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.
This paper presents the use of a generalized learning technique to automatically generate Bangla poetry. We have trained a Long Sort Term Memory (LSTM) based recurrent neural network model on 350 poems written by Rabindranath Tagore to inspect if the recurrent neural network learns to generate poems. Using the technique described in this paper, we are able to generate poems using seed texts provided...
Sentiment classification has gained much attention in big data era. Most existing methods rely on bag-of-words model, which disregard contextual information. In many cases however, the sentiment strength of a word is implicitly associated with its part of speech and context. In this paper, we present a WWE (weighted word embeddings) method that combines word embeddings and part-of-speech (POS) tagging...
A restricted Boltzmann machine (RBM) processor (RBM-P) supporting on-chip learning and inference is proposed for machine learning applications in this paper. Featuring neural network (NN) model reduction for external memory bandwidth saving, low power neuron binarizer (LPNB) with dynamic clock gating and area-efficient NN-like activation function calculators, user-defined connection map (UDCM) for...
In this work, a cascade classifier is trained to detect multi-view face samples. Comparing with most of face detection system which use different classifier to classify frontal face and profile face, our system has advantage in detection speed. The proposed face detector extracts the Haar-like feature from the training samples and train a cascade classifier by using Adaboost learing algorithm. Different...
Wi-Fi signals have been typically acting as information carriers in modern communication system, but recent research has revealed their powerful capability in detecting and identifying various targets. With Wi-Fi, we can now "see" people's location, activity, and even hand gestures. In this paper, a new method of dynamic gesture recognition using Wi-Fi based on signal processing and machine...
Twitter user profile information is very useful for various fields such as marketing, HRD, advertising, and personalization. Since user profile provided by Twitter is very limited, some latent attributes such as gender, age, work, or interest should be predicted. In this paper, we aim to predict those four latent attributes using her/his tweet and bio data by employing machine learning techniques...
Lack of (semi)automatic mechanisms for service classification in the Universal Description Discovery and Integration repositories and non utilization of explicit or implicit semantic information of a service during its publishing are the two major challenges in the area of web service discovery and selection. We propose a semantic model of human-machine collaboration for the classification, discovery...
In this paper, we apply GVF snake to vertebra segmentation and further improve it based on the knowledge of spine MRI, especially the shape knowledge. Owning to the contour of vertebra body being similar to a rectangle whose edges are concave to the center of the contour, we add a pressure force which moves the contour to the center as one of the external forces of snake, and then reset the weight...
Incorporating knowledge from domain expert to a classifier is one of the techniques which require to be considered in solving imbalanced dataset problems. In this study, the proposed technique is a development to extend the process for imbalanced dataset where the individual classification system has already been designed for balanced data set. This paper introduces a methodology and preliminary results...
Computer aided design (CAD) system for traditional Chinese paper-cutting provides significant assistance for folk artists creating delicate handicrafts. However, the large amount of paper-cutting patterns creates several major challenges for the management of an online pattern library. Artists could easily collect favorite pattern materials and share their creative works with others using an online...
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.