Pub Date : 2022-12-02DOI: 10.1109/ETECTE55893.2022.10007092
Zahid Ul Hassan, Nouman Bashir, Afaq Iltaf
Wearable electronic equipment is continually improving and becoming more integrated with technology for prosthesis control. These devices, which come in a variety of shapes and sizes, can detect, quantify, and perhaps use signals generated by the human body's physiological and muscular changes to control machinery. One such gadget, the MYO gesture/arm band, collects information from our forearm in the form of electromyographic (EMG) Signal, which is based on the measurement of small electrical impulses caused by ion exchange between muscle membranes, utilize these myoelectric impulses and converts them into input signals by using pre-defined motions. There is a range of tasks that may be carried out with this device and use of this device can give better results in a combination with another controlling modality. This paper addresses the use of several input modalities, including speech and myoelectric signals recorded through microphone and MYO band, respectively to control a robotic car. Hand gestures are used to control the car through MYO armband. The complete process is done by using Raspberry Pi. Classification of EMG signals is done by using Convolution Neural Network (CNN) classifier. Experimental results obtained as well as their accuracies for performance analysis are also presented.
{"title":"Electromyography and Speech Controlled Prototype Robotic Car using CNN Based Classifier for EMG","authors":"Zahid Ul Hassan, Nouman Bashir, Afaq Iltaf","doi":"10.1109/ETECTE55893.2022.10007092","DOIUrl":"https://doi.org/10.1109/ETECTE55893.2022.10007092","url":null,"abstract":"Wearable electronic equipment is continually improving and becoming more integrated with technology for prosthesis control. These devices, which come in a variety of shapes and sizes, can detect, quantify, and perhaps use signals generated by the human body's physiological and muscular changes to control machinery. One such gadget, the MYO gesture/arm band, collects information from our forearm in the form of electromyographic (EMG) Signal, which is based on the measurement of small electrical impulses caused by ion exchange between muscle membranes, utilize these myoelectric impulses and converts them into input signals by using pre-defined motions. There is a range of tasks that may be carried out with this device and use of this device can give better results in a combination with another controlling modality. This paper addresses the use of several input modalities, including speech and myoelectric signals recorded through microphone and MYO band, respectively to control a robotic car. Hand gestures are used to control the car through MYO armband. The complete process is done by using Raspberry Pi. Classification of EMG signals is done by using Convolution Neural Network (CNN) classifier. Experimental results obtained as well as their accuracies for performance analysis are also presented.","PeriodicalId":131572,"journal":{"name":"2022 International Conference on Emerging Trends in Electrical, Control, and Telecommunication Engineering (ETECTE)","volume":"16 10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130164378","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 : 2022-12-02DOI: 10.1109/ETECTE55893.2022.10007203
Farhan Azeem, L. Trainor, Ang Gao, Maya Isarov, D. Strekalov, H. Schwefel
Titanium doped sapphire (Ti:sapphire) is a ubiquitous gain medium. Due to its broadband gain it has been in use in the solid state laser industry for over three decades while still going strong. We recently demonstrated a Ti:sapphire laser using the whispering gallery mode (WGM) resonator platform. Here, we review some of our previous work, shedding light on the theoretical and experimental lasing threshold of this first high quality Ti:sapphire WGM laser and review amplification with this new platform as well. We also report on new results of multi-mode lasing observed with this system. These results can potentially be utilised in future to train neural networks to control the experimental parameters used to observe lasing.
