Human activity recognition (HAR) by deep learning is a challenging and interesting topic. Although there are robust models, there is also a bunch of parameters and variables, which affect the performance such as the number of layers, pooling type. This study presents a new deep learning architecture that is obtained by fine-tuning of the conventional CNN-LSTM model, namely, CNN (+3)-LSTM. Three changes are made to the conventional model to increase the accuracy. Firstly, kernel size is set to 1×1 to extract more information. Secondly, three convolutional layers are added to the model. Lastly, average pooling is used instead of max-pooling. Performance analysis of the proposed model is conducted on the KTH dataset and implemented on Keras. In addition to the overall accuracy of the proposed model, the contribution of each change is observed individually. Results show that adding layers made the highest contribution followed by kernel size and pooling, respectively. The proposed model is compared with state-of-art and outperformed some of the recent studies with a 94.1% recognition rate.
{"title":"Human activity recognition with fine-tuned CNN-LSTM","authors":"Erdal Genc, M. E. Yıldırım, Y. B. Salman","doi":"10.2478/jee-2024-0002","DOIUrl":"https://doi.org/10.2478/jee-2024-0002","url":null,"abstract":"\u0000 Human activity recognition (HAR) by deep learning is a challenging and interesting topic. Although there are robust models, there is also a bunch of parameters and variables, which affect the performance such as the number of layers, pooling type. This study presents a new deep learning architecture that is obtained by fine-tuning of the conventional CNN-LSTM model, namely, CNN (+3)-LSTM. Three changes are made to the conventional model to increase the accuracy. Firstly, kernel size is set to 1×1 to extract more information. Secondly, three convolutional layers are added to the model. Lastly, average pooling is used instead of max-pooling. Performance analysis of the proposed model is conducted on the KTH dataset and implemented on Keras. In addition to the overall accuracy of the proposed model, the contribution of each change is observed individually. Results show that adding layers made the highest contribution followed by kernel size and pooling, respectively. The proposed model is compared with state-of-art and outperformed some of the recent studies with a 94.1% recognition rate.","PeriodicalId":508697,"journal":{"name":"Journal of Electrical Engineering","volume":"41 6","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139888396","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}
The all-optical switching phenomena in the non-linear directional coupler using cross-phase modulation (XPM) effect have been proposed. It is designed to generate an all-optical XOR functionality, considering the XOR logic gates as a basic module the design and analysis of an efficient all-optical 4-bit binary to gray code converter and 4-bit even parity checker circuit is proposed. The design methodology includes the switching of a weak continuous-wave (CW) signal, which is controlled by the combination of two controlled pump signals. In this paper, mathematical analysis of the coupled mode theory associated with optical directional couplers has been discussed. The switching characteristics of XPM effect based All-optical directional couplers have been examined for appropriate values of the controlled pump signals. Appropriate values of extinction ratio and corresponding controlled pump signal levels are investigated for an efficient generation of XOR logic gates. Further, the detailed analysis of layout generation and design aspects of All-optical 4-bit binary to gray code converter and 4-bit even parity checker circuits have been carried out. The proposed methodology is verified by the appropriate simulation results, which include the transmittivity, extinction ratio (Xratio) curve variation and dynamic time domain plot associated with proposed units.
