{"title":"Automated Security-focused Network Configuration Management: State of the Art, Challenges, and Future Directions","authors":"Jinglu Xu, G. Russello","doi":"10.1109/DSA56465.2022.00061","DOIUrl":"https://doi.org/10.1109/DSA56465.2022.00061","url":null,"abstract":"With the continuous advancements and innovation in Information Technology (IT), new vendors and products constantly emerge to provide networking services and solutions. Meanwhile, the multi-vendor environment and the huge diversity of siloed devices require new approaches to tackle the complexity and heterogeneity in network configuration management. However, the traditional way of using configuration scripts requires domain expertise with the target system. In recent years, many automated solutions have emerged in academia and industry. This paper presents a literature review on the state-of-the-art of them. It focuses on the background that led to the development of automated techniques, summarizes domain-specific challenges, a nd discusses related studies published to date. Finally, five research gaps with research directions are identified, including 1) intent translation, 2) intelligent network configuration m anagement, 3) a utomated p lanning, 4) intent-based solutions for I2NSF, and 5) reliable network performance.","PeriodicalId":208148,"journal":{"name":"2022 9th International Conference on Dependable Systems and Their Applications (DSA)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114693543","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 Bearing Fault Diagnosis Method based on Improved LSTM-cascade CatBoost","authors":"Weicong Jin, Weizhi Liu, Wenxuan Zhang, Xia Fang","doi":"10.1109/DSA56465.2022.00069","DOIUrl":"https://doi.org/10.1109/DSA56465.2022.00069","url":null,"abstract":"Bearing faults are widely concerned in the field of fault diagnosis, it has numerous excellent detection algorithms currently. In this paper, a new model called LSTM-Cascade CatBoost is applied, which can directly classify bearing vibration signals in the case of multiple granularities and high dimensions without signal processing. The model is based on gcForest, which can automatically adjust its complexity to the size of the dataset and it uses LSTM to improve its feature extraction ability. CatBoost is used as the base classifier of cascade forest to improve classification accuracy. Experimental results show that this model has high accuracy in CWRU and XJTU-SY datasets. Besides, it not only demonstrates that the feature extraction ability of LSTM is significantly better than that of multi-grained scanning, but CatBoost as a base classifier can further improve the accuracy of a cascade forest.","PeriodicalId":208148,"journal":{"name":"2022 9th International Conference on Dependable Systems and Their Applications (DSA)","volume":"96 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127229348","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 General Dataset Generator for Industrial Internet of Things Using Multi-sensor Information Fusion","authors":"Mian Wang, Jinlong Sun, Zhiyi Lu, Yu Wang, Yifan Zhang, Jie Zhang, Zhe Zhang, Guan Gui","doi":"10.1109/DSA56465.2022.00034","DOIUrl":"https://doi.org/10.1109/DSA56465.2022.00034","url":null,"abstract":"The development of the fifth-generation (5G) communication technology is promoting the overall improvement of the Industrial Internet of Things (IIoT), and is accelerating the pace of the fourth industrial revolution. There lie problems in the IIoT, such as complex industrial field environment and diverse transmission information. It is difficult for us to collect and process massive real-time data for various devices in a timely, reliable, and efficient manner. In order to investigate and mitigate the above problems, we construct a general IIoT Dataset Generator based on a multi-sensor transmission and fusion architecture. The Dataset Generator has advantages such as good privacy, simple development and strong mobility. As an example, we use sound sensors and accelerometers to collect data for industrial scenes. The architecture is also equipped with a mature data preprocessing and visualization scheme. We demonstrate the effectiveness of the IIoT Dataset Generator and the processing algorithms under the considered scenario.","PeriodicalId":208148,"journal":{"name":"2022 9th International Conference on Dependable Systems and Their Applications (DSA)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128045705","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":"Keynote Speech","authors":"M. Soffa","doi":"10.1109/QSIC.2005.38","DOIUrl":"https://doi.org/10.1109/QSIC.2005.38","url":null,"abstract":"When we study, it is inevitable to look up the dictionary. The traditional searching methods of the Chinese dictionaries are mainly based on the radicals, stroke sequence, or spelling. For those who have used dictionaries would have encountered the frustration of not knwoing how to find specific characters. For example when you are using a dictionary with the radical searching, what are the radicals of “凹, 五, 七, 九”? For dictionaries with the stroke searching