Subhajit Pramanick, Gurram Joseph Spourgeon, K. Raj, P. Mandal
In this paper, we study the line formation problem using n oblivious point mobile robots located on distinct positions on the Euclidean plane. We assume that the robots agree on one coordinate axis. Robots operate in Look-Compute-Move (LCM) cycles and any two robots can see each other only if there is no robot present on the line segment joining them. Our aim is to solve the line formation problem even if some robots become faulty before achieving the goal. The robots cannot move anymore once they become faulty. We present a fault-tolerant distributed algorithm for line formation under y-axis agreement which runs in O(n) epochs in semi-synchronous setting. The same algorithm runs in D/ymin epochs in asynchronous setting, where D is the vertical distance between the farthest robots along the y-axis and ymin is the minimum non-zero vertical distance traveled by a robot in each LCM cycle.
{"title":"Asynchronous Line Formation in Presence of Faulty Robots","authors":"Subhajit Pramanick, Gurram Joseph Spourgeon, K. Raj, P. Mandal","doi":"10.1145/3569551.3569553","DOIUrl":"https://doi.org/10.1145/3569551.3569553","url":null,"abstract":"In this paper, we study the line formation problem using n oblivious point mobile robots located on distinct positions on the Euclidean plane. We assume that the robots agree on one coordinate axis. Robots operate in Look-Compute-Move (LCM) cycles and any two robots can see each other only if there is no robot present on the line segment joining them. Our aim is to solve the line formation problem even if some robots become faulty before achieving the goal. The robots cannot move anymore once they become faulty. We present a fault-tolerant distributed algorithm for line formation under y-axis agreement which runs in O(n) epochs in semi-synchronous setting. The same algorithm runs in D/ymin epochs in asynchronous setting, where D is the vertical distance between the farthest robots along the y-axis and ymin is the minimum non-zero vertical distance traveled by a robot in each LCM cycle.","PeriodicalId":177068,"journal":{"name":"Proceedings of the 9th International Conference on Networking, Systems and Security","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115605914","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}
Md. Harunur Rashid Bhuiyan, Muhammad Tafsirul Islam, Nazmul Islam, Mynul Islam, Anupom Mondol, Tarik Reza Toha, Shaikh Mohammad Mominul Alam
The textile sector is one of the vital driving forces in the economy of south Asian countries like Bangladesh, India, Pakistan, etc. However, most of the textile industries suffer from frequent machinery faults everyday which reduces their productivity, which in terms reduces their profit. Existing systems for detecting the faults in textile machinery fails to find a remedy to this problem due to several limitations. Among them, sound based and vibration based fault detection systems are based on prototype machinery and has smaller data set to detect machinery fault properly. The fabric defect based, machine learning based approaches only detect machinery fault after fabric has become already defected. To remedy these limitations, in this paper, we propose a sound based fault detection system consisting of trained machine learning model from large data set that can detect machinery fault in textile industry. We use a sound sensor to measure the sound signal of the machine. We artificially create three real faults in the experimented machine and measure the sound signal during the faults. Next, we conduct Fast Fourier Analysis derive sound frequency and statistical analysis to derive different statistical features from the prepared data set. From these two analysis, we determine if the sound frequency and amplitude changes during the fault. After that, we feed the data set to ten machine learning algorithms. Finally, we evaluate our trained machine leaning models through ten fold cross validation to determine the precision, recall, and F1 score. We find the highest F1 of 57.7% in Nearest Centroid Algorithm.
