{"title":"Fine-grained Human Action Recognition Based on Zero-Shot Learning","authors":"Yahui Zhao, Ping Shi, Ji’an You","doi":"10.1109/ICSESS47205.2019.9040818","DOIUrl":"https://doi.org/10.1109/ICSESS47205.2019.9040818","url":null,"abstract":"In recent years, the number of categories of human action recognition is increasing rapidly. On the one hand, the traditional supervised learning model has become increasingly difficult to collect enough training data to identify all categories. On the other hand, for some well-trained traditional supervised learning models, it is a waste of time to collect enough samples of new categories and retrain them together in order to identify new categories. We proposes a mapping between visual features of video and semantic description of fine-grained human action recognition. Unlike most current zero-shot learning methods, which use manual features as visual features, we uses features learnt from I3D network model as visual features, which are more general than manual features.","PeriodicalId":203944,"journal":{"name":"2019 IEEE 10th International Conference on Software Engineering and Service Science (ICSESS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115430528","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yong Shuai, Chuan Yang, Jie Chen, Can Yuan, Tailiang Song
{"title":"Secondary Screening Detection optimization Method for Electronic Components Based on Artificial Intelligence","authors":"Yong Shuai, Chuan Yang, Jie Chen, Can Yuan, Tailiang Song","doi":"10.1109/ICSESS47205.2019.9040798","DOIUrl":"https://doi.org/10.1109/ICSESS47205.2019.9040798","url":null,"abstract":"In view of the problem about low components code recognition accuracy, low detection efficiency, long detection time and high detection cost in electronic components secondary screening detection, this paper proposes an optimization method of electronic components secondary screening based on artificial intelligence model. Firstly, use the gradient-based decision tree model to calculate the relationship between the detection items, find the optimal secondary screening combination scheme for electronic components, then complete electronic component code recognizing based on CTPN+Tesseract-OCR deep learning model, improve the accuracy of electronic component code recognition. The cases analysis shows that the proposed method in this paper has a higher digital recognition rate, fewer detection times in the same batch of products, indicating the effectiveness and applicability of this method.(Abstract)","PeriodicalId":203944,"journal":{"name":"2019 IEEE 10th International Conference on Software Engineering and Service Science (ICSESS)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124847740","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Blockchain for Digital Rights Management of Design Works","authors":"Zihao Lu, Youqun Shi, Rao Tao, Zhaohui Zhang","doi":"10.1109/ICSESS47205.2019.9040744","DOIUrl":"https://doi.org/10.1109/ICSESS47205.2019.9040744","url":null,"abstract":"A design work not only has a complex functional composition, but also has special trading needs. These all result in the difficulties in content protection, copyright protection and the trading of works. To solve these problems, this paper proposes a scheme for digital rights management of design works using blockchain. Unlike existing digital rights management methods, this scheme binds the off-chain design work and its copyright record in the blockchain. The display of design effects, the confidentiality of design details and the compatibility with relevant laws are all taken into account. A new proof-of-delivery method is also proposed to ensure the fairness of the trade. By using smart contracts and public key cryptography, it has no need for active operation from participants in the trade. The scheme is evaluated, analyzed, and compared with other methods from multiple respects to demonstrate its rationality and effectiveness. Finally, a proof-of-concept experiment is described by taking digital garment design as an example.","PeriodicalId":203944,"journal":{"name":"2019 IEEE 10th International Conference on Software Engineering and Service Science (ICSESS)","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126189321","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Human Behavior Recognition Algorithm Based on HOG Feature and SVM Classifier","authors":"Qing Cai","doi":"10.1109/ICSESS47205.2019.9040826","DOIUrl":"https://doi.org/10.1109/ICSESS47205.2019.9040826","url":null,"abstract":"Human behavior analysis is a hot research in the field of computer vision. It has broad application prospects in the fields of intelligent monitoring, human-computer interaction, motion analysis and virtual reality. In order to improve the accuracy of human behavior recognition, a human behavior recognition method based on HOG feature and SVM classifier is proposed. First, the HOG features of the training set and the test set are extracted. Then, the multi-class problem is transformed into multiple dual-class problems, and multiple SVM classifiers are trained by using the HOG features. Finally, the trained classifiers are employed to recognize the human walking and waving behavior. Experimental results show that the recognition rate of walking and waving is 87.5% for the UIUC database. The human behavior recognition method proposed in this paper can effectively improve the recognition rate.","PeriodicalId":203944,"journal":{"name":"2019 IEEE 10th International Conference on Software Engineering and Service Science (ICSESS)","volume":"98 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122646724","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A Mirco-Service Tracing System Based on Istio and Kubernetes","authors":"Meina Song, Qingyang Liu, H. E","doi":"10.1109/ICSESS47205.2019.9040783","DOIUrl":"https://doi.org/10.1109/ICSESS47205.2019.9040783","url":null,"abstract":"In the development of micro-service architecture, fast error service location and the combing of service invocation chains are the key issues to be resolved. Otherwise, with the expansion of the system scale, the maintenance cost of the system will grow rapidly. Meanwhile, the existing tracing solution, such as Spring-Cloud, need a lot of modifications to the source code of the original system to embed, and the cost of modification is high. Based on this, this paper designs a micro-service tracing system based on Istio and container technology. This system can monitor and collect the calling information between micro-services in the micro-service architecture system. Through further analysis of this information, the duration of the single-step call and the dependence between services can also be discovered. At the same time, the tracing system has low code intrusion to the original system. Finally, we do experiments to prove that the tracing system has little impact on the performance of the original system.","PeriodicalId":203944,"journal":{"name":"2019 IEEE 10th International Conference on Software Engineering and Service Science (ICSESS)","volume":"34 5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122922378","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Software