Pub Date : 2018-11-01DOI: 10.1109/AIEEE.2018.8592144
K. Baltputnis, R. Petrichenko, D. Sobolevsky
Accurate demand forecasting in district heating networks is an essential and imperative task in the everyday operation of both, the network itself and the heating energy suppliers. Multiple regression is one of the possible approaches to solving the forecasting problem with sufficient accuracy and little computational effort. This paper presents a polynomial regression model and offers several additions for its further improvement. It is found that grouping the model residuals by hour-of-day allows notably reducing the forecast error. The value of other modifications and the optimum size of the training set can vary over time, thus an automatic model parameter selection before each new forecast is advised.
{"title":"Heating Demand Forecasting with Multiple Regression: Model Setup and Case Study","authors":"K. Baltputnis, R. Petrichenko, D. Sobolevsky","doi":"10.1109/AIEEE.2018.8592144","DOIUrl":"https://doi.org/10.1109/AIEEE.2018.8592144","url":null,"abstract":"Accurate demand forecasting in district heating networks is an essential and imperative task in the everyday operation of both, the network itself and the heating energy suppliers. Multiple regression is one of the possible approaches to solving the forecasting problem with sufficient accuracy and little computational effort. This paper presents a polynomial regression model and offers several additions for its further improvement. It is found that grouping the model residuals by hour-of-day allows notably reducing the forecast error. The value of other modifications and the optimum size of the training set can vary over time, thus an automatic model parameter selection before each new forecast is advised.","PeriodicalId":198244,"journal":{"name":"2018 IEEE 6th Workshop on Advances in Information, Electronic and Electrical Engineering (AIEEE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120968330","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 : 2018-11-01DOI: 10.1109/AIEEE.2018.8592307
P. Apse-Apsitis, A. Avotiņš, R. Porins
In this paper we report a power monitoring system used in the industrial greenhouse. Monitored data is processed in the device and then transferred to secure cloud services, where the data can be further processed, formatted and sent to the server used for data storage and later analysis. The power monitoring system is a part of the project where various parameters are measured in the greenhouse and as a result, could offer guidelines for the more efficient growth of plants [1] [2].
{"title":"Industrial Greenhouse Electrical Power Monitoring Using Secure Internet-of-Things(IoT) Platform","authors":"P. Apse-Apsitis, A. Avotiņš, R. Porins","doi":"10.1109/AIEEE.2018.8592307","DOIUrl":"https://doi.org/10.1109/AIEEE.2018.8592307","url":null,"abstract":"In this paper we report a power monitoring system used in the industrial greenhouse. Monitored data is processed in the device and then transferred to secure cloud services, where the data can be further processed, formatted and sent to the server used for data storage and later analysis. The power monitoring system is a part of the project where various parameters are measured in the greenhouse and as a result, could offer guidelines for the more efficient growth of plants [1] [2].","PeriodicalId":198244,"journal":{"name":"2018 IEEE 6th Workshop on Advances in Information, Electronic and Electrical Engineering (AIEEE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126405091","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 : 2018-11-01DOI: 10.1109/AIEEE.2018.8592167
Paulius Tumas, A. Serackis
A typical pedestrian protection system requires sophisticated hardware and robust detection algorithms. To solve these problems the existing systems use hybrid sensors where mono and stereo vision merged with active sensors. One of the most assuring pedestrian detection sensors is far infrared range camera. The classical pedestrian detection approach based on Histogram of oriented gradients is not robust enough to be applied in devices which consumers can trust. An application of deep neural network-based approach is able to perform with significantly higher accuracy. However, the deep learning approach requires a high number of labeled data examples. The investigation presented in this paper aimed the acceleration of pedestrian labeling in far-infrared image sequences. In order to accelerate pedestrian labeling in far-infrared camera videos, we have integrated the YOLOv3 object detector into labeling software. The verification of the pre-labeled results was around eleven times faster than manual labeling of every single frame.
