Abstract

With the rapid growth of the Internet, most of the textualdata in the form of newspapers, magazines and journals tend to be avail-able on-line. Summarizing these texts can aid the users access the in-formation content at a faster pace. However, doing this task manuallyis expensive and time-consuming. Automatic text summarization is asolution for dealing with this problem. For a given text, a text summa-rization algorithm selects a few salient sentences based on certain fea-tures. In the literature, weight-based, foci-based, and machine learningapproaches have been proposed. In this paper, we propose a popularity-based approach for text summarization. A popularity of the sentence isdetermined based on the number of other sentences similar to it. Usingthe notion of popularity, it is possible to extract potential sentences forsummarization that could not be extracted by the existing approaches.The experimental results show that by applying both popularity andweight-based criteria it is possible to extract effective summaries.

Abstract

No Results Found

Abstract

The growing trend towards commercial crops with ever changing technology packages necessitate a transformation in the existing agricultural extension system with emerging technologies like IT.In this context IIIT , Hyderabad has developed and implemented eSagu, a Web Based Agricultural Expert Advice Dissemination System in Atmakur mandal, Warangal district during 2004-05 covering 1,051 cotton farms. eSagu system of extension has succeeded in acquisition of infrastructure and human resources as envisaged and proved its organizational ability in coordinating different branches for a smooth functioning on proposed lines. Wholistic information in the form of clear images of crop (through digital photographs and zooming) and other information i.e. soil, weather, crop history has helped scientists to provide effective advice. The system was able to offer collective expert advice from one place with in 24 hours of response time to the farmers at the other end. Further, it is only the information that moved, while the farmers and scientists remained at their respective working places. The system has proved its technical efficiency in terms of pest identification and prediction with appropriate advices based on IPM practices to all sections of farmers. In the process of information dissemination, the system was able to provide 20,000 advices and accumulated 1,11,000 crop photographs in a period of one year. In the field of research it was able to identify new pests like stem borer and early detection of Gray Mildew disease and share the information with other research agencies. As an experiment, the project has tested feasibility and acceptability of IT for tapping its potential as an alternative to the existing extension system. It also offers scope for further reduction in the cost of delivery of advice provided a cluster based approach is adopted in the future

Abstract

In view of technology/extension gaps in Indian agriculture and to exploit ICT revolution, International Institute of Information Technology, Hyderabad, A.P., India had developed eSagu model of extension system and implemented it for the cotton crop in three villages of Oorugonda, Gudeppad and Oglapur covering 749 farmers and 1041 farms during 2004-05 crop season. The main objective is to build a cost effective and scalable agricultural expert advice dissemination system to all the farmers. The three-tier system consists of farmers as end users, coordinators as intermediaries to obtain crop status through digital photographs and text and communicate the advice to the farmers. The scientists with knowledge system prepare farm advices. The evaluation study clearly brings out the feasibility and acceptability of ICT based model of eSagu. The crop status, the zooming facility of digital photographs, weather data, crop history, soil data, all have enabled the scientists in advice making and prediction. The advices were provided to the farmers in 24-36 hours. eSagu operation has improved the access, knowledge and technology adoption rate as compared to their counter parts in non-project area. It further established that the acquired technology has been quite useful and reflected in increased production by 1.5 quintals per acre, saved fertilizers by 0.76 bags, pesticides by 2.3 sprays per acre. This has resulted in a net gain of Rs. 3820.0 per acre. Farmers’ response to the utility of the project is quite positive and they want the project to continue in the future. In conclusion, the evaluation study reveals that accomplishments of the project are impressive, the system is generally accepted and throws a promise for wider application in the future.

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 .

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

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

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

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

This paper presents a methodology for optimal target detection in a multi sensor surveillance system. The system consists of mobile sensors that guard a rectangular surveillance zone crisscrossed by moving targets. Targets percolate the surveillance zone in a poisson fashion with uniform velocities. Under these statistics this paper computes a motion strategy for a sensor that maximizes target detections for the next T time steps. A coordination mechanism between sensors ensures that overlapping areas between sensors is reduced. This coordination mechanism is interleaved with the motion strategy computation to reduce detections of the same target by more than one sensor. To avoid an exhaustive search in the joint space of all sensors the coordination mechanism constraints the search by assigning priorities to the sensors. A comparison of this methodology with other multi target tracking schemes verifies its efficacy in maximizing detections. A tabulation of these comparisons is reported in results section of the paper