Pub Date : 2022-07-08DOI: 10.1109/CONECCT55679.2022.9865766
S. Valli, K. Abhijith Saralaya
Recommendation system provides the facility to understand a person's taste and find new, desirable content for them automatically based on the pattern between their likes and rating of different items. Recommendation systems are mainly employed in applications such as online market, which works with big data. Performing data mining on big data is a tedious task due to its distributed nature and enormity. There are humanely overwhelming number of items for us to inspect, evaluate and choose from. This poses a huge challenge, since overwhelming the customers with huge catalog of items out of which the major portion of items are unrelated to user preferences.There is an imminent need for a recommendation system that eases the process of choosing products by the user and thereby enriching the user experience. To overcome this problem, a recommendation system that uses multiple ML algorithms, a hybrid version of content based filtering and collaborative item-item filtering algorithm is implemented so as to achieve better accuracy in recommendations. The project is aimed to result in a generic recommendation engine suitable for using with any type of items irrespective of domain and datasets.
{"title":"Generic Recommendation Engine using Hybrid Filtering Model","authors":"S. Valli, K. Abhijith Saralaya","doi":"10.1109/CONECCT55679.2022.9865766","DOIUrl":"https://doi.org/10.1109/CONECCT55679.2022.9865766","url":null,"abstract":"Recommendation system provides the facility to understand a person's taste and find new, desirable content for them automatically based on the pattern between their likes and rating of different items. Recommendation systems are mainly employed in applications such as online market, which works with big data. Performing data mining on big data is a tedious task due to its distributed nature and enormity. There are humanely overwhelming number of items for us to inspect, evaluate and choose from. This poses a huge challenge, since overwhelming the customers with huge catalog of items out of which the major portion of items are unrelated to user preferences.There is an imminent need for a recommendation system that eases the process of choosing products by the user and thereby enriching the user experience. To overcome this problem, a recommendation system that uses multiple ML algorithms, a hybrid version of content based filtering and collaborative item-item filtering algorithm is implemented so as to achieve better accuracy in recommendations. The project is aimed to result in a generic recommendation engine suitable for using with any type of items irrespective of domain and datasets.","PeriodicalId":380005,"journal":{"name":"2022 IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132406248","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}
Pub Date : 2022-07-08DOI: 10.1109/CONECCT55679.2022.9865691
K. Dineshkumar, G. Florence Sudha
Comparators are fundamental blocks in the architectures of analog to digital converters. Due to the requirement of low power and high speed converters, the dynamic comparators are the natural choice. Existing dynamic comparators have issues of higher power consumption and delay. To overcome these drawbacks, a low power dynamic comparator with charge distribution technique is proposed in this paper. The proposed comparator reduces the regeneration time delay with the reduction in the power consumption considerably. The proposed design and simulation is carried out in 180 nm CMOS technology. Results show reduced power consumption of 260 µW and delay of 220 ps with supply voltage of 1.8 V at 0.5 GHz of frequency.
{"title":"Design and Analysis of high speed low power CMOS comparator with charge distribution technique","authors":"K. Dineshkumar, G. Florence Sudha","doi":"10.1109/CONECCT55679.2022.9865691","DOIUrl":"https://doi.org/10.1109/CONECCT55679.2022.9865691","url":null,"abstract":"Comparators are fundamental blocks in the architectures of analog to digital converters. Due to the requirement of low power and high speed converters, the dynamic comparators are the natural choice. Existing dynamic comparators have issues of higher power consumption and delay. To overcome these drawbacks, a low power dynamic comparator with charge distribution technique is proposed in this paper. The proposed comparator reduces the regeneration time delay with the reduction in the power consumption considerably. The proposed design and simulation is carried out in 180 nm CMOS technology. Results show reduced power consumption of 260 µW and delay of 220 ps with supply voltage of 1.8 V at 0.5 GHz of frequency.","PeriodicalId":380005,"journal":{"name":"2022 IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT)","volume":"436 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126116137","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 this paper, we mainly focus on the use of sign language as an optimal means of communication in underground mines. Deep mining takes place in a highly technical and demanding environment, requiring major new solutions and best practices, as well as increased safety regulations, in order to overcome the hurdles and reap significant economic benefits. In this proposed solution, we use the technology of image processing to detect and recognise hand signs and convert them into audio messages which can be communicated to each worker in a wireless and hassle-free manner.
