Category Archives: Uncategorized

Abstract-The worldwide economy relies vigorously upon horticulture, yet ordinary cultivating rehearses remember disadvantages like flightiness for the climate, ineffectual asset the board, and an absence of ongoing independent direction. The information driven brilliant cultivating application introduced in this examination advances farming administration by joining Enormous Information, Computerized reasoning (man-made intelligence), and Web of Things (IoT) sensors. The framework involves OpenCV for plant illness finding, TensorFlow and K-Closest Neighbors (KNN) for crop observing, and Choice Tree calculations for crop suggestion. Besides, LLaMA-fueled “Vigro Bot,” a chatbot, offers ranchers constant exhortation. The proposed procedure supports practical cultivating techniques, increments efficiency, and lessens asset squander.

Abstract-The pharmaceutical industry, precision and efficiency of tablet manufacturing are required to meet quality standards. In this project, the production process is being modernized by incorporating information and communication technology (IoT) into the production line. The machine performs auto-loading of all important steps including material feeding, compression and ejection and also IoT-powered sensors track parameters such as compression force, tablet weight, and humidity. In real-time, data is data is sent to a cloud-based server, enabling remote monitoring and predictive maintenance. This system guarantees of quality tablet, reduces downtime, and improves efficiency. The resulting machine is scalable and intuitive to use, making it suitable for both small- and large-scale production and brings Smart Manufacturing into the pharmaceutical industry.

Abstract-Mental illnesses are a serious concern in India where every seventh person suffers from mental health problems[1,5]—with women more affected than men. While the burden of perinatal mental illnesses grows, India lacks exclusive policies to address it. Although postpartum depression or blues are restricted to the period of six weeks post-delivery, the roots of this condition are traced right from pre-pregnancy through the antenatal period to the period of one year post-delivery. We took up a study amongst postpartum mothers about their self-assessment of this condition, their awareness and their strategies to combat postpartum anxiety and reinforce the importance of psychological well-being as a part of routine assessment during antenatal period, fortified in the postpartum phase.

Abstract-Our work proposes a classification architecture based on deep learning techniques, particularly convolutional and recurrent neural networks, for the classification of tomato diseases from digital images. More specifically, the objective is to classify leaves infected by a disease using supervised learning on a pre-labeled image dataset from PlantVillage. One of the main challenges of using deep learning, however, is the need for a very large amount of annotated data, which is not always available. Therefore, the objective of our study is to develop a specific hybrid architecture, CNN-LSTM (Convolutional Neural Networks – Long Short-Term Memory), capable of leveraging small (frugal) and relatively imbalanced datasets. To assess the relevance of this approach, we propose to compare it with deep learning algorithms frequently described in the literature. The proposed model achieved better classification performance in terms of validation Accuracy of 94,16%,

Abstract-Inflammatory Bowel Disease (IBD) is a long-term condition that presents as Ulcerative Colitis (UC), or Crohn’s Disease (CD) based on its manifestations. It is characterized by inflammation in the small intestine and colon, impacting millions of individuals globally. The development of IBD is influenced by genetic, environmental, and immunological factors. Various pro-inflammatory agents such as TNF-α, IL-1β, IL-6, IL-12, TGF-β, INF-γ, COX-2, and increased reactive oxygen species contribute to significant intestinal damage. Typical symptoms of IBD include fever, abdominal pain, vomiting, diarrhea, weight loss, blood in the stool, and an elevated risk of colon cancer. Changes in colonic motility linked to IBD can worsen discomfort and diarrhea. Prostaglandins, particularly elevated in IBD patients, may modulate these alterations. The enzyme Cyclooxygenase-2, responsible for producing prostaglandins, is targeted in IBD treatment. The role of PGE2 in the pathogenesis of IBD is intricate; while it can have anti-inflammatory effects by inhibiting pro-inflammatory cytokines, it can also act pro-inflammatory in IBD. Dysregulation of PGE2 production in IBD can lead to excess levels in inflamed gut tissue, perpetuating chronic inflammation by attracting immune cells, increasing blood vessel permeability, and causing tissue damage. The context-dependent role of PGE2 in IBD warrants further research for a comprehensive understanding. Modulating PGE2 levels or its signaling pathways may provide potential therapeutic options for managing IBD. This review specifically examines the involvement of Cyclooxygenases and coxibs in treating IBD.

