Saša S. Nikolić, Miroslav B. Milovanović, Nikola B. Dankovic, D. Mitic, S. Peric, Andjela D. Djordjevic, Petar S. Djekic
Hammerstein-Wiener systems present a structure consisting of three serial cascade blocks. Two are static nonlinearities, which can be described with nonlinear functions. The third block represents a linear dynamic component placed between the first two blocks. Some of the common linear model structures include a rational-type transfer function, orthogonal rational functions (ORF), finite impulse response (FIR), autoregressive with extra input (ARX), autoregressive moving average with exogenous inputs model (ARMAX), and output-error (O-E) model structure. This paper presents a new structure, and a new improvement is proposed, which is consisted of the basic structure of Hammerstein-Wiener models with an improved orthogonal function of Müntz-Legendre type. We present an extension of generalised Malmquist polynomials that represent Müntz polynomials. Also, a detailed mathematical background for performing improved almost orthogonal polynomials, in combination with Hammerstein-Wiener models, is proposed. The proposed approach is used to identify the strongly nonlinear hydraulic system via the transfer function. To compare the results obtained, well-known orthogonal functions of the Legendre, Chebyshev, and Laguerre types are exploited.
{"title":"Identification of Nonlinear Systems Using the Hammerstein-Wiener Model with Improved Orthogonal Functions","authors":"Saša S. Nikolić, Miroslav B. Milovanović, Nikola B. Dankovic, D. Mitic, S. Peric, Andjela D. Djordjevic, Petar S. Djekic","doi":"10.5755/j02.eie.33838","DOIUrl":"https://doi.org/10.5755/j02.eie.33838","url":null,"abstract":"Hammerstein-Wiener systems present a structure consisting of three serial cascade blocks. Two are static nonlinearities, which can be described with nonlinear functions. The third block represents a linear dynamic component placed between the first two blocks. Some of the common linear model structures include a rational-type transfer function, orthogonal rational functions (ORF), finite impulse response (FIR), autoregressive with extra input (ARX), autoregressive moving average with exogenous inputs model (ARMAX), and output-error (O-E) model structure. This paper presents a new structure, and a new improvement is proposed, which is consisted of the basic structure of Hammerstein-Wiener models with an improved orthogonal function of Müntz-Legendre type. We present an extension of generalised Malmquist polynomials that represent Müntz polynomials. Also, a detailed mathematical background for performing improved almost orthogonal polynomials, in combination with Hammerstein-Wiener models, is proposed. The proposed approach is used to identify the strongly nonlinear hydraulic system via the transfer function. To compare the results obtained, well-known orthogonal functions of the Legendre, Chebyshev, and Laguerre types are exploited.","PeriodicalId":51031,"journal":{"name":"Elektronika Ir Elektrotechnika","volume":" ","pages":""},"PeriodicalIF":1.3,"publicationDate":"2023-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44295026","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
S. R. U. N. Jafri, Tariq Rehman, Asif Ahmed, Muhammad Shahzad Siddiqi, Asad Hayat, Tehniyat Saeed
This paper presents a motorbike-based custom made scanning and mapping system for surveying slums and highly populated urban regions. These vicinities are difficult to reach through standard vehicular scanning systems and require a compact solution as presented in this paper. The system consists of two small range 2D Hokuyo laser scanners mounted in right angle orientations to capture the environment. In addition, the global positioning system, the wheel encoder, the inertial measurement unit, and cameras have been integrated with the system to estimate the pose and visual information. Sensorial information has been used to localise the system using Kalman Filtering. Later, by applying the standard transformations, the 3D point cloud map of the surveyed vicinity has been developed. The scanning system has been tested at various locations including densely populated and slum regions. Precise and detailed 3D mapping results have been obtained, which are further extensively analysed to understand the built structure and the road furniture. The working of the system is found to be quite economical and faster than that of local urban surveying systems.
