This is a continuing work of Ngo et al, 2018 [1]. They have proposed a mixed binary integer quadratic programming (MIQP) model for cross-functional team selection. The model called Minimum distance to the boundary, MDSB. It is not only specific to team selection but also a generic model for other problems that in form of searching for the best-matched candidate to a predefined target. Ngo et al designed a generic algorithm (GA) for solving MDSB. The GA algorithm is efficient but it also comes with several disadvantages. In this paper, we propose a DCA-based algorithm to solve the MDSB. We compared the proposed algorithm with MIQP-CPLEX and Genetic Algorithm. The numerical results show that our algorithm not only provides the best objective value but also significantly faster than the other compared algorithms.
这是Ngo et al .， 2018[1]的继续工作。他们提出了一个用于跨职能团队选择的混合二进制整数二次规划(MIQP)模型。该模型称为到边界的最小距离MDSB。它不仅是特定于团队选择的，而且也是其他问题的通用模型，其形式是搜索与预定义目标最匹配的候选人。Ngo等设计了一种求解MDSB的通用算法(GA)。遗传算法是有效的，但也有一些缺点。在本文中，我们提出了一种基于dca的MDSB算法。将该算法与MIQP-CPLEX算法和遗传算法进行了比较。数值结果表明，该算法不仅提供了最佳的目标值，而且速度明显快于其他比较算法。
{"title":"DCA-Based Algorithm for Cross-Functional Team Selection","authors":"Ngo Tung Son, Tran Thi Thuy, Bui Ngoc Anh, Tran Van Dinh","doi":"10.1145/3316615.3316645","DOIUrl":"https://doi.org/10.1145/3316615.3316645","url":null,"abstract":"This is a continuing work of Ngo et al, 2018 [1]. They have proposed a mixed binary integer quadratic programming (MIQP) model for cross-functional team selection. The model called Minimum distance to the boundary, MDSB. It is not only specific to team selection but also a generic model for other problems that in form of searching for the best-matched candidate to a predefined target. Ngo et al designed a generic algorithm (GA) for solving MDSB. The GA algorithm is efficient but it also comes with several disadvantages. In this paper, we propose a DCA-based algorithm to solve the MDSB. We compared the proposed algorithm with MIQP-CPLEX and Genetic Algorithm. The numerical results show that our algorithm not only provides the best objective value but also significantly faster than the other compared algorithms.","PeriodicalId":268392,"journal":{"name":"Proceedings of the 2019 8th International Conference on Software and Computer Applications","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123428640","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}
The disease often suffered by Sugar Glider shown in terms of physical condition. However, the illness is often undetected by Sugar Glider owner until it reaches a serious stage and only began to be noticed after consulting with veterinary doctors. Therefore, this expert system allows the owner of Sugar Glider makes a preliminary diagnosis by selecting its symptoms. Selected symptoms will produce result contain diseases and treatment methods. Development of a knowledge base about the symptoms, diagnosis and treatment method for Expert System Apps for Diagnosing Sugar Glider Diseases (SGApps) have involvement and cooperation from one of the lecturer in Faculty of Veterinary Medicine, University Putra Malaysia. Knowledge engineering model has been chosen as methodology while forward chaining as the inference method. Atom software, the Apache server and MySQL database are implemented to develop a web-based system for the administrator. Next, Bootstrap software is used as a development platform for android, MySQL as database and Visual Studio as a compiler. Usability test by doctor suggests that this expert system can produce suitable diagnosis results that match the input symptoms. While usability testing with the owner of Sugar Glider show this android based expert system can provide information on proper care of the Sugar Glider. Finally, the system can allow users to ask any questions directly to the veterinarians.
