Search

The exponential growth of medical imaging datasets has necessitated robust methods for secure data transmission and accurate image analysis. Conventional methods often struggle with maintaining a balance between data security and processing efficiency, especially in sensitive domains like healthcare. The integration of cryptographic techniques with deep learning has shown promise in addressing these challenges. This work presents an AES-based cryptographic framework integrated with Deep Convolutional Neural Networks (Deep CNN) for enhanced medical document image processing and analysis. The AES encryption ensures secure transmission of sensitive medical data, safeguarding patient confidentiality. Once securely transmitted, the encrypted images are decrypted and analyzed using a Deep CNN model tailored for feature extraction and classification tasks in medical imaging datasets. The system was evaluated on publicly available datasets, including chest X-ray and brain MRI scans, comprising 10,000 images across various conditions. The proposed method achieved a classification accuracy of 98.7%, outperforming existing approaches by 3.4%. The encryption and decryption times were measured at 0.012 seconds and 0.015 seconds per image, ensuring minimal overhead during secure transmissions. Additionally, the system demonstrated an F1-score of 0.982 and a sensitivity of 97.8%, indicating its effectiveness in detecting anomalies in medical images. [ABSTRACT FROM AUTHOR]

Background: Amaranthus is the most popular and commercially cultivated leafy vegetable in the Southern part of India, especially Tamil Nadu and Kerala which is susceptible to a number of diseases. Among the different diseases affecting amaranth, foliar blight caused by Rhizoctonia solani Kuhn, is considered as the most serious disease in Kerala. Methods: A field experiment was taken up at Onattukara Regional Agricultural Research Station (O.R.A.R.S), Kayamkulam, Alappuzha, Kerala during December 2019 to February 2020 to assess the influence of dust and liquid formulations of Plant Growth Promoting Rhizobacteria (PGPR) mix I on growth, yield and disease incidence (Rhizoctonia leaf blight) in amaranthus. Result: The results of the study reveal that maximum number of leaves, number of branches per plant and yield were produced by the plants that were subjected to seedling root dip with 5% talc formulation followed by drenching with 5% talc solution at 30 DAT and 45 DAT. Regardless of talc or liquid formulation of PGPR mix I (2%) seedling dip followed by drenching at 15, 30 and 45 DAT provided the least disease incidence and disease severity in amaranthus at Onattukara condition. Hence use of PGPR mix I is a prerequisite for effective growth, yield and management of leaf blight of amaranthus at Onattukara. [ABSTRACT FROM AUTHOR]

Conservation agriculture (CA) is a sustainable option to adapt to climate change. Weed management is one of the most important challenges faced by CA. Information on CA in cropping systems involving elephant foot yam (Amorphophallus paeoniifolius (Dennst.) Nicolson), an important tuber crop, is lacking. Hence, this study aimed to determine the effect of CA in elephant foot yam on crop--weed dynamics, nutrient uptake, and soil microclimate. Field experiments were conducted in randomized block design over two seasons at ICAR-Central Tuber Crops Research Institute, Thiruvananthapuram, Kerala, India, in elephant foot yam (var. Gajendra) intercropped with banana (var. Robusta) with five treatments viz., conservation organic, conservation chemical, conventional chemical, existing conventional [package of practices (POP) as control], and existing organic package. The weed flora was dominated by broad-leaved weeds. By the fourth month, conservation chemical practice reduced the weed density by 58.8% and weed biomass by 55% over existing POP. The total biomass production and its partitioning to corms, uptake of nitrogen (N), phosphorus (P), and potassium (K), crop growth rate, corm bulking rate, and harvest index of elephant foot yam did not differ significantly under conservation or conventional practices but were higher in conservation chemical practice. The N, P, and K physiological efficiencies were higher in conventional chemical treatment. The soil microclimate was improved, with higher soil CO2 flux and soil moisture in conservation organic or organic plots. The study proved that conservation practices involving reduced tillage, residue retention, and use of herbicides was a viable alternative in banana+elephant foot yam system. [ABSTRACT FROM AUTHOR]

