{"title":"Fruit Market Trend Forecast Using Kmeans-based Deep Learning Models","authors":"Yongming Fang, Xiaoping Min, Ling Zheng, Defu Zhang","doi":"10.1109/ICSESS47205.2019.9040838","DOIUrl":"https://doi.org/10.1109/ICSESS47205.2019.9040838","url":null,"abstract":"The fluctuations of fruit market price are mainly related to the fruit output quantity that may be influenced by climate, pest, and many other natural disasters. In this paper, in order to precisely forecast the coming trend of fruit market, image clustering-based deep learning framework is proposed. Initially, a series of data points indicating fruit prices are transformed into a series of fixed-length two-dimensional curve images at intervals, and each image is segmented into the input curve and the output curve. Furthermore, to make training set, K class labels are obtained on the output curves using the Kmeans clustering. Finally, the training set are employed for training convolutional neural network, long short-term memory and the hybrid of convolutional neural network and long short-term memory. The comparative study shows that the convolutional neural network has more advanced capability in predicting the fruit market than the other two, while the prediction accuracy of these trained models may not be sufficiently high.","PeriodicalId":203944,"journal":{"name":"2019 IEEE 10th International Conference on Software Engineering and Service Science (ICSESS)","volume":"83 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":"116968241","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":"An Automatic Test Platform for Computer Interlocking System","authors":"Guohua Wang, Zhanyu Shen","doi":"10.1109/ICSESS47205.2019.9040848","DOIUrl":"https://doi.org/10.1109/ICSESS47205.2019.9040848","url":null,"abstract":"Aiming at the problem of insufficient and inefficient testing of computer interlocking system, this paper designs a computer interlocking system test platform (CISTP). Functioning in test case development and test case execution, this system consists of a test case development software and a test case execution software. In addition, test cases are developed for a computer interlocking (CI) system, and demonstrates on the CISTP. The results show that CISTP can improve the test efficiency obviously.","PeriodicalId":203944,"journal":{"name":"2019 IEEE 10th International Conference on Software Engineering and Service Science (ICSESS)","volume":"32 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":"122622368","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 Monitor Method based on Adaptive Frequency for Self-Adaptive Software","authors":"Wen Cheng, Qingshan Li, Lu Wang","doi":"10.1109/ICSESS47205.2019.9040738","DOIUrl":"https://doi.org/10.1109/ICSESS47205.2019.9040738","url":null,"abstract":"Self-Adaptive Systems (SASs) are required to adapt to the complex changes with different characteristics by frequent monitor. The problem with gathering and updating changes information frequently at runtime is that it may cause computing and communication overhead, which affects the real-time of SASs. However, if the frequencies are reduced, it is difficult to ensure the accuracy of changes identifying. So it is necessary to solve the trade-off between the accuracy and expensive overhead. Existing methods based on data processing improve accuracy by reducing potential uncertainties. Other methods based on adaptive frequency lack quantification and are difficult to ensure accuracy. We expect to combine them and break through the latter. To this purpose, this paper proposes a method based on adaptive frequency for SASs. The method can ensure the accuracy of adaptive adjustment by comprehensively analyzing the influencing factors of monitoring frequency, and can quantify the monitoring frequency in real time by calculating these factors according to the monitoring data. Finally, we exemplify these methods with an e-commerce System.","PeriodicalId":203944,"journal":{"name":"2019 IEEE 10th International Conference on Software Engineering and Service Science (ICSESS)","volume":"5 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":"123299549","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":"Design and Research of Edge Layer Service Platform Based on Flexible Service Architecture","authors":"Shilong Liu, Yunxiao Zu","doi":"10.1109/ICSESS47205.2019.9040827","DOIUrl":"https://doi.org/10.1109/ICSESS47205.2019.9040827","url":null,"abstract":"With the advent of the future generation networks(5G), high-bandwidth, high-density, and low-latency will become the mainstream features of network services. If we continue to adopt single cloud computing mode, speed, delay, or stability cannot be guaranteed at all. The edge calculation proposed in recent years can properly solves this problem. Edge computing is a network architecture that provides users with the services and cloud computing functions on the wireless side. At the same time, the emergence of virtualization technology enables the traditional server resources to be more fully utilized. Platform and application virtualization now is rapidly moving to the edge of the cloud. An edge computing platform is built by integrating