Abstract-Urbanization and population growth have led to an exponential increase in vehicles, exacerbating parking-related challenges. Efficient parking management systems have become imperative to mitigate congestion, reduce fuel consumption, and minimize environmental impact. This paper reviews the integration of Internet of Things (IoT) technologies, computer vision, and Bluetooth Low Energy (BLE)-based indoor positioning systems for developing an efficient parking management system in urban areas. The proposed system is divided into three core modules: prediction of parking availability, real-time parking detection, and indoor navigation to guide users. This review evaluates existing approaches, highlights technological advancements, and discusses potential challenges in developing a proof of concept for the Indian context, emphasizing the cost- efficiency of the system.

Abstract-Fingerprint matching is a crucial task in forensic science, where the accurate and reliable identification of individuals is essential for criminal investigations. Traditional fingerprint matching algorithms often struggle with challenges such as occlusion, distortion, and partial prints. In this study, we propose a novel approach that leverages Hypergraph Neural Networks (HGNNs) to enhance the robustness and accuracy of fingerprint matching in forensic applications. By modeling fingerprint features as hypergraphs, we capture higher-order relationships between minutiae points and their spatial configurations, enabling more effective matching despite partial or degraded fingerprints. The HGNN framework integrates both local and global feature information, improving the system’s ability to recognize subtle and complex patterns in fingerprint data. Extensive experiments on benchmark fingerprint datasets demonstrate that our approach outperforms conventional methods in terms of matching accuracy and robustness to noise. The proposed HGNN-based model provides a promising solution for advancing forensic fingerprint identification systems, offering improved performance under challenging real-world conditions.

Abstract-The efficiency of recycling systems is crucial for promoting sustainability and reducing environmental impact. However, contamination in recycling streams remains a significant challenge, often leading to decreased recycling effectiveness and increased operational costs. This paper investigates the potential of machine learning (ML) to optimize sorting systems in recycling plants, aiming to minimize contamination and improve material recovery rates. We explore the application of various ML algorithms, including Convolutional Neural Networks (CNNs), Support Vector Machines (SVM), and Random Forests, for automating the detection and classification of contaminants in waste streams. By leveraging sensor data, image recognition, and real-time decision-making, our approach enhances sorting accuracy, reduces human error, and supports the efficient separation of recyclable materials. Experimental results from simulations and real-world case studies demonstrate that ML-driven sorting systems can achieve higher contamination reduction and sorting efficiency compared to traditional methods. This study highlights the promising role of machine learning in transforming recycling processes and proposes future directions for integrating AI technologies in waste management to create more sustainable and effective recycling solutions.

Abstract-The sacred syllable “Aum” (or “Om”) holds profound significance in Hinduism, Buddhism, Jainism, and other spiritual traditions. It is revered as the primordial sound of the universe, symbolizing the essence of ultimate reality, consciousness, and the interconnectedness of all existence. Explores the multifaceted dimensions of Aum, bridging its spiritual symbolism with modern scientific and technological paradigms, particularly in the realm of Artificial Intelligence (AI). By examining Aum’s representation of creation, preservation, and destruction, as well as its vibrational resonance with Earth’s natural frequencies and cosmic phenomena, Highlights the potential for harmonizing AI development with ethical principles, sustainability, and human well-being. Furthermore, it delves into the applications of Aum-inspired concepts in data science, neural networks, quantum computing, and AI-driven meditation tools, offering a holistic perspective on the convergence of ancient wisdom and cutting-edge technology.

Abstract-Composite materials have emerged as a critical area of research and development, rapidly gaining importance as structural materials. Among polymer applications, composite materials are poised for significant advancements. Aluminum matrix composites (AMCs) are particularly favored in automotive and aerospace industries due to their exceptional mechanical properties, such as a high strength-to-weight ratio, superior wear resistance, increased stiffness, enhanced fatigue resistance, controlled thermal expansion, and stability at elevated temperatures. Stir casting is widely recognized as an efficient and cost-effective method for AMC fabrication. This study investigates the mechanical behavior of composites made from pure aluminum reinforced with copper, fabricated using the stir casting method. The composites were produced with reinforcement levels of 0%, 2%, 4%, and 6%. Results indicate that the inclusion of copper particles significantly enhanced the hardness, tensile strength, and wear resistance of the composites, though an increase in copper content resulted in decreased density. These findings highlight the potential of copper as a reinforcement material for aluminum-based metal matrix composites, offering valuable insights for diverse engineering applications.