• Journal of The Korean Association of Information Education
• /
• v.24 no.5
• /
• pp.473-481
• /
• 2020

Data science starts with small data analysis and includes machine learning and deep learning for big data analysis. Data science is a core area of artificial intelligence technology and should be systematically reflected in the school curriculum. For data science education, The Entry also provides a data analysis tool for elementary education. In a big data analysis, data samples are extracted and analysis results are interpreted through statistical guesses and judgments. In this paper, the big data analysis area that requires statistical knowledge is excluded from the elementary area, and data science education examples focusing on the elementary area are proposed. To this end, the general data science education stage was explained first, and the elementary data science education stage was newly proposed. After that, an example of comparing values of data variables and an example of analyzing correlations between data variables were proposed with public small data provided by Entry, according to the elementary data science education stage. By using these Entry data-analysis examples proposed in this paper, it is possible to provide data science convergence education in elementary school, with given data generated from various subjects. In addition, data science educational materials combined with text, audio and video recognition AI tools can be developed by using the Entry.

• The Korean Journal of Applied Statistics
• /
• v.35 no.3
• /
• pp.407-419
• /
• 2022

The semiconductor fabrication process is complex and time-consuming. There are sometimes errors in the process, which results in defective die on the wafer bin map (WBM). We can detect the faulty WBM by finding some patterns caused by dies. When one manually seeks the failure on WBM, it takes a long time due to the enormous number of WBMs. We suggest a two-step approach to discover the probable pattern on the WBMs in this paper. The first step is to separate the normal WBMs from the defective WBMs. We adapt a hierarchical clustering for de-noising, which nicely performs this work by wisely tuning the number of minimum points and the cutting height. Once declared as a faulty WBM, then it moves to the next step. In the second step, we classify the patterns among the defective WBMs. For this purpose, we extract features from the WBM. Then machine learning algorithm classifies the pattern. We use a real WBM data set (WM-811K) released by Taiwan semiconductor manufacturing company.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.3
• /
• pp.145-151
• /
• 2023

3D-CNN is one of the deep learning techniques for learning time series data. Such three-dimensional learning can generate many parameters, so that high-performance machine learning is required or can have a large impact on the learning rate. When learning dynamic hand-gestures in spatiotemporal domain, it is necessary for the improvement of the efficiency of dynamic hand-gesture learning with 3D-CNN to find the optimal conditions of input video data by analyzing the learning accuracy according to the spatiotemporal change of input video data without structural change of the 3D-CNN model. First, the time ratio between dynamic hand-gesture actions is adjusted by setting the learning interval of image frames in the dynamic hand-gesture video data. Second, through 2D cross-correlation analysis between classes, similarity between image frames of input video data is measured and normalized to obtain an average value between frames and analyze learning accuracy. Based on this analysis, this work proposed two methods to effectively select input video data for 3D-CNN deep learning of dynamic hand-gestures. Experimental results showed that the learning interval of image data frames and the similarity of image frames between classes can affect the accuracy of the learning model.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2024.01a
• /
• pp.55-58
• /
• 2024

