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 102 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. Creating a Methodology for User Profile:Architecture and Platform | |||
Chang Jielin,Niu Kun | |||
Computer Science and Technology 13 March 2020 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:User profile, an abstract information of user based on big data, which can help enterprises to achieve precision-targeted marketing to users according to their characteristics,and offer personality services for user. At present, the existing structures of user profile is based on the specific product, without forming a unified structure.Therefore, this paper proposes a user profile management architecture, which aims to provide an industry-wide generic model. From the point of person analysis, the character attributes are divided into six categories through the method of category division, and extend the subcategories in each category to form a label system. On the basis of building the model, this paper design an open platform. Introduceing the method of design interface which is open to the external platform, and describing the result. Moreover, designing the permission management for each interface to ensure the security of the system. Compared with other models, the user profile architecture provides in this paper has a wide adaptability and can be applied to various industries. | |||
TO cite this article:Chang Jielin,Niu Kun. Creating a Methodology for User Profile:Architecture and Platform[OL].[13 March 2020] http://en.paper.edu.cn/en_releasepaper/content/4751182 |
2. Implementation of Movie Recommendation System based on Android Platform | |||
WANG Xinyu | |||
Computer Science and Technology 24 February 2020 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:There are many apps proposed for movie news collecting or music recommendation. This paper developed an app on android platform for movie recommendation. This paper researched many recommendation algorithms. The algorithms include user collaborative filtering with threshold neighbourhoods, user collaborative filtering with fix-size neighbourhoods, item collaborative filtering and content-based filtering. This paper designed a strategy to mix these algorithms to improve recommendation effectivity. The system contains server and client. This paper designed and implemented the server which is based on Java and mainly includes recommendation, database, Servlet and controller. This paper designed and implemented database. The Servlet is used to respond the request from client. The controller is the core operator of server. This paper designed and implemented the client, the app, which mainly includes connection and UI. The connection is used to connect with server. The UI is important for presenting recommendation results. The user is able to use the app to rate movies and get recommendation. | |||
TO cite this article:WANG Xinyu. Implementation of Movie Recommendation System based on Android Platform[OL].[24 February 2020] http://en.paper.edu.cn/en_releasepaper/content/4750842 |
3. The Research on Web AR Avatar Generation System | |||
Feng Jingyi,Liao Jianxin | |||
Computer Science and Technology 13 February 2020 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:With the development of virtual reality and augmented reality (AR) technology, new types of social media continue to emerge and develop rapidly. One of the most important technologies of these social media applications is to generate a virtual image similar to that for users. Existing virtual image generation technologies are mainly divided into methods based on 3D scanning equipment and methods based on model library matching. Among them, the method based on the three-dimensional scanning device has high requirements on the device, which is not convenient to use and popularize; and the method based on the model library matching method has small individual differences in results. In order to solve the shortcomings of the existing methods, this paper proposes a method for directly generating a virtual image based on a two-dimensional image and generates an exclusive virtual image with personal characteristics for the user.This paper proposes a virtual image generation method based on web 3D face reconstruction and 3D model texture reconstruction. Use Tensorflow.js to transform the trained deep learning model into a format that can be recognized by the browser and predict the 3D face information and facial feature points on the web. Then, based on Delaunay triangulation and image affine transformation, a virtual image texture is generated for the model.The experimental results show that the method proposed in this paper can generate personalized and exclusive three-dimensional avatars based on the user's two-dimensional face information. It provides a feasibility reference for web-based virtual image related research. | |||
TO cite this article:Feng Jingyi,Liao Jianxin. The Research on Web AR Avatar Generation System[OL].[13 February 2020] http://en.paper.edu.cn/en_releasepaper/content/4750730 |
4. A Strategy for Reducing Redundancy in Test Suite Based on Spectrum Fault Localization | |||
