Varshitha Vankadaru, P. Srinivasu, Singavarapu Hemanth Hari Prasad, P. Rohit, Pydipamula Rohan Babu, Matta Deva Chandra Raju
{"title":"Text Identification from Handwritten Data using Bi-LSTM and CNN with FastAI","authors":"Varshitha Vankadaru, P. Srinivasu, Singavarapu Hemanth Hari Prasad, P. Rohit, Pydipamula Rohan Babu, Matta Deva Chandra Raju","doi":"10.1109/ICIDCA56705.2023.10099715","DOIUrl":"https://doi.org/10.1109/ICIDCA56705.2023.10099715","url":null,"abstract":"Text extraction is critical for any analysis in a document processing system. Text extraction is the process of recognizing text data from an image. The handcrafted elements used by traditional handwriting recognition systems require a lot of prior knowledge. Convolutional approaches can be used to train optical character recognition (OCR) systems, although doing so requires a lot of training data. Deep learning approaches are the main focus of handwriting recognition research, which has recently produced ground-breaking results. But the exponential expansion of handwritten text and the accessibility of vast computational power need an improvement in predictive performance and more study. To enable the automatic extraction of distinguishing features from handwritten characters and phrases, Convolutional Neural Networks (CNNs), a subset of Deep Learning technology, are especially adept at comprehending the structure of handwritten letters and phrases. The disadvantages of this approach include increased time and resource requirements. The proposed design is based on CNN with Bi-LSTM, is used to identify the text from the handwritten images.","PeriodicalId":108272,"journal":{"name":"2023 International Conference on Innovative Data Communication Technologies and Application (ICIDCA)","volume":"87 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121773666","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}
S. M. Udhaya Sankar, N. Kumar, D. Dhinakaran, K. S, Abenesh R
{"title":"Machine Learning System For Indolence Perception","authors":"S. M. Udhaya Sankar, N. Kumar, D. Dhinakaran, K. S, Abenesh R","doi":"10.1109/ICIDCA56705.2023.10099959","DOIUrl":"https://doi.org/10.1109/ICIDCA56705.2023.10099959","url":null,"abstract":"A person is more prone to nod off while driving, which could cause a traffic accident if they don't receive enough sleep or rest. This leads to a variety of unpleasant scenarios, which we refer to as driver drowsiness. Numerous people are injured or killed in traffic accidents every day throughout the world. According to studies, drivers operating a vehicle when extremely fatigued account for over one-fourth of all fatal highway collisions, suggesting that driver fatigue is a bigger contributor to collisions than drunk driving. This study's main goal is to recognize driver tiredness and decide the best course of action. There are many methods, and they all depend on how the driver is driving or how the automobile is moving. The alert system is one of the physiological strategies utilized to keep the driver attentive and distracted from tiredness. Many strategies are used to deal with expensive sensors and a lot of data. As an outcome, the real-time indolence perception system created in this research has a good method and an acceptable level of accuracy. This prototype system records and captures the driver's facial expressions using a webcam. Each movement in each frame is recognized using a variety of image processing algorithms. Using landmarks, several aspects are calculated, compared, and detected. The outcome is then provided in accordance with the calculated outcome. The alarm system is activated in accordance with comparisons to the current levels.","PeriodicalId":108272,"journal":{"name":"2023 International Conference on Innovative Data Communication Technologies and Application (ICIDCA)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116575778","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}
Monica C, B. Jyothi, Amogh Ramagiri, Sathwik Gottipati, V. Jahnavi, Syed Afreen Akther, R. Chinnaiyan
{"title":"Intelligent Traffic Monitoring, Prioritizing and Controlling Model based on GPS","authors":"Monica C, B. Jyothi, Amogh Ramagiri, Sathwik Gottipati, V. Jahnavi, Syed Afreen Akther, R. Chinnaiyan","doi":"10.1109/ICIDCA56705.2023.10100296","DOIUrl":"https://doi.org/10.1109/ICIDCA56705.2023.10100296","url":null,"abstract":"With the increasing global population and emerging technologies, there is a pressing need for efficient traffic management systems. Unfortunately, the traditional traffic control system, which relies on tri-colour signals is unable to prioritize emergency vehicles or control traffic effectively. Resulting in accidents, loss of life, and traffic congestion. However, recent technologies such as GPS, which provides live traffic data and emergency vehicle tracking, Artificial Intelligence (AI) and Deep Learning (DL), which can predict traffic solutions, Cloud Computing it processes the data and Internet of Things (IoI), which collects real-time data and offers promising solutions. Some of the challenges include the integration of various technologies, complexity in algorithms, scalability concerns, security and privacy. In this paper, we present a study on the role of AI, IoT and GPS in traffic management, proposing a better traffic signal management system that reduces congestion, prioritizes emergency vehicles, reduces commuting time and tracks vehicles.","PeriodicalId":108272,"journal":{"name":"2023 International Conference on Innovative Data Communication Technologies and Application (ICIDCA)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126377998","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":"Application of Data Analytics in Risk Management of Fintech Companies","authors":"Debapriya Chowdhury, Prasanna