{"title":"Slum Terrain Mapping Using Low-Cost 2D Laser Scanners","authors":"S. R. U. N. Jafri, Tariq Rehman, Asif Ahmed, Muhammad Shahzad Siddiqi, Asad Hayat, Tehniyat Saeed","doi":"10.5755/j02.eie.33884","DOIUrl":"https://doi.org/10.5755/j02.eie.33884","url":null,"abstract":"This paper presents a motorbike-based custom made scanning and mapping system for surveying slums and highly populated urban regions. These vicinities are difficult to reach through standard vehicular scanning systems and require a compact solution as presented in this paper. The system consists of two small range 2D Hokuyo laser scanners mounted in right angle orientations to capture the environment. In addition, the global positioning system, the wheel encoder, the inertial measurement unit, and cameras have been integrated with the system to estimate the pose and visual information. Sensorial information has been used to localise the system using Kalman Filtering. Later, by applying the standard transformations, the 3D point cloud map of the surveyed vicinity has been developed. The scanning system has been tested at various locations including densely populated and slum regions. Precise and detailed 3D mapping results have been obtained, which are further extensively analysed to understand the built structure and the road furniture. The working of the system is found to be quite economical and faster than that of local urban surveying systems.","PeriodicalId":51031,"journal":{"name":"Elektronika Ir Elektrotechnika","volume":" ","pages":""},"PeriodicalIF":1.3,"publicationDate":"2023-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41382213","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The use of renewable energy sources contributes to environmental awareness and sustainable development policy. The inexhaustible and nonpolluting nature of solar energy has attracted worldwide attention. Accurate forecasting of solar power is vital for the reliability and stability of power systems. However, the effect of the intermittency nature of solar radiation makes the development of accurate prediction models challenging. This paper presents a hybrid model based on Kernel Extreme Learning Machine (Kernel-ELM) and Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) for short-term solar power forecasting. The decomposition technique increases the number of stable, stationary, and regular patterns of the original signals. Each decomposed signal is fed into Kernel-ELM. To validate the performance of the hybrid model, solar power data from the BSEU Renewable Energy Laboratory, measured at 5-minute intervals, are used. To validate the proposed model, its performance is compared to some state-of-the-art forecasting models with seasonal data. The results highlight the good performance of the proposed hybrid model compared to other classical algorithms according to the metrics.
{"title":"Short-Term Solar Power Forecasting Based on CEEMDAN and Kernel Extreme Learning Machine","authors":"Ali Riza Gun, Emrah Dokur, U. Yuzgec, M. Kurban","doi":"10.5755/j02.eie.33856","DOIUrl":"https://doi.org/10.5755/j02.eie.33856","url":null,"abstract":"The use of renewable energy sources contributes to environmental awareness and sustainable development policy. The inexhaustible and nonpolluting nature of solar energy has attracted worldwide attention. Accurate forecasting of solar power is vital for the reliability and stability of power systems. However, the effect of the intermittency nature of solar radiation makes the development of accurate prediction models challenging. This paper presents a hybrid model based on Kernel Extreme Learning Machine (Kernel-ELM) and Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) for short-term solar power forecasting. The decomposition technique increases the number of stable, stationary, and regular patterns of the original signals. Each decomposed signal is fed into Kernel-ELM. To validate the performance of the hybrid model, solar power data from the BSEU Renewable Energy Laboratory, measured at 5-minute intervals, are used. To validate the proposed model, its performance is compared to some state-of-the-art forecasting models with seasonal data. The results highlight the good performance of the proposed hybrid model compared to other classical algorithms according to the metrics.","PeriodicalId":51031,"journal":{"name":"Elektronika Ir Elektrotechnika","volume":" ","pages":""},"PeriodicalIF":1.3,"publicationDate":"2023-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46533975","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Agriculture is crucial to economic growth and development, and maintaining high-quality, disease-free plants is crucial to its success. Early detection of plant diseases, which can be caused by environmental factors, fungi, bacteria, and viruses, is essential to implement appropriate treatments. Tomatoes, which are one of the most vital food crops, are susceptible to diseases that can result in significant economic losses in agriculture. This study introduces a method to evaluate the health of tomato leaf using image processing techniques and machine learning algorithms. A dataset of 1,778 images of healthy and infected tomato leaves was collected from tomato planting areas in the Turkish provinces of Samsun and Mersin. Sixteen advanced machine learning algorithms were used for classification, and the optimal hyperparameters for each algorithm were determined using a grid search approach. The classifiers were executed on Jetson Nano and TX2 embedded systems. The experimental results indicate that the Random Forest classifier outperformed other algorithms, achieving approximately 99 % accuracy in detecting and classifying the health status of tomato leaves. The proposed system enables faster and more accurate detection, allowing farmers to classify plants as infected or healthy, ultimately improving decision-making on treatment and pest management strategies.
