Pub Date : 2022-12-10DOI: 10.1109/STCR55312.2022.10009141
Jarabala Ranga, T. Arun Srinivas, Santosh Kumar, Harishchander Anandaram, P. Kulkarni, M. Amina Begum
Wind is considered as the renewable energy resource which consists of high state of efficiency with low pollution. The accurate level of forecasting can reduce the minimal range of losses and risk in the unrealizable factor. High energy of wind powers are defined where it comprises with the challenges in the power systems and other variability in generating the power. One of the key factors of the electricity supply is wind forecasting. It implies with the several improvements where many literatures have initially developed new technologies to forecast the wind power. A different range of forecast are been developed and are been categorized according to the expected production. These are indicated using the power productivity potential over the state of time interval. In this research paper, an overview of the different technologies used in the wind power forecasting are been discussed. This paper mainly focuses upon the research work of different literature review and their principles with the practical development. Based upon the categories, the futuristic development of each wind forecasting are been directed accordingly.
{"title":"Analysis of Artificial Intelligence based Forecasting Techniques for Renewable Wind Power Generation","authors":"Jarabala Ranga, T. Arun Srinivas, Santosh Kumar, Harishchander Anandaram, P. Kulkarni, M. Amina Begum","doi":"10.1109/STCR55312.2022.10009141","DOIUrl":"https://doi.org/10.1109/STCR55312.2022.10009141","url":null,"abstract":"Wind is considered as the renewable energy resource which consists of high state of efficiency with low pollution. The accurate level of forecasting can reduce the minimal range of losses and risk in the unrealizable factor. High energy of wind powers are defined where it comprises with the challenges in the power systems and other variability in generating the power. One of the key factors of the electricity supply is wind forecasting. It implies with the several improvements where many literatures have initially developed new technologies to forecast the wind power. A different range of forecast are been developed and are been categorized according to the expected production. These are indicated using the power productivity potential over the state of time interval. In this research paper, an overview of the different technologies used in the wind power forecasting are been discussed. This paper mainly focuses upon the research work of different literature review and their principles with the practical development. Based upon the categories, the futuristic development of each wind forecasting are been directed accordingly.","PeriodicalId":338691,"journal":{"name":"2022 Smart Technologies, Communication and Robotics (STCR)","volume":"33 8","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114014007","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 : 2022-12-10DOI: 10.1109/STCR55312.2022.10009123
S. Depuru, A. Nandam, S. Sivanantham, K. Amala, V. Akshaya, M. Saktivel
Recent research focuses towards Expression recognition. Variety of applications is now available ranging from security cameras to detecting emotions. Facial recognition is an important activity in emotion detection Convolutional Neural Networks (CNN) are used for facial recognition. Images are taken as input and facial expressions are produced as outcome like Happy, Sad, Disgust, Angry, Fear, Surprise and neutral. In this paper, we propose an Artificial Intelligence (AI) which recognizes the facial emotions using the different layers in the CNN. Thorough examination of deep Face Expression Recognizer (FER), including datasets and methods that shed light on these underlying difficulties. First, the FER scheme, which includes pertinent background information, is implemented for seeking advice for each level. The dataset used for experimentation is FER challenge dataset available in kaggle repository. The implementation environment includes keras, tensorflow, cv2 python packages. The results include the comparison of accuracy of emotion detection between training and testing phase. The average accuracy achieved was 84.50%.
