Search

Diseases in plants accounts to major crop losses which affects the economy of farmers and in turn the country. Recent advancements in technologies like Internet of Things and Machine learning has led to the development of automated systems for crucial applications. This paper focuses on developing such a system for agricultural application mainly for early detection of diseases in plant leaves and provides solutions to the farmers. The main contribution is the novel pixel replacement-based segmentation and double feature extraction techniques for enhancing classification process. Classification is done using Support vector machine classifier and the developed system was validated using pomegranate leaves. The system is evaluated using performance metrics such as detection accuracy and classification accuracy.

Agriculture is one of the primary sources of Indian economy as majority of the population depends on agriculture. Early detection of plant stress functions an evident role in smart agriculture. In order to improve the quality and quantity of food crop and to prevent the damage caused to the plant, it is necessary to detect the stress in plant using environmental parameters. Visual sensor along with environmental sensors helps to identify the colour change in leaves of the plant at the initial stage thereby reducing the damage. An efficient plant stress detection framework is proposed which is automated for ease of use for farmers. The framework makes use of camera for capturing the images of the leaves in the field and machine learning for classifying the leaves as healthy or unhealthy. Support vector machine algorithm makes use of the features extracted from the leaves for training the system and the input features are alone transmitted to the cloud. The agricultural consultant at the other end retrieves the features and the stress is detected with the help of classification. Gray level co-occurrence matrix textures are used for extracting the features from the healthy and unhealthy leaves. Metrics such as Accuracy in classification and stress detection is validated in the proposed system.

This paper focuses on the modified design, and implementations of single ended and differential mode low noise amplifiers targeted for wireless sensor network applications. Key issues in wireless sensor network receivers are discussed and the existing circuit level implementations of low noise amplifiers are compared. Emphasis was placed on observing device reliability constraints at low power to maximize the life time of the wireless sensor nodes. The proposed single ended and the differential LNA can operate at 2.4 GHz and dissipates a power of 22.6 and 30.3 μ W , respectively, from a 1 V supply. The noise performance at input, output and the frequency response is presented.