• 산업과 과학
• /
• 제3권2호
• /
• pp.8-16
• /
• 2024

본 논문에서는 인구통계학적, 생리학적 특성을 기반으로 환자에게 가장 적합한 약물을 예측하는 것을 목표로 하는 약물 분류 시스템을 제시한다. 데이터 세트에는 적절한 약물을 결정하기 위한 목적으로 연령, 성별, 혈압(BP), 콜레스테롤 수치, 나트륨 대 칼륨 비율(Na_to_K)과 같은 속성들이 포함된다. 본 연구에 사용된 모델은 KNN(K-Nearest Neighbors), 로지스틱 회귀 분석 및 Random Forest이다. 하이퍼파라미터를 최적화하기 위해 5겹 교차 검증을 갖춘 GridSearchCV를 활용하였으며, 각 모델은 데이터 세트에서 훈련 및 테스트 되었다. 초매개변수 조정 유무에 관계없이 각 모델의 성능은 정확도, 혼동 행렬, 분류 보고서와 같은 지표를 사용하여 평가되었다. GridSearchCV를 적용하지 않은 모델의 정확도는 0.7, 0.875, 0.975인 반면, GridSearchCV를 적용한 모델의 정확도는 0.75, 1.0, 0.975로 나타났다. GridSearchCV는 로지스틱 회귀 분석을 세 가지 모델 중 약물 분류에 가장 효과적인 모델로 식별했으며, K-Nearest Neighbors가 그 뒤를 이었고 Na_to_K 비율은 결과를 예측하는 데 중요한 특징인 것으로 밝혀졌다.

• Communications for Statistical Applications and Methods
• /
• 제21권5호
• /
• pp.411-422
• /
• 2014

A classification ensemble method aggregates different classifiers obtained from training data to classify new data points. Voting algorithms are typical tools to summarize the outputs of each classifier in an ensemble. WAVE, proposed by Kim et al. (2011), is a new weight-adjusted voting algorithm for ensembles of classifiers with an optimal weight vector. In this study, when constructing an ensemble, we applied the WAVE algorithm on the double-bagging method (Hothorn and Lausen, 2003) to observe if any significant improvement can be achieved on performance. The results showed that double-bagging using WAVE algorithm performs better than other ensemble methods that employ plurality voting. In addition, double-bagging with WAVE algorithm is comparable with the random forest ensemble method when the ensemble size is large.

• Journal of electromagnetic engineering and science
• /
• 제17권4호
• /
• pp.186-190
• /
• 2017

Visible-near-infrared (VIS-NIR) spectroscopy is a fast and non-destructive method for analyzing materials. However, most commercial VIS-NIR spectrometers are inappropriate for use in various locations such as in homes or offices because of their size and cost. In this paper, we classified eight food powders using a portable VIS-NIR spectrometer with a wavelength range of 450-1,000 nm. We developed three machine learning models using the spectral data for the eight food powders. The proposed three machine learning models (random forest, k-nearest neighbors, and support vector machine) achieved an accuracy of 87%, 98%, and 100%, respectively. Our experimental results showed that the support vector machine model is the most suitable for classifying non-linear spectral data. We demonstrated the potential of material analysis using a portable VIS-NIR spectrometer.

• 한국IT서비스학회지
• /
• 제14권4호
• /
• pp.159-169
• /
• 2015

Customer reviews are one of the important sources for purchase decision makings in online stores. Online stores have tried to provide useful reviews in product pages to customers. To assess the usefulness of customer reviews before other users have voted enough on the reviews, diverse aspects of reviews were utilized in prevous studies. Style and semantic information were utilized in many studies. This study aims to test diverse alogrithms and datasets for identifying a proper classification method and threshold to classify useful reviews. In particular, most researches utilized ratio type helpfulness index as Amazon.com used. However, there is another type of usefulness index utilized in TripAdviser.com or Yelp.com, count type helpfulness index. There was no proper threshold to classify useful reviews yet for count type helpfulness index. This study used reivews and their usefulness votes on restaurnats from Yelp.com to devise diverse datasets and applied text mining approaches to classify useful reviews. Random Forest, SVM, and GLMNET showed the greater values of accuracy than other approaches.

• International Journal of Internet, Broadcasting and Communication
• /
• 제11권1호
• /
• pp.47-53
• /
• 2019

The idea of ensemble learning is to train multiple models, each with the objective to predict or classify a set of results. Most of the errors from a model's learning are from three main factors: variance, noise, and bias. By using ensemble methods, we're able to increase the stability of the final model and reduce the errors mentioned previously. By combining many models, we're able to reduce the variance, even when they are individually not great. In this paper we propose an ensemble model and applied it to classification problem. In iris, Pima indian diabeit and semiconductor fault detection problem, proposed model classifies well compared to traditional single classifier that is logistic regression, SVM and random forest.

