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.
Two of the major problems in social media message classification are the data sparseness issue and the high degree of lexical variation. Paraphrases, or synonyms, are alternative ways of expressing the same meaning using different lexical variations. In this study, we try to use paraphrases to improve tweet topic classification performance. We explored two approaches to generating paraphrases, WordNet,...
This paper presents a new methodology for detecting deterioration in performance of deep neural networks when applied to on line visual analysis problems and enabling fine-tuning, or retraining, of the network to the current data characteristics. Pre-trained deep neural networks which have a satisfactory performance on the problem under study constitute the basis of the approach, with efficient transfer...
Radio frequency fingerprinting, based on Wi-Fi signals is a popular approach for indoor localization. Recently a few works have explored applicability of machine learning techniques to this problem. However, the challenging task of accurately finding the position depends on prior efforts of fingerprinting. Another challenge is that, distance sensitivity of signal strength depends on proximity to the...
When learning a new word in language learning, there are two problems. One is how difficult the word itself is. The second is, in what kind of situation, it will be used. There is a research that defined quantitative ambiguity of words based on the structure of WordNet, then investigated the relationship between the ambiguity and the difficulty level of words. In this paper, we re-define ambiguity...
Nowadays, software developers often utilize existing third party libraries and make use of Application Programming Interface (API) to develop a software. However, it is not always obvious which library to use or whether the chosen library will play well with other libraries in the system. Furthermore, developers need to spend some time to understand the API to the point that they can freely use the...
Selecting the appropriate parameters for an indoor positioning system may be a difficult task due to the large number of parameter combinations. It is more complex in realistic multi-building multi-floor environments, where severe wrong building and floor errors occur but they are not highlighted in the main evaluation metric. Moreover, a selected parameter configuration, that may seem appropriate...
Multidimensional long short-term memory recurrent neural networks achieve impressive results for handwriting recognition. However, with current CPU-based implementations, their training is very expensive and thus their capacity has so far been limited. We release an efficient GPU-based implementation which greatly reduces training times by processing the input in a diagonal-wise fashion. We use this...
The quality of skill teaching is vital for higher vocational colleges. From the perspective of sustainable development, we considered the essence of sustainable development in higher vocational education is student oriented and thus the skill teaching should focus on cultivating the students' flexible skill or their sustainability. This paper first analyzes the prevailing inefficient phenomenon in...
Smart home is one of the most important applications of ubiquitous computing. In this work, we propose an infrastructure of Vietnamese Smart homes as well as a training framework for activity recognition and forecast. In this framework, active learning technique is applied and a new mining algorithm is proposed. In addition to activity recognition, a forecast mechanism is also added into the smart...
The Multiple Listing Service, commonly known as the MLS, is the singularly most important database where real estate agents and brokers list real estate properties for sale. It is common that agents include textual comments pertinent to the property. Although the information content of comments varies, it is usually expressed in good faith and in many cases is helpful in shedding light on the overall...
Activity clustering and recognition is one of the most important research trends about smart home. Taking place inside a sensor smart home, activities differ from each other at typical characteristics such as sensor sets triggered as well as temporal ones. In this work, we present a smart home infrastructure and propose a method of calculating neighborhood radius for clustering and recognizing in-home...
Semantic segmentation, or segmenting all the objects in an image is one of the core problems of computer vision. In order to achieve an object-level semantic segmentation, we propose to label image regions and to improve the segmentation result based on these labels. We build upon the recent super parsing approach, which is a nonparametric solution to the image labelling problem. We propose to initialize...
This paper investigates the problem of defining the acoustic-phonetic unit set for flexible vocabulary continuous speech recognition systems. As an alternative to the classical modeling approach with biphones and triphones, a set of stationary/transitory state units is defined that is limited enough in number as to represent a closed set trainable once and for all. A major benefit of these units is...
In this paper, we propose a new method for singing voice detection based on a Bidirectional Long Short-Term Memory (BLSTM) Recurrent Neural Network (RNN). This classifier is able to take a past and future temporal context into account to decide on the presence/absence of singing voice, thus using the inherent sequential aspect of a short-term feature extraction in a piece of music. The BLSTM-RNN contains...
This study introduces an example-based chat-oriented dialogue system with personalization framework using long-term memory. Previous representative chat-bots use simple keyword and pattern matching methodologies. To maintain the quality of systems, generating numerous heuristic rules with human labour is inevitable. The language expert knowledge is also necessary to build those rules and matching...
In this paper, we propose a novel method for text/non-text classification in online handwritten document based on Recurrent Neural Network (RNN) and its improved version, Long Short-Term Memory (LSTM) network. The task of classifying strokes in a digital ink document into two classes (text and non-text) can be seen as a sequence labelling task. The bidirectional architecture is used in these networks...
In the paper, we compare the methods based on Markov Random fields (MRF) and Conditional Random fields (CRF) for separating text and non-text ink strokes in online handwritten Japanese documents. This paper validates the effect of context information in neighbor strokes based on graphical models of MRF and CRF. The task of separating text and non-text ink strokes in ink documents denotes classifying...
The ubiquity of smartphones with high quality cameras and fast network connections will spawn many new applications. One of these is visual object recognition, an emerging smartphone feature which could play roles in high-street shopping, price comparisons and similar uses. There are also potential roles for such technology in assistive applications, such as for people who have visual impairment....
The development of fully automatic face annotation techniques in online social networks (OSNs) is currently very important for effective management and organization of the large numbers of personal photos shared on social network platforms. In this paper, we construct the personalized and adaptive Fused Face Recognition unit for each member, which uses the Adaboost algorithm to fuse several different...
Parameter tuning is a common issue for many tracking algorithms. In order to solve this problem, this paper proposes an online parameter tuning to adapt a tracking algorithm to various scene contexts. In an offline training phase, this approach learns how to tune the tracker parameters to cope with different contexts. In the online control phase, once the tracking quality is evaluated as not good...
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.