{"title":"SGApps","authors":"Mimi Rosnida Osman, M. M. Yusof, Hanayanti Hafit","doi":"10.1145/3316615.3316649","DOIUrl":"https://doi.org/10.1145/3316615.3316649","url":null,"abstract":"The disease often suffered by Sugar Glider shown in terms of physical condition. However, the illness is often undetected by Sugar Glider owner until it reaches a serious stage and only began to be noticed after consulting with veterinary doctors. Therefore, this expert system allows the owner of Sugar Glider makes a preliminary diagnosis by selecting its symptoms. Selected symptoms will produce result contain diseases and treatment methods. Development of a knowledge base about the symptoms, diagnosis and treatment method for Expert System Apps for Diagnosing Sugar Glider Diseases (SGApps) have involvement and cooperation from one of the lecturer in Faculty of Veterinary Medicine, University Putra Malaysia. Knowledge engineering model has been chosen as methodology while forward chaining as the inference method. Atom software, the Apache server and MySQL database are implemented to develop a web-based system for the administrator. Next, Bootstrap software is used as a development platform for android, MySQL as database and Visual Studio as a compiler. Usability test by doctor suggests that this expert system can produce suitable diagnosis results that match the input symptoms. While usability testing with the owner of Sugar Glider show this android based expert system can provide information on proper care of the Sugar Glider. Finally, the system can allow users to ask any questions directly to the veterinarians.","PeriodicalId":268392,"journal":{"name":"Proceedings of the 2019 8th International Conference on Software and Computer Applications","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115026645","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}
Human action recognition is an active topic in computer vision. In recent years, tangible results have been shown through deep learning methods; however, at a very high computational cost. They may be suitable for video retrieval or video summarization of a movie or drama, but they are not suitable for the visual surveillance of human action, which should be analyzed in real time. In this study, we propose an action change detection method to reduce the computational cost. On the surveillance camera screen, anomalous actions such as movies and sports are frequently not observed, and simple actions are often repeated. Thus, it is very inefficient to continue to apply high cost action recognition methods on repeated actions. The proposed action change detection method decides whether the previous action of the person is the same as the current action. The action recognition method is applied only when it has determined that the action has changed. The action change detection process is as follows. First, extract the motion history image from the input video and create one-dimensional time-series data. Second, determine the action change using the change of time-series data trend by the threshold. Experiments on the proposed method were performed on the KTH dataset.
{"title":"Low-Level Human Action Change Detection Using the Motion History Image","authors":"Yohwan Noh, Dohoon Lee","doi":"10.1145/3316615.3316725","DOIUrl":"https://doi.org/10.1145/3316615.3316725","url":null,"abstract":"Human action recognition is an active topic in computer vision. In recent years, tangible results have been shown through deep learning methods; however, at a very high computational cost. They may be suitable for video retrieval or video summarization of a movie or drama, but they are not suitable for the visual surveillance of human action, which should be analyzed in real time. In this study, we propose an action change detection method to reduce the computational cost. On the surveillance camera screen, anomalous actions such as movies and sports are frequently not observed, and simple actions are often repeated. Thus, it is very inefficient to continue to apply high cost action recognition methods on repeated actions. The proposed action change detection method decides whether the previous action of the person is the same as the current action. The action recognition method is applied only when it has determined that the action has changed. The action change detection process is as follows. First, extract the motion history image from the input video and create one-dimensional time-series data. Second, determine the action change using the change of time-series data trend by the threshold. Experiments on the proposed method were performed on the KTH dataset.","PeriodicalId":268392,"journal":{"name":"Proceedings of the 2019 8th International Conference on Software and Computer Applications","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127505042","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}
Sim Liew Fong, Amir Ariff Azham bin Abu Bakar, F. Y. Ahmed, A. Jamal
The toll collection system in Malaysia has been one of the causes of traffic jams throughout major highways. One of the reasons for this is due to the fact that users need to either stop their car or slow down to pay for their toll fees. With the advancement of technology over the years, in particular, Radio-Frequency Identification (RFID), we can expect a faster reading time / response time by the device. By adapting RFID into toll collection system, there will be no need for boom barriers. While it is true that boom barriers avoid defaulters from using the toll, boom barriers also slow down the flow of traffic during peak hours. This project will provide a proof of concept by using a much weaker form of RFID to show that it is viable. The methodology that will be used for this particular project is Agile Unified Process (AUP).
