The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
The paper describes an automatic parts-of-speech tagging for Bengali sentences using Global Linear Model (GLM) which learns to represent the whole sentence through a feature vector called Global feature. Tagger has been trained using averaged perceptron algorithm. Performance of this tagger has been compared to Conditional Random Field (CRF), Support Vector Machine (SVM), Hidden Markov Model (HMM)...
This paper proposes an ingenious and fast method to classify videos into fixed broad classes, which would assist searching and indexing using semantic keywords. The model extracts constituent frames from videos and maps low-level features extracted these frames to high-level semantics. We use color, structure and texture features extracted from a standard image database to train an SVM classifier,...
This work explores the use of prosodic feature based sparse representation classification (SRC) system for language identification (LID) task. The prosodic features are computed by extracting syllable like unit with the help of a vowel onset points detection algorithm and mapped to i-vector domain for SRC using an exemplar dictionary. This work is a motivation from recently reported LID approach using...
This paper presents theoretically simple, yet computationally efficient approach for face recognition. In this approach the face image is divided into several sub-regions from which the information derived using the Local Binary Pattern (LBP) over a window and the information at the central pixel, which is a product of information source and fuzzy membership value. The LBP features possess the texture...
The researchers have started looking for Internet traffic recognition techniques that are independent of ‘well known’ TCP or UDP port numbers, or interpreting the contents of packet payloads. Newer approaches classify traffic by recognizing statistical patterns in externally observable attributes of the traffic (such as typical packet lengths and inter-arrival times). The main goal is to cluster or...
Mention detection is an important component in anaphora resolution. In this paper we present our works on mention detection based on differential evolution (DE). The proposed technique consists of two steps, viz. feature selection and classifier ensemble. In the first step the algorithm performs automatic feature selection for two machine learning algorithms, namely Conditional Random Field (CRF)...
The basic goal of this work is to develop a Consonant-Vowel Recognition System (CVRS) for determining a sequence of Consonant-Vowel (CV) units present in a given speech utterance. In this work, we are focusing on developing CVRSs for Indian languages namely Bengali and Odia. This framework of developing CVRSs can be extended to any Indian languages. We have developed two separate CVRSs for Bengali...
As the availability of solar energy varies widely with time and with different atmospheric condition, the cascaded multilevel inverters generates distorted output ac voltage and current if the generated PV voltages of each PV module are unequal. This paper proposes a novel space vector modulation technique for the single-phase cascaded H-bridge multilevel inverter (CHBMLI) to generate a balanced output...
In this paper, the problem of forest fire is considered and a comprehensive system is proposed with the use of wireless sensor network for real-time forest fire detection. The wireless sensor network can give more accurate detection of forest fire danger rate over traditional monitoring approaches like lookout towers and satellite based monitoring. This proposed framework mainly describes the data...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.