Wyniki wyszukiwania - BazTech

Ograniczanie wyników

2 2020

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Sortuj według:

Ogranicz wyniki do:

Generalized modeling of the sludge volume index and suspended solids to monitor activated sludge bioflocculation using image analysis

Khan Muhammad Burhan, Nisar Humaira, Ng Choon Aun

Environment Protection Engineering

2020

Vol. 46, nr 3

17--37

The performance of an activated sludge wastewater treatment plant depends on bioflocculation that is monitored by physical measurements such as the sludge volume index (SVI) and mixed liquor suspended solids (MLSS). The estimation of SVI and MLSS has been proposed using image analysis based modeling which is time-efficient and valid for multiple plants operating in different states. The methodology includes the sequence of image acquisition using bright-field microscopy, a robust segmentation of flocs, partitioning of flocs based on different ranges of their equivalent diameters, extraction of morphological features, and modeling of SVI and MLSS using the features. It is proposed that bright-field microscopy at lower magnification to capture the flocs is sufficient to model SVI and MLSS. A robust approach for image segmentation is adopted by integrating state-of-the-art image segmentation algorithms. It is hypothesized that flocs in different ranges of equivalent diameter respond differently to the variation in the operating state. Hence, flocs and their respective image analysis features are categorized based on the range of equivalent diameter. Finally, stepwise regression is used for feature selection and model identification to explore the feasibility of generalization of models to multiple plants in different states regarding SVI and MLSS.

Comparison of different feature extraction methods for EEG-based emotion recognition

Nawaz Rab, Cheah Kit Hwa, Nisar Humaira, Yap Vooi Voon

Biocybernetics and Biomedical Engineering

2020

Vol. 40, no. 3

910--926

EEG-based emotion recognition is a challenging and active research area in affective computing. We used three-dimensional (arousal, valence and dominance) model of emotion to recognize the emotions induced by music videos. The participants watched a video (1 min long) while their EEG was recorded. The main objective of the study is to identify the features that can best discriminate the emotions. Power, entropy, fractal dimension, statistical features and wavelet energy are extracted from the EEG signals. The effects of these features are investigated and the best features are identified. The performance of the two feature selection methods, Relief based algorithm and principle component analysis (PCA), is compared. PCA is adopted because of its improved performance and the efficacies of the features are validated using support vector machine, K-nearest neighbors and decision tree classifiers. Our system achieves an overall best classification accuracy of 77.62%, 78.96% and 77.60% for valence, arousal and dominance respectively. Our results demonstrated that time-domain statistical characteristics of EEG signals can efficiently discriminate different emotional states. Also, the use of three-dimensional emotion model is able to classify similar emotions that were not correctly classified by two-dimensional model (e.g. anger and fear). The results of this study can be used to support the development of real-time EEG-based emotion recognition systems.