Online Unsupervised Pattern Discovery in Speech Using Parallelization

Segmental dynamic time warping (DTW) has been demonstrated to be a useful technique for finding acoustic similarity scores between segments of two speech utterances. Due to its high computational requirements, it had to be computed in an offline manner, limiting the applications of the technique. In this paper, we present results of parallelization of this task by distributing the workload in either a static or dynamic way on an 8-processor cluster and discuss the trade-offs among different distribution schemes. We show that online unsupervised pattern discovery using segmental DTW is plausible with as low as 8 processors. This brings the task within reach of today's general purpose multi-core servers. We also show results on a 32-processor system, and discuss factors affecting scalability of our methods.

Online Handwriting Recognition of Tamil Script Using Fractal Geometry

We present a fractal coding method to recognize online handwritten Tamil characters and propose a novel technique to increase the efficiency in terms of time while coding and decoding. This technique exploits the redundancy in data, thereby achieving better compression and usage of lesser memory. It also reduces the encoding time and causes little distortion during reconstruction. Experiments have been conducted to use these fractal codes to classify the online handwritten Tamil characters from the IWFHR 2006 competition dataset. In one approach, we use fractal coding and decoding process. A recognition accuracy of 90% has been achieved by using DTW for distortion evaluation during classification and encoding processes as compared to 78% using nearest neighbor classifier. In other experiments, we use the fractal code, fractal dimensions and features derived from fractal codes as features in separate classifiers. While the fractal code is successful as a feature, the other two features are not able to capture the wide within-class variations.

Online Handwritten Kannada Word Recognizer with Unrestricted Vocabulary

In this paper, we propose a novel heuristic approach to segment recognizable symbols from online Kannada word data and perform recognition of the entire word. Two different estimates of first derivative are extracted from the preprocessed stroke groups and used as features for classification. Estimate 2 proved better resulting in 88% accuracy, which is 3% more than that achieved with estimate 1. Classification is performed by statistical dynamic space warping (SDSW) classifier which uses X, Y co-ordinates and their first derivatives as features. Classifier is trained with data from 40 writers. 295 classes are handled covering Kannada aksharas, with Kannada numerals, Indo-Arabic numerals, punctuations and other special symbols like $ and #. Classification accuracies obtained are 88% at the akshara level and 80% at the word level, which shows the scope for further improvement in segmentation algorithm

Unrestricted Kannada online handwritten akshara recognition using SDTW

In this paper, we present an unrestricted Kannada online handwritten character recognizer which is viable for real time applications. It handles Kannada and Indo-Arabic numerals, punctuation marks and special symbols like $, &, # etc, apart from all the aksharas of the Kannada script. The dataset used has handwriting of 69 people from four different locations, making the recognition writer independent. It was found that for the DTW classifier, using smoothed first derivatives as features, enhanced the performance to 89% as compared to preprocessed co-ordinates which gave 85%, but was too inefficient in terms of time. To overcome this, we used Statistical Dynamic Time Warping (SDTW) and achieved 46 times faster classification with comparable accuracy i.e. 88%, making it fast enough for practical applications. The accuracies reported are raw symbol recognition results from the classifier. Thus, there is good scope of improvement in actual applications. Where domain constraints such as fixed vocabulary, language models and post processing can be employed. A working demo is also available on tablet PC for recognition of Kannada words.

Prototype learning methods for online handwriting recognition

In this paper, we study different methods for prototype selection for recognizing handwritten characters of Tamil script. In the first method, cumulative pairwise- distances of the training samples of a given class are used to select prototypes. In the second method, cumulative distance to allographs of different orientation is used as a criterion to decide if the sample is representative of the group. The latter method is presumed to offset the possible orientation effect. This method still uses fixed number of prototypes for each of the classes. Finally, a prototype set growing algorithm is proposed, with a view to better model the differences in complexity of different character classes. The proposed algorithms are tested and compared for both writer independent and writer adaptation scenarios.

Time Series Classification for Online Tamil Handwritten Character Recognition – A Kernel Based Approach

In this paper, we consider the problem of time series classification. Using piecewise linear interpolation various novel kernels are obtained which can be used with Support vector machines for designing classifiers capable of deciding the class of a given time series. The approach is general and is applicable in many scenarios. We apply the method to the task of Online Tamil handwritten character recognition with promising results.

