• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.9
• /
• pp.345-351
• /
• 2020

Administrative agencies today are paying keen attention to big data analysis to improve their policy responsiveness. Of all the big data, news articles can be used to understand public opinion regarding policy and policy issues. The amount of news output has increased rapidly because of the emergence of new online media outlets, which calls for the use of automated bots or automatic document classification tools. There are, however, limits to the automatic collection of news articles related to specific agencies or departments based on the existing news article categories and keyword search queries. Thus, this paper proposes a method to process articles using classification glossaries that take into account each agency's different work features. To this end, classification glossaries were developed by extracting the work features of different departments using Word2Vec and topic modeling techniques from news articles related to different agencies. As a result, the automatic classification of newspaper articles for each department yielded approximately 71% accuracy. This study is meaningful in making academic and practical contributions because it presents a method of extracting the work features for each department, and it is an unsupervised learning-based automatic classification method for automatically classifying news articles relevant to each agency.

• Science of Emotion and Sensibility
• /
• v.22 no.4
• /
• pp.31-44
• /
• 2019

This study intended to investigate the effects of the subtitle location on the decreased working memory abilities caused by aging. A junior group (average age: 26, SD: 3.06, N=27) and a senior group (average age: 61.69, SD=4.18, N=26) participated in this study and they all performed N-back tasks which measured the working memory ability of the participants and video subtitle recognition tasks that assessed the most effectively recognized subtitle locations in the video. The results of the N-back task revealed slower response times and low accuracy rates in the senior group in comparison to the junior group, suggesting lower working memory abilities in the senior group vis-à-vis the junior group. The deterioration of working memory due to aging also negatively influenced the 'left-bottom' subtitle location in the video subtitle recognition task and positively influenced the 'left-center' location of the screen. The deterioration of working memory ability did not affect other subtitle locations. By examining the positive or negative effects of the deterioration of working memory ability as a function of age on subtitle locations, the present study suggests that the selection of suitable subtitle locations taking into account the ages of video viewers would cause information to be more effectively displayed on screen.

• The Mathematical Education
• /
• v.63 no.2
• /
• pp.165-186
• /
• 2024

Despite the growing attention on artificial intelligence-based automated scoring technology as a support method for the introduction of descriptive items in school environments and large-scale assessments, there is a noticeable lack of foundational research in mathematics compared to other subjects. This study developed an automated scoring model for two descriptive items in first-year middle school mathematics using the Random Forest algorithm, evaluated its performance, and explored ways to enhance this performance. The accuracy of the final models for the two items was found to be between 0.95 to 1.00 and 0.73 to 0.89, respectively, which is relatively high compared to automated scoring models in other subjects. We discovered that the strategic selection of the number of evaluation categories, taking into account the amount of data, is crucial for the effective development and performance of automated scoring models. Additionally, text preprocessing by mathematics education experts proved effective in improving both the performance and interpretability of the automated scoring model. Selecting a vectorization method that matches the characteristics of the items and data was identified as one way to enhance model performance. Furthermore, we confirmed that oversampling is a useful method to supplement performance in situations where practical limitations hinder balanced data collection. To enhance educational utility, further research is needed on how to utilize feature importance derived from the Random Forest-based automated scoring model to generate useful information for teaching and learning, such as feedback. This study is significant as foundational research in the field of mathematics descriptive automatic scoring, and there is a need for various subsequent studies through close collaboration between AI experts and math education experts.

