Pub Date : 2020-05-01DOI: 10.1109/ZINC50678.2020.9161768
K. Pranav, J. Manikandan
Design and development of autonomous vehicles capable of moving safely on roads by sensing the environment has motivated researchers to focus on design of pedestrian detection systems. Similarly, Convolution Neural Networks (CNN) is considered as one of the preferred image classification algorithms. Most of the papers reported in literature employ standard object detector modules available online for pedestrian detection. Design of a real-time pedestrian detection system using CNN for autonomous vehicles is proposed and the system is designed from scratch without using any standard module available. The performance evaluation of proposed system is carried out using INRIA dataset, PETA–CUHK dataset and realtime video input. The CNN parameters were also tuned to achieve best possible recognition accuracy. Recognition accuracies ranging between 96.73 – 100% is obtained on using the system, based on dataset employed. The results obtained are also compared with the results reported in literature and the system designed can be considered on par with those reported in literature. The proposed real-time pedestrian detection system can also be employed as driver assistance system for non-autonomous vehicles.
{"title":"Design and Evaluation of a Real-time Pedestrian Detection System for Autonomous Vehicles","authors":"K. Pranav, J. Manikandan","doi":"10.1109/ZINC50678.2020.9161768","DOIUrl":"https://doi.org/10.1109/ZINC50678.2020.9161768","url":null,"abstract":"Design and development of autonomous vehicles capable of moving safely on roads by sensing the environment has motivated researchers to focus on design of pedestrian detection systems. Similarly, Convolution Neural Networks (CNN) is considered as one of the preferred image classification algorithms. Most of the papers reported in literature employ standard object detector modules available online for pedestrian detection. Design of a real-time pedestrian detection system using CNN for autonomous vehicles is proposed and the system is designed from scratch without using any standard module available. The performance evaluation of proposed system is carried out using INRIA dataset, PETA–CUHK dataset and realtime video input. The CNN parameters were also tuned to achieve best possible recognition accuracy. Recognition accuracies ranging between 96.73 – 100% is obtained on using the system, based on dataset employed. The results obtained are also compared with the results reported in literature and the system designed can be considered on par with those reported in literature. The proposed real-time pedestrian detection system can also be employed as driver assistance system for non-autonomous vehicles.","PeriodicalId":6731,"journal":{"name":"2020 Zooming Innovation in Consumer Technologies Conference (ZINC)","volume":"58 8 1","pages":"155-159"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85455881","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 : 2020-05-01DOI: 10.1109/ZINC50678.2020.9161811
Tristan Lim
Customer retention is of importance, as the mobile industry experiences an average of 30-35 percent annual churn rate and it costs 5-10 times more to recruit a new customer than to retain an existing one. In this study, we investigate customer churn in a medium size U.S. mobile service operator (telco) with approximately 1 million subscribers. The operator is experiencing about 5% drop off rate every month, which implied that more than half of the company’s customers at the beginning of the year, are gone by the end of the year. The company aims to identify potential churned customers ahead of time and offer them appropriate incentives to entice them to stay. In order to study this, survival analysis was conducted. In this study, nonparametric Kaplan Meier estimator was used to estimated survival probabilities. Key determinants for further investigation were identified using the Walds Test and LogWorth size estimators. Further tests to identify the risk of churn were conducted using the semi-parametric Cox Proportional Hazard model to simultaneously evaluate the effect of covariates on survival and churn risk between the sub-covariates. The study identified the targeting of the top 62% of the customers for optimal benefit, and recommended appropriate actionable insights to implement a loyalty program. Through the understanding of the determinants of customer churning behavior, the prediction of which customers are most likely to leave, and the expected duration of customers who have yet to churn, the company can conduct pertinent marketing and promotional efforts to encourage customers to remain with the company for enhanced profitability. The findings of this study can be applied in supplier convergent triple-or-quad-play services, and form a useful guide to the industry implementation of data analytics survival analysis back-end platform, as part of a larger customer acquisition, development and retention analytics solution in mobile service operators.