{"title":"Convolutional Neural Network based Human Emotion Recognition System: A Deep Learning Approach","authors":"S. Depuru, A. Nandam, S. Sivanantham, K. Amala, V. Akshaya, M. Saktivel","doi":"10.1109/STCR55312.2022.10009123","DOIUrl":"https://doi.org/10.1109/STCR55312.2022.10009123","url":null,"abstract":"Recent research focuses towards Expression recognition. Variety of applications is now available ranging from security cameras to detecting emotions. Facial recognition is an important activity in emotion detection Convolutional Neural Networks (CNN) are used for facial recognition. Images are taken as input and facial expressions are produced as outcome like Happy, Sad, Disgust, Angry, Fear, Surprise and neutral. In this paper, we propose an Artificial Intelligence (AI) which recognizes the facial emotions using the different layers in the CNN. Thorough examination of deep Face Expression Recognizer (FER), including datasets and methods that shed light on these underlying difficulties. First, the FER scheme, which includes pertinent background information, is implemented for seeking advice for each level. The dataset used for experimentation is FER challenge dataset available in kaggle repository. The implementation environment includes keras, tensorflow, cv2 python packages. The results include the comparison of accuracy of emotion detection between training and testing phase. The average accuracy achieved was 84.50%.","PeriodicalId":338691,"journal":{"name":"2022 Smart Technologies, Communication and Robotics (STCR)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127718703","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 : 2022-12-10DOI: 10.1109/STCR55312.2022.10009609
K. M., D. D., C. K, Venkateshkumar U, S. V, P. l
In Vehicle-to-vehicle communication the Tera hertz band communication is not suitable as it affects health and RIS is the hopeful technique. This paper suggests a UAV to UAV or UAV to base station type of communication and its determining parameters under hardware constituting its errors. The position-based information is taken as a data source to avoid doppler effect and also spectrally efficient under a high-speed communication at hardware problems. This also aids the multi-RIS system. The proposed method upsurges the spectral efficiency for increasing the multi-RIS based communication. Comparisons are based on optimization of diverse phase shift with maximum spectral efficiency based on the power control. The proposed method eliminates the doppler spread. The delay spread is quite little possible and it can also be further more decreased by the using novel form of signal like delay-doppler modulation technique that utilizes a two-dimensional waveform. Simulation results show that increasing the number of IRS elements in each IRS gives a better spectral efficiency.
{"title":"UAV and Vehicular Communication with Hardware Impairments in Multiple RIS System","authors":"K. M., D. D., C. K, Venkateshkumar U, S. V, P. l","doi":"10.1109/STCR55312.2022.10009609","DOIUrl":"https://doi.org/10.1109/STCR55312.2022.10009609","url":null,"abstract":"In Vehicle-to-vehicle communication the Tera hertz band communication is not suitable as it affects health and RIS is the hopeful technique. This paper suggests a UAV to UAV or UAV to base station type of communication and its determining parameters under hardware constituting its errors. The position-based information is taken as a data source to avoid doppler effect and also spectrally efficient under a high-speed communication at hardware problems. This also aids the multi-RIS system. The proposed method upsurges the spectral efficiency for increasing the multi-RIS based communication. Comparisons are based on optimization of diverse phase shift with maximum spectral efficiency based on the power control. The proposed method eliminates the doppler spread. The delay spread is quite little possible and it can also be further more decreased by the using novel form of signal like delay-doppler modulation technique that utilizes a two-dimensional waveform. Simulation results show that increasing the number of IRS elements in each IRS gives a better spectral efficiency.","PeriodicalId":338691,"journal":{"name":"2022 Smart Technologies, Communication and Robotics (STCR)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130020004","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 : 2022-12-10DOI: 10.1109/STCR55312.2022.10009151
S. Martínez, Simon Valencia, Alejandro Toro-Ossaba, J. David Núñez, Juan C. Tejada, Santiago Rúa, A. López-González
Soft robotics has been widely explored in the past decade due to their ability to adapt to different environments and interact softly with external objects. This paper presents the design, manufacture, model identification and control of a low cost soft robotic pneumatic actuator with sensing capabilities, the proposed actuator has potential application in prosthetic and orthotic devices. Initially, the design and fabrication of the actuator is presented, including the design parameters and manufacturing techniques. The system was modeled using system identification techniques allowing to implement a PI controller to control the actuator deformation. In addition, the design and fabrication of a soft bending sensor, based on a variable resistance material, was presented. The sensor was used as feedback element for the control system and allowed to control the deformation of the actuator. The soft actuator only requires 0.4 bar of pressure to achieve maximum deformation; the controlled actuator achieved a settling time of 4.5 s and an steady state error of 2 %.