{"title":"Harnessing XPM effects in non-linear directional couplers for 4-bit gray code conversion and even parity verification","authors":"Ajay Yadav, Ajay Kumar, Amit Prakash","doi":"10.2478/jee-2024-0003","DOIUrl":"https://doi.org/10.2478/jee-2024-0003","url":null,"abstract":"\u0000 The all-optical switching phenomena in the non-linear directional coupler using cross-phase modulation (XPM) effect have been proposed. It is designed to generate an all-optical XOR functionality, considering the XOR logic gates as a basic module the design and analysis of an efficient all-optical 4-bit binary to gray code converter and 4-bit even parity checker circuit is proposed. The design methodology includes the switching of a weak continuous-wave (CW) signal, which is controlled by the combination of two controlled pump signals. In this paper, mathematical analysis of the coupled mode theory associated with optical directional couplers has been discussed. The switching characteristics of XPM effect based All-optical directional couplers have been examined for appropriate values of the controlled pump signals. Appropriate values of extinction ratio and corresponding controlled pump signal levels are investigated for an efficient generation of XOR logic gates. Further, the detailed analysis of layout generation and design aspects of All-optical 4-bit binary to gray code converter and 4-bit even parity checker circuits have been carried out. The proposed methodology is verified by the appropriate simulation results, which include the transmittivity, extinction ratio (Xratio) curve variation and dynamic time domain plot associated with proposed units.","PeriodicalId":508697,"journal":{"name":"Journal of Electrical Engineering","volume":"38 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139891994","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}
Zuzana Košelová, Lenka Horáková, D. Burda, Mohammad M. Allaham, A. Knápek, Z. Fohlerova
This study investigates the crucial process of cleaning cold field emission electron emitters and scanning tunnel microscopy (STM) probes, particularly focusing on tungsten tips. The cleanliness of these tips is essential for maintaining optimal cathode properties, preventing impurities that can significantly affect the emission process. Various cleaning methods, including macroetching, ammonia cleaning, and hydrofluoric acid (HF) cleaning were explored and compared by scanning electron microscopy. The macroetching method, involving a mixture of hydrochloric acid, nitric acid, and hydrogen fluoride, proved to be too reactive, causing significant material removal and altering the tip’s structure. Ammonia cleaning did not significantly improve or harm the samples. However, oxide islands appeared in some areas, suggesting the potential formation of ammonium tungsten oxide. HF cleaning, specifically at 20% and 50% concentrations, demonstrated effectiveness in removing tungsten oxides without damaging the tip. Pre-cleaning with water and ethanol proved beneficial for subsequent HF refinement. Results suggest that HF is the most suitable method for oxide removal but a rinse with water is essential for removing residual sodium hydroxide. To maintain optimal properties, it is crucial to apply a less reactive layer quickly or transfer the tips to a water/ethanol bath to prevent oxidation.
{"title":"Cleaning of tungsten tips for subsequent use as cold field emitters or STM probes","authors":"Zuzana Košelová, Lenka Horáková, D. Burda, Mohammad M. Allaham, A. Knápek, Z. Fohlerova","doi":"10.2478/jee-2024-0006","DOIUrl":"https://doi.org/10.2478/jee-2024-0006","url":null,"abstract":"\u0000 This study investigates the crucial process of cleaning cold field emission electron emitters and scanning tunnel microscopy (STM) probes, particularly focusing on tungsten tips. The cleanliness of these tips is essential for maintaining optimal cathode properties, preventing impurities that can significantly affect the emission process. Various cleaning methods, including macroetching, ammonia cleaning, and hydrofluoric acid (HF) cleaning were explored and compared by scanning electron microscopy. The macroetching method, involving a mixture of hydrochloric acid, nitric acid, and hydrogen fluoride, proved to be too reactive, causing significant material removal and altering the tip’s structure. Ammonia cleaning did not significantly improve or harm the samples. However, oxide islands appeared in some areas, suggesting the potential formation of ammonium tungsten oxide. HF cleaning, specifically at 20% and 50% concentrations, demonstrated effectiveness in removing tungsten oxides without damaging the tip. Pre-cleaning with water and ethanol proved beneficial for subsequent HF refinement. Results suggest that HF is the most suitable method for oxide removal but a rinse with water is essential for removing residual sodium hydroxide. To maintain optimal properties, it is crucial to apply a less reactive layer quickly or transfer the tips to a water/ethanol bath to prevent oxidation.","PeriodicalId":508697,"journal":{"name":"Journal of Electrical Engineering","volume":"19 6","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139828465","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}
The primary application of codes with locality and availability in distributed storage is for data recovery in case that data are lost on some damaged servers. Locality enables the recovery of lost data by contacting only a restricted number of remaining servers. Availability means that more than one subset of servers providing locality is available for data recovery for each server. The secondary application of these codes in distributed storage is to allow access to hot data in times of high demand. In this paper it is shown that the binary linear [14, 4, 7] code has locality 2 and availability 6 and it can be interpreted as a three-dimensional graph obtained from a [7, 3, 4] Simplex code. It is achieving upper bounds on basic parameters for codes with all-symbols locality and availability. This code can be a building element of more complex codes with scalability inspired by three-dimensional structures. The availability spectrum is introduced as a tool for analyzing codes with locality and availability.