{"title":"Smart Transportation System Using RFID","authors":"Sim Liew Fong, Amir Ariff Azham bin Abu Bakar, F. Y. Ahmed, A. Jamal","doi":"10.1145/3316615.3316719","DOIUrl":"https://doi.org/10.1145/3316615.3316719","url":null,"abstract":"The toll collection system in Malaysia has been one of the causes of traffic jams throughout major highways. One of the reasons for this is due to the fact that users need to either stop their car or slow down to pay for their toll fees. With the advancement of technology over the years, in particular, Radio-Frequency Identification (RFID), we can expect a faster reading time / response time by the device. By adapting RFID into toll collection system, there will be no need for boom barriers. While it is true that boom barriers avoid defaulters from using the toll, boom barriers also slow down the flow of traffic during peak hours. This project will provide a proof of concept by using a much weaker form of RFID to show that it is viable. The methodology that will be used for this particular project is Agile Unified Process (AUP).","PeriodicalId":268392,"journal":{"name":"Proceedings of the 2019 8th International Conference on Software and Computer Applications","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126748696","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}
Breast cancer is one of serious diseases that affect mainly woman and late diagnosis can lead to death. However early diagnosis increases survivability significantly, therefore making it very important. There are different diagnosis techniques for early detection of breast cancer. Breast tissue samples analyzed under microscope is considered reliable way to diagnose breast cancer. Automated classification techniques are so popular in many areas in order to reduce human dependency considering third world countries. Our purpose is to determine if sample is malignant or benign in automated manner. Many algorithms are studied so far in medical area along with other areas. However, algorithms are generally too complex even for simple tasks. We propose a simple algorithm that can differentiate cancerous and non-cancerous samples from breast tissue in automated manner. The images were taken from Near East University Hospital which is consisted of 50 cancerous and 100 healthy images. Total of 150 images were correctly differentiated through our algorithm.
{"title":"Segmentation of Microscopic Breast Cancer Images for Cancer Detection","authors":"Hamit Altıparmak, Fatih Veysel Nurçin","doi":"10.1145/3316615.3316695","DOIUrl":"https://doi.org/10.1145/3316615.3316695","url":null,"abstract":"Breast cancer is one of serious diseases that affect mainly woman and late diagnosis can lead to death. However early diagnosis increases survivability significantly, therefore making it very important. There are different diagnosis techniques for early detection of breast cancer. Breast tissue samples analyzed under microscope is considered reliable way to diagnose breast cancer. Automated classification techniques are so popular in many areas in order to reduce human dependency considering third world countries. Our purpose is to determine if sample is malignant or benign in automated manner. Many algorithms are studied so far in medical area along with other areas. However, algorithms are generally too complex even for simple tasks. We propose a simple algorithm that can differentiate cancerous and non-cancerous samples from breast tissue in automated manner. The images were taken from Near East University Hospital which is consisted of 50 cancerous and 100 healthy images. Total of 150 images were correctly differentiated through our algorithm.","PeriodicalId":268392,"journal":{"name":"Proceedings of the 2019 8th International Conference on Software and Computer Applications","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116826424","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}
In recent years, the importance of the Internet in our personal as well as our professional lives cannot be overstated as can be observed from the immense increase of its users. It therefore comes as no surprise that a lot of businesses are being carried out over the internet. It brings along privacy threats to the data and information of an organization. Data mining is the processing of analyze larger data in order to discover patterns and analyze hidden data concurring to distinctive sights for categorize into convenient information which is collected and assembled in common areas and other information necessities to eventually cut costs and increase revenue. In fact, the data mining has emerged as a significant technology for gaining knowledge from vast quantities of data. However, there was been growing concern that use of this technology is violating individual privacy. This tool aims to find useful patterns from large amount of data using by mining algorithms and approaches. The analysis of privacy preserving data mining (PPDM) algorithms should consider the effects of these algorithms in mining the results as well as in preserving privacy. Therefore, the success of privacy preserving data mining algorithms is measured in term of its performances, data utility, level of uncertainty, data anonymization, data randomization and so on based on data mining techniques and approaches are presented in this paper to analyze.