{"title":"Design and Control of Soft Pneumatic Actuator with Embedded Flexion Sensor","authors":"S. Martínez, Simon Valencia, Alejandro Toro-Ossaba, J. David Núñez, Juan C. Tejada, Santiago Rúa, A. López-González","doi":"10.1109/STCR55312.2022.10009151","DOIUrl":"https://doi.org/10.1109/STCR55312.2022.10009151","url":null,"abstract":"Soft robotics has been widely explored in the past decade due to their ability to adapt to different environments and interact softly with external objects. This paper presents the design, manufacture, model identification and control of a low cost soft robotic pneumatic actuator with sensing capabilities, the proposed actuator has potential application in prosthetic and orthotic devices. Initially, the design and fabrication of the actuator is presented, including the design parameters and manufacturing techniques. The system was modeled using system identification techniques allowing to implement a PI controller to control the actuator deformation. In addition, the design and fabrication of a soft bending sensor, based on a variable resistance material, was presented. The sensor was used as feedback element for the control system and allowed to control the deformation of the actuator. The soft actuator only requires 0.4 bar of pressure to achieve maximum deformation; the controlled actuator achieved a settling time of 4.5 s and an steady state error of 2 %.","PeriodicalId":338691,"journal":{"name":"2022 Smart Technologies, Communication and Robotics (STCR)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131398065","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 : 2022-12-10DOI: 10.1109/STCR55312.2022.10009425
Dinesh Kumar J R, Shri Dharshana S, G. C, P. K, Shamitha M, Reveetha A
Audio Signal processing is a method that uses intensive algorithms that are applied to audio signals. Audio signals are in the form of both analog and digital signals and they are the typical representation of sound. The frequency of audio ranges from 20Hz to 20,000 Hz, and 20Hz is the lower limit of our ears and 20,000Hz is the upper limit of our ears. The process of audio signal processing gives the desired audio by removing the unwanted noise from the speech signal. This process balances the time and frequency range. This process also aims on commutative methods by altering sounds and removes echo, unwanted noise and over modulation. Recent literatures focus on removal of noise from the audio signal. We are dealing with enhancing the quality of speech. Speech consists of various noises such as stationaries noises and non-stationary noises. Several strategies are proposed which are based on Deep learning and Deep Neural Networks to overcome this problem. The main goal of the paper is improvement in the quality of speech signals that are corrupted by noise. This will enhance the performance of digital hearing aid using Deep Neural Networks before it delivers to the needy people and also to measure and analyze the emotion of speech.
{"title":"Performance Analysis of Inbuilt Hearing Aid using Signal Enhancement by Deep Learning","authors":"Dinesh Kumar J R, Shri Dharshana S, G. C, P. K, Shamitha M, Reveetha A","doi":"10.1109/STCR55312.2022.10009425","DOIUrl":"https://doi.org/10.1109/STCR55312.2022.10009425","url":null,"abstract":"Audio Signal processing is a method that uses intensive algorithms that are applied to audio signals. Audio signals are in the form of both analog and digital signals and they are the typical representation of sound. The frequency of audio ranges from 20Hz to 20,000 Hz, and 20Hz is the lower limit of our ears and 20,000Hz is the upper limit of our ears. The process of audio signal processing gives the desired audio by removing the unwanted noise from the speech signal. This process balances the time and frequency range. This process also aims on commutative methods by altering sounds and removes echo, unwanted noise and over modulation. Recent literatures focus on removal of noise from the audio signal. We are dealing with enhancing the quality of speech. Speech consists of various noises such as stationaries noises and non-stationary noises. Several strategies are proposed which are based on Deep learning and Deep Neural Networks to overcome this problem. The main goal of the paper is improvement in the quality of speech signals that are corrupted by noise. This will enhance the performance of digital hearing aid using Deep Neural Networks before it delivers to the needy people and also to measure and analyze the emotion of speech.","PeriodicalId":338691,"journal":{"name":"2022 Smart Technologies, Communication and Robotics (STCR)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128227596","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 : 2022-12-10DOI: 10.1109/STCR55312.2022.10009636
B. R, Maheswari K T, B. M, Sangeethkumar C
Nowadays, due to the increased population, usage of public places becomes very high. However, garbage is left uncleaned in most public areas. There is no constant survey of the area at a given time so that the waste gets accumulated. The most crowded places like malls and parks remains unclean. This affects not only the environment but also the mindset of the people visiting the places, so the proposed idea provides a great solution to these problems through the following steps. It continuously monitors a given area and detects the presence of garbage in that given area. The live image is then calibrated to detect the distance and to operate the arm to pick up the trash. The picked trash is then thrown in the collector attached at the back of the bot and released when it is full, on the established disposal area. This will help to clean the environment in a drastic way and also in attracting the people to visit the area. The bot will help in reducing the burden of human beings and also provides 24/7 maintenance to the predefined area. For a much larger area using this bot will be the most commercially feasible, the bot will not only be most effective for the above scenario but it will be most commercially effective as well as a viable option as well. This is the main objective for making a bot that does the above function. In this paper, a software has been developed using python with which various items can be identified and can be segregated as trash and not a trash item. The autonomous trash collector robot has been designed using sold works and Roboanalyzer softwares and the results are analyzed.
