Search

The growth of deep learning technologies allows us to achieve higher accuracy in the classification of plant diseases, as well as in other domains. This research reveals the performance of several DL approaches, including custom convolutional neural networks (CNNs) and models which are pre-trained namely VGG16 and ResNet34, which were used for the recognition of diseases in plants that are depicted through the images. These models may obtain the necessary growing environment for training and assessing the models by using a publicly accessible dataset that includes pictures of both healthy and diseased plants, in total there are 14 unique plants used. The results of the experiment suggest that all the models combinedly gave 98.46% accuracy in the classification of diverse plant diseases. In addition to this, the paper discusses the hyperparameters like learning rate and optimizer choice that affect the model furthermore, the project discusses the methods involved in training deep learning models on GPU devices computationally speaking. Thereby, this project can be added to the field of agriculture vision by showing that deep learning methods are good for plant disease classification.

Agriculture is one of the major aspects of national development, yet plant diseases present a significant threat to agricultural production. In order to reduce associated losses and mitigate this threat, plant disease identification in early stages is very essential. Deep learning emerged as a significant advancement in the effective detection of various plant diseases as it can visualize and categorize the symptoms from the leaves of the plants This study examines the state-of-the-art deep learning methods for leafbased plant disease detection, with a particular emphasis on Convolutional Neural Networks (CNNs), Transfer Learning, and Ensemble Learning. In addition, a novel ensemble architecture is proposed, which combines a customized CNN architecture and a pretrained model called GoogLeNet. This proposed architecture can detect ten of the most prevalent plant diseases from the PlantVillage dataset, including tomato, apple, bell pepper, and potato. The suggested ensemble architecture achieves an astonishing 99.07% accuracy, demonstrating its potential to enhance plant disease diagnostics and promote sustainable agriculture

Objectives Maternal health-seeking behaviors are critical to improving maternal and child health in low-income countries. This study investigates associations between maternal decision-making input and their health-seeking behaviors in the first 1000-day period between pregnancy and a child's second birthday in Nepal. Methods We used data from a cross-sectional survey conducted in 2018 in 16 districts of Nepal. Among the 3648 households surveyed, 1910 mothers of a child 0 to 24 months with complete data were included for analyses. Logistic regression was used to examine associations between decision-making input and the utilization of antenatal, delivery and postnatal care services, and attendance at health mothers' group (HMG) meetings. We also used negative binomial regression to assess the relationship between her decision-making input and participation in growth monitoring and promotion (GMP) in the 6 months prior to the survey. For each relationship examined, we adjusted for clustering, as well as potentially confounding factors at individual and household levels. Results After adjusting for confounders, maternal decision-making input had a small but positive and significant association with receiving at least 4 antenatal care visits (OR = 1.09, 95% CI 1.02, 1.17), attendance at GMP in the 6 months prior to the survey (IRR = 1.02, 95% CI 1.00, 1.04), and HMG attendance (OR = 1.10, 95% CI 1.03, 1.17), but not with receiving at least 3 postnatal care visits or delivering in a health institution. Conclusions for Practice Our findings indicated that empowering women and mothers in household decision-making might warrant greater attention when developing future policies and programs in Nepal., Author(s): Zhongjie Zhang [sup.1] [sup.2] , Kenda Cunningham [sup.2] , Ramesh Prasad Adhikari [sup.2] , Subash Yogi [sup.2] [sup.3] , Shraddha Manandhar [sup.2] , Pooja Pandey Rana [sup.2] , Anne [...]

Soil is the loose surface material that covers land on which plants grow. It consists of a mixture of organic remains, clay, and rock particles, which gives it its uniqueness from place to place. Because of the uniqueness of soil, it has a high evidential value in the field of forensic science. In the present study, research has been conducted to check the range of variations in the soil collected from different crime-prone areas of Kottayam and Kollam districts of Kerala by physical, chemical, microscopic, and instrumental examination. In physical examination, soil colour, texture, consistency, and density were measured, and in chemical examination, pH and total soluble sulphate of the soil were measured. In instrumental examination, Heavy metal analysis was done by using Atomic Absorption Spectrometry (AAS), which helps to measure the amount of trace elements present in the soil. The study found that each soil has some significant variations that make it unique. In the field of forensic science, this can be highly helpful in determining the origin of soil by examining its colour, texture, structure, content, etc. [ABSTRACT FROM AUTHOR]