Pub Date : 2020-07-01DOI: 10.1109/ICEENG45378.2020.9171703
E. H. Kapeel, M. Abozied, A. Kamel, H. Hendy
Missile interception capability particularly depends on the guidance law implemented in the guidance processor of the missile. The majority of missiles employ proportional navigation (PN) as the primary guidance law since its first usage in the 20th century. PN tends to nullify the line-of-sight (LOS) angular rate by adjusting the missile turning rate proportionally to the LOS rate. With the great improvements in the aeronautic industry, PN is no more sufficient for highly maneuvering targets. Developing mathematical based advanced guidance laws has concerned a lot of researchers in that field and since then a lot of advanced guidance laws have been proposed and tested. Augmented PN (APN) is one of the proposed advanced guidance laws that can interact with highly maneuvering targets by augmenting the original PN with a target acceleration term which is estimated online. In this research, APN simulation and two-dimensioned missile-target intercept geometry are modeled using Matlab® Simulink™. Simulation results through different scenarios for modern guidance laws are evaluated and compared with other classical ones such as PN. The tuned APN law is implemented on a Xilinx FPGA processor using a system generator (Xilinx toolbox) which is conducted to the simulation model as a processor in the loop (SIL) simulation scheme. Simulation results show the superiority of APN against other classical guidance laws and the capability of the Xilinx FPGA processor is assessed and discussed.
{"title":"Evaluation of Missile Terminal Guidance Using Software in Loop (SIL)","authors":"E. H. Kapeel, M. Abozied, A. Kamel, H. Hendy","doi":"10.1109/ICEENG45378.2020.9171703","DOIUrl":"https://doi.org/10.1109/ICEENG45378.2020.9171703","url":null,"abstract":"Missile interception capability particularly depends on the guidance law implemented in the guidance processor of the missile. The majority of missiles employ proportional navigation (PN) as the primary guidance law since its first usage in the 20th century. PN tends to nullify the line-of-sight (LOS) angular rate by adjusting the missile turning rate proportionally to the LOS rate. With the great improvements in the aeronautic industry, PN is no more sufficient for highly maneuvering targets. Developing mathematical based advanced guidance laws has concerned a lot of researchers in that field and since then a lot of advanced guidance laws have been proposed and tested. Augmented PN (APN) is one of the proposed advanced guidance laws that can interact with highly maneuvering targets by augmenting the original PN with a target acceleration term which is estimated online. In this research, APN simulation and two-dimensioned missile-target intercept geometry are modeled using Matlab® Simulink™. Simulation results through different scenarios for modern guidance laws are evaluated and compared with other classical ones such as PN. The tuned APN law is implemented on a Xilinx FPGA processor using a system generator (Xilinx toolbox) which is conducted to the simulation model as a processor in the loop (SIL) simulation scheme. Simulation results show the superiority of APN against other classical guidance laws and the capability of the Xilinx FPGA processor is assessed and discussed.","PeriodicalId":346636,"journal":{"name":"2020 12th International Conference on Electrical Engineering (ICEENG)","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128064117","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 : 2020-07-01DOI: 10.1109/ICEENG45378.2020.9171757
M. S. Elkerdany, I. Safwat, Ahmed Medhat Mohamed Yossef, M. Elkhatib
Electrical propulsion system using Brushless DC(BLDC) motors is widely used nowadays in mini Unmanned Aerial Vehicle (UAV), as it guarantees an efficient performance and long flight endurance enhancement. The driver of BLDC has a pivotal role in this electrical propulsion system. Three-phase inverter with six switches design is the most common in the driver model of a conventional BLDC motor. In this paper, a comparative study between the BLDC motor drive system using a non-ideal six-switch three-phase inverter (SSTPI), and a non-ideal four-switch three phase inverter (FSTPI) is investigated. The study point-of-view is the enhancement of the propulsion system efficiency, cost, and controllability. Mathematical models for the two proposed systems including BLDC motor are introduced. Simulation using MATLAB Simulink is performed at different flight modes with variable motor speeds. A comparative study declares the tradeoff choice between the two drive systems to enhance the system performance based on the preferred selection criterion. This study provides a good guide for designing such BLDC motor driver systems.
