Pub Date : 2021-11-27DOI: 10.1109/i-PACT52855.2021.9696822
N. K. Swarnkar, Om Prakash Mahela, M. Lalwani
In this paper, evaluation of power quality (PQ) disturbances observed with a distribution system with availability of high penetration of wind power generation is achieved using the hybrid algorithm designed applying the Hilbert transform (HT) and Stockwell transform (ST). An index for PQ identification (IPI) and an index for event location (IPL) have been designed by processing the voltage signals using the ST and HT. IPI index effectively recognize PQ issues associated with utility grid with availability of high wind energy penetration. This is achieved for the grid operations such as switching of the loads & capacitors, feeder operations, wind power plant operations and island formation in the presence of high wind power generation. These events have been categorized using the decision rules driven by the features computed from the IPI and IPL indices. Proposed method performs better relative to Discrete Wavelet transform (DWT) based technique. Results are validated in MATLAB using an IEEE-13 node test network interfaced with wind power plants.
{"title":"Evaluation of Power Quality in Distribution System with High Penetration of Wind Power Generation","authors":"N. K. Swarnkar, Om Prakash Mahela, M. Lalwani","doi":"10.1109/i-PACT52855.2021.9696822","DOIUrl":"https://doi.org/10.1109/i-PACT52855.2021.9696822","url":null,"abstract":"In this paper, evaluation of power quality (PQ) disturbances observed with a distribution system with availability of high penetration of wind power generation is achieved using the hybrid algorithm designed applying the Hilbert transform (HT) and Stockwell transform (ST). An index for PQ identification (IPI) and an index for event location (IPL) have been designed by processing the voltage signals using the ST and HT. IPI index effectively recognize PQ issues associated with utility grid with availability of high wind energy penetration. This is achieved for the grid operations such as switching of the loads & capacitors, feeder operations, wind power plant operations and island formation in the presence of high wind power generation. These events have been categorized using the decision rules driven by the features computed from the IPI and IPL indices. Proposed method performs better relative to Discrete Wavelet transform (DWT) based technique. Results are validated in MATLAB using an IEEE-13 node test network interfaced with wind power plants.","PeriodicalId":335956,"journal":{"name":"2021 Innovations in Power and Advanced Computing Technologies (i-PACT)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115930246","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 : 2021-11-27DOI: 10.1109/i-PACT52855.2021.9696453
V. Srinivasan, D. Kumari, M. Fernando
With growing concerns related to climate change, protection of heritage monuments from lightning strikes has become vital. Though several research studies have culminated in the development of lightning protection systems, challenges related to strikes on tall structures, complexities in protection of monuments with varying geometries, uncertainties in leader prediction modeling etc., continue to confront researchers. This research envisages a novel framework for implementation of two-dimensional Cellular Automata (CA) based on stochastic field fluctuation criterion (FFC) for leader growth. A random variable which relates to uncertainty associated with atmospheric ionization, air density, etc., is utilized in modeling the field fluctuation. The electric field and potential in the highly conductive region are computed using the Laplace equation. Detailed simulations of CA models are carried out for a prominent world heritage monument in India, which has reported lightning strikes. Case studies for prediction of leader propagation based on varying cloud height, location, potential etc., have been carried out. Exhaustive analysis has been carried out to determine the vulnerable points during leader attachment on the monuments. Comparison of the leader trajectory with that of ‘striking distance’ as stipulated in standards is carried out to ascertain the effectiveness of the proposed models
{"title":"Two Dimensional Cellular Automaton for Lightning Leader Propagation and Prediction in Giant South Indian Heritage Monument","authors":"V. Srinivasan, D. Kumari, M. Fernando","doi":"10.1109/i-PACT52855.2021.9696453","DOIUrl":"https://doi.org/10.1109/i-PACT52855.2021.9696453","url":null,"abstract":"With growing concerns related to climate change, protection of heritage monuments from lightning strikes has become vital. Though several research studies have culminated in the development of lightning protection systems, challenges related to strikes on tall structures, complexities in protection of monuments with varying geometries, uncertainties in leader prediction modeling etc., continue to confront researchers. This research envisages a novel framework for implementation of two-dimensional Cellular Automata (CA) based on