Pub Date : 2023-02-01DOI: 10.1109/AICAPS57044.2023.10074229
Priya Thiagarajan, S. M
Background: Timely diagnosis of papilledema is essential to avoid vision loss and progress of life threatening conditions. Expert ophthalmologists or neurologists are not available in Emergency departments and in rural healthcare centers for timely detection. An intelligent, non-invasive detection system to aid healthcare professionals to detect papilledema and triage neurological patients is essential for early diagnosis for saving vision & even livesMethodology: Retinal fundus images are used to identify papilledema. After suitable preprocessing of the data, trained Convolutional Neural Networks can be used to classify the images to detect papilledema. Our proposed model uses EfficientNet-B3 to accurately and efficiently detect papilledema using an image dataset.Results: Accuracy of 98.54% is achieved with the EfficientNet-B3 model. Other performance metrics are also significantly higher than existing literature.Conclusion: The Intelligent Papilledema Detector will be very helpful in emergency departments and rural healthcare centers to aid with early detection of papilledema. The results obtained are very encouraging, though training with more data from various sources will help improve the practical usability of the system. Emerging trends of using smartphones with a lens assembly to capture also can be taken up as further work.
{"title":"Intelligent Papilledema Detector (IPD)","authors":"Priya Thiagarajan, S. M","doi":"10.1109/AICAPS57044.2023.10074229","DOIUrl":"https://doi.org/10.1109/AICAPS57044.2023.10074229","url":null,"abstract":"Background: Timely diagnosis of papilledema is essential to avoid vision loss and progress of life threatening conditions. Expert ophthalmologists or neurologists are not available in Emergency departments and in rural healthcare centers for timely detection. An intelligent, non-invasive detection system to aid healthcare professionals to detect papilledema and triage neurological patients is essential for early diagnosis for saving vision & even livesMethodology: Retinal fundus images are used to identify papilledema. After suitable preprocessing of the data, trained Convolutional Neural Networks can be used to classify the images to detect papilledema. Our proposed model uses EfficientNet-B3 to accurately and efficiently detect papilledema using an image dataset.Results: Accuracy of 98.54% is achieved with the EfficientNet-B3 model. Other performance metrics are also significantly higher than existing literature.Conclusion: The Intelligent Papilledema Detector will be very helpful in emergency departments and rural healthcare centers to aid with early detection of papilledema. The results obtained are very encouraging, though training with more data from various sources will help improve the practical usability of the system. Emerging trends of using smartphones with a lens assembly to capture also can be taken up as further work.","PeriodicalId":146698,"journal":{"name":"2023 International Conference on Advances in Intelligent Computing and Applications (AICAPS)","volume":"114 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128121967","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 : 2023-02-01DOI: 10.1109/AICAPS57044.2023.10074484
Ujjwal Kumar, A. J, Chandrika K R
In the era of Automation, there has to be a way to improvise online assessment. This paper has demonstrated a methodology to enhance the online assessment with the help of an Eye Tracker. That has the ability to categorize the behavior of the participant with the state of the art proposed within the paper. Compared with the traditional assessment, here with the help of this model, an automated feedback sentence is returned along with the score. This adds an advantage to the assessor for fair score awarding. The model has utilized an open-source eye tracker tool to capture eye movements during the assessment. Thereafter a customized classification model is used to provide the relevant keywords, out of which the sentence will be generated using a Deep Learning model.
