Forecasting Model of Silicon Content in Molten Iron Using Wavelet Decomposition and Artificial Neural Networks

Silicon content forecasting models have been requested by the operational team to anticipate necessary actions during the blast furnace operation when producing molten iron, to control the quality of the product and reduce costs. This paper proposed a new algorithm to perform the silicon content time series up to 8 h ahead, immediately after the molten iron chemical analysis is delivered by the laboratory. Due to the delay of the laboratory when delivering the silicon content measurement, the proposed algorithm considers a minimum useful forecasting horizon of 3 h ahead. In a first step, it decomposes the silicon content time series into different subseries using the Maximal Overlap Discrete Wavelet Packet Transform (MODWPT). Next, all subseries forecasts were determined through Nonlinear Autoregressive (NAR) networks, and finally, these forecasts were summed to furnish the long-term forecast of silicon content. Using data from a real industry, we showed that the prediction error was within an acceptable range according to the blast furnace technical team.

Use of Paraconsistent Feature Engineering to support the Long Term Feature choice for Speaker Verification

The state-of-art models for speech synthesis and voice conversion can generate synthetic speech perceptually indistinguishable from human speech, and speaker verification is crucial to prevent breaches. The building feature that best distinguishes genuine speech between spoof attacks is an open research subject. We used the baseline ASVSpoof2017, Transfer Learning (TL) set, and Symlet and Daubechies Discrete Wavelet Packet Transform (DWPT) for this investigation. To qualitatively assess the features, we used Paraconsistent Feature Engineering (PFE). Our experiments pointed out that for the use of more robust classifiers, the best choice would be the AlexNet method, while in terms of classification regarding the Equal Error Rate metric, the best suggestion would be Daubechies filter support 21. Finally, our findings indicate that Symlet filter support 17 as the most promising feature, which is evidence that PFE is a useful tool and contributes to feature selection.

Power Quality Classification of disturbances using Discrete Wavelet Packet Transform (DWPT) with Adaptive Neuro-Fuzzy System

With the development of the technologies, the demand for good quality of electric power is increasing day by day. In Distributed Generation Systems (DGs), the quality of power can cause serious problems such as sensitive equipment's malfunction, the temperature riseof machines. Therefore, detection of power quality events in the power system is more important to take further actions. The existing power quality events classification methods have high computational time with low accuracy. In order to overcome this problem, this paper presents Discrete Packet Wavelet Transform-Kalman filter based Adaptive Neuro-Fuzzy approach for identification and classification of PQ events. The proposed method classifies the events with better classification accuracy, less convergence time and low in error prediction. The results show that the proposed method has better performance compared with the existing classification methods. The proposed method is Implemented and tested using MATLAB and it provides more accuracy when compared to the existing systems such as Discrete Wavelet Transform based Fuzzy Logic Adaptive System and Fourier Transform based Artificial neural networks etc..

Automatic EEG-based Alertness Classification using Sparse Representation and Dictionary Learning

Automation of human alertness identification has been widely investigated in recent decades. Many applications can benefit from automatic alertness state identification, such as driver fatigue detection, monotonous task workers' vigilance detection and sleep studies in the medical field. Many researchers have tried to exploit different types of behavioural aspects in vigilance detection, such as eye movement, head position and facial expression. On the other hand, some biomedical signals like ECG, EEG and heart rhythm are also exploited; however, there is a consensus of the superiority of EEG signal in alertness classification due to its close relation with different human vigilant states. In this paper, we propose an automatic method for vigilance detection using a single EEG channel along with sparse representation and dictionary learning. We used Discrete Wavelet Packet Transform to extract the features related to different human vigilance states. We use well-known other classifiers to compare the performance of our proposed method. Results of classification with sparse representation and dictionary learning produced better accuracy results than the other methods.