{"title":"Design and Simulation of Object Detection Based Autonomous Trash Collector Bot","authors":"B. R, Maheswari K T, B. M, Sangeethkumar C","doi":"10.1109/STCR55312.2022.10009636","DOIUrl":"https://doi.org/10.1109/STCR55312.2022.10009636","url":null,"abstract":"Nowadays, due to the increased population, usage of public places becomes very high. However, garbage is left uncleaned in most public areas. There is no constant survey of the area at a given time so that the waste gets accumulated. The most crowded places like malls and parks remains unclean. This affects not only the environment but also the mindset of the people visiting the places, so the proposed idea provides a great solution to these problems through the following steps. It continuously monitors a given area and detects the presence of garbage in that given area. The live image is then calibrated to detect the distance and to operate the arm to pick up the trash. The picked trash is then thrown in the collector attached at the back of the bot and released when it is full, on the established disposal area. This will help to clean the environment in a drastic way and also in attracting the people to visit the area. The bot will help in reducing the burden of human beings and also provides 24/7 maintenance to the predefined area. For a much larger area using this bot will be the most commercially feasible, the bot will not only be most effective for the above scenario but it will be most commercially effective as well as a viable option as well. This is the main objective for making a bot that does the above function. In this paper, a software has been developed using python with which various items can be identified and can be segregated as trash and not a trash item. The autonomous trash collector robot has been designed using sold works and Roboanalyzer softwares and the results are analyzed.","PeriodicalId":338691,"journal":{"name":"2022 Smart Technologies, Communication and Robotics (STCR)","volume":"304 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132042474","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 : 2022-12-10DOI: 10.1109/STCR55312.2022.10009146
S. V, Poongodi C, S. G, S. S, S. V
Our paper uses an innovative 3D Convolutional Neural Network to determine lung cancer from patients' Computed Tomography (CT) scans because Convolutional Neural Networks (CNN) are useful for extracting important characteristics from images. This project aims to analyze CT scan slices (the data) and create a machine learning model based on the analysis. In this case, 3D Convolutional Neural Networks determine whether a person has cancer by evaluating the data and using a preprocessing technique. By utilizing this device, one can identify and eliminate cancerous cells at their earliest stages
{"title":"Lung Cancer Detection using 3D-Convolution Neural Network","authors":"S. V, Poongodi C, S. G, S. S, S. V","doi":"10.1109/STCR55312.2022.10009146","DOIUrl":"https://doi.org/10.1109/STCR55312.2022.10009146","url":null,"abstract":"Our paper uses an innovative 3D Convolutional Neural Network to determine lung cancer from patients' Computed Tomography (CT) scans because Convolutional Neural Networks (CNN) are useful for extracting important characteristics from images. This project aims to analyze CT scan slices (the data) and create a machine learning model based on the analysis. In this case, 3D Convolutional Neural Networks determine whether a person has cancer by evaluating the data and using a preprocessing technique. By utilizing this device, one can identify and eliminate cancerous cells at their earliest stages","PeriodicalId":338691,"journal":{"name":"2022 Smart Technologies, Communication and Robotics (STCR)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126624585","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 : 2022-12-10DOI: 10.1109/STCR55312.2022.10009103
Mohammed Sekhi, M. Ilyas
The process of exchanging information via electronic communications is a sensitive matter in our time, and with the development of devices, technologies, and methods of analysis, the usual methods may be unsafe, so we always resort to developing them or perhaps new ideas. In this research, we will talk about a new method of encryption called (FSUIE) that depends on the image, where the way to work will be by comparing the bytes of characters with the bytes of the image and using the locations of these bytes as an encrypted text sent to the future, regardless of the length of this encrypted text. In addition to mentioning some algorithms other to compare them to how each works.
{"title":"File Security using Image-based Encryption (FSUIE)","authors":"Mohammed Sekhi, M. Ilyas","doi":"10.1109/STCR55312.2022.10009103","DOIUrl":"https://doi.org/10.1109/STCR55312.2022.10009103","url":null,"abstract":"The process of exchanging information via electronic communications is a sensitive matter in our time, and with the development of devices, technologies, and methods of analysis, the usual methods may be unsafe, so we always resort to developing them or perhaps new ideas. In this research, we will talk about a new method of encryption called (FSUIE) that depends on the image, where the way to work will be by comparing the bytes of characters with the bytes of the image and using the locations of these bytes as an encrypted text sent to the future, regardless of the length of this encrypted text. In addition to mentioning some algorithms other to compare them to how each works.","PeriodicalId":338691,"journal":{"name":"2022 Smart Technologies, Communication and Robotics (STCR)","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126863386","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 : 2022-12-10DOI: 10.1109/STCR55312.2022.10009053
Aniket Ajit Tambe, Manasi Kulkarni
An Automated Essay Scoring System is a system that deals with grading Hand written essays without any human intervention. Most of the research done in this field involves direct mapping of an essay’s numerical representation, using word embedding, to its golden score, without any specific trait scoring. So, this research aims to use latest contextual Text Embedding i.e., BERT Embedding for numerical representation of Essay and granulate the scoring of essay into two modules: structure scoring module which deals with scoring essay on the basis of its structure and grammar scoring module, which deals with scoring essay on the basis of its grammatical correctness. To evaluate the proposed model, Quadratic Weighted Kappa Score is used. In this implementation, a QWK score of 0.75 for Structure score and 0.70 for Grammar Score has been obtained. This research and its specific trait scoring can be used as base for future implementation with more detailed feature specific scoring tasks and improve the scope of grammar scoring by considering more grammatical cases.