{"title":"Automated Image Annotation based on YOLOv3","authors":"Paulius Tumas, A. Serackis","doi":"10.1109/AIEEE.2018.8592167","DOIUrl":"https://doi.org/10.1109/AIEEE.2018.8592167","url":null,"abstract":"A typical pedestrian protection system requires sophisticated hardware and robust detection algorithms. To solve these problems the existing systems use hybrid sensors where mono and stereo vision merged with active sensors. One of the most assuring pedestrian detection sensors is far infrared range camera. The classical pedestrian detection approach based on Histogram of oriented gradients is not robust enough to be applied in devices which consumers can trust. An application of deep neural network-based approach is able to perform with significantly higher accuracy. However, the deep learning approach requires a high number of labeled data examples. The investigation presented in this paper aimed the acceleration of pedestrian labeling in far-infrared image sequences. In order to accelerate pedestrian labeling in far-infrared camera videos, we have integrated the YOLOv3 object detector into labeling software. The verification of the pre-labeled results was around eleven times faster than manual labeling of every single frame.","PeriodicalId":198244,"journal":{"name":"2018 IEEE 6th Workshop on Advances in Information, Electronic and Electrical Engineering (AIEEE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126805059","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 : 2018-11-01DOI: 10.1109/aieee.2018.8592301
{"title":"AIEEE 2018 Title Page","authors":"","doi":"10.1109/aieee.2018.8592301","DOIUrl":"https://doi.org/10.1109/aieee.2018.8592301","url":null,"abstract":"","PeriodicalId":198244,"journal":{"name":"2018 IEEE 6th Workshop on Advances in Information, Electronic and Electrical Engineering (AIEEE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114798960","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 : 2018-11-01DOI: 10.1109/AIEEE.2018.8592219
A. Zabasta, J. Peuteman, N. Kuņicina, Alexander K. Fedotov, Yu. L. Prylutskyy, A. Fedotov
Rapid development of Cyber-Physical Systems (CPS) products and applications, encouraged by advances on the Internet of Things, generates high market demand on engineers with a multi-disciplinary background in applied physics, mathematics, mechanical, electrical and computer science engineering. One of the challenges in the development of study programs is bridging the gap between industry needs and educational output, in terms of training the prospective researchers and engineers in the CPS field. Riga Technical University cooperated in Multi-Paradigm Modelling for CPS MPM4CPS COST (European Cooperation in Science and Technology) Action that pursued to develop CPS expert profiles into a suitable format for educational purposes. Additionally, RTU and EU partners succeeded in the ERASMUS+ project Physics, which aimed at a reform of the master-level educational system in Belarusian universities in the field of Applied Physics. RTU and EU partners applied knowledge and methods to validate in practice the viability of the approach and the methods developed in the COST Action in order to support the introduction of industry-focused curricula at Higher Education Institutions (HEIs) in Partner' Countries. In this research, we discuss how cooperation between COST and ERASMUS+ project teams provide benefits to both projects, how the COST team efforts towards analysis of tendencies, industry needs and acquiring best education practice, have been applied by the ERASMUS+team in order to create industry-focused curricula in CPS for HEIs of Belarus and Ukraine.
{"title":"Development of Industry Oriented Curricular on Cyber Physical Systems for Belarusian and Ukrainian Universities","authors":"A. Zabasta, J. Peuteman, N. Kuņicina, Alexander K. Fedotov, Yu. L. Prylutskyy, A. Fedotov","doi":"10.1109/AIEEE.2018.8592219","DOIUrl":"https://doi.org/10.1109/AIEEE.2018.8592219","url":null,"abstract":"Rapid development of Cyber-Physical Systems (CPS) products and applications, encouraged by advances on the Internet of Things, generates high market demand on engineers with a multi-disciplinary background in applied physics, mathematics, mechanical, electrical and computer science engineering. One of the challenges in the development of study programs is bridging the gap between industry needs and educational output, in terms of training the prospective researchers and engineers in the CPS field. Riga Technical University cooperated in Multi-Paradigm Modelling for CPS MPM4CPS COST (European Cooperation in Science and Technology) Action that pursued to develop CPS expert profiles into a suitable format for educational purposes. Additionally, RTU and EU partners succeeded in the ERASMUS+ project Physics, which aimed at a reform of the master-level educational system in Belarusian universities in the field of Applied Physics. RTU and EU partners applied knowledge and methods to validate in practice the viability of the approach and the methods developed in the COST Action in order to support the introduction of industry-focused curricula at Higher Education Institutions (HEIs) in Partner' Countries. In this research, we discuss how cooperation between COST and ERASMUS+ project teams provide benefits to both projects, how the COST team efforts towards analysis of tendencies, industry needs and acquiring best education practice, have been applied by the ERASMUS+team in order to create industry-focused curricula in CPS for HEIs of Belarus and Ukraine.","PeriodicalId":198244,"journal":{"name":"2018 IEEE 6th Workshop on Advances in Information, Electronic and Electrical Engineering (AIEEE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116687749","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 : 2018-11-01DOI: 10.1109/AIEEE.2018.8592012
K. Vītols, Edgars Grīnfogels, Deniss Nikonorovs
Four different batches of 18650 lithium-ion cells have been measured to obtain initial capacity. The obtained measurements are analyzed to evaluate off the shelf capacity dispersion and other statistical parameters which are used to estimate the likelihood of a good battery (similar capacities for all cells) if cells are selected at random. Additionally, capacity dispersion results are discussed to select appropriate cell balancing methodology.
