The need for safety critical systems （SCS） is both important and urgent, and their evaluation and verification are test-dependent. SCS are usually complex and very large, so manual testing of SCS are infeasible in p...The need for safety critical systems （SCS） is both important and urgent, and their evaluation and verification are test-dependent. SCS are usually complex and very large, so manual testing of SCS are infeasible in practice, and develop- ing automatic test approaches for SCS has become an impor- tant trend. This paper defines a formal semantics model for automatic test of SCS, called AutTMSCS, which describes behaviors in SCS testing. The model accommodates the high order collaboration in real time and temporariness of SCS testing. Testing tasks, test equipment and products under test are abstracted and architected in three layers, and a method for automatic testing is given. Based on extended label tran- sition system （LTS）, the convergency and correctness of the model are proved to demonstrate the computability of the model, indicating that the testing process of SCS can be au- tomatic.展开更多
Knowledge discovery from data directly can hardly avoid the fact that it is biased towards the collected experimental data, whereas, expert systems are always baffled with the manual knowledge acquisition bottleneck. ...Knowledge discovery from data directly can hardly avoid the fact that it is biased towards the collected experimental data, whereas, expert systems are always baffled with the manual knowledge acquisition bottleneck. So it is believable that integrating the knowledge embedded in data and those possessed by experts can lead to a superior modeling approach. Aiming at the classification problems, a novel integrated knowledge-based modeling methodology, oriented by experts and driven by data, is proposed. It starts from experts identifying modeling parameters, and then the input space is partitioned followed by fuzzification. Afterwards, single rules are generated and then aggregated to form a rule base, on which a fuzzy inference mechanism is proposed. The experts are allowed to make necessary changes on the rule base to improve the model accuracy. A real-world application, welding fault diagnosis, is presented to demonstrate the effectiveness of the methodology.展开更多
Journals and their citation relations are abstracted into journal citation networks, basing on CSTPC journal database from year 2003 to 2006. The network shows some typical characteristics from complex networks. This ...Journals and their citation relations are abstracted into journal citation networks, basing on CSTPC journal database from year 2003 to 2006. The network shows some typical characteristics from complex networks. This paper presents the idea of using motifs, subgraphs with higher occurrence in real network than in random ones, to discover two different citation patterns in journal communities. And a further investigation is addressed on both motif granularity and node centrality to figure out some reasons on the differences between two kinds of communities in journal citation network.展开更多
A new approach for dynamic Web services discovery based on similarity computation in the treatment of massive Web information resource is put forward. Firstly, three kinds of service description information, textual, ...A new approach for dynamic Web services discovery based on similarity computation in the treatment of massive Web information resource is put forward. Firstly, three kinds of service description information, textual, semantic and structural information, were modeled to compute the similarity of services. Then a novel dynamic Web services discovery mechanism was provided and the experiment on it was carried out. Results show that the new approach achieves considerable performance on precision and efficiency metrics for dynamic Web services discovery.展开更多
A syntactic and structural matching mechanism for service discovery was put forward, which tries to exploit the underlying semantics of web services to enhance tbe traditional syntactic service discovery. We commit WS...A syntactic and structural matching mechanism for service discovery was put forward, which tries to exploit the underlying semantics of web services to enhance tbe traditional syntactic service discovery. We commit WSDL （Web Service Description Language） as service description language. The syntactic matching mechanism is based on the textual similarity among WSDL documents using VSM （ Vector Space Model）. The structural information is extracted from WSDL document tree or the invocation sequence of a series of services which can be viewed as the problem of graph isomorphism. Then we combine the syntactic and structural similarity linearly to calculate the service similarity. Finally we provide a novel web services discovery framework named SG^＊ to find the exact services meeting the users＇ goals based on service similarity.展开更多
This paper proposes a practical algorithms of plane cutting, stereo clipping and arbitrary cutting for 3D surface model reconstructed from medical images. In plane cutting and stereo clipping algorithms, the 3D model ...This paper proposes a practical algorithms of plane cutting, stereo clipping and arbitrary cutting for 3D surface model reconstructed from medical images. In plane cutting and stereo clipping algorithms, the 3D model is cut by plane or polyhedron. Lists of edge and vertex in every cut plane are established. From these lists the boundary contours are created and their relationship of embrace is ascertained. The region closed by the contours is triangulated using Delaunay triangulation algorithm. Arbitrary cutting operation creates cutting curve interactively. The cut model still maintains its correct topology structure. With these operations, tissues inside can be observed easily and it can aid doctors to diagnose. The methods can also be used in surgery planning of radiotherapy.展开更多
