Earticle

본 논문은 평균 이상의 조직몰입과 가장 연관이 있는 인사제도를 순서 데로 나타내 보임으로써, 방대한 양의 인사관련 데이터의 통계적 분석을 통해 어떻게 조직이 귀납적으로 조직성과 향상을 위한 유의미한 정보를 추출할 수 있는지에 대한 하나의 예시를 제시한다. 한국의 제조업 분야 특정 기업 1,451명의 종업원을 대상으로 한 서베이 데이터를 R을 이용해 트리분석 (tree analysis)을 한 결과, 종업원이 회사의 성과관리 제도에 대한 만족도가 일정 수준 (5점 만점에 3.08)을 넘어서거나, 그렇지 않으면 그 종업원이 보상제도에 대한 만족도가 일정 수 준 (5점 만점에 2.83)을 넘어서야 그 종업원은 평균 이상의 조직몰입을 가질 것으로 예측할 수 있었다. 이러한 결과는 최소한 이 회사는 조직 몰입 향상을 위해 첫 번째 우선순위로 종업원의 성과관리에 대한 만족도 수준을 관리해야 하고, 이와 더불어 종업원의 보상제도에 대한 만 족도 수준을 짝으로 같이 관리할 때 효과적으로 조직몰입 향상을 이끌어 낼 수 있음을 제시한다. 본 연구가 학문적, 실무적으로 유의미하고 다양한 인적자원 Analytics에 대한 연구 활성화에 기여하기를 기대해 본다.

Which HR practices are more important in predicting employee commitment and how might they best be identified? Using classification tree analysis, a data mining technique, we find the priorities between practices the cut-off scores of each. The most important variable to predict above average-commitment employees is “performance management” and the next is “compensation.” Thus, performance management and compensation is a best fit to predict above average-commitment employees. The proposed approach contributes to the HR analytics and SHRM literature by introducing the notion of hierarchy of HR practices in eliciting higher commitment. Our hope is that the model presented in this paper provides a starting place for research and practice examining the role of data mining in HR, and toward the goal of developing effective organizational mechanisms for improving employee commitment.

일상적인 상황에서 방위산업에 관련된 물류관리의 중요성은 일반 산업에 비하여 크지 않으나, 예외적인 상황이 발생했을 때에는 신속한 해결책을 찾아내어 문제를 해결하지 않으면 국방에 있어서 전략적 공백으로 이어질 수 있다. 그러므로 예외상황에 대한 신속한 대비책을 구축하는 것이 필요하며 본 논문에서는 업무절차관리(BPMS) 시스템을 도입하여 물류 프로세스의 지속적인 개혁 및 개선을 유도한다. 이를 위하여 프로세스 저장소의 사용을 제안하며, 예외발생시 신속한 처리방안을 검색하기 위한 검색트리의 사용방법론을 제시한다. 획일적인 업무처리가 강조되는 군사작전 및 방위산업의 환경 하에서 예외상황의 처리를 위한 효율적 장치를 마련하는 것은 방산운용의 측면에서 매우 중요하다. 본 논문에서는 특히 지식경영의 관점에서 예외처리 시 생성되는 새로운 프로세스 지식을 프로세스 저장소(process repository)에 저장하고, 예외발생시 이 문제의 해결에 적합한 프로세스를 저장소에서 신속하게 검색하는 데 활용할 수 있는 검색트리의 생성과 활용에 대한 방법론을 연구하였다. 검색트리의 생성과 활용을 위하여 ‘상황변수’와 ‘의사결정변수’의 개념을 새로 도입함으로써 문제의 상황을 체계적으로 기술하고 저장 및 검색하는 방편을 제시하였으며, 예외상황의 인식능력(context awareness)을 제고시켰다. 정보의 엔트로피를 기초로 한 C5.0 알고리즘을 적용하여 정보이득을 최대화하는 검색트리를 생성하는 방법을 제시하였다.

This study was performed to construct tree species classification map according to three information types (spectral information, texture information, and spectral and texture information) by altitude (30 m, 60 m, 90 m) using the unmanned aerial vehicle images and the object-based classification method, and to evaluate the concordance rate through field survey data. The object-based, optimal weighted values by altitude were 176 for 30 m images, 111 for 60 m images, and 108 for 90 m images in the case of Scale while 0.4/0.6, 0.5/0.5, in the case of the shape/color and compactness/smoothness respectively regardless of the altitude. The overall accuracy according to the type of information by altitude, the information on spectral and texture information was about 88% in the case of 30 m and the spectral information was about 98% and about 86% in the case of 60 m and 90 m respectively showing the highest rates. The concordance rate with the field survey data per tree species was the highest with about 92% in the case of Pinus densiflora at 30 m, about 100% in the case of Prunus sargentii Rehder tree at 60 m, and about 89% in the case of Robinia pseudoacacia L. at 90 m.