{"title":"Cell Capacity Dispersion Analysis Based Battery Pack Design","authors":"K. Vītols, Edgars Grīnfogels, Deniss Nikonorovs","doi":"10.1109/AIEEE.2018.8592012","DOIUrl":"https://doi.org/10.1109/AIEEE.2018.8592012","url":null,"abstract":"Four different batches of 18650 lithium-ion cells have been measured to obtain initial capacity. The obtained measurements are analyzed to evaluate off the shelf capacity dispersion and other statistical parameters which are used to estimate the likelihood of a good battery (similar capacities for all cells) if cells are selected at random. Additionally, capacity dispersion results are discussed to select appropriate cell balancing methodology.","PeriodicalId":198244,"journal":{"name":"2018 IEEE 6th Workshop on Advances in Information, Electronic and Electrical Engineering (AIEEE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115229785","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 : 2018-11-01DOI: 10.1109/aieee.2018.8592280
{"title":"AIEEE 2018 International Technical Program Committee","authors":"","doi":"10.1109/aieee.2018.8592280","DOIUrl":"https://doi.org/10.1109/aieee.2018.8592280","url":null,"abstract":"","PeriodicalId":198244,"journal":{"name":"2018 IEEE 6th Workshop on Advances in Information, Electronic and Electrical Engineering (AIEEE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122337677","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 : 2018-11-01DOI: 10.1109/AIEEE.2018.8592043
A. Litvinenko, Jānis Eidaks, A. Aboltins
The current research is dedicated to the experimental study of wireless power transfer and RF-to-DC conversion efficiency using waveforms with a high Peak-to-Average Power Ratio (PAPR). Three devices: a classical voltage doubler circuits with and without matching network and a commercially available energy harvesting device – Powercast P2110B are selected for the study. The use of a software-defined radio (SDR) for generation of sub-GHz signals allows to achieve high accuracy and customization of waveforms. The analysis of RF-to-DC conversion efficiency is based on the results of measurements of the input average power and DC voltage in laboratory conditions. The impact of the PAPR level and input average power level on the RF-to-DC conversion efficiency is investigated. Moreover, the results of RF-to-DC conversion for high PAPR signals are compared to the case when a low PAPR single-carrier waveform is used.
{"title":"Usage of Signals with a High PAPR Level for Efficient Wireless Power Transfer","authors":"A. Litvinenko, Jānis Eidaks, A. Aboltins","doi":"10.1109/AIEEE.2018.8592043","DOIUrl":"https://doi.org/10.1109/AIEEE.2018.8592043","url":null,"abstract":"The current research is dedicated to the experimental study of wireless power transfer and RF-to-DC conversion efficiency using waveforms with a high Peak-to-Average Power Ratio (PAPR). Three devices: a classical voltage doubler circuits with and without matching network and a commercially available energy harvesting device – Powercast P2110B are selected for the study. The use of a software-defined radio (SDR) for generation of sub-GHz signals allows to achieve high accuracy and customization of waveforms. The analysis of RF-to-DC conversion efficiency is based on the results of measurements of the input average power and DC voltage in laboratory conditions. The impact of the PAPR level and input average power level on the RF-to-DC conversion efficiency is investigated. Moreover, the results of RF-to-DC conversion for high PAPR signals are compared to the case when a low PAPR single-carrier waveform is used.","PeriodicalId":198244,"journal":{"name":"2018 IEEE 6th Workshop on Advances in Information, Electronic and Electrical Engineering (AIEEE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126434321","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 : 2018-11-01DOI: 10.1109/aieee.2018.8592085
Jānis Pekša
{"title":"Forecasting using Contextual Data in Road Maintenance Work","authors":"Jānis Pekša","doi":"10.1109/aieee.2018.8592085","DOIUrl":"https://doi.org/10.1109/aieee.2018.8592085","url":null,"abstract":"","PeriodicalId":198244,"journal":{"name":"2018 IEEE 6th Workshop on Advances in Information, Electronic and Electrical Engineering (AIEEE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128142205","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：