stochastic field fluctuation criterion (FFC) for leader growth. A random variable which relates to uncertainty associated with atmospheric ionization, air density, etc., is utilized in modeling the field fluctuation. The electric field and potential in the highly conductive region are computed using the Laplace equation. Detailed simulations of CA models are carried out for a prominent world heritage monument in India, which has reported lightning strikes. Case studies for prediction of leader propagation based on varying cloud height, location, potential etc., have been carried out. Exhaustive analysis has been carried out to determine the vulnerable points during leader attachment on the monuments. Comparison of the leader trajectory with that of ‘striking distance’ as stipulated in standards is carried out to ascertain the effectiveness of the proposed models","PeriodicalId":335956,"journal":{"name":"2021 Innovations in Power and Advanced Computing Technologies (i-PACT)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124163206","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 : 2021-11-27DOI: 10.1109/i-PACT52855.2021.9696578
A. S. Sidthik, M. Ravindran
An electric power supply-demand is increasing in our day-to-day life, where power transformers are significant devices in the power system. Most industries prefer oil-filled transformers instead of dry-type transformers. Transformer oil (Mineral oil) is universally used insulating material in the high voltage power transformer. According to a British Research Council report, overexploitation of petroleum products, the mineral oil will run out in near future. Because of its non-biodegradable property it does not an eco-friendly product also it does not meet current environmental acts. To the concern of limitation of resources and ecological system, nowadays researchers focus on substitute for conventional mineral oil mainly. So the researchers analyze the practicability, feasibility, sustainability and performance of Natural esters (vegetable oils), specifically in high voltage power transformers. Because, Natural esters possess outstanding biodegrading property, non-poisonous ness, greater fire safety guarantees and dielectric strength compared to the conventional transformer oil or mineral oil. Investigation of this paper embraces the electrical, physical, chemical properties and their blend properties of natural esters.
{"title":"Typical Analysis of Different Natural Esters and their Performance: A Review","authors":"A. S. Sidthik, M. Ravindran","doi":"10.1109/i-PACT52855.2021.9696578","DOIUrl":"https://doi.org/10.1109/i-PACT52855.2021.9696578","url":null,"abstract":"An electric power supply-demand is increasing in our day-to-day life, where power transformers are significant devices in the power system. Most industries prefer oil-filled transformers instead of dry-type transformers. Transformer oil (Mineral oil) is universally used insulating material in the high voltage power transformer. According to a British Research Council report, overexploitation of petroleum products, the mineral oil will run out in near future. Because of its non-biodegradable property it does not an eco-friendly product also it does not meet current environmental acts. To the concern of limitation of resources and ecological system, nowadays researchers focus on substitute for conventional mineral oil mainly. So the researchers analyze the practicability, feasibility, sustainability and performance of Natural esters (vegetable oils), specifically in high voltage power transformers. Because, Natural esters possess outstanding biodegrading property, non-poisonous ness, greater fire safety guarantees and dielectric strength compared to the conventional transformer oil or mineral oil. Investigation of this paper embraces the electrical, physical, chemical properties and their blend properties of natural esters.","PeriodicalId":335956,"journal":{"name":"2021 Innovations in Power and Advanced Computing Technologies (i-PACT)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114397727","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 : 2021-11-27DOI: 10.1109/i-PACT52855.2021.9696825
A. Soumya, J. Belwin Edward
A new method of anti-islanding detection in a Microgrid using Artificial Neural Network (ANN) with Daubechies 4 type mother wavelet which is decomposed into five level wavelets is discussed in this paper. The Microgrid discussed here comprises of a Photovoltaic system, Wind Energy Conversion System (WECS), Solid Oxide Fuel Cell (SOFC) with a battery along with linear and non-linear loads. The potential difference in the PCC along with current waveform at the same point is used for detection of islanding. The system is studied under different fault conditions and the results are discussed. Signals such as Energy levels and SD of the extracted signals at the point of common coupling both under faulty and normal operating condition are used to train the neural network. MATLAB Simulink and M file is used for the analysis of this system at various conditions.