• KIPS Transactions on Software and Data Engineering
• /
• v.4 no.1
• /
• pp.57-64
• /
• 2015

Activity recognition technology is gaining attention because it can provide useful information follow user's situation. In research of activity recognition before smartphone's dissemination, we had to infer user's activity by using independent sensor. But now, with development of IT industry, we can infer user's activity by using inner sensor of smartphone. So, more animated research of activity recognition is being implemented now. By applying activity recognition system, we can develop service like recommending application according to user's preference or providing information of route. Some previous activity recognition systems have a defect using up too much energy, because they use GPS sensor. On the other hand, activity recognition system which Google released recently (Google Activity Recognition) needs only a few power because it use 'Network Provider' instead of GPS. Thus it is suitable to smartphone application system. But through a result from testing performance of Google Activity Recognition, we found that is difficult to getting user's exact activity because of unnecessary activity element and some wrong recognition. So, in this paper, we describe problems of Google Activity Recognition and propose AGAR(Advanced Google Activity Recognition) applied method to improve accuracy level because we need more exact activity recognition for new service based on activity recognition. Also to appraise value of AGAR, we compare performance of other activity recognition systems and ours and explain an applied possibility of AGAR by developing exemplary program.

• Korean Journal of Remote Sensing
• /
• v.28 no.1
• /
• pp.171-180
• /
• 2012

The field of wildlife habitat conservation research has attracted attention as integrated biodiversity management strategies. Considering the status of the species surveying data and the environmental variables in Korea, the GARP and Maxent models optimized for presence-only data could be one of the most suitable models in habitat modeling. For make sure applicability in the domestic environment we applied the machine learning species distribution model for analyzing habitats of the Korea water deer($Hydropotes$ $inermis$ $argyropus$) in the $Sapgyocheon$ watershed, $Chungcheong$ province. We used the $3^{rd}$ National Natural Environment Survey data and 10 environment variables by literature review for the modelling. Analysis results showed that habitats for the Korea water deer were predicted 16.3%(Maxent) and 27.1%(GARP), respectively. In terms of accuracy(training/test) the Maxent(0.85/0.69) was higher than the GARP(0.65/0.61), and the Spearman's rank correlation coefficient result of the Maxent(${\rho}$=0.71, p<0.01) was higher than the result of GARP(${\rho}$=0.55, p<0.05). However results could be depended on sites and target species, therefore selection of the appropriate model considering on the situation will be important to analyzing habitats.

• Journal of Broadcast Engineering
• /
• v.23 no.3
• /
• pp.351-360
• /
• 2018

Human emotion recognition is a research topic that is receiving continuous attention in computer vision and artificial intelligence domains. This paper proposes a method for classifying human emotions through multiple neural networks based on multi-modal signals which consist of image, landmark, and audio in a wild environment. The proposed method has the following features. First, the learning performance of the image-based network is greatly improved by employing both multi-task learning and semi-supervised learning using the spatio-temporal characteristic of videos. Second, a model for converting 1-dimensional (1D) landmark information of face into two-dimensional (2D) images, is newly proposed, and a CNN-LSTM network based on the model is proposed for better emotion recognition. Third, based on an observation that audio signals are often very effective for specific emotions, we propose an audio deep learning mechanism robust to the specific emotions. Finally, so-called emotion adaptive fusion is applied to enable synergy of multiple networks. The proposed network improves emotion classification performance by appropriately integrating existing supervised learning and semi-supervised learning networks. In the fifth attempt on the given test set in the EmotiW2017 challenge, the proposed method achieved a classification accuracy of 57.12%.

• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.12
• /
• pp.491-498
• /
• 2019

Digital twin is a technology that virtualizes physical objects of the real world on a computer. It is used by collecting sensor data through IoT, and using the collected data to connect physical objects and virtual objects in both directions. It has an advantage of minimizing risk by tuning an operation of virtual model through simulation and responding to varying environment by exploiting experiments in advance. Recently, artificial intelligence and machine learning technologies have been attracting attention, so that tendency to virtualize a behavior of physical objects, observe virtual models, and apply various scenarios is increasing. In particular, recognition of each robot's motion is needed to build digital twin for co-robot which is a heart of industry 4.0 factory automation. Compared with modeling based research for recognizing motion of co-robot, there are few attempts to predict motion based on sensor data. Therefore, in this paper, an experimental environment for collecting current and inertia data in co-robot to detect the motion of the robot is built, and a motion prediction model based on the collected sensor data is proposed. The proposed method classifies the co-robot's motion commands into 9 types based on joint position and uses current and inertial sensor values to predict them by accumulated learning. The data used for accumulating learning is the sensor values that are collected when the co-robot operates with margin in input parameters of the motion commands. Through this, the model is constructed to predict not only the nine movements along the same path but also the movements along the similar path. As a result of learning using SVM, the accuracy, precision, and recall factors of the model were evaluated as 97% on average.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.4
• /
• pp.137-144
• /
• 2020

