https://irju.jdvu.ac.in/jspui/handle/123456789/89 Sat, 07 Nov 2026 17:57:06 GMT 2026-11-07T17:57:06Z https://irju.jdvu.ac.in/jspui/handle/123456789/10740 Title: Advanced automated recognition: a true integration of ai and nature for multifaceted image analysis Authors: Samanta, Bidisha Abstract: Image classification using deep neural networks is a powerful technique in the field of computer vision, enabling machines to understand and categorize visual data with high accuracy. Deep neural networks, particularly convolutional neural networks (CNNs), have revolutionized image classification tasks due to their ability to automatically learn hierarchical features from raw pixel data. This thesis mainly focuses on automated categorization of diseased and healthy leaf samples, distinct foliage species, estimation of fruits and vegetables freshness as well as automated shoreline detection and curation of new databases for machine printed and handwritten documents classification in Bengali language. The export of fresh fruits plays a pivotal role in both national and international economies, providing a significant source of income for countless farmers. Ensuring the freshness and edibility of these fruits is crucial for maintaining quality during export and minimizing financial losses. Recent advances in deep neural networks have led to their successful application in non-invasive image classification tasks, including the quality assessment of various plant parts such as leaves, fruits, and vegetables. These methods are not only more time-efficient but also cost-effective. However, a major challenge faced by researchers in developing these automated systems is the scarcity of appropriate databases necessary for training. Addressing this gap, I have developed a new database called “FruityHub”, which includes 1786 image frames of eight different fruit types: Dragon Fruits, Net Melons, Strawberries, Star Fruit, Zucchini, Mango, Pineapple, and Plum. Each fruit category in FruityHub is classified into three conditions: Fresh, Damaged, and Severely Damaged, aiding in the automated assessment of fruit quality based on characteristics like skin colour, texture, and shape. I have also evaluated the effectiveness of this database using fourteen deep neural network models, including AlexNet, Vgg16, ResNet152, MobileNetv2, ShuffleNetv2, SqueezeNet, InceptionV3, InceptionResNetv2, DenseNet121, NasNetLarge, NasNetMobile, GhostNetv2, EfficientNetB7, and Xception. The performance of these models was assessed using metrics such as Test Accuracy, Recall, Precision, and F1 Score. The burgeoning field of automated leaf classification has made significant strides with the advent of advanced deep neural technologies. My latest research introduces "GreenMedNet," a groundbreaking and computationally efficient deep neural network tailored specifically for the classification of insulin leaves into diseased and healthy categories, given their intrinsic hyperglycemic properties. This study marks a pivotal advancement with the development of the "GreenMedNet" architecture, which ingeniously captures multiscale contextual information while maintaining a streamlined parameter count. A cornerstone of my innovation lies in the creation of a novel activation function that merges the advantages of existing functions in a scalable manner, effectively safeguarding the network against common pitfalls like vanishing gradients and the dying ReLU issue. This enhancement not only preserves the non-linear dynamics essential for deep learning but also optimizes the selection of hyperparameters to boost the overall efficiency of the network. Supporting my research is the meticulously curated "Nature’s Diabetes Helpers: Insulin Leaves Repository." This custom database comprises 600 meticulously balanced images, split evenly between healthy and damaged classes, providing a robust foundation for training, and testing my model. "GreenMedNet" has demonstrated remarkable effectiveness, achieving a Test Accuracy of 99.17%, complemented by high scores in Precision, Recall, and F1 metrics. This impressive performance not only confirms the network's robustness but also highlights its superiority over existing models, establishing "GreenMedNet" as a significant contribution to the field of leaf classification technology. In the dynamic field of vegetable quality assessment, innovative automated technologies have revolutionized the way I evaluate freshness. These systems, which analyze external morphology, texture, and colour, stand out as both efficient and economical solutions. They play an instrumental role in ensuring that only the finest vegetables reach both local and international markets, thereby substantially enhancing the revenue streams of the global food industry. The significance of this technological advancement has not gone unnoticed in the research community. Enthusiastic about its potential, scientists have been keen to harness advanced deep learning technologies to accurately categorize vegetables into distinct quality classes. However, the success of these cutting-edge methods largely depends on the availability and quality of training and validation databases. This presents a notable challenge, as there is a pressing need for more comprehensive and representative datasets to refine and validate these automated systems effectively. Optical Character Recognition (OCR) plays a critical role in