최근 각 기업의 AI 면접시스템 도입이 증가하고 있으며, AI 면접에 대한 실효성 논란 또한 많은 상황이다. 본 논문에서는 AI 면접 과정에서 지원자를 평가하는 방식을 시각, 음성, 자연어처리 3영역에서 구현함으로써, 면접 지원자를 다방면으로 분석 방법론의 적절성에 대해 평가하고자 한다. 첫째, 시각적 측면에서, 면접 지원자의 감정을 인식하기 위해, 합성곱 신경망(CNN) 기법을 활용해, 지원자 얼굴에서 6가지 감정을 인식했으며, 지원자가 카메라를 응시하고 있는지를 시계열로 도출하였다. 이를 통해 지원자가 면접에 임하는 태도와 특히 얼굴에서 드러나는 감정을 분석하는 데 주력했다. 둘째, 시각적 효과만으로 면접자의 태도를 파악하는 데 한계가 있기 때문에, 지원자 음성을 주파수로 환산해 특성을 추출하고, Bidirectional LSTM을 활용해 훈련해 지원자 음성에 따른 6가지 감정을 추출했다. 셋째, 지원자의 발언 내용과 관련해 맥락적 의미를 파악해 지원자의 상태를 파악하기 위해, 음성을 STT(Speech-to-Text) 기법을 이용하여 텍스트로 변환하고, 사용 단어의 빈도를 분석하여 지원자의 언어 습관을 파악했다. 이와 함께, 지원자의 발언 내용에 대한 감정 분석을 위해 KoBERT 모델을 적용했으며, 지원자의 성격, 태도, 직무에 대한 이해도를 파악하기 위해 객관적인 평가지표를 제작하여 적용했다. 논문의 분석 결과 AI 면접의 다면적 평가시스템의 적절성과 관련해, 시각화 부분에서는 상당 부분 정확도가 객관적으로 입증되었다고 판단된다. 음성에서 감정분석 분야는 면접자가 제한된 시간에 모든 유형의 감정을 드러내지 않고, 또 유사한 톤의 말이 진행되다 보니 특정 감정을 나타내는 주파수가 다소 집중되는 현상이 나타났다. 마지막으로 자연어처리 영역은 면접자의 발언에서 나오는 말투, 특정 단어의 빈도수를 넘어, 전체적인 맥락과 느낌을 이해할 수 있는 자연어처리 분석모델의 필요성이 더욱 커졌음을 판단했다.

• Informatization Policy
• /
• v.31 no.2
• /
• pp.3-38
• /
• 2024

Hallucination is a significant barrier to the utilization of large-scale language models or multimodal models. In this study, we collected 654 computer science papers with "hallucination" in the abstract from arXiv from December 2022 to January 2024 following the advent of Chat GPT and conducted frequency analysis, knowledge network analysis, and literature review to explore the latest trends in hallucination research. The results showed that research in the fields of "Computation and Language," "Artificial Intelligence," "Computer Vision and Pattern Recognition," and "Machine Learning" were active. We then analyzed the research trends in the four major fields by focusing on the main authors and dividing them into data, hallucination detection, and hallucination mitigation. The main research trends included hallucination mitigation through supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF), inference enhancement via "chain of thought" (CoT), and growing interest in hallucination mitigation within the domain of multimodal AI. This study provides insights into the latest developments in hallucination research through a technology-oriented literature review. This study is expected to help subsequent research in both engineering and humanities and social sciences fields by understanding the latest trends in hallucination research.

• Journal of Intelligence and Information Systems
• /
• v.28 no.1
• /
• pp.89-106
• /
• 2022