{"title":"Linear block code with locality and availability inspired by tetrahedron","authors":"Peter Farkaš","doi":"10.2478/jee-2024-0010","DOIUrl":"https://doi.org/10.2478/jee-2024-0010","url":null,"abstract":"\u0000 The primary application of codes with locality and availability in distributed storage is for data recovery in case that data are lost on some damaged servers. Locality enables the recovery of lost data by contacting only a restricted number of remaining servers. Availability means that more than one subset of servers providing locality is available for data recovery for each server. The secondary application of these codes in distributed storage is to allow access to hot data in times of high demand. In this paper it is shown that the binary linear [14, 4, 7] code has locality 2 and availability 6 and it can be interpreted as a three-dimensional graph obtained from a [7, 3, 4] Simplex code. It is achieving upper bounds on basic parameters for codes with all-symbols locality and availability. This code can be a building element of more complex codes with scalability inspired by three-dimensional structures. The availability spectrum is introduced as a tool for analyzing codes with locality and availability.","PeriodicalId":508697,"journal":{"name":"Journal of Electrical Engineering","volume":"8 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139890559","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}
Abstract Accurate sitting posture recognition plays a crucial role in improving improper postures and reducing the risk of associated health issues. The inherent complexity of human behavior, however, poses a great challenge to the development of a practical sitting posture monitoring system with pressure sensors. Towards facilitating the use of features, choice of classification models, and way of evaluating a sitting posture recognizer, in this study a comparative study on pressure-sensor-based sitting posture monitoring is conducted. Specifically, we extract discriminant features from the sensor data based on the distribution of pressure sensors and explore different combinations of these features. Then, five commonly used classification models are evaluated towards building a robust sitting posture recognizer. Finally, extensive comparative experiments concerning four performance metrics are conducted on the collected datasets in subject-dependent, subject-independent, and cross-subject settings. Results show that the joint use of sensors at different positions leads to higher accuracy and that random forest generally outperforms the other four classification models. Surprisingly, compared to the subject-dependent and subject-independent settings, cross-subject setting greatly suffers from degraded accuracy, where we preliminarily present the results of transfer learning techniques to mitigate this issue. In addition, we perform parameter sensitivity and time-cost analysis of random forest, which indicates its applicability to practical use.