{"title":"A Comparative Study on Using Brushless DC Motor Six-Switch and Four-Switch Inverter for UAV Propulsion System","authors":"M. S. Elkerdany, I. Safwat, Ahmed Medhat Mohamed Yossef, M. Elkhatib","doi":"10.1109/ICEENG45378.2020.9171757","DOIUrl":"https://doi.org/10.1109/ICEENG45378.2020.9171757","url":null,"abstract":"Electrical propulsion system using Brushless DC(BLDC) motors is widely used nowadays in mini Unmanned Aerial Vehicle (UAV), as it guarantees an efficient performance and long flight endurance enhancement. The driver of BLDC has a pivotal role in this electrical propulsion system. Three-phase inverter with six switches design is the most common in the driver model of a conventional BLDC motor. In this paper, a comparative study between the BLDC motor drive system using a non-ideal six-switch three-phase inverter (SSTPI), and a non-ideal four-switch three phase inverter (FSTPI) is investigated. The study point-of-view is the enhancement of the propulsion system efficiency, cost, and controllability. Mathematical models for the two proposed systems including BLDC motor are introduced. Simulation using MATLAB Simulink is performed at different flight modes with variable motor speeds. A comparative study declares the tradeoff choice between the two drive systems to enhance the system performance based on the preferred selection criterion. This study provides a good guide for designing such BLDC motor driver systems.","PeriodicalId":346636,"journal":{"name":"2020 12th International Conference on Electrical Engineering (ICEENG)","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132585969","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 : 2020-07-01DOI: 10.1109/ICEENG45378.2020.9171767
G. Tarek, H. Elsheikh
Step Frame Onboard Remote Sensing ElectroOptical Systems (SF-ORSEOS) have a major contribution to aerial photography. The SF-ORSEOS Field of View (FOV) is stepped across the flight track to observe a large area while the Forward Motion Compensation (FMC) is performed electronically in Focal Plane Arrays (FPA) to avoid imaging smearing during scene acquisition. The compatibility of the SF-ORSEOS parameters is challenging as it guarantees the most reliable construction of the SF-ORSEOS acquisition head (lens, FPA, ReadOut Integrated Circuit ROIC) that maintains the quality of the acquired information. In this paper, SFORSEOS-Pixel Level - Fast Motion Compensation -Computer Model (SF-ORSEOSPL-FMC-CM) is developed, based on pixel-level Spatio-temporal resolution with considering the flying velocity, flight height, observation looking angle, the overlap of the successive frames, lens and FPA parameters and characteristics. The major contribution of the SF-ORSEOS PL-FMC-CM appears in its facilitation of both the selection and design of the ROIC according to a predetermined custom user requirements. Moreover, it provides quantitative visual tools to predict the system behavior.
{"title":"Step Frame Onboard Remote Sensing Electro-Optical System Pixel Level Forward Motion Compensation Computer Model (SF-ORSEOS PL-FMC-CM)","authors":"G. Tarek, H. Elsheikh","doi":"10.1109/ICEENG45378.2020.9171767","DOIUrl":"https://doi.org/10.1109/ICEENG45378.2020.9171767","url":null,"abstract":"Step Frame Onboard Remote Sensing ElectroOptical Systems (SF-ORSEOS) have a major contribution to aerial photography. The SF-ORSEOS Field of View (FOV) is stepped across the flight track to observe a large area while the Forward Motion Compensation (FMC) is performed electronically in Focal Plane Arrays (FPA) to avoid imaging smearing during scene acquisition. The compatibility of the SF-ORSEOS parameters is challenging as it guarantees the most reliable construction of the SF-ORSEOS acquisition head (lens, FPA, ReadOut Integrated Circuit ROIC) that maintains the quality of the acquired information. In this paper, SFORSEOS-Pixel Level - Fast Motion Compensation -Computer Model (SF-ORSEOSPL-FMC-CM) is developed, based on pixel-level Spatio-temporal resolution with considering the flying velocity, flight height, observation looking angle, the overlap of the successive frames, lens and FPA parameters and characteristics. The major contribution of the SF-ORSEOS PL-FMC-CM appears in its facilitation of both the selection and design of the ROIC according to a predetermined custom user requirements. Moreover, it provides quantitative visual tools to predict the system behavior.","PeriodicalId":346636,"journal":{"name":"2020 12th International Conference on Electrical Engineering (ICEENG)","volume":"83 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132723501","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 : 2020-07-01DOI: 10.1109/ICEENG45378.2020.9171720
Basem M. Hamouda, B. M. Abdelrahman, H. Ahmed
In this paper, we propose a design of a 3.5-GHz class-AB power amplifier that achieves high efficiency. The proposed design, based on Wolfspeed’s CGH40006P GaNHEMT, provides drain efficiency up to 72%. To provide the balance between the maximum output power and amplifier efficiency within the desired bandwidth, source/load-pull simulations are employed. In addition, LC broadband matching, based on equiripple approximation, is applied for input matching while multi-section quarter-wave transformer is used for output matching. The drain bias is designed using a quarterwave transmission line to provide low insertion loss within the desired frequency band. Simulations show that the proposed design provides a small signal gain exceeding 14-dB, fractional bandwidth 28.5%, 38.5 dBm output power, and less than 10 dB return loss in both input and output within the whole bandwidth. The measurements of the implemented power amplifier demonstrate good conformity between simulation and measurement results.
