Earticle

This study evaluates the effectiveness of AI-driven CRM models in predicting consumer purchase behavior and examines how market volatility affects predictive performance. Using transactional data from Amazon, a customer-month panel is constructed to capture both active and inactive behavioral periods. Three modeling approaches are implemented, including a tree-based model and sequential learning models, to predict next-month purchase behavior using a time-based train-test split. The results demonstrate that LightGBM achieves superior predictive performance, with an AUC of 0.92, outperforming LSTM and GRU. However, the three models exhibit a decline in classification performance under high-volatility conditions. To further interpret model behavior, SHAP analysis is conducted, revealing that both behavioral features and market volatility significantly influence predictions. In particular, volatility emerges as an important contextual factor, with effects that vary across levels of customer activity.

The purpose of this study was to develop and evaluate Point Cloud Data (PCD) deep learning models and a rule-based system for segmenting tree structures (stems and crowns) using fixed terrestrial LiDAR data. The dataset comprised 48 Larix Kaemferi trees, which were collected and preprocessed. For the PCD deep learning models, three downsampled datasets consisting of 1024, 4096, and 16384 points were constructed from the original data. The data was divided into training (70%) and validation (30%) sets. Models were built using PointNet and PointNet++ architectures, resulting in a total of 12 tree structure segmentation models for accuracy comparison. The rule-based system was developed using the original data, applying techniques such as verticality checks, cylindrical structure detection, and slice-based circular fitting to detect the stem. It then segmented the stem through repetitive circle fitting and validation processes based on height. The average accuracy of the PCD deep learning tree structure segmentation models was approximately 95%, with the PointNet++ model using 16384 points achieving the highest classification accuracy of about 98%. The rule-based system achieved high classification accuracy of over 99% for both tree species. This study is expected to contribute to precise measurement and efficient management of forest resources by presenting automated methods for tree structure segmentation using AI technology and rule-based approaches. It is anticipated that this research will serve as a foundation for the advancement of forest digitalization, precision forest management technologies, forest structure analysis, and timber production estimation in various fields.

본 연구에서 의사결정트리는 지니 불순도(Gini Impurity)를 기준으로 데이터를 재귀적으로 분할하여 규칙 기반 예측 수행한다. 랜덤포레스트는 다수의 의사결정트리를 무작위 샘플링을 통해 학습시키고 투표 방식을 통해 최종 예측 수행한다. 그래디언트부스팅은 약한 분류기를 순차적으로 학습시키며, 이전 단계의 오차를 줄여나가는 방식으로 예측 성능 개선한다. 또한 해석 용이성을 위해 학습은 depth=3으로 고정했다. 학습이 더 깊어도 세 가지 모델들의 구조적인 그림은 max_depth=3까지만 나타냈다. 랜덤포레스트의 최종 예측 트리는 숲 전체의 다수결 판단을 근사하는 설명용 트리이다. 다시 말해서 이들의 최종 예측 트리는 숲의 수백 트리들을 한 장의 트리로 보여줄 수 없으므로 일반적으로 대리 트리 기법을 사용하였다. 그래디언트부스팅 트리에서는 300번째 트리를 출력했다. 인공지능 모델의 성능을 평가하는 데 중요한 지표들인 정확도, 정밀도, 재현율, 그리고 F1 점수 개념이다. 본 연구에서도 각각의 모델에 대해 정확도, 정밀도, 재현율, 그리고 F1 점수를 기반으로 성능을 평가하였다. 또한 각각의 모델에서 도출된 변수 중요도를 비교하여 해석적 차이를 분석하였다.

In this paper Rule-based prediction is performed by recursively dividing data based on Gini Impurity in the decision tree. Random forest trains multiple decision trees through random sampling and performs final prediction through voting. Gradient boosting learns weak classifiers sequentially and improves prediction performance by reducing errors in previous steps. Also for ease of interpretation, the learning is fixed as depth=3. Even if the learning is deeper, the structural picture of the three models is shown only up to max_depth=3. The final prediction tree of the random forest is an explanatory tree that approximates the majority judgment of the entire forest. In other words, their final prediction tree cannot show hundreds of trees in a forest as a single tree, so they generally used a surrogate tree technique. In the gradient boosting tree, the 300th tree was output. The concepts of Accuracy, Precision, Recall, and F1-Score are important indicators for evaluating the performance of artificial intelligence models. In this study, the performance of each model was evaluated based on Accuracy, Precision, Recall, and F1 score. In addition, analytical differences were analyzed by comparing the variable importance derived from each model.

In this paper, we present a new, easy-to-generate system that is capable of creating virtual 3D tree models and simulating a variety of growth processes of a tree from a single, real tree image. We not only construct various tree models with the same trunk through our proposed digital image matting method and skeleton-based abstraction of branches, but we also animate the visual growth of the constructed 3D tree model through usage of the branch age information combined with a scaling factor. To control the simulation of a tree growth process, we consider tree-growing attributes, such as branching orders, branch width, tree size, and branch self-bending effect, at the same time. Other invisible branches and leaves are automatically attached to the tree by employing parametric branch libraries under the conventional procedural assumption of structure having a local self-similarity. Simulations with a real image confirm that our system makes it possible to achieve realistic tree models and growth processes with ease.

본 연구에서는 기술문서의 인용 정보를 기반으로 직접인용과 간접인용을 고려하여 핵심 문서를 선별하였고 선별된 문서 간의 인용네트워크 트리(citation network tree)를 생성하여 기술진화 경로를 추출하고자 하였다. 활용 예시로 OLED(유기발광다이오드) 분야 특허데이터를 분석하여 핵심문서를 선별한 후 문서간 인용관계 트리 계보도를 생성하였고, 그 중 OLED 원천기술이 어떤 기술진화 경로를 통해 반도체 관련 기술로 전이되었는지 분석하였다. 다른 한편으로 그래핀(graphene) 분야 논문의 인용관계 트리 분석을 통하여 간접인용을 고려한 가중치 계산방법이 직접인용만을 고려한 피인용 회수 계산법보다 현실을 더 잘 반영함을 고찰하였다.

We selected core documents from enormous number of documents by analyzing citation relation of papers or patents including direct citation and indirect citation. Then we tried to creat the technology evolution path from citation network tree. By applying the method to the patent DB of OLED (Organic Light Emitting Diode), we obtained genealogical citation network of core patents of OLED. We analyzed how the one of OLED technology was transferred to the semiconductor related technology and we named the process of transition as 'technology evolution path' of OLED technology. And we also analyzed the genealogical citation network of papers on graphene. From the analysis, we found that the weight count method including indirect citation was better in evaluating the value of technology of a paper than the times cited method.