{"title":"Whispering gallery mode resonators: An alternate platform for Ti:sapphire lasers and amplifiers","authors":"Farhan Azeem, L. Trainor, Ang Gao, Maya Isarov, D. Strekalov, H. Schwefel","doi":"10.1109/ETECTE55893.2022.10007203","DOIUrl":"https://doi.org/10.1109/ETECTE55893.2022.10007203","url":null,"abstract":"Titanium doped sapphire (Ti:sapphire) is a ubiquitous gain medium. Due to its broadband gain it has been in use in the solid state laser industry for over three decades while still going strong. We recently demonstrated a Ti:sapphire laser using the whispering gallery mode (WGM) resonator platform. Here, we review some of our previous work, shedding light on the theoretical and experimental lasing threshold of this first high quality Ti:sapphire WGM laser and review amplification with this new platform as well. We also report on new results of multi-mode lasing observed with this system. These results can potentially be utilised in future to train neural networks to control the experimental parameters used to observe lasing.","PeriodicalId":131572,"journal":{"name":"2022 International Conference on Emerging Trends in Electrical, Control, and Telecommunication Engineering (ETECTE)","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126093849","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 : 2022-12-02DOI: 10.1109/ETECTE55893.2022.10007106
Muhammad Sufyan Arshad, Jawad Arif
White Blood cells are building blocks of the immune system of humans as they fight different types of infections, which is vital for healthy recovery. Changes in the number of White Blood Cell subtypes (WBCs) rule out certain diseases such as infection, heart disease and diabetes in medical practices. Conventional methods of counting the number of WBCs are dependent on manual testing and have chances of human error and the automated method apparatus is very costly. Thus the classification of White Blood Cell subtypes is of vital importance. In this study, CV based solution is proposed for White Blood Cell subtype identification. Different MCNN-based models along with transfer learning-based models (VGG16 & Resnet50) are trained and implemented for performance comparison and the effect of different training parameters on the performance of the models is also explored in the study. It was observed that changing the training parameters also affects the accuracy of the model. The highest accuracy of 96.6% was achieved using the MCNN-based model for the classification of White Blood Cells.
{"title":"Classification of White Blood Cells Subtype Using MCNN","authors":"Muhammad Sufyan Arshad, Jawad Arif","doi":"10.1109/ETECTE55893.2022.10007106","DOIUrl":"https://doi.org/10.1109/ETECTE55893.2022.10007106","url":null,"abstract":"White Blood cells are building blocks of the immune system of humans as they fight different types of infections, which is vital for healthy recovery. Changes in the number of White Blood Cell subtypes (WBCs) rule out certain diseases such as infection, heart disease and diabetes in medical practices. Conventional methods of counting the number of WBCs are dependent on manual testing and have chances of human error and the automated method apparatus is very costly. Thus the classification of White Blood Cell subtypes is of vital importance. In this study, CV based solution is proposed for White Blood Cell subtype identification. Different MCNN-based models along with transfer learning-based models (VGG16 & Resnet50) are trained and implemented for performance comparison and the effect of different training parameters on the performance of the models is also explored in the study. It was observed that changing the training parameters also affects the accuracy of the model. The highest accuracy of 96.6% was achieved using the MCNN-based model for the classification of White Blood Cells.","PeriodicalId":131572,"journal":{"name":"2022 International Conference on Emerging Trends in Electrical, Control, and Telecommunication Engineering (ETECTE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131203349","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 : 2022-12-02DOI: 10.1109/ETECTE55893.2022.10007349
Fazal Badshah, Qing He, Zeyun Shi, Haiyang Zhang, Jin Xie, Rahmatullah, M. Yousaf, Muqaddar Abbas
In high quality micromaser cavities, we investigate the tunnelling and traversal of ultra-cold A-type three-level atoms. We specifically discuss how a coherent driving field affects the tunnelling atoms' traversal behaviour. Phase time, which is shown to be a suitable measure of atoms' transit time through a cavity, is affected by driving induced atomic coherence. For example, atomic coherence leads to negative phase times for atomic transmission on both the excited and ground levels. The phase tunnelling time also exhibits alternate subclassical and superclassical traversal tendencies depending on the driving field value as atomic momentum increases.
