DAV Institute of Engineering & Technology

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

Agriculture is the foundation of global food security and economic growth. Fruits are a vital source of essential nutrients for a healthy diet. Guava, with its distinct flavor, is not just a delicious tropical fruit but also holds immense economic significance. In developing nations, guavas stand out for their exceptional nutritional value, loaded with vitamin C, dietary fiber, and powerful antioxidants like lycopene. However, the viability of guava cultivation is under severe threat from destructive diseases. One of the most alarming is anthracnose, caused by Colletotrichum gloeosporioides, which creates deep, dark lesions on the fruit. Fruit fly infestations, particularly those caused by the genera Anastrepha and Bactrocera, pose a serious threat by causing internal decay through larval feeding. The importance of accurately classifying healthy fruit for quality assurance cannot be overstated. Relying on traditional manual detection methods, which depend on visual inspections, is not only time-consuming but also prone to errors and difficult to scale. We need efficient solutions to ensure timely and reliable detection for better outcomes. Artificial intelligence effectively bridges the gaps in disease identification through automated and objective methods powered by deep learning and computer vision. Convolutional neural networks (CNNs) excel at capturing intricate local patterns but often fall short in understanding the broader context. In contrast, Vision Transformers and Swin Transformers are adept at modeling long-range dependencies, yet their high computational demands can hinder performance on domain-specific datasets where precise local features are critical. To overcome these limitations, we introduce the Triple Attention Fusion Network (TAF-Net), a powerful tri-branch hybrid framework designed to seamlessly integrate EfficientNetB3 for comprehensive global semantic features, DenseNet121 for optimal dense feature reuse, and a lightweight CNN for precise fine-grained texture extraction. An advanced attention mechanism—combining channel attention, multi-head self-attention, spatial attention, and squeeze-and-excitation convolutional block attention module (SE-CBAM) refinement—effectively integrates a variety of features. Meanwhile, gradient-weighted class activation mapping++ (GradCAM++) produces explainable heatmaps that enhance transparency in decision-making, ensuring trust and clarity in the results. TAF-Net sets a new standard in disease detection, achieving an impressive 98.69

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.

Abstract The present study provides theoretical insight into third harmonic generation (THG) in atomic clusters. Because atomic clusters are much smaller than the laser wavelength, their free electrons undergo collective oscillations under the action of the incident laser field. The restoring force acting on these electrons varies nonlinearly with the electron excursion, causing anharmonicity in the electron dynamics. Simultaneously, the ponderomotive force of the intense laser pulse perturbs the electron density within the cluster, generating a nonlinear current at the third harmonic frequency that is responsible for THG. Furthermore, laser irradiation causes the clusters to expand, forming a transient nanoplasma with time-dependent density and resonance conditions. The combination of anharmonic electron motion, efficient energy absorption, and broadened surface plasmon resonance significantly enhances the nonlinear current, leading to efficient harmonic generation. In this context, the present study focuses on optimizing the laser, cluster, and plasma parameters to maximize THG efficiency.