Books/Book Chapters/Edited Books

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

Browse

Filters

2025 - 20264

Settings

Subject: search.filters.subject.machine learning

Search Results

Now showing 1 - 4 of 4
  • Thumbnail Image
    Item
    Innovations and Impacts on Agricultural Practices: Improving Weed Management With Artificial Intelligence
    (Taylor and Francis, 2026) Aliya Firdaus, Syed Khalida Izhar, Shazia Qamar, Uzma Afaq
    Artificial intelligence (AI) plays a pivotal role in advancing environmental stewardship by enabling innovative solutions to address pressing ecological challenges. Through its ability to process vast amounts of data, AI empowers researchers and policymakers to monitor environmental changes, predict future trends, and develop strategies for sustainable resource management. By integrating AI into environmental efforts, societies can transition toward more sustainable practices, ensuring the preservation of natural ecosystems for future generations. Its transformative potential underscores the importance of leveraging AI as a critical tool in fostering global environmental resilience and sustainability. AI for Environmental Innovation and Stewardship examines this transformative potential by covering fundamental concepts, innovative methodologies, and real-world applications of AI in environmental contexts. It highlights the role of machine learning, data analytics, generative AI, supply chains, augmented reality, and virtual reality in providing new insights and solutions for managing complex ecological systems. It explains how AI is advancing environmental monitoring, enhancing predictive capabilities, optimizing resource usage, and supporting evidence-based decision-making.
  • Thumbnail Image
    Item
    Convolutional Neural Networks for Foliar Disease Diagnosis in Horticulture Crops: A Critical Review
    (Springer Nature Switzerland, 2026) Anshu Khare, Naimur Rahman Kidwai, Shrish Bajpai
    The research aims to examine further how to apply advanced machine learning models and deep learning models, especially convolutional neural network models (CNN), in detecting disease in both tomato and potato plants in advance. It emphasizes how various factors, such as disease-producing micro-organisms and environmental components in addition to less varying datasets, especially when using datasets such as PlantVillage, which have shown vast usage in various models in various research worldwide, can particularly influence the accuracy of disease detection models in crops such as potatoes and tomatoes using CNN models talked of in this study. CNN models, especially AlexNet models, ResNet models, and EfficientNet models, which show high accuracy in classifying different kinds of disease in various kinds of crops using 94–99.75% accuracy levels, are discussed in this study as a basis of further research to come up with more efficient models in promoting both machine learning and various uses of CNN models in disease management in promoting food security in many countries worldwide.
  • Thumbnail Image
    Item
    Study of an Innovative Approach to IoT Based Human Activity Recognition
    (BP International, 2025) Motashim Rasool , Rizwan Akhtar , Uvais Ahmad
    Recognizing human activities is vital for numerous contemporary applications rooted in the Internet of Things (IoT) framework, spanning from the creation of intelligent video surveillance setups to the advancement of robotic assistants for the elderly. Recently, there has been significant exploration into machine learning algorithms to enhance the recognition of human activities. Despite these research endeavors, there remains a notable dearth of studies focusing on efficiently recognizing complex human activities, particularly those involving transitions, and no research has been conducted to assess the impact of noise in training data on algorithm performance. This paper addresses these gaps by presenting an innovative activity recognition system centered on a neural classifier with memory capabilities, designed to optimize the classification of both transitional and non-transitional human activities. Utilizing unobtrusive IoT devices such as accelerometers and gyroscopes integrated into widely-used smartphones, the system effectively identifies human activities [1,2]. The key feature of the proposed system lies in leveraging a neural network augmented with short-term memory to retain information about preceding activities' characteristics. Experimental validation demonstrates the reliability and accuracy of the proposed system compared to state-of-the-art classifiers, highlighting its robustness in handling noisy data. Human Activity Recognition (HAR) is essential for various modern applications within the Internet of Things (IoT) framework, from developing intelligent video surveillance systems to enhancing robotic assistants for the elderly. Despite significant advancements in machine learning algorithms for HAR, there is a notable lack of research on effectively recognizing complex human activities, particularly those involving transitions, and assessing the impact of noise in training data on algorithm performance. This paper addresses these gaps by presenting an innovative activity recognition system centered on a neural classifier with memory capabilities. Designed to optimize the classification of both transitional and non-transitional human activities, the system employs unobtrusive IoT devices such as accelerometers and gyroscopes integrated into widely used smartphones [1,3]. A key feature of the proposed system is the utilization of a neural network augmented with short-term memory to retain information about preceding activities' characteristics. Experimental validation demonstrates the system's reliability and accuracy compared to state-of-the-art classifiers, emphasizing its robustness in handling noisy data.
  • Thumbnail Image
    Item
    Nanotechnology innovation: AI-enhanced polymer drug delivery systems
    (Walter de Gruyter GmbH, 2025) Usama Ahmad; Wan Nurhidayah Wan Hanaffi, Khan Aejaz Ahmed
    The confluence of polymer nanotechnology with artificial intelligence (AI) is revolutionizing drug development and targeted drug delivery, ensuring unprecedented precision in therapeutics. By coupling data analytics with AI-driven polymeric nanocarrier systems, the technology surpasses the constraints of traditional drug delivery, including bioavailability and patient-specificity, by virtue of superior design, encapsulation efficiency, and controlled release mechanisms for the drug. Predictive modeling and machine learning algorithms aid AI in optimizing drug–polymer interaction and optimizing the physicochemical characteristics of polymer nanocarriers so that therapeutics are released accurately and controllably at target sites to reduce side effects. AI’s capability to forecast the interaction of disease-specific, biocompati ble, and responsive polymers for patient profiles advances the principle of precision medicine. Improved encapsulation efficiency and optimized kinetics by AI-driven processes maximize the direct delivery of therapeutics to the target site with optimal doses for enhanced bioavailability and therapeutic efficacy. The amalgamation of AI with polymeric nanotechnology thus enables drug discovery in the rapid prototype and optimization of nanocarrier systems to deliver precise, individualized drug delivery with high accuracy to diverse therapeutic domains. This chapter discusses the development potential of AI-fortified polymer-based drug delivery systems, their ability to maximize the efficacy and selectivity of treatment regimens. With AI-driven innovation, polymer nanotechnology has the ability to improve patient treatment through highly personalized and potent medical options, beginning a new era of tailored medicine and new paths of drug innovation.