• ETRI Journal
• /
• v.42 no.1
• /
• pp.90-100
• /
• 2020

Named entity recognition (NER) continues to be an important task in natural language processing because it is featured as a subtask and/or subproblem in information extraction and machine translation. In Urdu language processing, it is a very difficult task. This paper proposes various deep recurrent neural network (DRNN) learning models with word embedding. Experimental results demonstrate that they improve upon current state-of-the-art NER approaches for Urdu. The DRRN models evaluated include forward and bidirectional extensions of the long short-term memory and back propagation through time approaches. The proposed models consider both language-dependent features, such as part-of-speech tags, and language-independent features, such as the "context windows" of words. The effectiveness of the DRNN models with word embedding for NER in Urdu is demonstrated using three datasets. The results reveal that the proposed approach significantly outperforms previous conditional random field and artificial neural network approaches. The best f-measure values achieved on the three benchmark datasets using the proposed deep learning approaches are 81.1%, 79.94%, and 63.21%, respectively.

• International Journal of Contents
• /
• v.15 no.4
• /
• pp.59-64
• /
• 2019

In recent years, emotion recognition has been an interesting and challenging topic. Compared to facial expressions and speech modality, gesture-based emotion recognition has not received much attention with only a few efforts using traditional hand-crafted methods. These approaches require major computational costs and do not offer many opportunities for improvement as most of the science community is conducting their research based on the deep learning technique. In this paper, we propose an end-to-end deep learning approach for classifying emotions based on bodily gestures. In particular, the informative keyframes are first extracted from raw videos as input for the 3D-CNN deep network. The 3D-CNN exploits the short-term spatiotemporal information of gesture features from selected keyframes, and the convolutional LSTM networks learn the long-term feature from the features results of 3D-CNN. The experimental results on the FABO dataset exceed most of the traditional methods results and achieve state-of-the-art results for the deep learning-based technique for gesture-based emotion recognition.

• Journal of KIISE:Software and Applications
• /
• v.30 no.5_6
• /
• pp.570-578
• /
• 2003

Maximum entropy models are promising candidates for natural language modeling. However, there are two major hurdles in applying maximum entropy models to real-life language problems, such as prepositional phrase attachment: feature selection and high computational complexity. In this paper, we propose a maximum entropy boosting model to overcome these limitations and the problem of imbalanced data in natural language resources, and apply it to prepositional phrase (PP) attachment and part-of-speech (POS) tagging. According to the experimental results on Wall Street Journal corpus, the model shows 84.3% of accuracy for PP attachment and 96.78% of accuracy for POS tagging that are close to the state-of-the-art performance of these tasks only with small efforts of modeling.

• Journal of Institute of Control, Robotics and Systems
• /
• v.11 no.12
• /
• pp.1020-1026
• /
• 2005

In the era of ubiquitous computing, human-friendly man-machine interface is getting more attention due to its possibility to offer convenient services. For this, in this paper, we introduce a 'Half-Mirror Interface System (HMIS)' as a novel type of human-friendly man-machine interfaces. Basically, HMIS consists of half-mirror, USB-Webcam, microphone, 2ch-speaker, and high-speed processing unit. In our HMIS, two principal operation modes are selected by the existence of the user in front of it. The first one, 'mirror-mode', is activated when the user's face is detected via USB-Webcam. In this mode, HMIS provides three basic functions such as 1) make-up assistance by magnifying an interested facial component and TTS (Text-To-Speech) guide for appropriate make-up, 2) Daily weather information provider via WWW service, 3) Health monitoring/diagnosis service using Chinese medicine knowledge. The second one, 'display-mode' is designed to show decorative pictures, family photos, art paintings and so on. This mode is activated when the user's face is not detected for a time being. In display-mode, we also added a 'healing-window' function and 'healing-music player' function for user's psychological comfort and/or relaxation. All these functions are accessible by commercially available voice synthesis/recognition package.