{"title":"An Intelligent Method of Anti Islanding Detection using ANN","authors":"A. Soumya, J. Belwin Edward","doi":"10.1109/i-PACT52855.2021.9696825","DOIUrl":"https://doi.org/10.1109/i-PACT52855.2021.9696825","url":null,"abstract":"A new method of anti-islanding detection in a Microgrid using Artificial Neural Network (ANN) with Daubechies 4 type mother wavelet which is decomposed into five level wavelets is discussed in this paper. The Microgrid discussed here comprises of a Photovoltaic system, Wind Energy Conversion System (WECS), Solid Oxide Fuel Cell (SOFC) with a battery along with linear and non-linear loads. The potential difference in the PCC along with current waveform at the same point is used for detection of islanding. The system is studied under different fault conditions and the results are discussed. Signals such as Energy levels and SD of the extracted signals at the point of common coupling both under faulty and normal operating condition are used to train the neural network. MATLAB Simulink and M file is used for the analysis of this system at various conditions.","PeriodicalId":335956,"journal":{"name":"2021 Innovations in Power and Advanced Computing Technologies (i-PACT)","volume":"87 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114506905","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 : 2021-11-27DOI: 10.1109/i-PACT52855.2021.9696665
Pallavi, Sonali, Tanuritha, Vidhya, Prof. Anjini
Visual Question Answering (VQA) in recent times challenges fields that have received an outsized interest from the areas of Natural Language Processing and Computer Vision. VQA aims to establish an intelligent system to predict the answers for the natural language questions raised related to the image. The questions about the abstract or real word images are appealed to the VQA system; The system understands the image, and questions using Natural Language Processing (NLP) and Computer Vision which aims to predict the answer in natural language. The main issues which affect the performance of the VQA system is the inability to deal with the open-ended question acquired from the user. The proposed system is developed with a Graphical User Interface (GUI) that extracts the image features using pretrained VGG 16, and Golve embedding and Long Short- Term Memory (LSTM) are used in order to extract question features. By merging the characteristics of the images and the questions using pointwise multiplication the ultimate result is obtained. The acquired result is passed through a softmax layer to find the top 5 predictions about the image question. The proposed system has been experimented with various open-ended questions to show the robustness of the system. VQA finds its application in various real-world scenarios such as self-driving cars and guiding visually impaired people. Visual questions aim different parts of an image, including underlying context and background details.
{"title":"Visual Question Answering Using Deep Learning","authors":"Pallavi, Sonali, Tanuritha, Vidhya, Prof. Anjini","doi":"10.1109/i-PACT52855.2021.9696665","DOIUrl":"https://doi.org/10.1109/i-PACT52855.2021.9696665","url":null,"abstract":"Visual Question Answering (VQA) in recent times challenges fields that have received an outsized interest from the areas of Natural Language Processing and Computer Vision. VQA aims to establish an intelligent system to predict the answers for the natural language questions raised related to the image. The questions about the abstract or real word images are appealed to the VQA system; The system understands the image, and questions using Natural Language Processing (NLP) and Computer Vision which aims to predict the answer in natural language. The main issues which affect the performance of the VQA system is the inability to deal with the open-ended question acquired from the user. The proposed system is developed with a Graphical User Interface (GUI) that extracts the image features using pretrained VGG 16, and Golve embedding and Long Short- Term Memory (LSTM) are used in order to extract question features. By merging the characteristics of the images and the questions using pointwise multiplication the ultimate result is obtained. The acquired result is passed through a softmax layer to find the top 5 predictions about the image question. The proposed system has been experimented with various open-ended questions to show the robustness of the system. VQA finds its application in various real-world scenarios such as self-driving cars and guiding visually impaired people. Visual questions aim different parts of an image, including underlying context and background details.","PeriodicalId":335956,"journal":{"name":"2021 Innovations in Power and Advanced Computing Technologies (i-PACT)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114672833","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 : 2021-11-27DOI: 10.1109/i-PACT52855.2021.9696572
R. Kapoor, P. Upadhyay, Thirmal Chinthakuntta, Ganapavarapu Neeraj Kumar
Electronic components are the vital parts of future power system. It is required to develop high power sustainable electronic materials for capacitors, transducers, sensors etc. Good dielectric property of Barium Titanate makes it an important material for electronic industry. But this dielectric property, depends on properties of material like porosity, density, concentration etc. It is very costly and time consuming to determine these properties every time by experimentation. So, developing a system that can predict the properties of barium titanate can be helpful for electronic industries. The Current work is to develop AI based model that can estimate the physical properties of barium titanate dielectric material. A three-layer artificial neural network is trained to estimate the physical properties of the ceramic using the experimental data with the mean square error of less than 1. The performance of trained model is verified on different experimental data set.
