Artificial Intelligence (AI) has emerged as a transformative technology across various industries, enabling advanced applications such as image recognition, natural language processing, and autonomous systems. A critical determinant of AI model performance is the quality and quantity of training data used during the model's development. However, acquiring and labeling large datasets for training can be resource-intensive, time-consuming, and privacy-sensitive. Synthetic data has emerged as a promising solution to address these challenges and enhance AI accuracy. This study explores the role of synthetic data in improving AI accuracy. Synthetic data refers to artificially generated data that mimics the distribution and characteristics of real-world data. By leveraging techniques from computer graphics, data augmentation, and generative modeling, researchers and practitioners can create diverse and representative synthetic datasets that supplement or replace traditional training data.
{"title":"Role of Synthetic Data for Improved AI Accuracy","authors":"None Ketha Dhana Veera Chaitanya, None Manas Kumar Yogi","doi":"10.36548/jaicn.2023.3.008","DOIUrl":"https://doi.org/10.36548/jaicn.2023.3.008","url":null,"abstract":"Artificial Intelligence (AI) has emerged as a transformative technology across various industries, enabling advanced applications such as image recognition, natural language processing, and autonomous systems. A critical determinant of AI model performance is the quality and quantity of training data used during the model's development. However, acquiring and labeling large datasets for training can be resource-intensive, time-consuming, and privacy-sensitive. Synthetic data has emerged as a promising solution to address these challenges and enhance AI accuracy. This study explores the role of synthetic data in improving AI accuracy. Synthetic data refers to artificially generated data that mimics the distribution and characteristics of real-world data. By leveraging techniques from computer graphics, data augmentation, and generative modeling, researchers and practitioners can create diverse and representative synthetic datasets that supplement or replace traditional training data.","PeriodicalId":500183,"journal":{"name":"Journal of Artificial Intelligence and Copsule Networks","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135737523","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 : 2023-09-01DOI: 10.36548/jaicn.2023.3.005
Alok Kumar, None N. Mahendran
In medical images, lesion segmentation is used to locate and isolate abnormal structures. It is an essential part of medical image analysis for precise diagnosis and care. However, obstacles exist in medical image lesion segmentation owing to things like image noise, shape and size fluctuation, and poor image quality. Automated lesion segmentation methods include conventional image processing techniques, deep learning (DL) models and machine learning (ML) algorithms to name a few. Thresholding, region growth, and active contour models are examples of conventional methods, while decision trees, random forests, and support vector machines are examples of ML techniques. DL models particularly convolutional neural networks (CNNs), have shown extraordinary performance in lesion segmentation because to their innate potential to autonomously collect high-level characteristics. The objective of the research is to study lesion segmentation in medical images and explore different methods for accurate and precise diagnosis and care.The research focuses on the obstacles faced in lesion segmentation in medical images, such as image noise, shape and size fluctuation, and poor image quality. The research also highlights the need for evaluation metrics, such as sensitivity, specificity, Dice coefficient, and Hausdorff distance, to assess the performance of lesion segmentation algorithms. Additionally, the research emphasizes the importance of annotated datasets for training and evaluating the performance of segmentation algorithms.
