Earticle

This study develops a systematic, verifiable experimental study to clarify when and how transforming tabular data into graph structures enhances node-level classification: AI-generated synthetic dataset with controlled numbers of nodes, classes, and imbalance; two interpretable graphs are constructed (1) a similarity-based k-nearest neighbors graph with the number of neighbors and model depth varied, and (2) a rule-based graph with explicit, transparent connection rules; and graph-based methods GCN, GraphSAGE to approach this baseline when k and depth are appropriately tuned, before performance saturates or declines due to excessive signal averaging; and rule-based graphs expose architectural differences GraphSAGE is higherperforming and more stable, whereas GCN is more structuresensitive and degrades with depth implying that approaches preserving node-specific information and flexibly aggregating signals are more robust to structural heterogeneity. Overall, the framework offers practical guidance for method selection and graph construction particularly the choice neighbors and depth in a simplified, reproducible form readily extensible to real-world applications.

Purpose: The 7th AJCC tumor node metastasis (TNM) staging system modified the classification of the lymph node metastasis widely compared to the 6th edition. To evaluate the prognostic predictability of the new TNM staging system, we analyzed the survival rate of the gastric cancer patients assessed by the 7th staging system. Materials and Methods: Among 2,083 patients who underwent resection for gastric cancer at the department of surgery, Hanyang Medical Center from July 1992 to December 2009, This study retrospectively reviewed 5-year survival rate (5YSR) of 624 patients (TanyN3M0: 464 patients, TanyNanyM1: 160 patients) focusing on the number of metastatic lymph node and distant metastasis. We evaluated the applicability of the new staging system. Results: There were no significant differences in 5YSR between stage IIIC with more than 29 metastatic lymph nodes and stage IV (P=0.053). No significant differences were observed between stage IIIB with more than 28 metastatic lymph nodes and stage IV (P=0.093). Distinct survival differences were present between patients who were categorized as TanyN3M0 with 7 to 32 metastatic lymph nodes and stage IV. But patients with more than 33 metastatic lymph nodes did not show any significant differences compared to stage IV (P=0.055). Among patients with TanyN3M0, statistical significances were seen between patients with 7 to 30 metastatic lymph nodes and those with more than 31 metastatic lymph nodes. Conclusions: In the new staging system, modifications of N classification is mandatory to improve prognostic prediction. Further study involving a greater number of cases is required to demonstrate the most appropriate cutoffs for N classification.

Purpose: The 7th AJCC tumor node metastasis (TNM) staging system modified the classification of the lymph node metastasis widely compared to the 6th edition. To evaluate the prognostic predictability of the new TNM staging system, we analyzed the survival rate of the gastric cancer patients assessed by the 7th staging system. Materials and Methods: Among 2,083 patients who underwent resection for gastric cancer at the department of surgery, Hanyang Medical Center from July 1992 to December 2009, This study retrospectively reviewed 5-year survival rate (5YSR) of 624 patients (TanyN3M0: 464 patients, TanyNanyM1: 160 patients) focusing on the number of metastatic lymph node and distant metastasis. We evaluated the applicability of the new staging system. Results: There were no significant differences in 5YSR between stage IIIC with more than 29 metastatic lymph nodes and stage IV (P=0.053). No significant differences were observed between stage IIIB with more than 28 metastatic lymph nodes and stage IV (P=0.093). Distinct survival differences were present between patients who were categorized as TanyN3M0 with 7 to 32 metastatic lymph nodes and stage IV. But patients with more than 33 metastatic lymph nodes did not show any significant differences compared to stage IV (P=0.055). Among patients with TanyN3M0, statistical significances were seen between patients with 7 to 30 metastatic lymph nodes and those with more than 31 metastatic lymph nodes. Conclusions: In the new staging system, modifications of N classification is mandatory to improve prognostic prediction. Further study involving a greater number of cases is required to demonstrate the most appropriate cutoffs for N classification.

정보통신 기술이 발전함에 따라 우리는 일상에서 다양한 형태의 데이터를 손쉽게 생성하고 있다. 이처럼 방대한 데이터를 효율적으로 관리하려면, 체계적인 카테고리별 분류가 필수적이다. 효율적인 검색과 탐색을 위해서 데이터는 트리 형태의 계층적 구조인 범주 트리로 조직화되는데, 이는 뉴스 웹사이트나 위키피디아에서 자주 볼 수 있는 구조이다. 이에 따라 방대한 양의 문서를 범주 트리의 단말 노드로 분류하는 다양한 기법들이 제안되었다. 그러나 범주 트리를 대상으로 하는 문서 분류기법들은 범주 트리의 높이가 증가할수록 단말 노드의 수가 기하급수적으로 늘어나고 루트 노드부터 단말 노드까지의 길이가 길어져서 오분류 가능성이 증가하며, 결국 분류 정확도의 저하로 이어진다. 그러므로 본 연구에서는 사용자의 요구 분류 정확도를 만족시키면서 세분화된 분류를 구현할 수 있는 새로운 노드 확장 기반 분류 알고리즘을 제안한다. 제안 기법은 탐욕적 접근법을 활용하여 높은 분류정확도를 갖는 노드를 우선적으로 확장함으로써, 범주 트리의 분류 정확도를 극대화한다. 실데이터를 이용한 실험 결과는 제안 기법이 단순 방법보다 향상된 성능을 제공함을 입증한다.