The increasing availability of folksonomy data makes them vital for user profiling approaches to precisely detect user preferences and better understand user interests, so as to render some personalized recommendation...The increasing availability of folksonomy data makes them vital for user profiling approaches to precisely detect user preferences and better understand user interests, so as to render some personalized recommendation or re- trieval results. This paper presents a rigorous probabilis- tic framework to discover user preference from folkson- omy data. Furthermore, we incorporate three models into the framework with the corresponding inference methods, expectation-maximization or Gibbs sampling algorithms. The user preference is expressed through topical conditional distributions. Moreover, to demonstrate the versatility of our framework, a recommendation method is introduced to show the possible usage of our framework and evaluate the applica- bility of the engaged models. The experimental results show that, with the help of the proposed framework, the user pref- erence can be effectively discovered.展开更多
1 Introduction.The superior performance of deep models in classification tasks relies heavily on large-scale supervision data with rich features[1].Recent research has shown that improving the feature diversity while ...1 Introduction.The superior performance of deep models in classification tasks relies heavily on large-scale supervision data with rich features[1].Recent research has shown that improving the feature diversity while expanding the data scale can improve the classification performance[2,3].Time series augmentation possessing the dual strategy is essential in successfully applying deep models in time series classification.展开更多
Hashtags, terms prefixed by a hash-symbol #, are widely used and inserted anywhere within short messages （tweets） on micro-blogging systems as they present rich sen- timent information on topics that people are inte...Hashtags, terms prefixed by a hash-symbol #, are widely used and inserted anywhere within short messages （tweets） on micro-blogging systems as they present rich sen- timent information on topics that people are interested in. In this paper, we focus on the problem of hashtag recommenda- tion considering their personalized and temporal aspects. As far as we know, this is the first work addressing this issue spe- cially to recommend personalized hashtags combining long- term and short-term user interest. We introduce three features to capture personal and temporal user interest： 1） hashtag textual information; 2） user behavior; and 3） time. We of- fer two recommendation models for comparison： a linear- combined model, and an enhanced session-based temporal graph （STG） model, Topic-STG, considering the features to learn user preferences and subsequently recommend person- alized hashtags. Experiments on two real tweet datasets illus- trate the effectiveness of the proposed models and algorithms.展开更多
A virtual cosmetics try-on system provides a realistic try-on experience for consumers and helps them efficiently choose suitable cosmetics.In this article,we propose a real-time augmented reality virtual cosmetics tr...A virtual cosmetics try-on system provides a realistic try-on experience for consumers and helps them efficiently choose suitable cosmetics.In this article,we propose a real-time augmented reality virtual cosmetics try-on system for smartphones(ARCosmetics),taking speed,accuracy,and stability into consideration at each step to ensure a better user experience.A novel and very fast face tracking method utilizes the face detection box and the average position of facial landmarks to estimate the faces in continuous frames.A dynamic weight Wing loss is introduced to assign a dynamic weight to every landmark by the estimated error during training.It balances the attention between small,medium,and large range error and thus increases the accuracy and robustness.We also designed a weighted average method to utilize the information of the adjacent frame for landmark refinement,guaranteeing the stability of the generated landmarks.Extensive experiments conducted on a large 106-point facial landmark dataset and the 300-VW dataset demonstrate the superior performance of the proposed method compared to other state-of-the-art methods.We also conducted user satisfaction studies further to verify the efficiency and effectiveness of our ARCosmetics system.展开更多
1 Introduction Time seriesaugmentationis an essential approachto solvethe overfitting problem on the time series classification(TSC)task[1,2].Although existing approaches perform better in mitigating this problem,none...1 Introduction Time seriesaugmentationis an essential approachto solvethe overfitting problem on the time series classification(TSC)task[1,2].Although existing approaches perform better in mitigating this problem,none of them focus on protecting saliency regions on time series.The key informative shapelets contained in these regions are the core basis for distinguishing categories(e.g.,upward spikes in ECG and high amplitude in Sensor).展开更多
文摘The need for safety critical systems （SCS） is both important and urgent, and their evaluation and verification are test-dependent. SCS are usually complex and very large, so manual testing of SCS are infeasible in practice, and develop- ing automatic test approaches for SCS has become an impor- tant trend. This paper defines a formal semantics model for automatic test of SCS, called AutTMSCS, which describes behaviors in SCS testing. The model accommodates the high order collaboration in real time and temporariness of SCS testing. Testing tasks, test equipment and products under test are abstracted and architected in three layers, and a method for automatic testing is given. Based on extended label tran- sition system （LTS）, the convergency and correctness of the model are proved to demonstrate the computability of the model, indicating that the testing process of SCS can be au- tomatic.
