Pub Date : 2020-05-01DOI: 10.1109/DAS49615.2020.9108946
E. Băutu, C. Puchianu, Emanuela Bran, D. Sburlan, D. Popovici
Traffic accidents due to driver’s lack of attention have always been a major concern. Recently, there have been numerous reports of accidents that took place because the drivers were checking their phone or even texting while driving. Current efforts of traffic safety policy makers target the development of strategies that limit mobile phone use while driving. We describe an in-vehicle software system that eases the interaction between the driver and the smartphone. Using our software system, the driver may choose to automatically filter, in an adaptive manner, messages and notifications from third party applications, while driving. Using information from the vehicle sensors, the system identifies potentially dangerous situations and adapts its behavior to limit user distraction. The software development process is based on the principle of separation of concerns. The system complies with Intelligent Environments principles, especially by prioritizing user’s safety at all times. Further system developments regard the integration of Augmented Reality visualization and hands-free interaction capabilities.
{"title":"In-Vehicle Software System for Fostering Driver’s Attentiveness","authors":"E. Băutu, C. Puchianu, Emanuela Bran, D. Sburlan, D. Popovici","doi":"10.1109/DAS49615.2020.9108946","DOIUrl":"https://doi.org/10.1109/DAS49615.2020.9108946","url":null,"abstract":"Traffic accidents due to driver’s lack of attention have always been a major concern. Recently, there have been numerous reports of accidents that took place because the drivers were checking their phone or even texting while driving. Current efforts of traffic safety policy makers target the development of strategies that limit mobile phone use while driving. We describe an in-vehicle software system that eases the interaction between the driver and the smartphone. Using our software system, the driver may choose to automatically filter, in an adaptive manner, messages and notifications from third party applications, while driving. Using information from the vehicle sensors, the system identifies potentially dangerous situations and adapts its behavior to limit user distraction. The software development process is based on the principle of separation of concerns. The system complies with Intelligent Environments principles, especially by prioritizing user’s safety at all times. Further system developments regard the integration of Augmented Reality visualization and hands-free interaction capabilities.","PeriodicalId":103267,"journal":{"name":"2020 International Conference on Development and Application Systems (DAS)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131053241","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/DAS49615.2020.9108927
D. Marcu, M. Danubianu
The education system is a source that generates significant amounts of data, daily, in various formats and, often, hiding valuable information. Finding a good way to unravel those hidden gems, represents one of the most challenging problems of natural language processing, namely sentiment analysis. This involves, applying NLP and text analysis techniques to identify and classify subjective opinions in different materials such as documents or sentences. In our work, we used as raw data, the opinions of students from eleven high schools in Suceava, related to various aspects of the educational process. They were collected through a Google Docs form, and analyzed through the Orange environment (an open source tool for machine learning and data visualization). In this paper, we make a comparative study of the obtained results using the Ekman and Plutchik models. Each model extracts from the analyzed texts, a different emotion, based on which the students’ sentiments towards the educational process will be analyzed.
{"title":"Sentiment Analysis from Students’ Feedback : A Romanian High School Case Study","authors":"D. Marcu, M. Danubianu","doi":"10.1109/DAS49615.2020.9108927","DOIUrl":"https://doi.org/10.1109/DAS49615.2020.9108927","url":null,"abstract":"The education system is a source that generates significant amounts of data, daily, in various formats and, often, hiding valuable information. Finding a good way to unravel those hidden gems, represents one of the most challenging problems of natural language processing, namely sentiment analysis. This involves, applying NLP and text analysis techniques to identify and classify subjective opinions in different materials such as documents or sentences. In our work, we used as raw data, the opinions of students from eleven high schools in Suceava, related to various aspects of the educational process. They were collected through a Google Docs form, and analyzed through the Orange environment (an open source tool for machine learning and data visualization). In this paper, we make a comparative study of the obtained results using the Ekman and Plutchik models. Each model extracts from the analyzed texts, a different emotion, based on which the students’ sentiments towards the educational process will be analyzed.","PeriodicalId":103267,"journal":{"name":"2020 International Conference on Development and Application Systems (DAS)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126798695","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/DAS49615.2020.9108918
F. Niculescu, A. Săvescu, M. Vasile
Gas turbines used in marine propulsion ensure increased efficiency and safety, with a very good power/weight ratio and with low maintenance and operation costs. The paper presents the control of the gas turbine so that it works in optimum operating conditions under any regime. The authors’ contribution consisted in the elaboration of control equations starting from the general equations of the gas turbine. These equations have been implemented in a digital control system that metered the fuel depending on the speed deviation. Finding the control algorithm involved determining the adjustment parameters so that the engine behaves stable at any speed. After testing the configuration on the stand, the actual testing was carried out on board the ship.