{"title":"Controlling Tunneling of Atoms Through aHigh-Quality Cavity Via an External Driving Field","authors":"Fazal Badshah, Qing He, Zeyun Shi, Haiyang Zhang, Jin Xie, Rahmatullah, M. Yousaf, Muqaddar Abbas","doi":"10.1109/ETECTE55893.2022.10007349","DOIUrl":"https://doi.org/10.1109/ETECTE55893.2022.10007349","url":null,"abstract":"In high quality micromaser cavities, we investigate the tunnelling and traversal of ultra-cold A-type three-level atoms. We specifically discuss how a coherent driving field affects the tunnelling atoms' traversal behaviour. Phase time, which is shown to be a suitable measure of atoms' transit time through a cavity, is affected by driving induced atomic coherence. For example, atomic coherence leads to negative phase times for atomic transmission on both the excited and ground levels. The phase tunnelling time also exhibits alternate subclassical and superclassical traversal tendencies depending on the driving field value as atomic momentum increases.","PeriodicalId":131572,"journal":{"name":"2022 International Conference on Emerging Trends in Electrical, Control, and Telecommunication Engineering (ETECTE)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132615883","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 : 2022-12-02DOI: 10.1109/ETECTE55893.2022.10007208
Tahir Hafeez, M. Numan, Akif Zia, H. A. Qureshi, Hasaan Farooq
For loosely coupled transformers, the leakage and magnetizing inductances vary due to the changing positions for the primary and the secondary sides of the transformer windings in inductive power transfer (IPT) systems. For reducing the effects of these varying inductances, various compensation networks have been proposed. These compensation networks are used to obtain a unity power factor and constant output voltage for power electronic applications. However, most of these compensation networks have a fixed compensation network designed for only a specific coupling coefficient. Therefore, a compensation network with variable components needs to be implemented to compensate for the changing inductances of the network. In this paper switched capacitor-based compensation network is proposed to match the resonant frequency of the network with the switching frequency of the converter. The proposed network compensates the magnetizing inductance for coupling coefficient in the range of 0.23 to 0,35 using a switched capacitor. Moreover, the proposed converter is symmetrical so that bidirectional power flow is possible while maintaining constant output voltage and unity power factor under zero voltage switching condition (ZVS).
{"title":"A Study on the Design and Analysis of a Bidirectional IPT System for EV wireless charging by Using Switch-Controlled Capacitor","authors":"Tahir Hafeez, M. Numan, Akif Zia, H. A. Qureshi, Hasaan Farooq","doi":"10.1109/ETECTE55893.2022.10007208","DOIUrl":"https://doi.org/10.1109/ETECTE55893.2022.10007208","url":null,"abstract":"For loosely coupled transformers, the leakage and magnetizing inductances vary due to the changing positions for the primary and the secondary sides of the transformer windings in inductive power transfer (IPT) systems. For reducing the effects of these varying inductances, various compensation networks have been proposed. These compensation networks are used to obtain a unity power factor and constant output voltage for power electronic applications. However, most of these compensation networks have a fixed compensation network designed for only a specific coupling coefficient. Therefore, a compensation network with variable components needs to be implemented to compensate for the changing inductances of the network. In this paper switched capacitor-based compensation network is proposed to match the resonant frequency of the network with the switching frequency of the converter. The proposed network compensates the magnetizing inductance for coupling coefficient in the range of 0.23 to 0,35 using a switched capacitor. Moreover, the proposed converter is symmetrical so that bidirectional power flow is possible while maintaining constant output voltage and unity power factor under zero voltage switching condition (ZVS).","PeriodicalId":131572,"journal":{"name":"2022 International Conference on Emerging Trends in Electrical, Control, and Telecommunication Engineering (ETECTE)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121427881","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 : 2022-12-02DOI: 10.1109/ETECTE55893.2022.10007292
Xu Zhang, J. Gu, M. Asad, U. Farooq, G. Abbas
This paper proposed an improved beetle bee algorithm and applied it to the trajectory tracking control of the OMNI manipulator. A metaheuristic algorithm mimics the beetle's excellent nature of food foraging in an unknown environment by their two antennas, and based on the intensity of smell, beetles decide to move left or right until they reach the final desired location. The convergence speed for a typical Beetle Antennae Search (BAS) is not fast enough, which is time-consuming, especially when dealing with higher dimensional systems. This proposed Improved Beetle Bee algorithm overcomes this problem by adding the square in angular velocities in the objective function. Finally, the simulation results will be compared between the proposed and state-of-the-art metaheuristic algorithms.
