• 산업경영시스템학회지
• /
• 제46권3호
• /
• pp.161-169
• /
• 2023

Degenerative arthritis is a common joint disease that affects many elderly people and is typically diagnosed through radiography. However, the need for remote diagnosis is increasing because knee pain and walking disorders caused by degenerative arthritis make face-to-face treatment difficult. This study collects three-dimensional joint coordinates in real time using Azure Kinect DK and calculates 6 gait features through visualization and one-way ANOVA verification. The random forest classifier, trained with these characteristics, classified degenerative arthritis with an accuracy of 97.52%, and the model's basis for classification was identified through classification algorithm by features. Overall, this study not only compensated for the shortcomings of existing diagnostic methods, but also constructed a high-accuracy prediction model using statistically verified gait features and provided detailed prediction results.

• Journal of Information Processing Systems
• /
• 제19권5호
• /
• pp.673-687
• /
• 2023

Convolutional neural network-based deep learning technology is the most commonly used in image identification, but it requires large-scale data for training. Therefore, application in specific fields in which data acquisition is limited, such as in the military, may be challenging. In particular, the identification of ground weapon systems is a very important mission, and high identification accuracy is required. Accordingly, various studies have been conducted to achieve high performance using small-scale data. Among them, the ensemble method, which achieves excellent performance through the prediction average of the pre-trained models, is the most representative method; however, it requires considerable time and effort to find the optimal combination of ensemble models. In addition, there is a performance limitation in the prediction results obtained by using an ensemble method. Furthermore, it is difficult to obtain the ensemble effect using models with imbalanced classification accuracies. In this paper, we propose a transfer learning-based feature fusion technique for heterogeneous models that extracts and fuses features of pre-trained heterogeneous models and finally, fine-tunes hyperparameters of the fully connected layer to improve the classification accuracy. The experimental results of this study indicate that it is possible to overcome the limitations of the existing ensemble methods by improving the classification accuracy through feature fusion between heterogeneous models based on transfer learning.

• 한국지능시스템학회논문지
• /
• 제26권6호
• /
• pp.433-438
• /
• 2016

본 논문에서는 한우의 근내 지방 부분을 초음파 기기를 이용하여 촬영한 초음파 영상의 특징 분석을 통해 classification 알고리즘을 이용하여 한우의 도체육질 등급을 예측하는 방법을 제안하며, 인체의 초음파 영상을 이용하여 진단 및 치료 검증 과제에 있어 사전 연구로 진행된 연구로, 차후에는 초음파 영상의 분석 범위를 확대할 예정이다. 한우의 초음파 영상을 활용한 경우에는 생체 정보를 한우 개량의 측면에서 생체 육질 정보를 조기에 획득하여 활용함으로써, 도축하지 않고도 육질 및 육량을 측정하여 개량의 속도를 배가시킬 수 있고, 농가 경영 측면에서 출하시기 및 방법의 조절로 농가 수익향상에 일조할 수 있는 중요한 핵심 기술이다. 이에 대한 많은 연구가 미국과 일본을 중심으로 이루어져 왔으며, 특히 기기에 의한 객관적인 측정방법들이 다양하게 연구되고 있지만 정확도가 낮다. 따라서 제안된 연구에서는 한우의 근내 지방 초음파 영상에 특징점 추출 알고리즘과 classification 알고리즘을 적용하여 한우의 도체 육질을 예측하였다. 실험 결과 제안하는 방법을 적용하였을 경우, 기존의 방법에 비해 효율적인 것을 확인할 수 있었다.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제8권1호
• /
• pp.1-5
• /
• 2008

Generally the analytical tools of data mining have two learning types which are supervised and unsupervised learning algorithms. Classification and prediction are main analysis tools for supervised learning. In this paper, we perform a comparison study of classification algorithms in data mining. We make comparative studies between popular classification algorithms which are LDA, QDA, kernel method, K-nearest neighbor, naive Bayesian, SVM, and CART. Also, we use almost all classification data sets of UCI machine learning repository for our experiments. According to our results, we are able to select proper algorithms for given classification data sets.

• ETRI Journal
• /
• 제37권2호
• /
• pp.222-232
• /
• 2015

In this paper, we propose a dual-phase approach to improve the process of heart disease prediction in a mobile environment. Firstly, only the confident frequent rules are extracted from a patient's clinical information. These are then used to foretell the possibility of the presence of heart disease. However, in some cases, subjects cannot describe exactly what has happened to them or they may have a silent disease - in which case it won't be possible to detect any symptoms at this stage. To address these problems, data records collected over a long period of time of a patient's heart rate variability (HRV) are used to predict whether the patient is suffering from heart disease. By analyzing HRV patterns, doctors can determine whether a patient is suffering from heart disease. The task of collecting HRV patterns is done by an online artificial neural network, which as well as learning knew knowledge, is able to store and preserve all previously learned knowledge. An experiment is conducted to evaluate the performance of the proposed heart disease prediction process under different settings. The results show that the process's performance outperforms existing techniques such as that of the self-organizing map and gas neural growing in terms of classification and diagnostic accuracy, and network structure.