{"title":"A Fast and Accurate Method for Classifying Tomato Plant Health Status Using Machine Learning and Image Processing","authors":"H. Ulutaş, V. Aslantaş","doi":"10.5755/j02.eie.33866","DOIUrl":"https://doi.org/10.5755/j02.eie.33866","url":null,"abstract":"Agriculture is crucial to economic growth and development, and maintaining high-quality, disease-free plants is crucial to its success. Early detection of plant diseases, which can be caused by environmental factors, fungi, bacteria, and viruses, is essential to implement appropriate treatments. Tomatoes, which are one of the most vital food crops, are susceptible to diseases that can result in significant economic losses in agriculture.\u0000This study introduces a method to evaluate the health of tomato leaf using image processing techniques and machine learning algorithms. A dataset of 1,778 images of healthy and infected tomato leaves was collected from tomato planting areas in the Turkish provinces of Samsun and Mersin. Sixteen advanced machine learning algorithms were used for classification, and the optimal hyperparameters for each algorithm were determined using a grid search approach. The classifiers were executed on Jetson Nano and TX2 embedded systems.\u0000The experimental results indicate that the Random Forest classifier outperformed other algorithms, achieving approximately 99 % accuracy in detecting and classifying the health status of tomato leaves. The proposed system enables faster and more accurate detection, allowing farmers to classify plants as infected or healthy, ultimately improving decision-making on treatment and pest management strategies.","PeriodicalId":51031,"journal":{"name":"Elektronika Ir Elektrotechnika","volume":" ","pages":""},"PeriodicalIF":1.3,"publicationDate":"2023-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46407359","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ferhat Kilic, Murat Korkmaz, Orhan Er, Cemil Altin
Caudal epidural anaesthesia is usually the most well-known technique in obstetrics to deal with chronic back pain. Due to variations in the shape and size of the sacral hiatus (SH), its classification is a crucial and challenging task. Clinically, it is required in trauma, where surgeons must make fast and correct selections. Past studies have focused on morphometric and statistical analysis to classify it. Therefore, it is vital to automatically and accurately classify SH types through deep learning methods. To this end, we proposed the Multi-Task Process (MTP), a novel classification approach to classify the SH MTP that initially uses a small medical tabular data set obtained by manual feature extraction on computed tomography scans of the sacrums. Second, it augments the data set synthetically through a Generative Adversarial Network (GAN). In addition, it adapts a two-dimensional (2D) embedding algorithm to convert tabular features into images. Finally, it feeds images into Convolutional Neural Networks (CNNs). The application of MTP to six CNN models achieved remarkable classification success rates of approximately 90 % to 93 %. The proposed MTP approach eliminates the small medical tabular data problem that results in bone classification on deep models.
{"title":"A CNN-Based Novel Approach for Classification of Sacral Hiatus with GAN-Powered Tabular Data Set","authors":"Ferhat Kilic, Murat Korkmaz, Orhan Er, Cemil Altin","doi":"10.5755/j02.eie.33852","DOIUrl":"https://doi.org/10.5755/j02.eie.33852","url":null,"abstract":"Caudal epidural anaesthesia is usually the most well-known technique in obstetrics to deal with chronic back pain. Due to variations in the shape and size of the sacral hiatus (SH), its classification is a crucial and challenging task. Clinically, it is required in trauma, where surgeons must make fast and correct selections. Past studies have focused on morphometric and statistical analysis to classify it. Therefore, it is vital to automatically and accurately classify SH types through deep learning methods. To this end, we proposed the Multi-Task Process (MTP), a novel classification approach to classify the SH MTP that initially uses a small medical tabular data set obtained by manual feature extraction on computed tomography scans of the sacrums. Second, it augments the data set synthetically through a Generative Adversarial Network (GAN). In addition, it adapts a two-dimensional (2D) embedding algorithm to convert tabular features into images. Finally, it feeds images into Convolutional Neural Networks (CNNs). The application of MTP to six CNN models achieved remarkable classification success rates of approximately 90 % to 93 %. The proposed MTP approach eliminates the small medical tabular data problem that results in bone classification on deep models.","PeriodicalId":51031,"journal":{"name":"Elektronika Ir Elektrotechnika","volume":" ","pages":""},"PeriodicalIF":1.3,"publicationDate":"2023-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43379933","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yasin Genç, Cagatay Korkuc, Nilay Aytas, E. Afacan, M. H. Sazli, E. Yazgan
This paper proposes a novel bilinear pairing-free identity-based privacy-preserving anonymous authentication scheme for vehicle-to-vehicle (V2V) communication, called “NIBPA”. Today, vehicular ad hoc networks (VANETs) offer important solutions for traffic safety and efficiency. However, VANETs are vulnerable to cyberattacks due to their use of wireless communication. Therefore, authentication schemes are used to solve security and privacy issues in VANETs. The NIBPA satisfies the security and privacy requirements and is robust to cyberattacks. It is also a pairing-free elliptic curve cryptography (ECC)-based lightweight authentication scheme. The bilinear pairing operation and the map-to-point hash function in cryptography have not been used because of their high computational costs. Moreover, it provides batch message verification to improve VANETs performance. The NIBPA is compared to existing schemes in terms of computational cost and communication cost. It is also a test for security in the random oracle model (ROM). As a result of security and performance analysis, NIBPA gives better results compared to existing schemes.