{"title":"A comparative study on real-time sitting posture monitoring systems using pressure sensors","authors":"Liang Zhao, Jingyu Yan, Aiguo Wang","doi":"10.2478/jee-2023-0055","DOIUrl":"https://doi.org/10.2478/jee-2023-0055","url":null,"abstract":"Abstract Accurate sitting posture recognition plays a crucial role in improving improper postures and reducing the risk of associated health issues. The inherent complexity of human behavior, however, poses a great challenge to the development of a practical sitting posture monitoring system with pressure sensors. Towards facilitating the use of features, choice of classification models, and way of evaluating a sitting posture recognizer, in this study a comparative study on pressure-sensor-based sitting posture monitoring is conducted. Specifically, we extract discriminant features from the sensor data based on the distribution of pressure sensors and explore different combinations of these features. Then, five commonly used classification models are evaluated towards building a robust sitting posture recognizer. Finally, extensive comparative experiments concerning four performance metrics are conducted on the collected datasets in subject-dependent, subject-independent, and cross-subject settings. Results show that the joint use of sensors at different positions leads to higher accuracy and that random forest generally outperforms the other four classification models. Surprisingly, compared to the subject-dependent and subject-independent settings, cross-subject setting greatly suffers from degraded accuracy, where we preliminarily present the results of transfer learning techniques to mitigate this issue. In addition, we perform parameter sensitivity and time-cost analysis of random forest, which indicates its applicability to practical use.","PeriodicalId":508697,"journal":{"name":"Journal of Electrical Engineering","volume":"37 5","pages":"474 - 484"},"PeriodicalIF":0.0,"publicationDate":"2023-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139191875","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}
V. T. Nguyen, Hong Viet Phuong Nguyen, Thi Bich Thanh Truong, Quang Vu Truong
Abstract The inertia in power systems plays a very important role in stabilizing the power system. With the growth of distributed generation (DG)/renewable energy source (RES) penetration in the power grid, there has been a concern about the lack of inertia in the power system. One of the solutions to solve the problem is to use the Virtual Synchronous Generator (VSG) control method. For energy storage, the Vehicle-to-grid (V2G) storage system can replace the traditional hybrid energy storage which consists of batteries and supercapacitors. This application will be implemented in Microgrid. The article will focus on simulating the Microgrid with the V2G system and solar energy as a renewable energy source, the inverters are controlled by the method of VSG control. The models will be simulated and the results will be shown on MATLAB/SIMULINK software.
{"title":"A virtual synchronous generator control method in microgrid with vehicle-to-grid system","authors":"V. T. Nguyen, Hong Viet Phuong Nguyen, Thi Bich Thanh Truong, Quang Vu Truong","doi":"10.2478/jee-2023-0057","DOIUrl":"https://doi.org/10.2478/jee-2023-0057","url":null,"abstract":"Abstract The inertia in power systems plays a very important role in stabilizing the power system. With the growth of distributed generation (DG)/renewable energy source (RES) penetration in the power grid, there has been a concern about the lack of inertia in the power system. One of the solutions to solve the problem is to use the Virtual Synchronous Generator (VSG) control method. For energy storage, the Vehicle-to-grid (V2G) storage system can replace the traditional hybrid energy storage which consists of batteries and supercapacitors. This application will be implemented in Microgrid. The article will focus on simulating the Microgrid with the V2G system and solar energy as a renewable energy source, the inverters are controlled by the method of VSG control. The models will be simulated and the results will be shown on MATLAB/SIMULINK software.","PeriodicalId":508697,"journal":{"name":"Journal of Electrical Engineering","volume":"3 1","pages":"492 - 502"},"PeriodicalIF":0.0,"publicationDate":"2023-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139191046","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}
Abstract Islanded microgrids with low-inertia distributed energy resources (DERs) are prone to frequency fluctuations. With the increasing integration of DERs in microgrids, the complexity of control and stability has also increased. Moreover, the integration of DERs into microgrids may result in a power imbalance between energy supply and demand during sudden changes in load or energy generation. This can cause frequency variations in the microgrid, which could have disastrous consequences such as equipment damage or even blackouts. This paper proposes a control strategy to ensure the efficient operation of an islanded hybrid microgrid consisting of a PV generator, battery energy storage system (BESS), and emergency diesel generator. According to Energy Exchange Model proposed in this paper, the hybrid system presented operates independently without being connected to the electrical grid, where the PV system and BESS act as the main energy sources, while the emergency diesel generator provides active power backup with voltage and frequency regulation. The novel in this paper is also that DER aids in frequency regulation during active power transients by delivering and absorbing active power in accordance with the inverter's suggested P droop control strategy. In this way inverter droop control decreases system frequency nadir emulating so called “synthetic inertia”. To design both the islanded hybrid system and the proposed control strategy, the MATLAB/Simulink environment is utilized. Based on the results, it can be concluded that the analyzed microgrid system is capable of maintaining stability and operating efficiently in a range of operating conditions.
