proposed method can better solve the problem of data sparseness and cold-start problems, improvement the accuracy of recommendation. © 2019 ACM.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

Grid Load Prediction Based on Improved Particle Swarm Optimization BP Neural Network 7

Grid Load Prediction Based on Improved Particle Swarm Optimi...

引用

7th International Conference on intelligent Information Processing, ICIIP 2022

作者： Lu, Jie Xie, Xiaolan School of Information Science and Engineering Guilin University of Technology China Guangxi Key Laboratory of Embedded Technology and Intelligent System China

ISBN: (纸本)9781450396714

Power grid load forecasting is an optimization of power grid structure deployment, which can achieve a dynamic balance between power production and use. Large errors in forecasting will lead to increased operation and maintenance costs. In view of the above problems, this paper proposes an algorithm based on improved particle swarm optimization BP neural network to solve the current power grid load forecasting, balance power production and use, and provide a theoretical basis for the economic benefits of energy production departments in ensuring users' reasonable power *** simulation results show that the improved particle swarm optimization BP neural network algorithm has better and more accurate effect in solving the power grid load prediction. © 2022 ACM.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

An improved channel estimation algorithm based on DFT in OFDM system

An improved channel estimation algorithm based on DFT in OFD...

引用

2020 International Conference on Computer Information and Big Data Applications, CIBDA 2020

作者： Feng, Mingming Hong, Jin College of Information Science and Engineering Guilin University of Technology Guangxi Key Laboratory of Embedded Technology and Intelligent System Guilin China

ISBN: (数字)9781728198378

ISBN: (纸本)9781728198378

In orthogonal frequency division multiplexing (OFDM) systems, the channel estimation algorithm based on discrete Fourier transform (DFT) overcomes the shortcoming of the least square (LS) channel estimation algorithm which does not consider noise in the process of channel estimation, and its performance is better than the LS channel estimation algorithm, and its computational complexity is low. However, the DFT algorithm does not take into account the processing of noise within the cyclic prefix, which affects the performance of the algorithm. In view of the shortcomings of this algorithm, this paper proposes an improved DFT channel estimation algorithm. First, the median of channel response amplitude modes of all samples in the range of cyclic prefix is taken, then the median of channel response amplitude modes of all samples outside the range of cyclic prefix is taken, and the sum of the median values of the two is used as the threshold, which preserves the data larger than the threshold and sets the data smaller than the threshold to zero. In this way, the noise within the cyclic prefix is filtered out and the performance of the algorithm is further improved. The simulation results show that the improved algorithm can effectively eliminate the influence of noise, make up for the shortcomings of the LS algorithm, have better performance than the DFT estimation algorithm, and further improve the accuracy of channel estimation. © 2020 IEEE.

关键词： Orthogonal frequency division multiplexing

来源：评论

学校读者我要写书评

暂无评论

Optimal voltage compensation method for focal plane avalanche detector based on improved random forest 2

Optimal voltage compensation method for focal plane avalanch...

引用

2nd International Conference on Electronic Information and Mechanical Manufacturing, EIMM 2022

作者： Chen, Mengqiang Yang, Jiazhi Yu, Guangwang Shen, Jie College of Information Science and Engineering Guilin University of Technology Guangxi Guilin541006 China Guangxi Key Laboratory of Embedded Technology and Intelligent System Guangxi Guilin541006 China

Working distance and background radiation greatly affect the signal-to-noise ratio of avalanche photodiode (APD) in the lidar detection system. The traditional method cannot adapt to a complex environment by offline compensation or pre-compensation according to the influence factors of the external environment. In this paper, an avalanche photodiode voltage compensation method based on the improved random forest is designed. Firstly, the distance image data is de-noised. Then the weight of each decision tree in the random forest was changed to improve the classification performance. The particle swarm optimization (PSO) algorithm was used to search for the optimal combination of parameters affecting classification accuracy and performance. Finally, the improved random forest algorithm is used to judge the current working state of APD at different distances, compensate for the bias voltage, and make APD work in the optimal state. The proposed method is compared with the k-nearest neighbor, support vector machine, and other commonly used classification algorithms, and the results verify the effectiveness of the proposed method. © Published under licence by IOP Publishing Ltd.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

Cloud Resource Integrated Prediction Model Based on Variational Modal Decomposition-Permutation Entropy and LSTM

引用

Computer systems Science & Engineering 2023年第11期47卷 2707-2724页

作者： Xinfei Li Xiaolan Xie Yigang Tang Qiang Guo Guangxi Key Laboratory of Embedded Technology and Intelligent System Guilin541006China School of Information Science and Engineering Guilin University of TechnologyGuilin541006China

Predicting the usage of container cloud resources has always been an important and challenging problem in improving the performance of cloud resource *** proposed an integrated prediction method of stacking container cloud resources based on variational modal decomposition(VMD)-Permutation entropy(PE)and long short-term memory(LSTM)neural network to solve the prediction difficulties caused by the non-stationarity and volatility of resource *** variational modal decomposition algorithm decomposes the time series data of cloud resources to obtain intrinsic mode function and residual components,which solves the signal decomposition algorithm’s end-effect and modal confusion *** permutation entropy is used to evaluate the complexity of the intrinsic mode function,and the reconstruction based on similar entropy and low complexity is used to reduce the difficulty of ***,we use the LSTM and stacking fusion models to predict and superimpose;the stacking integration model integrates Gradient boosting regression(GBR),Kernel ridge regression(KRR),and Elastic net regression(ENet)as primary learners,and the secondary learner adopts the kernel ridge regression method with solid generalization *** Amazon public data set experiment shows that compared with Holt-winters,LSTM,and Neuralprophet models,we can see that the optimization range of multiple evaluation indicators is 0.338∼1.913,0.057∼0.940,0.000∼0.017 and 1.038∼8.481 in root means square error(RMSE),mean absolute error(MAE),mean absolute percentage error(MAPE)and variance(VAR),showing its stability and better prediction accuracy.