{"title":"Neuro-Estimation of Physical Properties of BaTiO3 Ceramic Capacitors for High Power Applications","authors":"R. Kapoor, P. Upadhyay, Thirmal Chinthakuntta, Ganapavarapu Neeraj Kumar","doi":"10.1109/i-PACT52855.2021.9696572","DOIUrl":"https://doi.org/10.1109/i-PACT52855.2021.9696572","url":null,"abstract":"Electronic components are the vital parts of future power system. It is required to develop high power sustainable electronic materials for capacitors, transducers, sensors etc. Good dielectric property of Barium Titanate makes it an important material for electronic industry. But this dielectric property, depends on properties of material like porosity, density, concentration etc. It is very costly and time consuming to determine these properties every time by experimentation. So, developing a system that can predict the properties of barium titanate can be helpful for electronic industries. The Current work is to develop AI based model that can estimate the physical properties of barium titanate dielectric material. A three-layer artificial neural network is trained to estimate the physical properties of the ceramic using the experimental data with the mean square error of less than 1. The performance of trained model is verified on different experimental data set.","PeriodicalId":335956,"journal":{"name":"2021 Innovations in Power and Advanced Computing Technologies (i-PACT)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123554271","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 : 2021-11-27DOI: 10.1109/i-PACT52855.2021.9696883
Kandaswamy K V, S. Sahoo, F. Yanine
The study looks at a hybrid control approach for an islanded solar low voltage photovoltaic-based dc microgrid, with the goal of overcoming the limitations of both centralized and distributed control schemes. A Photo Volatile system with battery storage is used on bus 1, battery storage with supercapacitor is used on bus 2, and variable loads like automobile applications are used on bus 3. The suggested hybrid control approach is capable of effortlessly transitioning between high and low bandwidth communication to construct a distributed control system in the event of a central failure. The central supervisory control system is in responsible of adjusting grid settings as well as sending and receiving data to and from local node controllers, that govern bus voltage and energy management. The study demonstrates how system transients are absorbed using battery and supercapacitor devices during load changes. The simulation depicts the continuous flow of information and decision-making processes via each level of control while taking subsystem restrictions into consideration.
{"title":"Islanded Hybrid DC Micro Grid Power Scheme with Super Capacitor","authors":"Kandaswamy K V, S. Sahoo, F. Yanine","doi":"10.1109/i-PACT52855.2021.9696883","DOIUrl":"https://doi.org/10.1109/i-PACT52855.2021.9696883","url":null,"abstract":"The study looks at a hybrid control approach for an islanded solar low voltage photovoltaic-based dc microgrid, with the goal of overcoming the limitations of both centralized and distributed control schemes. A Photo Volatile system with battery storage is used on bus 1, battery storage with supercapacitor is used on bus 2, and variable loads like automobile applications are used on bus 3. The suggested hybrid control approach is capable of effortlessly transitioning between high and low bandwidth communication to construct a distributed control system in the event of a central failure. The central supervisory control system is in responsible of adjusting grid settings as well as sending and receiving data to and from local node controllers, that govern bus voltage and energy management. The study demonstrates how system transients are absorbed using battery and supercapacitor devices during load changes. The simulation depicts the continuous flow of information and decision-making processes via each level of control while taking subsystem restrictions into consideration.","PeriodicalId":335956,"journal":{"name":"2021 Innovations in Power and Advanced Computing Technologies (i-PACT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125838789","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 : 2021-11-27DOI: 10.1109/i-PACT52855.2021.9696587
Shachi Sinha, E. Teli, R. Sivakumar
The use and examination of 3D picture files of the human body, generally gathered from a Computed Tomography (CT) or Magnetic Resonance Imaging (MRI) scanner, to diagnose diseases, guide medical operations such as surgery planning, or for research purposes, is known as medical image processing. It allows for a comprehensive study of the internal anatomy while being non-invasive. 3D models of anatomical structures of interest can be built and studied in order to improve patient treatment outcomes, develop better medical equipment and drug delivery systems, and arrive at more accurate diagnoses. It has recently become one of the most essential instruments for medical improvement. It was shown that curvelet transformations performed better than other transforms on medical data. In tests, Curvelet greatly improves the classification of aberrant tissues in scans and reduces the surrounding noise. We gave an overview of contemporary advances and technologies including curvelet transform as well as digital subtraction angiography in this paper. The study also discusses the uses of wavelet and ridglet transforms, as well as the drawbacks that inspired the use of the curvelet transform for improved image visualisation.
