Pub Date : 2022-02-16DOI: 10.1109/ICEEICT53079.2022.9768635
Sandip Desai, C. Gode, P. Fulzele
In the field of pharmaceutical industry, botany and agricultural there is a need of algorithm which will classify the flowers by processing its image. In this context, we propose a flower classification approach based on convolutional neural network. We have applied transfer learning approach for classification of flowers. We have used VGG19 convolution neural network architecture for extraction of features. As we wanted to classify flowers in 17 different classes so we have used 17 neurons in final dense layer of VGG19 convolution neural network architecture with the use of softmax activation function. Results show that we have classified flowers with the validation accuracy of 91.1 % and training accuracy of 100%.
{"title":"Flower Image Classification Using Convolutional Neural Network","authors":"Sandip Desai, C. Gode, P. Fulzele","doi":"10.1109/ICEEICT53079.2022.9768635","DOIUrl":"https://doi.org/10.1109/ICEEICT53079.2022.9768635","url":null,"abstract":"In the field of pharmaceutical industry, botany and agricultural there is a need of algorithm which will classify the flowers by processing its image. In this context, we propose a flower classification approach based on convolutional neural network. We have applied transfer learning approach for classification of flowers. We have used VGG19 convolution neural network architecture for extraction of features. As we wanted to classify flowers in 17 different classes so we have used 17 neurons in final dense layer of VGG19 convolution neural network architecture with the use of softmax activation function. Results show that we have classified flowers with the validation accuracy of 91.1 % and training accuracy of 100%.","PeriodicalId":201910,"journal":{"name":"2022 First International Conference on Electrical, Electronics, Information and Communication Technologies (ICEEICT)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131973083","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 : 2022-02-16DOI: 10.1109/ICEEICT53079.2022.9768535
Namrata Gupta, Alok Naugarhiya
This paper proposed a 1.4kV-class superjunction vertical IGBT (DMG-SJIGBT) with gate workfunction variation along with stepped oxide thickness. Two distinct workfunction materials, P+ and N+ polysilicon are used as gate poly and oxide thickness is varied in x-direction. All the stepped oxide is connected via metal on the top. The proposed structure's gate oxide is narrow at the emitter and wide at the collector to improve the device performance. It has been discovered that the ON-resistance (Ron.A) of the DMG-SJIGBT has been diminished by 23% as a result of this structural modification. Gate engineering improves the transconductivity by increasing the gate-emitter capacitance (CGE) and reducing the gate-collector capacitance (CGC), which lowers switching delay. To improve performance metrics, the gate length has been optimized. A mixed mode module of SILVACO has used to perform capacitance-voltage analysis. Further the gate charge and FOM has also been measured and indicating 36% and 34% respectively reduction for proposed device signifying enhanced performance.
{"title":"Capacitive Analysis of Superjunction Vertical IGBT with Gate Engineering","authors":"Namrata Gupta, Alok Naugarhiya","doi":"10.1109/ICEEICT53079.2022.9768535","DOIUrl":"https://doi.org/10.1109/ICEEICT53079.2022.9768535","url":null,"abstract":"This paper proposed a 1.4kV-class superjunction vertical IGBT (DMG-SJIGBT) with gate workfunction variation along with stepped oxide thickness. Two distinct workfunction materials, P+ and N+ polysilicon are used as gate poly and oxide thickness is varied in x-direction. All the stepped oxide is connected via metal on the top. The proposed structure's gate oxide is narrow at the emitter and wide at the collector to improve the device performance. It has been discovered that the ON-resistance (Ron.A) of the DMG-SJIGBT has been diminished by 23% as a result of this structural modification. Gate engineering improves the transconductivity by increasing the gate-emitter capacitance (CGE) and reducing the gate-collector capacitance (CGC), which lowers switching delay. To improve performance metrics, the gate length has been optimized. A mixed mode module of SILVACO has used to perform capacitance-voltage analysis. Further the gate charge and FOM has also been measured and indicating 36% and 34% respectively reduction for proposed device signifying enhanced performance.","PeriodicalId":201910,"journal":{"name":"2022 First International Conference on Electrical, Electronics, Information and Communication Technologies (ICEEICT)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133219601","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 : 2022-02-16DOI: 10.1109/ICEEICT53079.2022.9768565
Ayush Dalara, Dr. Sindhu C, R. Vasanth