摘要 采用低惯性分布式能源资源（DER）的孤岛微电网容易出现频率波动。随着 DER 在微电网中的集成度越来越高，控制和稳定性的复杂性也随之增加。此外，在负荷或发电量突然变化时，将 DER 集成到微电网中可能会导致能源供需之间的功率不平衡。这可能会导致微电网的频率变化，从而造成设备损坏甚至停电等灾难性后果。本文提出了一种控制策略，以确保由光伏发电机、电池储能系统（BESS）和应急柴油发电机组成的孤岛式混合微电网的高效运行。根据本文提出的能量交换模型，所介绍的混合系统可在不与电网连接的情况下独立运行，其中光伏系统和电池储能系统作为主要能源，而应急柴油发电机则提供具有电压和频率调节功能的有功备用电源。本文的新颖之处还在于，在有功功率瞬态期间，DER 可根据逆变器建议的 P 下垂控制策略提供和吸收有功功率，从而帮助进行频率调节。通过这种方式，逆变器下垂控制可降低系统频率低谷，模拟所谓的 "合成惯性"。为了设计孤岛式混合系统和建议的控制策略，使用了 MATLAB/Simulink 环境。根据结果可以得出结论，所分析的微电网系统能够在各种运行条件下保持稳定并高效运行。
{"title":"Voltage and frequency control of solar – battery – diesel based islanded microgrid","authors":"L. Vuić, J. Hivziefendic, M. Saric, Jakub Osmić","doi":"10.2478/jee-2023-0052","DOIUrl":"https://doi.org/10.2478/jee-2023-0052","url":null,"abstract":"Abstract Islanded microgrids with low-inertia distributed energy resources (DERs) are prone to frequency fluctuations. With the increasing integration of DERs in microgrids, the complexity of control and stability has also increased. Moreover, the integration of DERs into microgrids may result in a power imbalance between energy supply and demand during sudden changes in load or energy generation. This can cause frequency variations in the microgrid, which could have disastrous consequences such as equipment damage or even blackouts. This paper proposes a control strategy to ensure the efficient operation of an islanded hybrid microgrid consisting of a PV generator, battery energy storage system (BESS), and emergency diesel generator. According to Energy Exchange Model proposed in this paper, the hybrid system presented operates independently without being connected to the electrical grid, where the PV system and BESS act as the main energy sources, while the emergency diesel generator provides active power backup with voltage and frequency regulation. The novel in this paper is also that DER aids in frequency regulation during active power transients by delivering and absorbing active power in accordance with the inverter's suggested P droop control strategy. In this way inverter droop control decreases system frequency nadir emulating so called “synthetic inertia”. To design both the islanded hybrid system and the proposed control strategy, the MATLAB/Simulink environment is utilized. Based on the results, it can be concluded that the analyzed microgrid system is capable of maintaining stability and operating efficiently in a range of operating conditions.","PeriodicalId":508697,"journal":{"name":"Journal of Electrical Engineering","volume":"53 4","pages":"442 - 453"},"PeriodicalIF":0.0,"publicationDate":"2023-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139192146","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}
Veronika Kurilová, Dominika Bemberáková, Matúš Kocián, Daniel Šterbák, Tomáš Knapčok, Miriam Palkovič, Samuel Hančák, J. Pavlovičová, M. Oravec, Andrej Thurzo, Petr Kolář, N. Majtánová
Abstract Reconstruction of a 3D eye model by photogrammetry from a smartphone video could be prospectively used in self-diagnosis, screening and telemedicine monitoring of diseases of the front part of the eye and its surroundings. The main use could be found in the treatment of diseases of the curvature and surface of the cornea and in follow-up after some refractive procedures. In our work, we create 3D image-based models of the eye after scanning the face with a smartphone. An unexpected phenomenon appeared during the reconstruction of the transparent cornea – a crater-like depression was formed at the place where nearby objects reflected on the cornea, which corresponds to the first Purkinje image, the so-called glint. We thus encountered complications that may arise when modelling transparent living structures from a video taken in a normal environment, which will need to be solved if we want to create such 3D models of the eye using this method for medical purposes. Another 3D reconstruction approach or additional algorithms must be considered as a future work.
