UFFDFR: Undersampling framework with denoising, fuzzy c-means clustering, and representative sample selection for imbalanced data classification

Power transformers play an important role in electrical systems; being considered the core of electric power transmissions and distribution networks, the owners and users of these assets are increasingly concerned with adopting reliable, automated, and non-invasive techniques to monitor and diagnose their operating conditions. Thus, monitoring the conditions of power transformers has evolved, in the sense that a complete characterization of the conditions of oil–paper insulation can be achieved through dissolved gas analysis (DGA) and furan compounds analysis, since these analyses provide a lot of information about the phenomena that occur in power transformers. The Duval triangles and pentagons methods can be used with a high percentage of correct predictions compared to the known classical methods (key gases, International Electrotechnical Commission (IEC), Rogers, Doernenburg ratios), because, in addition to the six types of basic faults, they also identify four sub-types of thermal faults that provide important additional information for the appropriate corrective actions to be applied to the transformers. A new approach is presented based on the complementarity between the analysis of the gases dissolved in the transformer oil and the analysis of furan compounds, for the identification of the different faults, especially when there are multiple faults, by extending the diagnosis of the operating conditions of the power transformers, in terms of paper degradation. The implemented software system based on artificial neural networks was tested and validated in practice, with good results.

Complementary Analysis for DGA Based on Duval Methods and Furan Compounds Using Artificial Neural Networks

This work presents an approach to delay-based reservoir computing (RC) at the sensor level without input modulation. It employs a time-multiplexed bias to maintain transience while utilizing either an electrical signal or an environmental signal (such as acceleration) as an unmodulated input signal. The proposed approach enables RC carried out by sufficiently nonlinear sensory elements, as we demonstrate using a single electrostatically actuated microelectromechanical system (MEMS) device. The MEMS sensor can perform colocalized sensing and computing with fewer electronics than traditional RC elements at the RC input (such as analog-to-digital and digital-to-analog converters). The performance of the MEMS RC is evaluated experimentally using a simple classification task, in which the MEMS device differentiates between the profiles of two signal waveforms. The signal waveforms are chosen to be either electrical waveforms or acceleration waveforms. The classification accuracy of the presented MEMS RC scheme is found to be over 99%. Furthermore, the scheme is found to enable flexible virtual node probing rates, allowing for up to 4× slower probing rates, which relaxes the requirements on the system for reservoir signal sampling. Finally, our experiments show a noise-resistance capability for our MEMS RC scheme.

/pdf/colocalized-sensing-and-intelligent-computing-in-micro-137zzit894.pdf

Colocalized Sensing and Intelligent Computing in Micro-Sensors.

The class-imbalance problem has been widely distributed in various research fields. The larger the data scale and the higher the data imbalance, the more difficult the proper classification. For large-scale highly imbalanced data sets, the ensemble method based on under-sampling is one of the most competitive techniques among the existing techniques. However, it is susceptible to improperly sampling strategies, easy to lose the useful information of the majority class, and not easy to generalize the learning model. To overcome these limitations, we propose an equalization ensemble method (EASE) with two new schemes. First, we propose an equalization under-sampling scheme to generate a balanced data set for each base classifier, which can reduce the impact of class imbalance on the base classifiers; Second, we design a weighted integration scheme, where the G-mean scores obtained by base classifiers on the original imbalanced data set are used as the weights. These weights can not only make the better-performed base-classifiers dominate the final classification decision, but also adapt to a variety of imbalanced data sets with different scales while avoiding the occurrence of some extremely bad situations. Experimental results on three metrics show that EASE increases the diversity of base classifiers and outperforms twelve state-of-the-art methods on the imbalanced data sets with different scales. 

Equalization ensemble for large scale highly imbalanced data classification

Conventional classification algorithms have shown great success in balanced hyperspectral data classification. However, the imbalanced class distribution is a fundamental problem of hyperspectral data, and it is regarded as one of the great challenges in classification tasks. To solve this problem, a non-ANN based deep learning, namely SMOTE-Based Weighted Deep Rotation Forest (SMOTE-WDRoF) is proposed in this paper. First, the neighboring pixels of instances are introduced as the spatial information and balanced datasets are created by using the SMOTE algorithm. Second, these datasets are fed into the WDRoF model that consists of the rotation forest and the multi-level cascaded random forests. Specifically, the rotation forest is used to generate rotation feature vectors, which are input into the subsequent cascade forest. Furthermore, the output probability of each level and the original data are stacked as the dataset of the next level. And the sample weights are automatically adjusted according to the dynamic weight function constructed by the classification results of each level. Compared with the traditional deep learning approaches, the proposed method consumes much less training time. The experimental results on four public hyperspectral data demonstrate that the proposed method can get better performance than support vector machine, random forest, rotation forest, SMOTE combined rotation forest, convolutional neural network, and rotation-based deep forest in multiclass imbalance learning.

SMOTE-Based Weighted Deep Rotation Forest for the Imbalanced Hyperspectral Data Classification

Undersampling is a popular method to solve imbalanced classification problems However, sometimes it may remove too many majority samples which may lead to loss of informative samples In this article, the hashing-based undersampling ensemble (HUE) is proposed to deal with this problem by constructing diversified training subspaces for undersampling Samples in the majority class are divided into many subspaces by a hashing method Each subspace corresponds to a training subset which consists of most of the samples from this subspace and a few samples from surrounding subspaces These training subsets are used to train an ensemble of classification and regression tree classifiers with all minority class samples The proposed method is tested on 25 UCI datasets against state-of-the-art methods Experimental results show that the HUE outperforms other methods and yields good results on highly imbalanced datasets

Hashing-Based Undersampling Ensemble for Imbalanced Pattern Classification Problems.

Over the past few years, the Internet of Things (IoT) has been greatly developed with one instance being smart home devices gradually entering into people's lives. To maximize the impact of such deployments, home-based activity recognition is required to initially recognize behaviors within smart home environments and to use this information to provide better health and social care services. Activity recognition has the ability to recognize people's activities from the information about their interaction with the environment collected by sensors embedded within the home. In this paper, binary data collected by anonymous binary sensors such as pressure sensors, contact sensors, passive infrared sensors etc. are used to recognize activities. A radial basis function neural network (RBFNN) with localized stochastic-sensitive autoencoder (LiSSA) method is proposed for the purposes of home-based activity recognition. An autoencoder (AE) is introduced to extract useful features from the binary sensor data by converting binary inputs into continuous inputs to extract increased levels of hidden information. The generalization capability of the proposed method is enhanced by minimizing both the training error and the stochastic sensitivity measure in an attempt to improve the ability of the classifier to tolerate uncertainties in the sensor data. Four binary home-based activity recognition datasets including OrdonezA, OrdonezB, Ulster, and activities of daily living data from van Kasteren (vanKasterenADL) are used to evaluate the effectiveness of the proposed method. Compared with well-known benchmarking approaches including support vector machine (SVM), multilayer perceptron neural network (MLPNN), random forest and an RBFNN-based method, the proposed method yielded the best performance with 98.35%, 86.26%, 96.31%, 92.31% accuracy on four datasets, respectively.

https://www.mdpi.com/1424-8220/20/5/1479/pdf

Shichao Xu

Papers

Hashing-Based Undersampling Ensemble for Imbalanced Pattern Classification Problems.

Radial Basis Function Neural Network with Localized Stochastic-Sensitive Autoencoder for Home-Based Activity Recognition.