YANG Xingyuan,WANG Chun | |||
Computer Science and Technology 26 January 2020 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:The spectrum-based fault localization technology can effectively use the operating spectrum information and achieve rapid fault localization. For spectrum-based software fault localization technology, spectrum information is critical to the final localization effect, but there is a lot of redundant information in the spectrum information, which not only wastes a lot of calculation time, but also affects the final localization effect. This paper proposes a strategy based on failed execution sets for the redundancy of spectrum information in dimensions, which greatly improves the localizing efficiency. In addition, a strategy based on Chameleon\'s algorithm is proposed for the redundancy in passed test cases, and the feasibility of the strategy is verified through comparative experiments on Defects4J. | |||
TO cite this article:YANG Xingyuan,WANG Chun. A Strategy for Reducing Redundancy in Test Suite Based on Spectrum Fault Localization[OL].[26 January 2020] http://en.paper.edu.cn/en_releasepaper/content/4750584 |
5. A Defect Feature Extraction and Confirmation Method Based on Global Data Flow Analysis | |||
Chen Lulu,Jin Dahai,Gong Yunzhan | |||
Computer Science and Technology 28 December 2019 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:Static code detection tools perform code inspection and analysis, which helps to detect and prevent errors early, greatly improve software reliability and reduce software development costs. However, the problem caused by this is that static analysis often generates a large number of false defect reports. Manual review of false positives is necessary, and it takes time and effort, so it is necessary to optimize the reports generated by static detection tools. This paper analyzes thetest problems of Defect Test System (DTS). Based on this, a feature extraction method based on global data flow analysis is proposed. This method obtains the context feature of the defect from the paths to the target point(TP), maps the feature to feature vector and finally uses machine learning methods for learning and training. Take null-pointer defect (NPD) that occupies the majority of alarms reported by DTS as an example, automatic confirmation of defects is achieved. The experimental results show that this method correctly confirms about 75% of the defects and can serve the static code detection tool better. | |||
TO cite this article:Chen Lulu,Jin Dahai,Gong Yunzhan. A Defect Feature Extraction and Confirmation Method Based on Global Data Flow Analysis[OL].[28 December 2019] http://en.paper.edu.cn/en_releasepaper/content/4750208 |
6. A New Hybrid User Similarity Model for Collaborative Filtering Algorithms | |||
FU Bin,HU Xiang | |||
Computer Science and Technology 02 April 2019 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:Collaborative filtering (CF) is one of the most widely used personalized recommendation methods. Its basic assumption is that users with similar behaviors tend to share similar preferences and make the same choices. Similarity calculation between users or items is considered to be the key of traditional collaborative filtering recommendation algorithm.Traditional collaborative filtering algorithm relies entirely on the common rating items of users when calculating the similarity,while the rating matrix is extremely sparse, the common rating items of users are rare, which results in that the similarity can not be measured or the measurement error is very large, thus affecting the recommendation effect. In addition, the traditional similarity model does not fully consider the influence factor of similarity, which causes the search for similar neighbor errors and the quality of recommendation is not high。To solve this problem, a new hybrid user similarity model for collaborative filtering is proposed,it effectively considers the impact of user\'s non-common rating information on user similarity, which solves the problem that similarity depends entirely on common rating items.At the same time, it fully considers the influence factors of user similarity, such as user common rating reward factor, item attribute preference factor, user confidence factor. The common rating reward factor increases the proportion of common reward items in the similarity measure. The item attribute preference factor can effectively distinguish the user\'s different attribute preferences for different items. The user confidence factor can reduce the influence of noise data and improve the reliability of the model output . The test is carried out on the MovieLens dataset with extremely sparse data and experimental results show that the proposed algorithm has higher accuracy of user similarity, which helps to find suitable nearest neighbor users and improve recommendation accuracy. | |||
TO cite this article:FU Bin,HU Xiang. A New Hybrid User Similarity Model for Collaborative Filtering Algorithms[OL].[ 2 April 2019] http://en.paper.edu.cn/en_releasepaper/content/4748227 |
7. Research and application of keyword driven automated testing framework in regression testing | |||
GE Jinpeng,ZHOU Xiaoguang | |||