{"title":"A 3.5-GHz, Highly-Efficient Power Amplifier for Wireless Communication Applications","authors":"Basem M. Hamouda, B. M. Abdelrahman, H. Ahmed","doi":"10.1109/ICEENG45378.2020.9171720","DOIUrl":"https://doi.org/10.1109/ICEENG45378.2020.9171720","url":null,"abstract":"In this paper, we propose a design of a 3.5-GHz class-AB power amplifier that achieves high efficiency. The proposed design, based on Wolfspeed’s CGH40006P GaNHEMT, provides drain efficiency up to 72%. To provide the balance between the maximum output power and amplifier efficiency within the desired bandwidth, source/load-pull simulations are employed. In addition, LC broadband matching, based on equiripple approximation, is applied for input matching while multi-section quarter-wave transformer is used for output matching. The drain bias is designed using a quarterwave transmission line to provide low insertion loss within the desired frequency band. Simulations show that the proposed design provides a small signal gain exceeding 14-dB, fractional bandwidth 28.5%, 38.5 dBm output power, and less than 10 dB return loss in both input and output within the whole bandwidth. The measurements of the implemented power amplifier demonstrate good conformity between simulation and measurement results.","PeriodicalId":346636,"journal":{"name":"2020 12th International Conference on Electrical Engineering (ICEENG)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134215715","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 : 2020-07-01DOI: 10.1109/ICEENG45378.2020.9171721
A. M. Shiddiq Yunus, Makmur Saini, M. Djalal
Doubly Fed Induction Generator (DFIG) has become the most popular wind turbine generator that has been installed worldwide since a decade ago. It cannot be denied that the expansion of loads might be increased from time to time which might also influence the performance of DFIG. Moreover, at the same time, Fault Ride Through (FRT) must also be complied by the grid-connected DFIG. In this paper, an investigation of Flicker Disturbance on DFIG Performance is studied. The flicker disturbance could be sourced from pulsating loads such as arc furnace, compressor, and welding machine loads, it will affect the industrial production process and could cause fatigue due to loss of concentration as a contribution of eye epileptic when working under rapid blinking light. Additionally, when significant flicker sources connected to the system with DFIG, the FRT such as voltage profile at PCC and DC-Link might cause the protection system operates to disconnect the DFIGs from the grid.
{"title":"Impact of Connected Flicker Sources on DFIG Performance","authors":"A. M. Shiddiq Yunus, Makmur Saini, M. Djalal","doi":"10.1109/ICEENG45378.2020.9171721","DOIUrl":"https://doi.org/10.1109/ICEENG45378.2020.9171721","url":null,"abstract":"Doubly Fed Induction Generator (DFIG) has become the most popular wind turbine generator that has been installed worldwide since a decade ago. It cannot be denied that the expansion of loads might be increased from time to time which might also influence the performance of DFIG. Moreover, at the same time, Fault Ride Through (FRT) must also be complied by the grid-connected DFIG. In this paper, an investigation of Flicker Disturbance on DFIG Performance is studied. The flicker disturbance could be sourced from pulsating loads such as arc furnace, compressor, and welding machine loads, it will affect the industrial production process and could cause fatigue due to loss of concentration as a contribution of eye epileptic when working under rapid blinking light. Additionally, when significant flicker sources connected to the system with DFIG, the FRT such as voltage profile at PCC and DC-Link might cause the protection system operates to disconnect the DFIGs from the grid.","PeriodicalId":346636,"journal":{"name":"2020 12th International Conference on Electrical Engineering (ICEENG)","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134313761","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 : 2020-07-01DOI: 10.1109/ICEENG45378.2020.9171775
M. Hamid, M. Safy
InSAR image noise has a great effect on the efficiency of the phase unwrapping process and consequently the correct generation of the digital elevation model (DEM). However, phase unwrapping can be easier and more efficient by excellent interferometric phase image filtering which can be achieved by high noise reduction, perfect preservation of the image detail, and decreasing the number of residues. In this paper, a grey-scale soft morphological filter is optimized using the genetic algorithm and used to filter out the interferometric phase image noise. The filter parameters are optimized to achieve an optimum balance between the amount of noise reduction and the degree of preservation of the image detail. Simulated and real interferograms are employed to evaluate the performance of the optimized filter. The evaluation is based on both objective and subjective measures. The results demonstrate that the proposed filter achieves high noise reduction with perfect image detail preservation and very small number of residues. This outstanding performance guarantees efficient phase unwrapping and hence accurate DEM generation. The results show also that the filter outperforms other traditional filters used for denoising interferogram images.