{"title":"Adaptive Control for Marine Gas Turbine","authors":"F. Niculescu, A. Săvescu, M. Vasile","doi":"10.1109/DAS49615.2020.9108918","DOIUrl":"https://doi.org/10.1109/DAS49615.2020.9108918","url":null,"abstract":"Gas turbines used in marine propulsion ensure increased efficiency and safety, with a very good power/weight ratio and with low maintenance and operation costs. The paper presents the control of the gas turbine so that it works in optimum operating conditions under any regime. The authors’ contribution consisted in the elaboration of control equations starting from the general equations of the gas turbine. These equations have been implemented in a digital control system that metered the fuel depending on the speed deviation. Finding the control algorithm involved determining the adjustment parameters so that the engine behaves stable at any speed. After testing the configuration on the stand, the actual testing was carried out on board the ship.","PeriodicalId":103267,"journal":{"name":"2020 International Conference on Development and Application Systems (DAS)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128220007","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/das49615.2020.9108936
{"title":"DAS 2020 Copyright Page","authors":"","doi":"10.1109/das49615.2020.9108936","DOIUrl":"https://doi.org/10.1109/das49615.2020.9108936","url":null,"abstract":"","PeriodicalId":103267,"journal":{"name":"2020 International Conference on Development and Application Systems (DAS)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133717471","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/das49615.2020.9108960
{"title":"DAS 2020 TOC","authors":"","doi":"10.1109/das49615.2020.9108960","DOIUrl":"https://doi.org/10.1109/das49615.2020.9108960","url":null,"abstract":"","PeriodicalId":103267,"journal":{"name":"2020 International Conference on Development and Application Systems (DAS)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121286626","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/DAS49615.2020.9108969
I. Cojuhari, I. Fiodorov, B. Izvoreanu, Dumitru Moraru
In this paper is proposed a tuning algorithm of PID controller that offers the maximum stability degree of the control system, based on the genetic algorithm. The tuning algorithm was designed based on the maximum stability degree method with iterations, where the tuning parameters depend on maximum stability degree which is varied. Based on its values, it was proposed to implement genetic algorithm to find the tuning parameters. The maximum stability degree method permits to obtain the high stability and high performance of the system, but this method has some limitations in case when control object is described by the model of object with inertia low order. In this case to find the best tuning parameters was proposed to use the genetic algorithm. For efficacy analysis of the proposed algorithm, there are presented some case studies and practical applications.
