2023 International Conference on Advances in Computing, Communication and Applied Informatics (ACCAI)最新文献

{"title":"Intelligent Farmhouse Attendance Monitoring System Using Deep Learning","authors":"Dr. J. R. Jeba, S.Tephillah","doi":"10.1109/ACCAI58221.2023.10200346","DOIUrl":"https://doi.org/10.1109/ACCAI58221.2023.10200346","url":null,"abstract":"In large farmhouses, attendance is recorded by the supervisor and the record is maintained manually. It results in an increase in time and manpower. It also suffers from human error, and there may be the possibility of missing paper before reaching the owner of the farm for future reference. Deep learning is one of the most popular and emerging technologies in the digital world today. It has become extraordinary in recent years owing to its many applications. In this proposed work, the face recognition technique is used to design a prototype that handles attendance records automatically without any human intervention. To track the workers' attendance in this project, an intelligent attendance tracking system is created by identifying their facial features using efficient algorithms. It also sends the message automatically to the owner of the farmhouse and mails the report to the officers involved in the administration of the farmhouse. In addition to these features, it is also designed with live monitoring facilities. Also the simulation results prove an increase of 1% to 5% in accuracy of identification with different data sets. This low-cost, robust, and portable technology is also very effective and steady, saving the owners' valuable time.","PeriodicalId":382104,"journal":{"name":"2023 International Conference on Advances in Computing, Communication and Applied Informatics (ACCAI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130977944","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}

{"title":"Accuracy Improvement of Flooded Area Detection from Satellite Images using Novel K-Nearest Neighbors in Comparison with Support Vector Machine","authors":"C. Vamsi, V. Amudha, S. R","doi":"10.1109/ACCAI58221.2023.10199536","DOIUrl":"https://doi.org/10.1109/ACCAI58221.2023.10199536","url":null,"abstract":"In this study, we examine the outcomes of employing Novel K-nearest Neighbors and Support Vector Machines to assess the accuracy of recognizing flooded areas. The data set that was used in this inquiry had a total of 118 samples. These samples were divided into two sets: a training set that contained 70 samples, and a testing set that contained 48 samples. An alpha value of 0.05 and a G power of 80% were used in the calculation to determine the total number of samples that were necessary for the investigation. The accuracy of the new K-nearest neighbor algorithm is 80.26 percent, whereas the accuracy of the support vector machine is 75.48%, with a significance of 0.000078 (p<0.05). The newly created K-nearest neighbor algorithm performs much better than the Support vector machine when it comes to the task of finding areas that have been flooded.","PeriodicalId":382104,"journal":{"name":"2023 International Conference on Advances in Computing, Communication and Applied Informatics (ACCAI)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126840715","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}

{"title":"A Novel Deep Learning Approach to Detect Manufacturing Defects over Textile Fabric Materials","authors":"T. D. Subha, Pavaiyarkarasi Pavaiyarkarasi, S. Vijayalakshmi, Dommaraju Nikhil Varma, Chandel Deepak Singh, Ganugapenta Nandi Vardhan","doi":"10.1109/ACCAI58221.2023.10199335","DOIUrl":"https://doi.org/10.1109/ACCAI58221.2023.10199335","url":null,"abstract":"Since the evaluation of textile fabric quality is crucial to the success of every textile business, the need for computer-based intelligent visual inspection systems is on the rise. There has been a lot of interest in the study of fabric defect identification as of late due to the increasing labor costs and the increased use of automation in the textile sector. We suggested a structure based on machine learning to identify flaws in fabrics automatically. In this study, we offer an automated AI-based fabric defect identification system that makes use of deep neural network models that have already been trained. The networks are trained using pre-processed, improved versions of the fabric pictures obtained using standard image processing methods. In order to train and categorize various fabric flaws, the LightGBM is combined with a pretrained network, AlexNet. We have also examined how well our categorization model works with varying values of the experimental variables. At long last, a thorough comparison of various methods has been provided.","PeriodicalId":382104,"journal":{"name":"2023 International Conference on Advances in Computing, Communication and Applied Informatics (ACCAI)","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126051188","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}