基金partially supported by the Overseas Research Scholar Fund from Zhejiang University of Technology.
文摘Knowledge discovery from data directly can hardly avoid the fact that it is biased towards the collected experimental data, whereas, expert systems are always baffled with the manual knowledge acquisition bottleneck. So it is believable that integrating the knowledge embedded in data and those possessed by experts can lead to a superior modeling approach. Aiming at the classification problems, a novel integrated knowledge-based modeling methodology, oriented by experts and driven by data, is proposed. It starts from experts identifying modeling parameters, and then the input space is partitioned followed by fuzzification. Afterwards, single rules are generated and then aggregated to form a rule base, on which a fuzzy inference mechanism is proposed. The experts are allowed to make necessary changes on the rule base to improve the model accuracy. A real-world application, welding fault diagnosis, is presented to demonstrate the effectiveness of the methodology.
文摘Journals and their citation relations are abstracted into journal citation networks, basing on CSTPC journal database from year 2003 to 2006. The network shows some typical characteristics from complex networks. This paper presents the idea of using motifs, subgraphs with higher occurrence in real network than in random ones, to discover two different citation patterns in journal communities. And a further investigation is addressed on both motif granularity and node centrality to figure out some reasons on the differences between two kinds of communities in journal citation network.
基金Sponsored by the National Basic Research Development Program of China (973 Program) (Grant No.2005CB321901)
文摘A new approach for dynamic Web services discovery based on similarity computation in the treatment of massive Web information resource is put forward. Firstly, three kinds of service description information, textual, semantic and structural information, were modeled to compute the similarity of services. Then a novel dynamic Web services discovery mechanism was provided and the experiment on it was carried out. Results show that the new approach achieves considerable performance on precision and efficiency metrics for dynamic Web services discovery.
文摘A syntactic and structural matching mechanism for service discovery was put forward, which tries to exploit the underlying semantics of web services to enhance tbe traditional syntactic service discovery. We commit WSDL （Web Service Description Language） as service description language. The syntactic matching mechanism is based on the textual similarity among WSDL documents using VSM （ Vector Space Model）. The structural information is extracted from WSDL document tree or the invocation sequence of a series of services which can be viewed as the problem of graph isomorphism. Then we combine the syntactic and structural similarity linearly to calculate the service similarity. Finally we provide a novel web services discovery framework named SG^＊ to find the exact services meeting the users＇ goals based on service similarity.
基金Acknowledgments： This work has been supported by the National Grand Fundamental Research 973 Program of China under Grant No.2007CB310800 and the National Natural Science Foundation of China under Grant No. 60496323.
基金This research was supported by the National Nature Science Foundation of China under Grant No.60473024 the Nature Science Foundation of Zhejiang Province of China under Grant No.Y104341 and z105391.
文摘This paper proposes a practical algorithms of plane cutting, stereo clipping and arbitrary cutting for 3D surface model reconstructed from medical images. In plane cutting and stereo clipping algorithms, the 3D model is cut by plane or polyhedron. Lists of edge and vertex in every cut plane are established. From these lists the boundary contours are created and their relationship of embrace is ascertained. The region closed by the contours is triangulated using Delaunay triangulation algorithm. Arbitrary cutting operation creates cutting curve interactively. The cut model still maintains its correct topology structure. With these operations, tissues inside can be observed easily and it can aid doctors to diagnose. The methods can also be used in surgery planning of radiotherapy.