Kulkarni","doi":"10.1109/ICIDCA56705.2023.10099795","DOIUrl":"https://doi.org/10.1109/ICIDCA56705.2023.10099795","url":null,"abstract":"Technology is rooting the fintech companies at an unprecedented rate raising the rate of risk prevailing in this domain. The application of Data Analytics in the fintech industry, characterized by fraud detection, prevention, and risk management, has offered better solutions to the risks. It provides a more accurate prediction of their potential outcomes. There is a considerable increase in recognition of risk management in Data Analytics due to the increasing volume of data. There is a need for research in Data Analytics as it helps companies better understand the onset of risk factors. The application of data analytics in risk management for fintech companies presents several challenges, like data quality and availability, lack of expertise, cybersecurity and data privacy, bias, ethical concerns, etc. Fintech companies must balance the potential benefits of data analytics in risk management with the challenges and risks of implementing and maintaining effective data analytics models. Fintech companies can mitigate risks by collaborating with other companies, industry associations, and regulators. This can help them stay updated with the latest risks and best practices and identify potential risks early on. This research paper comprehensively presents a picture of the application of Data Analytics in managing the risks involved in Fintech companies and notes the shortcomings regarding appropriate policies for data management, transparency, and reliability.","PeriodicalId":108272,"journal":{"name":"2023 International Conference on Innovative Data Communication Technologies and Application (ICIDCA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126446511","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":"The Impact of Big Data on Climate Change","authors":"Adish Chandra Shrivastava, Mohd. Umar","doi":"10.1109/ICIDCA56705.2023.10099659","DOIUrl":"https://doi.org/10.1109/ICIDCA56705.2023.10099659","url":null,"abstract":"The precariousness and impacts of climate change are spreading worldwide, resulting in economic, environmental, and social damages. Due to this damage, some irregular variations in temperature, rainfalls, and sea level are being experienced. Such variations in temperature, rainfall patterns, or sea level rise are irrelevant. Variations in rainfall intensity will significantly impact water level and water quality. Rising sea levels will impact land usage and development in the coastal area. Big climate data analytics implementations havefocused on climate change because it is a new issue, and extensive study has been done on various subjects. Rainfall prediction is the most crucial aspect of Big data techniques in climate change. Since most individuals worldwide depend on agriculture, this may benefit farmers and the general populace. The study illustrates numerous methods by which big data has aided in creating predictions regarding the problem of climate change. It can assist farmers in making wise judgments on crop yield. Studying the timing of floods or droughts simultaneously may be possible.","PeriodicalId":108272,"journal":{"name":"2023 International Conference on Innovative Data Communication Technologies and Application (ICIDCA)","volume":"15 16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126167508","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 Shared Network Security System for Cloud Computing","authors":"T. Arumugam, P. Senthilraja, A. Gnanabaskaran","doi":"10.1109/ICIDCA56705.2023.10100001","DOIUrl":"https://doi.org/10.1109/ICIDCA56705.2023.10100001","url":null,"abstract":"Cloud computing has hastened the creation of web and mobile apps that may reach tens of millions of users by enabling small firms to access virtual infrastructures. This preserves data and programs from several shared data center residents, blurring system barriers for each cloud user. Challenges of different inhabitants have varied safety requirements, while some demand other security procedures. Network visualization matches the underlying network with tenant-specific criteria, enabling tenant datacenters to immediately resolve a variety of tenant needs. This system proposes the framework implementation of shared network security, a partnership in multi-tenant data centers. A multitenant data center for cloud computing is a facility that provides computing infrastructure and services to multiple customers, or tenants, in a shared environment. This shared network security system is based on unified threat management system. Shared network security uses intelligent package verdict for intelligence flow analysis to avoid data center network attacks.","PeriodicalId":108272,"journal":{"name":"2023 International Conference on Innovative Data Communication Technologies and Application (ICIDCA)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125701479","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}
S. S. Kumar, M. Jyothirmai, S. Kaliappan, Vikas Rathiv
