Recent Trends in Artificial Intelligence & it's Applications(e-ISSN:2583-4819) <p><strong>RTAIA </strong>is a peer-reviewed journal in the discipline of Computer Science published by the MAT Journals Pvt. Ltd. It is a print and e-journal focused towards the rapid publication of fundamental research papers on all areas of Artificial Intelligence. The Journal aims to promote high-quality empirical Research, Review articles, case studies and short communications mainly focused on Artificial Neural Networks, Machine Learning, Pattern Recognition, Soft Computing and Fuzzy Systems, Intelligent Robotic Systems, Image and Video Processing and Analysis, Swarm Intelligence, Medical Imaging, Speech Generation and Recognition.</p> en-US Recent Trends in Artificial Intelligence & it's Applications(e-ISSN:2583-4819) Used Car Price Prediction Using Artificial Neural Networks and Machine Learning Techniques <p>Regardless of the substantial rise in car use, <br>newly constructed motor vehicles fail to <br>attract potential clients due to a variety of <br>reasons such as prohibitive costs, shortages <br>of vehicles, budgetary constraints, along <br>with other variables. As such, the market <br>for second-hand automobiles is expanding <br>quickly everywhere, except for the nation of <br>India, where it remains very young and <br>strongly controlled by unorganized<br>vendors. This raises the possibility of fraud <br>when buying a vehicle that is used. Asking <br>choosing the consumer and the <br>merchandiser in order to determine the <br>price of a previously owned automobile, a <br>highly precise estimate is required. This <br>framework creates two models: a<br>Computerized Random Walden and an<br>Oversaw learning-based Artificial Neural <br>Network framework every one of which can <br>take advantage of the specified transport <br>data collection.<br>A wide range of unique features is taken <br>into account for accurate projections. The<br>results obtained beat examples that depend<br>on simple linear models as well as are<br>consistent with theoretical predictions.<br>Artificial neural networks (ANNs). The<br>collection of data for automobiles is used<br>for evaluating these methods. The results of <br>the experiments show that the random <br>forests approach, which achieves a median <br>absolute error of 1.0970472 and an R2 <br>mistake that is 0.772584, generates the least<br>amount of failures compared to every other<br>approach.<br>Every day, the world and everyone’s<br>expectations are expanding. Out of all<br>the anticipation, one of them will buy the <br>motor vehicle. As no one is able, the cost of<br>another one at all times, everybody will <br>eventually buy a used one. However, a <br>newcomer is unfamiliar with the asking <br>price of the wanted automobile on the used <br>car marketplace. Whenever the purchase <br>price of new cars increased due to increased<br>technological costs, the economic case for<br>older cars became more powerful</p> Revathi .R Gunasekaran K Copyright (c) 2023 Recent Trends in Artificial Intelligence & it's Applications(e-ISSN:2583-4819) 2023-07-28 2023-07-28 2 3 1 5 A Second User Automotive Value Prediction System for Consumer’s Purchasing Using Machine Learning Approach <p>Determining the value of a used automobile <br>can be a challenging task due to the multitude <br>of factors influencing its market worth. The <br>objective of this project is to create machine <br>learning models capable of accurately <br>predicting the value of a secondhand vehicle <br>based on its various attributes, facilitating <br>informed purchasing decisions. The global <br>trend of rising interest in buying and selling <br>used cars, underscores the urgent need for a <br>reliable Secondhand Vehicle Value Prediction <br>system that can efficiently determine the <br>precise value of a car by considering a range <br>of features. Historically, this challenge was <br>addressed through arbitrary pricing decisions <br>by sellers, leaving buyers and sellers in the <br>dark regarding the actual value of the vehicle <br>in the current market. Sellers often lacked <br>knowledge about the vehicle's true worth and <br>what price to list it for. The project's <br>approach involves evaluating the <br>performance of different regression <br>algorithms, including linear regression, Ridge <br>Regression, and Lasso Regression. The <br>primary objective is to provide a reliable tool <br>that benefits both buyers and sellers by <br>bringing transparency and accuracy to the <br>valuation of secondhand vehicles, ultimately <br>aiding in more informed purchasing <br>decisions. In essence, this project seeks to <br>bring transparency and precision to the <br>valuation process.</p> Ramya N J.Rajeswari Copyright (c) 2023 Recent Trends in Artificial Intelligence & it's Applications(e-ISSN:2583-4819) 2023-09-22 2023-09-22 2 3 6 10 Smart Cam: An Empowering Communication with Flask-Powered Image-to-Text Conversion <p>Today, many of us go outside of the state or <br>country for jobs or holidays. Each location or <br>area may have their regional communication <br>language because of which a communication <br>gap may occur. Due to communication gaps, <br>people often are not able to communicate with <br>native people or perceive the written notes or <br>sign boards and typically don't seem to be <br>ready to do their work. This becomes a big <br>hurdle for many people who need a quick <br>solution. However, with the advancement of <br>technology, it is possible to use some <br>techniques to fill this communication gap by <br>translating images into text. The concept of <br>text-to-image offer user-friendly and efficient <br>communication between human and <br>computer (machine) that too in natural <br>languages. This paper proposed a web <br>application that translates the image into a <br>native language as per the user’s need. The <br>web-based application is developed with a <br>flask with numerous libraries such as <br>PyTesseract, OpenCV, Numpy, and textblob <br>libraries. The proposed work is based on <br>Tesseract. Tesseract is an OCR engine that <br>relies on Unicode and can recognize more <br>than 100 languages. The proposed work helps <br>the employee or tourist to visit foreign <br>countries or other places whose language is <br>not known or understandable to the person.