데이터를 기반으로 컴퓨터가 사람처럼 인식하고 분류할 수 있도록 만들어 주는 기계학습 알고리즘은 빅 데이터 시대를 맞이하여 다양한 분야에서 활용되고 있다. 기계학습 알고리즘의 하나인 결정트리 알고리즘도 간단 하지만, 준수한 성능으로 다양한 분야에서, 특히 내장형 시스템상에서 구현되어 많이 활용되고 있다. 본 논문에서 는 이 결정트리 알고리즘의 분류 속도를 향상시키는 방법을 제안한다. 제안되는 알고리즘은 먼저 트리의 운행 중 노드의 계산값을 기반으로 오분류의 가능성을 식별하고 운행을 중단한다. 그리고 중단된 벡터의 클래스를 예측하 기 위해 확률을 기반으로 미리 선정된 대체 클래스를 이용한다. 실험 결과, 제안된 결정트리 알고리즘은 분류 정 확도의 저하 없이 기존의 결정트리 알고리즘보다 평균적으로 1.38배 빠른 분류 속도를 보였다. 빨라진 분류 속도 는 사용자에게 보다 쾌적한 서비스를 제공하며, 만약 내장형 시스템에서 사용된다면 전력소모를 줄여 배터리 사용 시간을 연장시킬 것으로 기대된다.

Machine learning algorithms, which allow computers to recognize and classify data like humans, are widely used across various fields in the big data era. The decision tree algorithm, known for its simplicity and effectiveness, is particularly popular in embedded systems. This paper introduces a method to speed up this algorithm by stopping tree traversal when a potential misclassification is identified, and using a predetermined alternate class based on probability for halted vectors. Experimental results show that the proposed decision tree algorithm is 1.38 times faster than traditional ones without sacrificing classification accuracy. The increased classification speed is expected to provide a more pleasant service to users and, if used in embedded systems, is anticipated to reduce power consumption and extend battery life.

본 연구는 고해상도 위성영상과 항공영상을 이용하여 샘플영역의 크기 변화에 따른 수종분류 시 정확도와 신뢰도에 미치는 영향을 객관적으로 규명하고 그 경향성을 파악하는데 목적이 있다. 영상이 포함하고 있는 밴드들의 특성을 모두 고려하여 수종분류를 실시하기 위해 위성영상과 항공영상 각각에 대해 다중분광영상을 제작하였으며, 이를 기반으로 감독분류를 수행하였다. 그리고 정확도 검증단계에서 전체정확도를 산출하였으며, 그 결과 위성영상의 3*3에서 84.7%, 항공영상은 5*5에서 83%로 가장 높게 나타났으며 Kappa 계수는 각각 0.84, 0.82로 나타났다. 또한 두 영상의 샘플영역의 크기가작아질수록 정확도가 높아지는 것으로 판단된다.

The purpose of this study was to investigate the objective impact in accuracy and reliability with tendency depend ontraining samples by using the high-resolution images. Supervised classification was performed based on multi-spectral imageswhich made by each satellite and aerial images for considering all of bands’ characteristics. The highest accuracy was84.7% with satellite image(3*3) and 83% with aerial image(5*5) at the accuracy verification phase. Also, the overallaccuracy with the consideration of Kappa coefficient were 0.84 for satellite images and 0.82 for aerial images. In all of theimages, the smaller training sample was, the higher accuracy showed. Therefore, tree species classification accuracy wastended to rely on training sample size.