{"title":"Beetle Bee Algorithm Applied to Trajectory Tracking Control of OMNI Manipulator","authors":"Xu Zhang, J. Gu, M. Asad, U. Farooq, G. Abbas","doi":"10.1109/ETECTE55893.2022.10007292","DOIUrl":"https://doi.org/10.1109/ETECTE55893.2022.10007292","url":null,"abstract":"This paper proposed an improved beetle bee algorithm and applied it to the trajectory tracking control of the OMNI manipulator. A metaheuristic algorithm mimics the beetle's excellent nature of food foraging in an unknown environment by their two antennas, and based on the intensity of smell, beetles decide to move left or right until they reach the final desired location. The convergence speed for a typical Beetle Antennae Search (BAS) is not fast enough, which is time-consuming, especially when dealing with higher dimensional systems. This proposed Improved Beetle Bee algorithm overcomes this problem by adding the square in angular velocities in the objective function. Finally, the simulation results will be compared between the proposed and state-of-the-art metaheuristic algorithms.","PeriodicalId":131572,"journal":{"name":"2022 International Conference on Emerging Trends in Electrical, Control, and Telecommunication Engineering (ETECTE)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116796742","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 : 2022-12-02DOI: 10.1109/ETECTE55893.2022.10007182
M. U. Sardar, Dou Manfeng, Umar Saleem, Mannan Hassan, Muhammad Kashif Nawaz
Nowadays, vehicles based on electric charge and operation due to the motor are more prevalent in use due to their superiority in zero-emission, lowest noise, higher power density to size or weight ratio, and higher performance. In this scenario, synchronous machines using permanent interior magnets (IPMSM) are a suitable candidate and a potential source of mechanical power generation in electric vehicles (EVs). They have unique merits over the other types of electric motor families. A rare earth permanent magnet material with an interior V-type rotor is used as a model motor, and its optimal design shows higher performance characteristics. This research paper presents and validates an optimally designed state-of-the-art IPMSM motor, which gives higher torque density, lower torque ripples, efficiency of the drive, lower magnet volume, and higher power factor. The design input parameters include magnet thickness, width, and pole V-angle. Using the initial model of a 60kW PMSM motor, the results are generated through FEA analysis, optimization with OptiSlang, and performance is validated with an input of urban drive cycle and operation in the wide speed range.
{"title":"State-of-the-Art Design Optimization of an IPM Synchronous Motor for Electric Vehicle Applications","authors":"M. U. Sardar, Dou Manfeng, Umar Saleem, Mannan Hassan, Muhammad Kashif Nawaz","doi":"10.1109/ETECTE55893.2022.10007182","DOIUrl":"https://doi.org/10.1109/ETECTE55893.2022.10007182","url":null,"abstract":"Nowadays, vehicles based on electric charge and operation due to the motor are more prevalent in use due to their superiority in zero-emission, lowest noise, higher power density to size or weight ratio, and higher performance. In this scenario, synchronous machines using permanent interior magnets (IPMSM) are a suitable candidate and a potential source of mechanical power generation in electric vehicles (EVs). They have unique merits over the other types of electric motor families. A rare earth permanent magnet material with an interior V-type rotor is used as a model motor, and its optimal design shows higher performance characteristics. This research paper presents and validates an optimally designed state-of-the-art IPMSM motor, which gives higher torque density, lower torque ripples, efficiency of the drive, lower magnet volume, and higher power factor. The design input parameters include magnet thickness, width, and pole V-angle. Using the initial model of a 60kW PMSM motor, the results are generated through FEA analysis, optimization with OptiSlang, and performance is validated with an input of urban drive cycle and operation in the wide speed range.","PeriodicalId":131572,"journal":{"name":"2022 International Conference on Emerging Trends in Electrical, Control, and Telecommunication Engineering (ETECTE)","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121814025","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 : 2022-12-02DOI: 10.1109/ETECTE55893.2022.10007126
Badar Ali, A. Mughal