{"title":"Applications of Curvelet Transform: A Review","authors":"Shachi Sinha, E. Teli, R. Sivakumar","doi":"10.1109/i-PACT52855.2021.9696587","DOIUrl":"https://doi.org/10.1109/i-PACT52855.2021.9696587","url":null,"abstract":"The use and examination of 3D picture files of the human body, generally gathered from a Computed Tomography (CT) or Magnetic Resonance Imaging (MRI) scanner, to diagnose diseases, guide medical operations such as surgery planning, or for research purposes, is known as medical image processing. It allows for a comprehensive study of the internal anatomy while being non-invasive. 3D models of anatomical structures of interest can be built and studied in order to improve patient treatment outcomes, develop better medical equipment and drug delivery systems, and arrive at more accurate diagnoses. It has recently become one of the most essential instruments for medical improvement. It was shown that curvelet transformations performed better than other transforms on medical data. In tests, Curvelet greatly improves the classification of aberrant tissues in scans and reduces the surrounding noise. We gave an overview of contemporary advances and technologies including curvelet transform as well as digital subtraction angiography in this paper. The study also discusses the uses of wavelet and ridglet transforms, as well as the drawbacks that inspired the use of the curvelet transform for improved image visualisation.","PeriodicalId":335956,"journal":{"name":"2021 Innovations in Power and Advanced Computing Technologies (i-PACT)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126010990","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 : 2021-11-27DOI: 10.1109/i-PACT52855.2021.9696653
Sree Harsha Bommisetty, Shiva sai Anuraag Nalam, Jujare Sai Vardhan, S. Ashok
Electroencephalograms (EEG) signals generally vary rapidly with time. These signals also have effect on the biotic lives which have brain. As the signals are rapid, their categorization becomes difficult. Most of the works regarding EEG signal categorization are highly domain specific. It requires a lot of time for the sub processes which are processing of signals and feature extraction. As EEG signals are analog, rapid changing, they have negligible Signal to Noise Ratio (SNR) value and hence this makes them vulnerable to any small disturbances or discrepancies. The proposed work is hence non-domain specific and has a comparison about the accuracies when the objective is achieved using Evolutionary Back Propagation Training Algorithm (EBPTA) and k-nearest neighbor (K-NN) algorithms. Convolutional operation is used for effective changing of specific data that can reveal the implicit spatial dependence of the Electroencephalography signals distribution. A dataset of 14 features and information about eye status is taken, and is tested, validated after training accordingly with two algorithms that is EBPTA and K-NN algorithms differently. The trails done prove that our work outperforms few other algorithms and results in accuracies of 98.94% and 96.99% for EBPTA and K-NN algorithms respectively, on chosen dataset with considerable resilience and time which makes them suitable for various range of problems which may be encountered in future.
