Search

The production rate of crops is significantly declining due to natural disasters, animal interventions and plant diseases. Internet of things (IoT) and wireless sensor networks are widely applied in crop field monitoring systems to observe the quality of each plant and the field. This work proposes IoT based crop field protection system (ICFPS) that monitors and protects the crop fields from animal intrusions. This proposed system uses ultrasonic sensors, hyperspectral cameras, voice recorded buzzers and other agriculture sensors to protect the entire crop field. This system uses numerous sensor nodes and cameras for gathering field objects (images and environmental objects). The proposed ICFPS creates deep learning techniques such as recurrent convolutional neural networks (RCNN) and recurrent generative adversarial neural networks (RGAN) for feature extraction, disease detection and field data monitoring practices. This proposed work develops a smart city‐based agriculture system using cognitive learning approaches. This proposed system analyses crop field data and provide automatic alerts regarding animal interferences and crop diseases. Moreover, the cognitive smart crop field system observes various field conditions which support for good production rate. In this system, sensors and camera‐enabled agriculture drones are coordinated with each other to collect the field data regularly. At the same time, the proposed work trains the RCNN and RGAN units using effective crop field datasets to attain realistic decisions within minimal time intervals. The experiment details and results show the proposed ICFPS works with 8%–10% of more classification accuracy than existing systems. [ABSTRACT FROM AUTHOR]

Electroencephalogram (EEG) signals are commonly used in analysing the brain activity. The EEG signals have small amplitude and hence, they are often affected by the artefacts. For the efficient processing, it is necessary to remove the artefacts from the EEG signals. This paper develops a technique through deep learning scheme for removing the artefacts present in the EEG signal. Initially, the EEG signals are pre-processed and provided to the feature extraction process, where the wavelet features are extracted from the signal by applying the wavelet transform. The extracted features are provided to the proposed classifier, namely deep-ConvLSTM, for removing the artefacts from the EEG signal. Here, the deep learner is trained based on the proposed Cat Swarm Fractional Calculus Optimisation (CSFCO) algorithm, which is the integration of Cat Swarm Optimisation (CSO) and Fractional Calculus (FC). Experimentation of the proposed technique is carried out by introducing artefacts, such as ECG, EMG, EOG and random noise on the EEG signal. Simulation results carried out on the proposed deep-ConvLSTM depict that the proposed framework has better performance than the comparative techniques with the values of 3888.362, 62.356, and 69.939 dB, for the MSE, RMSE, and SNR, respectively. [ABSTRACT FROM AUTHOR]

Electroencephalography (EEG) is an electrophysiological monitoring method to record electrical activity of the brain. EEG recording is highly susceptible to various forms and sources of noise, which present significant difficulties and challenges in analysis and interpretation of EEG data. Noise sources may consist of power line interference, base line noise, random body movements or respiration. A number of strategies are available to deal with noise effectively both at the time of EEG recording as well as during pre-processing of recorded data [8]. In this work, the authors have proposed FrFT based Barlett window to enhance the quality of EEG signal and the fidelity parameters like Signal to Noise Ratio (SNR), MSE, LSE, and sensitivity have to be computed and analyzed in a Matlab environment. [ABSTRACT FROM AUTHOR]