{"title":"Sign Language Recognition and Translation to Speech for Mine Workers using Deep Learning Technologies","authors":"Hridya Dhulipala, Sowmya Hegde, Chaya Hegde, Swetha Gumpena, Geetishree Mishra","doi":"10.1109/CONECCT55679.2022.9865741","DOIUrl":"https://doi.org/10.1109/CONECCT55679.2022.9865741","url":null,"abstract":"In this paper, we mainly focus on the use of sign language as an optimal means of communication in underground mines. Deep mining takes place in a highly technical and demanding environment, requiring major new solutions and best practices, as well as increased safety regulations, in order to overcome the hurdles and reap significant economic benefits. In this proposed solution, we use the technology of image processing to detect and recognise hand signs and convert them into audio messages which can be communicated to each worker in a wireless and hassle-free manner.","PeriodicalId":380005,"journal":{"name":"2022 IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123840587","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}
Pub Date : 2022-07-08DOI: 10.1109/CONECCT55679.2022.9865112
Sridhar R.V.L.N., Chandana R., Shashank Pandey, Prashanth C.U., Umesh S.B., M. S, E. S., Sriram K.V
Laser Induced Plasma Spectroscopy (LIPS) is a promising spectrochemical analytical method for rapid analysis of multi-element samples, and, has become a potential field of both fundamental and exploratory research including the space science in recent times. Although, the LIPS technique is highly versatile, its element detection capability at times is intriguing due to spectral peak overlapping that can hamper the elemental detection accuracy. This paper presents details on executed trade-off simulations and optimization of algorithm parameters that may aid for effective mitigation of spectral overlapping issues of LIPS spectra and precise peak finding. Four pelletized samples were used to acquire spectra in high vacuum (≤ 5x10-6 mbar) environment to mimic space-like conditions.
{"title":"An Automatic Peak Finding and Fitting Aspects of Laser Induced Plasma Spectra acquired in High Vacuum: Tradeoff Simulations and Statistics","authors":"Sridhar R.V.L.N., Chandana R., Shashank Pandey, Prashanth C.U., Umesh S.B., M. S, E. S., Sriram K.V","doi":"10.1109/CONECCT55679.2022.9865112","DOIUrl":"https://doi.org/10.1109/CONECCT55679.2022.9865112","url":null,"abstract":"Laser Induced Plasma Spectroscopy (LIPS) is a promising spectrochemical analytical method for rapid analysis of multi-element samples, and, has become a potential field of both fundamental and exploratory research including the space science in recent times. Although, the LIPS technique is highly versatile, its element detection capability at times is intriguing due to spectral peak overlapping that can hamper the elemental detection accuracy. This paper presents details on executed trade-off simulations and optimization of algorithm parameters that may aid for effective mitigation of spectral overlapping issues of LIPS spectra and precise peak finding. Four pelletized samples were used to acquire spectra in high vacuum (≤ 5x10-6 mbar) environment to mimic space-like conditions.","PeriodicalId":380005,"journal":{"name":"2022 IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125865401","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}
Pub Date : 2022-07-08DOI: 10.1109/CONECCT55679.2022.9865852
Gurleen Kaur, B. Thangaraju
It is estimated that there are about 1.2 million terabytes of data on the internet. This data is increasing every second. This makes the exercise of filtering, aggregating and/or consuming data more and more complex. This work proposes the creation of an Information Bot that facilitates users to subscribe to any kind of information over the web and get it delivered in a structured and defined form via multiple channels like email, notifications, text messages, etc. We leverage the Event based micro-services architecture to achieve this. The flexibility to choose - be it the specific information one would like to subscribe to, or the delivery channel is what makes the information bot framework unique. It can also provide real-time data delivery.
{"title":"Event Driven Micro-services based Information Bot","authors":"Gurleen Kaur, B. Thangaraju","doi":"10.1109/CONECCT55679.2022.9865852","DOIUrl":"https://doi.org/10.1109/CONECCT55679.2022.9865852","url":null,"abstract":"It is estimated that there are about 1.2 million terabytes of data on the internet. This data is increasing every second. This makes the exercise of filtering, aggregating and/or consuming data more and more complex. This work proposes the creation of an Information Bot that facilitates users to subscribe to any kind of information over the web and get it delivered in a structured and defined form via multiple channels like email, notifications, text messages, etc. We leverage the Event based micro-services architecture to achieve this. The flexibility to choose - be it the specific information one would like to subscribe to, or the delivery channel is what makes the information bot framework unique. It can also provide real-time data delivery.","PeriodicalId":380005,"journal":{"name":"2022 IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127176990","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}
Pub Date : 2022-07-08DOI: 10.1109/CONECCT55679.2022.9865765
K. Vaibhav, V. Rc, Shobha K R, Harish Mm, D. S. Murthy, Lakshmi S, M. Ravikanth, Twishi Tyagi
The existing Intelligent Navigation systems for Robotic operations suffer from high-cost requirements of the camera modules or the sensory tracking modules used in the Simultaneous Localization and Mapping (SLAM) technique. The sensor in such systems needs to be replaced with high-end cameras which can provide depth information as well, which further adds to the cost of the system. The depth information is necessary to build 3D maps of the environment for further navigation requirements. This makes it ineffective for everyday in-home applications. To solve this, a system that can use available smartphones to perform sensing operations required for Oriented FAST and Rotated BRIEF-SLAM (ORB SLAM) is proposed. The proposed system performs object detection of common household objects using the YOLO algorithm along with CNN networks.Utilizing a smartphone camera, a point cloud map has been designed using the ORB SLAM algorithm with re-localization, loop closing, and map reuse features. Tested with indoor sequences, the integrated Robot Operating System (ROS) provides exemplary performance in real-time. The targets could be detected using ORB SLAM, and point clouds that display and map the surrounding spaces and explore the unknown environment were created. This system eliminates the need for expensive 3D cameras or depth sensors by providing a cheaper alternative using any monocular camera and performing operations like point cloud mapping, depth mapping, and object detection in real-time.