基金This work was supported by the National Basic Re-search program of China （2014CB340305）, partly by the National Natural Science Foundation of China （Grant Nos. 61300070 and 61421003） and partly by the State Key Lab for Software Development Environment.
文摘The increasing availability of folksonomy data makes them vital for user profiling approaches to precisely detect user preferences and better understand user interests, so as to render some personalized recommendation or re- trieval results. This paper presents a rigorous probabilis- tic framework to discover user preference from folkson- omy data. Furthermore, we incorporate three models into the framework with the corresponding inference methods, expectation-maximization or Gibbs sampling algorithms. The user preference is expressed through topical conditional distributions. Moreover, to demonstrate the versatility of our framework, a recommendation method is introduced to show the possible usage of our framework and evaluate the applica- bility of the engaged models. The experimental results show that, with the help of the proposed framework, the user pref- erence can be effectively discovered.
基金the Fundamental Research Funds for the Central Universities(No.2-9-2022-062)。
文摘1 Introduction.The superior performance of deep models in classification tasks relies heavily on large-scale supervision data with rich features[1].Recent research has shown that improving the feature diversity while expanding the data scale can improve the classification performance[2,3].Time series augmentation possessing the dual strategy is essential in successfully applying deep models in time series classification.
文摘Hashtags, terms prefixed by a hash-symbol #, are widely used and inserted anywhere within short messages （tweets） on micro-blogging systems as they present rich sen- timent information on topics that people are interested in. In this paper, we focus on the problem of hashtag recommenda- tion considering their personalized and temporal aspects. As far as we know, this is the first work addressing this issue spe- cially to recommend personalized hashtags combining long- term and short-term user interest. We introduce three features to capture personal and temporal user interest： 1） hashtag textual information; 2） user behavior; and 3） time. We of- fer two recommendation models for comparison： a linear- combined model, and an enhanced session-based temporal graph （STG） model, Topic-STG, considering the features to learn user preferences and subsequently recommend person- alized hashtags. Experiments on two real tweet datasets illus- trate the effectiveness of the proposed models and algorithms.
基金supported in part by the National Key R&D Program of China(2021ZD0140407)in part by the National Natural Science Foundation of China(Grant No.U21A20523).
文摘A virtual cosmetics try-on system provides a realistic try-on experience for consumers and helps them efficiently choose suitable cosmetics.In this article,we propose a real-time augmented reality virtual cosmetics try-on system for smartphones(ARCosmetics),taking speed,accuracy,and stability into consideration at each step to ensure a better user experience.A novel and very fast face tracking method utilizes the face detection box and the average position of facial landmarks to estimate the faces in continuous frames.A dynamic weight Wing loss is introduced to assign a dynamic weight to every landmark by the estimated error during training.It balances the attention between small,medium,and large range error and thus increases the accuracy and robustness.We also designed a weighted average method to utilize the information of the adjacent frame for landmark refinement,guaranteeing the stability of the generated landmarks.Extensive experiments conducted on a large 106-point facial landmark dataset and the 300-VW dataset demonstrate the superior performance of the proposed method compared to other state-of-the-art methods.We also conducted user satisfaction studies further to verify the efficiency and effectiveness of our ARCosmetics system.
基金supported by the National Key Research and Development Program (2018YFB1306000)Ministry of Industry and Information Technology of China (2105-370171-07-02-860873)+1 种基金State Key Lab of Software Development Environment (SKLSDE)Beijing Advanced Innovation Center for Big Data and Brain Computing (BDBC).
文摘1 Introduction Time seriesaugmentationis an essential approachto solvethe overfitting problem on the time series classification(TSC)task[1,2].Although existing approaches perform better in mitigating this problem,none of them focus on protecting saliency regions on time series.The key informative shapelets contained in these regions are the core basis for distinguishing categories(e.g.,upward spikes in ECG and high amplitude in Sensor).
