• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권7호
• /
• pp.2304-2320
• /
• 2021

Intelligently detecting anomalies in health sensor data streams (e.g., Electrocardiogram, ECG) can improve the development of E-health industry. The physiological signals of patients are collected through sensors. Timely diagnosis and treatment save medical resources, promote physical health, and reduce complications. However, it is difficult to automatically classify the ECG data, as the features of ECGs are difficult to extract. And the volume of labeled ECG data is limited, which affects the classification performance. In this paper, we propose a Generative Adversarial Network (GAN)-based deep learning framework (called CAB) for heart arrhythmia classification. CAB focuses on improving the detection accuracy based on a small number of labeled samples. It is trained based on the class-imbalance ECG data. Augmenting ECG data by a GAN model eliminates the impact of data scarcity. After data augmentation, CAB classifies the ECG data by using a Bidirectional Long Short Term Memory Recurrent Neural Network (Bi-LSTM). Experiment results show a better performance of CAB compared with state-of-the-art methods. The overall classification accuracy of CAB is 99.71%. The F1-scores of classifying Normal beats (N), Supraventricular ectopic beats (S), Ventricular ectopic beats (V), Fusion beats (F) and Unclassifiable beats (Q) heartbeats are 99.86%, 97.66%, 99.05%, 98.57% and 99.88%, respectively. Unclassifiable beats (Q) heartbeats are 99.86%, 97.66%, 99.05%, 98.57% and 99.88%, respectively.

• 경영과정보연구
• /
• 제21권
• /
• pp.239-269
• /
• 2007

The purpose of this thesis is to analyze empirically the relationship between market structure, measured by Herfindahl-Hershmann Index(HHI), and financial factors, and innovation in Korean industry panel datasets for 2000-2006. Results show that debt ratio and scale of the firm has a consistent positive effect on the investment in research and development. As more scale of the firm is getting bigger, the investment in R&D decrease. Also, as more debt ratio of firm rise, the investment for innovation increase. Concentration ratio, the HHI and the classification factor of High-tech industry and Low-tech industry has a consistent positive effect on the innovation. Factors affecting the investment in research and development include market structure and characteristics of industry as well as the internal affairs of the firm.

• 한국멀티미디어학회논문지
• /
• 제22권9호
• /
• pp.1122-1131
• /
• 2019

This paper covers research on terrain construction for unmanned aerial vehicle simulators using spatial information that was distributed by public institutions. Aerial photography, DEM, vector maps and 3D model data were used in order to create a realistic terrain simulator. A data converting method was suggested while researching, so it was generated to automatically arrange and build city models (vWorld provided) and classification methods so that realistic images could be generated by 3D objects. For example: rivers, forests, roads, fields and so on, were arranged by aerial photographs, vector map (land cover map) and terrain construction based on the tile map used by DEM. In order to verify the terrain data of unmanned aircraft simulators produced by the proposed method, the location accuracy was verified by mounting onto Unreal Engine and checked location accuracy.

• 산업경영시스템학회지
• /
• 제42권4호
• /
• pp.165-172
• /
• 2019

Innovation activities represented by Six Sigma (6σ) led to improvements not only in manufacturing industries but also in various business fields. In the aviation industry, Six Sigma has been used as a tool of innovation since the beginning of 2000, and it has developed into a comprehensive form of innovation activity that includes various improvement tools. In this study, the innovation activities in K company that is a representative company of aviation industry are summarized in the last 10 years, and the effectiveness of the innovation tools and the performance of the tasks are also analyzed. The results of 2,091 projects over the past decade have been analyzed from various perspectives. First, we found out the tools that were used frequently at each DMAIC step, showed their frequency, and analyzed the evaluation results for the project. The project was evaluated from grade 1 (highest level) to grade 7 (lowest level) with an average grade of 4.1 for the overall project. The evaluation grades of the projects were compared and analyzed in terms of the qualifications of the leader, the roadmap for the implementation of the project, the financial effect, the size of the financial effect, the business classification, and the project execution period. These results may suggest new perspectives for companies considering or adopting innovation programs.

• Nuclear Engineering and Technology
• /
• 제55권1호
• /
• pp.339-352
• /
• 2023

Prediction of the time-related traits of pebble flow inside pebble-bed HTGRs is of great significance for reactor operation and design. In this work, an image-driven approach with the aid of a convolutional neural network (CNN) is proposed to predict the remaining time of initially loaded pebbles and the time interval of paired flow images of the pebble bed. Two types of strategies are put forward: one is adding FC layers to the classic classification CNN models and using regression training, and the other is CNN-based deep expectation (DEX) by regarding the time prediction as a deep classification task followed by softmax expected value refinements. The current dataset is obtained from the discrete element method (DEM) simulations. Results show that the CNN-aided models generally make satisfactory predictions on the remaining time with the determination coefficient larger than 0.99. Among these models, the VGG19+DEX performs the best and its CumScore (proportion of test set with prediction error within 0.5s) can reach 0.939. Besides, the remaining time of additional test sets and new cases can also be well predicted, indicating good generalization ability of the model. In the task of predicting the time interval of image pairs, the VGG19+DEX model has also generated satisfactory results. Particularly, the trained model, with promising generalization ability, has demonstrated great potential in accurately and instantaneously predicting the traits of interest, without the need for additional computational intensive DEM simulations. Nevertheless, the issues of data diversity and model optimization need to be improved to achieve the full potential of the CNN-aided prediction tool.