{"title":"Applying Survival Analysis for Customer Retention: A U.S. Regional Mobile Service Operator","authors":"Tristan Lim","doi":"10.1109/ZINC50678.2020.9161811","DOIUrl":"https://doi.org/10.1109/ZINC50678.2020.9161811","url":null,"abstract":"Customer retention is of importance, as the mobile industry experiences an average of 30-35 percent annual churn rate and it costs 5-10 times more to recruit a new customer than to retain an existing one. In this study, we investigate customer churn in a medium size U.S. mobile service operator (telco) with approximately 1 million subscribers. The operator is experiencing about 5% drop off rate every month, which implied that more than half of the company’s customers at the beginning of the year, are gone by the end of the year. The company aims to identify potential churned customers ahead of time and offer them appropriate incentives to entice them to stay. In order to study this, survival analysis was conducted. In this study, nonparametric Kaplan Meier estimator was used to estimated survival probabilities. Key determinants for further investigation were identified using the Walds Test and LogWorth size estimators. Further tests to identify the risk of churn were conducted using the semi-parametric Cox Proportional Hazard model to simultaneously evaluate the effect of covariates on survival and churn risk between the sub-covariates. The study identified the targeting of the top 62% of the customers for optimal benefit, and recommended appropriate actionable insights to implement a loyalty program. Through the understanding of the determinants of customer churning behavior, the prediction of which customers are most likely to leave, and the expected duration of customers who have yet to churn, the company can conduct pertinent marketing and promotional efforts to encourage customers to remain with the company for enhanced profitability. The findings of this study can be applied in supplier convergent triple-or-quad-play services, and form a useful guide to the industry implementation of data analytics survival analysis back-end platform, as part of a larger customer acquisition, development and retention analytics solution in mobile service operators.","PeriodicalId":6731,"journal":{"name":"2020 Zooming Innovation in Consumer Technologies Conference (ZINC)","volume":"83 1","pages":"338-342"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83991121","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 : 2020-05-01DOI: 10.1109/ZINC50678.2020.9161815
J. Galic, B. Markovic
In this paper an analysis on the recognition of words from speech database Whi-Spe in normal and whispered phonation, based on the conventional HMM/GMM framework, is presented. The analysis based on multi-style training is performed in the speaker dependent (SD) and speaker independent mode (SI). The analysis showed that a small portion of whisper data in training (10%) is required for the recognition of whisper higher than 90%, for both the SD and SI recognition.
{"title":"The Recognition of Bimodal Produced Speech based on Multi-style Training","authors":"J. Galic, B. Markovic","doi":"10.1109/ZINC50678.2020.9161815","DOIUrl":"https://doi.org/10.1109/ZINC50678.2020.9161815","url":null,"abstract":"In this paper an analysis on the recognition of words from speech database Whi-Spe in normal and whispered phonation, based on the conventional HMM/GMM framework, is presented. The analysis based on multi-style training is performed in the speaker dependent (SD) and speaker independent mode (SI). The analysis showed that a small portion of whisper data in training (10%) is required for the recognition of whisper higher than 90%, for both the SD and SI recognition.","PeriodicalId":6731,"journal":{"name":"2020 Zooming Innovation in Consumer Technologies Conference (ZINC)","volume":"86 1","pages":"11-14"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84010766","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 : 2020-05-01DOI: 10.1109/ZINC50678.2020.9161430
Nursena Baygin, M. Baygin, M. Karakose
Today, thanks to the developing technology, mass production technology is progressing very fast. With these systems, which aim to meet the increasing customer demands correctly, effectively and efficiently, it is aimed to produce customer-specific products. In this method called mass customization, customers can customize the product they demand and create it according to their personal tastes. In this study, the mass customization concept, which is one of the current production technologies, is modeled by using blockchain. In the proposed system, a blockchain-based smart contract was created to bring together the parties and establish a healthy communication. In addition, it is aimed to produce more effective products with the proposed method. By providing a simulation environment for the products to be produced, it is presented to the users' information and a feedback system is created. Thus, a consensus-based production model is being built.
