• 대한응급의학회지
• /
• 제29권5호
• /
• pp.455-464
• /
• 2018

Objective: Machine learning is not yet widely used in the medical field. Therefore, this study was conducted to compare the performance of preexisting severity prediction models and machine learning based models (random forest [RF], gradient boosting [GB]) for mortality prediction in pneumonia patients. Methods: We retrospectively collected data from patients who visited the emergency department of a tertiary training hospital in Seoul, Korea from January to March of 2015. The Pneumonia Severity Index (PSI) and Sequential Organ Failure Assessment (SOFA) scores were calculated for both groups and the area under the curve (AUC) for mortality prediction was computed. For the RF and GB models, data were divided into a test set and a validation set by the random split method. The training set was learned in RF and GB models and the AUC was obtained from the validation set. The mean AUC was compared with the other two AUCs. Results: Of the 536 investigated patients, 395 were enrolled and 41 of them died. The AUC values of PSI and SOFA scores were 0.799 (0.737-0.862) and 0.865 (0.811-0.918), respectively. The mean AUC values obtained by the RF and GB models were 0.928 (0.899-0.957) and 0.919 (0.886-0.952), respectively. There were significant differences between preexisting severity prediction models and machine learning based models (P<0.001). Conclusion: Classification through machine learning may help predict the mortality of pneumonia patients visiting the emergency department.

• 한국컴퓨터정보학회논문지
• /
• 제14권3호
• /
• pp.139-147
• /
• 2009

메모리 기반 추론 기법은 단순히 학습패턴이나 대표패턴의 형태로 메모리에 저장하며 테스트 패턴과의 거리 계산을 통하여 분류한다. 이 기법의 가장 큰 문제점은 학습 패턴 전체를 메모리에 저장하거나 학습 패턴들을 대표 패턴으로 대체하는 방법을 사용함으로 다른 기계학습 방법에 비하여 많은 메모리 공간을 필요로 하며, 저장되는 학습패턴이 증가할수록 분류에 필요한 시간도 많이 소요된다는 단점을 갖는다. 본 논문은 효율적인 메모리 사용과 분류 성능의 향상을 위한 EAS 기법을 제안하였다. 즉, 학습패턴에 대해 분할공간을 생성한 후 생성된 각 분할공간을 MDL기법과 PM기법으로 평가하였다. 그리고 평가 결과 가장 우수한 분할공간만을 취하여 대표패턴으로 삼고 나머지는 다시 분할하여 평가를 반복하는 기법이다. UCI Machine Learning Repository에서 벤치마크 데이터를 발췌한 실험 자료를 사용하여 제안한 기법의 성능과 메모리 사용량에 있어 우수함을 입증하였다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 하계종합학술대회 논문집(3)
• /
• pp.135-138
• /
• 2002

This paper addresses incremental learning method for regression. SVM(support vector machine) is a recently proposed learning method. In general training a support vector machine requires solving a QP (quadratic programing) problem. For very large dataset or incremental dataset, solving QP problems may be inconvenient. So this paper presents an incremental support vector learning method for function approximation problems.

• 정보교육학회논문지
• /
• 제25권6호
• /
• pp.1015-1024
• /
• 2021

엔트리, Machine Learning for Kids, Teachable Machine과 같이 블록 기반 프로그래밍 언어에서 활용할 수 있도록 인공지능을 간단히 학습시킬 수 있는 다양한 플랫폼들이 존재한다. 그러나 이와 같은 플랫폼들은 별도의 메뉴를 통해 인공지능 학습을 진행한 다음, 학습된 모델을 코드 에디터에서 활용하는 방식을 따르고 있다. 이와 같은 방식은 학습되는 과정을 학생들이 더 직관적으로 살펴볼 수 있다는 장점이 있지만, 학습 메뉴와 코드 에디터를 모두 활용해야 한다는 단점도 존재한다. 본 논문에서는 코드 에디터에서 인공지능 학습과 코딩을 모두 진행할 수 있는 인공지능 블록을 개발한다. 본 인공지능 블록은 스크래치 블록으로 제시되지만 실제 학습 과정은 파이썬 서버를 통해 수행된다. 파란색 펜과 빨간색 펜을 분류하는 모델, 덴탈 마스크와 KF94 마스크를 분류하는 모델을 학습하는 과정을 통해 본 블록에 대해 상세히 기술한다. 또, 학습 성능 면에서 Teachable Machine와 큰 차이가 없음을 실험적으로 나타내었다.

