• Journal of Information Processing Systems
• /
• v.18 no.4
• /
• pp.535-548
• /
• 2022

Using a rich resource language to classify sentiments in a language with few resources is a popular subject of research in natural language processing. Burmese is a low-resource language. In light of the scarcity of labeled training data for sentiment classification in Burmese, in this study, we propose a method of transfer learning for sentiment analysis of a language that uses the feature transfer technique on sentiments in English. This method generates a cross-language word-embedding representation of Burmese vocabulary to map Burmese text to the semantic space of English text. A model to classify sentiments in English is then pre-trained using a convolutional neural network and an attention mechanism, where the network shares the model for sentiment analysis of English. The parameters of the network layer are used to learn the cross-language features of the sentiments, which are then transferred to the model to classify sentiments in Burmese. Finally, the model was tuned using the labeled Burmese data. The results of the experiments show that the proposed method can significantly improve the classification of sentiments in Burmese compared to a model trained using only a Burmese corpus.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.4
• /
• pp.1080-1099
• /
• 2023

Digital healthcare combined with telemedicine services in the form of convergence with digital technology and AI is developing rapidly. Digital healthcare research is being conducted on many conditions including shock. However, the causes of shock are diverse, and the treatment is very complicated, requiring a high level of medical knowledge. In this paper, we propose a shock detection method based on the correlation between shock and data extracted from hemodynamic monitoring equipment. From the various parameters expressed by this equipment, four parameters closely related to patient shock were used as the input data for a machine learning model in order to detect the shock. Using the four parameters as input data, that is, feature values, a random forest-based ensemble machine learning model was constructed. The value of the mean arterial pressure was used as the correct answer value, the so called label value, to detect the patient's shock state. The performance was then compared with the decision tree and logistic regression model using a confusion matrix. The average accuracy of the random forest model was 92.80%, which shows superior performance compared to other models. We look forward to our work playing a role in helping medical staff by making recommendations for the diagnosis and treatment of complex and difficult cases of shock.

• Information Systems Review
• /
• v.24 no.1
• /
• pp.1-19
• /
• 2022

Social media-based communication has become crucial part of our personal and official lives. Therefore, it is no surprise that social media sentiment analysis has emerged an important way of detecting potential customers' sentiment trends for all kinds of companies. However, social media sentiment analysis suffers from huge number of sentiment features obtained in the process of conducting the sentiment analysis. In this sense, this study proposes a novel method by using Bayesian Network. In this model MBFS (Markov Blanket-based Feature Selection) is used to reduce the number of sentiment features. To show the validity of our proposed model, we utilized online review data from Yelp, a famous social media about restaurant, bars, beauty salons evaluation and recommendation. We used a number of benchmarking feature selection methods like correlation-based feature selection, information gain, and gain ratio. A number of machine learning classifiers were also used for our validation tasks, like TAN, NBN, Sons & Spouses BN (Bayesian Network), Augmented Markov Blanket. Furthermore, we conducted Bayesian Network-based what-if analysis to see how the knowledge map between target node and related explanatory nodes could yield meaningful glimpse into what is going on in sentiments underlying the target dataset.

• The KIPS Transactions:PartB
• /
• v.19B no.1
• /
• pp.37-42
• /
• 2012

The pseudo relevance feedback suggests that frequent words at the top documents are related to initial query. However, the main drawback associated with the term frequency method is the fact that it relies on feature independence, and disregards any dependencies that may exist between words in the text. In this paper, we propose query expansion based on word graph using term proximity. It supplements term frequency method. On TREC WT10g test collection, experimental results in MAP(Mean Average Precision) show that the proposed method achieved 6.4% improvement over language model.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.12 no.2
• /
• pp.199-205
• /
• 2009

A simple and effective analysis method is presented for predicting the best infiltration area. Based on geospatial information, numerical estimation barometer for degree of infiltration risk has been derived. The dominant geospatial features influencing infiltration risk have been found to be area altitude, degree of surface gradient, relative direction of surface gradient to the surveillance line, degree of surface gradient repetition, regional forest information. Each feature has been numerically expressed corresponding to the degree of infiltration risk of that area. Four different detection probability maps of infiltration risk for the surveillance area are drawn on the actual map with respect to the numerically expressed five dominant factors of infiltration risks. By combining the four detection probability maps, the complete picture of thr best infiltration area has been drawn. By using the map and the analytic method the effectiveness of surveillance operation can be improved.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.1D
• /
• pp.157-167
• /
• 2006