Sculpture recognition is one of the most challenging problems in the image classification field due to the high variations in the design of various sculptures. In order to classify the Indian entity's sculpture, we require images from multiple perspectives with different orientations of the structure. This research conducts a comparative study by combining various algorithms for the purpose of sculpture recognition based on their features. The SIFT (Scale Invariant Feature Transform) algorithm was used to find descriptors for the key points detected and it was paired with various classifiers (K-Nearest Neighbors, Support Vector Machine, Artificial Neural Network) by using the “Min key”, “Max key padding”, “Mean key padding”, “Median key padding” and “Mode key padding” approach for efficiency testing purposes. CNNs (Convolutional Neural Networks) were also tested for the same. The models were trained on various representations of different Indian sculptures, gathered from various sources, signifying our cultural diversity. Experiments were carried out on the manually acquired data set that consists of 15 different sculpture classes, where each sculpture class consists of 150 images for training and 20 for testing. An attempt was also made to increase the efficiency of these models by the application of CLAHE (Contrast Limited Adaptive Histogram Equalization). The experiments showed the performance of these models when they were trained on various representations of sculpture images. For 15 different sculpture classes, the maximum accuracy achieved was a respectable 70.66% utilizing the CLAHE along with the CNN model. However, the accuracy values of non-CNN-based approaches were substandard.
{"title":"Entity Recognition in Indian Sculpture using CLAHE and machine learning","authors":"Ayush Dalara, Dr. Sindhu C, R. Vasanth","doi":"10.1109/ICEEICT53079.2022.9768565","DOIUrl":"https://doi.org/10.1109/ICEEICT53079.2022.9768565","url":null,"abstract":"Sculpture recognition is one of the most challenging problems in the image classification field due to the high variations in the design of various sculptures. In order to classify the Indian entity's sculpture, we require images from multiple perspectives with different orientations of the structure. This research conducts a comparative study by combining various algorithms for the purpose of sculpture recognition based on their features. The SIFT (Scale Invariant Feature Transform) algorithm was used to find descriptors for the key points detected and it was paired with various classifiers (K-Nearest Neighbors, Support Vector Machine, Artificial Neural Network) by using the “Min key”, “Max key padding”, “Mean key padding”, “Median key padding” and “Mode key padding” approach for efficiency testing purposes. CNNs (Convolutional Neural Networks) were also tested for the same. The models were trained on various representations of different Indian sculptures, gathered from various sources, signifying our cultural diversity. Experiments were carried out on the manually acquired data set that consists of 15 different sculpture classes, where each sculpture class consists of 150 images for training and 20 for testing. An attempt was also made to increase the efficiency of these models by the application of CLAHE (Contrast Limited Adaptive Histogram Equalization). The experiments showed the performance of these models when they were trained on various representations of sculpture images. For 15 different sculpture classes, the maximum accuracy achieved was a respectable 70.66% utilizing the CLAHE along with the CNN model. However, the accuracy values of non-CNN-based approaches were substandard.","PeriodicalId":201910,"journal":{"name":"2022 First International Conference on Electrical, Electronics, Information and Communication Technologies (ICEEICT)","volume":"96 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133396832","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 : 2022-02-16DOI: 10.1109/ICEEICT53079.2022.9768585
Ranjith Kumar Painam, M. Suchetha
In synthetic aperture radar (SAR) images, speckle noise is common, and SAR data is handled coherently. Multiplicative noise is another name for speckle. The purpose of this paper is to compare several approaches for reducing speckle noise. These techniques will be used to demonstrate trends and numerous different approaches that have evolved over the years. The technical aspects of the various adaptive spatial domain filters were discussed in this paper, and they were summarised for use in removing speckle noise from SAR images. ENL, SSI, and SSIM are the performance parameters that have been quantitatively and qualitatively analysed. It indicates that the adaptive filters with varied window sizes can be used to eliminate speckle and that noise suppression is more effective in SAR images. It may be enhanced to incorporate several machine learning techniques to optimise the result in order to improve various performance parameters. The experimental results show that the structural details are better preserved while speckle noise is suppressed.