{"title":"Automated Essay Scoring System with Grammar Score Analysis","authors":"Aniket Ajit Tambe, Manasi Kulkarni","doi":"10.1109/STCR55312.2022.10009053","DOIUrl":"https://doi.org/10.1109/STCR55312.2022.10009053","url":null,"abstract":"An Automated Essay Scoring System is a system that deals with grading Hand written essays without any human intervention. Most of the research done in this field involves direct mapping of an essay’s numerical representation, using word embedding, to its golden score, without any specific trait scoring. So, this research aims to use latest contextual Text Embedding i.e., BERT Embedding for numerical representation of Essay and granulate the scoring of essay into two modules: structure scoring module which deals with scoring essay on the basis of its structure and grammar scoring module, which deals with scoring essay on the basis of its grammatical correctness. To evaluate the proposed model, Quadratic Weighted Kappa Score is used. In this implementation, a QWK score of 0.75 for Structure score and 0.70 for Grammar Score has been obtained. This research and its specific trait scoring can be used as base for future implementation with more detailed feature specific scoring tasks and improve the scope of grammar scoring by considering more grammatical cases.","PeriodicalId":338691,"journal":{"name":"2022 Smart Technologies, Communication and Robotics (STCR)","volume":"110 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131761884","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 : 2022-12-10DOI: 10.1109/STCR55312.2022.10009556
G. C, Gowri Shankar M, H. Rajaguru, Priyanka G S, A. T
Epilepsy is a neurological illness that affects a significant number of individuals all over the globe, and the treatment that they get with medicine is not always effective. Analyzing recordings made using electroencephalography (EEG) could provide one with a wealth of information on the system that is responsible for the formation of epilepsy. For exhibiting the many attributes of non stationary signals, like recurring patterns and discontinuities, the wavelet transform tool is very helpful. Therefore, the wavelet transform tool is employed in order to quantify and investigate the epileptiform events. In this study, Haar and dB2 are employed to reduce the features dimensionality from EEG outputs. After this, the reduced information is identified with the assistance of a Compensatory Gaussian Mixture Model (GMM) learning algorithm. Results indicate that an average accuracy of 89.43% is achieved when the Haar wavelet features is identified using compensatory GMM and an average accuracy of 85.75% is achieved when the dB2 wavelet features is identified using compensatory GMM.
{"title":"Analyzing Haar and dB2 with Compensatory GMM Classifier for Epilepsy Detection","authors":"G. C, Gowri Shankar M, H. Rajaguru, Priyanka G S, A. T","doi":"10.1109/STCR55312.2022.10009556","DOIUrl":"https://doi.org/10.1109/STCR55312.2022.10009556","url":null,"abstract":"Epilepsy is a neurological illness that affects a significant number of individuals all over the globe, and the treatment that they get with medicine is not always effective. Analyzing recordings made using electroencephalography (EEG) could provide one with a wealth of information on the system that is responsible for the formation of epilepsy. For exhibiting the many attributes of non stationary signals, like recurring patterns and discontinuities, the wavelet transform tool is very helpful. Therefore, the wavelet transform tool is employed in order to quantify and investigate the epileptiform events. In this study, Haar and dB2 are employed to reduce the features dimensionality from EEG outputs. After this, the reduced information is identified with the assistance of a Compensatory Gaussian Mixture Model (GMM) learning algorithm. Results indicate that an average accuracy of 89.43% is achieved when the Haar wavelet features is identified using compensatory GMM and an average accuracy of 85.75% is achieved when the dB2 wavelet features is identified using compensatory GMM.","PeriodicalId":338691,"journal":{"name":"2022 Smart Technologies, Communication and Robotics (STCR)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132723570","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：