{"title":"Unexpected corneal reflection phenomenon alters smartphone 3D image-based models of the eye","authors":"Veronika Kurilová, Dominika Bemberáková, Matúš Kocián, Daniel Šterbák, Tomáš Knapčok, Miriam Palkovič, Samuel Hančák, J. Pavlovičová, M. Oravec, Andrej Thurzo, Petr Kolář, N. Majtánová","doi":"10.2478/jee-2023-0059","DOIUrl":"https://doi.org/10.2478/jee-2023-0059","url":null,"abstract":"Abstract Reconstruction of a 3D eye model by photogrammetry from a smartphone video could be prospectively used in self-diagnosis, screening and telemedicine monitoring of diseases of the front part of the eye and its surroundings. The main use could be found in the treatment of diseases of the curvature and surface of the cornea and in follow-up after some refractive procedures. In our work, we create 3D image-based models of the eye after scanning the face with a smartphone. An unexpected phenomenon appeared during the reconstruction of the transparent cornea – a crater-like depression was formed at the place where nearby objects reflected on the cornea, which corresponds to the first Purkinje image, the so-called glint. We thus encountered complications that may arise when modelling transparent living structures from a video taken in a normal environment, which will need to be solved if we want to create such 3D models of the eye using this method for medical purposes. Another 3D reconstruction approach or additional algorithms must be considered as a future work.","PeriodicalId":508697,"journal":{"name":"Journal of Electrical Engineering","volume":"283 4","pages":"513 - 520"},"PeriodicalIF":0.0,"publicationDate":"2023-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139188168","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}
Abstract This paper aims to overcome the problems and limitations of the communications of Unmanned Aerial Vehicles (UAV) by incorporating Intelligent Reflecting Surface (IRS) into UAV for channel tracking. Since IRS may change the propagation environment, is a desirable option for combining with UAV to improve wireless network security. Due to its capacity to proactively configure the wireless environment, IRS technology is a potential one for future communication systems. IRS is able to provide steady communications and serve a greater coverage area by reflecting signals to create virtual LoS routes. Moreover, we develop a federated learning-based channel tracking technique in which federated learning is used to determine the security and pre-estimation constituent. In addition, for channel tracking, Long Short-Term Memory (LSTM) is developed. Due to their ability to understand long-term connections between data time steps, LSTMs are frequently used to learn, analyze, and classify sequential data.
{"title":"Channel tracking in IRS-based UAV communication systems using federated learning","authors":"Itika Sharma, Sachin Kumar Gupta","doi":"10.2478/jee-2023-0060","DOIUrl":"https://doi.org/10.2478/jee-2023-0060","url":null,"abstract":"Abstract This paper aims to overcome the problems and limitations of the communications of Unmanned Aerial Vehicles (UAV) by incorporating Intelligent Reflecting Surface (IRS) into UAV for channel tracking. Since IRS may change the propagation environment, is a desirable option for combining with UAV to improve wireless network security. Due to its capacity to proactively configure the wireless environment, IRS technology is a potential one for future communication systems. IRS is able to provide steady communications and serve a greater coverage area by reflecting signals to create virtual LoS routes. Moreover, we develop a federated learning-based channel tracking technique in which federated learning is used to determine the security and pre-estimation constituent. In addition, for channel tracking, Long Short-Term Memory (LSTM) is developed. Due to their ability to understand long-term connections between data time steps, LSTMs are frequently used to learn, analyze, and classify sequential data.","PeriodicalId":508697,"journal":{"name":"Journal of Electrical Engineering","volume":"69 3-4","pages":"521 - 531"},"PeriodicalIF":0.0,"publicationDate":"2023-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139190863","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}
