• 산업경영시스템학회지
• /
• 제44권2호
• /
• pp.15-23
• /
• 2021

Most of the open-source decision tree algorithms are based on three splitting criteria (Entropy, Gini Index, and Gain Ratio). Therefore, the advantages and disadvantages of these three popular algorithms need to be studied more thoroughly. Comparisons of the three algorithms were mainly performed with respect to the predictive performance. In this work, we conducted a comparative experiment on the splitting criteria of three decision trees, focusing on their interpretability. Depth, homogeneity, coverage, lift, and stability were used as indicators for measuring interpretability. To measure the stability of decision trees, we present a measure of the stability of the root node and the stability of the dominating rules based on a measure of the similarity of trees. Based on 10 data collected from UCI and Kaggle, we compare the interpretability of DT (Decision Tree) algorithms based on three splitting criteria. The results show that the GR (Gain Ratio) branch-based DT algorithm performs well in terms of lift and homogeneity, while the GINI (Gini Index) and ENT (Entropy) branch-based DT algorithms performs well in terms of coverage. With respect to stability, considering both the similarity of the dominating rule or the similarity of the root node, the DT algorithm according to the ENT splitting criterion shows the best results.

• 한국컴퓨터정보학회논문지
• /
• 제14권7호
• /
• pp.89-95
• /
• 2009

본 논문의 공간색인을 사용하여 RFID 태그를 관리하는 태그색인 기법을 제안한다. 재고 관리 등에 사용되는 태그는 리더에 의해 위치가 결정된다. 즉, 태그가 부착된 제품이 리더에 인식됨으로써 제품의 위치가 생성되어 추적이 가능하다. 본 논문은 RFID 태그가 부착된 제품을 관리하는 혼합태그색인(hTag-tree: Hybrid Tag index)을 제안한다. hTag-tree는 태그의 특성을 반영하여 빠른 검색이 가능하도록 제안하는 새로운 색인이며 리더의 공간좌표를 이용하여 태그를 관리하는 태그 인덱스이다. 본 제안 색인은 동적환경에서 태그의 삽입, 삭제, 갱신에서 빠른 노드접근이 가능하며, 기존 기법에 비해 태그 검색시 노드접근 횟수를 최소화한다. 또한 기존 태그색인에서 MBR의 확장으로 인하여 조상 노드를 접근함으로써 탐색성능이 저하되는 것을 방지하였다. 제안한 색인의 실험은 태그 인덱스인 Fixed Interval R-tree와 기존의 공간색인인 R-tree를 비교 하였으며 결과적으로 데이터 탐색을 위한 노드접근횟수와 검색 시간에 있어서 hTag-tree가 더 향상된 시간을 나타낸다. 이는 제안 색인을 이용하면 다량의 RFID 태그를 보다 효율적으로 관리할 수 있다는 사실을 보여주고 있는 것이다.

• 한방안이비인후피부과학회지
• /
• 제16권2호
• /
• pp.1-45
• /
• 2003

We get the conclusion this following through bibliographic consideration about the cause of disease, disease mechanisms and remedy, prescription of tuberculosis of the cervical lymphic node. 1. The tuberculosis of the cervical Iymphic node is named the linear lump of scrofula(마도라력), the scrofula around neck(반사력), the wide-spread scrofula(류주력), the papule like lotus seed(련자력), the scrofula(라력), the subcutaneous nodes(結核), the scrofula due to disorder of Gi(기력) and the scrofula due to accumulation of phlegm(담력) according to the criterion of regions of disease, causes, rounding parts and shapes. 2. The cause of the tuberculosis of the cervical lymphic node are the stagnation of liver Gi(肝氣鬱結), the accumulation of phlegm and the stagnation of Gi(痰凝氣滯), the deficiency of vital essence of the liver and kidney(肝腎陰虛), the wind-heat of liver, gallbladder and triple warmer(肝膽三焦風熱), the dry-fire(燥火), the dryness of blood(血燥), the unwholesome diet(飮食不潔), the abundance of diet(食味之厚), the stagnation of Gi(鬱氣之積), the exhaustion syndrome(虛勞), the excessive thought(思慮過多), the toxin of wind-heat(風熱毒) and the germ of subcutaneous nodes(結核菌). 3. Symptoms of the tuberculosis of the cervical lymphic node are swelling slowly in comparison in the early days of occurrence, and are not pain, not itch, not heat, not other special symptoms. But in some cases, tuberculosis of the cervical lymphic node are quickly swelling in the early days of occurrence, and the fever and pain appear, The pyosis is accompanied with the fever and the pain at first generally, and then removing the pus from abscess is dissolved the fever and the pain in the majority of cases and representative of the general exhaustion syndrome. 4, The remedy of tuberculosis of the cervical Iymphic node is the early days, clearing the liver and relieves constraint(疏肝解鬱), phlegm and dissolving accumulation(化痰散結) the middle days, pus draining and toxin expelIing(托裏透膿) the latter days, replenish the kidney and strengthen the spleen(滋腎健脾). 5. The medication to treat the tuberculosis of the cervical lymphic node are the 益氣養榮湯(lkgiyangyoungtang)(14th), the 夏枯草散(Hagochosan)(10th) and et cetra in regular sequence. 6. The herb to treat the tuberculosis of the cervical Iymphic node are the 連翹(FRUCTUS FORSYTHlAE)(59th), the 甘草(RADIX GLYCYRRHIZAE)(51th), the 當歸(RADIX ANGELICAE GlGANTIS)(47th), the 黃芩(RADlXSCUTELLARIAE)(40th), the 夏枯草(SPICA PRUNELLAE)(23th) in regular sequence.