{"title":"InSAR Image Denoising Filter for Accurate DEM Generation","authors":"M. Hamid, M. Safy","doi":"10.1109/ICEENG45378.2020.9171775","DOIUrl":"https://doi.org/10.1109/ICEENG45378.2020.9171775","url":null,"abstract":"InSAR image noise has a great effect on the efficiency of the phase unwrapping process and consequently the correct generation of the digital elevation model (DEM). However, phase unwrapping can be easier and more efficient by excellent interferometric phase image filtering which can be achieved by high noise reduction, perfect preservation of the image detail, and decreasing the number of residues. In this paper, a grey-scale soft morphological filter is optimized using the genetic algorithm and used to filter out the interferometric phase image noise. The filter parameters are optimized to achieve an optimum balance between the amount of noise reduction and the degree of preservation of the image detail. Simulated and real interferograms are employed to evaluate the performance of the optimized filter. The evaluation is based on both objective and subjective measures. The results demonstrate that the proposed filter achieves high noise reduction with perfect image detail preservation and very small number of residues. This outstanding performance guarantees efficient phase unwrapping and hence accurate DEM generation. The results show also that the filter outperforms other traditional filters used for denoising interferogram images.","PeriodicalId":346636,"journal":{"name":"2020 12th International Conference on Electrical Engineering (ICEENG)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114499998","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 : 2020-07-01DOI: 10.1109/ICEENG45378.2020.9171771
H. Suyono, E. Subekti, Hery Purnomo, Tri Nurwati, R. Hasanah
The rapid growth of population and economic development of a country requires an adequate support of electrical power supply management. The interconnected system of generation plants with appropriate economic dispatch is purposed to achieve certain goal. This paper describes the use of a hybrid method between the Particle Swarm Optimization (PSO) method and Ant Colony Optimization (ACO) method to be implemented for economic dispatch of the 500kV Java-Bali power system. It aims to divide the generation loading among the whole thermal power plants in the system and to look for the best combination which gives the most economical generation cost. The search for solutions using this hybrid method is determined by the Gbest’s particle distribution and the ability of ants to find the best solution, which is called BestAnt. In this study, the evaluation process was carried out using 60 iterations for the 30-bus network and the 500kV Java-Bali power network based on the available data. The optimization results show that the generation cost being optimized using the hybrid method is lower than when using the PSO method, even if it is still higher than when using the ACO method. However, the hybrid method offers the best achievement in terms of computation speed being compared to both the PSO and ACO methods.