{"title":"Analysis of the Mean Square Error between the Unquant Decoding Scheme and an Innovative Simplified Hard Decoding Scheme in a Massive MIMO OFDM System","authors":"V. Hemanth, A. Raja, S. G","doi":"10.1109/ACCAI58221.2023.10201111","DOIUrl":"https://doi.org/10.1109/ACCAI58221.2023.10201111","url":null,"abstract":"In this body of work, a comparison is made between the mean squared error (MSE) of an Unquant decoding approach and an Innovative Simplified Hard Decoding strategy for a large Multiple Input Multiple Output (MIMO) Orthogonal Frequency Division Multiplexing (OFDM) system. In this section, an examination is carried out on both the Innovative Simplified Hard Decoding Scheme as well as the Unquant Decoding Scheme with regard to the resources and methods that each of these schemes requires. This category includes the subcategories Unquant and Innovative Simplified Hard Decoding Schemes, both of which are subcategories of this category. These are the locations where unquantified and innovative streamlined hard decoding schemes should be implemented. Calculate the huge MIMO MSE by comparing a recently created, less complicated hard decoding strategy with unquant decoding approaches that require 10 samples. This will allow you to calculate the MSE more accurately. As a direct consequence of this comparison, MSE now has a higher degree of precision. The findings of this comparison make it possible to make estimates. On the basis of the sample sizes, we came to the conclusion that the pretest power would be 80%. According to the results of the computation, the Innovative Simplified Hard Decoding Scheme, as well as the Unquant Decoding Scheme both, yielded a mean square error. At a signal-to-noise ratio (SNR) of 14 dB, the mean square error value produced by unquant decoding is 10 4.8, while the value produced by Innovative Simplified Hard Decoding is 10 6. If the difference between them is smaller than 0.025, then the results can be considered statistically significant.","PeriodicalId":382104,"journal":{"name":"2023 International Conference on Advances in Computing, Communication and Applied Informatics (ACCAI)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121035227","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}

{"title":"NFT Marketplace for Geospatial Data Using Blockchain","authors":"S. R, A. Sheeba","doi":"10.1109/ACCAI58221.2023.10199268","DOIUrl":"https://doi.org/10.1109/ACCAI58221.2023.10199268","url":null,"abstract":"Rights that can be transferred to digital assets like pictures, videos, or music are known as non-fungible tokens (NFTs). The phenomenon and its marketplaces have grown dramatically since early 2021. NFT marketplaces are becoming more prevalent since a few years ago. Most of them store digital materials on centralized systems (files). This study makes a recommendation for a secure trading environment for non-fungible tokenized digital assets. Users will be able to create new digital assets and exchange them for Ethereum-based currency. Also, the IPFS protocol-based decentralized file system's technological potential for more secure digital asset storage is examined. In this approach, the problem of file storage is attempted to be solved. It also represents an effort to promote the usage of blockchain technology. In a typical storage system, the user and provider sign a digitalized contract that gives the user legal recourse against the provider should their data be lost, compromised, or sold to a third party for services that they do not supply.Geospatial Data can be safely stored and secured by the user. To make the storage system more secure, two ERC rules will be used.The files are distributedly stored using this technology's decentralized network, which prohibits unauthorized access to the storage system. The blockchain project relies on hashing to function. Every block in a blockchain creates a hash using the SHA 256 hashing algorithm.","PeriodicalId":382104,"journal":{"name":"2023 International Conference on Advances in Computing, Communication and Applied Informatics (ACCAI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121066883","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}