• 한국멀티미디어학회논문지
• /
• 제9권12호
• /
• pp.1529-1541
• /
• 2006

Moving objects have been widely employed in traffic and logistic applications. Spatio-temporal aggregations mainly describe the moving object's behavior in the spatial data warehouse. The previous works usually express the object moving in some certain region, but ignore the object often moving along as the trajectory. Other researches focus on aggregation and comparison of trajectories. They divide the spatial region into units which records how many times the trajectories passed in the unit time. It not only makes the storage space quite ineffective, but also can not maintain spatial data property. In this paper, a spatio-temporal aggregation index structure for moving object trajectory in constrained network is proposed. An extended B-tree node contains the information of timestamp and the aggregation values of trajectories with two directions. The network is divided into segments and then the spatial index structure is constructed. There are the leaf node and the non leaf node. The leaf node contains the aggregation values of moving object's trajectory and the pointer to the extended B-tree. And the non leaf node contains the MBR(Minimum Bounding Rectangle), MSAV(Max Segment Aggregation Value) and its segment ID. The proposed technique overcomes previous problems efficiently and makes it practicable finding moving object trajectory in the time interval. It improves the shortcoming of R-tree, and makes some improvement to the spatio-temporal data in query processing and storage.

• 한국IT서비스학회지
• /
• 제15권4호
• /
• pp.97-109
• /
• 2016

The rapid deployment of millions of mobile sensors and smart devices has resulted in high demand for opportunistic encounter-based networking. For the cooperative video surveillance of dashboard cameras in nearby vehicles, a fast and energy-efficient asynchronous neighbor discovery protocol is indispensable because a dashboard camera is an energy-hungry device after the vehicle's engine has turned off. In the existing asynchronous neighbor discovery protocols, all nodes always try to discover all neighbors. However, a dashboard camera needs to discover nearby dashboard cameras when an event is detected. In this paper, we propose a fast and energy-efficient asynchronous neighbor discovery protocol, which enables nodes : 1) to have different roles in neighbor discovery, 2) to discover neighbors within a search range, and 3) to report promptly the exact discovery result. The proposed protocol has two modes: periodic wake-up mode and active discovery mode. A node begins with the periodic wake-up mode to be discovered by other nodes, switches to the active discovery mode on receiving a neighbor discovery request, and returns to the periodic wake-up mode when the active discovery mode finishes. In the periodic wake-up mode, a node wakes up at multiples of number ${\alpha}$, where ${\alpha}$ is determined by the node's remaining battery power. In the active discovery mode, a node wakes up for consecutive ${\gamma}$ slots. Then, the node operating in the active discovery mode can discover all neighbors waking up at multiples of ${\beta}$ for ${\beta}{\leq}{\gamma}$ within ${\gamma}$ time slots. Since the proposed protocol assigns one half of the duty cycle to each mode, it consumes equal to or less energy than the existing protocols. A performance comparison shows that the proposed protocol outperforms the existing protocols in terms of discovery latency and energy consumption, where the frequency of neighbor discovery requests by car accidents is not constantly high.