{"title":"Comparative Performance Analysis of Spatial Domain Filters for Removing Speckle Noise in SAR images","authors":"Ranjith Kumar Painam, M. Suchetha","doi":"10.1109/ICEEICT53079.2022.9768585","DOIUrl":"https://doi.org/10.1109/ICEEICT53079.2022.9768585","url":null,"abstract":"In synthetic aperture radar (SAR) images, speckle noise is common, and SAR data is handled coherently. Multiplicative noise is another name for speckle. The purpose of this paper is to compare several approaches for reducing speckle noise. These techniques will be used to demonstrate trends and numerous different approaches that have evolved over the years. The technical aspects of the various adaptive spatial domain filters were discussed in this paper, and they were summarised for use in removing speckle noise from SAR images. ENL, SSI, and SSIM are the performance parameters that have been quantitatively and qualitatively analysed. It indicates that the adaptive filters with varied window sizes can be used to eliminate speckle and that noise suppression is more effective in SAR images. It may be enhanced to incorporate several machine learning techniques to optimise the result in order to improve various performance parameters. The experimental results show that the structural details are better preserved while speckle noise is suppressed.","PeriodicalId":201910,"journal":{"name":"2022 First International Conference on Electrical, Electronics, Information and Communication Technologies (ICEEICT)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133939918","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 : 2022-02-16DOI: 10.1109/ICEEICT53079.2022.9768415
N. A. Kumar, G. S. Satapathi, M. Anuradha
In this paper a novel technique on automated optical disk (OD) segmentation is proposed. The proposed OD algorithm depends on morphological based algorithm. This technique is assessed on openly accessible standard data sets DRIONS. The average accuracy rate of proposed segmented technique is 97.6% on DRIONS database. The proposed algorithm achieved Average Sensitivity, Average Specificity and Average Overlap of 93.1 %, 98.4% and 86.3% respectively on DRIONS data sets. Test results shows the algorithm is superior with comparable execution time over existing OD algorithms. Further, the algorithm has been implemented in System-on-chip (Zync-7000) kit.
{"title":"System-on-chip based Automated Optic Disk Segmentation in Retinal Images","authors":"N. A. Kumar, G. S. Satapathi, M. Anuradha","doi":"10.1109/ICEEICT53079.2022.9768415","DOIUrl":"https://doi.org/10.1109/ICEEICT53079.2022.9768415","url":null,"abstract":"In this paper a novel technique on automated optical disk (OD) segmentation is proposed. The proposed OD algorithm depends on morphological based algorithm. This technique is assessed on openly accessible standard data sets DRIONS. The average accuracy rate of proposed segmented technique is 97.6% on DRIONS database. The proposed algorithm achieved Average Sensitivity, Average Specificity and Average Overlap of 93.1 %, 98.4% and 86.3% respectively on DRIONS data sets. Test results shows the algorithm is superior with comparable execution time over existing OD algorithms. Further, the algorithm has been implemented in System-on-chip (Zync-7000) kit.","PeriodicalId":201910,"journal":{"name":"2022 First International Conference on Electrical, Electronics, Information and Communication Technologies (ICEEICT)","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124525250","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 : 2022-02-16DOI: 10.1109/ICEEICT53079.2022.9768599
J. Cornejo, Juan Palacios, Antonio Escobar, Yordan Torres
In the year 2020, countries were in a race against the spread of Covid-19, leading to major deficiencies in the areas of health, economy, and construction. For this reason, the robotics industry emerged as a viable and safe option to perform important and critical tasks in different sectors, one of them is the real estate. For this reason, a robotic arm was designed to wall painting, this study is supported by the mechatronics engineering department of the Universidad Tecnológica del Perú. The designed robot called: “UTP-ISR01” has 6 axes and a linear displacement of 2.8 m with turns of 0.24 sec/60°. For the calculation of the forward kinematics the Denavit Hartenberg method was used, then the homogeneous transformation matrices were used to calculate the rotation and translation movements of the robotic manipulator. With the equations identified in the inverse kinematics, the positions and orientations of the robot were plotted, as well as the dimensions of the working area. The CAD design was carried out with engineering software, such as Autodesk Inventor for the mechanical design and assembly of the parts. In addition, with RoboDK software, kinematic simulations and analysis were performed. In conclusion, the robotic arm will reduce the delivery times of the apartments built by the real estate companies.