{"title":"Monocular Cloud Map Generation for Intelligent Navigation","authors":"K. Vaibhav, V. Rc, Shobha K R, Harish Mm, D. S. Murthy, Lakshmi S, M. Ravikanth, Twishi Tyagi","doi":"10.1109/CONECCT55679.2022.9865765","DOIUrl":"https://doi.org/10.1109/CONECCT55679.2022.9865765","url":null,"abstract":"The existing Intelligent Navigation systems for Robotic operations suffer from high-cost requirements of the camera modules or the sensory tracking modules used in the Simultaneous Localization and Mapping (SLAM) technique. The sensor in such systems needs to be replaced with high-end cameras which can provide depth information as well, which further adds to the cost of the system. The depth information is necessary to build 3D maps of the environment for further navigation requirements. This makes it ineffective for everyday in-home applications. To solve this, a system that can use available smartphones to perform sensing operations required for Oriented FAST and Rotated BRIEF-SLAM (ORB SLAM) is proposed. The proposed system performs object detection of common household objects using the YOLO algorithm along with CNN networks.Utilizing a smartphone camera, a point cloud map has been designed using the ORB SLAM algorithm with re-localization, loop closing, and map reuse features. Tested with indoor sequences, the integrated Robot Operating System (ROS) provides exemplary performance in real-time. The targets could be detected using ORB SLAM, and point clouds that display and map the surrounding spaces and explore the unknown environment were created. This system eliminates the need for expensive 3D cameras or depth sensors by providing a cheaper alternative using any monocular camera and performing operations like point cloud mapping, depth mapping, and object detection in real-time.","PeriodicalId":380005,"journal":{"name":"2022 IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129275395","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}
Pub Date : 2022-07-08DOI: 10.1109/CONECCT55679.2022.9865740
Ashutosh Holla B, M. M, Ujjwal Verma, R. Pai
In recent years, the development of robust Intelligent transportation systems (ITS) is tackled across the globe to provide better traffic efficiency by reducing frequent traffic problems. As an application of ITS, vehicle re-identification has gained ample interest in the domain of computer vision and robotics. Convolutional neural network (CNN) based methods are developed to perform vehicle re-identification to address key challenges such as occlusion, illumination change, scale, etc. The advancement of transformers in computer vision has opened an opportunity to explore the re-identification process further to enhance performance. In this paper, a framework is developed to perform the re-identification of vehicles across CCTV cameras. To perform re-identification, the proposed framework fuses the vehicle representation learned using a CNN and a transformer model. The framework is tested on a dataset that contains 81 unique vehicle identities observed across 20 CCTV cameras. From the experiments, the fused vehicle re-identification framework yields an mAP of 61.73% which is significantly better when compared with the standalone CNN or transformer model.