{"title":"Automatic feedback captions for eye-tracker based online assessment","authors":"Ujjwal Kumar, A. J, Chandrika K R","doi":"10.1109/AICAPS57044.2023.10074484","DOIUrl":"https://doi.org/10.1109/AICAPS57044.2023.10074484","url":null,"abstract":"In the era of Automation, there has to be a way to improvise online assessment. This paper has demonstrated a methodology to enhance the online assessment with the help of an Eye Tracker. That has the ability to categorize the behavior of the participant with the state of the art proposed within the paper. Compared with the traditional assessment, here with the help of this model, an automated feedback sentence is returned along with the score. This adds an advantage to the assessor for fair score awarding. The model has utilized an open-source eye tracker tool to capture eye movements during the assessment. Thereafter a customized classification model is used to provide the relevant keywords, out of which the sentence will be generated using a Deep Learning model.","PeriodicalId":146698,"journal":{"name":"2023 International Conference on Advances in Intelligent Computing and Applications (AICAPS)","volume":"196 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131880630","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 : 2023-02-01DOI: 10.1109/AICAPS57044.2023.10074161
S. Shilaskar, S. Bhatlawande, Shivpriya Deshmukh, Harshal Dhande
Autism spectrum disorder (ASD) and dyslexia are expanding more swiftly than ever nowadays. Finding the characteristics of dyslexia and autism through screening tests is costly and time-consuming. Thanks to breakthroughs in artificial intelligence, computers, and machine learning, autism and dyslexia may be predicted at a very young age (ML). Even though several studies have been carried out using quite a few different approaches, none of them has shown a clear justification for how to predict autism and dyslexia traits across age groups. This study attempts to build a suitable prediction model enabled by ML technology to predict ASD and dyslexia for people of any age. This work seeks to examine the possible use of Random Forest, SVM with linear kernel, SVM with polynomial kernel, SVM with rbf kernel, SVM with sigmoid kernel, XGBoost, Decision Tree, Logistic Regression, Naïve Bayes, and KNN to forecast and assess ASD and dyslexia difficulties in children, adolescents and adults. Using real data set collected from individuals with and without autistic traits, the proposed model and the AQ-10 screening tool were assessed. The data for dyslexia is made up of 3644 cases with 197 properties, 196 of which are independent variables and one is a dependent variable. The data for autism consists of 704 cases with 22 characteristics, 21 independent variables, and 1 dependent variable with binary values (YES or NO). The results of the research showed that, in terms of accuracy, precision, F1 score, and recall, the recommended prediction model gave better results for the data set.
{"title":"Prediction of Autism and Dyslexia Using Machine Learning and Clinical Data Balancing","authors":"S. Shilaskar, S. Bhatlawande, Shivpriya Deshmukh, Harshal Dhande","doi":"10.1109/AICAPS57044.2023.10074161","DOIUrl":"https://doi.org/10.1109/AICAPS57044.2023.10074161","url":null,"abstract":"Autism spectrum disorder (ASD) and dyslexia are expanding more swiftly than ever nowadays. Finding the characteristics of dyslexia and autism through screening tests is costly and time-consuming. Thanks to breakthroughs in artificial intelligence, computers, and machine learning, autism and dyslexia may be predicted at a very young age (ML). Even though several studies have been carried out using quite a few different approaches, none of them has shown a clear justification for how to predict autism and dyslexia traits across age groups. This study attempts to build a suitable prediction model enabled by ML technology to predict ASD and dyslexia for people of any age. This work seeks to examine the possible use of Random Forest, SVM with linear kernel, SVM with polynomial kernel, SVM with rbf kernel, SVM with sigmoid kernel, XGBoost, Decision Tree, Logistic Regression, Naïve Bayes, and KNN to forecast and assess ASD and dyslexia difficulties in children, adolescents and adults. Using real data set collected from individuals with and without autistic traits, the proposed model and the AQ-10 screening tool were assessed. The data for dyslexia is made up of 3644 cases with 197 properties, 196 of which are independent variables and one is a dependent variable. The data for autism consists of 704 cases with 22 characteristics, 21 independent variables, and 1 dependent variable with binary values (YES or NO). The results of the research showed that, in terms of accuracy, precision, F1 score, and recall, the recommended prediction model gave better results for the data set.","PeriodicalId":146698,"journal":{"name":"2023 International Conference on Advances in Intelligent Computing and Applications (AICAPS)","volume":"152 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133684969","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 : 2023-02-01DOI: 10.1109/AICAPS57044.2023.10074214
K. Banumathi, G. Sudhasadasivam, B. Banurekha, N. Shahana, K. Vaishnavi
Dyslexia is a learning disorder characterized with a difficulty in learning due to impairment of the left hemisphere of the brain associated with processing. In India, the incidence of dyslexia is believed to be around 15%. Literacy is the foundation of all learning and hence, identifying dyslexia at an early age is critical. The appropriate age to identify dyslexia is between 5 and 8 years since early detection can nurture corrective measures. Identifying dyslexia at this age will also prevent future school drop outs. The major challenge in detecting dyslexia among children at an early age includes lack of awareness among school teachers and parents. The absence of simple standardized screening and assessment tools in regional languages makes the task more difficult. A Smartphone application to screen dyslexia offers the advantages of universal use and standardization. However, primary school educators feel the need to have screening apps in regional languages (like Tamil), as most of the communication in local population is using regional language. In this research work, a Smartphone based screening application for dyslexia is developed in Tamil. The app consists of questions that cover the areas of general qualities, health & personality, unique talents, speech & hearing skills, visual acuity& reading skills, writing & motor skills, mathematical ability and memory & cognitive skills. The app was created utilizing the expertise of special educators and following regional practices. The app generates visualizations and provides scoring on the severity level of dyslexia for the user. The report can be downloaded and printed. Then the dataset is subjected to training with five different machine learning algorithms and results are compared by their report of classification and error rates.