{"title":"A Novel Identity-Based Privacy-Preserving Anonymous Authentication Scheme for Vehicle-to-Vehicle Communication","authors":"Yasin Genç, Cagatay Korkuc, Nilay Aytas, E. Afacan, M. H. Sazli, E. Yazgan","doi":"10.5755/j02.eie.30990","DOIUrl":"https://doi.org/10.5755/j02.eie.30990","url":null,"abstract":"This paper proposes a novel bilinear pairing-free identity-based privacy-preserving anonymous authentication scheme for vehicle-to-vehicle (V2V) communication, called “NIBPA”. Today, vehicular ad hoc networks (VANETs) offer important solutions for traffic safety and efficiency. However, VANETs are vulnerable to cyberattacks due to their use of wireless communication. Therefore, authentication schemes are used to solve security and privacy issues in VANETs. The NIBPA satisfies the security and privacy requirements and is robust to cyberattacks. It is also a pairing-free elliptic curve cryptography (ECC)-based lightweight authentication scheme. The bilinear pairing operation and the map-to-point hash function in cryptography have not been used because of their high computational costs. Moreover, it provides batch message verification to improve VANETs performance. The NIBPA is compared to existing schemes in terms of computational cost and communication cost. It is also a test for security in the random oracle model (ROM). As a result of security and performance analysis, NIBPA gives better results compared to existing schemes.","PeriodicalId":51031,"journal":{"name":"Elektronika Ir Elektrotechnika","volume":" ","pages":""},"PeriodicalIF":1.3,"publicationDate":"2023-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42521453","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
J. Papán, I. Bridova, P. Brida, Michal Hraska, Slavomir Tatarka, Oleksandra Yeremenko
Currently, network requirements are placed on the efficiency and size of the networks. These conditions can be ensured by modern converged networks that integrate the functions of both data and telecommunication networks. Line or router failures have always been a part of transmission networks, which is no different from converged networks. As a result of outages, which can take from ms to tens of seconds, packets are lost. These outages cause degraded transmission quality, which is undesirable when transmitting real-time multimedia services (Voice over IP, video). To solve the mentioned problems, the IETF organization has developed IP Fast Reroute mechanisms to minimise the time to restore the connection after a line or node failure and, consequently, less packet loss. The article reviews and compares the latest IP Fast Reroute mechanisms deployed in the last three years. First, we have Optimistic Fast Rerouting, which calculates optimistic and fallback scenarios. The second is Post-processing Fast Reroute, which decomposes the network according to metrics such as load and route length. Third, Local Fast Reroute focused on low congestion and random access.