{"title":"An Application of IoT in Programmed Tidal Energy Observation System","authors":"S. S. Kumar, M. Jyothirmai, S. Kaliappan, Vikas Rathiv","doi":"10.1109/ICIDCA56705.2023.10100013","DOIUrl":"https://doi.org/10.1109/ICIDCA56705.2023.10100013","url":null,"abstract":"According to the Internet of Things (IoT), internet objects will play an important role as computer products in every part of our daily life. With the use of the current network infrastructure, IoT provides devices to be monitored or directly controlled, optimized, precision enabled, and economic improvement and also by reducing human participation. This innovation has a broad spectrum of applications, such as solar energy, tidal power stations, smart villagers, microgrids, and tidal-powered appliances. As renewable energy had its greatest success ever throughout this time, with a growth that was recorded considerably higher than ever. The problem and solution described here involve displaying tidal power's electricity usage as a sustainable power source on the IoT-enabled controller. Using suitable sensing devices and raspberry pi, this approach has been formed. Through a monitoring dashboard, every renewable electricity use is monitored. The user will find it simpler to comprehend how much electricity the system is generating daily. Both the utilization of sustainable energy and power generation issues are touchedon by this research work.","PeriodicalId":108272,"journal":{"name":"2023 International Conference on Innovative Data Communication Technologies and Application (ICIDCA)","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130345875","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}
K. Sk, Roja D, Sunkara Santhi Priya, Lavanya Dalavi, S. Vellela, Venkateswara Reddy B
{"title":"Coronary Heart Disease Prediction and Classification using Hybrid Machine Learning Algorithms","authors":"K. Sk, Roja D, Sunkara Santhi Priya, Lavanya Dalavi, S. Vellela, Venkateswara Reddy B","doi":"10.1109/ICIDCA56705.2023.10099579","DOIUrl":"https://doi.org/10.1109/ICIDCA56705.2023.10099579","url":null,"abstract":"Nowadays, digitalization in the healthcare organizations places great emphasis on technological advances in clinical healthcare providers. Traditional methods for measuring and evaluating outcomes for patients in forecasting and diagnosing chronic diseases are being substituted by techniques that capture the most significant insights from medical information by combining predictive modeling with a highly valuable application of machine learning. Heart disease is nowadays among the worst disorders in the world. Because the death rate from heart disease remained largely significant, more intensive efforts in preventive are required, such as enhancing the accuracy of a heart disease prediction system. Additionally, an early diagnosis supports in the appropriate diagnosis of the condition as well as the management of its symptoms. By creating forecasting analytics, Machine Learning (ML) techniques can be used to anticipate chronic diseases including kidneys and cardiac disorders. Hence, this analysis presents coronary heart disease prediction and classification utilizing Hybrid Machine Learning methods. In this approach the combination of Decision Tree (DT) and Ada Boosting algorithms is used as a hybrid ML algorithm to predict the CHD. This method's performance is determined by the performance metrics such as accuracy, True Positive Rate (TPR), and Specificity.","PeriodicalId":108272,"journal":{"name":"2023 International Conference on Innovative Data Communication Technologies and Application (ICIDCA)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132128019","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":"Malware Intrusion in Smart Traffic System and Rectification using Djikstra Algorithm","authors":"K. P, M. Damle","doi":"10.1109/ICIDCA56705.2023.10100019","DOIUrl":"https://doi.org/10.1109/ICIDCA56705.2023.10100019","url":null,"abstract":"Traffic signal systems are employed to continuously manage traffic flow and promote a safe and smooth flow of transport. Traditional traffic signal system provides instructions to stop the vehicle, but if a person breaks the traffic network system, then this system cannot apprehend them, and there are chances of malpractice. Due to the continuous increase in traffic congestion, it is necessary to evaluate the current system and implement improvised technologies to provide an intelligent traffic signal system. Hence, to increase the security of traffic signals, reduce human errors, and avoid malpractices, an intelligent traffic signal system in which the Dijkstra algorithm is practised is introduced. This paper analyzes how to resist a malicious software assault on an intelligent traffic signal system that leads to collision avoidance and check signal latency while adjusting the system during the attack.","PeriodicalId":108272,"journal":{"name":"2023 International Conference on Innovative Data Communication Technologies and Application (ICIDCA)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131236018","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":"Text Detection based on Deep Learning","authors":"A. Thilagavathy, Karuturi Hemanth Suresh, Katari Tejesh Chowdary, Meka Tejash, Vijayarao Lakshmi Chakradhar","doi":"10.1109/ICIDCA56705.2023.10099672","DOIUrl":"https://doi.org/10.1109/ICIDCA56705.2023.10099672","url":null,"abstract":"Optical Character Recognition (OCR), a system for automatic recognition, is used in a variety of application sectors to convert text or images into editable data. With the distinct outline and size, printable or typed letters are easy to identify. However, this is never the case while dealing with handwritten text since each person's handwriting is unique. Handwritten text is difficult for OCR to read. This study presents a two-phase method for recognizing and classifying the input data. Convolutional Neural Networks (CNNs) were used as a framework for categorization. The process starts with the recognition of input text. The second stage is to determine the language used to generate the input number. Further, Python is used to analyze the handwritten characters in MNIST database. The simulation results show an error-free recognition rate and extremely high efficiency. The proposed work has achieved a 1.4% training loss, 99% testing accuracy and 99.6% training accuracy.","PeriodicalId":108272,"journal":{"name":"2023 International Conference on Innovative Data Communication Technologies and Application (ICIDCA)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134132395","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}