During the first and second NGIS projects by the Korean government, The first one (1995~2000) was limited on constructing geographic information and the second (2001~2005) was focused on circulation and practical use of geoinformation from the result of the first project. In the latter half of 2nd NGIS project, However, the geographic information from the NGIS projects have not been renewed even though there were significant geographical changes. The accurate renewal of geoinformation is a matter of great importance to the next generation industry (e.g. LBS, Ubiquitous, Telematics). In this respect, it is time to update the geographic information in the latter half of the second NGIS project. Therefore, It is not only important to build an accurate geoinformation but also rapid and correct renewal of the geoinformation. NGII (National Geographic Information Institute) has been studying for improvement of digital map that was constructed by the result of the 1st NGIS project. Through the construction of clean digital map, NGII constructed Framework Data to three kinds of formats (NGI, NDA, NRL). Framework Data was contained to other database, and provided the reference system of location or contents for combining geoinformation. Framework Data is consist of Data Set, Data Model and UFID (Unique Feature Identifier). It will be achieved as national infrastructure data. This paper attempts to explore a method of the update to practical framework data with realtime geoinformation on feature's creation, modification and destruction managed by 'Feature management agency' using UFID's process. Furthermore, it suggests a method which can provide important data in order to plan the Framework update with the land change ratio.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.11
• /
• pp.5427-5445
• /
• 2019

While deep neural networks have achieved remarkable performance in representation learning, a huge amount of labeled training data are usually required by supervised deep models such as convolutional neural networks. In this paper, we propose a new representation learning method, namely generative adversarial networks (GAN) based bagging deep convolutional autoencoders (GAN-BDCAE), which can map data to diverse hierarchical representations in an unsupervised fashion. To boost the size of training data, to train deep model and to aggregate diverse learning machines are the three principal avenues towards increasing the capabilities of representation learning of neural networks. We focus on combining those three techniques. To this aim, we adopt GAN for realistic unlabeled sample generation and bagging deep convolutional autoencoders (BDCAE) for robust feature learning. The proposed method improves the discriminative ability of learned feature embedding for solving subsequent pattern recognition problems. We evaluate our approach on three standard benchmarks and demonstrate the superiority of the proposed method compared to traditional unsupervised learning methods.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.8
• /
• pp.3136-3150
• /
• 2015

A vision-based 3D tracking of articulated human hand is one of the major issues in the applications of human computer interactions and understanding the control of robot hand. This paper presents an improved approach for tracking and recovering the 3D position and orientation of a human hand using the Kinect sensor. The basic idea of the proposed method is to solve an optimization problem that minimizes the discrepancy in 3D shape between an actual hand observed by Kinect and a hypothesized 3D hand model. Since each of the 3D hand pose has 23 degrees of freedom, the hand articulation tracking needs computational excessive burden in minimizing the 3D shape discrepancy between an observed hand and a 3D hand model. For this, we first created a 3D hand model which represents the hand with 17 different parts. Secondly, Random Forest classifier was trained on the synthetic depth images generated by animating the developed 3D hand model, which was then used for Haar-like feature-based classification rather than performing per-pixel classification. Classification results were used for estimating the joint positions for the hand skeleton. Through the experiment, we were able to prove that the proposed method showed improvement rates in hand part recognition and a performance of 20-30 fps. The results confirmed its practical use in classifying hand area and successfully tracked and recovered the 3D hand pose in a real time fashion.

• Journal of Information Processing Systems
• /
• v.20 no.4
• /
• pp.558-573
• /
• 2024

Considering factors such as illumination, camera quality variations, and background-specific variations, identifying a face using a smartphone-based facial image capture application is challenging. Face Image Quality Assessment refers to the process of taking a face image as input and producing some form of "quality" estimate as an output. Typically, quality assessment techniques use deep learning methods to categorize images. The models used in deep learning are shown as black boxes. This raises the question of the trustworthiness of the models. Several explainability techniques have gained importance in building this trust. Explainability techniques provide visual evidence of the active regions within an image on which the deep learning model makes a prediction. Here, we developed a technique for reliable prediction of facial images before medical analysis and security operations. A combination of gradient-weighted class activation mapping and local interpretable model-agnostic explanations were used to explain the model. This approach has been implemented in the preselection of facial images for skin feature extraction, which is important in critical medical science applications. We demonstrate that the use of combined explanations provides better visual explanations for the model, where both the saliency map and perturbation-based explainability techniques verify predictions.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.6 no.2
• /
• pp.101-112
• /
• 2003

This paper designs and implements the management system that can calibrate the contamination vulnerability of the ground water, using an object oriented data model. Geographic-objects are specified by features extracted from an applicable geographic domain, and geographic-fields are defined by chemical factors extracted from each driven water. To show the topological relationships among the geographic-objects and the geographic-fields, this paper attach the weight and the ratio of the drastic model to chemical factors represented on the land use digital map and the ground water digital map. The geographic feature class, administrative boundary class, land use class and driven water class consist of a class composition hierarchy for evaluating the convenient contamination vulnerability calibration with spatial relationships among the well objects. Therefore, this management system for evaluating the contamination vulnerability can also contribute to the application of other natural environments.