{"title":"Sound-Based Fault Detection For Textile Machinery","authors":"Md. Harunur Rashid Bhuiyan, Muhammad Tafsirul Islam, Nazmul Islam, Mynul Islam, Anupom Mondol, Tarik Reza Toha, Shaikh Mohammad Mominul Alam","doi":"10.1145/3569551.3569557","DOIUrl":"https://doi.org/10.1145/3569551.3569557","url":null,"abstract":"The textile sector is one of the vital driving forces in the economy of south Asian countries like Bangladesh, India, Pakistan, etc. However, most of the textile industries suffer from frequent machinery faults everyday which reduces their productivity, which in terms reduces their profit. Existing systems for detecting the faults in textile machinery fails to find a remedy to this problem due to several limitations. Among them, sound based and vibration based fault detection systems are based on prototype machinery and has smaller data set to detect machinery fault properly. The fabric defect based, machine learning based approaches only detect machinery fault after fabric has become already defected. To remedy these limitations, in this paper, we propose a sound based fault detection system consisting of trained machine learning model from large data set that can detect machinery fault in textile industry. We use a sound sensor to measure the sound signal of the machine. We artificially create three real faults in the experimented machine and measure the sound signal during the faults. Next, we conduct Fast Fourier Analysis derive sound frequency and statistical analysis to derive different statistical features from the prepared data set. From these two analysis, we determine if the sound frequency and amplitude changes during the fault. After that, we feed the data set to ten machine learning algorithms. Finally, we evaluate our trained machine leaning models through ten fold cross validation to determine the precision, recall, and F1 score. We find the highest F1 of 57.7% in Nearest Centroid Algorithm.","PeriodicalId":177068,"journal":{"name":"Proceedings of the 9th International Conference on Networking, Systems and Security","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126288788","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}
Mohammad Shihab Mustafa, Jannatul Ferdaus Khan Lisa, J. Mukta
Abstract—Nowadays, women face imminent risk of sexual harassment, rape and molestation in the streets as male predators roam around in search of their potential targets. In this precarious scenario, women needs to be protected in the street for their safety. To address these challenges, in this paper, we propose a wearable device that will protect and enhance the safety of women. This goal is achieved by analyzing the user’s pulse rate and oxygen measurements and updating them on the Blynk IoT web server. The user’s pulse-rate and blood oxygen saturation is determined by acquiring raw heart-rate and oxygen values from a pulse oximeter and oxygen sensor installed at the heart of the device. Real-time monitoring of user data is achieved by transferring sensor data to the Blynk IoT web server. This wireless device is specifically programmed to continuously monitor the user’s pulse-rate and oxygen values and react in case of a danger situation. It does so by detecting the abnormal pulse-rate and oxygen values, after which it sends the alert text message along with the location and live video streaming to the guardian’s mobile device via the Tasker app. Meanwhile, the alarm starts ringing. Besides, we validate our system architecture using different real time test cases. Moreover, we present a comparison of our proposed architecture with existing literature’s.
{"title":"Design and Implementation of Wireless IoT Device for Women’s Safety","authors":"Mohammad Shihab Mustafa, Jannatul Ferdaus Khan Lisa, J. Mukta","doi":"10.1145/3569551.3569559","DOIUrl":"https://doi.org/10.1145/3569551.3569559","url":null,"abstract":"Abstract—Nowadays, women face imminent risk of sexual harassment, rape and molestation in the streets as male predators roam around in search of their potential targets. In this precarious scenario, women needs to be protected in the street for their safety. To address these challenges, in this paper, we propose a wearable device that will protect and enhance the safety of women. This goal is achieved by analyzing the user’s pulse rate and oxygen measurements and updating them on the Blynk IoT web server. The user’s pulse-rate and blood oxygen saturation is determined by acquiring raw heart-rate and oxygen values from a pulse oximeter and oxygen sensor installed at the heart of the device. Real-time monitoring of user data is achieved by transferring sensor data to the Blynk IoT web server. This wireless device is specifically programmed to continuously monitor the user’s pulse-rate and oxygen values and react in case of a danger situation. It does so by detecting the abnormal pulse-rate and oxygen values, after which it sends the alert text message along with the location and live video streaming to the guardian’s mobile device via the Tasker app. Meanwhile, the alarm starts ringing. Besides, we validate our system architecture using different real time test cases. Moreover, we present a comparison of our proposed architecture with existing literature’s.","PeriodicalId":177068,"journal":{"name":"Proceedings of the 9th International Conference on Networking, Systems and Security","volume":"8 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125659430","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}
Hospitals or Health organizations collect data from patients and store it in databases. The data are scattered in different locations and significant to share from remote places for serving quality treatment and urgent decisions. Any data alternation while transmitting through the transmission channel may cause security issues like data integrity. Data integrity is essential because any alteration of data can hamper medical diagnoses by losing sensitive data. Watermarking could be a practical approach for ensuring such data security with a lower computational cost. Various strategies of watermarking were used to secure health data, especially images. However, watermarking for patient text data has been difficult due to the availability of the right techniques. Therefore, this paper introduces a new watermarking strategy to share patient text from distributed databases. We use the prescription data for testing the proposed system. The experimental results indicate that the method outperforms the existing method against intended attacks.