• Journal of Information Processing Systems
• /
• v.19 no.3
• /
• pp.355-369
• /
• 2023

Since the widespread adoption of deep-learning and related distributed representation, there have been substantial advancements in part-of-speech (POS) tagging for many languages. When training word representations, morphology and shape are typically ignored, as these representations rely primarily on collecting syntactic and semantic aspects of words. However, for tasks like POS tagging, notably in morphologically rich and resource-limited language environments, the intra-word information is essential. In this study, we introduce a deep neural network (DNN) for POS tagging that learns character-level word representations and combines them with general word representations. Using the proposed approach and omitting hand-crafted features, we achieve 90.47%, 80.16%, and 79.32% accuracy on our own dataset for three morphologically rich languages: Uyghur, Uzbek, and Kyrgyz. The experimental results reveal that the presented character-based strategy greatly improves POS tagging performance for several morphologically rich languages (MRL) where character information is significant. Furthermore, when compared to the previously reported state-of-the-art POS tagging results for Turkish on the METU Turkish Treebank dataset, the proposed approach improved on the prior work slightly. As a result, the experimental results indicate that character-based representations outperform word-level representations for MRL performance. Our technique is also robust towards the-out-of-vocabulary issues and performs better on manually edited text.

• The Journal of Korean society of community based occupational therapy
• /
• v.1 no.1
• /
• pp.79-89
• /
• 2011

The number of the disabled person had been increased for the industrial accident and the environmental pollution. Especially, developmental disability has the high prevalence rate between 5% and 10% of the whole children. The children with a developmental disability can be treated by the physical therapy, the occupational therapy, the psychology therapy, speech therapy, and art therapy. Visual preception which is function to recognize the external environment through the optic organ could be related to most behaviors on the everyday life. But because the children with disability could not develop the visual-preception enough, they came to have difficulties in executing daily life project. For this reason, it is most important to understand the estimation and the cure on the visual-preception in the pediatric occupational therapy. To improve the visual-preception power, we have many kind of methods including sensory integration, training program for the visual-perception and art-craft program. Particularly, the art-craft which is the representative activity for making something by hands, can be applied to anyone. As the study on the brain has been activated, it was proved that handicraft actives could have an good effect on the brain function and using brain. When the fine motor exercise and more delicate and accurate motion were carried, these motions need the essential help of the visual-perception. So it could be expected that using the repetitive hand function by art-craft makes the brain function improve, when a activity that needs a fine motor exercise and more delicate, accurate motion was carried, It also indicates that the art-craft program has a clear treatment value. Though the intervention between visual-perception development and visual-perception disability have a majority in the field of occupational therapy, there is a few study yet. Therefore, this study tried to look back on the necessity of applying the art-craft program to the children with disability as the prestudy for preliminary validity of the master's thesis.

• (The) Research of the performance art and culture
• /
• no.41
• /
• pp.187-218
• /
• 2020

Ulsan Dutbeki is a local dance handed down by the Ulsan people through custom. This study was discussed on the locality of Ulsan Dutbeki. The method of this study is as follows. First of all, the perception of Dutbeki from the perspective of Ulsan's local characteristic. First, Ulsan Dutbeki is based on the local characteristic of the southeastern coastal area of the Korean peninsula. Second, Dutbeki features local characteristics of Ulsan as a military cultural area. Third, in Dutbeki, there is a local culture of Ulsan which was originated from the village Dongjeol and outdoor performances. Next, the researcher perceived Ulsan Dutbeki which had been handed down through custom and approached its shape. The origins of the shape are, firstly, the speech tone and gestures of Ulsan people. Secondly, folk plays related to worshiping martial arts and military training. Thirdly, the characteristics of the Dutbeki dance in coastal areas of Gyeongsangdo. Fourth, local custom displayed at the village festival of Ulsan. Ulsan is a region of Gyeongsang culture area and has similarity with other localities. However, this study limited its comparisons with regard to Dutbeki that were originated from the local characteristics of other regions. The results of this study recognized Ulsan Dutbeki as a local dance in Ulsan area. In other words, this study perceived Dutbeki, which had been an entertaining component of traditional lifestyle, as an intangible cultural heritage and studied the form in every conceivable way from an artistic point of view.

