Dimitrije Stojanović, N. Cetic, Jelena Kocic, Bogdan Pavković
{"title":"Improving Lane Annotation in Autonomous Driving Data Sets with Classical Computer Vision Techniques","authors":"Dimitrije Stojanović, N. Cetic, Jelena Kocic, Bogdan Pavković","doi":"10.1109/ZINC58345.2023.10174073","DOIUrl":"https://doi.org/10.1109/ZINC58345.2023.10174073","url":null,"abstract":"Autonomous driving systems rely on accurate and reliable lane detection to safely navigate roads. In this paper, we propose a method for improving lane annotation in autonomous driving data sets using classical computer vision techniques. The proposed method combines the Hough transform and linear curve fitting to detect and smooth the positions of lane markings in a video stream. We evaluate the performance of the proposed method on the Berkeley DeepDrive (BDD) dataset and compare it to the ground truth annotations. Results show that the proposed method achieves a high level of accuracy and robustness in lane detection, and can effectively improve lane annotation in autonomous driving data sets. Our method provides a valuable tool for training and evaluating autonomous driving systems, and can also be applied to improve annotation in different datasets.","PeriodicalId":383771,"journal":{"name":"2023 Zooming Innovation in Consumer Technologies Conference (ZINC)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114327178","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Discussion Manipulation, Language and Domain Dependent Models: An Overview","authors":"Filip Chalás, Igor Stupavský, V. Vranić","doi":"10.1109/ZINC58345.2023.10174128","DOIUrl":"https://doi.org/10.1109/ZINC58345.2023.10174128","url":null,"abstract":"The amount of antisocial online behavior (AOB) in the political field has been on the rise in recent years. In the research, we are dealing with the reason for confusing AOB with other forms of antisocial behavior. We specifically dealt with NLP in the political field in the Slovak language, with a specific number of prefixes and suffixes. In this paper, we focus on the area of detection of manipulation of political discussions. The data source consisted of previously collected data in the period from April 2018 with an update until November 19, 2022 realized within this research from the site demagog.sk, which we supplemented with new claims. We trained several classification models on preprocessed data and evaluated them. For multi-class classification, the best results were achieved using logistic regression and a support vector machine trained on the resampled dataset—both achieving an accuracy of 0.56 and a macro F1 score of 0.39. In the case of binary classification, the best results were achieved by logistic regression—accuracy 0.7 and macro F1 score 0.56. These models could help detect manipulation in online political discussions.","PeriodicalId":383771,"journal":{"name":"2023 Zooming Innovation in Consumer Technologies Conference (ZINC)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122321339","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}
Vuk Cabrilo, Dusan Kenjic, Radomir Zlatkovic, Marija Antic
{"title":"One solution of a Distributed System intended for communication between ADAS and IVI Systems","authors":"Vuk Cabrilo, Dusan Kenjic, Radomir Zlatkovic, Marija Antic","doi":"10.1109/ZINC58345.2023.10174250","DOIUrl":"https://doi.org/10.1109/ZINC58345.2023.10174250","url":null,"abstract":"Current trends of digitalization and automation in the automotive industry have increased the complexity of computer clusters in different domains of vehicular ecosystems, which are required to support new features. This has led to redundancy in resource usage in specific use cases, resulting in increased production costs and manufacturer suggested retail price (MSRP) markups for the finalized products. The average retail price of a new vehicle in the United States increased by 13.4% between 2015 and 2020. Considering the global chip shortage of 2020 and current global inflation, the average price of a new vehicle in the United States reached $49,500 in 2023 [1]. With the electrification of current automotive platforms underway, as well as the move to centralized system architectures, new approaches to inter-domain communication are expected. This paper proposes a solution of a distributed AUTOSAR Adaptive system that can establish communication with the In-Vehicle Infotainment (IVI) domain. The proof of concept implemented in a controlled environment proves viable for inter-domain communication, as it provides good scalability and adaptability to different scenarios. The use of a distributed approach facilitates the applicability of distributed system principles, allowing for the implementation of a stable system.","PeriodicalId":383771,"journal":{"name":"2023 Zooming Innovation in Consumer Technologies Conference (ZINC)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128767915","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}
J. Tomic, Nemanja Gazivoda, M. Kušljević, P. Sovilj, Milan Šaš
{"title":"Travel Route Planning in Smart Cities","authors":"J. Tomic, Nemanja Gazivoda, M. Kušljević, P. Sovilj, Milan Šaš","doi":"10.1109/ZINC58345.2023.10174121","DOIUrl":"https://doi.org/10.1109/ZINC58345.2023.10174121","url":null,"abstract":"Travel route planning techniques for motor and electric vehicles are designed to find the optimal path from the start to the destination point on a roadmap. As traffic conditions can change very quickly during the journey, it is necessary to immediately update all changes in real time. For example, traffic congestion may occur in certain parts of the route due to an increased number of vehicles. The shortest path generally may not be in all cases the best path, as many conditions can affect the length of the journey. If we want to make our cities smart, the transportation system also has to be smart. In this paper, a practically implemented system for vehicle route planning in urban areas is presented, which works in real time and takes a large number of parameters of travel into account. Therefore, this system provides an estimation of travel time that is much more accurate than the standard auto router. In