method, what are the stroke sequence or the total strokes of “凸, 齲, 龜, 龘”? For dictionaries with the spelling searching method, what are the spelling of “戁, 奅, 尀”?","PeriodicalId":208148,"journal":{"name":"2022 9th International Conference on Dependable Systems and Their Applications (DSA)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129985282","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":"Improved Deep Bi-directional Transformer Keyword Extraction based on Semantic Understanding of News","authors":"Rui Cheng, Haijun Zhang","doi":"10.1109/DSA56465.2022.00110","DOIUrl":"https://doi.org/10.1109/DSA56465.2022.00110","url":null,"abstract":"To address the problems of existing methods such as neglecting semantic information and the lack of diversity in extracted keywords. This paper proposes an improved deep bi-directional transformer model based on semantic understanding of news, combining pre-trained word vectors with K-Means algorithm. After extracting word vectors with rich semantic information based on contextual words through the bert pre-training model, then the K-Means clustering algorithm is used to form clusters of different topics. The extracted keywords semantically highlight the central theme and at the same time can better solve the problem that lack of the diversity of keywords. Experiments show that the improved deep bi-directional transformer model based on news language understanding proposed in this paper has significantly improved in accuracy, recall and F-value compared with RAKE, TF-IDF, LDA, RNN, LSTM models for extracting keywords and word2vec models for static extraction of word vectors.","PeriodicalId":208148,"journal":{"name":"2022 9th International Conference on Dependable Systems and Their Applications (DSA)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132526718","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}
Youwei Huang, Feng Lu, Xiaolong Sang, Bin Hu, Jiachun Tao
{"title":"Precise Epidemic Control based on GeoHash","authors":"Youwei Huang, Feng Lu, Xiaolong Sang, Bin Hu, Jiachun Tao","doi":"10.1109/DSA56465.2022.00156","DOIUrl":"https://doi.org/10.1109/DSA56465.2022.00156","url":null,"abstract":"Coronavirus Disease 2019 (COVID-19) is a highly transmissible and pathogenic coronavirus that emerged in late 2019 and has caused a pandemic of acute respiratory disease. Before vaccines are widely used or the invention of specific medication, many measures have been taken by human beings to prevent the spread of the epidemic. Quarantining infected groups and locking down high-risk regions are common means used by the latest medical experience. As such measures are generally carried out under administrative divisions, issues of imprecise epidemic control and unquantifiable risk warning are exposed gradually. In order to better achieve the purpose of precise epidemic prevention and control, we propose a kind of dynamic block division technology based on GeoHash which can be used to monitor, mark out and control the epidemic regions. By using GeoHash, we divide the earth map into connected dynamic blocks. Dynamic blocks are easily visualized in geographic information systems (GIS) equipped in electronic devices. GeoHash blocks are dynamically overlaid on the map as grids. Each block contains essential epidemic-related data and important features which are concerned by professional medical work. Quantitative analysis of epidemic data is carried out on each block. Our research shows the analysis results can support decision-making, measures formulation, and effectiveness assessment of COVID-19 prevention and control. Such research can be applied not only to COVID-19 but also to other infectious diseases.","PeriodicalId":208148,"journal":{"name":"2022 9th International Conference on Dependable Systems and Their Applications (DSA)","volume":"43 6","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114039847","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":"Forest Fire Spread Prediction Method based on BP Neural Network","authors":"Binhao. Li, Jingwen Zhong, Guoliang Shi, Jie Fang","doi":"10.1109/DSA56465.2022.00134","DOIUrl":"https://doi.org/10.1109/DSA56465.2022.00134","url":null,"abstract":"This paper proposes a method suitable for edge computing to use neural networks to predict the spread of forest fires, aiming to improve the accuracy and efficiency of fire spread prediction, and to achieve edge computing on the drone side with low energy consumption requirements. The BP neural network model is trained by the simulated fire spread raster data obtained by FlamMap, the direction and speed of fire spread are predicted respectively, and according to the Huygens' principle, the vector fire line is obtained by the prediction data fit, and the fire line obtained by FlamMap is compared to verify the accuracy of the method. It can be considered that the same effect can be trained and calculated for the spread of fire through remote sensing data of real fires.","PeriodicalId":208148,"journal":{"name":"2022 9th International Conference on Dependable Systems and Their Applications (DSA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115027645","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}