{"title":"DesignChain: A Smart Contract-based Customized Production Model","authors":"Nursena Baygin, M. Baygin, M. Karakose","doi":"10.1109/ZINC50678.2020.9161430","DOIUrl":"https://doi.org/10.1109/ZINC50678.2020.9161430","url":null,"abstract":"Today, thanks to the developing technology, mass production technology is progressing very fast. With these systems, which aim to meet the increasing customer demands correctly, effectively and efficiently, it is aimed to produce customer-specific products. In this method called mass customization, customers can customize the product they demand and create it according to their personal tastes. In this study, the mass customization concept, which is one of the current production technologies, is modeled by using blockchain. In the proposed system, a blockchain-based smart contract was created to bring together the parties and establish a healthy communication. In addition, it is aimed to produce more effective products with the proposed method. By providing a simulation environment for the products to be produced, it is presented to the users' information and a feedback system is created. Thus, a consensus-based production model is being built.","PeriodicalId":6731,"journal":{"name":"2020 Zooming Innovation in Consumer Technologies Conference (ZINC)","volume":"69 1","pages":"138-141"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82963735","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 : 2020-05-01DOI: 10.1109/ZINC50678.2020.9161817
Radenko Banović, Ilija Basěević, M. Popovic, Nemanja Fimic
In the digital television industry today, three broadcast standards are dominant worldwide, Digital Video Broadcasting (DVB), Integrated Service Digital Broadcasting (ISDB), Advanced Television System Committee (ATSC). All of these broadcast standards use Moving Pictures Experts Group - Transport Stream (MPEG-TS) digital container format for transmission through the network. Many broadcasters change the configuration on the head-end to support different applications. Some of them add a timestamp to the beginning of the transport stream and create a new digital container format called Timestamped Transport Stream (TTS). This paper presents one solution of DVB software demultiplexer module adaptation to support TTS.
{"title":"One Solution of DVB Software Demultiplexer Adaptation for Timestamped Transport Stream","authors":"Radenko Banović, Ilija Basěević, M. Popovic, Nemanja Fimic","doi":"10.1109/ZINC50678.2020.9161817","DOIUrl":"https://doi.org/10.1109/ZINC50678.2020.9161817","url":null,"abstract":"In the digital television industry today, three broadcast standards are dominant worldwide, Digital Video Broadcasting (DVB), Integrated Service Digital Broadcasting (ISDB), Advanced Television System Committee (ATSC). All of these broadcast standards use Moving Pictures Experts Group - Transport Stream (MPEG-TS) digital container format for transmission through the network. Many broadcasters change the configuration on the head-end to support different applications. Some of them add a timestamp to the beginning of the transport stream and create a new digital container format called Timestamped Transport Stream (TTS). This paper presents one solution of DVB software demultiplexer module adaptation to support TTS.","PeriodicalId":6731,"journal":{"name":"2020 Zooming Innovation in Consumer Technologies Conference (ZINC)","volume":"5 1","pages":"319-320"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82184733","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 : 2020-05-01DOI: 10.1109/ZINC50678.2020.9161789
S. Sridhar, Sowmya Sanagavarapu
There is an increase in the demand for the interior décor planning industry. Although initially used for extravagant events, the facilities have become gradually availed by everyone. The applications of Augmented Reality could potentially transform this industry by making it more convenient for consumers to plan their home and office interiors in their own time on their phone or system. This application would help in designing and planning the floor space virtually with a range of options available for selection. The implemented system works by using not just the images captured by the camera on the device, rather by using the orientation of the camera with respect to the ground plane that has to be detected. The Maxst SDK performs instant tracking to find the relative distance between the camera and the plane by focusing on the ground plane. This gives a more realistic view for the consumer to judge their fit efficiently with the dimensions of items, and save the manual work of moving furniture. The implemented system is evaluated for its deployment time for various models and performance under different distances.
{"title":"Instant Tracking-Based Approach for Interior Décor Planning with Markerless AR","authors":"S. Sridhar, Sowmya Sanagavarapu","doi":"10.1109/ZINC50678.2020.9161789","DOIUrl":"https://doi.org/10.1109/ZINC50678.2020.9161789","url":null,"abstract":"There is an increase in the demand for the interior décor planning industry. Although initially used for extravagant events, the facilities have become gradually availed by everyone. The applications of Augmented Reality could potentially transform this industry by making it more convenient for consumers to plan their home and office interiors in their own time on their phone or system. This application would help in designing and planning the floor space virtually with a range of options available for selection. The implemented system works by using not just the images captured by the camera on the device, rather by using the orientation of the camera with respect to the ground plane that has to be detected. The Maxst SDK performs instant tracking to find the relative distance between the camera and the plane by focusing on the ground plane. This gives a more realistic view for the consumer to judge their fit efficiently with the dimensions of items, and save the manual work of moving furniture. The implemented system is evaluated for its deployment time for various models and performance under different distances.","PeriodicalId":6731,"journal":{"name":"2020 Zooming Innovation in Consumer Technologies Conference (ZINC)","volume":"89 1","pages":"103-108"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82249105","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 : 2020-05-01DOI: 10.1109/ZINC50678.2020.9161773
N. Petrovic, Samir Koničanin, Dejan N. Milic, S. Suljovic, S. Panic
Mobile networks have significant impact on many aspects of our everyday lives. The number of users and requirements increase continuously, which poses many challenges to service providers. Efficient resource planning and ability to adapt to current demands are crucial when it comes to deployment of large-scale and high-performance commercial mobile networks. Leveraging modelling and simulation tools provides faster and cheaper analysis of planned deployments. In this paper, a framework aiming modelling, simulation and planning of mobile networks within smart cities is presented. The solution makes use of GPGPU approach for faster calculations.