{"title":"Tuning of the PID Controller to the System with Maximum Stability Degree using Genetic Algorithm","authors":"I. Cojuhari, I. Fiodorov, B. Izvoreanu, Dumitru Moraru","doi":"10.1109/DAS49615.2020.9108969","DOIUrl":"https://doi.org/10.1109/DAS49615.2020.9108969","url":null,"abstract":"In this paper is proposed a tuning algorithm of PID controller that offers the maximum stability degree of the control system, based on the genetic algorithm. The tuning algorithm was designed based on the maximum stability degree method with iterations, where the tuning parameters depend on maximum stability degree which is varied. Based on its values, it was proposed to implement genetic algorithm to find the tuning parameters. The maximum stability degree method permits to obtain the high stability and high performance of the system, but this method has some limitations in case when control object is described by the model of object with inertia low order. In this case to find the best tuning parameters was proposed to use the genetic algorithm. For efficacy analysis of the proposed algorithm, there are presented some case studies and practical applications.","PeriodicalId":103267,"journal":{"name":"2020 International Conference on Development and Application Systems (DAS)","volume":"246 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114359325","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/DAS49615.2020.9108908
Eduard Zadobrischi
The chaotic increase in the number of vehicles and the population density makes road safety an important topic from all points of view. Urban planning and disorganization in terms of traffic efficiency and fluidization solutions cause massive traffic congestion in most cities around the world. The diversity of mechanisms and devices dedicated to the fluidization of traffic in pedestrian areas or pedestrian crossings does not offer safety to all categories of persons, here referring to the sick, elderly, children. A number of studies that have analyzed and focused on the field, offer solutions whereby a combination of vehicles and automated tools, used in conjunction with an efficient data communication type, can reduce traffic congestion problems and reduce traffic jams. Wireless communications technologies have the possibility of the dynamic and increase the security of the transmission mode. We can say that this article presents an overview. of the most important and promising technologies that can be. used in the applications dedicated to the road safety sector based on communication between cars. We propose a system prototype based on RF (Radio-Frequency) communications and VLC (Visible Light Communications) technology, thus making a promising alternative in the field. Based on these proposals, analyzes and simulations are performed on a hybrid architecture, offering results on performance evaluation of the solution.
{"title":"System Prototype Proposed for Vehicle Communications Based on VLC-RF Technologies Adaptable on Infrastructure","authors":"Eduard Zadobrischi","doi":"10.1109/DAS49615.2020.9108908","DOIUrl":"https://doi.org/10.1109/DAS49615.2020.9108908","url":null,"abstract":"The chaotic increase in the number of vehicles and the population density makes road safety an important topic from all points of view. Urban planning and disorganization in terms of traffic efficiency and fluidization solutions cause massive traffic congestion in most cities around the world. The diversity of mechanisms and devices dedicated to the fluidization of traffic in pedestrian areas or pedestrian crossings does not offer safety to all categories of persons, here referring to the sick, elderly, children. A number of studies that have analyzed and focused on the field, offer solutions whereby a combination of vehicles and automated tools, used in conjunction with an efficient data communication type, can reduce traffic congestion problems and reduce traffic jams. Wireless communications technologies have the possibility of the dynamic and increase the security of the transmission mode. We can say that this article presents an overview. of the most important and promising technologies that can be. used in the applications dedicated to the road safety sector based on communication between cars. We propose a system prototype based on RF (Radio-Frequency) communications and VLC (Visible Light Communications) technology, thus making a promising alternative in the field. Based on these proposals, analyzes and simulations are performed on a hybrid architecture, offering results on performance evaluation of the solution.","PeriodicalId":103267,"journal":{"name":"2020 International Conference on Development and Application Systems (DAS)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132683390","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/DAS49615.2020.9108942
Marina Adriana Mercioni, S. Holban
This paper is an overview of the most used activation functions, classic functions and current functions as well. When we say classic, we mean the first activation functions, the most popular and used in the past. But due to their disadvantages appeared other new activation functions that we refer them as current. These most influential functions are among the most known artificial intelligence activation functions in the research of Machine learning and Deep Learning as well. With each function, we provide a brief description of the activation function, discuss its impact and show the domain where it is applicable, its advantages and disadvantages and more details to have an overview. These functions cover more issues like vanishing gradient, exploding gradient when we are using Gradient Descent and so on. These solutions to these issues are all among the most important topics in Artificial Intelligence research and development part.