{"title":"AI Powered Screening Aid for Dyslexic Children in Tamil","authors":"K. Banumathi, G. Sudhasadasivam, B. Banurekha, N. Shahana, K. Vaishnavi","doi":"10.1109/AICAPS57044.2023.10074214","DOIUrl":"https://doi.org/10.1109/AICAPS57044.2023.10074214","url":null,"abstract":"Dyslexia is a learning disorder characterized with a difficulty in learning due to impairment of the left hemisphere of the brain associated with processing. In India, the incidence of dyslexia is believed to be around 15%. Literacy is the foundation of all learning and hence, identifying dyslexia at an early age is critical. The appropriate age to identify dyslexia is between 5 and 8 years since early detection can nurture corrective measures. Identifying dyslexia at this age will also prevent future school drop outs. The major challenge in detecting dyslexia among children at an early age includes lack of awareness among school teachers and parents. The absence of simple standardized screening and assessment tools in regional languages makes the task more difficult. A Smartphone application to screen dyslexia offers the advantages of universal use and standardization. However, primary school educators feel the need to have screening apps in regional languages (like Tamil), as most of the communication in local population is using regional language. In this research work, a Smartphone based screening application for dyslexia is developed in Tamil. The app consists of questions that cover the areas of general qualities, health & personality, unique talents, speech & hearing skills, visual acuity& reading skills, writing & motor skills, mathematical ability and memory & cognitive skills. The app was created utilizing the expertise of special educators and following regional practices. The app generates visualizations and provides scoring on the severity level of dyslexia for the user. The report can be downloaded and printed. Then the dataset is subjected to training with five different machine learning algorithms and results are compared by their report of classification and error rates.","PeriodicalId":146698,"journal":{"name":"2023 International Conference on Advances in Intelligent Computing and Applications (AICAPS)","volume":"119 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122471483","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 : 2023-02-01DOI: 10.1109/AICAPS57044.2023.10074490
Narendra Kumar Chahar, Krishan Pal Singh, M. Hussain
In recent years, the emergence of the Internet and E-commerce has steered significant growth in digital transactions. Businesses today need mobile wallets, credit and debit cards, and e-cash to digitize payments. Digital payment systems are in transition and promise amazing advancements, but they also pose many risks and as the number of online transactions is increasing tremendously, we need a security system that follows all security norms. In this paper, we study digital transaction systems and evaluate various components of E-commerce plat-forms to address the security of these services. We evaluate the attributes that affect the security of digital payment processes and identify several barriers that hinder their performance to propose a simplified payment mechanism for micro-payments that eliminates the double payment problem.