• 한국컴퓨터정보학회논문지
• /
• 제24권1호
• /
• pp.25-32
• /
• 2019

With the rapid development of artificial intelligence technology, the patenting activities related to the fields of AI is increasing worldwide. In particular, a share of patent filed in China has exploded in recent years and overtakes the numbers in the US. In the present study, we focus our attention on the patenting activity of China and the US. We analyzed 6,281 and 13,664 patent applications in the US and China respectively between 2008 and 2018, and belonging to the "G06F(Electric Digital Data Processing)", "G06N(Computer Systems Based on Specific Computational Models)", "H04L(Transmission of Digital Information)" and nine more relevant technological classes, as indicated by the International Patent Classification(IPC). Our analysis contributes to: first, the understanding of patent application trends from foreign countries filed in the US and China, 2) patent application status by applicants category such as companies, universities and individuals, 3) the development direction and forecasting vacant technology of AI according to main IPC code. Through the analysis of this paper, we can suggest some implications for patent research related to artificial intelligence in Korea. Plus, by analyzing the most recent patent data, we can provide important information for future artificial intelligence technology research.

• 기술혁신학회지
• /
• 제9권2호
• /
• pp.304-324
• /
• 2006

재무분석가들은 기업의 파산에 양향을 미치는 예측변수를 탐색하기 위해서 상당한 연구가 수행되어 왔다. 그러나 기술지향적 중소벤처기업은 일반적으로 역사적 재무자료가 부족하고, 기술경쟁력 수준에 따라 잠재적인 고성장과 고위험이 존재한다. 본 논문에서는 재무자료 대신에 기술력평가 자료를 이용하여 파산을 예측하기 위해서 파산예측 판별모형을 제안하였고, 모형의 정분류율을 통해서 예측력을 검증하기 위해서 교차타당성방법, 최대사후확률방법 등을 사용하였다. 분석결과 중소 벤처기업의 파산예측모형으로 선형판별모형이 로지스틱판별모형보다 적합한 모형이고, 표본자료에 대한 정분류율 추정은 약 69% 이고 정분류율 예측은 약 67% 가 될 것으로 기대된다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권9호
• /
• pp.2904-2926
• /
• 2022

Currently, diabetes is the most common chronic disease in the world, affecting 23.7% of the population in the Kingdom of Saudi Arabia. Diabetes may be the cause of lower-limb amputations, kidney failure and blindness among adults. Therefore, diagnosing the disease in its early stages is essential in order to save human lives. With the revolution in technology, Artificial Intelligence (AI) could play a central role in the early prediction of diabetes by employing Machine Learning (ML) technology. In this paper, we developed a diagnosis system using machine learning models for the detection of type 2 diabetes among adults, through the adoption of two different diabetes datasets: one for training and the other for the testing, to analyze and enhance the prediction accuracy. This work offers an enhanced classification accuracy as a result of employing several pre-processing methods before applying the ML models. According to the obtained results, the implemented Random Forest (RF) classifier offers the best classification accuracy with a classification score of 98.95%.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• 제27권2호
• /
• pp.135-145
• /
• 2023

Recently, as deep learning technology has developed, various deep learning technologies have been introduced in handwritten recognition, greatly contributing to performance improvement. The recognition accuracy of handwritten Hangeul recognition has also improved significantly, but prior research has focused on recognizing 520 Hangul characters or 2,350 Hangul characters using SERI95 data or PE92 data. In the past, most of the expressions were possible with 2,350 Hangul characters, but as globalization progresses and information and communication technology develops, there are many cases where various foreign words need to be expressed in Hangul. In this paper, we propose a model that recognizes and combines the consonants, medial vowels, and final consonants of a Korean syllable using a multi-label classification model, and achieves a high recognition accuracy of 98.38% as a result of learning with the public data of Korean handwritten characters, PE92. In addition, this model learned only 2,350 Hangul characters, but can recognize the characters which is not included in the 2,350 Hangul characters

• 대한안전경영과학회지
• /
• 제16권1호
• /
• pp.213-220
• /
• 2014

This study suggests new approach to identify core technologies through patent analysis. Specially, the approach applied data mining technique and multi-criteria decision making method to the co-classification information of registered patents. First, technological interrelationship matrices of intensity, relatedness, and cross-impact perspectives are constructed with support, lift and confidence values calculated by conducting an association rule mining on the co-classification information of patent data. Second, the analytic network process is applied to the constructed technological interrelationship matrices in order to produce the importance values of technologies from each perspective. Finally, data envelopment analysis is employed to the derived importance values in order to identify priorities of technologies, putting three perspectives together. It is expected that suggested approach could help technology planners to formulate strategy and policy for technological innovation.