Books/Book Chapters/Edited Books

Permanent URI for this collectionhttp://192.168.24.11:4000/handle/123456789/237

Browse

Start date: 2020Subject: search.filters.subject.Machine learning

Search Results

Now showing 1 - 4 of 4
  • Thumbnail Image
    Item
    A Machine Learning-based Approach for Smart Agriculture Monitoring and Decision Support
    (Bentham Science, 2026) Ankit Jain, Anita Shukla, Imran Ullah Khan
    The field of machine learning is expanding and has a wide range of potential uses in agriculture. Machine learning is used to forecast pests and illnesses, decrease water usage, and increase crop yields, which is a topic of investigation for farmers and agricultural experts. Machine learning is capable of improving resource efficacy along with food production sustainability for farmers in the future. Numerous factors either directly or indirectly affect crop growth. Among these are the climate parameters. We can boost productivity by employing machine learning to monitor and regulate these parameters. In addition, there is a need for technological solutions to address a number of issues, including fire alerts, maintaining humidity levels and appropriate temperatures, and meeting the needs of sophisticated plants while monitoring unauthorized entry into agricultural areas. The significance of an appropriate and satisfactory supply of power cannot be understated. By using a NodeMCU Wi-Fi module, the technology offers a practical and effective solution to the issues identified in the Indian farming system. Various sensors such as those for temperature, fire, light, PIR, humidity, and soil moisture, have been utilized to monitor and regulate a variety of technological issues. Using IOT and machine learning, the projected system uses a Wi-Fi module to display real-time data that can be watched online from any location in the world. The farmer is automatically notified by this module about the need for water, site temperature, moisture and humidity, light, fire warning, and unwelcome occupancy or encroachment. Using the machine learning principle, an experiment was conducted with varying soil and plant levels. It was established that the sensor exhibited sufficient sensitivity to yield consistent results under varying water level situations for diverse combinations of plants and soil.
  • Thumbnail Image
    Item
    A Review on The Use of Robotics in Integrated Waste Management Through Artificial Intelligence & Machine Learning
    (International Society of Waste Management, Air and Water (ISWMAW), 2025, 2025) Mohammad Usama
    The development of artificial intelligence and machine learning is playing an important role in different aspects of urban lifestyle. It is now playing a significant role in ensuring sanitation and health in cities through the use of AI-powered robots in integrated waste management. AI-powered robots use artificial intelligence and machine learning in waste management, like they use it in automated waste sorting, collection of wastes, trash compaction, remote surveillance, under water clean up and waste to energy facilities. The benefits of bringing automation and robotics in waste management are many like robots can precisely sort and handle wastes. Robots are supported with high resolution cameras, sensors and they use artificial intelligence in identifying and sorting diverse types of wastes like plastics, paper, metal etc. from mixed streams. It is very effective in reducing occupational health concerns like injuries to workers from hazardous wastes. Waste collection and transportation have been transformed entirely through the use of robotics, as it involves using autonomous vehicles having robotic arms for waste collection and optimizing the routes. The volume of trash in bins is reduced as robotic systems can compact waste. Floating debris can be also removed from water bodies by robots. Waste disposal sites can be managed effectively through surveillance robots and drones having cameras and sensors. Waste Disposal in landfills gets reduced by automation as recycling rate of wastes increase and natural resources are also conserved through effective recovery of materials. Automation brings cost reduction in waste management, as it lowers the cost of labor and also helps in achieving environmental sustainability through efficient resource management. AI supported sorting of wastes provides flexibility and adaptability as they can identify new materials and can also adapt to varying waste streams. This is not possible in manual sorting of wastes. Somme of the successful case studies regarding use of robotics in waste management are Zen Robotics (Finland), AMP Robotics (USA), Prairie Robotics, Waste Robotics and Recycleye
  • Thumbnail Image
    Item
    Role of Artificial Intelligence in Teaching and Learning Chemical Sciences
    (Bentham Science Publishers Pte. Ltd. Singapore, 2024) Shahla Tanveer, Mariyam Tanveer, Ayesha Tanveer
    Artificial Intelligence (AI) is revolutionizing our everyday tasks, and education has certainly not been left behind. AI harnesses technologies such as machine learning, natural language processing, and deep learning, to execute tasks and elevate our problem-solving capabilities. The infinite possibilities that arise due to interactions between atoms and molecules further leading to bond formation are nearly impossible for a human to comprehend. Thus, AI is playing a vital role in understanding chemistry by accelerating research, designing novel molecules, and optimizing processes. AI plays a diverse role, from assisting in drug discovery research to identifying new drug targets to supporting personalized learning experiences that aid students in their learning journeys. AI-powered adaptive learning system identifies a student’s performance and tailor the learning requirements accordingly. Students receive real-time feedback and personalised content helping them to understand the concepts more easily. AI is being used to develop interactive simulations and customized learning programs to help students learn chemistry more efficiently. Virtual laboratories driven by AI provide a safe and reachable environment for hands-on experience. This allows students to be inquisitive about chemical reactions, molecular structures, and their spectroscopic analysis in a risk-free environment. Some examples include Chat GPT, which helps create a customized learning experience for students while helping them answer their queries, an AI-powered tutoring system known as Socratic, which helps the students learn chemistry concepts, and Molecules in Motion (an AI-powered simulation) to inspect the behaviour of molecules. This chapter discusses how the union of AI and chemical sciences has accelerated innovation in the field of chemistry and can further improve learning outcomes.
  • Thumbnail Image
    Item
    Machine Learning Approaches to Rational Drug Design
    (Springer, 2020) Salman Akhtar, Mohammad Kalim Ahmad Khan, Khwaja Osama
    Pharmaceutical industries are multibillionaire setups with a diligent team ofscientists, researchers, technical manpower, and investors. A major concern ofsuch industries is to always curtail the time and cost factor associated with them.Bioinformatics involving machine learning (ML) methods have come to theforefront to address this problem. The predictive and statistical efficacy of MLmethodologies has even proven to propose better leads than a wet lab pipeline.This chapter aims to give a brief overview of underlying principles of mainly GAsand ANNs as popular ML algorithms and deeper insight into their robustapplications in the field of modern day drug design. It also attempts to share thefuture prospects of such ML techniques and their limitations with possiblesolutions hereafter.