Computer Science and Technology 29 June 2018 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:With the development of information technology, software version iteration is frequent. The testing process is a large part of the overall development process. Improving test efficiency is an urgent problem to be solved. This paper introduces regression testing, the idea of automated testing, and the existing related automated testing tools. In order to improve the efficiency of regression testing, an automatic testing framework based on the idea of keyword driven is proposed. The framework is based on the JAVA Selenium framework and is described in detail in terms of automated test framework modules, hierarchies, and workflow. | |||
TO cite this article:GE Jinpeng,ZHOU Xiaoguang. Research and application of keyword driven automated testing framework in regression testing[OL].[29 June 2018] http://en.paper.edu.cn/en_releasepaper/content/4745514 |
8. A Method for Reducing the Size of Android Application Updates with Less Memory | |||
LI Jinfeng,QI Qi | |||
Computer Science and Technology 21 December 2017 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:With the popularity of smartphones, mobile applications have become an integral part of the Internet age. However, the faster version changes and installation files become larger and larger, leading to a decrease in user\'s enthusiasm for the upgrade. Incremental upgrade has become an important way to solve this problem. The current mainstream incremental upgrade program is bsdiff /bsdiff, but it also has its own flaws. Among them, bsdiff/bspatch excessive memory consumption problem is fatal for large files. Therefore, the paper proposes an incremental update algorithm based on file blocking, using smaller memory. This algorithm is a bit less efficient than bsdiff/bspatch, but can effectively solve the problem of incremental updates of large files. | |||
TO cite this article:LI Jinfeng,QI Qi. A Method for Reducing the Size of Android Application Updates with Less Memory[OL].[21 December 2017] http://en.paper.edu.cn/en_releasepaper/content/4742797 |
9. A recommendation approach based on tensor for multi-criteria rating system | |||
Yang Jingting,Yuan Hanning,Wang Shuliang,Wang ShaoPeng | |||
Computer Science and Technology 26 May 2017 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:Now users are encouraged to provide multiple criteria ratings for items which can be used to improve recommendation accuracy. However most model-based recommendation approaches for multi-criteria rating system don't provide straight- forward and effective way for integrating multi-criteria rating information into the model. In this research, a new recommendation method based on tensor is proposed to represent and fuse multi-criteria rating information effectively. In this approach, user-item-criteria representation model based on three-order tensor enables a generic integration of multi-criteria rating information and canonical poly based decomposition model is used to predict ratings in scenarios of highly sparse data. Experimental results on real world dataset show that the proposed method consistently improve recommendation accuracy for multi-criteria rating system in relation to effectively fusing multi-criteria rating information. | |||
TO cite this article:Yang Jingting,Yuan Hanning,Wang Shuliang, et al. A recommendation approach based on tensor for multi-criteria rating system[OL].[26 May 2017] http://en.paper.edu.cn/en_releasepaper/content/4735085 |
10. ROSIE: Runtime Optimization of SPARQL Queries Using Incremental Evaluation | |||
GAI Lei, CHEN Wei, WANG Teng-Jiao | |||
Computer Science and Technology 17 April 2017 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:Currently, relational databases are wildly adopted in RDF (Resource Description Framework) data management, but they show problematic performance in SPARQL query evaluation. One important factor is how to tackle the suboptimal query plan caused by error-prone cardinaltiy estimation. Consider the schema-free nature of RDF data and the extsc{Join}-intensive characteristic of SPARQL query, determine an optimal query plan is costly or even infeasible, especially for complex queries on large-scale data. In this paper, we propose ROSIE, a underline{R}untime underline{O}ptimization framework that iteratively re-optimize the underline{S}PARQL query plan accroding to the actual cardinality derived from underline{I}ncremental partial query underline{E}valuation. By introducing a heuristic-based plan generation approach, as well as a mechanism to detect cardinaltiy estimation error at runtime, ROSIE relieves the problem of biased cardinality propagation, and thus is more resilient to complex query evaluation. Extensive experiments on real and benchmark data show that compared to the state-of-the-arts, ROSIE can improve query performance by orders of magnitude. | |||
TO cite this article:GAI Lei, CHEN Wei, WANG Teng-Jiao. ROSIE: Runtime Optimization of SPARQL Queries Using Incremental Evaluation[OL].[17 April 2017] http://en.paper.edu.cn/en_releasepaper/content/4725396 |
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