{"title":"Simplified Micropayment Mechanism to Eliminate the Risk of Double Payment in E-Commerce","authors":"Narendra Kumar Chahar, Krishan Pal Singh, M. Hussain","doi":"10.1109/AICAPS57044.2023.10074490","DOIUrl":"https://doi.org/10.1109/AICAPS57044.2023.10074490","url":null,"abstract":"In recent years, the emergence of the Internet and E-commerce has steered significant growth in digital transactions. Businesses today need mobile wallets, credit and debit cards, and e-cash to digitize payments. Digital payment systems are in transition and promise amazing advancements, but they also pose many risks and as the number of online transactions is increasing tremendously, we need a security system that follows all security norms. In this paper, we study digital transaction systems and evaluate various components of E-commerce plat-forms to address the security of these services. We evaluate the attributes that affect the security of digital payment processes and identify several barriers that hinder their performance to propose a simplified payment mechanism for micro-payments that eliminates the double payment problem.","PeriodicalId":146698,"journal":{"name":"2023 International Conference on Advances in Intelligent Computing and Applications (AICAPS)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121446423","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 : 2023-02-01DOI: 10.1109/AICAPS57044.2023.10074544
K. N. Rajanikanth, Mohammed Rehab Sait, Sumukh R Kashi
The pandemic situation (Covid 19) brought new challenges in the education sector while simultaneously presenting unique opportunities for technology enabled services. The use of Mobile Robotic Telepresence systems in educational sector is promising as it provides means to significantly enhance the involvement and benefits to stakeholders involved in such interactions. An immersive user interaction with such a system depends on many aspects which are both static and dynamic. We approach the dynamic aspect of such interactions recognizing that the video and audio aspects of such a system will require fine tuning and adaptation. Closely related is the aspect of maintaining the necessary quality of network connection. Considering each of these aspects a reinforcement learning mechanism is incorporated to improve the overall user experience with such a system. A working system is built and experiments performed to demonstrate the effectiveness of the approach. Reward generation matrix, a crucial piece of data gathering from the environment, takes about 45 minutes, offline training time is less than a second, while the robot is able to cover the workspace in slightly less than a minute. The system is not limited to educational sector alone and provides a foundational framework to extend the concepts and principles to adjacent markets.
{"title":"Enhancing Immersive User Experience Quality of StudoBot Telepresence Robots with Reinforcement Learning","authors":"K. N. Rajanikanth, Mohammed Rehab Sait, Sumukh R Kashi","doi":"10.1109/AICAPS57044.2023.10074544","DOIUrl":"https://doi.org/10.1109/AICAPS57044.2023.10074544","url":null,"abstract":"The pandemic situation (Covid 19) brought new challenges in the education sector while simultaneously presenting unique opportunities for technology enabled services. The use of Mobile Robotic Telepresence systems in educational sector is promising as it provides means to significantly enhance the involvement and benefits to stakeholders involved in such interactions. An immersive user interaction with such a system depends on many aspects which are both static and dynamic. We approach the dynamic aspect of such interactions recognizing that the video and audio aspects of such a system will require fine tuning and adaptation. Closely related is the aspect of maintaining the necessary quality of network connection. Considering each of these aspects a reinforcement learning mechanism is incorporated to improve the overall user experience with such a system. A working system is built and experiments performed to demonstrate the effectiveness of the approach. Reward generation matrix, a crucial piece of data gathering from the environment, takes about 45 minutes, offline training time is less than a second, while the robot is able to cover the workspace in slightly less than a minute. The system is not limited to educational sector alone and provides a foundational framework to extend the concepts and principles to adjacent markets.","PeriodicalId":146698,"journal":{"name":"2023 International Conference on Advances in Intelligent Computing and Applications (AICAPS)","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122021019","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 : 2023-02-01DOI: 10.1109/AICAPS57044.2023.10074051
P. Ghadekar, Dhruva Khanwelkar, Nirvisha Soni, Harsh More, Juhi Rajani, Chirag Vaswani
In recent years, several supervised deep-learning architectures have achieved state-of-the art accuracies in video-classification. However, they demand a considerable amount of annotated data which can be both cost and resource intensive. This study proposes a Semi-Supervised GAN architecture to efficiently perform classification on video datasets with a small percentage of labelled data. While the Generative Adversarial Network (GAN) architecture is known for its generative ability, we harness the discriminative property of this network instead for the classification of videos. The proposed model leverages the features extracted from the unlabelled data to classify the labelled videos. Results show that the proposed approach achieves 46% accuracy with just 5% labelled videos, reaching up to 62% when 50% of the videos are labelled. These results are a significant improvement over a standard supervised approach and show a promising aspect in the field of Semi-Supervised Learning domain.