{"title":"GPU-enabled Framework for Modelling, Simulation and Planning of Mobile Networks in Smart Cities","authors":"N. Petrovic, Samir Koničanin, Dejan N. Milic, S. Suljovic, S. Panic","doi":"10.1109/ZINC50678.2020.9161773","DOIUrl":"https://doi.org/10.1109/ZINC50678.2020.9161773","url":null,"abstract":"Mobile networks have significant impact on many aspects of our everyday lives. The number of users and requirements increase continuously, which poses many challenges to service providers. Efficient resource planning and ability to adapt to current demands are crucial when it comes to deployment of large-scale and high-performance commercial mobile networks. Leveraging modelling and simulation tools provides faster and cheaper analysis of planned deployments. In this paper, a framework aiming modelling, simulation and planning of mobile networks within smart cities is presented. The solution makes use of GPGPU approach for faster calculations.","PeriodicalId":6731,"journal":{"name":"2020 Zooming Innovation in Consumer Technologies Conference (ZINC)","volume":"39 1","pages":"280-285"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77331577","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 : 2020-05-01DOI: 10.1109/ZINC50678.2020.9161797
I. Shirokov, A. Mironov, A. N. Grekov
Measurement of the parameters of the upper layer of the ocean is one of the tasks of oceanology, on the solution of which the progress of a number of areas of ocean research depends on. So, the data of field measurements are used for verifying and calibrating the processing algorithms of remote meters, oceanographic models, in various research problems and in synoptic/climatic monitoring of the ocean. A continuous increasing in the volume of remote sensing data, an increasing in the complexity of their processing algorithms, and improvement of ocean modeling methods form new requirements for the quality and quantity of experimental measurements. In this paper a small-sized drifter is considered. It is equipped with the necessary measuring channels and software, as an element of the system for measuring the spatiotemporal characteristics of the surface layer of the ocean, namely, the stream vector and the angular spectrum of sea waves. Its structural scheme, the general view, the description of the mechanical part, as well as the scheme for performing the experimental work, all of them are presented in the paper.
{"title":"Ocean Surface State Monitoring with Drifters Array","authors":"I. Shirokov, A. Mironov, A. N. Grekov","doi":"10.1109/ZINC50678.2020.9161797","DOIUrl":"https://doi.org/10.1109/ZINC50678.2020.9161797","url":null,"abstract":"Measurement of the parameters of the upper layer of the ocean is one of the tasks of oceanology, on the solution of which the progress of a number of areas of ocean research depends on. So, the data of field measurements are used for verifying and calibrating the processing algorithms of remote meters, oceanographic models, in various research problems and in synoptic/climatic monitoring of the ocean. A continuous increasing in the volume of remote sensing data, an increasing in the complexity of their processing algorithms, and improvement of ocean modeling methods form new requirements for the quality and quantity of experimental measurements. In this paper a small-sized drifter is considered. It is equipped with the necessary measuring channels and software, as an element of the system for measuring the spatiotemporal characteristics of the surface layer of the ocean, namely, the stream vector and the angular spectrum of sea waves. Its structural scheme, the general view, the description of the mechanical part, as well as the scheme for performing the experimental work, all of them are presented in the paper.","PeriodicalId":6731,"journal":{"name":"2020 Zooming Innovation in Consumer Technologies Conference (ZINC)","volume":"27 1","pages":"113-117"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74046739","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 : 2020-05-01DOI: 10.1109/ZINC50678.2020.9161799
Tamara Zivkovic, M. Zivkovic
Software testing is one of the most important activities in the software development lifecycle. White box testing assumes access to the source code of the program. One of the main problems when selecting a testing approach is to try to minimize the number of tests while guaranteeing 100% test coverage.The testing of object-oriented programs is more complex than the testing of procedural programs. All traditional testing techniques can be applied, however, it is required to consider special characteristics of object-oriented programs, such as abstraction. Several techniques can be applied to the testing of the object-oriented programs – in this paper we have selected and compared two approaches and applied them to the same object-oriented program sample. Generated test sets were analyzed in terms of coverage quality with the PIT tool for mutation testing.