{"title":"A Watermarking Approach to Communicate Patient Data Securely from Distributed Sources","authors":"Subrata Kumar Das, Mohammad Zahidur Rahman","doi":"10.1145/3569551.3569552","DOIUrl":"https://doi.org/10.1145/3569551.3569552","url":null,"abstract":"Hospitals or Health organizations collect data from patients and store it in databases. The data are scattered in different locations and significant to share from remote places for serving quality treatment and urgent decisions. Any data alternation while transmitting through the transmission channel may cause security issues like data integrity. Data integrity is essential because any alteration of data can hamper medical diagnoses by losing sensitive data. Watermarking could be a practical approach for ensuring such data security with a lower computational cost. Various strategies of watermarking were used to secure health data, especially images. However, watermarking for patient text data has been difficult due to the availability of the right techniques. Therefore, this paper introduces a new watermarking strategy to share patient text from distributed databases. We use the prescription data for testing the proposed system. The experimental results indicate that the method outperforms the existing method against intended attacks.","PeriodicalId":177068,"journal":{"name":"Proceedings of the 9th International Conference on Networking, Systems and Security","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123163113","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}
Md. Sohel Aman Khan, Ahmad Rahman Farabi, Anindya Iqbal
Firebase is the leading Platform-as-a-Service (PaaS) solution in the application development industry. It is globally used by millions of mobile applications and websites. Being a very popular and robust development platform, Firebase has introduced and developed many features and components over the years. Various services and modules are being added to the platform. So, the developers who use Firebase in their applications, need to have versatile knowledge of the platform. It is difficult to acquire an overview of the trends and discussions of any vast and dynamic platform such as Firebase. Therefore, learners, enthusiasts, and often developers have to put in a lot of effort to figure out topics they should explore and focus on. As a large number of application developers frequently use it and engage in various discussions about it in popular community discussion forums for developers, it has become a very promising source for identifying the topics and trends related to Firebase. Stack Overflow is the most popular community for developers’ discussions. It has grown to be a vast ocean of knowledge to explore. In this study, a systematic approach is followed to explore, extract, and analyze Stack Overflow discussions on Firebase to present an overview of the platform. Natural language processing and machine learning methods were used for extracting information from Stack Overflow data. Information collected was reviewed, analyzed, and compiled into this paper by the research group who have practical experiences in the Firebase platform and other relevant software engineering fields.