{"title":"Economic Dispatch of 500 kV Java-Bali Power System using Hybrid Particle Swarm-Ant Colony Optimization Method","authors":"H. Suyono, E. Subekti, Hery Purnomo, Tri Nurwati, R. Hasanah","doi":"10.1109/ICEENG45378.2020.9171771","DOIUrl":"https://doi.org/10.1109/ICEENG45378.2020.9171771","url":null,"abstract":"The rapid growth of population and economic development of a country requires an adequate support of electrical power supply management. The interconnected system of generation plants with appropriate economic dispatch is purposed to achieve certain goal. This paper describes the use of a hybrid method between the Particle Swarm Optimization (PSO) method and Ant Colony Optimization (ACO) method to be implemented for economic dispatch of the 500kV Java-Bali power system. It aims to divide the generation loading among the whole thermal power plants in the system and to look for the best combination which gives the most economical generation cost. The search for solutions using this hybrid method is determined by the Gbest’s particle distribution and the ability of ants to find the best solution, which is called BestAnt. In this study, the evaluation process was carried out using 60 iterations for the 30-bus network and the 500kV Java-Bali power network based on the available data. The optimization results show that the generation cost being optimized using the hybrid method is lower than when using the PSO method, even if it is still higher than when using the ACO method. However, the hybrid method offers the best achievement in terms of computation speed being compared to both the PSO and ACO methods.","PeriodicalId":346636,"journal":{"name":"2020 12th International Conference on Electrical Engineering (ICEENG)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114244438","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 : 2020-07-01DOI: 10.1109/ICEENG45378.2020.9171748
Sameh I. Beaber, A. Abdelhamid, Maged M. Abou Elyazed
The biological locomotion of animals shows an incredible degree of flexibility and durability that gives them an advantage to move across rough terrain. Even if hexapod robots are so superior to adjust with uneven terrains, they already have some problems to follow a smooth path exactly. With such obstacles, regular Periodic walking gates will not be able to respond quickly. During this study, the task to follow an accurately predetermined route in the Cartesian region is built through the adaptive gate. The Phantom_ll model robot case study is simulated via Matlab SimMechanics™ toolbox to evaluate and estimate dynamics of the hexapod and the adaptive gate implemented. In addition, the Phantom 11 case study is evaluated in the kinematic model that consisting of two main objectives, the direct and inverse kinematics. Inverse kinematics is calculated geometrically and the Denavit-Hartenberg method is applied to determine the direct kinematics. The robot margin of stability and kinematic limitations are also taken into consideration. Simulation results showed the suitability of the presented adaptive gait.
{"title":"Road Following for Hexapod Mobile Robot with Adaptive Tripod Gait","authors":"Sameh I. Beaber, A. Abdelhamid, Maged M. Abou Elyazed","doi":"10.1109/ICEENG45378.2020.9171748","DOIUrl":"https://doi.org/10.1109/ICEENG45378.2020.9171748","url":null,"abstract":"The biological locomotion of animals shows an incredible degree of flexibility and durability that gives them an advantage to move across rough terrain. Even if hexapod robots are so superior to adjust with uneven terrains, they already have some problems to follow a smooth path exactly. With such obstacles, regular Periodic walking gates will not be able to respond quickly. During this study, the task to follow an accurately predetermined route in the Cartesian region is built through the adaptive gate. The Phantom_ll model robot case study is simulated via Matlab SimMechanics™ toolbox to evaluate and estimate dynamics of the hexapod and the adaptive gate implemented. In addition, the Phantom 11 case study is evaluated in the kinematic model that consisting of two main objectives, the direct and inverse kinematics. Inverse kinematics is calculated geometrically and the Denavit-Hartenberg method is applied to determine the direct kinematics. The robot margin of stability and kinematic limitations are also taken into consideration. Simulation results showed the suitability of the presented adaptive gait.","PeriodicalId":346636,"journal":{"name":"2020 12th International Conference on Electrical Engineering (ICEENG)","volume":"110 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128639935","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 : 2020-07-01DOI: 10.1109/ICEENG45378.2020.9171768
S. S. Ibrahiem, S. Ismail, K. Bahnasy, M. Aref
Social media platforms generate continuously tremendous quantities of valuable knowledge for users’ perspectives towards our global societies for example, Twitter. Sentiment analysis reveals its vital role to take the advantage of these different perspectives for different applications like, political votes, business domains, financial risks, and etc. Most traditional approaches in sentiment analysis predict a single attitude from the users’ tweets. This is not considered a quiet correct approach, due to multiple of implied feelings in the users’ tweets towards a specific topic, person, or event. This research presents hybrid machine learning approach, that can predict multiple feelings in the same tweet. It applies two methods, which are Binary relevance based on four machine learning algorithms in addition to Convolutional neural networks. The tweets preprocessed and converted into feature vectors. Word embedding, emotion lexicons, and frequency distribution probability are used to extract features from the input tweets. The paper finally presents a case study of two experiments to show the multi emotion prediction classifiers workflow on real tweets. The applied dataset is on SemEval2018 Task E-c. Binary relevance method has hamming score 0.53, and Convolutional neural network method has score 0.54.