2020年，各国竞相抗击新冠肺炎疫情，导致卫生、经济、建设等领域出现重大不足。出于这个原因，机器人行业成为在不同领域执行重要和关键任务的可行和安全的选择，其中之一就是房地产。为此，设计了一个机械臂来粉刷墙壁，这项研究得到了universsidad Tecnológica del Perú机电工程系的支持。所设计的机器人名为“UTP-ISR01”，有6个轴，线性位移为2.8 m，匝数为0.24秒/60°。采用Denavit Hartenberg法计算机器人的正运动学，然后采用齐次变换矩阵计算机器人的旋转和平移运动。通过在运动学逆解中确定的方程，绘制出机器人的位置和姿态，以及工作区域的尺寸。采用Autodesk Inventor等工程软件进行CAD设计，对零件进行机械设计和装配。此外，利用RoboDK软件进行了运动学仿真和分析。总之，机械臂将减少房地产公司建造公寓的交付时间。
{"title":"Mechatronics Design and Kinematic Simulation of UTP-ISR01 Robot with 6-DOF Anthropomorphic Configuration for Flexible Wall Painting","authors":"J. Cornejo, Juan Palacios, Antonio Escobar, Yordan Torres","doi":"10.1109/ICEEICT53079.2022.9768599","DOIUrl":"https://doi.org/10.1109/ICEEICT53079.2022.9768599","url":null,"abstract":"In the year 2020, countries were in a race against the spread of Covid-19, leading to major deficiencies in the areas of health, economy, and construction. For this reason, the robotics industry emerged as a viable and safe option to perform important and critical tasks in different sectors, one of them is the real estate. For this reason, a robotic arm was designed to wall painting, this study is supported by the mechatronics engineering department of the Universidad Tecnológica del Perú. The designed robot called: “UTP-ISR01” has 6 axes and a linear displacement of 2.8 m with turns of 0.24 sec/60°. For the calculation of the forward kinematics the Denavit Hartenberg method was used, then the homogeneous transformation matrices were used to calculate the rotation and translation movements of the robotic manipulator. With the equations identified in the inverse kinematics, the positions and orientations of the robot were plotted, as well as the dimensions of the working area. The CAD design was carried out with engineering software, such as Autodesk Inventor for the mechanical design and assembly of the parts. In addition, with RoboDK software, kinematic simulations and analysis were performed. In conclusion, the robotic arm will reduce the delivery times of the apartments built by the real estate companies.","PeriodicalId":201910,"journal":{"name":"2022 First International Conference on Electrical, Electronics, Information and Communication Technologies (ICEEICT)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127704083","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 : 2022-02-16DOI: 10.1109/ICEEICT53079.2022.9768434
K. Ramaabirami, G. Ram Sundar
The medical system is a developing innovation engine and spreads far more advanced, like humans care and offer a variety of choices for consumer health. Health is an important factor for human resource development which plays an important role in improving quality of the people. Because they are the active players in the economy development. Better prosperity will contribute to the improvement of economic situation of the poor and overall improvement of the country. When analysing the patient support system, every patient is only connected with their respective health care. During an emergency, it is impossible to identify a patient's history and leads to major loss in human lives. Thiswork focus on cloud computing to achieve an efficient maintenance of patient's history. This helps to save the life of a patient on time and can avoid the medical losses. This core medical system mainly focuses on effective maintenance of patient's history, timely assistance, reduces the medical expenditures, and minimizes data duplication and prescribing or reference. This medical care system is needed to improve the quality and quantity of the health care system. The proposed system will be more useful with the help of patient record through monitoring and evaluation system during emergency cases.
