Unsupervised feature selection for sensor time-series in pervasive computing applications

Genetic Algorithm in Data Mining of Colorectal Images

There is currently no effective analytical method in colorectal image analysis, which leads to certain errors in colorectal image analysis. In order to improve the accuracy of colorectal imaging detection, this study used a genetic algorithm as the data mining algorithm and combined it with image processing technology to perform image analysis. At the same time, combined with the actual requirements of image detection, the gray theory model is used as the basic theory of image processing, and the image detection prediction model is constructed to predict the data. In addition, in order to study the effectiveness of the algorithm, the experiment is carried out to analyze the validity of the data of the study, and the predicted value is compared with the actual value. The research shows that the proposed algorithm has certain accuracy and can provide theoretical reference for subsequent related research.

Digital Twins in Solar Farms: An Approach through Time Series and Deep Learning

The generation of electricity through renewable energy sources increases every day, with solar energy being one of the fastest-growing. The emergence of information technologies such as Digital Twins (DT) in the field of the Internet of Things and Industry 4.0 allows a substantial development in automatic diagnostic systems. The objective of this work is to obtain the DT of a Photovoltaic Solar Farm (PVSF) with a deep-learning (DL) approach. To build such a DT, sensor-based time series are properly analyzed and processed. The resulting data are used to train a DL model (e.g., autoencoders) in order to detect anomalies of the physical system in its DT. Results show a reconstruction error around 0.1, a recall score of 0.92 and an Area Under Curve (AUC) of 0.97. Therefore, this paper demonstrates that the DT can reproduce the behavior as well as detect efficiently anomalies of the physical system.

Augmenting Recurrent Neural Networks Resilience by Dropout

This brief discusses the simple idea that dropout regularization can be used to efficiently induce resiliency to missing inputs at prediction time in a generic neural network. We show how the approach can be effective on tasks where imputation strategies often fail, namely, involving recurrent neural networks and scenarios where whole sequences of input observations are missing. The experimental analysis provides an assessment of the accuracy-resiliency tradeoff in multiple recurrent models, including reservoir computing methods, and comprising real-world ambient intelligence and biomedical time series.