Docker technology and Kubernetes technology in this paper. In addition, network service experiments on the platform are performed. Through the comparison of experiment results on the edge layer and the cloud layer, conclusions are obtained that the edge computing layer can satisfy the low-latency and stable demand of service.","PeriodicalId":203944,"journal":{"name":"2019 IEEE 10th International Conference on Software Engineering and Service Science (ICSESS)","volume":"17 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":"123361002","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":"An Efficient End-to-End Channel Level Pruning Method for Deep Neural Networks Compression","authors":"Lei Zeng, Shi Chen, Sen Zeng","doi":"10.1109/ICSESS47205.2019.9040742","DOIUrl":"https://doi.org/10.1109/ICSESS47205.2019.9040742","url":null,"abstract":"Deep neural networks (DNNS) have obtained compelling performance among many visual tasks by a significant increase in the computation and memory consumption, which severely impede their applications on resource-constrained systems like smart mobiles or embedded devices. To solve these problems, recent efforts toward compressing DNNS have received increased focus. In this paper, we proposed an effective end-to-end channel pruning approach to compress DNNS. To this end, firstly, we introduce additional auxiliary classifiers to enhance the discriminative power of shallow and intermediate layers. Secondly, we impose Ll-regularization on the scaling factors and shifting factors in batch normalization (BN) layer, and adopt the fast and iterative shrinkage-thresholding algorithm (FISTA) to effectively prune the redundant channels. Finally, by forcing selected factors to zero, we can prune the corresponding unimportant channels safely, thus obtaining a compact model. We empirically reveal the prominent performance of our approach with several state-of-theart DNNS architectures, including VGGNet, and MobileNet, on different datasets. For instance, on cifar10 dataset, the pruned MobileNet achieves 26. 9x reduction in model parameters and 3. 9x reduction in computational operations with only 0.04% increase of classification error.","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":"128782015","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 Static Call Graph Construction Method Based on Simulation Execution","authors":"Fan Zhang, Naijie Gu, Junjie Su","doi":"10.1109/ICSESS47205.2019.9040837","DOIUrl":"https://doi.org/10.1109/ICSESS47205.2019.9040837","url":null,"abstract":"Call graphs have many applications in the field of software engineering. For instance, they are at the foundation of many advanced analysis, such as inter-procedural data-flow analysis, and can help software developers to understand programs. Although many methods have been proposed to statically construct call graphs in C/C++ programs, the call graphs constructed by these methods are still not complete and accurate enough. Especially for the parent-child relationship between threads, there is currently no method that can extract it statically. In order to solve these problems, this paper proposes a static analysis method based on simulation execution to construct call graphs of C/C++ programs. The method analyzes the LLVM IR generated by the source program compilation, and it performs simulation execution on the LLVM IR to generate call graphs. The experimental results show that compared to existing static analysis methods, the proposed method has higher recall rate and higher precision rate, and can analyze the parent-child relationship between threads in a program that uses the pthread library.","PeriodicalId":203944,"journal":{"name":"2019 IEEE 10th International Conference on Software Engineering and Service Science (ICSESS)","volume":"135 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":"116148232","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}
Zhibo Yu, Jiale Han, Tianpu Zhao, Ning Tian, Jingyang Wang
{"title":"Research and Implementation of Online Judgment System Based on Micro Service","authors":"Zhibo Yu, Jiale Han, Tianpu Zhao, Ning Tian, Jingyang Wang","doi":"10.1109/ICSESS47205.2019.9040684","DOIUrl":"https://doi.org/10.1109/ICSESS47205.2019.9040684","url":null,"abstract":"Since the OJ (Online Judgment) system began to be used, the Internet has continued to develop as demand. As a result, higher requirements are placed on the function, performance and scalability of the system. Based in part on the shortcomings of the existing OJ system, this paper puts forward the research and implementation of a kind of OJ system based on micro service; Expounds on the functions and related knowledge of the system; Gives the implementation method, and describes in detail the two key technologies used to deal with malicious code and high concurrency. The system uses the judge machine as a stand-alone module. This module creates micro services using Docker, ensures system security through Docker isolation and runtime and memory limitations, implements Docker Monitoring and system load balancing using Consul, Haproxy, Telegraf and elastic scripts. After the test system is running, the effect is good. The system has