변량 분석 알고리듬은 알츠하이머 병을 예측하기 위한 툴로 종종 사용된다. 정상인으부터 경도인지장애와 알츠하이머 병의 효과적인 조기 예측 및 진단은 매우 중요하다. 조기 예방 치료는 노인 복지에 있어 점차적으로 위험요소를 줄이 는데 도움이 되며 안정적인 삶이 보장되어 질 것이다. 비침습적인 바이오마커로 MRI가 사용된다. 이는 형태학적 차이 와 뇌 위축 정도를 파악한다. 그리고 Freesurfer 툴을 사용하여 피질 분할 후 MRI 슬라이스를 사용한다. 새로운 접 근법은 듀얼 트리 복한 웨이블릿 계수 추출, 최소 중복성과 최대 관계 특색 부분 집합을 사용하여 정상인과 알츠하이 머 병 예측에 적용한다. 새로운 제안 방법의 성능은 91.02±3.38%, 83.10±3.4%로 높은 특이도와 민감도의 성능이 며 예측 정확도는 87.07±2.71%까지 산출되어진다. 실험결과는 제안 방법은 기존의 방법보다 우수함을 보여준다.

Multivariate analysis algorithms have been frequently used tool for predicting Alzheimer disease (AD). An efficient early prediction and diagnosis of AD and Mild Cognitive Impairment (MCI) from Healthy Controls (HC) is always very important. Early preventive care could help to degenerate its risk factors gradually in the elderly and the stable life will be guaranteed. The noninvasive biomarker of Magnetic Resonance (MR) images are used here because morphometric difference and cerebral atrophy could be realized. And we also used MR image slices after subcortical segmentation by using FreeSurfer tool. A novel approach is applied for predicting AD from HC using dual tree complex wavelet coefficients extraction, principal components of min-redundancy and max relevance feature subset selection. The prediction accuracy of the novel proposed method is yielded up to 87.07±2.71% with high specificity, sensitivity about 91.02±3.38%, 83.10±3.4% respectively. The experimental results show that the performance of our proposed method is better than that of conventional ones.

This paper reviews ordinal decision tree algorithms for ordinal classification, exploring theoretical foundations, key algorithms (MDT, QMDT), specialized splitting criteria (Ordinal Gini, Weighted Information Gain), and ensemble methods. It discusses applications in healthcare and social sciences, highlighting interpretability and flexibility while acknowledging overfitting and instability. As implications for future research, this study points out advantages such as interpretability and flexibility, and limitations such as overfitting and instability.

인식 대상 학습 모델이 분류되어 있지 않거나 명확하게 분류되지 않은 경우 어휘 인식을 결정하지 못하여 인 식률이 저하되며 학습 모델 분류 형태가 변경되거나 새로운 학습 모델이 추가되면 인식 모델의 결정 트리 구조가 변 경되어야 하는 구조적 문제가 발생한다. 이러한 문제점을 해결하기 위하여 학습 모델 분류를 위한 결정 트리 학습 알 고리즘을 제안한다. 음운 현상이 충분히 반영된 음성 데이터베이스를 구성하고 학습 효과를 확보하기 위하여 학습 모 델 분류를 위한 결정 트리 방법을 사용하였다. 본 연구에서는 실내 환경에 대하여 어휘 종속 인식과 어휘 독립 인식 실험을 수행한 결과 실내 환경의 어휘 종속 실험에서는 98.3%의 인식 성능을 보였고, 어휘 독립 실험에서 98.4%의 인식 성능을 보였다.

Target learning model is not recognized in this category or not classified clearly failed to determine if the vocabulary recognition is reduced. Form of classification learning model is changed or a new learning model is added to the recognition decision tree structure of the model should be changed to a structural problem. In order to solve these problems, a decision tree learning model for classification learning algorithm is proposed. Phonological phenomenon reflected sound enough to configure the database to ensure learning a decision tree learning model for classifying method was used. In this study, the indoor environment-dependent recognition and vocabulary words for the experimental results independent recognition vocabulary of the indoor environment-dependent recognition performance of 98.3% in the experiment showed, vocabulary independent recognition performance of 98.4% in the experiment shown.