{"title":"What Do Firebase Developers Discuss About? An Empirical Study on Stack Overflow Posts","authors":"Md. Sohel Aman Khan, Ahmad Rahman Farabi, Anindya Iqbal","doi":"10.1145/3569551.3569558","DOIUrl":"https://doi.org/10.1145/3569551.3569558","url":null,"abstract":"Firebase is the leading Platform-as-a-Service (PaaS) solution in the application development industry. It is globally used by millions of mobile applications and websites. Being a very popular and robust development platform, Firebase has introduced and developed many features and components over the years. Various services and modules are being added to the platform. So, the developers who use Firebase in their applications, need to have versatile knowledge of the platform. It is difficult to acquire an overview of the trends and discussions of any vast and dynamic platform such as Firebase. Therefore, learners, enthusiasts, and often developers have to put in a lot of effort to figure out topics they should explore and focus on. As a large number of application developers frequently use it and engage in various discussions about it in popular community discussion forums for developers, it has become a very promising source for identifying the topics and trends related to Firebase. Stack Overflow is the most popular community for developers’ discussions. It has grown to be a vast ocean of knowledge to explore. In this study, a systematic approach is followed to explore, extract, and analyze Stack Overflow discussions on Firebase to present an overview of the platform. Natural language processing and machine learning methods were used for extracting information from Stack Overflow data. Information collected was reviewed, analyzed, and compiled into this paper by the research group who have practical experiences in the Firebase platform and other relevant software engineering fields.","PeriodicalId":177068,"journal":{"name":"Proceedings of the 9th International Conference on Networking, Systems and Security","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117175546","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}
Recommendation systems are vulnerable to injection attacks by malicious users due to their fundamental openness. One of the vulnerabilities is the fake co-visitation injection attack, which significantly impacts recommendation systems since it modifies the system according to the attacker’s wishes. To date, the detection of co-visitation injection attacks is challenging as: (1) the choice of attribute representation of nodes is hard, (2) practical evidence for analyzing and detecting anomalies in real-world data is insufficient, (3) it is challenging to filter between the original and injected co-visitation data in terms of node behaviors. This paper investigates a unified detection framework that combines attribute and network structure information synergistically to detect outlier nodes based on CUR decomposition and residual analysis. At first, co-visitation graphs are constructed using association rules, and attribute representations of their nodes are developed. Then, both attributes and network structure information are blended in order to identify suspicious nodes. Extensive experiments on both synthetic and real-world dataset exhibit the efficacy of the proposed detection approach compared to other state-of-the-art approaches. The experimental results show that the detection performance can improve by up to 50% for co-visitation injection attacks over the baselines in terms of false alarm rate (FAR) while keeping the highest detection rate (DR).
{"title":"Detecting Fake Co-visitation Injection Attack in Graph-based Recommendation Systems","authors":"Tropa Mahmood, Muhammad Abdullah Adnan","doi":"10.1145/3569551.3569556","DOIUrl":"https://doi.org/10.1145/3569551.3569556","url":null,"abstract":"Recommendation systems are vulnerable to injection attacks by malicious users due to their fundamental openness. One of the vulnerabilities is the fake co-visitation injection attack, which significantly impacts recommendation systems since it modifies the system according to the attacker’s wishes. To date, the detection of co-visitation injection attacks is challenging as: (1) the choice of attribute representation of nodes is hard, (2) practical evidence for analyzing and detecting anomalies in real-world data is insufficient, (3) it is challenging to filter between the original and injected co-visitation data in terms of node behaviors. This paper investigates a unified detection framework that combines attribute and network structure information synergistically to detect outlier nodes based on CUR decomposition and residual analysis. At first, co-visitation graphs are constructed using association rules, and attribute representations of their nodes are developed. Then, both attributes and network structure information are blended in order to identify suspicious nodes. Extensive experiments on both synthetic and real-world dataset exhibit the efficacy of the proposed detection approach compared to other state-of-the-art approaches. The experimental results show that the detection performance can improve by up to 50% for co-visitation injection attacks over the baselines in terms of false alarm rate (FAR) while keeping the highest detection rate (DR).","PeriodicalId":177068,"journal":{"name":"Proceedings of the 9th International Conference on Networking, Systems and Security","volume":"28 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116107410","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}
Farabi Fardin Khan, Nafis Mohaimin Hossain, Md. Nazrul Huda Shanto, Sad Bin Anwar, Jannatun Noor
Cloud computing has gained noticeable popularity due to its ability to radically improve computing power through the application of virtual machines. In this era of the internet, however, security threats are increasing and it is costing many businesses. The seemingly legitimate traffic of these application-level attacks renders the previous detection and mitigation methods ineffective. These cyber-attacks have grown ever so sophisticated and the detection and mitigation of these attacks has become one of the major concerns of security researchers and cloud service providers all around the globe. In this paper, we propose a resource sharing method to create a universal solution to mitigate DDoS attacks. We use an existing filtering method to track the IP addresses of attackers, then send them to the proxy server and delete unwanted IP packet requests by memory management system. Later, we emulate the blockchain network using 50 Nginx VM servers as a start to show the potential of our proposal. We show that our method can mitigate 66% of attacks with only 50VMs. To maximize the capability of mitigating DDoS attacks of our network, we need to increase the number of VM’s and it may take at least a few dozen developers working years on end to develop. Therefore, the goal of this paper is to lay the foundation on which one day the universal solution will be created.