{"title":"An Enhanced and highly Authenticated Medical Treatment for an Emergency Management System using Cloud Computing","authors":"K. Ramaabirami, G. Ram Sundar","doi":"10.1109/ICEEICT53079.2022.9768434","DOIUrl":"https://doi.org/10.1109/ICEEICT53079.2022.9768434","url":null,"abstract":"The medical system is a developing innovation engine and spreads far more advanced, like humans care and offer a variety of choices for consumer health. Health is an important factor for human resource development which plays an important role in improving quality of the people. Because they are the active players in the economy development. Better prosperity will contribute to the improvement of economic situation of the poor and overall improvement of the country. When analysing the patient support system, every patient is only connected with their respective health care. During an emergency, it is impossible to identify a patient's history and leads to major loss in human lives. Thiswork focus on cloud computing to achieve an efficient maintenance of patient's history. This helps to save the life of a patient on time and can avoid the medical losses. This core medical system mainly focuses on effective maintenance of patient's history, timely assistance, reduces the medical expenditures, and minimizes data duplication and prescribing or reference. This medical care system is needed to improve the quality and quantity of the health care system. The proposed system will be more useful with the help of patient record through monitoring and evaluation system during emergency cases.","PeriodicalId":201910,"journal":{"name":"2022 First International Conference on Electrical, Electronics, Information and Communication Technologies (ICEEICT)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117127870","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 : 2022-02-16DOI: 10.1109/ICEEICT53079.2022.9768404
Ramprasath Selvaraj, K. Chittibabu, Muthumariyammal Anandharaj, Rameshbabu Perumal
This work presents a systematic and analytical investigation of non-isolated Hybrid Quadratic Boost Converter (HQBC) topology from the Reduced Redundant Power Processing (R2P2) converter family. The voltage conversion is performed by a single switch with a pair of inductor and capacitor. Due to the suggested HQBC quadratic behavior, significant voltage gain may be attained with a modest variation in duty cycle. The theoretical study of the converter's effective step-up voltage ratio and current stresses under continuous conduction mode, are emphasized. Steady state and dynamic modeling were used to examine the behavior of proposed converter. Steady state average equation was derived and a model was designed for 500 w and simulated in MATLAB/ Simulink. The Design and performance analysis of the suggested converter typologies is validated by simulation results.
{"title":"Modeling and Analysis of Hybrid Quadratic Boost Converter in MATLAB/Simulink Environment","authors":"Ramprasath Selvaraj, K. Chittibabu, Muthumariyammal Anandharaj, Rameshbabu Perumal","doi":"10.1109/ICEEICT53079.2022.9768404","DOIUrl":"https://doi.org/10.1109/ICEEICT53079.2022.9768404","url":null,"abstract":"This work presents a systematic and analytical investigation of non-isolated Hybrid Quadratic Boost Converter (HQBC) topology from the Reduced Redundant Power Processing (R2P2) converter family. The voltage conversion is performed by a single switch with a pair of inductor and capacitor. Due to the suggested HQBC quadratic behavior, significant voltage gain may be attained with a modest variation in duty cycle. The theoretical study of the converter's effective step-up voltage ratio and current stresses under continuous conduction mode, are emphasized. Steady state and dynamic modeling were used to examine the behavior of proposed converter. Steady state average equation was derived and a model was designed for 500 w and simulated in MATLAB/ Simulink. The Design and performance analysis of the suggested converter typologies is validated by simulation results.","PeriodicalId":201910,"journal":{"name":"2022 First International Conference on Electrical, Electronics, Information and Communication Technologies (ICEEICT)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114613180","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 : 2022-02-16DOI: 10.1109/ICEEICT53079.2022.9768465
Shushma Gb, I. Jacob
The speech emotion is a critical human communication, which unquestionably involves a high level of happiness or sadness communication between people contacts. The sentimental feeling varies in significant proportions among different languages across the other regions over the world. The recognition of emotional states is a reasonably new method in the field of machine learning and AI. The paper presents the study and the performance results of a system for emotion taxonomy. The emotion can be expressed in ways that can be seen, such as makeover terminologies. The analyses on the Autism spectrum disorder(ASD) recorded voice data set are converted into text data. However, in this research paper, we are interested in detecting emotions from the various textual dataset as well as using semantic data augmentation process to fill a few of the words, sentences, or half-broken words, as the Autism spectrum disorder (ASD) patients lack the social communication skills, as the patient does not very well articulate their communication.