{"title":"Use of Machine Learning and Deep Learning Techniques to Predict Cases of Hospitalizations Caused by Dengue","authors":"T. Lalitha, Jagruthi H, L. V., Dibyhash Bordoloi, N. Balaji, Ramesh Singh Rawat","doi":"10.1109/ACCAI58221.2023.10199840","DOIUrl":"https://doi.org/10.1109/ACCAI58221.2023.10199840","url":null,"abstract":"Dengue fever mosquito-borne disease viral global health crisis affecting tens of millions of people every year. Early prediction of hospitalizations caused by dengue fever can help healthcare providers allocate resources and plan for outbreaks. Deep learning and machine learning techniques happen to be used to predict dengue outbreaks, but their application to predict hospitalizations caused by dengue fever is relatively new. This case study, we propose implementation of ML/DL (machine learning/deep learning) techniques to predict cases of hospitalizations caused by dengue fever. We collected data from hospitals in dengue-endemic areas and used it to train and validate our models. The data includes patient demographic information, clinical features, and laboratory results. We applied several machine learning and deep strategies for learning which include Using a Logistic Model, A.N.N.s, decision trees, random forests, and support vector machines, the use of deep neural networks. We assessed the efficiency of these models using various indicators such F1 score, recall rate, and accuracy rate.Our results show that deep neural networks outperformed all other models, with an accuracy of 96.4%. The model was also able to identify the most important features that contribute to hospitalizations caused by dengue fever, including platelet count, hematocrit level, and age. The implementation of ML/DL techniques techniques to predict hospitalizations caused by dengue fever can help healthcare providers allocate resources more efficiently and plan for outbreaks. Future studies can further improve the accuracy of these models by incorporating additional features and data sources, such as meteorological and environmental data.","PeriodicalId":382104,"journal":{"name":"2023 International Conference on Advances in Computing, Communication and Applied Informatics (ACCAI)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121221593","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}

{"title":"Block Chain and Distributed Computing Aided with Cloud Technology- A Specific Reference to Security Issues of Healthcare Industry","authors":"Dr. C. Murugumani, Dr. Bhaludra R Nadh Singh, Ms. KalluPravalika, Ms. P. Rethvikha Sri, Ms. ChennuruSaiSowmya, Ms. Mankhala Shreya Reddy","doi":"10.1109/ACCAI58221.2023.10200779","DOIUrl":"https://doi.org/10.1109/ACCAI58221.2023.10200779","url":null,"abstract":"There has been a significant uptick in the need for user-centric electronic records to save the many characteristics of a patient's medical history as they are recorded at a hospital during treatment and to make those records available as and when they are needed for future treatment, care, or invoicing. Blockchain technology allows us to save these data on a distributed ledger, allowing us to begin and enable use at breakneck speeds while still maintaining a transparent and secure system. To save records safely and in an interoperable fashion, a distributed system with ledger functionality is used. Block chain technology has the potential to revolutionize the way digital assets are transacted by removing the need for a trusted third party to authenticate data authenticity, record asset ownership, or mediate financial or data transactions. Immutability, decentralisation, and transparency are three of its defining characteristics, making it well suited to resolving pressing problems in the healthcare industry, such as the lack of comprehensive peer-to-peer files and the inability to easily access patients' medical histories. Health care systems that are efficient and successful depend on interoperability, the capacity of different health organisations and manufacturers of different software products to connect and share data in a safe and smooth manner. Many problems in modern healthcare can be traced back to a lack of interoperability, such as siloed data, sluggish communications, and different workflow tools. To address this, it is recommended to implement a system that provides secure, pseudo-anonymous access to complete, recognised longitudinal medical records stored in silos. In this article, we conducted a system overview and literature review of block chain technology in a fog computing environment, both of which are capable of processing vast amounts of data in a decentralised fashion. Our in-progress experimental study reveals weaknesses in existing systems and foreshadows directions for future investigation.","PeriodicalId":382104,"journal":{"name":"2023 International Conference on Advances in Computing, Communication and Applied Informatics (ACCAI)","volume":"184 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124919983","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}