{"title":"The Most Used Activation Functions: Classic Versus Current","authors":"Marina Adriana Mercioni, S. Holban","doi":"10.1109/DAS49615.2020.9108942","DOIUrl":"https://doi.org/10.1109/DAS49615.2020.9108942","url":null,"abstract":"This paper is an overview of the most used activation functions, classic functions and current functions as well. When we say classic, we mean the first activation functions, the most popular and used in the past. But due to their disadvantages appeared other new activation functions that we refer them as current. These most influential functions are among the most known artificial intelligence activation functions in the research of Machine learning and Deep Learning as well. With each function, we provide a brief description of the activation function, discuss its impact and show the domain where it is applicable, its advantages and disadvantages and more details to have an overview. These functions cover more issues like vanishing gradient, exploding gradient when we are using Gradient Descent and so on. These solutions to these issues are all among the most important topics in Artificial Intelligence research and development part.","PeriodicalId":103267,"journal":{"name":"2020 International Conference on Development and Application Systems (DAS)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126600111","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/DAS49615.2020.9108928
Cătălin Beguni, A. Căilean, Sebastian-Andrei Avatamanitei, M. Dimian
To address the most common issues found in automotive Visible Light Communication applications, a new photodiode amplifier based on an instrumentation amplifier is proposed. In order to improve the results, buffer stages have been replaced with transimpedance amplifiers providing the circuit with offset cancellation loops that enable the sensing of the DC output offset and with T-networks in the feedback path, that reduce the effect of parasitic capacitances. Thus, the resulted output signal will be ready for further processing in the analog-digital conversion (ADC) stage providing improved results in terms of parasitic light resilience and SNR.
{"title":"Photodiode Amplifier with Transimpedance and Differential Stages for Automotive Visible Light Applications","authors":"Cătălin Beguni, A. Căilean, Sebastian-Andrei Avatamanitei, M. Dimian","doi":"10.1109/DAS49615.2020.9108928","DOIUrl":"https://doi.org/10.1109/DAS49615.2020.9108928","url":null,"abstract":"To address the most common issues found in automotive Visible Light Communication applications, a new photodiode amplifier based on an instrumentation amplifier is proposed. In order to improve the results, buffer stages have been replaced with transimpedance amplifiers providing the circuit with offset cancellation loops that enable the sensing of the DC output offset and with T-networks in the feedback path, that reduce the effect of parasitic capacitances. Thus, the resulted output signal will be ready for further processing in the analog-digital conversion (ADC) stage providing improved results in terms of parasitic light resilience and SNR.","PeriodicalId":103267,"journal":{"name":"2020 International Conference on Development and Application Systems (DAS)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122698427","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/DAS49615.2020.9108940
Eduard Zadobrischi, M. Negru
With the expansion of accessibility and availability of personal cars towards the population, the environment, road safety, and pedestrian safety faces greater problems. The neediest for the management of information through autonomous systems dedicated to pedestrian detection and improvement of analysis and road prevention algorithms is an important factor addressed in this paper. The purpose of this paper is to demonstrate and propose viable solutions that will help drivers to practice an efficient, safe, and event-free driving style. This paper presents a prototype under development that can avoid various traffic events, the system analyzing, and alerting the driver regarding pedestrian intentions, marking each detection separately according to the degree of danger that it constitutes for both the driver, as well as for pedestrians. This research analyzes and emphasizes that at this point everything is already focused on the paradigm from which it is possible for all these technologies to cooperate in a hybrid platform, offering a real solution to the demands of human users but also of IoT solutions.
{"title":"Pedestrian detection based on TensorFlow YOLOv3 embedded in a portable system adaptable to vehicles","authors":"Eduard Zadobrischi, M. Negru","doi":"10.1109/DAS49615.2020.9108940","DOIUrl":"https://doi.org/10.1109/DAS49615.2020.9108940","url":null,"abstract":"With the expansion of accessibility and availability of personal cars towards the population, the environment, road safety, and pedestrian safety faces greater problems. The neediest for the management of information through autonomous systems dedicated to pedestrian detection and improvement of analysis and road prevention algorithms is an important factor addressed in this paper. The purpose of this paper is to demonstrate and propose viable solutions that will help drivers to practice an efficient, safe, and event-free driving style. This paper presents a prototype under development that can avoid various traffic events, the system analyzing, and alerting the driver regarding pedestrian intentions, marking each detection separately according to the degree of danger that it constitutes for both the driver, as well as for pedestrians. This research analyzes and emphasizes that at this point everything is already focused on the paradigm from which it is possible for all these technologies to cooperate in a hybrid platform, offering a real solution to the demands of human users but also of IoT solutions.","PeriodicalId":103267,"journal":{"name":"2020 International Conference on Development and Application Systems (DAS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131176699","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：