{"title":"Comparative Analysis of Techniques for Testing Object Oriented Programs","authors":"Tamara Zivkovic, M. Zivkovic","doi":"10.1109/ZINC50678.2020.9161799","DOIUrl":"https://doi.org/10.1109/ZINC50678.2020.9161799","url":null,"abstract":"Software testing is one of the most important activities in the software development lifecycle. White box testing assumes access to the source code of the program. One of the main problems when selecting a testing approach is to try to minimize the number of tests while guaranteeing 100% test coverage.The testing of object-oriented programs is more complex than the testing of procedural programs. All traditional testing techniques can be applied, however, it is required to consider special characteristics of object-oriented programs, such as abstraction. Several techniques can be applied to the testing of the object-oriented programs – in this paper we have selected and compared two approaches and applied them to the same object-oriented program sample. Generated test sets were analyzed in terms of coverage quality with the PIT tool for mutation testing.","PeriodicalId":6731,"journal":{"name":"2020 Zooming Innovation in Consumer Technologies Conference (ZINC)","volume":"47 3 1","pages":"270-275"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80608135","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 : 2020-05-01DOI: 10.1109/ZINC50678.2020.9161816
Luka Roguljić, M. Vranješ, M. Milosevic, D. Samardzija
Due to the rapid development of automotive technology and the rapid increase in number of advanced driver assistance systems (ADAS) in today’s vehicles, the amount of automotive data traffic is significantly rising day by day. Finding errors and disrupted messages in vehicle communication network is crucial part of vehicle safety system, as well as the safety of the whole its environment. The focus of this paper is analyzing the automotive data traffic transmitted via the CAN bus in the vehicle. The proposed software solution parses the.asc log which contains all the traffic data on the bus. The software solution filters and classifies messages according to their names and routing direction, and according to the routing rules in the network that are described in the routing scenario. Furthermore, proposed solution finds errors by looking for irregularities in data block and checking the response time of the message. As a result of the software solution, a report is given in form of.xlsx file. Based on this report, it is possible to analyze the communication and take steps to improve future communication. The proposed solution is created in Python script language and has features of modularity and upgradability since it is created in modules that can be modified independently of other modules. Verification was carried out within the software solution so that different cases were created by entering anomalies into the.asc file. The results of the verification are positive and meet the requirements set prior to making the solution itself. The proposed solution solves the problem of displaying dry data so that all data read from the bus is filtered, classified and displayed in graphical form for easier analysis of the data itself.
{"title":"Automotive Data Traffic Filtering and Classification with Finding Errors","authors":"Luka Roguljić, M. Vranješ, M. Milosevic, D. Samardzija","doi":"10.1109/ZINC50678.2020.9161816","DOIUrl":"https://doi.org/10.1109/ZINC50678.2020.9161816","url":null,"abstract":"Due to the rapid development of automotive technology and the rapid increase in number of advanced driver assistance systems (ADAS) in today’s vehicles, the amount of automotive data traffic is significantly rising day by day. Finding errors and disrupted messages in vehicle communication network is crucial part of vehicle safety system, as well as the safety of the whole its environment. The focus of this paper is analyzing the automotive data traffic transmitted via the CAN bus in the vehicle. The proposed software solution parses the.asc log which contains all the traffic data on the bus. The software solution filters and classifies messages according to their names and routing direction, and according to the routing rules in the network that are described in the routing scenario. Furthermore, proposed solution finds errors by looking for irregularities in data block and checking the response time of the message. As a result of the software solution, a report is given in form of.xlsx file. Based on this report, it is possible to analyze the communication and take steps to improve future communication. The proposed solution is created in Python script language and has features of modularity and upgradability since it is created in modules that can be modified independently of other modules. Verification was carried out within the software solution so that different cases were created by entering anomalies into the.asc file. The results of the verification are positive and meet the requirements set prior to making the solution itself. The proposed solution solves the problem of displaying dry data so that all data read from the bus is filtered, classified and displayed in graphical form for easier analysis of the data itself.","PeriodicalId":6731,"journal":{"name":"2020 Zooming Innovation in Consumer Technologies Conference (ZINC)","volume":"30 1","pages":"201-206"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78298417","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：