{"title":"Research on Optimizing Online Course Construction Mode","authors":"Zhen Xiong, Lin Zhi","doi":"10.1109/ICCSE.2019.8845379","DOIUrl":"https://doi.org/10.1109/ICCSE.2019.8845379","url":null,"abstract":"With the rapid development of online education, its core resource is online courses. Online courses not only have achieved considerable growth in the number of users, but also have the advantages that traditional courses cannot match. This paper introduces the existing online course construction mode, and analyzes the advantages and disadvantages of the existing online course mode. This paper puts forward the mode optimization construction of online course from three aspects of course design elements analysis, course design principles and course optimization methods.","PeriodicalId":351346,"journal":{"name":"2019 14th International Conference on Computer Science & Education (ICCSE)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126401749","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 Deep Learning Method for Fault Detection of Autonomous Vehicles","authors":"Jing Ren, Rui Ren, Mark Green, Xishi Huang","doi":"10.1109/ICCSE.2019.8845483","DOIUrl":"https://doi.org/10.1109/ICCSE.2019.8845483","url":null,"abstract":"Fault detection is a crucial step for the safe operation of autonomous vehicles. Failure to detect faults can result in component failure leading to the breakdown of the car or even catastrophic accidents. In this paper, we propose a general fault detection method using deep learning techniques to learn patterns of faults reflected in the dynamic model of an autonomous vehicle. We have applied the proposed method to a remotely operated scaled multi-wheeled combat vehicle and evaluated the algorithm using normal and defective signals. The results show that the proposed deep learning method can accurately identify faults that are caused by mechanical problems or changes in system parameter which are reflected in the dynamic models. This general deep learning technique can be tailored to detect many defects or faults in the manufacturing and/or operation of autonomous vehicles.","PeriodicalId":351346,"journal":{"name":"2019 14th International Conference on Computer Science & Education (ICCSE)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126881218","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 Research on Generative Adversarial Networks Applied to Text Generation","authors":"Chao Zhang, Caiquan Xiong, Lingyun Wang","doi":"10.1109/ICCSE.2019.8845453","DOIUrl":"https://doi.org/10.1109/ICCSE.2019.8845453","url":null,"abstract":"Using deep learning methods to generate text, a sequence-to-sequence model is typically used. This kind of models is very effective in dealing with tasks that have a strong correspondence between input and output, such as machine translation. Generative Adversarial Networks(GAN) is a generation model that has been proposed in recent years, which has achieved good results in generating continuous and divisible data such as images. This paper proposes an improved model based on GAN, specifically using the transformer network structure instead of the original general Convolutional Neural Network or Recurrent Neural Networks as generator, and using the reinforcement learning algorithm Actor-Critic to improve the model training method. By comparing experiments, and selecting the perplexity, the BLEU score, and the percentages of unique n-gram to evaluate the quality of the generated sentences. The results show that the improved model proposed in this paper perform better than comparative models on above three evaluation indexes. This verifies its effectiveness in text generation.","PeriodicalId":351346,"journal":{"name":"2019 14th International Conference on Computer Science & Education (ICCSE)","volume":"110 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127108440","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":"Artificial Intelligence to Assist E-Learning","authors":"Hsiao-Hui Li, Yuan-Hsun Liao, Yuehua Wu","doi":"10.1109/ICCSE.2019.8845449","DOIUrl":"https://doi.org/10.1109/ICCSE.2019.8845449","url":null,"abstract":"Teaching norms are taught through the way of large class teaching. Nowadays, most of the teaching method is still dependent on physical classes. Therefore, it’s hard to design individual lesson based on different students’ ability to achieve fundamental education. Good teaching is” According to the ability, ambition and interest of different learners, give appropriate teaching methods”. Therefore, this paper is analysis students learning effectiveness through artificial intelligence adjusting the learning content and curriculum according to different learners to give learners the most appropriate learning style. The design can achieve personalized learning and auto-didacticism and instant feedback to meet the learners’ different learning styles and thus improve the overall learning benefits.","PeriodicalId":351346,"journal":{"name":"2019 14th International Conference on Computer Science & Education (ICCSE)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120821421","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":"Security Analysis and Improvement of Hybrid Signcryption Scheme Based on Heterogeneous System","authors":"Shijin Li, Fushou Tao, Ting Shi","doi":"10.1109/ICCSE.2019.8845053","DOIUrl":"https://doi.org/10.1109/ICCSE.2019.8845053","url":null,"abstract":"The heterogeneous hybrid signcryption scheme can not only solve the problem that only the short message can be encrypted in the traditional public key signcryption, but also realize the secure communication between different cryptosystems. Firstly, the security analysis of a heterogeneous hybrid signcryption scheme shows that the scheme does not satisfy confidentiality and unforgeability. In order to enhance security, an improved heterogeneous hybrid signcryption scheme is proposed. Based on the bilinear Diffie-Hellman problem and discrete logarithm problem, the new scheme is proved to satisfy confidentiality and unforgeability. Compared with the original solution, the new solution reduces the computational overhead while improving security.","PeriodicalId":351346,"journal":{"name":"2019 14th International Conference on Computer Science & Education (ICCSE)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122881603","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":"Research on Leamers9 Eye Movements for Online Video Courses","authors":"Yuanhan Wang, Wei Xu, Xiaoqing Zhan, Wenqi Liu, Wei Liu, W. Cheng","doi":"10.1109/ICCSE.2019.8845375","DOIUrl":"https://doi.org/10.1109/ICCSE.2019.8845375","url":null,"abstract":"Among the presentation styles of online video courses, although Khan-style video has been proved to be effective by relevant research, it does not replace the dominant position of traditional PPT-style video in China. We compare and analyze Khan-style video and PPT-style video by questionnaire survey and eye movement experiment. For analysis method, we first propose the Voice-centric model, which realizes more dynamic and more accurate statistical analysis of learners’ eye movements in learning process. For experimental environment, we develop an experimental system to prepare experiments and process materials graphically. Results show that compared with PPT-style video, Khan-style video is better at helping learners increase the engagement and improve study score.","PeriodicalId":351346,"journal":{"name":"2019 14th International Conference on Computer Science & Education (ICCSE)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123109863","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}