Novel algorithm for online voltage stability assessment based on feed forward neural network

This paper presents an artificial feed forward neural network (FFNN) approach for the assessment of power system voltage stability. A novel approach based on the input-output relation between real and reactive power, as well as voltage vectors for generators and load buses is used to train the neural net (NN). The input properties of the feed forward network are generated from offline training data with various simulated loading conditions using a conventional voltage stability algorithm based on the L-index. The neural network is trained for the L-index output as the target vector for each of the system loads. Two separate trained NN, corresponding to normal loading and contingency, are investigated on the 367 node practical power system network. The performance of the trained artificial neural network (ANN) is also investigated on the system under various voltage stability assessment conditions. As compared to the computationally intensive benchmark conventional software, near accurate results in the value of L-index and thus the voltage profile were obtained. Proposed algorithm is fast, robust and accurate and can be used online for predicting the L-indices of all the power system buses. The proposed ANN approach is also shown to be effective and computationally feasible in voltage stability assessment as well as potential enhancements within an overall energy management system in order to determining local and global stability indices

An Online Actor-Critic Algorithm with Function Approximation for Constrained Markov Decision Processes

We develop an online actor-critic reinforcement learning algorithm with function approximation for a problem of control under inequality constraints. We consider the long-run average cost Markov decision process (MDP) framework in which both the objective and the constraint functions are suitable policy-dependent long-run averages of certain sample path functions. The Lagrange multiplier method is used to handle the inequality constraints. We prove the asymptotic almost sure convergence of our algorithm to a locally optimal solution. We also provide the results of numerical experiments on a problem of routing in a multi-stage queueing network with constraints on long-run average queue lengths. We observe that our algorithm exhibits good performance on this setting and converges to a feasible point.

Online Computation of Hysteresis Boundary for Constant Switching Frequency Current-Error Space-Vector-Based Hysteresis Controller for VSI-Fed IM Drives

This paper proposes a current-error space-vector-based hysteresis controller with online computation of boundary for two-level inverter-fed induction motor (IM) drives. The proposed hysteresis controller has got all advantages of conventional current-error space-vector-based hysteresis controllers like quick transient response, simplicity, adjacent voltage vector switching, etc. Major advantage of the proposed controller-based voltage-source-inverters-fed drive is that phase voltage frequency spectrum produced is exactly similar to that of a constant switching frequency space-vector pulsewidth modulated (SVPWM) inverter. In this proposed hysteresis controller, stator voltages along alpha- and beta-axes are estimated during zero and active voltage vector periods using current errors along alpha- and beta-axes and steady-state model of IM. Online computation of hysteresis boundary is carried out using estimated stator voltages in the proposed hysteresis controller. The proposed scheme is simple and capable of taking inverter upto six-step-mode operation, if demanded by drive system. The proposed hysteresis-controller-based inverter-fed drive scheme is experimentally verified. The steady state and transient performance of the proposed scheme is extensively tested. The experimental results are giving constant frequency spectrum for phase voltage similar to that of constant frequency SVPWM inverter-fed drive.

Lexicon-free, novel segmentation of online handwritten indic words

Research in the field of recognizing unlimited vocabulary, online handwritten Indic words is still in its infancy. Most of the focus so far has been in the area of isolated character recognition. In the context of lexicon-free recognition of words, one of the primary issues to be addressed is that of segmentation. As a preliminary attempt, this paper proposes a novel script-independent, lexicon-free method for segmenting online handwritten words to their constituent symbols. Feedback strategies, inspired from neuroscience studies, are proposed for improving the segmentation. The segmentation strategy has been tested on an exhaustive set of 10000 Tamil words collected from a large number of writers. The results show that better segmentation improves the overall recognition performance of the handwriting system.

Language models for online handwritten Tamil word recognition

N-gram language models and lexicon-based word-recognition are popular methods in the literature to improve recognition accuracies of online and offline handwritten data. However, there are very few works that deal with application of these techniques on online Tamil handwritten data. In this paper, we explore methods of developing symbol-level language models and a lexicon from a large Tamil text corpus and their application to improving symbol and word recognition accuracies. On a test database of around 2000 words, we find that bigram language models improve symbol (3%) and word recognition (8%) accuracies and while lexicon methods offer much greater improvements (30%) in terms of word recognition, there is a large dependency on choosing the right lexicon. For comparison to lexicon and language model based methods, we have also explored re-evaluation techniques which involve the use of expert classifiers to improve symbol and word recognition accuracies.

Hybrid online non-negative matrix factorization for clustering of documents

When document corpus is very large, we often need to reduce the number of features. But it is not possible to apply conventional Non-negative Matrix Factorization(NMF) on billion by million matrix as the matrix may not fit in memory. Here we present novel Online NMF algorithm. Using Online NMF, we reduced original high-dimensional space to low-dimensional space. Then we cluster all the documents in reduced dimension using k-means algorithm. We experimentally show that by processing small subsets of documents we will be able to achieve good performance. The method proposed outperforms existing algorithms.