{"title":"A Semi-Supervised GAN Architecture for Video Classification","authors":"P. Ghadekar, Dhruva Khanwelkar, Nirvisha Soni, Harsh More, Juhi Rajani, Chirag Vaswani","doi":"10.1109/AICAPS57044.2023.10074051","DOIUrl":"https://doi.org/10.1109/AICAPS57044.2023.10074051","url":null,"abstract":"In recent years, several supervised deep-learning architectures have achieved state-of-the art accuracies in video-classification. However, they demand a considerable amount of annotated data which can be both cost and resource intensive. This study proposes a Semi-Supervised GAN architecture to efficiently perform classification on video datasets with a small percentage of labelled data. While the Generative Adversarial Network (GAN) architecture is known for its generative ability, we harness the discriminative property of this network instead for the classification of videos. The proposed model leverages the features extracted from the unlabelled data to classify the labelled videos. Results show that the proposed approach achieves 46% accuracy with just 5% labelled videos, reaching up to 62% when 50% of the videos are labelled. These results are a significant improvement over a standard supervised approach and show a promising aspect in the field of Semi-Supervised Learning domain.","PeriodicalId":146698,"journal":{"name":"2023 International Conference on Advances in Intelligent Computing and Applications (AICAPS)","volume":"117 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116198640","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 : 2023-02-01DOI: 10.1109/AICAPS57044.2023.10074158
Sharini D L, Ravilla Dilli, K. M
The rapid growth of extreme data traffic and over occupied networks are the current challenges in the wireless communication networks. However, next generation networks tackle them by utilizing vast frequency bands. These are FR2/FR1 frequency bands that play an important role in next-generation technologies, namely B5G or 6G. mmWave being one of those technologies, also utilize such frequency bands. Nevertheless, massive antennas and propagation characteristics of the channel model describes its behavior and some crucial aspects that need to be considered when operating on FR2 frequency bands for 5G NR networks. This paper analyzes the behavior of a mmWave massive MIMO channel at FR1 and FR2 frequency bands under for specific atmospheric conditions. The channel behavior was simulated using NYUSIM software and the performance metrics include path loss, received power, and path loss exponent of the channel power delay profile.
{"title":"Statistical Modelling of Massive MIMO Channel at FR2 Frequency Bands for B5G Networks","authors":"Sharini D L, Ravilla Dilli, K. M","doi":"10.1109/AICAPS57044.2023.10074158","DOIUrl":"https://doi.org/10.1109/AICAPS57044.2023.10074158","url":null,"abstract":"The rapid growth of extreme data traffic and over occupied networks are the current challenges in the wireless communication networks. However, next generation networks tackle them by utilizing vast frequency bands. These are FR2/FR1 frequency bands that play an important role in next-generation technologies, namely B5G or 6G. mmWave being one of those technologies, also utilize such frequency bands. Nevertheless, massive antennas and propagation characteristics of the channel model describes its behavior and some crucial aspects that need to be considered when operating on FR2 frequency bands for 5G NR networks. This paper analyzes the behavior of a mmWave massive MIMO channel at FR1 and FR2 frequency bands under for specific atmospheric conditions. The channel behavior was simulated using NYUSIM software and the performance metrics include path loss, received power, and path loss exponent of the channel power delay profile.","PeriodicalId":146698,"journal":{"name":"2023 International Conference on Advances in Intelligent Computing and Applications (AICAPS)","volume":"403 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126698195","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 : 2023-02-01DOI: 10.1109/AICAPS57044.2023.10074562
Sabitha Rani B. S, M. G., E. Sherly
kidney stones scientifically known as renal calculus or nephrolith consist of dense crystal masses generally originate in the kidneys and pass through the urinary tract which includes urethra, bladder and ureters. Genetic, dietary and environmental causes can be associated with the occurrence and severity of kidney stones. Imaging studies play a vital part in the treatment of kidney stone patients. CT is a precise diagnostic procedure for gastrointestinal illnesses. In essence, CT sends x-rays in small pieces that are saved on the screen as photographs from the body. The proposed method involves the diagnosis of kidney stones using image processing techniques such as pre-processing,segmentation,feature extraction and classification etc. In the initial stage the salt and pepper noise is removed by using a 3x3 median filter and discrete wavelet transform (DWT).K-Means clustering algorithm is used after segmenting the kidney stones using the watershed segmentation algorithm. The key objective of this study is to extract the features of segmented kidney stones by using the Grey level co-occurrence matrix(GLCM) and classify it using Probabilistic Neural Network (PNN) .The results we got indicate that 194 and 107 as the maximum sensitivity and maximum specificity point which was higher than the conventional renal calculus detection approaches.Also our proposed framework achieves an overall accuracy of 86.8%.
