2024

Permanent URI for this collection

https://atlasuniversitylibraryir.in/handle/123456789/412

Browse

Browsing 2024 by Subject "Artificial Intelligence"

Now showing 1 - 3 of 3
  • No Thumbnail Available
    Item
    AgroScan : Crop Identification Application using Artificial Intelligence Approach
    (Nanotechnology Perceptions, 2024) Meher, Kunal
    Artificial intelligence (AI) has the potential to revolutionize agriculture, particularly in the realm of crop analysis. AI-based systems can accurately identify crops in images, even under challenging conditions such as low light or shading. These systems have numerous applications, including crop monitoring and management, precision agriculture, and food safety and security. The goal of this research paper is to develop a robust, accurate, and efficient AI-based crop identification system. The system will be trained on an extensive dataset of crop images to identify various crops and detect certain diseases in new images. To evaluate our system's performance, we will compare it against new and emerging methods using a held-out test set. This study aims to develop an AI-driven crop identification system that will benefit farmers and other stakeholders in the agricultural sector by improving crop yields and quality, reducing costs, minimizing environmental impacts, and enhancing food safety.
  • No Thumbnail Available
    Item
    Contemporary Trends and Challenges and Advances, in the Manufacturing Industry, with a special focus on applications of Artificial Intelligence and Deep Learning
    (European Economic Letters, 2024) Grover, Pooja; Kumari, Sweta; Vaishnav, Jaimine; Mohammed, Shoaib
    In the last few years’ artificial intelligence (AI), has begun to make its appearance in our everyday life. Even though it is still in its early stage of development, AI has proved beyond human intelligence. DeepMind’s AlphaGo is an illustration of how the AI could provide amazing benefits, particularly in industries such as manufacturing. At the moment there are attempts to connect AI technology with precision engineering and manufacturing in order to change classical production methods. This research paper focuses on some notable milestones that have already been attained in the realization of AI for manufacturing and how it will change the face of any manufacturing facility. There are several challenges in the AI manufacturing application; these include data acquisition and management, human resources, infrastructure, security risks associated with trust issues as well implantation of hurdles. For instance, the collection of data required to train AI models can be challenging for rare events or expensive in large datasets that require labeling. The introduction of AI models into industrial control systems can also pose risks to the security, and some players in industry may be reluctant to use AI because they don’t trust it or understand what is going on. However, these hindrances do not deter AI from becoming an effective solution for predictive maintenance and quality assurance in the sector of manufacturing. Therefore, one should ponder over each manufacturing case and its needs before deciding if or how to adopt AI. The aim of this research paper is to analyze the current progress, problems and prospects in AI-ML across manufacturing entities. Its aim is to enhance knowledge of accessible technologies, support decision-making in choosing appropriate AI/ML technologies and determine where further research needs are possible centered on latest developments. Initial findings indicate that the combination of AI/ML technologies with advanced data collection capabilities from manufacturing networks can produce massive cost and efficiency gains. Though the accurate representation of complex phenomenon in manufacturing is problematic, AI can revolutionize this industry. Other areas where AI is intensively studied include medical image analysis, bioinformatics, recommendation systems and finance. Many notable AI products such as Amazon’s Alexa, IBM Watson and DeepMind AlphaGo have already integrated into our daily use. To address limitations such as interpretability and degraded performance with insufficient data, several sub-branches of deep learning are currently researched namely; Physics - Informed Deep Learning (PIDL), Explainable AI(XAI), Domain Adaptation, (DA) Active Leaning (AL), Multi Task Learning MTL, Graph Neural Network GNN. Convergence of AI with other engineering industries have a potential issue that should not be ignored. The aim is to enable an effective use of AI by the precision engineering and manufacturing community for future-oriented manufacture.
  • No Thumbnail Available
    Item
    Recent Advances, Challenges in Applying Artificial Intelligence and Deep Learning in the Manufacturing Industry
    (Pacific Business Review (International), 2024-01-07) Jaimine, Vaishnav
    Artificial intelligence (AI) and deep learning have emerged as transformative technologies in the manufacturing industry, revolutionizing traditional processes and enhancing operational efficiency. The use, implications, and challenges related to their integration are explored in this study. When evaluating the effects of current developments and the difficulties in implementing artificial intelligence (AI) and deep learning in their business, it is essential to include the viewpoint of workers in industrial facilities. An attempt has been made to summarize these people's views on the combination of deep learning and artificial intelligence. The implementation of AI and deep learning in manufacturing has undoubtedly brought about transformative changes, promising increased efficiency, improved processes, and enhanced productivity. Despite their promising benefits, several challenges hinder the widespread implementation of AI and deep learning in manufacturing.This study is an attempt to explore the application areas, its effectiveness and challenges in implementation of artificial intelligence and deep learning in manufacturing industry.The results of the study demonstrated how deep learning and artificial intelligence are being applied by the manufacturing industry in various areas, such as process design, sector-based control units, platform technology, operation technology, and so on.Workspace planning and production have become more standardized thanks to the use of deep learning and artificial intelligence.