{"title":"A Semantic Approach for Computing Speech Emotion Text Classification Using Machine Learning Algorithms","authors":"Shushma Gb, I. Jacob","doi":"10.1109/ICEEICT53079.2022.9768465","DOIUrl":"https://doi.org/10.1109/ICEEICT53079.2022.9768465","url":null,"abstract":"The speech emotion is a critical human communication, which unquestionably involves a high level of happiness or sadness communication between people contacts. The sentimental feeling varies in significant proportions among different languages across the other regions over the world. The recognition of emotional states is a reasonably new method in the field of machine learning and AI. The paper presents the study and the performance results of a system for emotion taxonomy. The emotion can be expressed in ways that can be seen, such as makeover terminologies. The analyses on the Autism spectrum disorder(ASD) recorded voice data set are converted into text data. However, in this research paper, we are interested in detecting emotions from the various textual dataset as well as using semantic data augmentation process to fill a few of the words, sentences, or half-broken words, as the Autism spectrum disorder (ASD) patients lack the social communication skills, as the patient does not very well articulate their communication.","PeriodicalId":201910,"journal":{"name":"2022 First International Conference on Electrical, Electronics, Information and Communication Technologies (ICEEICT)","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127161787","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 : 2022-02-16DOI: 10.1109/ICEEICT53079.2022.9768405
M. S. Eswari, S. Balamurali
Glaucoma is a group of diseases in which the nerve linking the eyes to the brain becomes destroyed, typically as a result of excessive intraocular pressure. The much more prevalent type of glaucoma diseases frequently manifests itself through gradual eyesight impairment. This kind of visual loss due to glaucoma is called open angle glaucoma and although this kind of angular glaucoma is uncommon, it is a clinical crisis with some indications such as eye pain and anxiety as well as acute vision disruption. In this paper, a new deep learning mechanism is used to identify the glaucoma disease in an intense manner, which is called Deep Neural Classification Network (DNCN). This proposed approach identifies the glaucoma disease efficiently by analyzing the retinal images with respect to two form factors such as Optical Coherence Tomography (OCT) and Retinal Fundus Images. The proposed DNCN model processes the retinal image based on the different processing procedures such as pre-processing, feature extraction, filtration and classification, in which it assures the accuracy ratio of 97.3% in outcome with the error rate of 0.27%.
{"title":"A Pragmatic Glaucoma Detection Based On Deep Neural Network Strategy","authors":"M. S. Eswari, S. Balamurali","doi":"10.1109/ICEEICT53079.2022.9768405","DOIUrl":"https://doi.org/10.1109/ICEEICT53079.2022.9768405","url":null,"abstract":"Glaucoma is a group of diseases in which the nerve linking the eyes to the brain becomes destroyed, typically as a result of excessive intraocular pressure. The much more prevalent type of glaucoma diseases frequently manifests itself through gradual eyesight impairment. This kind of visual loss due to glaucoma is called open angle glaucoma and although this kind of angular glaucoma is uncommon, it is a clinical crisis with some indications such as eye pain and anxiety as well as acute vision disruption. In this paper, a new deep learning mechanism is used to identify the glaucoma disease in an intense manner, which is called Deep Neural Classification Network (DNCN). This proposed approach identifies the glaucoma disease efficiently by analyzing the retinal images with respect to two form factors such as Optical Coherence Tomography (OCT) and Retinal Fundus Images. The proposed DNCN model processes the retinal image based on the different processing procedures such as pre-processing, feature extraction, filtration and classification, in which it assures the accuracy ratio of 97.3% in outcome with the error rate of 0.27%.","PeriodicalId":201910,"journal":{"name":"2022 First International Conference on Electrical, Electronics, Information and Communication Technologies (ICEEICT)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125426742","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：