the digitization of documents, making textual content searchable and editable, thus streamlining workflows, and extracting actionable insights. It not only enhances accessibility for those with visual impairments but also underpins e-government initiatives and optimizes document management systems. OCR technology significantly enriches customer interaction platforms, assists in adhering to financial and legal regulations, and synchronizes seamlessly with advanced technologies such as Computer Vision, Natural Language Processing, and Machine Learning. As a cornerstone technology, OCR transforms analog documents into valuable digital formats, promoting greater operational efficiency, accuracy, and accessibility across various industries in today's digital landscape. In the realm of OCR applications, the distinction between handwritten and machine-printed texts is critical, necessitating tailored processing techniques for each. Handwritten texts require sophisticated algorithms, often based on neural networks with Long Short-Term Memory (LSTM) layers, to interpret diverse and complex writing styles. Conversely, machine-printed texts can be processed using relatively straightforward algorithms such as template matching due to their uniformity. Adaptive pre-processing strategies are essential, with techniques for handwritten texts focusing on normalizing writing styles and managing cursive scripts, while machine-printed texts may involve binarization and noise reduction. For feature extraction, handwritten OCR systems analyze characteristics like loops and slant angles, whereas machine-printed OCR systems concentrate on geometric properties. The selection of training data also varies significantly; handwritten text recognition systems benefit from datasets rich in writing style variability, whereas machine-printed systems utilize more standardized font collections. By employing document-type specific processing and adaptive learning techniques, OCR systems can significantly enhance both accuracy and processing efficiency, thereby optimizing the overall performance of OCR technologies. Automated prediction and assessment of coastline changes using advanced technologies like deep learning networks and machine learning methods are gaining significant attention for their reliability and efficiency. This research area is crucial in today's context, playing a vital role in sustainable coastal development, environmental conservation, disaster risk mitigation, and decision-making impacting both human communities and coastal ecosystems. While automated shoreline change prediction has been proposed by some, it remains relatively underexplored. My study aims to fill this gap by conducting a comprehensive analysis of existing methods, covering various aspects such as data sources and methodological approaches. By delving deeply into this subject, My work seeks to provide valuable insights to researchers and offer solutions to unexplored territories within this domain. The works presented in this thesis offer several noteworthy contributions, including: FruityHub: A diverse collection of fruits created for edibility estimation. GreenMedNet: A computationally inexpensive hyperparameter optimised for efficient classification of healthy and damaged insulin leaves. Natural vegetable progression evaluation through new developed database (VDBB). Nature’s Best vs. Bruised: A Veggie Evaluation BengaliPrintDB: A Repository of Machine-Printed Bengali Documents In-depth survey of automated shoreline alteration identification methods This thesis addresses three critical problems selected for their profound real-world significance. Through detailed analysis of statistical data from reputable sources, the practical importance of each topic is thoroughly explored. Additionally, an extensive literature review is provided for each problem, highlighting deficiencies in existing approaches and proposing novel methods to address these shortcomings. Mon, 01 Jan 2024 00:00:00 GMT https://irju.jdvu.ac.in/jspui/handle/123456789/10740 2024-01-01T00:00:00Z https://irju.jdvu.ac.in/jspui/handle/123456789/10739 Title: A study on geriatric care using IOT Authors: Ansar Ali Mon, 01 Jan 2024 00:00:00 GMT https://irju.jdvu.ac.in/jspui/handle/123456789/10739 2024-01-01T00:00:00Z https://irju.jdvu.ac.in/jspui/handle/123456789/10738 Title: Intelligent techniques for economic time-series Authors: Das, Purnima Abstract: Prediction of a non-stationary time-series is hard as the frequency components and their amplitudes in the series vary randomly over time. This paper proposes a two-step approach for prediction of such non- stationary time-series. The first step employs Taylor series to approximately predict the next time-point value in the series from its current and last two preceding sample values. The Taylor series-based prediction, however, presumes that the time-series is locally stationary. The second step includes reinforcement learning inspired error correction in the Taylor series-based prediction results using an adaptive probabilistic learning matrix. The said matrix is used to encode the scale factors (error coefficients) in the learning equation from an estimate of errors incurred in Taylor series-based prediction. The learning is performed by a reward/penalty type adaptation of conditional probabilities involved in the probabilistic learning matrix. On convergence of the matrix, the saved