{"title":"Detection of Eye State using Brain Signal Classification with EBPTA and KNN Algorithm","authors":"Sree Harsha Bommisetty, Shiva sai Anuraag Nalam, Jujare Sai Vardhan, S. Ashok","doi":"10.1109/i-PACT52855.2021.9696653","DOIUrl":"https://doi.org/10.1109/i-PACT52855.2021.9696653","url":null,"abstract":"Electroencephalograms (EEG) signals generally vary rapidly with time. These signals also have effect on the biotic lives which have brain. As the signals are rapid, their categorization becomes difficult. Most of the works regarding EEG signal categorization are highly domain specific. It requires a lot of time for the sub processes which are processing of signals and feature extraction. As EEG signals are analog, rapid changing, they have negligible Signal to Noise Ratio (SNR) value and hence this makes them vulnerable to any small disturbances or discrepancies. The proposed work is hence non-domain specific and has a comparison about the accuracies when the objective is achieved using Evolutionary Back Propagation Training Algorithm (EBPTA) and k-nearest neighbor (K-NN) algorithms. Convolutional operation is used for effective changing of specific data that can reveal the implicit spatial dependence of the Electroencephalography signals distribution. A dataset of 14 features and information about eye status is taken, and is tested, validated after training accordingly with two algorithms that is EBPTA and K-NN algorithms differently. The trails done prove that our work outperforms few other algorithms and results in accuracies of 98.94% and 96.99% for EBPTA and K-NN algorithms respectively, on chosen dataset with considerable resilience and time which makes them suitable for various range of problems which may be encountered in future.","PeriodicalId":335956,"journal":{"name":"2021 Innovations in Power and Advanced Computing Technologies (i-PACT)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128185529","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 : 2021-11-27DOI: 10.1109/i-PACT52855.2021.9696624
Kasthuri N, Nethra Krupa A, N. S, Madhavan R
In the present world visually impaired people use a state-of-art called Braille to read and interpret the text. But these books are available in only certain places and not in a great numbers. This makes visually impaired people to come out and enjoy the real world everyone is enjoying. To overcome this and to help visually impaired people to read the text on the go anywhere and under any circumstances we have proposed a system which is a wearable finger device that is worn on the pointing finger that can read aloud the text pointed by the pointing finger. This ensures the visually impaired people enjoy reading on their own and get a real life reading experience wearing this device. In the proposed system, a finger wearable device is put on the pointing finger and the device is mounted with camera that captures the word pointed by the finger. This image processed from TesserOCR is pre processed by image binarization. This image is then processed with TesseractOCR. Finger from the image is found and the word that's pointed is tracked down and is read aloud for the visually impaired. This helps the visually impaired person to get a real time reading experience. The goal of the project is to provide aid to blind and visually impaired with a portable device to read any text on the go, whether in the digital realm or physically, on any surface.
{"title":"Finger Vision for Visually Impaired","authors":"Kasthuri N, Nethra Krupa A, N. S, Madhavan R","doi":"10.1109/i-PACT52855.2021.9696624","DOIUrl":"https://doi.org/10.1109/i-PACT52855.2021.9696624","url":null,"abstract":"In the present world visually impaired people use a state-of-art called Braille to read and interpret the text. But these books are available in only certain places and not in a great numbers. This makes visually impaired people to come out and enjoy the real world everyone is enjoying. To overcome this and to help visually impaired people to read the text on the go anywhere and under any circumstances we have proposed a system which is a wearable finger device that is worn on the pointing finger that can read aloud the text pointed by the pointing finger. This ensures the visually impaired people enjoy reading on their own and get a real life reading experience wearing this device. In the proposed system, a finger wearable device is put on the pointing finger and the device is mounted with camera that captures the word pointed by the finger. This image processed from TesserOCR is pre processed by image binarization. This image is then processed with TesseractOCR. Finger from the image is found and the word that's pointed is tracked down and is read aloud for the visually impaired. This helps the visually impaired person to get a real time reading experience. The goal of the project is to provide aid to blind and visually impaired with a portable device to read any text on the go, whether in the digital realm or physically, on any surface.","PeriodicalId":335956,"journal":{"name":"2021 Innovations in Power and Advanced Computing Technologies (i-PACT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127310448","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}