Extension of a Kernel-Based Classifier for Discriminative Spoken Keyword Spotting

A keyword spotter is considered as a binary classifier that separates a class of utterances containing a target keyword from utterances without the keyword. These two classes are not inherently linearly separable. Thus, linear classifiers are not completely suitable for such cases. In this paper, we extend a kernel-based classification approach to separate the mentioned two non-linearly separable classes so that the area under the Receiver/Relative Operating Characteristic (ROC) curve (the most common measure for keyword spotter evaluation) is maximized. We evaluated the proposed keyword spotter under different experimental conditions on TIMIT database. The results indicate that, in false alarm per keyword per hour smaller than two, the true detection rate of the proposed kernel-based classification approach is about 15 % greater than that of the linear classifiers exploited in previous researches. Additionally, area under the ROC curve (AUC) of the proposed method is 1 % higher than AUC of the linear classifiers that is significant due to confidence levels 80 and 95 % obtained by t-test and F-test evaluations, respectively. In addition, we evaluated the proposed method in different noisy conditions. The results indicate that the proposed method show a good robustness in noisy conditions.     

An improved feature transformation method using mutual information

The feature transformation is a very important step in pattern recognition systems. A feature transformation matrix can be obtained using different criteria such as discrimination between classes or feature independence or mutual information between features and classes. The obtained matrix can also be used for feature reduction. In this paper, we propose a new method for finding a feature transformation-based on Mutual Information (MI). For this purpose, we suppose that the Probability Density Function (PDF) of features in classes is Gaussian, and then we use the gradient ascent to maximize the mutual information between features and classes. Experimental results show that the proposed MI projection consistently outperforms other methods for a variety of cases. In the UCI Glass database we improve the classification accuracy up to 7.95 %. Besides, the improvement of phoneme recognition rate is 3.55 % on TIMIT.     

Numerical analysis of restitution coefficient,rotational speed and particle size effects on the hydrodynamics of particles in a rotating drum

Hydrodynamic behavior of two dimensional horizontal rotating drum was studied by using finite volume method and granular kinetic theory. In this work, the effects of the different parameters such as rotation speed, restitution coefficient and particle size on the hydrodynamic and especially on the granular temperature of particles were investigated. At first, the results of present work were verified with previous experimental results. Packing limit of 0.6 and restitution coefficient of 0.95 with Gidaspow inter-phase momentum coefficient showed the good agreement with experimental works. It is found that by increasing the restitution coefficient, the granular temperature at different depth of bed increased and affected the hydrodynamic behavior of the bed. Also, particle size and rotation speed directly changed the granular temperature. Moreover, augmentation of the rotation speed leads to increasing the repose angle which caused better mixing of bed, granular temperature rising and consequently particle velocity alteration in the bed.     

RAID-RMS: A fault tolerant stripped mirroring RAID architecture for distributed systems

Disk arrays, or RAIDs, have become the solution to increase the capacity, bandwidth and reliability of most storage systems. In spite of its high redundancy level, disk mirroring is a popular RAID paradigm, because replicating data also doubles the bandwidth available for processing read requests, improves the reliability and achieves fault tolerance. In this paper, we present a new RAID architecture called RAID-RMS in which a special hybrid mechanism is used to map the data blocks to the cluster. The main idea behind the proposed algorithm is to combine the data block striping and disk mirroring technique with a data block rotation. The resulting architecture improves the parallelism reliability and efficiency of the RAID array. We show that the proposed architecture is able to serve many more disk requests compared to the other mirroring-based architectures. We also argue that a more balanced disk load is attained by the given architecture, especially when there are some disk failures.     

Identification of the Groundwater Potential Recharge Zones Using MCDM Models: Full Consistency Method (FUCOM), Best Worst Method (BWM) and Analytic Hierarchy Process (AHP)

Water Resources Management - In arid and semi-arid regions, groundwater is considered being the most available natural resources for different water use. However, it is being limited in...     

Crop and land cover classification in Iran using Landsat 7 imagery

Remote sensing provides one way of obtaining more accurate information on total cropped area and crop types in irrigated areas. The technique is particularly well suited to arid and semi‐arid areas where almost all vegetative growth is associated with irrigation. In order to obtain more information with regard to crop patterns in the irrigated areas in the Zayandeh Rud basin, a classification analysis was made of the Landsat 7 image of 2 July 2000. The target of the classification was to primarily focus on the agricultural land use. The date of the image fell in the transition period where the first crops were harvested and many fields were being prepared for the second crop. The image has therefore captured an instantaneous picture of a system generally in transition from the first to the second crop, but with significant differences from system to system, both with respect to crop types and agricultural cycles. The overall accuracy of image registration was about 30 m (one pixel). Fieldwork was conducted on various occasions in August–October 2000 and May–October 2001. Farmers were interviewed to determine the situation on 2 July 2000. Fields were mapped in detail with the GPS instruments, and data compiled for 112 fields. Using a supervised classification system, training areas were selected and initial classifications were made to determine the validity of the classes. After merging several classes and testing several new classes a final classification system was made. All seven Landsat bands were used in the determination of the feature statistics. The final classification was made with the minimum distance algorithm. The statistics with respect to areas and crop type for the districts was obtained by crossing the raster map with the irrigation district raster map. The results with respect to crop type and total irrigated area per district were compared with those of previous studies. This included both NOAA/AVHRR and conventional agricultural district statistics.     

A NEW APPROACH TO THE VERTEX COLORING PROBLEM

The vertex coloring problem is a well-known classical optimization problem in graph theory in which a color is assigned to each vertex of the graph in such a way that no two adjacent vertices have the same color. The minimum vertex coloring problem is known to be an NP-hard problem in an arbitrary graph, and a host of approximation solutions are available. In this article, a learning automata–based approximation algorithm is proposed to solve the minimum vertex coloring problem. The proposed algorithm iteratively finds the different possible colorings of the graph and compares it at each stage with the best coloring found so far. If the number of distinct colors in the chosen coloring is less than that of the best coloring, the chosen coloring is rewarded; otherwise, it is penalized. Convergence of the proposed algorithm to the optimal solution is proven. The proposed vertex coloring algorithm is compared with the well-known coloring techniques and the results show the superiority of the proposed algorithm over the others both in terms of the color set size and running time of algorithm.     

Degree constrained minimum spanning tree problem: a learning automata approach

Degree-constrained minimum spanning tree problem is an NP-hard bicriteria combinatorial optimization problem seeking for the minimum weight spanning tree subject to an additional degree constraint on graph vertices. Due to the NP-hardness of the problem, heuristics are more promising approaches to find a near optimal solution in a reasonable time. This paper proposes a decentralized learning automata-based heuristic called LACT for approximating the DCMST problem. LACT is an iterative algorithm, and at each iteration a degree-constrained spanning tree is randomly constructed. Each vertex selects one of its incident edges and rewards it if its weight is not greater than the minimum weight seen so far and penalizes it otherwise. Therefore, the vertices learn how to locally connect them to the degree-constrained spanning tree through the minimum weight edge subject to the degree constraint. Based on the martingale theorem, the convergence of the proposed algorithm to the optimal solution is proved. Several simulation experiments are performed to examine the performance of the proposed algorithm on well-known Euclidean and non-Euclidean hard-to-solve problem instances. The obtained results are compared with those of best-known algorithms in terms of the solution quality and running time. From the results, it is observed that the proposed algorithm significantly outperforms the existing method.