Delirium is among the most common mental disorders encountered in patients with a temporary cognitive impairment such as consciousness disorder, attention disorder, and poor speech, particularly among those who are older. Delirium is distressing for patients and families, can interfere with the management of symptoms such as pain, and is associated with increased elderly mortality. The purpose of this paper is to generate useful clinical knowledge that can be used to distinguish the outcomes of patients with delirium in long-term care facilities. For this purpose, we extracted the clinical classification knowledge associated with delirium using a local covering rule acquisition approach with the rough lower approximation region. The clinical applicability of the proposed method was verified using data collected from a prospective cohort study. From the results of this study, we found six useful clinical pieces of evidence that the duration of delirium could more than 12 days. Also, we confirmed eight factors such as BMI, Charlson Comorbidity Index, hospitalization path, nutrition deficiency, infection, sleep disturbance, bed scores, and diaper use are important in distinguishing the outcomes of delirium patients. The classification performance of the proposed method was verified by comparison with three benchmarking models, ANN, SVM with RBF kernel, and Random Forest, using a statistical five-fold cross-validation method. The proposed method showed an improved average performance of 0.6% and 2.7% in both accuracy and AUC criteria when compared with the SVM model with the highest classification performance of the three models respectively.

• Journal of Korea Society of Industrial Information Systems
• /
• v.11 no.4
• /
• pp.82-92
• /
• 2006

In the field of image recognition, research on face recognition has recently attracted a lot of attention. The most important step in face recognition is automatic eye detection researched as a prerequisite stage. Existing eye detection methods for focusing on the frontal face can be mainly classified into two categories: active infrared(IR)-based approaches and image-based approaches. This paper proposes an eye region detection method in non-frontal faces. The proposed method is based on the edge--based method that shows the fastest computation time. To extract eye region in non-frontal faces, the method uses edge orientationhistogram of the global region of faces. The problem caused by some noise and unfavorable ambient light is solved by using proportion of width and height for local information and relationship between components for global information in approximately extracted region. In experimental results, the proposed method improved precision rates, as solving 3 problems caused by edge information and achieves a detection accuracy of 83.5% and a computational time of 0.5sec per face image using 300 face images provided by The Weizmann Institute of Science.

• Journal of radiological science and technology
• /
• v.39 no.3
• /
• pp.369-376
• /
• 2016

Positron Emission Tomography(PET) is nuclear medical tests which is a combination of several compounds with a radioactive isotope that can be injected into body to quantitatively measure the metabolic rate (in the body). Especially, Phenomena that increase (sing) glucose metabolism in cancer tissue using the $^{18}F$-FDG (Fluorodeoxyglucose) is utilized widely in cancer diagnosis. And then, Numerous studies have been reported that incidence seems high availability even in the modern diagnosis of dementia and Parkinson's (disease) in brain disease. When using a dynamic PET iamge including the time information in the static information that is provided for the diagnosis many can increase the accuracy of diagnosis. For this reason, clinical researchers getting great attention but, it is the lack of tools to conduct research. And, it interfered complex mathematical algorithm and programming skills for activation of research. In this study, in order to easy to use and enable research dPET, we developed the software based graphic user interface(GUI). In the future, by many clinical researcher using DIA-Tool is expected to be of great help to dPET research.