{"title":"Comparison of New Solutions in IP Fast Reroute","authors":"J. Papán, I. Bridova, P. Brida, Michal Hraska, Slavomir Tatarka, Oleksandra Yeremenko","doi":"10.5755/j02.eie.33863","DOIUrl":"https://doi.org/10.5755/j02.eie.33863","url":null,"abstract":"Currently, network requirements are placed on the efficiency and size of the networks. These conditions can be ensured by modern converged networks that integrate the functions of both data and telecommunication networks. Line or router failures have always been a part of transmission networks, which is no different from converged networks. As a result of outages, which can take from ms to tens of seconds, packets are lost. These outages cause degraded transmission quality, which is undesirable when transmitting real-time multimedia services (Voice over IP, video). To solve the mentioned problems, the IETF organization has developed IP Fast Reroute mechanisms to minimise the time to restore the connection after a line or node failure and, consequently, less packet loss.\u0000The article reviews and compares the latest IP Fast Reroute mechanisms deployed in the last three years. First, we have Optimistic Fast Rerouting, which calculates optimistic and fallback scenarios. The second is Post-processing Fast Reroute, which decomposes the network according to metrics such as load and route length. Third, Local Fast Reroute focused on low congestion and random access.","PeriodicalId":51031,"journal":{"name":"Elektronika Ir Elektrotechnika","volume":" ","pages":""},"PeriodicalIF":1.3,"publicationDate":"2023-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47538642","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Austėja Dapkutė, V. Siozinys, Martynas Jonaitis, Mantas Kaminickas, M. Siozinys
This paper presents a novel approach to applying the Virtual Power Plant (VPP) concept and for the Cost-Reflective Network Charging Tariff. The paper proposes an innovative energy trade concept based on current research and literature analysis. The technical novelty of the paper is motivated by reviewing the current developments in the Lithuanian renewable energy sector and related research on VPPs and cost-reflective pricing. The components of the VPP, including balancing of generation and consumption profiles, load forecasting, and solar generation predicted, are thoroughly described, along with a method for determining the network and VPP costs. An optimisation algorithm for cost optimisation is also presented. The paper concludes by demonstrating the implementation and operation of the EA-SAS Cloud Virtual Power Plant platform, which represents a significant contribution to the field of smart energy management.
{"title":"Virtual Power Plant as a Tool for Cost-Reflective Network Charging Tariff","authors":"Austėja Dapkutė, V. Siozinys, Martynas Jonaitis, Mantas Kaminickas, M. Siozinys","doi":"10.5755/j02.eie.33885","DOIUrl":"https://doi.org/10.5755/j02.eie.33885","url":null,"abstract":"This paper presents a novel approach to applying the Virtual Power Plant (VPP) concept and for the Cost-Reflective Network Charging Tariff. The paper proposes an innovative energy trade concept based on current research and literature analysis. The technical novelty of the paper is motivated by reviewing the current developments in the Lithuanian renewable energy sector and related research on VPPs and cost-reflective pricing. The components of the VPP, including balancing of generation and consumption profiles, load forecasting, and solar generation predicted, are thoroughly described, along with a method for determining the network and VPP costs. An optimisation algorithm for cost optimisation is also presented. The paper concludes by demonstrating the implementation and operation of the EA-SAS Cloud Virtual Power Plant platform, which represents a significant contribution to the field of smart energy management.","PeriodicalId":51031,"journal":{"name":"Elektronika Ir Elektrotechnika","volume":" ","pages":""},"PeriodicalIF":1.3,"publicationDate":"2023-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43222833","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
V. Kolář, Lukáš Demel, R. Hrbác, J. Ciganek, S. Zajaczek, M. Durica
Estimating the electric power used by railway vehicles is an important factor in the planning of future power consumption, looking for possibilities to reduce the use of electric power and therefore also reduce carbon emissions. To improve the estimation, we used the imperialist competitive algorithm in the optimisation process of a mathematical model of a tram vehicle. Specifically, in the setting of the proportional and summation constant of the vehicle speed controller which emulates the activity of the driver in the simulation. Our work presents a new approach to optimising the estimation of energy consumption in tram transport. The method used is based on mathematical modelling and simulation of social development in human society. To obtain the input data for the simulation, we performed a measurement of the reference speed by means of a GPS receiver located in a sample tram vehicle. Subsequently, to verify the model and energy calculation results, we measured the output currents and voltage from the traction converter station at the corresponding time. Our method achieved a 93 % match between the measured and simulated power consumption.