본 논문에서는 상황 변화 환경에서 적응적인 객체 인식을 위한 계층적 트리 구조를 이용한 조명 온톨로지 분류에 대한 방식을 제안한다. 본 논문에서는 상황이 불변하는 환경에서 동작하는 개발된 많은 시스템을 찾아냈고, 상황에 맞는 감지를 위한 새로운 개념의 트리 구조를 이용한 온톨로지를 도입하였다. 조명의 영향이 상황 인지 인식 시스템을 아주 설계하기 어려운 시스템으로 만들기 때문에 본 논문에서는 트리 구조의 온톨로지를 사용하여 이러한 상황 변화 시스템을 설계하는데 더 중점을 두었다. 온톨로지는 일반적으로 사람들이 특정 분야의 것들에 대해 생각하는 방법의 추상적 모델에서 전형적으로 캡처된 한 분야의 개념화의 명시적 사양으로 정의 할 수 있다. 인간은 기본 원칙과 환경을 이해하고 설명하기 위해 온톨로지를 생성한다. 본 연구에서는 상황 온톨로지, 상황 모델링, 상황 적응 및 조명 기준에 따라 트리 구조 온톨로지를 설계하는 상황 분류를 제안했다. 조명 온톨로지의 적당한 영역을 선택한 후, 그 영역에서 더 나은 성능을 생산하는 동작의 한 집합을 선택하는데 있어서 장점을 얻었다. 본 논문에서는 역동적인 변화 환경에서 객체 인식의 영역에서 이러한 개념을 이용하여 폭 넓은 실험을 수행하였으며 제안하는 기본 개념에 대해 수행할 수 있는 많은 성공을 얻었다.

This paper proposes a ontology of tree structure approach for adaptive object recognition in a situation-variant environment. In this paper, we introduce a new concept, ontology of tree structure ontology, for context sensitivity, as we found that many developed systems work in a context-invariant environment. Due to the effects of illumination on a supreme obstinate designing context-sensitive recognition system, we have focused on designing such a context-variant system using ontology of tree structure. Ontology can be defined as an explicit specification of conceptualization of a domain typically captured in an abstract model of how people think about things in the domain. People produce ontologies to understand and explain underlying principles and environmental factors. In this research, we have proposed context ontology, context modeling, context adaptation, and context categorization to design ontology of tree structure based on illumination criteria. After selecting the proper light-ontology domain, we benefit from selecting a set of actions that produces better performance on that domain. We have carried out extensive experiments on these concepts in the area of object recognition in a dynamic changing environment, and we have achieved enormous success, which will enable us to proceed on our basic concepts.

In the field of transportation, many of the vehicle amount of raw data value which can be accompanied by a large number of unknown information, and these information can provide people with more help. This paper aimed at the master data, and by using the method of survey of data modeling and prediction. First this paper introduces the data survey methods and the characteristics of the model, and then applied to the vehicles recognition judgment in their ability to recognize and to compare the analysis. The conclusion by principal component analysis and discriminant analysis method bus and van in four categories, the two on the training set and testing set of identification is quite high (high purity), so the four classified into two categories, the key to deal with opel (has been) and class and Po (saab) class. After the processing of raw data, and finally compares the model results.

Decision tree induction has gained its popularity as an effective automated method for data classification mainly because of its simple, easy-to-understand, and noise-tolerant characteristics. The induced tree reveals the most informative attributes that can best characterize training data and accurately predict classes of unseen data. Despite its predictive power, the tree structure can be overly expanded or deeply grown when the training data do not show explicit patterns. Such bushy and deep trees are difficult to comprehend and interpret by humans. We thus propose a logic-based method to query over a complicate tree structure to extract only parts of the tree model that are really relevant to users’ interest. The implementation using ECLiPSe constraint language to perform constrained search over a decision tree model is given in this paper. The illustrative examples on medical domains support our hypothesis regarding simplicity of constrained tree-based patterns.

For multi-relational data mining, efficiency is always a focus of research. The main bottleneck to improve the efficiency of the algorithm is hypothesis space. This paper presents the improved multi-relational decision tree algorithm, MRDTL-2, whose efficiency is improved. First, the tuple ID propogation technology is applied to the multi-relational decision tree algorithm. Secondly, under user’s guide, when a data item is greater than the transmitting threshold, set the null relationship Ra. And transmit the primary key, the background attributes, the class label to Ra, then Ra involves in other multi-relational decision tree algorithms instead of the background relations. Finally, the paper has carried on the experiments to verify the improved multi-relational decision tree algorithm MRDTL-2.

In the paper, with the introduction of data mining algorithm of the classification in detail, and then combining the classification algorithm and incremental learning technology, an incremental decision tree algorithm is proposed to solve the problem of incremental learning and analysis the experimental data for this algorithm. The paper used ID3 and C4.5 algorithm for detailed research. According to two algorithms, combining Bayesian classification algorithm’s incremental learning characteristic, the paper proposed an incremental decision tree algorithm , and by the analysis of experimental data. This algorithm can solve the incremental learning problem of the decision tree algorithm very well.