Sherif A. Khaleel, Mahmoud Shaban, M. F. Alsharekh, Ehab K. I. Hamad, Mohamed I. M. Shehata
Abstract In this work, fluorine-doped tin oxide (FTO) and graphene/fluorine-doped (G-FTO) thin films were prepared using a low-cost spray pyrolysis method at a substrate temperature of 500 °C. For the FTOs, stannous chloride was dissolved in methanol and acetic acid to form the precursor solution. A 0.05 mole (M) of hydrofluoric acid was added to the precursor as an n-type impurity. The FTO thin film has an optical transmittance of 82% and electrical sheet resistance of 15 Ω/□. By meticulously integrating graphene into the optimal precursor solution of FTO, a significant improvement in the electrical conductivity of the prepared samples was achieved, leading to a reduction in the sheet resistance to 8 Ω/□ with a suitable optical transmittance of 79%. Structural, morphological, optical, and electrical properties of the prepared sample are investigated using X-ray diffraction, scanning electron microscope, UV spectroscopy, and four-point probe technique. The best performance of the FTO thin films is achieved utilizing 2.5 µmole/L of fluorine concentration at a substrate temperature of 500°C for a spraying exposer time of 20 min. The prepared sample has an electrical sheet resistance of 15 Ω/□, optical transmittance of 82%, and figure-of-merit of 91.2×10−4 Ω−1.The addition of 0.4 µmole/L of graphene to the optimum FTO samples enhances the performance by a remarkable reduction in the electrical the sheet resistance to 8 Ω/□ and an acceptable reduction in the optical transmittance of 79%. The overall value of the figure-of-merit increased to 118.3×10−4 Ω−1. The achieved results offer a high potential for adopting the prepared films for electronic and optoelectronic applications.
{"title":"Preparation and characterization of graphene-based fluorine doped tin dioxide thin films via spray pyrolysis technique","authors":"Sherif A. Khaleel, Mahmoud Shaban, M. F. Alsharekh, Ehab K. I. Hamad, Mohamed I. M. Shehata","doi":"10.2478/jee-2023-0054","DOIUrl":"https://doi.org/10.2478/jee-2023-0054","url":null,"abstract":"Abstract In this work, fluorine-doped tin oxide (FTO) and graphene/fluorine-doped (G-FTO) thin films were prepared using a low-cost spray pyrolysis method at a substrate temperature of 500 °C. For the FTOs, stannous chloride was dissolved in methanol and acetic acid to form the precursor solution. A 0.05 mole (M) of hydrofluoric acid was added to the precursor as an n-type impurity. The FTO thin film has an optical transmittance of 82% and electrical sheet resistance of 15 Ω/□. By meticulously integrating graphene into the optimal precursor solution of FTO, a significant improvement in the electrical conductivity of the prepared samples was achieved, leading to a reduction in the sheet resistance to 8 Ω/□ with a suitable optical transmittance of 79%. Structural, morphological, optical, and electrical properties of the prepared sample are investigated using X-ray diffraction, scanning electron microscope, UV spectroscopy, and four-point probe technique. The best performance of the FTO thin films is achieved utilizing 2.5 µmole/L of fluorine concentration at a substrate temperature of 500°C for a spraying exposer time of 20 min. The prepared sample has an electrical sheet resistance of 15 Ω/□, optical transmittance of 82%, and figure-of-merit of 91.2×10−4 Ω−1.The addition of 0.4 µmole/L of graphene to the optimum FTO samples enhances the performance by a remarkable reduction in the electrical the sheet resistance to 8 Ω/□ and an acceptable reduction in the optical transmittance of 79%. The overall value of the figure-of-merit increased to 118.3×10−4 Ω−1. The achieved results offer a high potential for adopting the prepared films for electronic and optoelectronic applications.","PeriodicalId":508697,"journal":{"name":"Journal of Electrical Engineering","volume":"8 2","pages":"463 - 473"},"PeriodicalIF":0.0,"publicationDate":"2023-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139191094","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：