Search Results (5)

The article presents research on the influence of the type of UHF antenna and the type of machine learning algorithm on the effectiveness of classification of partial discharges (PD) occurring in the insulation system of a power transformer. For this purpose, four antennas specially adapted to be installed in the transformer tank (UHF disk sensor, UHF drain valve sensor, planar inverted F-type antenna, Hilbert curve fractal antenna) and a reference log-periodic antenna were used in laboratory tests. During the research, the main types of PD, typical for oil-paper insulation, were generated, i.e., PD in oil, PD in oil wedge, PD in gas bubbles, surface discharges, and creeping sparks. For the registered UHF PD pulses, nine features in the frequency domain and four features in the wavelet domain were extracted. Then, the PD classification process was carried out with the use of selected methods of supervised machine learning. The study investigated the influence of the number and type of feature on the obtained classification results gained with the following machine-learning methods: decision tree, support vector machine, Bayes method, k-nearest neighbor, linear discriminant, and ensemble machine. As a result of the works carried out, it was found that the highest accuracies are gathered for the feature representing peak frequency using a decision tree, reaching values, depending on the type of antenna, from 89.7% to 100%, with an average of 96.8%. In addition, it was found that the MRMR method reduces the number of features from 13 to 1 while maintaining very high effectiveness. The broadband log-periodic antenna ensured the highest average efficiency (100%) in the PD classification. In the case of the tested antennas adapted to work in an energy transformer tank, the highest defect-recognition efficiency is provided by the UHF disk sensor (99.3%), and the lowest (89.7%) is by the UHF drain valve sensor. Full article

The usage of wearable gadgets is growing in the cloud-based health monitoring systems. The signal compression, computational and power efficiencies play an imperative part in this scenario. In this context, we propose an efficient method for the diagnosis of cardiovascular diseases based on electrocardiogram (ECG) signals. The method combines multirate processing, wavelet decomposition and frequency content-based subband coefficient selection and machine learning techniques. Multirate processing and features selection is used to reduce the amount of information processed thus reducing the computational complexity of the proposed system relative to the equivalent fixed-rate solutions. Frequency content-dependent subband coefficient selection enhances the compression gain and reduces the transmission activity and computational cost of the post cloud-based classification. We have used MIT-BIH dataset for our experiments. To avoid overfitting and biasness, the performance of considered classifiers is studied by using five-fold cross validation (5CV) and a novel proposed partial blind protocol. The designed method achieves more than 12-fold computational gain while assuring an appropriate signal reconstruction. The compression gain is 13 times compared to fixed-rate counterparts and the highest classification accuracies are 97.06% and 92.08% for the 5CV and partial blind cases, respectively. Results suggest the feasibility of detecting cardiac arrhythmias using the proposed approach. Full article

This paper aims to examine whether there is inherent dynamic connectedness among coal market prices, new energy stock prices and carbon emission trading (CET) prices in China under time- and frequency-varying perspectives. For this purpose, we apply a novel wavelet method proposed by Aguiar-Conraria et al. (2018). Specifically, utilizing the single wavelet power spectrum, the multiple wavelet coherency, the partial wavelet coherency, also combined with the partial phase difference and the partial wavelet gains, this paper discovers the time-frequency interaction between three markets. The empirical results show that the connectedness between the CET market price and the coal price is frequency-varying and mainly occur in the lower and higher frequency bands, while the connectedness between the CET market price and the new energy stock price mainly happen in the middle and lower frequency bands. In the high-frequency domain, the CET market price is mainly affected by the coal price, while the CET market price is dominated by the new energy stock price in the middle frequency. These uncovered frequency-varying characteristics among these markets in this study could provide several implications. Main participants in these markets, such as polluting industries, governments and financial actors, should pay close attention to the connectedness under different frequencies, in order to realize their goal of the production, the policymaking, and the investment. Full article

Precise solar radiation forecasting is of great importance for solar energy utilization and its integration into the grid, but because of the daily solar radiation’s intrinsic non-stationary and nonlinearity, which is influenced by a lot of elements, single predicting models may have difficulty obtaining results with high accuracy. Therefore, this paper innovatively puts forward an original hybrid model that predicts solar radiation through extreme learning machine (ELM) optimized by the bat algorithm (BA) based on wavelet transform (WT) and principal component analysis (PCA). First, choose the meteorological variables on the basis of Pearson coefficient test, and WT will decompose historical solar radiation into two time series, which are de-noised signal and noise signal. In the approximate series, the lag phase of historical radiation is obtained by partial autocorrelation function (PACF). After that, use PCA to reduce the dimensions of the influencing factors, including meteorological variables and historical radiation. Finally, ELM is established to predict daily solar radiation, whose input weight and deviation thresholds gained optimization by BA, thus it is called BA-ELM henceforth. In view of the four distinct solar radiation series obtained by NASA, the empirical simulation explained the hybrid model’s validity and effectiveness compared to other primary methods. Full article

Tegillarca granosa samples contaminated artificially by three kinds of toxic heavy metals including zinc (Zn), cadmium (Cd), and lead (Pb) were attempted to be distinguished using laser-induced breakdown spectroscopy (LIBS) technology and pattern recognition methods in this study. The measured spectra were firstly processed by a wavelet transform algorithm (WTA), then the generated characteristic information was subsequently expressed by an information gain algorithm (IGA). As a result, 30 variables obtained were used as input variables for three classifiers: partial least square discriminant analysis (PLS-DA), support vector machine (SVM), and random forest (RF), among which the RF model exhibited the best performance, with 93.3% discrimination accuracy among those classifiers. Besides, the extracted characteristic information was used to reconstruct the original spectra by inverse WTA, and the corresponding attribution of the reconstructed spectra was then discussed. This work indicates that the healthy shellfish samples of Tegillarca granosa could be distinguished from the toxic heavy-metal-contaminated ones by pattern recognition analysis combined with LIBS technology, which only requires minimal pretreatments. Full article