• Asia pacific journal of information systems
• /
• 제25권3호
• /
• pp.579-596
• /
• 2015

Many studies have focused on the prediction of corporate credit rating using various data mining techniques. One of the most frequently used algorithms is support vector machines (SVM), and recently, novel techniques such as SVM+ and SVM+MTL have emerged. This paper intends to show the applicability of such new techniques to multi-classification and corporate credit rating and compare them with conventional SVM regarding prediction performance. We solve multi-class SVM+ and SVM+MTL problems by constructing several binary classifiers. Furthermore, to demonstrate the robustness and outstanding performance of SVM+MTL algorithm over other techniques, we utilized four typical multi-class processing methods in our experiments. The results show that SVM+MTL outperforms both conventional SVM and novel SVM+ in predicting corporate credit rating. This study contributes to the literature by showing the applicability of new techniques such as SVM+ and SVM+MTL and the outperformance of SVM+MTL over conventional techniques. Thus, this study enriches solving techniques for addressing multi-class problems such as corporate credit rating prediction.

• 정보처리학회논문지B
• /
• 제13B권1호
• /
• pp.1-6
• /
• 2006

단백질의 기능 예측 모델은 guilt-by-association 개념을 바탕으로 단백질-단백질 상호작용 맵을 이용하고 있다. 이 방법은 목표 단백질이 기능이 알려진 단백질과 상호작용이 없는 경우 기능 예측이 불가능하다. 본 논문에서는 단백질 기능 예측 모델을 K-class 다중 분류 문제로 재 정의하고 단백질-단백질 상호작용 데이터 및 단백질의 알려진 속성 등을 학습 모델에 이용한 단위신경망의 설계와 응용을 제안한다. 제안하는 모델은 Yeast 단백질 데이터의 기능 예측에서 단백질-단백질 상호작용 데이터를 이용하는 방법에 비해 분류 예측율에서 우수한 성능을 보였으며 또한 상호작용이 밝혀지지 않은 단백질의 기능 예측을 할 수 있다.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 1998년도 Proceedings of International Workshop on Advanced Image Technology
• /
• pp.165-170
• /
• 1998

This paper presents a new prediction method RBP region-based prediction model where the context used for prediction contains regions instead of individual pixels. There is a meaningful property that RBP can partition a cartoon image into two distinctive types of regions, one containing full-color backgrounds and the other containing boundaries, edges and home-chromatic areas. With the development of computer techniques, synthetic images created with CG (computer graphics) becomes attactive. Like the demand on data compression, it is imperative to efficiently compress synthetic images such as cartoon animation generated with CG for storage of finite capacity and transmission of narrow bandwidth. This paper a lossy compression method to full-color regions and a lossless compression method to homo-chromatic and boundaries regions. Two criteria for partitioning are described, constant criterion and variable criterion. The latter criterion, in form of a linear function, gives the different threshold for classification in terms of contents of the image of interest. We carry out experiments by applying our method to a sequence of cartoon animation. We carry out experiments by applying our method to a sequence of cartoon animation. Compared with the available image compression standard MPEG-1, our method gives the superior results in both compression ratio and complexity.

• 한국컴퓨터정보학회논문지
• /
• 제20권5호
• /
• pp.73-81
• /
• 2015

소프트웨어 결함 예측 연구들의 대부분은 입력 개체의 결함 유무를 예측하는 이진 분류 모델들에 관한 것들이다. 하지만 모든 결함들이 같은 심각도를 갖지는 않으므로 예측 모델이 입력 개체의 결함경향성을 몇 개의 심각도 범주로 분류할 수 있다면 훨씬 유용하게 사용될 수 있다. 본 논문에서는 전통적인 복잡도와 크기 메트릭들을 입력으로 하는 심각도 기반 결함 예측 모델을 제안하였다. 학습 알고리즘은 많이 사용되는 네 개의 기계학습 기법들을 사용하였으며, 모델 구조는 삼진 분류 모델로 하였다. 모델 성능 평가를 위해 실험 데이터는 두 개의 NASA 공개 데이터 집합을 사용하였고, 평가 측정치는 Accuracy를 이용하였다. 평가 실험 결과는 역전파 신경망 모델이 두 데이터 집합에 대해 각각 81%와 88% 정도의 Accuracy 값으로 가장 좋은 성능을 보였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권12호
• /
• pp.4476-4491
• /
• 2021

Video service providers tend to face user network problems in the process of transmitting video streams. They strive to provide user with superior video quality in a limited bitrate environment. It is necessary to accurately determine the target bitrate range of the video under different quality requirements. Recently, several schemes have been proposed to meet this requirement. However, they do not take the impact of visual influence into account. In this paper, we propose a new multi-category model to accurately predict the target bitrate range with target visual quality by machine learning. Firstly, a dataset is constructed to generate multi-category models by machine learning. The quality score ladders and the corresponding bitrate-interval categories are defined in the dataset. Secondly, several types of spatial-temporal features related to VMAF evaluation metrics and visual factors are extracted and processed statistically for classification. Finally, bitrate prediction models trained on the dataset by RandomForest classifier can be used to accurately predict the target bitrate of the input videos with target video quality. The classification prediction accuracy of the model reaches 0.705 and the encoded video which is compressed by the bitrate predicted by the model can achieve the target perceptual quality.