DAV Institute of Engineering and Technology (DAVIET) is an elite engineering institute in Jalandhar City, established by the Dayanand Anglo-Vedic College Trust and Management Society offering undergraduate and graduate and doctoral courses. The DAV College Trust and Management Society is the largest non-government educational organization in India, managing a chain of about 700 institutions in India and abroad. The institute is located in the heart of city adjacent to DAV College, Jalandhar, on the left side of the Jalandhar-Amritsar National Highway.The institute is approved by AICTE All India Council for Technical Education and affiliated to IK Gujral Punjab Technical University, Jalandhar. It received ISO 9001:2000 certification in 2005 under joint accreditation of SGS Group and UKAS (United Kingdom Accreditation Service) Quality Management. It has received A NAAC Accreditation.
Agriculture is vital for global food security and economic stability. Technological advancements can significantly enhance productivity and sustainability. Mango, one of the world’s most cherished fruits, holds immense commercial and nutritional value. However, its cultivation is threatened by diseases such as Alternaria (causing dark leaf spots), Anthracnose (leading to black, sunken spots), Black Mould Rot (characterized by sooty fungal growth), Stem End Rot (causing decay from the stem end), and the crucial Healthy category. These diseases compromise fruit quality and yield, causing substantial economic losses. Manual diagnosis is subjective, time-consuming, and requires expertise, making it impractical for large-scale use. Artificial intelligence offers a transformative solution by enabling automated, accurate disease identification. In deep learning, conventional models such as Convolutional Neural Networks (CNNs) have a limited receptive field and struggle with long-range dependencies. Also, vision transformers are data-hungry and computationally exhaustive. Both of the above approaches lack focus on disease-specific features in complex agricultural settings. To address these gaps, we propose SAAEffNet, a synthetic-augmented attention-based EfficientNet deep learning model for classifying mango diseases. The model begins with a curated dataset, expanded using CycleGAN to generate high-fidelity synthetic images for enhanced diversity. In the previous pre-trained model, i.e., EfficientNetB3, we integrate the Convolutional Block Attention Module (CBAM) approach to refine features such as dark leaf spots, sunken spots, sooty fungal growth, etc. The model is trained with adaptive scheduling and early stopping. Our model achieves superior generalization, offering a robust tool for automated mango disease diagnosis. The model has undergone rigorous training and validation with a comprehensive dataset that includes images of both diseased and healthy mangoes, ensuring its effectiveness in accurately detecting and diagnosing mango health conditions. The results clearly illustrate our model’s exceptional performance, achieving remarkable metrics: accuracy 98.40
This study presents a theoretical investigation of second harmonic generation (SHG) resulting from the nonlinear interaction of a q-Gaussian laser beam with an anharmonic clustered plasma. The incident laser interacts with anharmonic atomic clusters, leading to the ionization of cluster atoms, and the formation of dense plasma spheres, commonly referred to as plasma balls. The laser exerts a nonlinear ponderomotive force on the cluster electrons, causing them to oscillate with a nonlinear velocity. This nonlinear motion leads to perturbations in the electron density within the cluster. Furthermore, the oscillatory velocity interacts with an externally applied wiggler magnetic field, giving rise to an additional ponderomotive force. This results in a nonlinear velocity component that contributes to the generation of a nonlinear current density at the second harmonic. As a consequence of this nonlinearity, second harmonic generation (SHG) is observed. To enhance its efficiency, various parameters are optimized. It is found that a q-Gaussian laser beam with a flattened top (characterized by the q parameter) leads to a broadened plasmon resonance, thereby improving the efficiency of harmonic generation. The anharmonicity of the clusters further enhances their nonlinear response. Additionally, the amplitude of the second harmonic increases under an external wiggler magnetic field and at higher laser intensity. The maximum normalized amplitude is obtained for q = 0.7 and a cluster radius of 10 nm.
In many countries, Liquefied Petroleum Gas (LPG) cylinders are popular for home cooking. But customers are unsure about how much gas remains in a cylinder, and often experience abrupt supply shortages. This report suggests a predictive Internet of Things (IoT) use case for weighing LPG usage with gas sensors and cloud analytics. The system combines a load cell sensor with a microcontroller for continuous measurement of cylinder weights. The microcontroller communicates with a cloud server and analytics algorithms which forecast usage based on the supply depletion rate and predict how many days the gas will last. The system's experimental evaluation corroborates a prediction accuracy of 92% when compared with the gas depletion time. The system help to eliminate the challenges of inconvenient unexpected shortages by enabling LPG gas depletion prediction. Once the gas supply falls below a determined value, the system will issue a notification to the users. The system is designed to be low-cost and easily scalable, making it a good option for smart home technologies.
Watermelon cultivation is frequently affected by foliar diseases which cause substantial yield losses if not identified at an early stage. In many agricultural regions, disease diagnosis still relies on expert visual inspection, which is often time-consuming and inaccessible in remote areas. Although deep learning–based approaches have shown promising performance for plant disease detection, many existing methods rely on computationally intensive convolutional neural networks, limiting their deployment on mobile and edge devices used in field conditions.This paper proposes a lightweight hybrid deep learning model, termed LHDL, which integrates EfficientNet-B0 and MobileNetV2 within a shared feature representation framework. The architecture retains only the feature extraction stages of both backbones and incorporates dropout regularization to improve generalization. The proposed model is evaluated on 6,000 watermelon leaf images across three classes: Downy Mildew, Mosaic Virus, and Healthy leaves.Observed results show that the proposed approach achieves a test accuracy of 96%. Grad-CAM visualizations further indicate that the model focuses on disease-relevant leaf regions rather than background artifacts. Owing to its compact architecture and low computational overhead, the proposed method is suitable for deployment on mobile and edge devices, offering a practical solution for plant disease monitoring in resource-constrained agricultural environments.
