The necessity of fault detection and notification has been exploited by the growth of renewable energy systems. The application of fault detection and notification is seen as an effective tool to monitor the performance of renewable energy systems. Looking at the importance of fault detection and notification integration into renewable energy systems based on the conducted literature review, this paper presents fault notification mechanism and implementation, which also consist of detection in an IoT-based photovoltaic panel monitoring and analysis system. The implemented fault notification detects the abnormalities of the voltage-current-temperature in the IoT-based photovoltaic panel monitoring and analysis system. The implemented fault notification in the IoT-based photovoltaic panel monitoring and analysis detects and notify any sort of abnormality of the voltage-current-temperature that is recorded at the photovoltaic panel. The implemented fault notification operates based on the threshold values of the voltage-current-temperature that has been programmed in the centralised controller. Hence, when any parameter input is below the preset threshold value, an email notification is sent to the centralised system to notify the maintenance team. Based on the implementation and obtained results, the implemented fault notification in the developed IoT-based photovoltaic panel monitoring and analysis system successfully performed and validated the purpose of the implementation.
Electroencephalogram (EEG) based classification has achieved a promising performance using deep learning models like Convolutional Neural Network. Various pre-processing strategies such as smoothing the EEG data or filtering are commonly used to pre-process the captured EEG signal before the subsequent feature extraction and classification while hyperparameters tuning might help to improve the classification performance. As well, the number of layers used in the CNN can affect the performance of the classification. In this paper, the number of layers needed for the CNN to classify the EEG data correctly, the effect of apply smoothing to pre-process the EEG signal for modern end-to-end CNN and the effect of enabling hyperparameters tuning during the training phase of CNN is investigated and analyzed. Two CNN models, namely Deep CNN with 5 layers and Shallow CNN with 1 layer, with convincing classification accuracy on motor execution classification as reported in the literature were chosen for this study. Both the CNN models are trained on EEG motor execution dataset with different training strategies and dataset pre-processing. Based on the obtained training and test classification accuracy, Shallow CNN trained with enabling hyper parameters tuning and without smoothing the EEG data achieved the best classification accuracy with average training accuracy of 99.9% and test accuracy of 96.87%. This indicates that CNN does not need to have many layers to correctly classify the motor execution data and the EEG data does not require smoothing.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.