关键词： Cloud resource prediction variational modal decomposition permutation entropy long and short-term neural network stacking integration

来源：评论

学校读者我要写书评

暂无评论

Task Scheduling Based on Improved Particle Swarm Optimization for Cloud Computing 8th

Task Scheduling Based on Improved Particle Swarm Optimizatio...

引用

8th International Conference on Artificial Intelligence and Security , ICAIS 2022

作者： Zhang, Qiming Xie, Xiaolan Wang, Jiaming Guangxi Key Laboratory of Embedded Technology and Intelligent System Guangxi Guilin541006 China School of Information Science and Engineering Guilin University of Technology Guangxi Guilin541006 China

ISBN: (纸本)9783031067600

Particle Swarm Optimization (PSO) algorithm is widely used in cloud computing task scheduling. As PSO algorithm tends to fall into local optimum and has poor convergence accuracy in the later stage, as a result, in this paper i integrates Simulated Annealing algorithm (SA) into PSO algorithm and adopts a strategy of mixing random and nonlinear decreasing inertia weight. At the same time, the idea of "accept the bad solution with a certain probability" in simulated annealing is used to improve the global search ability of the algorithm. Finally, the chaotic disturbance strategy is added to make the algorithm search for a better solution as far as possible, so as to improve the convergence accuracy of the algorithm in the later stage. The improved PSOSA algorithm and the standard particle swarm optimization algorithm are applied to the task scheduling test in the cloud environment through the Cloudsim simulation platform. The results show that the improved algorithm can achieve better scheduling results and faster convergence speed. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Simulated annealing

来源：评论

学校读者我要写书评

暂无评论

Application and Research of Spam Classification Based on Cluster Intelligence Algorithm to Optimize SVM 2

Application and Research of Spam Classification Based on Clu...

引用

2020 2nd International Conference on Electronic Engineering and Informatics, EEI 2020

作者： Xia, Zhennan Deng, Jianzhi College of Information Science and Engineering Guilin Univ. of Technol. Guangxi Key Laboratory of Embedded Technology and Intelligent System Guilin Guilin China College of Information Science and Engineering Guilin Univ. of Technol. Guangxi Key Laboratory of Embedded Technology and Intelligent System Guilin China

With the development of science and technology, the increasing popularity of the Internet, email has been widely used. Because of its convenience and low cost, e-mail has been used by more and more criminals to maliciously spread commercial advertisements, computer viruses and bad information. In order to resist spam, this paper proposes a spam classification method based on swarm intelligence algorithm optimized SVM. It classifies English spam and extracts features with special sensitive word coding. The model and method in this paper have certain reference value for spam classification research. © Published under licence by IOP Publishing Ltd.

关键词： Computer viruses

来源：评论

学校读者我要写书评

暂无评论

Slant split criterion random forests classification algorithm based on soft margin hyperplane 9

Slant split criterion random forests classification algorith...

引用

9th IEEE Joint International Information technology and Artificial Intelligence Conference, ITAIC 2020

作者： Kan, Xueda Li, Tiansong Guilin University of Technology College of Information Science and Engineering Guilin China Guangxi Key Laboratory of Embedded Technology and Intelligent System Guilin China

In order to further to improve the classification accuracy of the random forest algorithm, an Slant Split Criterion Random Forests based on Soft Margin Hyperplane (SSCRF) algorithm is proposed. In the decision tree node splitting process, consider using multiple attribute soft margin hyperplane of the decision tree to replace a single attribute splitting criterion, so that the splitting criterion becomes an inclined hyperplane in the data space, which effectively improves the accuracy of decision tree classification;In order to make the algorithm suitable for multi-classification problems, the 'one-to-many' strategy is adopted in the process of node splitting;in the process of transforming into leaf nodes, various adaptive weights are assigned to improve the algorithm's classification ability. The experimental results show that the SSCRF algorithm has higher classification accuracy than the random forest algorithm. © 2020 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

MRNA Big Data Analysis of Hepatoma Carcinoma between Different Genders 20

MRNA Big Data Analysis of Hepatoma Carcinoma between Differe...

引用

6th International Conference on Computing and Artificial Intelligence, ICCAI 2020

作者： Deng, Jianzhi Zhou, Yuehan Cheng, Xiaohui Li, Tianyu Qin, Chuling Guilin University of Technology Guilin541004 China Guilin University of Technology Guangxi Key Laboratory Embedded Technology and Intelligent System Guilin541004 China

ISBN: (纸本)9781450377089

In this paper, we did the researches of the directly related differentially expression mRNAs (DEmRNAs) and their gene ontology (GO), Kyoto Encyclopedia of Genes and Genomes (KEGG) signal pathway, COX model and survival analysis. For the purpose, the 87 directly related DEmRNAs (DRmRNAs) to the hepatoma carcinoma illness were selected from the intersectional DEmRNAs of normal-tumor sample matrix and male-female tumor's sample matrix. By the analysis of online databases, DAVID, KOBAS and KEGG, DRmRNAs were enriched in 18 biological process (BP), 5 cellular component (CC), 9 molecular function (MF) and 3 signal pathways (hsa04974, hsa04972 and hsa04080). The co-expression DRmRNAs were analyzed by using the COX model. CHGA was regard as a potential biomarker of hepatoma carcinoma by the proof of survival kmplot analysis and ROC curve analysis. © 2020 ACM.

关键词： Gene Ontology

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：