Recently, the amount of video data collected from smartphones, CCTVs, black boxes, and high-definition cameras has increased rapidly. According to the increasing video data, the requirements for analysis and utilization are increasing. Due to the lack of skilled manpower to analyze videos in many industries, machine learning and artificial intelligence are actively used to assist manpower. In this situation, the demand for various computer vision technologies such as object detection and tracking, action detection, emotion detection, and Re-ID also increased rapidly. However, the object detection and tracking technology has many difficulties that degrade performance, such as re-appearance after the object's departure from the video recording location, and occlusion. Accordingly, action and emotion detection models based on object detection and tracking models also have difficulties in extracting data for each object. In addition, deep learning architectures consist of various models suffer from performance degradation due to bottlenects and lack of optimization. In this study, we propose an video analysis system consists of YOLOv5 based DeepSORT object tracking model, SlowFast based action recognition model, Torchreid based Re-ID model, and AWS Rekognition which is emotion recognition service. Proposed model uses single-linkage hierarchical clustering based Re-ID and some processing method which maximize hardware throughput. It has higher accuracy than the performance of the re-identification model using simple metrics, near real-time processing performance, and prevents tracking failure due to object departure and re-emergence, occlusion, etc. By continuously linking the action and facial emotion detection results of each object to the same object, it is possible to efficiently analyze videos. The re-identification model extracts a feature vector from the bounding box of object image detected by the object tracking model for each frame, and applies the single-linkage hierarchical clustering from the past frame using the extracted feature vectors to identify the same object that failed to track. Through the above process, it is possible to re-track the same object that has failed to tracking in the case of re-appearance or occlusion after leaving the video location. As a result, action and facial emotion detection results of the newly recognized object due to the tracking fails can be linked to those of the object that appeared in the past. On the other hand, as a way to improve processing performance, we introduce Bounding Box Queue by Object and Feature Queue method that can reduce RAM memory requirements while maximizing GPU memory throughput. Also we introduce the IoF(Intersection over Face) algorithm that allows facial emotion recognized through AWS Rekognition to be linked with object tracking information. The academic significance of this study is that the two-stage re-identification model can have real-time performance even in a high-cost environment that performs action and facial emotion detection according to processing techniques without reducing the accuracy by using simple metrics to achieve real-time performance. The practical implication of this study is that in various industrial fields that require action and facial emotion detection but have many difficulties due to the fails in object tracking can analyze videos effectively through proposed model. Proposed model which has high accuracy of retrace and processing performance can be used in various fields such as intelligent monitoring, observation services and behavioral or psychological analysis services where the integration of tracking information and extracted metadata creates greate industrial and business value. In the future, in order to measure the object tracking performance more precisely, there is a need to conduct an experiment using the MOT Challenge dataset, which is data used by many international conferences. We will investigate the problem that the IoF algorithm cannot solve to develop an additional complementary algorithm. In addition, we plan to conduct additional research to apply this model to various fields' dataset related to intelligent video analysis.

• Proceedings of the Korean Institute Of Construction Engineering and Management
• /
• autumn
• /
• pp.180-185
• /
• 2003

The increase of traffic over a bridge has been emerged as one of the most severe problems in view of bridge maintenance, since the load effect caused by the vehicle passage over the bridge has brought out a long-term damage to bridge structure, and it is nearly impossible to maintain operational serviceability of bridge to user's satisfactory level without any concern on bridge maintenance at the phase of completion. Moreover, bridge maintenance operation should be performed by regular inspection over the bridge to prevent structural malfunction or unexpected accidents front breaking out by monitoring on cracks or deformations during service. Therefore, technical breakthrough related to this uninterested field of bridge maintenance leading the public to the turning point of recognition is desperately needed. This study has the aim of development on automated inspection system to lower surface of bridge superstructures to replace the conventional system of bridge inspection with the naked eye, where the monitoring staff is directly on board to refractive or other type of maintenance .vehicles, with which it is expected that we can solve the problems essentially where the results of inspection are varied to change with subjective manlier from monitoring staff, increase stabilities in safety during the inspection, and make contribution to construct data base by providing objective and quantitative data and materials through image processing method over data captured by cameras. By this system it is also expected that objective estimation over the right time of maintenance and reinforcement work will lead enormous decrease in maintenance cost.

• Journal of Intelligence and Information Systems
• /
• v.17 no.3
• /
• pp.25-41
• /
• 2011

Recently, support vector machines (SVMs) are being recognized as competitive tools as compared with other data mining techniques for solving pattern recognition or classification decision problems. Furthermore, many researches, in particular, have proved them more powerful than traditional artificial neural networks (ANNs) (Amendolia et al., 2003; Huang et al., 2004, Huang et al., 2005; Tay and Cao, 2001; Min and Lee, 2005; Shin et al., 2005; Kim, 2003).The classification decision, such as a binary or multi-class decision problem, used by any classifier, i.e. data mining techniques is so cost-sensitive particularly in financial classification problems such as the credit ratings that if the credit ratings are misclassified, a terrible economic loss for investors or financial decision makers may happen. Therefore, it is necessary to convert the outputs of the classifier into wellcalibrated posterior probabilities-based multiclass credit ratings according to the bankruptcy probabilities. However, SVMs basically do not provide such probabilities. So it required to use any method to create the probabilities (Platt, 1999; Drish, 2001). This paper applied AdaBoost algorithm-based support vector machines (SVMs) into a bankruptcy prediction as a binary classification problem for the IT companies in Korea and then performed the multi-class credit ratings of the companies by making a normal distribution shape of posterior bankruptcy probabilities from the loss functions extracted from the SVMs. Our proposed approach also showed that their methods can minimize the misclassification problems by adjusting the credit grade interval ranges on condition that each credit grade for credit loan borrowers has its own credit risk, i.e. bankruptcy probability.

