Authentication email has already been sent, please check your email box: and activate it as soon as possible.
You can login to My Profile and manage your email alerts.
If you haven’t received the email, please:
|
|
There are 212 papers published in subject: since this site started. |
Select Subject |
Select/Unselect all | For Selected Papers |
Saved Papers
Please enter a name for this paper to be shown in your personalized Saved Papers list
|
1. Research on Deep Learning Stock Selection Method Based on Trend Decomposition Algorithm | |||
Wu Cheng-Hui,Zhang Hong-Jian | |||
Computer Science and Technology 20 June 2023 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:Some studies using machine learning and deep learning models did not fully explore other indicator features that affect stock price trends, resulting in significant prediction errors and difficulty in directly applying the prediction results to obtain excess returns. Therefore, it is necessary to establish an efficient deep learning model based on stock characteristics and fully explore the factors that affect stock price trends to improve prediction accuracy.In view of the shortcomings of traditional stock trend prediction, this paper constructs LSTM-BP neural network based on Tianniuxu optimization for stock price prediction, and constructs PCA-BP neural network model based on particle swarm optimization based on multi angle correlation analysis for trend prediction. Taking into account both price prediction and trend prediction dimensions, construct a deep quantitative stock selection method. In this process, a stock trend decomposition judgment algorithm is proposed to identify and classify the stock data, improve the data utilization, build a new data set, and use the particle swarm optimization to adjust and optimize the parameters.The results of strategy backtesting show that compared to other deep learning strategies and benchmark strategies, the stock selection method and strategy proposed in this article have significantly improved in terms of victory and return. This indicates that the model has good predictive ability and application potential, and can provide effective decision support for stock investment. | |||
TO cite this article:Wu Cheng-Hui,Zhang Hong-Jian. Research on Deep Learning Stock Selection Method Based on Trend Decomposition Algorithm[OL].[20 June 2023] http://en.paper.edu.cn/en_releasepaper/content/4760906 |
2. Moving Object Detection Algorithm Based on Dynamic Vision Sensor | |||
SUN Xue,SUN Xue,LIU Dengfeng,LIU Dengfeng | |||
Computer Science and Technology 11 April 2023 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:Target detection and tracking mainly use RGB camera and deep learning algorithm. The information in the image is complex and redundant so the computing consumes a lot of resources. To solve the above problems, this paper proposes an improved spectral clustering algorithm to detect moving object. The algorithm is based on event data generated by dynamic vision sensors. In this paper, the cosine - Manhattan fusion distance is used to obtain a more accurate similarity matrix. The clustering results of some data are used to guide other data to speed up operation. The number of clusters is set adaptively to avoid the subjective influence of human beings. The results show that the accuracy of the improved algorithm on multiple data sets is more than 80%, and the time is significantly shortened. Spectral clustering algorithm based on dynamic vision sensor has great application potential in dealing with multi-target motion problems. | |||
TO cite this article:SUN Xue,SUN Xue,LIU Dengfeng, et al. Moving Object Detection Algorithm Based on Dynamic Vision Sensor[OL].[11 April 2023] http://en.paper.edu.cn/en_releasepaper/content/4760291 |
3. WFLNNet: Weighted Fusion of Linear and Nonlinear Predictions for Multivariate Time Series | |||
Dan Liu,Yuke Wang,Kun Xie,Ruotian Xie,Wei Liang,Dafang Zhang,Jigang Wen | |||
Computer Science and Technology 19 May 2022 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:Multivariate time series forecasting has been widely used in finance, environment, transportation and other fields. However, traditional statistical prediction models usually assume that the time series conforms to a certain distribution or functional form, and cannot capture the complex nonlinear relationships. Although neural network based algorithms have powerful learning abilities, they usually ignore the linear features in time series. By weighted and fused both Linear and Nonlinear Predictions, this paper proposes a novel WFLNNet, where the linear prediction module is designed based on an autoregressive model while the nonlinear prediction module is designed based on the neural network and consists of a feature extraction encoder, an interactive attention network, and a fully connected layer to capture the most effective features in temporal and spatial correlations, as well as a mutual influence among multivariate time series. We have done experiments using 4 real datasets by comparing them with 6 baseline algorithms. The experimental results demonstrate that WFLNNet outperforms the 6 baseline algorithms with more accurate prediction. | |||
TO cite this article:Dan Liu,Yuke Wang,Kun Xie, et al. WFLNNet: Weighted Fusion of Linear and Nonlinear Predictions for Multivariate Time Series[OL].[19 May 2022] http://en.paper.edu.cn/en_releasepaper/content/4757819 |
