Moumita Saha

Rough set based multi-class fault diagnosis of induction motor using Hilbert Transform

The paper proposes a Rough-set Theory based methodology for multi-class fault diagnosis of induction motors using Hilbert Transform (HT). Depending on the motor condition the vibration signals are associated with unique predominant frequency components and instantaneous amplitudes. The axial vibration signals acquired through data acquisition system are split into different mono-components using Kaiser windowed FIR band pass filter. Statistical features of the Hilbert coefficients obtained from the mono-component signals are used as attributes for fault classification. Rough-set theory is successfully applied for dimensionality reduction of the attributes (by 67%) with almost no degradation of classification accuracy. The proposed Rough-set-Hilbert model eliminates the limitation of wavelet based fault diagnosis technique. The computational efficiency of the proposed classifiers increase due to selection of most relevant features, even at a low sampling frequency of 5120 Hz.

Fuzzy Clustering-Based Ensemble Approach to Predicting Indian Monsoon

Indian monsoon is an important climatic phenomenon and a global climatic marker. Both statistical and numerical prediction schemes for Indian monsoon have been widely studied in literature. Statistical schemes are mainly based on regression or neural networks. However, the variability of monsoon is significant over the years and a single model is often inadequate. Meteorologists revise their models on different years based on prevailing global climatic incidents like El-Nino. These indices often have degree of severity associated with them. In this paper, we cluster the monsoon years based on their fuzzy degree of associativity to these climatic event patterns. Next, we develop individual prediction models for the year clusters. A weighted ensemble of these individual models is used to obtain the final forecast. The proposed method performs competitively with existing forecast models.

Recurrent neural network based prediction of indian summer monsoon using global climatic predictors

Statistical models built on historical data are often found to be effective in forecasting Indian summer monsoon. However, linear models are found to be inadequate, and non-linear models like neural networks provide better performance. In this article, we study the use of recurrent neural network for long range forecast of Indian monsoon at lead of one season. Recurrent network model the sequential structure of the historical data yielding higher importance to near years than distant ones. A detailed study of the effectiveness of a set of fourteen global climatic predictors is carried out and Indian summer monsoon is predicted. The proposed recurrent network model gives mean absolute error in prediction as 3.3%, which is appreciable for forecasting complex monsoon phenomenon. Prediction skill of our model outperforms traditional multilayer neural network and it is also found to be superior than existing India Meteorology Department models.

Predictor Discovery for Early-late Indian Summer Monsoon Using Stacked Autoencoder

Indian summer monsoon has distinct behaviors in its early and late phase. The influencing climatic factors are also different. In this work we aim to predict the national rainfall in these phases. The predictors used by the forecast models are discovered using a stacked autoencoder deep neural network. A fitted regression tree is used as the forecast model. A superior accuracy to state of art method is achieved. We also observe that the late monsoon can be predicted with higher accuracy than early monsoon rainfall.

Co-Clustering Based Approach for Indian Monsoon Prediction☆

Abstract Prediction of Indian monsoon is a challenging task due to complex dynamics and variability over the years. Skills of statistical predictors that perform well in a set of years are not as good for others. In this paper, we attempt to identify a set of predictors that have high skills for a cluster of years. A co-clustering algorithm, which extracts groups of years, paired with good predictor sets for those years, is used for this purpose. Weighted ensemble of these predictors are used in final prediction. Results on past 65 years data show that the approach is competitive with state of art techniques.

Fault diagnosis of induction motor using CWT and rough-set theory

The paper proposes a Rough-Set CWT based algorithm for multi-class fault diagnosis of induction motor. Use of powerful signal processing technique like CWT drastically reduces the hardware (sensor) requirement of the diagnostic system. Only axial vibration signal is enough to classify seven different types of motor faults. Moreover, successful application of Rough Set theory has enabled to select most relevant CWT scales and corresponding coefficients. Thus, the inherent deficiencies and limitations of CWT are eliminated. Consequently, the computational efficiency has also improved to a great extend. With reduction of attributes by 65% the classification accuracy of the classifiers is very consistent even in presence of high level of noise and with a low frequency sampling frequency of 5120 Hz.

Dimensionality reduction using genetic algorithm and fuzzy-rough concepts

Real-world datasets are often vague and redundant, creating problem to take decision accurately. Very recently, Rough-set theory has been used successfully for dimensionality reduction but is applicable only on discrete dataset. Discretisation of data leads to information loss and may add inconsistency in the datasets. The paper aims at developing an algorithm using fuzzy-rough concept to overcome this situation. By this approach, dimensionality of the dataset has been reduced and using genetic algorithm, an optimal subset of attributes is obtained, sufficient to classify the objects. The proposed algorithm reduces dimensionality to a great extent without degrading the accuracy of classification and avoid of being trapped at local minima. Results are compared with the existing algorithms demonstrate compatible outcome.

Predictor-Year Subspace Clustering Based Ensemble Prediction of Indian Summer Monsoon

Forecasting the Indian summer monsoon is a challenging task due to its complex and nonlinear behavior. A large number of global climatic variables with varying interaction patterns over years influence monsoon. Various statistical and neural prediction models have been proposed for forecasting monsoon, but many of them fail to capture variability over years. The skill of predictor variables of monsoon also evolves over time. In this article, we propose a joint-clustering of monsoon years and predictors for understanding and predicting the monsoon. This is achieved by subspace clustering algorithm. It groups the years based on prevailing global climatic condition using statistical clustering technique and subsequently for each such group it identifies significant climatic predictor variables which assist in better prediction. Prediction model is designed to frame individual cluster using random forest of regression tree. Prediction of aggregate and regional monsoon is attempted. Mean absolute error of 5.2% is obtained for forecasting aggregate Indian summer monsoon. Errors in predicting the regional monsoons are also comparable in comparison to the high variation of regional precipitation. Proposed joint-clustering based ensemble model is observed to be superior to existing monsoon prediction models and it also surpasses general nonclustering based prediction models.

Climate Network Based Index Discovery for Prediction of Indian Monsoon

Identification of climatic indices are vital in essence of their ability to characterize different climatic events. We focus on discovery of climatic indices important for Indian summer monsoon from climatic parameters surface pressure and zonal wind velocity. We use climatic network based community detection approach for discovery of climatic indices. New indices depict better correlation with monsoon than existing indices. Regression and non-linear models are designed using newly discovered climatic indices for prediction of Indian summer monsoon. Models show superior accuracy to existing state of art models.

VLGAAC: Variable Length Genetic Algorithm Based Alternative Clustering

Complex and heterogeneous data sets can often be interpreted as having multiple clustering, each of which are valid but distinct from the others. Several algorithms involving multiple objective functions have been reported for such alternative clusterings. We propose a genetic algorithm based approach for obtaining valid but diverse clustering. A variable length genetic algorithm approach is used to enable varying number of clusters in each interpretation. A suitable method for population initialization and appropriate crossover and mutation operators are also used. Experimental results on benchmark data sets show that the method is comparable with related alternative clustering techniques.