• International Journal of Computer Science & Network Security
• /
• 제22권8호
• /
• pp.275-279
• /
• 2022

The growth of technology nowadays has made many things easy for humans. These things are from everyday small task to more complex tasks. Such growth also comes with the illegal activities that are perform by using technology. These illegal activities can simple as displaying annoying message to big frauds. The easiest way for the attacker to perform such activities is to convenience user to click on the malicious link. It has been a great concern since a decay to classify URLs as malicious or benign. The blacklist has been used initially for that purpose and is it being used nowadays. It is efficient but has a drawback to update blacklist automatically. So, this method is replace by classification of URLs based on machine learning algorithms. In this paper we have use four machine learning classification algorithms to classify URLs as malicious or benign. These algorithms are support vector machine, random forest, n-nearest neighbor, and decision tree. The dataset that is used in this research has 36694 instances. A comparison of precision accuracy and recall values are shown for dataset with and without preprocessing.

• International Journal of Computer Science & Network Security
• /
• 제23권9호
• /
• pp.186-191
• /
• 2023

Neural Networks are widely used for huge variety of tasks solution. Machine Learning methods are used also for signal and time series analysis, including electrocardiograms. Contemporary wearable devices, both medical and non-medical type like smart watch, allow to gather the data in real time uninterruptedly. This allows us to transfer these data for analysis or make an analysis on the device, and thus provide preliminary diagnosis, or at least fix some serious deviations. Different methods are being used for this kind of analysis, ranging from medical-oriented using distinctive features of the signal to machine learning and deep learning approaches. Here we will demonstrate a neural network-based approach to this task by building an ensemble of 1D CNN classifiers and a final classifier of selection using logistic regression, random forest or support vector machine, and make the conclusions of the comparison with other approaches.

• 한국멀티미디어학회논문지
• /
• 제13권12호
• /
• pp.1786-1797
• /
• 2010

Automatic understanding of contents in document image is a very hard problem due to involvement with mathematically challenging problems originated mainly from the over-determined system induced by document segmentation process. In both academic and industrial areas, there have been incessant and various efforts to improve core parts of content retrieval technologies by the means of separating out segmentation related issues using semi-structured document, e.g., invoice,. In this paper we proposed classification models for text lines on invoice document in which text lines were clustered into the five categories in accordance with their contents: purchase order header, invoice header, summary header, surcharge header, purchase items. Our investigation was concentrated on the performance of machine learning based models in aspect of linear-discriminant-analysis (LDA) and non-LDA (logic based). In the group of LDA, na$\"{\i}$ve baysian, k-nearest neighbor, and SVM were used, in the group of non LDA, decision tree, random forest, and boost were used. We described the details of feature vector construction and the selection processes of the model and the parameter including training and validation. We also presented the experimental results of comparison on training/classification error levels for the models employed.

• 방송공학회논문지
• /
• 제22권3호
• /
• pp.282-294
• /
• 2017

본 논문에서는 차량이 움직일 때 발생하는 카메라의 움직임, 도로상의 광원에 강건한 지능형 전조등 제어 시스템을 제안한다. 후보광원을 검출할 때 카메라의 원근 범위 추정 모델을 기반으로 한 ROI (Region of Interest)를 사용하며 이는 FROI (Front ROI)와 BROI (Back ROI)로 나뉘어 사용된다. ROI내에서 차량의 전조등과 후미등, 반사광 및 주변 도로의 조명들은 2개의 적응적 임계값에 의해 세그먼트화 된다. 세그먼트화 된 광원 후보군들로부터 후미등은 적색도(redness)와 Haar-like특징에 기반한 랜덤포레스트 분류기에 의해 검출된다. 전조등과 후미등 분류 과정에서 빠른 학습과 실시간 처리를 위해 SVM(Support Vector Machine) 또는 CNN(Convolutional Neural Network)을 사용하지 않고 랜덤포레스트 분류기를 사용했다. 마지막으로 페어링(Pairing) 단계에서는 수직좌표 유사성, 광원들간의 연관성 검사와 같은 사전 정의된 규칙을 적용한다. 제안된 알고리즘은 다양한 야간 운전환경을 포함하는 데이터에 적용한 결과, 최근의 관련연구 보다 향상된 검출 성능을 보여주었다.

• Journal of Forest and Environmental Science
• /
• 제40권3호
• /
• pp.210-226
• /
• 2024

Old-growth mixed-conifer forests in Bhutan are characterized by remarkable tree species compositional heterogeneity. However, our knowledge of tree species assemblages and their structural attributes in these forests has been limited. Therefore, forest classification has been reliant on a single dominant species. This study aimed to distinguish tree species assemblages in an old-growth mixed conifer forest in Western Bhutan and to describe their natural compositional and stand structural characteristics. Furthermore, the regeneration status of species was investigated and the quantity and quality of accumulated coarse woody debris were assessed. Ninety simple random sampling plots were surveyed in the study site between 3,000 and 3,600 meters above sea level. Tree, standing deadwood, regeneration, and coarse woody debris data were collected. Seven tree species assemblages were distinguished by Hierarchical Cluster Analysis and Indicator Species Analysis, representing five previously undescribed tree species associations with unique set of consistent species. Principal Component Analysis revealed two transitional pathways of species dominance along an altitudinal gradient, highly determined by relative topographic position. The level of stand stratification varied within a very wide range, corresponding to physiognomic composition. Rotated-sigmoid and negative exponential diameter distributions were formed by overstorey species with modal, and understorey species with negative exponential distribution. Overstorey dominant species showed extreme nurse log dependence during regeneration, which supports the formation of their modal distribution by an early natural selection process. This allows the coexistence of overstorey and understorey dominant species, increasing the sensitivity of these primary ecosystems to forest management.