Visual analysis has potential to be used for recognition, and it is one of the hottest but most difficult subjects in computer vision. In order to identify pedestrian movement in an Intelligent Security Monitoring System, the video activity in the prospect is represented by a series of spatio-temporal interest points. Since human posture has the characteristics of uncertainty and illegibility, the clustering centers of each class are computed by fuzzy clustering techniques. We presented a pedestrian classification method based on improved support vector machines in order to solve non-rigid objects that are difficult to identify in intelligent monitoring systems. The Support Vector Machine technology and the decision tree have combined into one multi-class classifier so as to solve multi-class classification problems. Then a full-SVM (Support Vector Machine) decision tree is constructed based on the conventional decision tree. At last, the method is evaluated on the KTH action dataset and receives a comparatively high correct recognition rate.

The motivation of this paper is based on a hypothesis that non-linear decision nodes provide a better classification performance than axis-parallel decision nodes do in many practical problems, such as image classification, and voice classification. The algorithm – MNCS_DT is introduced in this paper to create non-linear splits nodes by novel discriminant analysis in decision tree for multi-classification problem and take cost-sensitive problem into account when the features are selected. In experiment part, we use four UCI data sets to compare the performance of MNCS_DT and C4.5 CS by costs and error rates. The performance of MNCS_DT is better than C4.5 CS. And eight data sets from UCI are used to compare the performance of three different feature sets measured by accuracy, G-mean, and operation time. The performance of feature set consisting of features that follow multivariate normal distribution and altered information gain values higher than average one is better than two other feature sets in most data sets.

In food consumption, food addiction is behavioral and biological overlaps have been observed between eating and addictive disorders. Food addiction influence to healthy life. Food addiction caused by overeating, bingo eating, eating disorder, eating addiction, mindless eating, craving, chocaholic, and emotional eating. Determination between addiction and normal condition in food consumption, need to classification. Classification is very important in determine signs of food addiction. Classification using Naïve Bayes Algorithm and Decision Tree Algorithm. Class target is Class Normal and Class Addiction. Classification using Naïve Bayes Algorithm by criterion is Calorie Dense Food, Fatty Food, Sweet Food, Diet and Stress. This criterion as causal factor of food addiction. Classification using Decision Tree Algorithm by criterion is Stress, Fatty Food and Calorie Dense Food. This criterion as causal factor of food addiction. The experimental result is a Classification Model. This model became data source for national policy in public health.

We present a scalable and accurate method for classifying program traces to detect system intrusion attempts. By employing inter-element dependency models to overcome the independence violation problem inherent in the Naïve Bayes learners, our method yields intrusion detectors with better accuracy. For efficient counting of n-gram features without losing accuracy, we use a k-truncated generalized suffix tree (k-TGST) for storing n-gram features. The k-TGST storage mechanism enables to scale up the classifiers, which cannot be easily achieved by SVM (Support Vector Machine) based methods that require implausible computing power and resources for accuracy.

Since the launch of AI, technology development to implement complete and sophisticated AI functions has continued. In efforts to develop technologies for complete automation, Machine Learning techniques and deep learning techniques are mainly used. These techniques deal with supervised learning, unsupervised learning, and reinforcement learning as internal technical elements, and use the Big-data Analysis method again to set the cornerstone for decision-making. In addition, established decision-making is being improved through subsequent repetition and renewal of decision-making standards. In other words, big data analysis, which enables data classification and recognition/recognition, is important enough to be called a key technical element of AI function. Therefore, big data analysis itself is important and requires sophisticated analysis. In this study, among various tools that can analyze big data, we will use a Python program to find out what variables can affect addiction according to smartphone use in a decision tree environment. We the Python program checks whether data classification by decision tree shows the same performance as other tools, and sees if it can give reliability to decision-making about the addictiveness of smartphone use. Through the results of this study, it can be seen that there is no problem in performing big data analysis using any of the various statistical tools such as Python and R when analyzing big data.

Early detection of cancer is the best method to increase the chances of survival. In early stage, cancer can be detected using mammography, fine needle aspirate, and surgical biopsy. In this study, we propose the use of Dual-Tree Complex Wavelet Transform (DTCWT) based feature with neural network classifier for mammography image analysis. The result is evaluated using specificity, sensitivity, and accuracy. Computational experiments show the proposed method is superior compare to DWT with 96.3% accuracy.