• 국제물리치료학회지
• /
• 제12권1호
• /
• pp.2261-2266
• /
• 2021

Background: Deep learning related research works on website medical images have been actively conducted in the field of health care, however, articles related to the musculoskeletal system have been introduced insufficiently, deep learning-based studies on classifying orthopedic manual therapy images would also just be entered. Objectives: To create a deep learning model that categorizes cervical mobilization images and establish a web application to find out its clinical utility. Design: Research and development. Methods: Three types of cervical mobilization images (central posteroanterior (CPA) mobilization, unilateral posteroanterior (UPA) mobilization, and anteroposterior (AP) mobilization) were obtained using functions of 'Download All Images' and a web crawler. Unnecessary images were filtered from 'Auslogics Duplicate File Finder' to obtain the final 144 data (CPA=62, UPA=46, AP=36). Training classified into 3 classes was conducted in Teachable Machine. The next procedures, the trained model source was uploaded to the web application cloud integrated development environment (https://ide.goorm.io/) and the frame was built. The trained model was tested in three environments: Teachable Machine File Upload (TMFU), Teachable Machine Webcam (TMW), and Web Service webcam (WSW). Results: In three environments (TMFU, TMW, WSW), the accuracy of CPA mobilization images was 81-96%. The accuracy of the UPA mobilization image was 43~94%, and the accuracy deviation was greater than that of CPA. The accuracy of the AP mobilization image was 65-75%, and the deviation was not large compared to the other groups. In the three environments, the average accuracy of CPA was 92%, and the accuracy of UPA and AP was similar up to 70%. Conclusion: This study suggests that training of images of orthopedic manual therapy using machine learning open software is possible, and that web applications made using this training model can be used clinically.

• Smart Structures and Systems
• /
• 제31권5호
• /
• pp.485-500
• /
• 2023

Machine learning-based structural health monitoring (ML-based SHM) methods are researched extensively in the recent decade due to the availability of advanced information and sensing technology. ML methods are well-known for their pattern recognition capability for complex problems. However, the main obstacle of ML-based SHM is that it often requires pre-collected historical data for model training. In most actual scenarios, damage presence can be detected using the unsupervised learning method through anomaly detection, but to further identify the damage types would require prior knowledge or historical events as references. This creates the cold-start problem, especially for new and unobserved structures. Modal-based methods identify damages based on the changes in the structural global properties but often require dense measurements for accurate results. Therefore, a two-stage hybrid modal-machine learning damage detection scheme is proposed. The first stage detects damage presence using Principal Component Analysis-Frequency Response Function (PCA-FRF) in an unsupervised manner, whereas the second stage further identifies the damage. To solve the cold-start problem, mode shape assessment using the first mode is initiated when no trained model is available yet in the second stage. The damage identified by the modal-based method would be stored for future training. This work highlights the performance of the scheme in alleviating the cold-start issue as it transitions through different phases, starting from zero damage sample available. Results showed that single and multiple damages can be identified at an acceptable accuracy level even when training samples are limited.