Mingwei Tang, Zhiwei Xu, Yuhao Qin, Cui Su, Yi Zhu, Feifei Tao, Junhua Ding
{"title":"A Quantitative Study of Impact of Incentive to Quality of Software Reviews","authors":"Mingwei Tang, Zhiwei Xu, Yuhao Qin, Cui Su, Yi Zhu, Feifei Tao, Junhua Ding","doi":"10.1109/DSA56465.2022.00016","DOIUrl":"https://doi.org/10.1109/DSA56465.2022.00016","url":null,"abstract":"Online reviews like product reviews are important references for a potential user to learn the basic information of a product. However, some reviewers were rewarded for writing the reviews, which may impact the objectiveness of the reviews. But on the other hand, the reviews written by reviewers who weren't rewarded could be in low quality. Research study already showed incentivized reviewers may give a higher overall score than non-incentivized reviewers (or called organic) do, but does that pattern also apply to review content? In this paper, a quantitative comparison study is conducted to investigate the differences between the incentivized reviews and organic reviews of software products. Four pairs of comparison including overall score, sentiment preference, correlation, and similarity are performed by using statistical and text mining methods. The results show there is no statistically significant difference between the incentive reviews and organic reviews except the sentiment of total, “Problems and Benefits” and “Summary” part of a review text. The results are unexpected since the reviews collected from the website for reviewing software product already filtered low quality reviews. It demonstrates that the incentivized action might not be necessary to produce biased reviews and it may be an effective way to attract more reviews since the website include more than 75% incentivized reviews. The paper also analyzed the possible reasons from the feature of reviewers' position in a company, a review's indicator, and reviewers' common actions. Based on the analysis, this study suggests that a potential user may pay attention to some quality dimensions of a review to mitigate the bias risk from the reviews.","PeriodicalId":208148,"journal":{"name":"2022 9th International Conference on Dependable Systems and Their Applications (DSA)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128512113","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}
Bojiang Liu, Lijin Wu, Xiaomei Shen, W. He, Xinyu Han
{"title":"Software Vulnerability Mining Technology of Shipbuilding Industry based on Dynamic Binary Code Analysis","authors":"Bojiang Liu, Lijin Wu, Xiaomei Shen, W. He, Xinyu Han","doi":"10.1109/DSA56465.2022.00141","DOIUrl":"https://doi.org/10.1109/DSA56465.2022.00141","url":null,"abstract":"This paper takes the shipbuilding industry software as the research object, uses the dynamic binary code technology to track the instructions to realize the program defect detection, records the instruction flow, data flow and the execution of each instruction on the system state during the program execution at the assembly instruction level. The impact and other information are studied from the dynamic binary code analysis method and the tracking and debugging model. Finally, the advantages and disadvantages of this method are given according to the effect of software vulnerability mining in the shipbuilding industry.","PeriodicalId":208148,"journal":{"name":"2022 9th International Conference on Dependable Systems and Their Applications (DSA)","volume":"4 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129392687","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-based Smart Supply Chain Management","authors":"Emil Lobachev, M. N. Mahmoud, A. Patooghy","doi":"10.1109/DSA56465.2022.00035","DOIUrl":"https://doi.org/10.1109/DSA56465.2022.00035","url":null,"abstract":"A promising solution to improve traditional supply chain security operation is by integrating blockchain technology. Combining the two technologies can result in processes with enhanced transparency, security, and automated administrative activities. This paper investigates the integration of blockchain technology to aid in supply chain management. A framework for tracking the time and location of items through the supply chain is developed using off-the-shelf low-cost components such as radio-frequency identification (RFID) and Raspberry PI 4B. Items can be scanned by RFID tags at any stage through the supply chain and recorded on the blockchain by triggering a smart contract developed on the Ethereum Kovan blockchain. The purpose of our work is to construct, test, and verify a feasible environment, in which the information from an RFID tag can be scanned, uploaded to the blockchain, and read easily by the system operators. Experimental analysis shows that the developed framework is functioning properly and is efficient for practical use.","PeriodicalId":208148,"journal":{"name":"2022 9th International Conference on Dependable Systems and Their Applications (DSA)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133589744","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}