Abstract

We present a framework for modeling and analysis for a surveillance network consisting of multiple sensors. Sensors monitor targets that crisscross a rectangular surveillance zone. When a sensor pursuits a target it leaves areas unguarded through which other targets can get past undetected. A methodology that computes the tracking time for a sensor such that a fraction of the targets expected to cross its home area is detected to an arbitrary probabilistic guarantee is presented based on the framework. Targets enter the surveillance zone according to Poisson statistics. The time spent by a target within a sensor's home area follows uniform random statistics. The home area of the sensor is the area guarded by it when it is stationed at its home position, its default position when it is not in pursuit of a target. The framework is further extended to situations where multiple sensors monitor the same home area. Simulation results presented corroborate with the probabilistic framework developed and verify its correctness for single as well as multi-sensor cases.

Abstract

We present an extension of the FCM over the loss functions used in the M-estimators of robust statistics akin to the generalization of the fuzzy-C-means algorithms over the norm distances [1]. The effect of these estimators in reducing the bias of the outliers while estimating the cluster prototypes are studied and compared. The comparisons have been done over synthetic data as well as simulated data consisting of range sensor readings representative of the objects in the neighborhood of a navigating mobile robot. For the synthetic data set the comparison is attempted over the popular FCM algorithm. For the sensory data set the Adaptive Fuzzy Clustering (AFC) algorithm [2] has been employed and extended over the loss functions of robust statistics. The AFC is utilized considering the shape of the objects encountered by the robot in a typical indoor environment.

Abstract

A hierarchical framework for document segmentation is proposed as an optimization problem. The model incorporates the dependencies between various levels of the hierarchy unlike traditional document segmentation algorithms.This framework is applied to learn the parameters of the document segmentation algorithm using optimization methods like gradient descent and Q-learning.The novelty of our approach lies in learning the segmentation parameters in the absence of ground truth.

Abstract

We present a document understanding system in which the arrangement of lines of text and block separators within a document are modeled by stochastic context free gram-mars. A grammar corresponds to a document genre; our system may be adapted to a new genre simply by replacing the input grammar. The system incorporates an optical character recognition system that outputs characters,their positions and font sizes. These features are combined to form a document representation of lines of text and separators. Lines of text are labeled as tokens using regular expression matching. The maximum likelihood parse of this stream of tokens and separators yields a functional labeling of the document lines. We describe business card and business letter applications.

Abstract

Earthquake problems in India need no introduction. From recent earthquakes, it is very well understood that lack of awareness is one of the contributing factors for huge casualty losses. In order to increase the awareness about the effects of earthquakes among professionals involved in construction, it is necessary to make them understand the concepts of structural dynamics and earthquake engineering. To address this issue, we have developed a software tool named Virtual Structural Dynamics Laboratory. Using this tool, a person with some knowledge of structural engineering can be able to learn by himself the fundamentals of structural dynamics. For convenience in explaining the concepts, we divided this tool into four modules. Each module contains few experiments with good G.U.I. In these experiments, user can find the explanation with graphical diagram. At the end of fourth module user can understand the dynamic behavior of the structure. This software tool aims to help students, architects and civil engineers in understanding the principles of structural dynamics.

Abstract

Natural disasters like earthquake, landslide, flood, drought, cyclone, forest fire, volcanic eruption are quite common in different parts of the globe. These natural disasters lead to the loss of life, property damage and socio-economic disruption. Earthquakes are one of the worst among the natural disasters. Seismic zonation map given in IS 1893:2002 shows that India is highly vulnerable for earthquake and over 60% of India is prone to moderate to major earthquakes. During past century, India has witnessed more than 650 earthquakes of magnitude greater than 5 and during past 15 years, 6 earthquakes of magnitude over 6. From recent earthquakes, it is very well understood that lack of awareness is one of the contributing factors for huge casualty losses. In order to increase the awareness about the effects of earthquakes among professionals involved in construction, it is necessary to make them understand the concepts of structural dynamics and earthquake engineering. For this, we have developed a software tool called “Interactive Structural Dynamics Learning Kit (ISDLK)” for explaining structural dynamics in a simple manner. For convenience in explaining the concepts, we divided the tool into six modules. Each module contains few experiments with good G.U.I. In these modules, user can input the value and he/she can find the desired results with explanation using graphical diagram. At the end of sixth module, user can understand the complete dynamic behavior of a structure. ISDLK aims to help students, architects and design professional in understanding structural dynamics.

Abstract

Earthquake, now everyone is familiar with this word. We have clearly witnessed during the recent Sumatra, Indonesia earthquake (M 9.0) the amount of damage an earthquake can cause to the society. Had this earthquake occurred on land, it would have easily damaged few hundreds of kilometers and the damage estimates would have been unimaginable. Earthquakes are not new to our country. We have had the long history of earthquake occurrences. Some of the major earthquakes of the world occurred in our country and neighborhood areas. During past 15 years also we have witnessed 6 moderate earthquakes: Bihar-Nepal border (M6.4) in 1988, Uttarkashi, Uttaranchal (M6.6) in 1991, Latur, Maharastra (M6.3) in 1993, Jabalpur, Madhya Pradesh (M6.0) in 1997, Chamoli, Uttaranchal (M6.8) in 1999 and Bhuj, Gujarat (M6.9) in 20011). These earthquakes caused around 40,000 casualties (see Table 1) and innumerable property loss. These events occurred with a time gap of 2 ~ 3 years. Are we ready to face another event?

Abstract

India has witnessed 6 earthquakes during past 15 years causing around 40,000 casualties and immense property loss. More than 90% of these casualties are due to collapse of buildings and they occurred within very short period of time after the earthquake. Hence, for reducing casualty losses and subsequent consequences due to earthquake, it is very important to study the response of structures due to seismic excitations. For studying the response of the structures and consequent issues after the earthquake disaster, information technology can play a major role. This paper contributes to understand the importance of information technology in earthquake disaster mitigation

Abstract

Multilingual speech recognition system is required for tasksthat use several languages in one speech recognition application. In thispaper, we propose an approach for multilingual speech recognition byspotting consonant-vowel (CV) units. The important features of spottingapproach are that there is no need for automatic segmentation of speechand it is not necessary to use models for higher level units to recognisethe CV units. The main issues in spotting multilingual CV units are thelocation of anchor points and labeling the regions around these anchorpoints using suitable classifiers. The vowel onset points (VOPs) have beenused as anchor points. The distribution capturing ability of autoassocia-tive neural network (AANN) models is explored for detection of VOPsin continuous speech. We explore classification models such as supportvector machines (SVMs) which are capable of discriminating confusableclasses of CV units and generalisation from limited amount of trainingdata. The data for similar CV units across languages are shared to trainthe classifiers for recognition of CV units of speech in multiple languages.We study the spotting approach for recognition of a large number of CVunits in the broadcast news corpus of three Indian languages

Abstract

In this paper, we present studies on combining evidence from multiple classifiers to recognize a large number of consonant-vowel (CV) unit.s of speech. Multiple classi­fier systems may lead to a better solution to the complex speech recognition tasks, when the evidence obtained from individual systems is complementary in nature. Hidden Markov models (HIvlMs) are based on the max­imum likelihood (ML) approach for training CV pat­terns of variable lengt.h. Support vector machine (SVM) models are based on discriminative learning approach for training fixed length CV patterns. Because of the differences in the training methods and in the pattern representation used, they may provide complementary evidence for CV classes. Complement.ary evidence avail­able from these classifiers is combined using the sum rule. Effectiveness of the multiple classifier system is demonstrated for recognition of CV units of speech in Indian languages .