{"title":"Mitigating DDoS Attacks Using a Resource Sharing Network","authors":"Farabi Fardin Khan, Nafis Mohaimin Hossain, Md. Nazrul Huda Shanto, Sad Bin Anwar, Jannatun Noor","doi":"10.1145/3569551.3569560","DOIUrl":"https://doi.org/10.1145/3569551.3569560","url":null,"abstract":"Cloud computing has gained noticeable popularity due to its ability to radically improve computing power through the application of virtual machines. In this era of the internet, however, security threats are increasing and it is costing many businesses. The seemingly legitimate traffic of these application-level attacks renders the previous detection and mitigation methods ineffective. These cyber-attacks have grown ever so sophisticated and the detection and mitigation of these attacks has become one of the major concerns of security researchers and cloud service providers all around the globe. In this paper, we propose a resource sharing method to create a universal solution to mitigate DDoS attacks. We use an existing filtering method to track the IP addresses of attackers, then send them to the proxy server and delete unwanted IP packet requests by memory management system. Later, we emulate the blockchain network using 50 Nginx VM servers as a start to show the potential of our proposal. We show that our method can mitigate 66% of attacks with only 50VMs. To maximize the capability of mitigating DDoS attacks of our network, we need to increase the number of VM’s and it may take at least a few dozen developers working years on end to develop. Therefore, the goal of this paper is to lay the foundation on which one day the universal solution will be created.","PeriodicalId":177068,"journal":{"name":"Proceedings of the 9th International Conference on Networking, Systems and Security","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115766963","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}
Ishita Haque, Rudaiba Adnin, Sadia Afroz, Faria Huq, Sazan Mahbub, S. Azam, A. A. Islam
Even though emails are identified as a prominent source of exchanging abusive behaviors, very little work has explored abuse over emails. In our accepted paper in NSysS 2021, we explore perceptions of users on types of abuse detection systems for emails, revealing privacy concerns and lack of control in human-moderator-based systems and a noteworthy demand for an automated system. Motivated by the findings, we iteratively develop an automated abuse detection system "Citadel" for emails in two sequential phases and evaluate in both phases - first over 39 participants through in-person demonstrations, and second over 21 participants through a 3-day field study and over 63 participants through a video demonstration. Evaluation results portray efficacy, efficiency, and user acceptance of "Citadel" in detecting and preventing abusive emails.
{"title":"Citadel: An Automated Abuse Detection System to Detect And Prevent Abusive Behaviors over Emails","authors":"Ishita Haque, Rudaiba Adnin, Sadia Afroz, Faria Huq, Sazan Mahbub, S. Azam, A. A. Islam","doi":"10.1145/3569551.3569555","DOIUrl":"https://doi.org/10.1145/3569551.3569555","url":null,"abstract":"Even though emails are identified as a prominent source of exchanging abusive behaviors, very little work has explored abuse over emails. In our accepted paper in NSysS 2021, we explore perceptions of users on types of abuse detection systems for emails, revealing privacy concerns and lack of control in human-moderator-based systems and a noteworthy demand for an automated system. Motivated by the findings, we iteratively develop an automated abuse detection system \"Citadel\" for emails in two sequential phases and evaluate in both phases - first over 39 participants through in-person demonstrations, and second over 21 participants through a 3-day field study and over 63 participants through a video demonstration. Evaluation results portray efficacy, efficiency, and user acceptance of \"Citadel\" in detecting and preventing abusive emails.","PeriodicalId":177068,"journal":{"name":"Proceedings of the 9th International Conference on Networking, Systems and Security","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128796135","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}
Because of the rapid advancement in computer technology, police enforcement agencies are now able to keep enormous databases that contain specific information about crimes. These databases can be utilized to analyze crime patterns, criminal characteristics, and the demographics of both criminals and victims. Through the application of various machine learning algorithms to these datasets, it is possible to generate decision-aid systems that can assist in the conduct of police investigations. When there is a large amount of data accessible, several data-driven deep learning approaches can also be utilized. Within the scope of this investigation, our primary objective is to create a tool that may be utilized during the standard investigative process. To forecast criminal demographic profiles using crime evidence data and victim demographics, we present a deep factorization machine-based DNN architecture. We evaluate the performance of our architecture in comparison to that of traditional machine learning algorithms and deep learning algorithms, and we provide our findings in a comparative study.