{"title":"Enhanced Vehicle Re-identification for ITS: A Feature Fusion approach using Deep Learning","authors":"Ashutosh Holla B, M. M, Ujjwal Verma, R. Pai","doi":"10.1109/CONECCT55679.2022.9865740","DOIUrl":"https://doi.org/10.1109/CONECCT55679.2022.9865740","url":null,"abstract":"In recent years, the development of robust Intelligent transportation systems (ITS) is tackled across the globe to provide better traffic efficiency by reducing frequent traffic problems. As an application of ITS, vehicle re-identification has gained ample interest in the domain of computer vision and robotics. Convolutional neural network (CNN) based methods are developed to perform vehicle re-identification to address key challenges such as occlusion, illumination change, scale, etc. The advancement of transformers in computer vision has opened an opportunity to explore the re-identification process further to enhance performance. In this paper, a framework is developed to perform the re-identification of vehicles across CCTV cameras. To perform re-identification, the proposed framework fuses the vehicle representation learned using a CNN and a transformer model. The framework is tested on a dataset that contains 81 unique vehicle identities observed across 20 CCTV cameras. From the experiments, the fused vehicle re-identification framework yields an mAP of 61.73% which is significantly better when compared with the standalone CNN or transformer model.","PeriodicalId":380005,"journal":{"name":"2022 IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129942434","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}
Pub Date : 2022-07-08DOI: 10.1109/CONECCT55679.2022.9865115
Mehdi Davoudi, Alireza Keyanfar
There are various computer tools for preparation of electronic-learning materials and each of the produced materials has some limitations such as hardware/software requirements, or communication infrastructures. In addition, there is another limitation of such materials related to the level of user interaction. This paper proposes a method for producing intelligent videos to offer the possibility of interaction between the audience and educational material on the one hand, and can also be played on almost all devices on the other hand In the proposed method, the educational videos are prepared in a hierarchical structure in which at the end of each section, a question will be asked from the user, and according to the answer, the video will be continued to the next level of video in case of positive answer or it will review previous materials
{"title":"An Innovative Approach for Intelligent Educational Materials Preparation Enabling the User Interaction with Video Content","authors":"Mehdi Davoudi, Alireza Keyanfar","doi":"10.1109/CONECCT55679.2022.9865115","DOIUrl":"https://doi.org/10.1109/CONECCT55679.2022.9865115","url":null,"abstract":"There are various computer tools for preparation of electronic-learning materials and each of the produced materials has some limitations such as hardware/software requirements, or communication infrastructures. In addition, there is another limitation of such materials related to the level of user interaction. This paper proposes a method for producing intelligent videos to offer the possibility of interaction between the audience and educational material on the one hand, and can also be played on almost all devices on the other hand In the proposed method, the educational videos are prepared in a hierarchical structure in which at the end of each section, a question will be asked from the user, and according to the answer, the video will be continued to the next level of video in case of positive answer or it will review previous materials","PeriodicalId":380005,"journal":{"name":"2022 IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117157094","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}
Pub Date : 2022-07-08DOI: 10.1109/CONECCT55679.2022.9865750
Shailesh Ghotgalkar, Ashish Vanjari, Han Zhang, Prasanth Viswanathan Pillai, Mihir Mody, K. Rajamanickam, Mohammad Asif Farooqui
The power train in Electric Vehicle (EV) requires the highest level of Automotive Functional Safety Integrity Level (namely ASIL D) system due to the life-critical risk associated with the failure. The development of these systems typically involves the usage of hardware components and software that meets the highest functional safety levels. This can result in a significantly higher cost of development and component compared to a lower functional safety integrity solution. Besides cost, the key challenge of these systems is the rising high performance (RPM and efficiency) requirement for EV motors due to the underlying range and efficiency targets. These goals are difficult to achieve using generic safety-certified MCUs. This paper proposes a system solution using components with different safety integrity levels and software support for system-level safety requirement decomposition. The solution consists of innovative techniques namely optimal decomposition of safety requirements, an intelligent safety-checker for high-performance motor drive, and enabling Freedom From Interference (FFI) due to the mix-criticality of hardware and software components in the system. The proposed solution is implemented on Texas Instruments’ C2000 MCU (F2838x) for motor control and TMS570 MCU for safety augmentation meeting the highest automotive functional safety level i.e. ASIL D assessed by TÜV SÜD. The ASIL decomposition-based safety concept eliminates the need for entire solution redevelopment as well as ability to scaleup motor control performance with a software upgrade to the C2000 MCU (F2838x) without significant changes to the safety architecture.