4. Opponent Modeling with Limited Cognition | |||
WANG Die,LIU Xuan,CHEN Xin-Ning,WANG Hao,ZHANG Shi-Geng | |||
Computer Science and Technology 19 May 2022 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:It is difficult for agents to learn effective policies in multi-agent systems, as the co-evolution of multiple agents leads to the non-stationarity of environments. To cope with this inherent problem of multi-agent systems, recent works have tried to stabilize policy learning by reasoning the policies of other agents, known as opponent modeling. However, existing opponent modeling methods always require agents have a fully observable of the environment, which is an unrealistic assumption. For many real-world multi-agent tasks, each agent usually has limited knowledge of the environment, especially in partially observable environments, which brings great difficulty for existing methods to learn opponent modeling. In this paper, we propose a novel opponent modeling framework POLO (Opponent Modeling with Limited Cognition) to model other agents in limited cognitive environments. POLO allows agents to reason intention and behavior with merely their own local observations using attention mechanism and behavior modeling network, thus freeing agents from the demand on fully cognitive environments and access to the opponent's observations or actions. We evaluate our framework on several partially-observable tasks and find it surpasses existing works in convergent speed and policy performance. | |||
TO cite this article:WANG Die,LIU Xuan,CHEN Xin-Ning, et al. Opponent Modeling with Limited Cognition[OL].[19 May 2022] http://en.paper.edu.cn/en_releasepaper/content/4757776 |
5. Research and implementation of Node.js based large file upload | |||
ZHOU Yuying,WANG Danzhi | |||
Computer Science and Technology 21 February 2022 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:Currently, the number of applications that upload files via web networks is increasing, and in the application scenario of large-capacity file uploading, it often leads to long waiting time, browser lag and even crash due to excessive resources, which reduces the user experience; in response to the many limitations of the large file upload process, the paper implements a complete large file upload system based on the stream merging technology of node.js and the concurrency function of browsers. By using the File API on the front-end to slice large files and convert them into smaller sliced files, the server performs stream merging on the received sliced files sequentially through validation, breaking the limitations of the traditional upload process, and the test results prove the effectiveness. | |||
TO cite this article:ZHOU Yuying,WANG Danzhi. Research and implementation of Node.js based large file upload[OL].[21 February 2022] http://en.paper.edu.cn/en_releasepaper/content/4756383 |
6. P-SANET: A HIGH-PRECISION REALTIME POINT CLOUD SEMANTIC SEGMENTATION FRAMEWORK | |||
GOU Xiaofeng,JIAO Jichao,ZHANG Chengkai | |||
Computer Science and Technology 10 January 2022 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:Perception in autonomous system is an important task to guide decision execu-tion. Lidar point cloud is a type of dataset to complete perception task, it is rich in original information, easy to collect, and convenient to store. Compared to camera image, point cloud contains precise spatial information and adapts to various en-vironments, nevertheless, more information means more computing power con-sumption. The processing speed and accuracy are two key metrics of neural net-work framework. The traditional methods have to pay the price of reducing accu-racy for increasing processing speed. Though some frameworks preprocess point cloud into projected image, the 2D image tensor also contains a large number of redundant channel features in the traditional 2Dconvolution operation. In this pa-per, we propose a point clouds semantic segmentation framework, we replace the standard convolutional layer with a new sub-module, and it greatly reduces the amount of computation, besides, we introduce a sub-module to fuse the coordi-nate values and middle tensors. The framework in this paper is divided into three parts: spherical projection preprocessing module, En-Decoder module and data post-processing module. We use the SemanticKITTI dataset to conduct experi-ments, and the results show that our framework outperforms other frameworks both in prediction accuracy and prediction speed. We also use sparse point cloud dataset to test the generalization of our framework, and the experiments show that it performs better than other frameworks. Code is available at: https://github.com/windtries/P-SANet | |||
TO cite this article:GOU Xiaofeng,JIAO Jichao,ZHANG Chengkai. P-SANET: A HIGH-PRECISION REALTIME POINT CLOUD SEMANTIC SEGMENTATION FRAMEWORK[OL].[10 January 2022] http://en.paper.edu.cn/en_releasepaper/content/4755947 |
7. Implementation of DSL compiler based on ANTLR | |||
Jiang Ya-Yun, Man Yi | |||