{"title":"Kidney Stone Detection from CT images using Probabilistic Neural Network(PNN) and Watershed Algorithm","authors":"Sabitha Rani B. S, M. G., E. Sherly","doi":"10.1109/AICAPS57044.2023.10074562","DOIUrl":"https://doi.org/10.1109/AICAPS57044.2023.10074562","url":null,"abstract":"kidney stones scientifically known as renal calculus or nephrolith consist of dense crystal masses generally originate in the kidneys and pass through the urinary tract which includes urethra, bladder and ureters. Genetic, dietary and environmental causes can be associated with the occurrence and severity of kidney stones. Imaging studies play a vital part in the treatment of kidney stone patients. CT is a precise diagnostic procedure for gastrointestinal illnesses. In essence, CT sends x-rays in small pieces that are saved on the screen as photographs from the body. The proposed method involves the diagnosis of kidney stones using image processing techniques such as pre-processing,segmentation,feature extraction and classification etc. In the initial stage the salt and pepper noise is removed by using a 3x3 median filter and discrete wavelet transform (DWT).K-Means clustering algorithm is used after segmenting the kidney stones using the watershed segmentation algorithm. The key objective of this study is to extract the features of segmented kidney stones by using the Grey level co-occurrence matrix(GLCM) and classify it using Probabilistic Neural Network (PNN) .The results we got indicate that 194 and 107 as the maximum sensitivity and maximum specificity point which was higher than the conventional renal calculus detection approaches.Also our proposed framework achieves an overall accuracy of 86.8%.","PeriodicalId":146698,"journal":{"name":"2023 International Conference on Advances in Intelligent Computing and Applications (AICAPS)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133301383","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 : 2023-02-01DOI: 10.1109/AICAPS57044.2023.10074582
Satyajit Ghosh, Rakibul Islam, A. Jaman, Aratrika Bose, Abhishek Roy
Finding a suitable employment position is a crucial and difficult task. Nowadays, Job seekers may instantly apply for multiple job openings using job search platforms. Personal information has to be exchanged as part of every job application. Sharing personal information across unsafe channels, however, increases the risk of data theft. Apart from that, attempts to tamper with hiring data are unfortunately common. Previously, traditional databases were only used for job search platforms, which do not provide sufficient transparency or protection against tampering. The incorporation of blockchain technology in job search portals can address these issues and provide a more transparent and secure process. Our proposed solution uses Hyperledger Fabric (HLF), an open-source blockchain frame-work, to create a secure and transparent job search platform. In this platform, both recruiters and job seekers can participate in a permissioned network, where smart contracts are used to ensure a transparent and privacy-friendly hiring process. To demonstrate the feasibility of this solution, we have implemented and deployed a prototype using Amazon Managed Blockchain Service. To understand the optimal configuration for our system, we tested the performance of our network using the Hyperledger Caliper tool. Although further research is necessary to fully understand the capabilities and limitations of using blockchain technology in job search portals.
{"title":"ChainHire: A Privacy-Preserving and Transparent Job Search Portal Using an Enterprise-Level Permissioned Blockchain Framework","authors":"Satyajit Ghosh, Rakibul Islam, A. Jaman, Aratrika Bose, Abhishek Roy","doi":"10.1109/AICAPS57044.2023.10074582","DOIUrl":"https://doi.org/10.1109/AICAPS57044.2023.10074582","url":null,"abstract":"Finding a suitable employment position is a crucial and difficult task. Nowadays, Job seekers may instantly apply for multiple job openings using job search platforms. Personal information has to be exchanged as part of every job application. Sharing personal information across unsafe channels, however, increases the risk of data theft. Apart from that, attempts to tamper with hiring data are unfortunately common. Previously, traditional databases were only used for job search platforms, which do not provide sufficient transparency or protection against tampering. The incorporation of blockchain technology in job search portals can address these issues and provide a more transparent and secure process. Our proposed solution uses Hyperledger Fabric (HLF), an open-source blockchain frame-work, to create a secure and transparent job search platform. In this platform, both recruiters and job seekers can participate in a permissioned network, where smart contracts are used to ensure a transparent and privacy-friendly hiring process. To demonstrate the feasibility of this solution, we have implemented and deployed a prototype using Amazon Managed Blockchain Service. To understand the optimal configuration for our system, we tested the performance of our network using the Hyperledger Caliper tool. Although further research is necessary to fully understand the capabilities and limitations of using blockchain technology in job search portals.","PeriodicalId":146698,"journal":{"name":"2023 International Conference on Advances in Intelligent Computing and Applications (AICAPS)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130062128","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：