{"title":"High performance and EV power train system using C2000 MCU for functional safety","authors":"Shailesh Ghotgalkar, Ashish Vanjari, Han Zhang, Prasanth Viswanathan Pillai, Mihir Mody, K. Rajamanickam, Mohammad Asif Farooqui","doi":"10.1109/CONECCT55679.2022.9865750","DOIUrl":"https://doi.org/10.1109/CONECCT55679.2022.9865750","url":null,"abstract":"The power train in Electric Vehicle (EV) requires the highest level of Automotive Functional Safety Integrity Level (namely ASIL D) system due to the life-critical risk associated with the failure. The development of these systems typically involves the usage of hardware components and software that meets the highest functional safety levels. This can result in a significantly higher cost of development and component compared to a lower functional safety integrity solution. Besides cost, the key challenge of these systems is the rising high performance (RPM and efficiency) requirement for EV motors due to the underlying range and efficiency targets. These goals are difficult to achieve using generic safety-certified MCUs. This paper proposes a system solution using components with different safety integrity levels and software support for system-level safety requirement decomposition. The solution consists of innovative techniques namely optimal decomposition of safety requirements, an intelligent safety-checker for high-performance motor drive, and enabling Freedom From Interference (FFI) due to the mix-criticality of hardware and software components in the system. The proposed solution is implemented on Texas Instruments’ C2000 MCU (F2838x) for motor control and TMS570 MCU for safety augmentation meeting the highest automotive functional safety level i.e. ASIL D assessed by TÜV SÜD. The ASIL decomposition-based safety concept eliminates the need for entire solution redevelopment as well as ability to scaleup motor control performance with a software upgrade to the C2000 MCU (F2838x) without significant changes to the safety architecture.","PeriodicalId":380005,"journal":{"name":"2022 IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115629140","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}
Pub Date : 2022-07-08DOI: 10.1109/CONECCT55679.2022.9865682
C. Sowmyarani, L. G. Namya, G. K. Nidhi, P. Ramakanth Kumar
The infrastructure required for data storage and processing has become increasingly feasible, and hence, there has been a massive growth in the field of data acquisition and analysis. This acquired data is published, empowering organizations to make informed data-driven decisions based on previous trends. However, data publishing has led to the compromise of privacy as a result of the release of entity-specific information. Privacy-Preserving Data Publishing [1] can be accomplished by methods such as Data Swapping, Differential Privacy, and the likes of k-Anonymity. k-Anonymity is a well-established method used to protect the privacy of the data published. We propose a clustering-based novel algorithm named SAC or the Score, Arrange, and Cluster Algorithm to preserve privacy based on k-Anonymity. This method outperforms existing methods such as the Mondrian Algorithm by K. LeFevre and the One-pass K-means Algorithm by Jun-Lin Lin from a data quality perspective. SAC can be used to overcome temporal attack across subsequent releases of published data. To measure data quality post anonymization we present a metric that takes into account the relative loss in the information, that occurs while generalizing attribute values.
数据存储和处理所需的基础设施已经变得越来越可行，因此，在数据获取和分析领域有了巨大的增长。这些获得的数据被发布，使组织能够根据以前的趋势做出明智的数据驱动决策。然而，数据发布由于实体特定信息的发布而导致了隐私的妥协。保护隐私的数据发布[1]可以通过数据交换、差分隐私和k-匿名等方法来实现。k-匿名是一种行之有效的方法，用于保护发布数据的隐私。我们提出了一种基于聚类的新算法SAC (Score, Arrange, and Cluster algorithm)来保护基于k-匿名的隐私。该方法在数据质量方面优于K. LeFevre的Mondrian算法和Jun-Lin Lin的One-pass K-means算法等现有方法。SAC可用于克服已发布数据的后续版本之间的时间攻击。为了衡量匿名化后的数据质量，我们提出了一个度量，该度量考虑了在概括属性值时发生的信息的相对损失。
{"title":"Enhanced k-Anonymity model based on clustering to overcome Temporal attack in Privacy Preserving Data Publishing","authors":"C. Sowmyarani, L. G. Namya, G. K. Nidhi, P. Ramakanth Kumar","doi":"10.1109/CONECCT55679.2022.9865682","DOIUrl":"https://doi.org/10.1109/CONECCT55679.2022.9865682","url":null,"abstract":"The infrastructure required for data storage and processing has become increasingly feasible, and hence, there has been a massive growth in the field of data acquisition and analysis. This acquired data is published, empowering organizations to make informed data-driven decisions based on previous trends. However, data publishing has led to the compromise of privacy as a result of the release of entity-specific information. Privacy-Preserving Data Publishing [1] can be accomplished by methods such as Data Swapping, Differential Privacy, and the likes of k-Anonymity. k-Anonymity is a well-established method used to protect the privacy of the data published. We propose a clustering-based novel algorithm named SAC or the Score, Arrange, and Cluster Algorithm to preserve privacy based on k-Anonymity. This method outperforms existing methods such as the Mondrian Algorithm by K. LeFevre and the One-pass K-means Algorithm by Jun-Lin Lin from a data quality perspective. SAC can be used to overcome temporal attack across subsequent releases of published data. To measure data quality post anonymization we present a metric that takes into account the relative loss in the information, that occurs while generalizing attribute values.","PeriodicalId":380005,"journal":{"name":"2022 IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT)","volume":"27 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120876702","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：