Abstract This paper describes a news summarization system using the Fuzzy Graph based Document Model. News articles are modelled as fuzzy graphs whose nodes are sentences and edges are weighted by the fuzzy similarity measure between the sentences. The similarity between sentences is in between 0 and 1. Centrality of the graph retrieves important sentences. The proposed system produces summaries by Eigen value... This paper describes a news summarization system using the Fuzzy Graph based Document Model. News articles are modelled as fuzzy graphs whose nodes are sentences and edges are weighted by the fuzzy similarity measure between the sentences. The similarity between sentences is in between 0 and 1. Centrality of the graph retrieves important sentences. The proposed system produces summaries by Eigen value convergence of the similarity matrix. The summaries are evaluated based on the human generated summaries in DUC 2007 data set. The resultd show fuzzy graph based approach for news summarization using Eigen value analysis are quite encouraging. It shows high correlation with human generated summaries. Read More Read Less

Abstract With the birth of the internet in the 1990’s, society grew used to turn to the internet as first port of information. Search engines play a major role in finding the desired information among the billions of websites available and are one of the most used services online. The effectiveness of search engines has already been evaluated in numerous studies... With the birth of the internet in the 1990’s, society grew used to turn to the internet as first port of information. Search engines play a major role in finding the desired information among the billions of websites available and are one of the most used services online. The effectiveness of search engines has already been evaluated in numerous studies and under many different aspects. However, only few studies touch upon search engine evaluation from a user perspective, and even less studies from a user perspective of speakers of a specific language. This study aims at shedding more light on search engine usage from the perspective of Arab users. A survey made among 70 Arab students in Jordan reveals new aspects of search behavior and user satisfaction. The study assesses the frequency of search engine usage, preferred search engines, and user priorities for search engine selection. It investigates language preferences such as search language and search engine language interface, and user opinion on the quality of English search results versus Arabic search results. User satisfaction with search engine results, contentment with first page search results as well as the perceived necessity for several searches and query paraphrasing are being discussed. Some of these aspects are being examined in this study for the first time. Where possible, the study draws parallels to comparable international research as well as to the few available studies on Arab users. Read More Read Less

Abstract Automatic recognition of isolated spoken digits is one of the most challenging tasks in the area of automatic speech recognition. In this paper, database development and automatic speech recognition of isolated Pashto spoken digits from sefer (0) to naha (9) has been presented. A number of 50 individual Pashto native speakers (25 male and 25 female) of different ages, ranging from... Automatic recognition of isolated spoken digits is one of the most challenging tasks in the area of automatic speech recognition. In this paper, database development and automatic speech recognition of isolated Pashto spoken digits from sefer (0) to naha (9) has been presented. A number of 50 individual Pashto native speakers (25 male and 25 female) of different ages, ranging from 18 to 60 years, were involved to utter from sefer (0) to naha (9) digits separately. Sony PCM-M 10 linear recorder is used for recoding purpose in the office and home in noise free environment. Adobe audition version 1.0 is used to split the audio of digits into individual digits and result is saved in .wav format. Mel Frequency Cepstral Coefficients (MFCC) is used to extract speech features. K Nearest Neighbor (K-NN) classifier is used for the first time up to author knowledge in Pashto language to classify the features of speech. The experimental results are evaluated, and the overall average recognition accuracy of 76.8% is obtained. Read More Read Less