{"title":"Critical Studies on Lesion Segmentation in Medical Images","authors":"Alok Kumar, None N. Mahendran","doi":"10.36548/jaicn.2023.3.005","DOIUrl":"https://doi.org/10.36548/jaicn.2023.3.005","url":null,"abstract":"In medical images, lesion segmentation is used to locate and isolate abnormal structures. It is an essential part of medical image analysis for precise diagnosis and care. However, obstacles exist in medical image lesion segmentation owing to things like image noise, shape and size fluctuation, and poor image quality. Automated lesion segmentation methods include conventional image processing techniques, deep learning (DL) models and machine learning (ML) algorithms to name a few. Thresholding, region growth, and active contour models are examples of conventional methods, while decision trees, random forests, and support vector machines are examples of ML techniques. DL models particularly convolutional neural networks (CNNs), have shown extraordinary performance in lesion segmentation because to their innate potential to autonomously collect high-level characteristics. The objective of the research is to study lesion segmentation in medical images and explore different methods for accurate and precise diagnosis and care.The research focuses on the obstacles faced in lesion segmentation in medical images, such as image noise, shape and size fluctuation, and poor image quality. The research also highlights the need for evaluation metrics, such as sensitivity, specificity, Dice coefficient, and Hausdorff distance, to assess the performance of lesion segmentation algorithms. Additionally, the research emphasizes the importance of annotated datasets for training and evaluating the performance of segmentation algorithms.","PeriodicalId":500183,"journal":{"name":"Journal of Artificial Intelligence and Copsule Networks","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135433679","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 : 2023-09-01DOI: 10.36548/jaicn.2023.3.006
Sulav Shrestha, Sagar Panta
The Blockchain-based Electronic Health Record (B-EHR) system represents a significant advancement in healthcare data management. Concerns over data confidentiality and security have become increasingly critical in the healthcare sector, given the need for immediate data accessibility. Traditional centralized systems face accessibility issues, necessitating a transformative solution, and blockchain technology emerges as a promising candidate. This research introduces a patient-controlled, blockchain-based system that efficiently manages and safeguards individuals' health-related data. By harnessing the Ethereum network and utilizing tools such as Ganache, Solidity, and web3.js, this system takes a systematic approach to overcome the limitations of centralized systems. Smart contracts, the basis of blockchain technology, serve as the backbone for storing and processing patients' data in a decentralized manner. Transactions are conducted securely through these smart contracts, ensuring patient privacy and data security. Notably, any modifications to transactions can be verified and propagated across the entire distributed network, enhancing data integrity. Complementing this system is a cryptocurrency wallet like MetaMask, providing a centrally controlled repository where records can be swiftly accessed and secured by authorized individuals, including doctors and patients. This integration significantly improves data accessibility and security within the healthcare domain. Ultimately, this research aims to leverage blockchain technology for simultaneous data retrieval, enhancing efficiency, credibility, and accessibility. It offers a robust framework for securely storing data with tailored access permissions and facilitates the safe transfer of patient medical records. In essence, it introduces a swift and secure health record system and an innovative protocol, promoting greater transparency and ownership of sensitive data in the healthcare sector through blockchain integration.
{"title":"Blockchain-based Electronic Health Record Management System","authors":"Sulav Shrestha, Sagar Panta","doi":"10.36548/jaicn.2023.3.006","DOIUrl":"https://doi.org/10.36548/jaicn.2023.3.006","url":null,"abstract":"The Blockchain-based Electronic Health Record (B-EHR) system represents a significant advancement in healthcare data management. Concerns over data confidentiality and security have become increasingly critical in the healthcare sector, given the need for immediate data accessibility. Traditional centralized systems face accessibility issues, necessitating a transformative solution, and blockchain technology emerges as a promising candidate. This research introduces a patient-controlled, blockchain-based system that efficiently manages and safeguards individuals' health-related data. By harnessing the Ethereum network and utilizing tools such as Ganache, Solidity, and web3.js, this system takes a systematic approach to overcome the limitations of centralized systems. Smart contracts, the basis of blockchain technology, serve as the backbone for storing and processing patients' data in a decentralized manner. Transactions are conducted securely through these smart contracts, ensuring patient privacy and data security. Notably, any modifications to transactions can be verified and propagated across the entire distributed network, enhancing data integrity. Complementing this system is a cryptocurrency wallet like MetaMask, providing a centrally controlled repository where records can be swiftly accessed and secured by authorized individuals, including doctors and patients. This integration significantly improves data accessibility and security within the healthcare domain. Ultimately, this research aims to leverage blockchain technology for simultaneous data retrieval, enhancing efficiency, credibility, and accessibility. It offers a robust framework for securely storing data with tailored access permissions and facilitates the safe transfer of patient medical records. In essence, it introduces a swift and secure health record system and an innovative protocol, promoting greater transparency and ownership of sensitive data in the healthcare sector through blockchain integration.","PeriodicalId":500183,"journal":{"name":"Journal of Artificial Intelligence and Copsule Networks","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135686484","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 : 2023-09-01DOI: 10.36548/jaicn.2023.3.007
None Rahul Kumar Jha
This study delves into the intricate relationship between power plant attributes and electricity generation, employing data analysis and predictive modelling techniques. Through a comprehensive analysis of a global power plant dataset, critical factors such as plant capacity and commissioning year were identified as significant influencers on electricity generation. The research utilized correlation heatmaps to visually represent these relationships, offering valuable insights for policymakers and investors. A linear regression model was employed, leveraging capacity and commissioning year as features to predict electricity generation. The model's accuracy was evaluated using mean squared error, providing a quantitative measure of its predictive capabilities.