• Journal of IKEEE
• /
• v.25 no.3
• /
• pp.493-500
• /
• 2021

In this paper, we propose the development of deep learning structure to improve quality of polygonal containers. The deep learning structure consists of a convolution layer, a bottleneck layer, a fully connect layer, and a softmax layer. The convolution layer is a layer that obtains a feature image by performing a convolution 3x3 operation on the input image or the feature image of the previous layer with several feature filters. The bottleneck layer selects only the optimal features among the features on the feature image extracted through the convolution layer, reduces the channel to a convolution 1x1 ReLU, and performs a convolution 3x3 ReLU. The global average pooling operation performed after going through the bottleneck layer reduces the size of the feature image by selecting only the optimal features among the features of the feature image extracted through the convolution layer. The fully connect layer outputs the output data through 6 fully connect layers. The softmax layer multiplies and multiplies the value between the value of the input layer node and the target node to be calculated, and converts it into a value between 0 and 1 through an activation function. After the learning is completed, the recognition process classifies non-circular glass bottles by performing image acquisition using a camera, measuring position detection, and non-circular glass bottle classification using deep learning as in the learning process. In order to evaluate the performance of the deep learning structure to improve quality of polygonal containers, as a result of an experiment at an authorized testing institute, it was calculated to be at the same level as the world's highest level with 99% good/defective discrimination accuracy. Inspection time averaged 1.7 seconds, which was calculated within the operating time standards of production processes using non-circular machine vision systems. Therefore, the effectiveness of the performance of the deep learning structure to improve quality of polygonal containers proposed in this paper was proven.