R. Rastogi, Simran Popli, Nima Dorji Moktan, Sweta Sharma
{"title":"A Unified Multi-label Relationship Learning","authors":"R. Rastogi, Simran Popli, Nima Dorji Moktan, Sweta Sharma","doi":"10.1109/ICCSE.2019.8845526","DOIUrl":"https://doi.org/10.1109/ICCSE.2019.8845526","url":null,"abstract":"Multi-label learning belongs to the class of supervised learning wherein each sample is represented by a single instance and is associated with a set of relevant labels. Many realworld applications like medical diagnosis and image classification involve multi-label classification wherein label correlations are essential to the performance of the classifier. To utilize this correlation among labels, in this paper, we propose a novel model termed as Unified Multi-label Relationship Learning (UMRL) which considers the explicit and implicit correlation inherent in data to build an effective learning model. We adopt the Accelerated Gradient Method (AGM) to train the underlying optimization model efficiently. Extensive experimental comparisons to state-of-the-art multi-label algorithms demonstrate the validity and effectiveness of our proposed approach.","PeriodicalId":351346,"journal":{"name":"2019 14th International Conference on Computer Science & Education (ICCSE)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126627874","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":"Analysis of Progression of Scratch Users based on their Use of Elementary Patterns","authors":"K. Amanullah, T. Bell","doi":"10.1109/ICCSE.2019.8845495","DOIUrl":"https://doi.org/10.1109/ICCSE.2019.8845495","url":null,"abstract":"Block based programming languages are a popular way to introduce computer programming to young students. However, concerns have been raised that students may not be learning important programming skills. Previous analyses of Scratch projects online have revealed that the use of important computational elements such as variables, if statements and controlled loops is extremely low, and introducing elementary patterns to the teaching sequence emerged as a potential solution. Although students might have success in the Scratch environment with a limited vocabulary of constructs, it has been pointed out in the literature that the transition process to a different programming language might be difficult. A concern with prior studies of a static analysis of uploaded Scratch projects is that they might be biased towards one-off or brief encounters with programming, where students have a short experience, upload a simple program, and share no further work. We address this concern in this study by measuring the progress of Scratch users over the years, particularly through their use of elementary patterns. Our study has identified all projects submitted by 34,832 users in the Scratch community, and for each user we have compared the skills demonstrated in the first half with those in the second half of their projects. There were no clear signs of any progression, and even some indications of negative progression, and even after more than a year of programming, for most users we found that the use of key elements of programming was still low.","PeriodicalId":351346,"journal":{"name":"2019 14th International Conference on Computer Science & Education (ICCSE)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129951784","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":"Creative Internet of Things (IoT) for Undergraduates","authors":"S. Lee, Andrew Jung, Mira Yun","doi":"10.1109/ICCSE.2019.8845363","DOIUrl":"https://doi.org/10.1109/ICCSE.2019.8845363","url":null,"abstract":"This article presents results of our pilot study for a new Internet of Things (IoT) course for CS undergraduates. Most of the current IoT courses proposed focused on designing and developing new classroom activities and projects. However, we strongly believe that open-ended student project can enhance students’ creative thinking. After providing fundamental theories and related hands-on activities, we allowed students to choose their own final project topic. Since our course covers hardware platforms, programming, networking protocols, and data storage of IoT systems and applications in the classroom, students can be ready for exploring new real-world problems at the end. By choosing their own project topic, students have a chance to apply their classroom leanings to solve new problems creatively and learn new skills by themselves. Course evaluation based on student feedback shows high level of enthusiasm and engagement for the course especially for hands-on activities and final open-ended project.","PeriodicalId":351346,"journal":{"name":"2019 14th International Conference on Computer Science & Education (ICCSE)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130216424","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 Single-channel BSS Method Based on ICEEMDAN and FastICA and Its Application in EMI Analysis","authors":"Hongyi Li, Wei Lin, Di Zhao","doi":"10.1109/ICCSE.2019.8845382","DOIUrl":"https://doi.org/10.1109/ICCSE.2019.8845382","url":null,"abstract":"In the field of electromagnetic compatibility, electromagnetic interference (EMI) has always been a difficult problem for researchers. In order to achieve accurate separation of single-channel EMI signal, this paper proposes a one-stop method based on ICEEMDAN and FastICA. Firstly, the ICEEMDAN algorithm is used to extract several intrinsic mode functions (IMFs) from a single-channel mixture. Secondly, the multi-dimensional signals are reconstructed according to the IMFs and the original aliasing signal and separated by the FastICA algorithm. Finally, the feasibility of the proposed method is proved by experiments. Compared with the existing methods, it has better separation effect, which provides a reference for solving EMI problems.","PeriodicalId":351346,"journal":{"name":"2019 14th International Conference on Computer Science & Education (ICCSE)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133954757","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}