Biomechanical modelling in three dimensions of human voluntary motion with motor control is an extremely important field that consists of human intended behaviors. The human body demonstrates extremely complicated motion trajectories with a very high level of mobility and degree of freedom (DOF). In this research, we have extended our 3D biomechanical model research to develop the optimal motor controls that exhibit biomechanical schemes for human sit to stand (STS) motion. The developed three modelling schemes are realized to analyze the motion constraints on rigid body model of human STS motion. Model developed in CAD software SOLIDWORKS Corp. comprising of a 3D 8-segment biped having 2 feet, 2 calf, 2 thigh, a pelvic and a HAT segment is utilized to generate the LQR based optimal control on the developed reference trajectories of each joint. Model having one foot fix and other a 1DOF prismatic joint is utilized for controller development due to its full rank controllability and observability. The optimal control is developed in MATLAB / SIMULINK after linearizing the model in SIMSCAPE / SIMULINK by importing the xml files from SOLIDWORKS. Control system utilized the feedback of position and speed of each joint and generates the torque inputs for the model based on the required reference trajectories. The developed model is of 22nd order and the results show that all the motor joints followed the reference trajectories.
{"title":"Modelling and Optimal Control of Human Voluntary Motion in 3D for Bipedal","authors":"Badar Ali, A. Mughal","doi":"10.1109/ETECTE55893.2022.10007126","DOIUrl":"https://doi.org/10.1109/ETECTE55893.2022.10007126","url":null,"abstract":"Biomechanical modelling in three dimensions of human voluntary motion with motor control is an extremely important field that consists of human intended behaviors. The human body demonstrates extremely complicated motion trajectories with a very high level of mobility and degree of freedom (DOF). In this research, we have extended our 3D biomechanical model research to develop the optimal motor controls that exhibit biomechanical schemes for human sit to stand (STS) motion. The developed three modelling schemes are realized to analyze the motion constraints on rigid body model of human STS motion. Model developed in CAD software SOLIDWORKS Corp. comprising of a 3D 8-segment biped having 2 feet, 2 calf, 2 thigh, a pelvic and a HAT segment is utilized to generate the LQR based optimal control on the developed reference trajectories of each joint. Model having one foot fix and other a 1DOF prismatic joint is utilized for controller development due to its full rank controllability and observability. The optimal control is developed in MATLAB / SIMULINK after linearizing the model in SIMSCAPE / SIMULINK by importing the xml files from SOLIDWORKS. Control system utilized the feedback of position and speed of each joint and generates the torque inputs for the model based on the required reference trajectories. The developed model is of 22nd order and the results show that all the motor joints followed the reference trajectories.","PeriodicalId":131572,"journal":{"name":"2022 International Conference on Emerging Trends in Electrical, Control, and Telecommunication Engineering (ETECTE)","volume":"942 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127007288","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 : 2022-12-02DOI: 10.1109/ETECTE55893.2022.10007379
Sara Khan, Amna Qureshi
Cyberbullying has become a significant problem with the surge in the use of social media. The most basic way to prevent cyberbullying on these social media platforms is to identify and remove offensive comments. However, it is hard for humans to read and remove all the comments manually. Current research work focuses on using machine learning to detect and eliminate cyberbullying. Although most of the work has been conducted on English texts to detect cyberbullying, limited to no work can be found in Urdu. This paper aims to detect cyberbullying from the users' comments posted in Urdu on Twitter using machine learning and Natural Language Processing (NLP) techniques. To the best of our knowledge, cyberbullying detection on Urdu text comments has not been performed due to the lack of a publicly available standard Urdu dataset. In this paper, we created a dataset of offensive user-generated Urdu comments from Twitter. The comments in the dataset are classified into five categories. n-gram techniques are used to extract features at character and word levels. Various supervised machine-learning techniques are applied to the dataset to detect cyberbullying. Evaluation metrics such as precision, recall, accuracy and F1 scores are used to analyse the performance of machine learning techniques.