• 치위생과학회지
• /
• 제20권4호
• /
• pp.206-212
• /
• 2020

Background: A Teachable Machine is a kind of machine learning web-based tool for general persons. In this paper, the feasibility of Google's Teachable Machine (ver. 2.0) was studied in the diagnosis of the tooth-marked tongue. Methods: For machine learning of tooth-marked tongue diagnosis, a total of 1,250 tongue images were used on Kaggle's web site. Ninety percent of the images were used for the training data set, and the remaining 10% were used for the test data set. Using Google's Teachable Machine (ver. 2.0), machine learning was performed using separated images. To optimize the machine learning parameters, I measured the diagnosis accuracies according to the value of epoch, batch size, and learning rate. After hyper-parameter tuning, the ROC (receiver operating characteristic) analysis method determined the sensitivity (true positive rate, TPR) and specificity (false positive rate, FPR) of the machine learning model to diagnose the tooth-marked tongue. Results: To evaluate the usefulness of the Teachable Machine in clinical application, I used 634 tooth-marked tongue images and 491 no-marked tongue images for machine learning. When the epoch, batch size, and learning rate as hyper-parameters were 75, 0.0001, and 128, respectively, the accuracy of the tooth-marked tongue's diagnosis was best. The accuracies for the tooth-marked tongue and the no-marked tongue were 92.1% and 72.6%, respectively. And, the sensitivity (TPR) and specificity (FPR) were 0.92 and 0.28, respectively. Conclusion: These results are more accurate than Li's experimental results calculated with convolution neural network. Google's Teachable Machines show good performance by hyper-parameters tuning in the diagnosis of the tooth-marked tongue. We confirmed that the tool is useful for several clinical applications.

• International journal of advanced smart convergence
• /
• 제10권4호
• /
• pp.165-171
• /
• 2021

The current study investigated cyber learners' use and perceptions of online machine translation (MT) tools. The results show that learners use several MT tools frequently and extensively for various second language learning (L2) purposes according to their needs. The learners' overall perceptions of using MT for English learning were generally positive. The learners reported several advantages of machine translation: ease of use, helpful feedback, effective revision, and facilitation of self-directed learning. At the same time, a considerable number of learners were aware of MT's drawbacks, such as awkward sentences, inaccurate grammar, and inappropriate words, and thus held a negative or skeptical view on the quality and accuracy of MT. These findings have important pedagogical implications for using MT in the context of a cyber university. For successful integration of MT in English classes, teachers need to provide appropriate guidelines and training that will help learners use MT effectively.

• Soft Computing and Machine Intelligence
• /
• 제1권1호
• /
• pp.11-23
• /
• 2021

House price prediction is a significant financial decision for individuals working in the housing market as well as for potential buyers. From investment to buying a house for residence, a person investing in the housing market is interested in the potential gain. This paper presents machine learning algorithms to develop intelligent regressions models for House price prediction. The proposed research methodology consists of four stages, namely Data Collection, Pre Processing the data collected and transforming it to the best format, developing intelligent models using machine learning algorithms, training, testing, and validating the model on house prices of the housing market in the Capital, Islamabad. The data used for model validation and testing is the asking price from online property stores, which provide a reasonable estimate of the city housing market. The prediction model can significantly assist in the prediction of future housing prices in Pakistan. The regression results are encouraging and give promising directions for future prediction work on the collected dataset.

• Journal of Positioning, Navigation, and Timing
• /
• 제12권2호
• /
• pp.149-155
• /
• 2023

In urban areas it can be difficult to utilize global navigation satellite systems (GNSS) due to signal reflections and blockages. It is thus crucial to detect reflected or blocked signals because they lead to significant degradation of GNSS positioning accuracy. In a previous study, a classifier for global positioning system (GPS) signal reception conditions was developed using three features and the support vector machine (SVM) algorithm. However, this classifier had limitations in its classification performance. Therefore, in this study, we developed an improved machine learning based method of classifying GPS signal reception conditions by including an additional feature with the existing features. Furthermore, we applied various machine learning classification algorithms. As a result, when tested with datasets collected in different environments than the training environment, the classification accuracy improved by nine percentage points compared to the existing method, reaching up to 58%.