{"title":"A Survey on Privacy Preserving Data Mining Approaches and Techniques","authors":"M. M. Siraj, Nurul Adibah Rahmat, M. Din","doi":"10.1145/3316615.3316632","DOIUrl":"https://doi.org/10.1145/3316615.3316632","url":null,"abstract":"In recent years, the importance of the Internet in our personal as well as our professional lives cannot be overstated as can be observed from the immense increase of its users. It therefore comes as no surprise that a lot of businesses are being carried out over the internet. It brings along privacy threats to the data and information of an organization. Data mining is the processing of analyze larger data in order to discover patterns and analyze hidden data concurring to distinctive sights for categorize into convenient information which is collected and assembled in common areas and other information necessities to eventually cut costs and increase revenue. In fact, the data mining has emerged as a significant technology for gaining knowledge from vast quantities of data. However, there was been growing concern that use of this technology is violating individual privacy. This tool aims to find useful patterns from large amount of data using by mining algorithms and approaches. The analysis of privacy preserving data mining (PPDM) algorithms should consider the effects of these algorithms in mining the results as well as in preserving privacy. Therefore, the success of privacy preserving data mining algorithms is measured in term of its performances, data utility, level of uncertainty, data anonymization, data randomization and so on based on data mining techniques and approaches are presented in this paper to analyze.","PeriodicalId":268392,"journal":{"name":"Proceedings of the 2019 8th International Conference on Software and Computer Applications","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116874056","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}
Mobile application that is available in Android operating system can do many functions such as access to the internet wirelessly, take digital photos, or even locate itself using Global Positioning System. Smart City Bus Application is an application that assist users in providing public buses' information such as bus route view on map, quick response (QR) code payment, etc. This paper however will discuss about the results from system testing and passengers' satisfaction view of each of the system's functions. System testing was performed using black-box method by sorting to project's objectives. The result from system testing is all positive meaning it is performed as expected from given input. In the other hand, acceptance testing was conducted by giving out the application to get evaluated by selected people that uses bus frequently. After testing, questionnaire where given to score each system's feature scaling from 1 to 5 as "Not Satisfy" and "Very Satisfy" respectively. In the end of the questionnaire, system's overall score was asked and the result is mostly positive.
{"title":"Smart City Bus Application with Quick Response (QR) Code Payment","authors":"Sim Liew Fong, D. Yung, F. Y. Ahmed, A. Jamal","doi":"10.1145/3316615.3316718","DOIUrl":"https://doi.org/10.1145/3316615.3316718","url":null,"abstract":"Mobile application that is available in Android operating system can do many functions such as access to the internet wirelessly, take digital photos, or even locate itself using Global Positioning System. Smart City Bus Application is an application that assist users in providing public buses' information such as bus route view on map, quick response (QR) code payment, etc. This paper however will discuss about the results from system testing and passengers' satisfaction view of each of the system's functions. System testing was performed using black-box method by sorting to project's objectives. The result from system testing is all positive meaning it is performed as expected from given input. In the other hand, acceptance testing was conducted by giving out the application to get evaluated by selected people that uses bus frequently. After testing, questionnaire where given to score each system's feature scaling from 1 to 5 as \"Not Satisfy\" and \"Very Satisfy\" respectively. In the end of the questionnaire, system's overall score was asked and the result is mostly positive.","PeriodicalId":268392,"journal":{"name":"Proceedings of the 2019 8th International Conference on Software and Computer Applications","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121903824","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}
Mahmoud Mohammad Ahmad Ibrahim, Sharifah Mashita Syed-Mohamad, M. Husin
DevOps is an intermarriage between developmental practices and operational modalities. The methodology employs the practices of continuous integration and delivery and places the deployment pipeline as the main requirement to automate, deliver and operate software in a robust way, without compromising on the quality in the software development process. Over time, many systems and tools have been developed to implement the deployment pipeline and support the continuous delivery process. A pipeline splits the process of software delivery into various stages. Each stage is designed to verify the quality of new features from a new perspective to attest to the functionality and prevent either small or big errors from impacting the end users. The pipeline must provide a response and feedback loop to the concerned team and provide a window into the flow of changes that takes place. However, there is no clear rule to define what goes into a pipeline. This paper reviews the challenges of quality assurance of DevOps and provides tentative recommendations to deal with quality issues. Our proposed pipeline with analytic features is expected to provide accurate metrics on a real-time basis.