Computer Science and Technology 06 December 2021 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:This paper presents a method to implement domain specific language compiler based on ANTLR tool. The domain specific language studied in this paper is a chip development language but higher than instruction language. The language is concise and all variables in it refer to registers, The purpose of this paper is to realize the compiler of it and obtain its corresponding assembly code. The implementation of the compiler is based on ANTLR tool, which eliminates the cumbersome process of handwritten lexical analysis and syntax analysis. The listener generated by it is combined with a handwritten Conversion tool to compile the domain specific language. Finally, the results are given to verify the correctness of the compiler. | |||
TO cite this article:Jiang Ya-Yun, Man Yi. Implementation of DSL compiler based on ANTLR[OL].[ 6 December 2021] http://en.paper.edu.cn/en_releasepaper/content/4755893 |
8. Flexible revocation in ciphertext-policy attribute-based encryption with verifiable ciphertext delegation | |||
Shijie Deng,Gaobo Yang,Wen Dong,Ming Xia | |||
Computer Science and Technology 12 May 2021 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:Attribute-based encryption (ABE) is a promising approach to enables fine-grained access control over encrypted data in cloud storage. However, to design a flexible and effective revocation mechanism has always been a tricky problem in ABE schemes, especially for situations where revocation occurs frequently. In this paper, we propose a practical attribute-based access control system by introducing a ciphertext-policy attribute-based encryption (CP-ABE) scheme that allows the trusted authority (TA) to efficiently manage the credentials of data users. The problem of revocation is solved efficiently by exploiting user binary tree. To achieve flexible revocation, our scheme supports both attribute revocation and user revocation to accommodate different revocation needs. Non-revoked users can still decrypt the ciphertext as long as his/her remaining attributes satisfy the access policy associated with the ciphertext. Moreover, verifiable ciphertext delegation is presented to reduce the heavy computation cost brought by frequent revocation. The merits of the proposed scheme are shown by comparing it with the related works. Security analysis and performance discussions further demonstrate the effectiveness of our scheme in cloud systems. | |||
TO cite this article:Shijie Deng,Gaobo Yang,Wen Dong, et al. Flexible revocation in ciphertext-policy attribute-based encryption with verifiable ciphertext delegation[OL].[12 May 2021] http://en.paper.edu.cn/en_releasepaper/content/4754941 |
9. An extended model of group chase and escape based on refuges | |||
ZHANG Xinglei,LIU Shaohua | |||
Computer Science and Technology 24 March 2021 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:In this paper,an extended model is proposed to describe the motion trajectory of group chase and escape based on refuges.The rich dynamic behaviors of chaser and escaper are demonstrated by using a cellular automata model and the protective effect of refuge on escaper is explored in both long-term and short-term modes. The protective effect of different refuge density and distribution is compared in this paper. A critical refuge density which provides 100% protection for escaper is founded as refuge density increases and the optimal refuge distribution for prey\'s survival is concluded. These findings can provide references for the establishment of endangered animal refuges and the modeling of crowd evacuation under attack, and have profound significance on the topic of group chase and escape. | |||
TO cite this article:ZHANG Xinglei,LIU Shaohua. An extended model of group chase and escape based on refuges[OL].[24 March 2021] http://en.paper.edu.cn/en_releasepaper/content/4754164 |
10. User Authentication from Smartwatch Photoplethysmography sensor | |||
TAN ZhiHao,HUANG Qinlong,YANG Yixian | |||
Computer Science and Technology 22 March 2021 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:With the rapid proliferation of smartwatch, a secure and convenient smartwatch-based user authentication scheme are desired. As the widely deployed bioelectrical signal sensor in smartwatch, Photoplethysmography (PPG) sensors have shown potentials for authentication. Existing authentication solutions usually have some limitations. They require the user to provide an amount of registration data from user to reflect the profile of user, which may impact the experience of user. In this paper, we propose a PPG-based smartwatch authentication scheme. We leverage the Siamese Network to extract the feature of user from the PPG signal affected by the finger-level gesture for authentication. We conduct some experiments to evaluate the performance of the scheme. The experiment results show that our model has an average accuracy rate of 92.43\%. In addition, the authentication model can achieve high authentication accuracy with a small amount of user registration data. | |||
TO cite this article:TAN ZhiHao,HUANG Qinlong,YANG Yixian. User Authentication from Smartwatch Photoplethysmography sensor[OL].[22 March 2021] http://en.paper.edu.cn/en_releasepaper/content/4754180 |
Select/Unselect all | For Selected Papers |
Saved Papers
Please enter a name for this paper to be shown in your personalized Saved Papers list
|
|
About Sciencepaper Online | Privacy Policy | Terms & Conditions | Contact Us
© 2003-2012 Sciencepaper Online. unless otherwise stated