{"title":"Forecasting Consumer Price Index (CPI) Using Deep Learning and Hybrid Ensemble Technique","authors":"Mohammed Adnan. A, Prince Immanuel J, Roobini M. S","doi":"10.1109/ACCAI58221.2023.10200153","DOIUrl":"https://doi.org/10.1109/ACCAI58221.2023.10200153","url":null,"abstract":"In today’s day and age, economic crises are all over the world due to high inflation. Inflation is a rise in price of the goods and services produced in a country. As a result of rising prices, a given amount of money can now buy fewer goods and services. The general public’s cost of living is affected by this loss of purchasing power, which ultimately slows economic growth. Thus, it has a negative impact on the purchasing power of the people. Various sorts of baskets of commodities are generated and tracked as price indices to calculate inflation or deflation, depending on the chosen set of goods and services used. One type of price index proposed in this project is Consumer Price Index (CPI), which looks at the weighted average of costs for a variety of products and services like transportation, food, and healthcare. This paper proposes different deep learning time series models such as LSTM, BiLSTM and hybrid ensemble learning to forecast the Indian consumer price index (CPI). These two single RNN models (LSTMs and BiLSTMs) are compared with the hybrid ensemble learning model to see which gives better forecasting results for the consumer price index.","PeriodicalId":382104,"journal":{"name":"2023 International Conference on Advances in Computing, Communication and Applied Informatics (ACCAI)","volume":"32 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114042255","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}

{"title":"Impact of Elon Musk’s tweets on the price of Dogecoin using Sentiment Analysis","authors":"Sneha Vasishth, S. Sharma, A. Nayyar, K. Vijayakuamar","doi":"10.1109/ACCAI58221.2023.10199593","DOIUrl":"https://doi.org/10.1109/ACCAI58221.2023.10199593","url":null,"abstract":"Social media is pervasive and a regular part of our lives. People need to comprehend this in order to be able to influence the crypto currency market and an investor's purchasing and selling activity. Even one connected tweet from a powerful person like Elon Musk has a significant impact on these markets. This study aims to investigate how Elon Musk's tweets have affected the price of Dogecoin. The study describes how the sentiment of Musk's tweets correlates with the value of Dogecoin and how this has an impact on its value. Sentiment analysis is utilised to examine this correlation. For our research, we used two datasets: one containing tweets from Elon Musk, and the other being the Dogecoin dataset. Our findings suggest that Musk's tweets have a significant impact on the value of Dogecoin, and that the sentiment of Musk's tweets is an important factor that influences this relationship.","PeriodicalId":382104,"journal":{"name":"2023 International Conference on Advances in Computing, Communication and Applied Informatics (ACCAI)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122407484","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}

{"title":"Traffic Sign Recognition Using Deep Learning Neural Network and Spatial Transformer","authors":"Arindam Baruah, Rakesh Kumar, Meenu Gupta","doi":"10.1109/ACCAI58221.2023.10199560","DOIUrl":"https://doi.org/10.1109/ACCAI58221.2023.10199560","url":null,"abstract":"Recently, numerous applications of Intelligent Transportation Systems (ITS) have gained increasingly more focus. One of the most crucial functions of ITS is Traffic Signs Detection and Recognition (TSDR) by notifying drivers of the status of road signs and providing helpful information regarding safety procedures which helps to improve safety. A deep learning system is designed that is a combination of Convolution Neural Network(CNN) and Spatial Transformer Network(STN) to obtain maximum accuracy. AlexNet (Model-A) and BaselineNet (Model-B) are the two CNN- architecture-based models and the two sets of datasets used in the study are Belgian Traffic Sign Classification(BTSC) and German Traffic Sign Recognition Benchmark(GTSRB). To test the models in rainy, foggy, extreme sunlight, and low-light conditions augmenters like gaussian-blur, fog, snow, spatter, and contrast have been applied to the images. Further, a comparison is done between the model performance parameters after training both datasets.","PeriodicalId":382104,"journal":{"name":"2023 International Conference on Advances in Computing, Communication and Applied Informatics (ACCAI)","volume":"115 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133393904","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}