Decision tree model

About: Decision tree model is a research topic. Over the lifetime, 2256 publications have been published within this topic receiving 38142 citations.

A lazy algorithm for decision tree induction based on importance of attributes

Abstract: This paper applies lazy idea to fuzzy decision tree induction A new algorithm is proposed in this paper based on important of attributes This algorithm, which does not generate a decision tree for all training examples, only determines a specified path for each test case Obviously the algorithm has reduced the computational effort of training but increase the complexity of testing We experimentally find that the proposed algorithm is superior to the traditional one on robustness

A novel classifier using random sampling and expert knowledge

Abstract: In this work we investigate several issues in order to improve the performance of decision trees. Firstly, we introduced or adopt a new composite splitting criterion aimed to improve classification accuracy. Secondly, we derive a new pruning technique using expert knowledge, which is able to significantly reduce the size of tree without degrading the classification accuracy. Finally, we implemented our new splitting criterion and pruning technique to form a new decision tree model; Classification Using Randomization and Expert knowledge (CURE). Carried out experiments using 40 UCI datasets on four existing algorithms showed empirical effectiveness of the devised approach.

A Prediction Model of Hospitalized Medical Service Behavior Using Decision Tree Analysis: Using Korea Medical Service Patient Experience Survey

Abstract: 코로나19는 우리 사회 전반에 큰 변화를 가져왔으며 특히 보건의료 분야의 의료이용에 영향을 가져왔다. 본 연구는 2020 의료서비스 경험조사 원시자료를 이용하여 치료를 목적으로 입원 의료서비스 경험이 있는 497명을 대상으로 입원 의료서비스 경험 실태를 파악하고 행동예측 모형을 개발하고자 한다. 연구 결과 입원 의료서비스 행동의도 중 치료 결과 만족도는 신체노출보호와 시설의 안락함에 의해 결정되었으며, 전반적인 만족도와 의료기관 추천의향은 담당 의사의 필요시 응대에 의해 결정되는 것으로 조사되었다. 이러한 결과를 종합적으로 정리해보면, 의료기관에서는 고객의 치료 결과 만족 향상을 위하여 진료나 검사 시 신체 노출을 최소화 할 수 있는 방안과 함께 의료진의 배려가 필요하며, 입원 의료서비스 이용 고객이 의료기관 시설환경에 안락함과 편안함을 느낄 수 있도록 하는 노력이 요구된다. 또한 입원 의료서비스 이용 시 행정부서 및 담당 의사와의 소통과 상호작용이 중요한 결정요인라 할 수 있다. 본 연구는 입원 의료서비스 이용자를 대상으로 행동의도를 예측함으로써 정부의 보건의료 정책방향과 의료기관의 효율적인 관리방안에 대하여 시사점을 제공하고자 한다.

Fault diagnosis decision-making method and computer readable medium

Abstract: The invention discloses a fault diagnosis decision-making method and a computer readable medium. The fault diagnosis decision-making method comprises the steps: improving a fault sample information gain based on a fault sample data set and the cost of each diagnosis operation execution action, and obtaining a cost information gain expression; generating a decision tree model according to the costinformation gain selection operation action auctioned by the traversal operation; and determining the fault diagnosis decision tree with the optimal cost by calculating the expected cost of the decision tree. The fault diagnosis decision-making method can accurately find the sequence of the fault diagnosis operation actions with the lowest expected cost, and can guarantee that the cost is lowest while fault diagnosis is completed to the maximum extent.

Landscaping of random forests through controlled deforestation

Abstract: Random forest (RF) is an ensemble learner constructed using a set of decision trees, where each tree is trained using randomly bootstrapped samples and aggregated to provide a decision. While the generalization error is reduced by increasing the number of trees in a RF, it substantially increases the testing time complexity, inhibiting its fast deployment in practical applications. In this paper, we propose a post-training optimization technique termed landscaping of RF for reducing computational complexity by compensating for trees associated with similar decision boundary. This allows faster deployment of the RF without compromising its performance. Landscaping is achieved through a two stage mechanism: (i) computation of decision similarity between all pairs of trees in the RF, and (ii) deletion of the computationally expensive tree in the RF with decision bias compensation for the removed tree. Performance of the proposed methodology was evaluated using three publicly available datasets. The RF performance before and after landscaping over the datasets was observed to have an error of 0.1084 ± 0.03 and 0.1087 ± 0.03, respectively, while testing times of the RF before landscaping was 2.5508 ± 0.08 sec. and 0.9066 ± 0.19 sec. after landscaping with 32 – 76% reduction in execution time. These results strongly substantiates our claim of achieving deployment speedup without compromising the decision quality with landscaping of RF through controlled deforestation.