</p> Ashutosh Sharma Abhishek Kr. Singh Rupesh Sharma Aquib Ahmad Pushpa Singh Copyright (c) 2023 Recent Trends in Artificial Intelligence & it's Applications(e-ISSN:2583-4819) 2023-09-22 2023-09-22 2 3 11 16 Anatomization of Respiratory Diseases Using Machine Learning <p>The respiratory system is frequently <br>susceptible to various diseases, with chronic <br>obstructive pulmonary disease (COPD) <br>serving as a notable illustration. COPD is <br>distinguished by an enduring lung ailment <br>characterized by a gradual reduction in lung <br>function over time. Precise prediction of <br>respiratory diseases is of utmost importance, <br>as a failure to do so can lead to fatal <br>consequences. Timely diagnosis plays a <br>pivotal role in reducing mortality rates. In <br>this research, raw spirometry data undergoes <br>a process of feature selection to identify<br>relevant attributes. These selected <br>characteristics are subsequently input into a <br>classification system to distinguish between <br>normal, obstructive, and restrictive cases. The <br>study illustrates how the accuracy of <br>classification algorithms, particularly in the <br>field of machine learning, can be significantly <br>improved through feature selection methods. <br>The suggested study has significantly <br>enhanced the accuracy of categorization using <br>a variety of algorithms, such as Naïve Bayes, <br>Support Vector Machine, Logistic Regression, <br>and K-Nearest Neighbor. Among these <br>algorithms, Logistic Regression emerges as <br>the most accurate classifier in this specific <br>context. This investigation underscores the <br>critical importance of early detection and <br>emphasizes the potential of machine learning <br>techniques in enhancing the accuracy of <br>diagnosing respiratory diseases, particularly <br>COPD, which can have a profound impact on <br>patient outcomes</p> K. Karunya Nivetha M Tamil Selvan H Janani G S Aniruddh Aiyengar Copyright (c) 2023 Recent Trends in Artificial Intelligence & it's Applications(e-ISSN:2583-4819) 2023-10-09 2023-10-09 2 3 17 27 Natural Language Processing Techniques Using Machine Learning <p>Natural language processing (NLP) is an <br>artificial intelligence subset. Computers can <br>talk in people's native languages, and other <br>language-related jobs are scaled. NLP enables <br>computers to read text and hear voices, <br>comprehend it, measure sentiment, and <br>identify significant components. NLP is a <br>synthesis of several disciplines, including <br>computing linguistics, machine learning, deep <br>learning, and statistics. These technologies <br>work together to enable computer software to <br>interpret and understand human language in <br>the same way that another human would, <br>including meaning, intent, and sentiment. <br>Human language can be understood by <br>machines. It could take the form of speech or <br>text. It employs ML (Machine Learning) to <br>achieve the goal of Artificial Intelligence. The <br>ultimate goal is to bridge the gap between <br>how humans communicate and what <br>computers can understand.<br>When used in conjunction NLP produces <br>systems that can learn to complete tasks on <br>their own and improve with practice using <br>machine learning techniques. Among many <br>other things, NLP-powered solutions can <br>assist you in categorizing and recognizing <br>identifiable entities from commercial <br>correspondence or assessing mood in social <br>media posts. In this study, the importance of <br>machine learning in NLP and its potential <br>applications are discussed in detail.</p> Sanjay Kumar Copyright (c) 2023 Recent Trends in Artificial Intelligence & it's Applications(e-ISSN:2583-4819) 2023-10-30 2023-10-30 2 3 28 33 Applications of AI in Technology and Management <p>Artificial intelligence refers to the emulation<br>of human cognitive processes via the use of<br>machines, particularly computer systems. The<br>objectives of Artificial Intelligence (AI) have<br>been focused on the advancement of<br>computers to accomplish activities that were<br>previously exclusive to human capabilities,<br>including decision-making, natural language<br>processing, and intricate problem-solving.<br>This pursuit has been the driving force<br>behind AI research from its start. Currently,<br>the field of artificial intelligence (AI) is<br>marked by a diverse range of applications,<br>including several sectors such as healthcare,<br>banking, and manufacturing. These<br>applications include self-driving vehicles and<br>virtual assistants, which have brought about<br>significant advancements in these areas. The<br>current state of Artificial Intelligence exhibits<br>indications of not just automating tasks, but<br>also possessing the potential to revolutionize<br>our lifestyles and professional endeavors. In<br>this discourse, we shall explore the realm of<br>artificial intelligence, delving into its many<br>classifications, objectives, and obstacles, while<br>also examining its evolutionary trajectory.<br>The primary aim of this article is to highlight<br>the various applications of artificial<br>intelligence (AI) within the domains of<br>technology and management. These<br>applications encompass automation,<br>predictive maintenance, and computer vision,<br>natural language processing (NLP),<br>recommendation systems, data analytics,<br>supply chain optimization, and financial<br>management.</p> Mayur M Sevak Komal K Shukla Copyright (c) 2023 Recent Trends in Artificial Intelligence & it's Applications(e-ISSN:2583-4819) 2023-11-29 2023-11-29 2 3 34 40