probabilities are used to determine the appropriate scale factor needed to scale the estimated error in Taylor series-based prediction with an aim to rectify the prediction result by adding the scaled error to the predicted time-series value. Experiments undertaken confirm that the proposed technique outperforms the state-of-the-art prediction models by a significant margin of prediction accuracy. Mon, 01 Jan 2024 00:00:00 GMT https://irju.jdvu.ac.in/jspui/handle/123456789/10738 2024-01-01T00:00:00Z https://irju.jdvu.ac.in/jspui/handle/123456789/10737 Title: Brain-computer interface for position control of a neuro-prosthetic artificial limb Authors: Pathak, Deblina Abstract: Brain Computer Interface (BCI), sometimes called a Brain Machine interface (BMI), is a direct communication link between the brain's electrical activity and an external device, most commonly a computer or robotic limb, bypassing traditional neuromuscular routes. BCIs are often directed at researching, mapping, assisting, augmenting, or repairing human cognitive or sensory-motor functions. They are often conceptualized as a human–machine interface that skips the intermediary of moving body parts although they also raise the possibility of erasing the distinction between brain and machine. Brain-Computer Interface (BCI) technology has emerged as a revolutionary approach for controlling neuroprosthetic devices, offering a new lease of functional independence to individuals with severe motor impairments. Sophisticated signal processing and machine learning algorithms decode these signals into precise control commands, facilitating intuitive and responsive prosthetic movement. Current research focuses on enhancing the accuracy, reliability, and usability of BCI-controlled neuroprosthetics. Innovations in high-resolution signal acquisition, noise reduction, and real-time processing are critical to improving system performance. Integrating sensory feedback mechanisms, such as haptic feedback, is a promising area of development, aimed at providing users with real-time information about the prosthetic's interaction with the environment. This feedback is crucial for tasks requiring fine motor control and can significantly enhance the user experience by making the control of the prosthetic arm more natural and intuitive. Personalization and adaptability of BCI systems are also key research areas, with adaptive algorithms that learn and adjust to the user’s unique neural patterns over time. The development of wireless and wearable BCI devices aims to increase mobility and ease of use, making these systems more practical for everyday applications. Additionally, interdisciplinary collaboration among neuroscientists, engineers, and clinicians is essential to advance the field, along with addressing ethical and regulatory considerations related to data privacy, user consent, and long-term impacts. This Thesis presents a 2-loop architecture of brain-actuated position control system of a robot arm, realized with a Takagi-Sugeno type fuzzy speed modulator placed in the outer loop and a traditional speed-controller placed in the inner loop. Chapter 1 provides a detailed review on the Brain-Computer Interface (BCI) technology. It begins with a classification BCI-based controllers, and gradually explores different types of standard BCI system along with their control policies. The different modules of a closed-loop BCI are discussed in brief with their current state-of-the-art approaches. It also provides an outline of the electroencephalography (EEG)-based brain signals commonly used in closed-loop BCI-based robot control tasks. Chapter 2 provides a 2-loop position control scheme is proposed here with an outer loop for position control of the motor and the inner loop for speed-setting of a robotic limb. Three distinct models of brain-actuated speed-setting with possible control policies and stability analysis are presented. The analysis reveals that Takagi–Sugeno type fuzzy control yields the best results. Additionally, cognitive load is also reduced significantly as the user needs to generate error-related potential once only to identify the position of the targeted object he needs to translate. Traditional BCI-based position control schemes utilize acquired motor imagery signals of the subject for motor actuation and error-related potential signals to detect positional overshoots. The positional overshoot results in steady-state positional error. Current BCI research attempts to reduce steady-state errors at the cost of high cognitive load of the subjects. The motivation here is to reduce the steady-state positional error without enhancing cognitive load of the subjects. Chapter 3 provides the designing of Brain-Actuated Speed Modulator along with the corresponding Simulink Models and plots. Finally, Chapter 4 ends with a brief conclusion along with future scope and innovations. The future scope of BCI-based neuroprosthetic control is vast, with the potential to significantly enhance the quality of life for individuals with disabilities. By continuing to refine the technology and addressing current challenges, BCIs can offer more precise, intuitive, and accessible solutions for neuroprosthetic control, paving the way for broader adoption and improved outcomes in clinical and everyday settings. Mon, 01 Jan 2024 00:00:00 GMT https://irju.jdvu.ac.in/jspui/handle/123456789/10737 2024-01-01T00:00:00Z