With the advancement of information and communication technology, we can easily generate various forms of data in our daily lives. To efficiently manage such a large amount of data, systematic classification into categories is essential. For effective search and navigation, data is organized into a tree-like hierarchical structure known as a category tree, which is commonly seen in news websites and Wikipedia. As a result, various techniques have been proposed to classify large volumes of documents into the terminal nodes of category trees. However, document classification methods using category trees face a problem: as the height of the tree increases, the number of terminal nodes multiplies exponentially, which increases the probability of misclassification and ultimately leads to a reduction in classification accuracy. Therefore, in this paper, we propose a new node expansion-based classification algorithm that satisfies the classification accuracy required by the application, while enabling detailed categorization. The proposed method uses a greedy approach to prioritize the expansion of nodes with high classification accuracy, thereby maximizing the overall classification accuracy of the category tree. Experimental results on real data show that the proposed technique provides improved performance over naive methods.

현재 트위터에서 제공되는 친구추천 시스템은 영향력이 높은 사용자를 우선적으로 추천해준다. 하지만 사용자정보의 유사성이 높은 다른 사용자는 추천되지 않는 단점을 가지고 있다. 사용자들은 정보의 유사성이 높은 사용자 추천을 원하기 때문에 이러한 단점을 극복하기 위하여 본 논문에서는 사용자정보의 유사성을 기반으로 팔로어 추천 시스템을 구현하였다. 본 논문에서 사용된 데이터는 SNAP(Stanford Network Analysis Platform)에서 제공하는 데이터로, 팔로어의 수가 10,000명이상인 트위터의 사용자정보와 노드간 연결 데이터로 구성된다. 이 데이터를 트레이닝 데이터로 활용하여 팔로어간의 관계를 분류해줄 수 있는 분류자를 생성하고, 10-Fold Cross Validation을 활용하여, 분류자의 정확도를 판단한다. 두 트위터의 정보가 주어지면 그들 사이에 친구 관계, 팔로우 관계, 비연결 관계를 추천한다.

Current friend recommendation system on Twitter primarily recommends the most influential twitter. However, this way of recommendation has drawbacks where it does not recommend the users of which attributes of interests are similar to theirs. Since users want other users of which attributes are similar, this study implements follower recommendation system based on the similarity of twitter node informations. The data in this study is from SNAP(Stanford Network Analysis Platform), and it consists of twitter node information of which number of followers is over 10,000 and twitter link information. We used the SNAP data as a training data, and generated a classifier which recommends and predicts the relation between followers. We evaluated the classifier by 10-Fold Cross validation. Once two twitter node informations are given, our model can recommend the relationship of the two twitters as one of following such as: FoFo(Follower Follower), FoFr(Follower Friend), NC(Not Connected).

본 논문은 실시간 영상 분석을 통해서 반려견에 대한 객체를 추출해 내고, 추출된 이미지로부터 반려견 행동을 분류하는 방법을 구현한다. 반려견 객체 탐지를 위해서 Darknet YOLO를 사용하였으며, 추출된 이미지로부터 행동 패턴 분류는 구글에서 제공하고 있는 Teachable Machine을 이용하였다. 학습된 Teachable Machine은 구글 드라이브에 저장되어 node.js 서버 상에서 ml5.js로 구현하여 사용할 수 있다. 분류된 행동 패턴 결과는 사용자의 스마트 폰 또는 PC로 실시간 전송되며, 언제 어디서든 확인 가능할 수 있게 node.js 서버에서 socket.io 모듈을 사용해서 상호반응 웹 서버를 구현하였다.

This paper implements a method of extracting an object about a dog through real-time image analysis and classifying dog behaviors from the extracted images. The Darknet YOLO was used to detect dog objects, and the Teachable Machine provided by Google was used to classify behavior patterns from the extracted images. The trained Teachable Machine is saved in Google Drive and can be used by ml5.js implemented on a node.js server. By implementing an interactive web server using a socket.io module on the node.js server, the classified results are transmitted to the user's smart phone or PC in real time so that it can be checked anytime, anywhere.