• Journal of Korean Academy of Nursing
• /
• v.11 no.1
• /
• pp.65-87
• /
• 1981

The study is aimed at exploring concept held by clinical nurses of nursing. The data were collected from 225 nurses conviniently selected from the population of nurses working in Kang Won province. Findings include. 1) Nurse's Qualification. The respondents view that specialized knowledge is more important qualification of the nurse. Than warm personality. Specifically, 92.9% of the respondents indicated specialized knowledge as the most important qualification while only 43.1％ indicated warm personality. 2) On Nursing Profession. The respondents view that nursing profession as health service oriented rather than independent profession specifically. This suggests that nursing profession is not consistentic present health care delivery system nor support nurses working independently. 3) On Clients of Nursing Care The respondents include patients, family and the community residents in the category of nursing care. Specifically, 92.0％ of the respondents view that patient is the client, while only 67.1％ of nursing student and 74.7％ of herself. This indicates the lack of the nurse's recognition toward their clients. 4) On the Priority of Nursing care. Most of the respondents view the clients physical psychological respects as important component of nursing care but not the spiritual ones. Specially, 96.0% of the respondents indicated the physical respects, 93% psychological ones, while 64.1% indicated the spiritual ones. This means the lack of comprehensive conception on nursing aimension. 5) On Nursing Care. 91.6% of the respondents indicated that nursing care is the activity decreasing pain or helping to recover illness, while only 66.2% indicated earring out the physicians medical orders. 6) On Purpose of Nursing Care. 89.8% of the respondents indicated preventing illness and than 76.6% of them decreasing 1;ai of clients. On the other hand, maintaining health has the lowest selection at the degree of 13.8%. This means the lack of nurses' recognition for maintaining health as the most important point. 7) On Knowledge Needed in Nursing Care. Most of the respondents view that the knowledge faced with the spot of nursing care is needed. Specially, 81.3% of the respondents indicated simple curing method and 75.1%, 73.3%, 71.6% each indicated child nursing, maternal nursing and controlling for the communicable disease. On the other hand, knowledge w hick has been neglected in the specialized courses of nursing education, that is, thinking line among com-w unity members, overcoming style against between stress and personal relation in each home, and administration, management have a low selection at the depree of 48.9%,41.875 and 41.3%. 8) On Nursing Idea. The highest degree of selection is that they know themselves rightly, (The mean score measuring distribution was 4.205/5) In the lowest degree,3.016/5 is that devotion is the essential element of nursing, 2.860/5 the religious problems that human beings can not settle, such as a fatal ones, 2,810/5 the nursing profession is worth trying in one's life. This means that the peculiarly essential ideas on the professional sense of value. 9) On Nursing Services. The mean score measuring distribution for the nursing services showed that the inserting of machine air way is 2.132/5, the technique and knowledge for surviving heart-lung resuscitating is 2.892/s, and the preventing air pollution 3.021/5. Specially, 41.1% of the respondents indicated the lack of the replied ratio. 10) On Nurses' Qualifications. The respondents were selected five items as the most important qualifications. Specially, 17.4% of the respondents indicated specialized knowledge, 15.3% the nurses' health, 10.6％ satisfaction for nursing profession, 9.8% the experience need, 9.2% comprehension and cooperation, while warm personality as nursing qualifications have a tendency of being lighted. 11) On the Priority of Nursing Care The respondents were selected three items as the most important component. Most of the respondents view the client's physical, spiritual: economic points as important components of nursing care. They showed each 36.8%, 27.6%, 13.8% while educational ones showed 1.8%. 12) On Purpose of Nursing Care. The respondents were selected four items as the most important purpose. Specially,29.3% of the respondents indicated curing illness for clients, 21.3% preventing illness for client 17.4% decreasing pain, 15.3% surviving. 13) On the Analysis of Important Nursing Care Ranging from 5 point to 25 point, the nurses' qualification are concentrated at the degree of 95.1%. Ranging from 3 point to 25, the priorities of nursing care are concentrated at the degree of 96.4%. Ranging from 4 point to 16, the purpose of nursing care is concentrated at the degree of 84.0%. 14) The Analysis, of General Characteristics and Facts of Nursing Concept. The correlation between the educational high level and nursing care showed significance. (P < 0.0262). The correction between the educational low level and purpose of nursing care showed significance. (P < 0.002) The correlation between nurses' working yeras and the degree of importance for the purpose of nursing care showed significance (P < 0.0155) Specially, the most affirmative answers were showed from two years to four ones. 15) On Nunes' qualification and its Degree of Importance The correlation between nurses' qualification and its degree of importance showed significance. (r = 0.2172, p< 0.001) 0.005) B. General characteristics of the subjects The mean age of the subject was 39 ; with 38.6% with in the age range of 20-29 ; 52.6% were male; 57.9％ were Schizophrenia; 35.1% were graduated from high school or high school dropouts; 56.l％ were not have any religion; 52.6% were unmarried； 47.4% were first admission; 91.2% were involuntary admission patients. C. Measurement of anxiety variables. 1. Measurement tools of affective anxiety in this study demonstrated high reliability (.854). 2. Measurement tools of somatic anxiety in this study demonstrated high reliability (.920). D. Relationship between the anxiety variables and the general characteristics. 1. Relationship between affective anxiety and general characteristics. 1) The level of female patients were higher than that of the male patient (t = 5.41, p < 0.05). 2) Frequencies of admission were related to affective anxiety, so in the first admission the anxiety level was the highest. (F = 5.50, p < 0.005). 2, Relationship between somatic anxiety and general characteristics. 1) The age range of 30-39 was found to have the highest level of the somatic anxiety. (F = 3.95, p < 0.005). 2) Frequencies of admission were related to the somatic anxiety, so .in first admission the anxiety level was the highest. (F = 9.12, p ＜ 0.005) 0. Analysis of significant anxiety symptoms for nursing intervention. 1. Seven items such as dizziness, mental integration, sweating, restlessness, anxiousness, urinary frequency and insomnia, init. accounted for 96％ of the variation within the first 24 hours after admission. 2. Seven items such as fear, paresthesias, restlessness, sweating insomnia, init., tremors and body aches and pains accounted for 84% of the variation on the 10th day after admission.