{"title":"Sustainable Energy Transition: Analyzing the Impact of Renewable Energy Sources on Global Power Generation","authors":"None Rahul Kumar Jha","doi":"10.36548/jaicn.2023.3.007","DOIUrl":"https://doi.org/10.36548/jaicn.2023.3.007","url":null,"abstract":"This study delves into the intricate relationship between power plant attributes and electricity generation, employing data analysis and predictive modelling techniques. Through a comprehensive analysis of a global power plant dataset, critical factors such as plant capacity and commissioning year were identified as significant influencers on electricity generation. The research utilized correlation heatmaps to visually represent these relationships, offering valuable insights for policymakers and investors. A linear regression model was employed, leveraging capacity and commissioning year as features to predict electricity generation. The model's accuracy was evaluated using mean squared error, providing a quantitative measure of its predictive capabilities.","PeriodicalId":500183,"journal":{"name":"Journal of Artificial Intelligence and Copsule Networks","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135736511","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}
Bacteria play a significant role in our environment by being helpful or harmful; hence, it is crucial to identify the various bacterial species. The microscopic image captured by camera with microscope is not reliable due to the poor quality of image, making bacterial counting a difficult and time-consuming task. This paper proposes improved and enhanced Multi-Scale Retinex with Chromacity Preservation and Otsu Thresholding techniques for increasing the quality of images of bacterial cells for segmentation and contrast enhancement. A combinative procedure of image enhancement and segmentation is illustrated in this paper. The parameters for Image Quality Assessment (IQA) used are Enhancement Measure Estimation and Standard Deviation of the upgraded images. The proposed approach gives better segmentation results, as proven by the incremental changes in the IQA parameters.
{"title":"Segmentation of Microscopy images using Multi-Scale Retinex with Chromacity Preservation and Otsu Thresholding","authors":"Ajay Yadav, Abhijeet Singh, Adarsh Singh, Anupam Yadav, Sashank Singh","doi":"10.36548//jaicn.2023.1.002","DOIUrl":"https://doi.org/10.36548//jaicn.2023.1.002","url":null,"abstract":"Bacteria play a significant role in our environment by being helpful or harmful; hence, it is crucial to identify the various bacterial species. The microscopic image captured by camera with microscope is not reliable due to the poor quality of image, making bacterial counting a difficult and time-consuming task. This paper proposes improved and enhanced Multi-Scale Retinex with Chromacity Preservation and Otsu Thresholding techniques for increasing the quality of images of bacterial cells for segmentation and contrast enhancement. A combinative procedure of image enhancement and segmentation is illustrated in this paper. The parameters for Image Quality Assessment (IQA) used are Enhancement Measure Estimation and Standard Deviation of the upgraded images. The proposed approach gives better segmentation results, as proven by the incremental changes in the IQA parameters.","PeriodicalId":500183,"journal":{"name":"Journal of Artificial Intelligence and Copsule Networks","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135079960","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：