{"title":"Cri-Astrologer: Predicting Demography of Involved Criminals based on Historical Data","authors":"Md.Atiqur Rahman, A. A. Islam","doi":"10.1145/3569551.3569561","DOIUrl":"https://doi.org/10.1145/3569551.3569561","url":null,"abstract":"Because of the rapid advancement in computer technology, police enforcement agencies are now able to keep enormous databases that contain specific information about crimes. These databases can be utilized to analyze crime patterns, criminal characteristics, and the demographics of both criminals and victims. Through the application of various machine learning algorithms to these datasets, it is possible to generate decision-aid systems that can assist in the conduct of police investigations. When there is a large amount of data accessible, several data-driven deep learning approaches can also be utilized. Within the scope of this investigation, our primary objective is to create a tool that may be utilized during the standard investigative process. To forecast criminal demographic profiles using crime evidence data and victim demographics, we present a deep factorization machine-based DNN architecture. We evaluate the performance of our architecture in comparison to that of traditional machine learning algorithms and deep learning algorithms, and we provide our findings in a comparative study.","PeriodicalId":177068,"journal":{"name":"Proceedings of the 9th International Conference on Networking, Systems and Security","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129641704","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}
Trajectory User Linking (TUL) is the problem of identifying the user (i.e., his identity) from the trajectories generated by him. Existing works on TUL leverage a single trajectory for identifying a user. We propose a novel problem called Multi-Trajectory User Linking (MTUL), which leverages all available trajectories generated by a particular user to identify him. Thus, MTUL is essentially the generalized TUL problem. This problem has significant applications in Location-Based Services (LBSs) such as personalized route planning and point-of-interests (POI) recommendation, movement anomaly detection, etc. We provide an end-to-end solution to the MTUL problem using sequence embedding and GRU and achieve reasonable accuracy by taking into account the POI type and region information. We consider this work to be an important addition to the TUL research.
{"title":"MTUL: A Novel Approach for Multi-Trajectory User Linking","authors":"Fariha Tabassum Islam, Md. Tareq Mahmood, Mahmuda Naznin","doi":"10.1145/3569551.3569554","DOIUrl":"https://doi.org/10.1145/3569551.3569554","url":null,"abstract":"Trajectory User Linking (TUL) is the problem of identifying the user (i.e., his identity) from the trajectories generated by him. Existing works on TUL leverage a single trajectory for identifying a user. We propose a novel problem called Multi-Trajectory User Linking (MTUL), which leverages all available trajectories generated by a particular user to identify him. Thus, MTUL is essentially the generalized TUL problem. This problem has significant applications in Location-Based Services (LBSs) such as personalized route planning and point-of-interests (POI) recommendation, movement anomaly detection, etc. We provide an end-to-end solution to the MTUL problem using sequence embedding and GRU and achieve reasonable accuracy by taking into account the POI type and region information. We consider this work to be an important addition to the TUL research.","PeriodicalId":177068,"journal":{"name":"Proceedings of the 9th International Conference on Networking, Systems and Security","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124475190","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：