• 한국산학기술학회논문지
• /
• 제15권10호
• /
• pp.6329-6335
• /
• 2014

스트럿-타이 모델에서 절점 폭은 해석과 설계에서 중요하다. 그것은 트러스 유사 시스템에서 힘의 분포에 영향을 준다. 또한, 설계 코드를 만족시키기 위한 모든 스트럿 및 절점의 검증에도 영향을 미친다. 여기서 코드는 ACI-318 코드를 의미한다. 절점 폭을 결정하는 4가지 방법이 있다. 즉 1)유효 깊이를 보 높이의 0.9배로 가정하는 방법 2)모멘트 평형을 이용하는 방법 3)절점 폭을 380mm로 가정하는 방법 그리고 4)본 연구에서 제안된 방법이다. 106개의 파라미터 연구를 분석하였다. 그 결과 필요로 하는 총 강재량이 4가지 방법 모두 크게 차이가 나지 않기 때문에 가장 쉬운 방법으로 선택하는 것이 시간 절약 측면에서 좋을 것으로 판단된다.

• 한국정보처리학회논문지
• /
• 제5권8호
• /
• pp.2061-2074
• /
• 1998

패턴 인식의 분야에서 그래프는 복잡한 대상체의 표현 및 인식의 도구로서 많이 사용되지만, 그래프간의 유사성 비교에는 많은 시간이 소요될 뿐아니라 실제 입력되는 영상은 왜곡으로 인해 저장되어 있는 이상적인 영상과 동일함을 기대할 수 없으므로 유사한 정도를 판별하는 기준이 마련되어야만 한다. 이 논문에서는 행렬을 그래프의 표현 수단으로 사용하였다. 행렬은 표현이 간단하며, 정의되어 있는 연산을 통해 순서 배열 및 매칭 과정을 간단히 수행하루 수 있다. 이 때 그래프를 구성하는 노드(node)들을 기하학적 위치에 따라 순서 배열함으로써 그래프를 구성하는 노드들 사이의 대응 관계를 효율적으로 찾을 수 있도록 하였으며, 또한 왜곡으로 인하여 기호를 표현하는 그래프의 노드가 제대로 추출되지 못한 경우는 기호의 구조를 고려하여 보정해 줄 수 있는 분할 과정을 도입하여 해결하였다. 제안한 방법은 악보의 비음표 기호 인식을 통해 실험하였으며, 실험 결과 95% 정도의 인식률을 얻을 수 있었다.

• 대한전자공학회논문지TC
• /
• 제49권5호
• /
• pp.72-76
• /
• 2012

이동성이 있는 센서 노드로 구성 된 센서 네트워크를 효율적으로 사용하기 위하여 고려해야 할 사항 중 중요한 것이 자원의 효율적인 사용과 신호를 빠르고 정확하게 보내는 것이다. 본 논문에서는 무선 센서 네트워크 내에서 SNR(Signal to Noise Ratio)과 릴레이 노드의 신호 증폭률 그리고 노드와 노드 간 직접적으로 통신하는 경우 경로의 이득의 변화에 따른 무선 센서 네트워크의 특성에 대하여 분석하고 다수의 협동 릴레이 노드가 존재할 때 선택기준을 제시하고 이에 따른 영향을 정량적으로 평가하였다.

• 한국경영과학회지
• /
• 제16권2호
• /
• pp.86-102
• /
• 1991

The purpose of this paper is to present a branch and bound algorithm for the hierarchical transportation network design problem in 2-level directed networks. This problem is to find the least cost of hierarchical transportation networks which consist of a primary path and a secondary path. The primary path is a simple path from a prespecified orgin node to a prespecified terminal node. All nodes must be either a transsipment node on the primary path or connected to that path via secondary arcs. This problem is formulated to a 0-1 inter programming problem with assignment and illegal subtour elimination equations as constaints. We show that the subproblem relaxing subtour elimination constraints is transformed to a linear programming problem by means of the totally unimodularity. Optimal solutions of this subproblem are polynoially obtained by the assignment algorithm and complementary slackness conditions. Therefore, the optimal value of this subproblme is used as a lower bound. When an optimal solution of the subproblem has an illegal subtour, a better disjoint rule is adopted as the branching strategy for reducing the number of branched problems. The computational comparison between the least bound rule and the depth first rule for the search strategy is given.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권5호
• /
• pp.1929-1950
• /
• 2020

Reliable and secure data transmission in the application environment assisted by the wireless sensor network is one of the major challenges. Problem like blind forwarding and data inaccessibility affect the efficiency of overall infrastructure performance. This paper proposes routing protocol for forwarding and error recovery during packet loss. The same is achieved by energy and hops distance-based formulation of the routing mechanism. The reachability of the intermediate node to the source node is the major factor that helps in improving the lifetime of the network. On the other hand, intelligent hop selection increases the reliability over continuous data transmission. The number of hop count is factor of hop weight and available energy of the node. The comparison over the previous state of the art using QualNet-7.4 network simulator shows the effectiveness of proposed work in terms of overall energy conservation of network and reliable data delivery. The simulation results also show the elimination of blind forwarding and data inaccessibility.