certain guiding significance for practical application.","PeriodicalId":203944,"journal":{"name":"2019 IEEE 10th International Conference on Software Engineering and Service Science (ICSESS)","volume":"24 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":"126289658","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":"SPPlagiarise: A Tool for Generating Simulated Semantics-Preserving Plagiarism of Java Source Code","authors":"Hayden Cheers, Yuqing Lin, Shamus P. Smith","doi":"10.1109/ICSESS47205.2019.9040853","DOIUrl":"https://doi.org/10.1109/ICSESS47205.2019.9040853","url":null,"abstract":"Source code plagiarism is a common occurrence in undergraduate computer science education. Studies have indicated at least 50% of students plagiarize during their undergraduate career. To identity cases of source code plagiarism, many source code plagiarism detection tools have been proposed. However, conclusively determining the effectiveness these tools at identifying cases of source code plagiarism is difficult. Evaluations are typically performed using unreleased data sets. Without a comprehensive publicly available data set for source code plagiarism detection evaluation, it is difficult to perform an unbiased and reproducible evaluations of tools. To address this problem, this paper presents a tool, SPPlagiarise, which is designed to produce simulated source code plagiarism of Java source code. SPPlagiarise applies a random number of semantics-preserving source code obfuscations at random locations to a Java code base to simulate source code plagiarism. In this paper the design of the tool and an evaluation of a generated plagiarism data set is presented.","PeriodicalId":203944,"journal":{"name":"2019 IEEE 10th International Conference on Software Engineering and Service Science (ICSESS)","volume":"51 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":"127091124","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":"An Microservices-Based Openstack Monitoring Tool","authors":"M. Yang, Ming Huang","doi":"10.1109/ICSESS47205.2019.9040740","DOIUrl":"https://doi.org/10.1109/ICSESS47205.2019.9040740","url":null,"abstract":"Monitoring of openstack clouds is an imperative necessity for cloud providers and administrators to analyze and discover what is happening in the cloud. In this paper, a microservices-based openstack monitoring system, namely openstack-reporter, is proposed, aiming at monitoring openstack clouds and providing a convenient tool for the administrators. Openstack-reporter adopting microservices architecture consists of three constituent components where each component is responsible for a single aspect. The connection among these components is implemented with the help of kubernetes DNS-based service discovery and Role-based access control (RBAC) mechanisms. The management of these three components is performed by kubernetes which is devoted to automate rollouts, rollbacks. We have released the openstack-reporter, docker images and kubernetes configurations which can be accessed publicly. One can easily build the openstack monitoring system just by deploying the openstack-reporter in our kubernetes cluster. To validate the performance of the proposed monitoring system, an openstack platform and openstack-reporter have been built in our datacenter and the management center respectively, and the results are displayed.","PeriodicalId":203944,"journal":{"name":"2019 IEEE 10th International Conference on Software Engineering and Service Science (ICSESS)","volume":"4 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":"125259549","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}
Xing Xing, Jianyan Luo, Zhichun Jia, Yanyan Li, Qiuyang Han
{"title":"Automated Fault Detection for Web Services using Naïve Bayes Approach","authors":"Xing Xing, Jianyan Luo, Zhichun Jia, Yanyan Li, Qiuyang Han","doi":"10.1109/ICSESS47205.2019.9040756","DOIUrl":"https://doi.org/10.1109/ICSESS47205.2019.9040756","url":null,"abstract":"With the development of the web service technology, the service application becomes an important and popular solution for the distributed computing model. As more and more web services are deployed on the network, the web services can fail for many reasons. One of challenges in this evolution is how to provide a necessary fault detection method for minimizing the service failure impact and enhance the reliability of the services. For this purpose, we present an automatic fault detection framework and a fault detection model based on the Naïve Bayes approach. By analyzing the available service execution logs, our method can achieve the training data and convert them into the detection model. Using the Naïve Bayes approach and the given threshold value, our model computes the service posterior probability to each fault type and identifies the service faults. Experimental results show that our method is effective in detecting the service faults.","PeriodicalId":203944,"journal":{"name":"2019 IEEE 10th International Conference on Software Engineering and Service Science (ICSESS)","volume":"59 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":"127198453","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}