{"title":"YOLOXD: A New Network for Metal Surface Defect Detection","authors":"Hao Wang, Mengjiao Li, Pengxiang Gao, Shumei Zhang","doi":"10.1109/ICCS56273.2022.9988327","DOIUrl":"https://doi.org/10.1109/ICCS56273.2022.9988327","url":null,"abstract":"The detection of metal surface defects is an essential part of the industrial production process. Most of the current detection methods are poorly detected due to the diversity of metal surface defect morphologies and the complex reality of the environment. To address this problem, this paper proposes a novel metal surface defect detection network YOLOXD based on YOLOX, which is designed with Dilated Pyramid Pooling to increase the receptive field and introduces an attention mechanism to enhance feature extraction compared to YOLOX. And the Mish activation function is used to assist the model training. Our method achieves 78.45% $mathbf{mAP}$ in the proposed dataset.","PeriodicalId":382726,"journal":{"name":"2022 IEEE 2nd International Conference on Computer Systems (ICCS)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117040531","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":"APT Attack Detection Method Based on Traffic Log Features","authors":"Xingjie Huang, Beibei Su, Ru Zhang, Feiyu Chen, Jinmeng Zhao, Yating Gao","doi":"10.1109/ICCS56273.2022.9987983","DOIUrl":"https://doi.org/10.1109/ICCS56273.2022.9987983","url":null,"abstract":"APT (Advanced Persistent Threat) attack can generally hide the attack process by evading the detection of the IDS system. This paper proposes a detection model for C2 stage network behavior in APT attacks using anonymized datasets. For C2 domain name access records, a number of features based on DNS behavior rules are proposed, and these features are fused with traffic features. Experiments are carried out by combining the data collected in a large-scale organization with the simulation data. The experiments result shows that the method in this paper has the ability to detect APT attacks under large data, and can detect suspected infected hosts.","PeriodicalId":382726,"journal":{"name":"2022 IEEE 2nd International Conference on Computer Systems (ICCS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133044964","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":"Formal Modelling and Visualization of Elevator System Based on Event-B","authors":"Junpeng Yao, Sheng-rong Zou, Xue Geng","doi":"10.1109/ICCS56273.2022.9988440","DOIUrl":"https://doi.org/10.1109/ICCS56273.2022.9988440","url":null,"abstract":"When designing complex systems with high security requirements, it is essential to use reliable formal modeling methods to verify whether the resulting system is what the designer wants. This paper presents a case study of an elevator system based on Event-B and Rodin platform. Event-B method is a formal modeling method based on set theory and predicate logic. Its main features are layer by layer refinement and theorem proof. Event-B is supported by Rodin platform. We use ProB to perform animation simulation and model check on the machine to ensure the correctness and effectiveness of the model. Finally, BMotionWeb is used to visualize the model to further enhance the model's comprehensibility and interactivity, so that designers can find hidden errors more quickly.","PeriodicalId":382726,"journal":{"name":"2022 IEEE 2nd International Conference on Computer Systems (ICCS)","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127297441","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 Implementation of Music Recommendation System Based on Big Data Platform","authors":"Yongri Lin","doi":"10.1109/ICCS56273.2022.9988197","DOIUrl":"https://doi.org/10.1109/ICCS56273.2022.9988197","url":null,"abstract":"With the development of network technology, music recommendation system has also developed rapidly, and online music platform has become the first choice for people to listen to music. However, the music recommendation system also faces some problems, such as data storage confusion, low computational efficiency, cold start and data sparsity caused by large data scale. The recommendation system is analyzed and studied, and a hybrid recommendation algorithm based on collaborative filtering is designed. Two channels of offline data transmission and real-time data transmission are designed to collect and transmit data; Secondly, the overall architecture of the music recommendation system is designed, and each functional module is designed and implemented. The music data warehouse is built, and the data is processed and stored hierarchically. Then preprocess the data to facilitate the calculation of the recommended model. Based on the improved algorithm and Hadoop distributed framework, the recommendation module is completed and the music recommendation system is implemented; Finally, the music recommendation system is tested to verify the feasibility and stability of the recommendation system, which reflects the efficiency, scalability and stability of the music recommendation system, and can meet the personalized music needs of users.","PeriodicalId":382726,"journal":{"name":"2022 IEEE 2nd International Conference on Computer Systems (ICCS)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125376485","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}