Alzheimer's disease (AD) early diagnosis plays a pivotal role in effective intervention and patient care. With limited and noisy medical imaging datasets, GANs are utilized to generate synthetic brain images, aiding in the augmentation of existing data. The selected classification algorithms are well-established in computer vision and have demonstrated efficacy in image classification tasks. The GAN is employed for data augmentation, creating synthetic images representative of AD-associated features. Subsequently, the augmented dataset is utilized to train and evaluate the performance of multiple classification algorithms, providing a comprehensive analysis of their effectiveness in AD detection. This research contributes to the field of Alzheimer's disease diagnosis by integrating GANs for data augmentation and evaluating the performance of ten diverse classification algorithms, offering insights into their suitability for early detection. In this study, we leverage Generative Adversarial Networks (GANs) for data augmentation in medical imaging, enhancing the quality and diversity of brain images associated with AD. Various classification algorithms, including AlexNet, GoogleNet, VGG 16, VGG 19, ResNet 18, ResNet 50, ResNet 101, ShuffleNet, MobileNet, and DenseNet 201, are employed for robust AD detection. Our experiments demonstrate improved classification accuracy and robustness due to GAN-based data augmentation. Among the classification algorithms, ResNet 50 and DenseNet 201 exhibit superior performance, showcasing their potential in accurate and reliable early AD diagnosis. [ABSTRACT FROM AUTHOR]

In recent years, image dehazing has gained significant attention in the field of computer vision and image processing due to its crucial role in enhancing visibility and improving visual perception. The presence of haze in images captured under adverse weather conditions or polluted environments poses a challenge to various computer vision applications, such as autonomous driving, surveillance, and satellite imagery. Traditional image dehazing methods often struggle to achieve optimal results, particularly in complex scenes with varying degrees of haze and intricate details. The need for a robust and efficient dehazing approach has become imperative for addressing real-world challenges in computer vision applications. Despite the advancements in traditional methods, a research gap exists in developing a comprehensive solution that can handle diverse atmospheric conditions and complex scenes effectively. The integration of deep learning techniques presents an opportunity to bridge this gap, leveraging the power of neural networks to learn and adapt to intricate patterns in hazy images. This research proposes a novel deep learningbased approach for image dehazing and visibility enhancement. A Convolutional Neural Network (CNN) architecture is designed to learn complex relationships between hazy and clear images, allowing the model to effectively remove haze and enhance visibility. The network is trained on a diverse dataset encompassing various atmospheric conditions and scene complexities to ensure generalization. Experimental results demonstrate the superior performance of the proposed deep learning approach compared to traditional methods. The model exhibits robustness in handling challenging scenarios, achieving significant improvements in image clarity, contrast, and overall visibility. The findings highlight the potential of deep learning in addressing the limitations of existing dehazing techniques. [ABSTRACT FROM AUTHOR]

Rice stem borers, which belong to the Pyralidae family are one of the most economically important rice pests, causing significant damage to the rice crop in Kerala. A survey was conducted during Kharif season of 2018 to study the species diversity, distribution and incidence of rice stem borers in south Kerala. Though many species are present in the rice ecosystems throughout Kerala, the predominant species identified in south Kerala are the yellow stem borer Scirpophaga incertulas (Walker) and white stem borerScirpophaga innotata (Walker). Out of these S. incertulas was observed to be present in all the three representative locations viz. Thiruvananthapuram, Onattukara and Kuttanad in south Kerala while S. innotata was observed only in Onattukara and Kuttanad. Thiruvananthapuram recorded the lowest population of S. incertulas andthe highest population was recorded in Onattukara. The highest population of S. innotata was also recorded in Onattukara and the lowest in Kuttanad. [ABSTRACT FROM AUTHOR]