{"title":"Cyberbullying Detection in Urdu Language Using Machine Learning","authors":"Sara Khan, Amna Qureshi","doi":"10.1109/ETECTE55893.2022.10007379","DOIUrl":"https://doi.org/10.1109/ETECTE55893.2022.10007379","url":null,"abstract":"Cyberbullying has become a significant problem with the surge in the use of social media. The most basic way to prevent cyberbullying on these social media platforms is to identify and remove offensive comments. However, it is hard for humans to read and remove all the comments manually. Current research work focuses on using machine learning to detect and eliminate cyberbullying. Although most of the work has been conducted on English texts to detect cyberbullying, limited to no work can be found in Urdu. This paper aims to detect cyberbullying from the users' comments posted in Urdu on Twitter using machine learning and Natural Language Processing (NLP) techniques. To the best of our knowledge, cyberbullying detection on Urdu text comments has not been performed due to the lack of a publicly available standard Urdu dataset. In this paper, we created a dataset of offensive user-generated Urdu comments from Twitter. The comments in the dataset are classified into five categories. n-gram techniques are used to extract features at character and word levels. Various supervised machine-learning techniques are applied to the dataset to detect cyberbullying. Evaluation metrics such as precision, recall, accuracy and F1 scores are used to analyse the performance of machine learning techniques.","PeriodicalId":131572,"journal":{"name":"2022 International Conference on Emerging Trends in Electrical, Control, and Telecommunication Engineering (ETECTE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129760431","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 : 2022-12-02DOI: 10.1109/ETECTE55893.2022.10007132
M. Yousaf, Muhammad Ahmad Khan, M. F. Tahir, Chen Zhichu, Fazal Badshah, S. Khalid
With the rising use of Phase Measurement Units (PMUs) in smart grid applications, it is important for PMUs to function in extreme circumstances, resulting in outliers and missing dataset. Traditional approaches take an inordinate amount of time to clear outliers and fill missing data to assure better accuracy. This study offers a flexible ensemble approach (FEA) to construct a precise, rapid, and sustainable data cleaning procedure with Apache Spark. To discover outliers in the suggested system, an ensemble model based on a soft voting technique employs PCA in combination with the K-means, GMM, and iForest approach. The suggested method fills the data with an improved gradient-boosting decision tree for each obtained PMUs characteristic after outlier detection. The test results demonstrate that the proposed model acquired good accuracy during comparing with LOF and DBSCAN techniques. To evaluate the suggested technique's data-filling outcomes against modern methods such as decision tree and linear regression techniques, the MAE and RMSE criteria are applied.
{"title":"The FE Approach for Data Cleaning of Phase Measurement Units","authors":"M. Yousaf, Muhammad Ahmad Khan, M. F. Tahir, Chen Zhichu, Fazal Badshah, S. Khalid","doi":"10.1109/ETECTE55893.2022.10007132","DOIUrl":"https://doi.org/10.1109/ETECTE55893.2022.10007132","url":null,"abstract":"With the rising use of Phase Measurement Units (PMUs) in smart grid applications, it is important for PMUs to function in extreme circumstances, resulting in outliers and missing dataset. Traditional approaches take an inordinate amount of time to clear outliers and fill missing data to assure better accuracy. This study offers a flexible ensemble approach (FEA) to construct a precise, rapid, and sustainable data cleaning procedure with Apache Spark. To discover outliers in the suggested system, an ensemble model based on a soft voting technique employs PCA in combination with the K-means, GMM, and iForest approach. The suggested method fills the data with an improved gradient-boosting decision tree for each obtained PMUs characteristic after outlier detection. The test results demonstrate that the proposed model acquired good accuracy during comparing with LOF and DBSCAN techniques. To evaluate the suggested technique's data-filling outcomes against modern methods such as decision tree and linear regression techniques, the MAE and RMSE criteria are applied.","PeriodicalId":131572,"journal":{"name":"2022 International Conference on Emerging Trends in Electrical, Control, and Telecommunication Engineering (ETECTE)","volume":"316 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126938592","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}