• Journal of IKEEE
• /
• v.2 no.1 s.2
• /
• pp.150-159
• /
• 1998

This paper described the recognition of the Off-line handwritten Hangul based on neural network using a feature extraction method. Features of Hangul can be extracted by a $5{\times}5$ window method which is the modified $3{\times}3$ mask method. These features are coded to binary patterns in order to use neural network's inputs efficiently. Hangul character is recognized by the consonant, the vertical vowel, and the horizontal vowel, separately. In order to verify the recognition rate, three different coding methods were used for neural networks. Three methods were the fixed-code method, the learned-code I method, and the learned-code II method. The result was shown that the learned-code II method was the best among three methods. The result of the learned-code II method was shown 100% recognition rate for the vertical vowel, 100% for the horizontal vowel, and 98.33% for the learned consonants and 93.75% for the new consonants.

• Journal of Biosystems Engineering
• /
• v.19 no.2
• /
• pp.124-137
• /
• 1994

Visual features of a mushroom(Lentinus Edodes, L.) are critical in grading and sorting as most agricultural products are. Because of its complex and various visual features, grading and sorting of mushrooms have been done manually by the human expert. To realize the automatic handling and grading of mushrooms in real time, the computer vision system should be utilized and the efficient and robust processing of the camera captured visual information be provided. Since visual features of a mushroom are distributed over the front and back sides, recognizing sides and states of the stalk including the stalk orientation from the captured image is a prime process in the automatic task processing. In this paper, the efficient and robust recognition process identifying the front and back side and the state of the stalk was developed and its performance was compared with other recognition trials. First, recognition was tried based on the rule set up with some experimental heuristics using the quantitative features such as geometry and texture extracted from the segmented mushroom image. And the neural net based learning recognition was done without extracting quantitative features. For network inputs the segmented binary image obtained from the combined type automatic thresholding was tested first. And then the gray valued raw camera image was directly utilized. The state of the stalk seriously affects the measured size of the mushroom cap. When its effect is serious, the stalk should be excluded in mushroom cap sizing. In this paper, the stalk removal process followed by the boundary regeneration of the cap image was also presented. The neural net based gray valued raw image processing showed the successful results for our recognition task. The developed technology through this research may open the new way of the quality inspection and sorting especially for the agricultural products whose visual features are fuzzy and not uniquely defined.

• Journal of Korea Game Society
• /
• v.17 no.6
• /
• pp.113-120
• /
• 2017

With the development of virtual reality technology, in recent years, user-friendly hand gesture interface has been more studied for natural interaction with a virtual 3D object. Most earlier studies on the hand-gesture interface are using relatively simple hand gestures. In this paper, we suggest an intuitive hand gesture interface for interaction with 3D object in the virtual reality applications. For hand gesture recognition, first of all, we preprocess various hand data and classify the data through the binary decision tree. The classified data is re-sampled and converted to the chain-code, and then constructed to the hand feature data with the histograms of the chain code. Finally, the input gesture is recognized by MCSVM-based machine learning from the feature data. To test our proposed hand gesture interface we implemented a 'Virtual Block' game. Our experiments showed about 99.2% recognition ratio of 16 kinds of command gestures and more intuitive and user friendly than conventional mouse interface.

• Korean Medical Education Review
• /
• v.19 no.3
• /
• pp.115-120
• /
• 2017

Despite the importance of how the premedical education curriculum is organized, the basic direction of the curriculum has not been evaluated at a fundamental level. In order to explore the basic directions of the premedical education curriculum, this study examined medical education as a university education, the historical basis of premedical education, and the direction of the premedical education curriculum. Historically, as medical education was incorporated into the university education system, premedical education developed based on basic science and liberal arts education. Accordingly, the direction of the premedical education curriculum began to split into two approaches: one believing in a basic science-based education intended to serve as the foundation of medical training, and the other believing in a liberal arts-based education intended to cultivate the qualities of a doctor. In recent years, however, the binary division in the direction of premedical education has ceased to exist, and the paradigm has now shifted to an agreement that premedical education must cultivate the basic scientific competence required for learning medical knowledge as well as the social qualities that a doctor should have, which are cultivated through the liberal arts. Furthermore, it has been asserted that the direction of premedical education should move toward the qualities that will be required in the future. With the fourth industrial revolution underway, the role of doctors is now being re-examined. This means that today's medical education must change in a future-oriented way, and the direction of the premedical education curriculum must be on the same page.

• The Journal of the Acoustical Society of Korea
• /
• v.40 no.4
• /
• pp.337-346
• /
• 2021

Detection of abnormal signal generally can be done by using features of normal signals as main information because of data imbalance. This paper propose an efficient method for abnormal signal detection using parallel AutoEncoder (AE) which can use features of abnormal signals as well. The proposed Parallel AE (PAE) is composed of a normal and an abnormal reconstructors having identical AE structure and train features of normal and abnormal signals, respectively. The PAE can effectively solve the imbalanced data problem by sequentially training normal and abnormal data. For further detection performance improvement, additional binary classifier can be added to the PAE. Through experiments using public acoustic data, we obtain that the proposed PAE shows Area Under Curve (AUC) improvement of minimum 22 % at the expenses of training time increased by 1.31 ~ 1.61 times to the single AE. Furthermore, the PAE shows 93 % AUC improvement in detecting abnormal underwater acoustic signal when pre-trained PAE is transferred to train open underwater acoustic data.