Effective Evaluating Technology: SWEET","authors":"Yaozong Li, Tao Wang, Yue Yu, Dongyang Hu","doi":"10.1109/ICSESS47205.2019.9040753","DOIUrl":"https://doi.org/10.1109/ICSESS47205.2019.9040753","url":null,"abstract":"In open source community, there are a large number of software resources existing. Such software resources distribute in different societies or storehouses, which require different software characteristic. This phenomenon results in difficult to evaluate software quality using traditional methods. In this case, a novel open-source software sorting algorithm may be an effective solution. Considering both subjective and objective levels, we propose a new method on software sorting and retrieving. In the subjective level, metrics are selected from the corresponding collaborative development community based on software topic. In the objective level, metrics are obtained from the group emotional evaluation value of the knowledge sharing community. We have proved the effectiveness of the method through comparison experiments. Combining with the Solrcloud tool, this method has been integrated into the OSSEAN platform.","PeriodicalId":203944,"journal":{"name":"2019 IEEE 10th International Conference on Software Engineering and Service Science (ICSESS)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114417622","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"The Service Computational Resource Management Strategy Based On Edge-Cloud Collaboration","authors":"You Li, Liutong Xu","doi":"10.1109/ICSESS47205.2019.9040830","DOIUrl":"https://doi.org/10.1109/ICSESS47205.2019.9040830","url":null,"abstract":"Using edge computing technology can effectively solve the network latency and stability problems in industry IoT system. In order to improve the stability of the edge, this paper studies the traditional IoT rule engine and proposes an edge-cloud collaborative computational resource management strategy. Firstly, our strategy prioritizes rules and keep the more important rule executed at the edge end. Our strategy continuously adjusts the executing position of the rules between the cloud server and edge server by the resources loaded and the priority of the rules on edge. The experimental results indicate that our strategy has led to edge CPU usage and memory usage below 90%. It shows that this strategy has good performance of the resource management under the condition that the platform has a large number of rules, and our strategy can provide faster and more stable rule processing and application.","PeriodicalId":203944,"journal":{"name":"2019 IEEE 10th International Conference on Software Engineering and Service Science (ICSESS)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121899906","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Pointer-Generator Abstractive Text Summarization Model with Part of Speech Features","authors":"Shuxia Ren, Zheming Zhang","doi":"10.1109/ICSESS47205.2019.9040715","DOIUrl":"https://doi.org/10.1109/ICSESS47205.2019.9040715","url":null,"abstract":"The typical sequence-to-sequence with attention mechanism models have achieved good results in the task of abstractive text summarization. However, this kind of models always have some shortcomings: they have out-of-vocabulary (OOV) problems, sometimes may repeat themselves and are always of low quality. In order to solve these problems, we propose a pointer-generator text summarization model with part of speech features. First, we use the word vector and prat of speech vector as the input of the model, and then improve the quality of generated abstracts by combining convolutional neural network (CNN) and bi-directional LSTM. Second, we use pointergenerator network to control whether generating or copying words to solve the problem of OOV. Finally, we use coverage mechanism to monitor the abstract we have generated to avoid duplication problems. Compared with the classic pointergenerator network, the ROUGE scores of our model have greatly improved and the performance on LCSTS dataset is better than the state-of-the-art model at present.","PeriodicalId":203944,"journal":{"name":"2019 IEEE 10th International Conference on Software Engineering and Service Science (ICSESS)","volume":"116 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126976577","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Durong Yin, Yi Yang, Mao Yang, Zhigang Yang, Caihong Li, Lian Li
{"title":"A New Distributed Power System for Stability Prediction And Analysis","authors":"Durong Yin, Yi Yang, Mao Yang, Zhigang Yang, Caihong Li, Lian Li","doi":"10.1109/ICSESS47205.2019.9040711","DOIUrl":"https://doi.org/10.1109/ICSESS47205.2019.9040711","url":null,"abstract":"Grid system is prone to all kinds of disturbances. These disturbances only appear in a moment, but often cause cascading failures. Aiming at this problem, a prediction and analysis system for distributed power grid stability is developed. Firstly, combined with advanced data processing technology, the factors affecting the stability of power grid are analyzed and described. Secondly, a combined model KRR-XGBoost is proposed to predict the grid stability index, and the grid stability can be judged according to the predicted results. In order to verify the effectiveness of the model, we take the UCI distributed grid stability data set as an example to carry out the test. The experimental results show that compared with the other four models, this model can provide more accurate prediction results and better predict the stability of distributed power system, which further provides effective design guidance and cost optimization for distributed power supply system.","PeriodicalId":203944,"journal":{"name":"2019 IEEE 10th International Conference on Software Engineering and Service Science (ICSESS)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129345153","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Text Summarization Model of Combining Global Gated Unit and Copy Mechanism","authors":"Shuxia Ren, Kaijie Guo","doi":"10.1109/ICSESS47205.2019.9040794","DOIUrl":"https://doi.org/10.1109/ICSESS47205.2019.9040794","url":null,"abstract":"Text summarization is a common task in NLP. Automatic text summarization aims to transform lengthy documents into shortened versions. Recently, the neural networks based on seq2seq with attention are good at generating summarization. However, the accuracy of the summarization too difficult are to guarantee. In addition, the Out-of-Vocabulary (OOV) problem is also an important factor affecting the quality of the generated summary. To solve these problems, we hybrid the advantages of the extractive and abstractive summarization systems to propose text summarization model of combining global gated unit and copy mechanism (GGUC). The experiment results demonstrate that the performance of the model is better than the other text summary system on LCSTS datasets.","PeriodicalId":203944,"journal":{"name":"2019 IEEE 10th International Conference on Software Engineering and Service Science (ICSESS)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126532393","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}