{"title":"A Case Study in Multi-Emotion Classification via Twitter","authors":"S. S. Ibrahiem, S. Ismail, K. Bahnasy, M. Aref","doi":"10.1109/ICEENG45378.2020.9171768","DOIUrl":"https://doi.org/10.1109/ICEENG45378.2020.9171768","url":null,"abstract":"Social media platforms generate continuously tremendous quantities of valuable knowledge for users’ perspectives towards our global societies for example, Twitter. Sentiment analysis reveals its vital role to take the advantage of these different perspectives for different applications like, political votes, business domains, financial risks, and etc. Most traditional approaches in sentiment analysis predict a single attitude from the users’ tweets. This is not considered a quiet correct approach, due to multiple of implied feelings in the users’ tweets towards a specific topic, person, or event. This research presents hybrid machine learning approach, that can predict multiple feelings in the same tweet. It applies two methods, which are Binary relevance based on four machine learning algorithms in addition to Convolutional neural networks. The tweets preprocessed and converted into feature vectors. Word embedding, emotion lexicons, and frequency distribution probability are used to extract features from the input tweets. The paper finally presents a case study of two experiments to show the multi emotion prediction classifiers workflow on real tweets. The applied dataset is on SemEval2018 Task E-c. Binary relevance method has hamming score 0.53, and Convolutional neural network method has score 0.54.","PeriodicalId":346636,"journal":{"name":"2020 12th International Conference on Electrical Engineering (ICEENG)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121292549","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 : 2020-07-01DOI: 10.1109/ICEENG45378.2020.9171706
Ayman Emam, M. Shalaby, Mohamed A. Aboelazm, H. A. Bakr, H. Mansour
Both Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) are the main classes of artificial neural networks used for recognition and prediction problems. Recently, it has been applied in the field of communications to identify the modulation types of the signals according to their features. In this paper, we use the RadioML2016.10b dataset generated in a real system using GNU radio to classify radio modulation by two types of neural networks, namely CNN and LSTM. The two networks automatically learn from in-phase and quadrature (I&Q) time domain data without manual expert features requirement. New architecture of Convolutional Long- Short Term Deep Neural Network (CLDNN) has been proposed that integrates selected architectures of CNNs, LSTM and deep neural networks (DNN) models. Different CLDNN architectures have been tested with different number of memory cells in the LSTM layers. In the proposed model setting, the modifications included three convolutional CNN layers, followed by one LSTM layer with 50 computing units and two fully connected DNN layers, which perform better result and higher accuracy compared to other settings. A great improve in performance has been achieved on the test data set with signal to noise ratio (SNR) varying from –18 dB to 20 dB. CLDNN model provided a 2-3% relative improvement in accuracy over the results of CNN and LSTM individual models.
{"title":"A Comparative Study between CNN, LSTM, and CLDNN Models in The Context of Radio Modulation Classification","authors":"Ayman Emam, M. Shalaby, Mohamed A. Aboelazm, H. A. Bakr, H. Mansour","doi":"10.1109/ICEENG45378.2020.9171706","DOIUrl":"https://doi.org/10.1109/ICEENG45378.2020.9171706","url":null,"abstract":"Both Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) are the main classes of artificial neural networks used for recognition and prediction problems. Recently, it has been applied in the field of communications to identify the modulation types of the signals according to their features. In this paper, we use the RadioML2016.10b dataset generated in a real system using GNU radio to classify radio modulation by two types of neural networks, namely CNN and LSTM. The two networks automatically learn from in-phase and quadrature (I&Q) time domain data without manual expert features requirement. New architecture of Convolutional Long- Short Term Deep Neural Network (CLDNN) has been proposed that integrates selected architectures of CNNs, LSTM and deep neural networks (DNN) models. Different CLDNN architectures have been tested with different number of memory cells in the LSTM layers. In the proposed model setting, the modifications included three convolutional CNN layers, followed by one LSTM layer with 50 computing units and two fully connected DNN layers, which perform better result and higher accuracy compared to other settings. A great improve in performance has been achieved on the test data set with signal to noise ratio (SNR) varying from –18 dB to 20 dB. CLDNN model provided a 2-3% relative improvement in accuracy over the results of CNN and LSTM individual models.","PeriodicalId":346636,"journal":{"name":"2020 12th International Conference on Electrical Engineering (ICEENG)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121200531","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：