{"title":"Managing Quality Assurance Challenges of DevOps through Analytics","authors":"Mahmoud Mohammad Ahmad Ibrahim, Sharifah Mashita Syed-Mohamad, M. Husin","doi":"10.1145/3316615.3316670","DOIUrl":"https://doi.org/10.1145/3316615.3316670","url":null,"abstract":"DevOps is an intermarriage between developmental practices and operational modalities. The methodology employs the practices of continuous integration and delivery and places the deployment pipeline as the main requirement to automate, deliver and operate software in a robust way, without compromising on the quality in the software development process. Over time, many systems and tools have been developed to implement the deployment pipeline and support the continuous delivery process. A pipeline splits the process of software delivery into various stages. Each stage is designed to verify the quality of new features from a new perspective to attest to the functionality and prevent either small or big errors from impacting the end users. The pipeline must provide a response and feedback loop to the concerned team and provide a window into the flow of changes that takes place. However, there is no clear rule to define what goes into a pipeline. This paper reviews the challenges of quality assurance of DevOps and provides tentative recommendations to deal with quality issues. Our proposed pipeline with analytic features is expected to provide accurate metrics on a real-time basis.","PeriodicalId":268392,"journal":{"name":"Proceedings of the 2019 8th International Conference on Software and Computer Applications","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130346165","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}
Xinni Liu, Fengrong Han, K. Ghazali, I. Mohamed, Yue Zhao
Effectively analysis of remote-sensing images is very important in many practical applications, such as urban planning, geospatial object detection, military monitoring, vegetation mapping and precision agriculture. Recently, convolutional neural network based deep learning algorithm has achieved a series of breakthrough research results in the fields of objective detection, image semantic segmentation and image classification, etc. Their powerful feature learning capabilities have attracted more attention and have important research value. In this article, firstly we have summarized the basic structure and several classical convolutional neural network architectures. Secondly, the recent research problems on convolutional neural network are discussed. Later, we summarized the latest research results in convolutional neural network based remote sensing fields. Finally, the conclusion has made on the basis of current issue on convolutional neural networks and the future development direction.
{"title":"A review of Convolutional Neural Networks in Remote Sensing Image","authors":"Xinni Liu, Fengrong Han, K. Ghazali, I. Mohamed, Yue Zhao","doi":"10.1145/3316615.3316712","DOIUrl":"https://doi.org/10.1145/3316615.3316712","url":null,"abstract":"Effectively analysis of remote-sensing images is very important in many practical applications, such as urban planning, geospatial object detection, military monitoring, vegetation mapping and precision agriculture. Recently, convolutional neural network based deep learning algorithm has achieved a series of breakthrough research results in the fields of objective detection, image semantic segmentation and image classification, etc. Their powerful feature learning capabilities have attracted more attention and have important research value. In this article, firstly we have summarized the basic structure and several classical convolutional neural network architectures. Secondly, the recent research problems on convolutional neural network are discussed. Later, we summarized the latest research results in convolutional neural network based remote sensing fields. Finally, the conclusion has made on the basis of current issue on convolutional neural networks and the future development direction.","PeriodicalId":268392,"journal":{"name":"Proceedings of the 2019 8th International Conference on Software and Computer Applications","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129635892","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}
Network-based Intrusion Detection System (IDS) is gaining wide attention from the research community since the past decades. While having a precise classification model in separating the normal and malicious network traffics is still remain as the ultimate goal, the privacy protection for network traffic database cannot be ignore as well. The impetuous ignorance of database privacy will continue to restrain governments, organisations and individuals in releasing the real and ontological network traces. The common solution to tackle this matter is anonymising the database through the statistical approach. Anonymising can be referred to masking, hiding or removing certain sensitive information from the database. Thus, this will be subsequently resulting in information loss. In this paper, a truncation method is explored to preserve the sensitive information of the network traffic database (i.e. IP addresses). The truncated database is then tested with 10 machine learning classifiers from Weka. We tested four different options of IP address truncation against the 6 percent of GureKDDCup dataset.
{"title":"Privacy Preserving of IP Address through Truncation Method in Network-based Intrusion Detection System","authors":"Yee Jian Chew, S. Ooi, Kok-Seng Wong, Y. Pang","doi":"10.1145/3316615.3316626","DOIUrl":"https://doi.org/10.1145/3316615.3316626","url":null,"abstract":"Network-based Intrusion Detection System (IDS) is gaining wide attention from the research community since the past decades. While having a precise classification model in separating the normal and malicious network traffics is still remain as the ultimate goal, the privacy protection for network traffic database cannot be ignore as well. The impetuous ignorance of database privacy will continue to restrain governments, organisations and individuals in releasing the real and ontological network traces. The common solution to tackle this matter is anonymising the database through the statistical approach. Anonymising can be referred to masking, hiding or removing certain sensitive information from the database. Thus, this will be subsequently resulting in information loss. In this paper, a truncation method is explored to preserve the sensitive information of the network traffic database (i.e. IP addresses). The truncated database is then tested with 10 machine learning classifiers from Weka. We tested four different options of IP address truncation against the 6 percent of GureKDDCup dataset.","PeriodicalId":268392,"journal":{"name":"Proceedings of the 2019 8th International Conference on Software and Computer Applications","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129795351","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：