this paper, this estimation of travel time is practically proven.","PeriodicalId":383771,"journal":{"name":"2023 Zooming Innovation in Consumer Technologies Conference (ZINC)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115590566","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Organizational Fit and Contingency Factors in the Implementation of ERP Projects in Bahrain","authors":"Minwir M. Al-Shammari, Younis Abdulla","doi":"10.1109/ZINC58345.2023.10173969","DOIUrl":"https://doi.org/10.1109/ZINC58345.2023.10173969","url":null,"abstract":"Previous research found cultural differences as the primary driver for successful ERP adoption. The adoption of ERP has been rather prevalent in developed countries. This study examines how implementation and organizational fit affect ERP project success in Bahrain, a developing country. This paper looks at the ERP organizational fit (process fit, data fit, and user interface fit), ERP implementation risks (process adaptation, ERP adaptation, and organizational resistance), and ERP implementation success factors (cost/time and performance/benefit). The information was gathered from 78 respondents actively involved in the ERP implementation process. The results showed that organizational fit, process adaptation, training, and the success of an ERP project all strongly link to each other. It was found that there was a small link between traditional success factors like organizational resistance and the success of an ERP project. Based on the results of this study, ERP project managers and top management should look at how well their business and the ERP system they want to use match up. ERP implementation and process adaptation should be measured and managed well to minimize business disruptions and user resistance. Project managers need to minimize business disruptions and user resistance to evaluate the organizational fit of ERP based on its relevance.","PeriodicalId":383771,"journal":{"name":"2023 Zooming Innovation in Consumer Technologies Conference (ZINC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130815613","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Chemical senses and Consumer Technologies: a journey from the human physiology towards the Metaverse","authors":"A. Tonacci","doi":"10.1109/zinc58345.2023.10173962","DOIUrl":"https://doi.org/10.1109/zinc58345.2023.10173962","url":null,"abstract":"","PeriodicalId":383771,"journal":{"name":"2023 Zooming Innovation in Consumer Technologies Conference (ZINC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130976963","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Representing Multifunctional Devices in Voice-Controlled Systems","authors":"Dušan Mačkić, Marija Antic","doi":"10.1109/ZINC58345.2023.10174038","DOIUrl":"https://doi.org/10.1109/ZINC58345.2023.10174038","url":null,"abstract":"As the number of smart devices continues to grow, it is becoming increasingly required by the consumers to integrate them into voice-controlled systems like Google Home and Amazon Alexa. However, many device types are not fully supported on these platforms, and the integration often require modifications to fit the voice assistant platform requirements, which is sometimes not possible. In particular, if multifunctional devices have to be represented in a way supported by Google Home and Amazon Alexa APIs, many features are not visible within the assistant and it is not possible to control them. This paper proposes a solution for representing complex devices within a voice-controlled system, by using unique templates specific to the device model and manufacturer. The template contains the necessary information, which allows to split the functionality of one physical device into multiple logical devices so that each logical device can be controlled by the voice assistant.","PeriodicalId":383771,"journal":{"name":"2023 Zooming Innovation in Consumer Technologies Conference (ZINC)","volume":"56 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114045705","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}
Boban P. Bondzulic, V. Lukin, Dimitrije Bujaković, Fangfang Li, S. Kryvenko, B. Pavlović
{"title":"On Visually Lossless JPEG Image Compression","authors":"Boban P. Bondzulic, V. Lukin, Dimitrije Bujaković, Fangfang Li, S. Kryvenko, B. Pavlović","doi":"10.1109/ZINC58345.2023.10174090","DOIUrl":"https://doi.org/10.1109/ZINC58345.2023.10174090","url":null,"abstract":"This paper presents an investigation into the visually lossless JPEG compression which provides maximum compression ratio applied before the resulting compressed image appears distorted. The research was conducted using two publicly available databases with the results of just noticeable difference tests. It has been shown that using visually lossless compression can save memory and communication resources by 80% compared to conventional JPEG compression approach with a fixed quality factor. Compared to JPEG lossless compression, this saves memory resources by about eight times. Also, it is shown that the mean gradient magnitude of the original uncompressed image can be used to predict the JPEG visually lossless compression ratio. The last part of the research provides comments on visually lossless quality prediction using a simple prediction approach based on only one feature of the original image with a comparison with the results of a deep learning approach.","PeriodicalId":383771,"journal":{"name":"2023 Zooming Innovation in Consumer Technologies Conference (ZINC)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122372738","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}
M. Bjelica, M. Milosevic, V. Petrović, Ognjen Bjekovic, Ivan Popovic
{"title":"Software platforms in next-generation vehicles: trends, varieties and challenges","authors":"M. Bjelica, M. Milosevic, V. Petrović, Ognjen Bjekovic, Ivan Popovic","doi":"10.1109/zinc58345.2023.10174228","DOIUrl":"https://doi.org/10.1109/zinc58345.2023.10174228","url":null,"abstract":"","PeriodicalId":383771,"journal":{"name":"2023 Zooming Innovation in Consumer Technologies Conference (ZINC)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123957264","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}