• (The) Research of the performance art and culture
• /
• no.25
• /
• pp.135-181
• /
• 2012

The celebration day of national foundation(開國紀元節) is to celebrate the foundation of Joseon by Taejo Lee Seong Gye. It is also shortly called as the celebration day. The events celebrating this were performed either on a large or small scale by the court or the people from 1895 right before 1910, the Korea-Japan Annexation. As you can see from the period of its performance, the celebration day of national foundation was not one of the Joseon's traditional court events, but it was one of the national holidays(慶節) institutionalized newly after the port opening (1876). In Korea, too, they strived to concentrate on modernization as exchanging with all different countries in the world after the port opening. Also, they considered how to concretize all different celebration events for national holidays characterized by the modern days of celebration. As a result, additionally or partly from the traditional court events, the events to celebrate national holidays appeared one after another from 1895. And this article examined the celebration day of national foundation, one of the national holidays referred to as modern-style days of celebration. The event to celebrate this can be seen from Geongbok-gung(景福宮) on the day of July 16th, 1895. And the Independence Association(獨立協會) also held the event for the celebration day of national foundation. The event performed for the celebration day of national foundation shows very distinct aspects on the ground to maintain the congratulatory ways partly. In particular, the ritual for the celebration day of national foundation held by the Independence Association induced modernized ways of celebration such as the congratulatory address and speech, and it also included new elements like the harmony of various music including court music(宮中音樂) or Chang-ga(唱 歌).

• (The) Research of the performance art and culture
• /
• no.36
• /
• pp.585-602
• /
• 2018

This article examines the academic world of Professor Sa jin-sil. This article is not a detailed and rigorous assessment of Prof. Sa's work. During my directly or indirectly meeting with Prof. Sa jin-sil, the writing was based on my experiences. This is why the theme of "participatory observation records" is attached. I was aware that this writing would become a customary and formal funeral speech. Because I thought Prof. Sa also did not want formal and customary writing. The initiation of the participatory observational records that I describe was the literature study of Prof. Sa. What I am about to say in the title of the table of "Known Performance and to Revalue." There I summarized my thoughts on what Prof. Sa contributed to the research of the literature study on traditional performance and my opinion of the justice of the assessment of her contributions. I have not recommitted again about contributions or achievements that have already been widely recognized. What I noticed here was what was to be revalued. I once again stressed the achievements that were not properly evaluated despite their importance and significance. In the ensuing discussion, I looked at Prof. Sa's entirely different academic side. I call the passage "an unexpected result against prejudice." The subjects covered were Prof. Sa's field-contextual studies. Prof. Sa is often referred to as a dramatical history or a traditional performing arts scholar who studies literature. Such an idea is so common that it is easy to overlook field-contextual research results, not literature-based. But I think this is prejudice. That is why the title of the table of contents has the words 'unexpected' and 'prejudice'. Here I actively emphasized and evaluated Professor Sa's achievements in field-contextual studies.

• International Journal of Computer Science & Network Security
• /
• v.22 no.4
• /
• pp.420-426
• /
• 2022

Breast cancer is among the cancers that may be healed as the disease diagnosed at early times before it is distributed through all the areas of the body. The Automatic Analysis of Diagnostic Tests (AAT) is an automated assistance for physicians that can deliver reliable findings to analyze the critically endangered diseases. Deep learning, a family of machine learning methods, has grown at an astonishing pace in recent years. It is used to search and render diagnoses in fields from banking to medicine to machine learning. We attempt to create a deep learning algorithm that can reliably diagnose the breast cancer in the mammogram. We want the algorithm to identify it as cancer, or this image is not cancer, allowing use of a full testing dataset of either strong clinical annotations in training data or the cancer status only, in which a few images of either cancers or noncancer were annotated. Even with this technique, the photographs would be annotated with the condition; an optional portion of the annotated image will then act as the mark. The final stage of the suggested system doesn't need any based labels to be accessible during model training. Furthermore, the results of the review process suggest that deep learning approaches have surpassed the extent of the level of state-of-of-the-the-the-art in tumor identification, feature extraction, and classification. in these three ways, the paper explains why learning algorithms were applied: train the network from scratch, transplanting certain deep learning concepts and constraints into a network, and (another way) reducing the amount of parameters in the trained nets, are two functions that help expand the scope of the networks. Researchers in economically developing countries have applied deep learning imaging devices to cancer detection; on the other hand, cancer chances have gone through the roof in Africa. Convolutional Neural Network (CNN) is a sort of deep learning that can aid you with a variety of other activities, such as speech recognition, image recognition, and classification. To accomplish this goal in this article, we will use CNN to categorize and identify breast cancer photographs from the available databases from the US Centers for Disease Control and Prevention.