• The Journal of the Korea Contents Association
• /
• v.22 no.7
• /
• pp.548-562
• /
• 2022

This study was conducted to diagnose the issues of AI ethics in global content and to discuss what kind of discourse is needed to strengthen human identity. To this end, the study selected Netflix original content "The Social Dilemma" for analysis and adopted narrative analysis as the research method. The analysis results confirmed that "Social Dilemma" showed the structure of a traditional current affairs documentary and mainly used experts and statistical data to develop the story. It also reinforced core content claims by enumerating domestic and foreign cases such as the 2021 Myanmar massacre and the spread of fake news. In addition, the relationship between the characters clearly revealed the binary opposition between developers and media companies as well as users and advertisers. For the solution to the problem, strong regulations on businesses and the suspension of social media use were reached. However, "The Social Dilemma" merely pointed out the misuse of AI technology and had a narrative that ignored human identity and social relationships. Such results raise the need for creating contents that emphasize the importance of human sociality, relationships, and learning ability in the age of AI.

• Physical Therapy Rehabilitation Science
• /
• v.11 no.3
• /
• pp.285-295
• /
• 2022

Objective: The purpose of this study is to use logistic regression and decision tree analysis to identify the factors that affect the success or failurein the national physical therapy examination; and to build and compare predictive models. Design: Secondary data analysis study Methods: We analyzed 76,727 subjects from the physical therapy national examination data provided by the Korea Health Personnel Licensing Examination Institute. The target variable was pass or fail, and the input variables were gender, age, graduation status, and examination area. Frequency analysis, chi-square test, binary logistic regression, and decision tree analysis were performed on the data. Results: In the logistic regression analysis, subjects in their 20s (Odds ratio, OR=1, reference), expected to graduate (OR=13.616, p<0.001) and from the examination area of Jeju-do (OR=3.135, p<0.001), had a high probability of passing. In the decision tree, the predictive factors for passing result had the greatest influence in the order of graduation status (x²=12366.843, p<0.001) and examination area (x²=312.446, p<0.001). Logistic regression analysis showed a specificity of 39.6% and sensitivity of 95.5%; while decision tree analysis showed a specificity of 45.8% and sensitivity of 94.7%. In classification accuracy, logistic regression and decision tree analysis showed 87.6% and 88.0% prediction, respectively. Conclusions: Both logistic regression and decision tree analysis were adequate to explain the predictive model. Additionally, whether actual test takers passed the national physical therapy examination could be determined, by applying the constructed prediction model and prediction rate.

• Journal of the International Relations & Interdisciplinary Education
• /
• v.1 no.1
• /
• pp.61-79
• /
• 2021

In order to implement an artificial intelligence lawyer, this study looked at how to structure legal principles, and then gave specific examples of how structured legal principles can be expressed in predicate logic. While previous studies suggested a method of introducing predicate logic for the reasoning engine of artificial intelligence lawyers, this study focused on the method of expressing legal principles with predicate logic based on the structural appearance of legal principles. Jurisprudence was limited to the content of articles and precedents, and the vertical hierarchy leading to 'law facts - legal requirements - legal effect' and the horizontal hierarchy leading to 'legal effect - defense - defense' were examined. In addition, legal facts were classified and explained that most of the legal facts can be usually expressed in unary or binary predicates. In future research, we plan to program the legal principle expressed in predicate logic and realize an inference engine for artificial intelligence lawyers.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.11
• /
• pp.123-130
• /
• 2022

Recently, studies on the detection and classification of Android malware based on API Call sequence have been actively carried out. However, API Call sequence based malware classification has serious limitations such as excessive time and resource consumption in terms of malware analysis and learning model construction due to the vast amount of data and high-dimensional characteristic of features. In this study, we analyzed various classification models such as LightGBM, Random Forest, and k-Nearest Neighbors after significantly reducing the dimension of features using PCA(Principal Component Analysis) for CICAndMal2020 dataset containing vast API Call information. The experimental result shows that PCA significantly reduces the dimension of features while maintaining the characteristics of the original data and achieves efficient malware classification performance. Both binary classification and multi-class classification achieve higher levels of accuracy than previous studies, even if the data characteristics were reduced to less than 1% of the total size.

• Journal of radiological science and technology
• /
• v.46 no.4
• /
• pp.277-285
• /
• 2023

In this study, pneumonia identification networks with the small number of layers were constructed by using chest X-ray images. The networks had similar trainable-parameters, and the performance of the trained models was quantitatively evaluated with the modification of the network architectures. A total of 6 networks were constructed: convolutional neural network (CNN), VGGNet, GoogleNet, residual network with identity blocks, ResNet with bottleneck blocks and ResNet with identity and bottleneck blocks. Trainable parameters for the 6 networks were set in a range of 273,921-294,817 by adjusting the output channels of convolution layers. The network training was implemented with binary cross entropy (BCE) loss function, sigmoid activation function, adaptive moment estimation (Adam) optimizer and 100 epochs. The performance of the trained models was evaluated in terms of training time, accuracy, precision, recall, specificity and F1-score. The results showed that the trained models with the small number of layers precisely detect pneumonia from chest X-ray images. In particular, the overall quantitative performance of the trained models based on the ResNets was above 0.9, and the performance levels were similar or superior to those based on the CNN, VGGNet and GoogleNet. Also, the residual blocks affected the performance of the trained models based on the ResNets. Therefore, in this study, we demonstrated that the object detection networks with the small number of layers are suitable for detecting pneumonia using chest X-ray images. And, the trained models based on the ResNets can be optimized by applying appropriate residual-blocks.