{"title":"The Use of the Imperialist Competitive Algorithm in Optimising the Setting of the Tram Speed Controller in the Development of a Matlab-Simulink Environment","authors":"V. Kolář, Lukáš Demel, R. Hrbác, J. Ciganek, S. Zajaczek, M. Durica","doi":"10.5755/j02.eie.33896","DOIUrl":"https://doi.org/10.5755/j02.eie.33896","url":null,"abstract":"Estimating the electric power used by railway vehicles is an important factor in the planning of future power consumption, looking for possibilities to reduce the use of electric power and therefore also reduce carbon emissions. To improve the estimation, we used the imperialist competitive algorithm in the optimisation process of a mathematical model of a tram vehicle. Specifically, in the setting of the proportional and summation constant of the vehicle speed controller which emulates the activity of the driver in the simulation. Our work presents a new approach to optimising the estimation of energy consumption in tram transport. The method used is based on mathematical modelling and simulation of social development in human society. To obtain the input data for the simulation, we performed a measurement of the reference speed by means of a GPS receiver located in a sample tram vehicle. Subsequently, to verify the model and energy calculation results, we measured the output currents and voltage from the traction converter station at the corresponding time. Our method achieved a 93 % match between the measured and simulated power consumption.","PeriodicalId":51031,"journal":{"name":"Elektronika Ir Elektrotechnika","volume":" ","pages":""},"PeriodicalIF":1.3,"publicationDate":"2023-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47106371","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In deep learning (DL), the deep generative model is helpful for data augmentation objectives to tackle the lack of datasets that have a significant impact on learning performance. Data augmentation or synthesis is expected to solve the issue in a small/sparse database. The problem of databasing also exists in the fingerprint-based indoor localisation system. The dense offline fingerprint database must be constructed with the accuracy requirement. However, this will affect the high cost, massive laborious work, and increase the complexity of the system. Therefore, this paper proposes to address these issues by generating synthetic data via a deep generative model. The generative adversarial network (GAN) is selected to generate the synthetic fingerprint database for indoor localisation. Our database consideration consists of power-based parameters, i.e., the received signal strength indicator (RSSI) from Wi-Fi devices obtained from the actual measurement campaign. Some of the literature mainly discusses how GAN works in a vast and complex dataset. Here, we consider applying GAN in a relatively small dataset and for a simple setup. Our results show that by only using the 20 % fraction of actual RSSI data combined with the synthetic RSSI, the accuracy validation performance is slightly higher than when using all actual data usage. Moreover, in only 60 % of actual data usage and in combination with 625 samples of synthetic data, the accuracy performance is improved to 0.73 (1.37 times higher than the use of all actual data, 0.53). Thus, this result proves that the challenges of offline fingerprint databases can be alleviated by data synthesis through GAN by using only a small dataset.
{"title":"Synthesis of a Small Fingerprint Database through a Deep Generative Model for Indoor Localisation","authors":"Dwi Joko Suroso, P. Cherntanomwong, P. Sooraksa","doi":"10.5755/j02.eie.31905","DOIUrl":"https://doi.org/10.5755/j02.eie.31905","url":null,"abstract":"In deep learning (DL), the deep generative model is helpful for data augmentation objectives to tackle the lack of datasets that have a significant impact on learning performance. Data augmentation or synthesis is expected to solve the issue in a small/sparse database. The problem of databasing also exists in the fingerprint-based indoor localisation system. The dense offline fingerprint database must be constructed with the accuracy requirement. However, this will affect the high cost, massive laborious work, and increase the complexity of the system. Therefore, this paper proposes to address these issues by generating synthetic data via a deep generative model. The generative adversarial network (GAN) is selected to generate the synthetic fingerprint database for indoor localisation. Our database consideration consists of power-based parameters, i.e., the received signal strength indicator (RSSI) from Wi-Fi devices obtained from the actual measurement campaign. Some of the literature mainly discusses how GAN works in a vast and complex dataset. Here, we consider applying GAN in a relatively small dataset and for a simple setup. Our results show that by only using the 20 % fraction of actual RSSI data combined with the synthetic RSSI, the accuracy validation performance is slightly higher than when using all actual data usage. Moreover, in only 60 % of actual data usage and in combination with 625 samples of synthetic data, the accuracy performance is improved to 0.73 (1.37 times higher than the use of all actual data, 0.53). Thus, this result proves that the challenges of offline fingerprint databases can be alleviated by data synthesis through GAN by using only a small dataset.","PeriodicalId":51031,"journal":{"name":"Elektronika Ir Elektrotechnika","volume":" ","pages":""},"PeriodicalIF":1.3,"publicationDate":"2023-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49272230","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","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：