• Title/Summary/Keyword: whole-tree

Search Result 318, Processing Time 0.029 seconds

A Study on Digit Modeling for Korean Connected Digit Recognition (한국어 연결숫자인식을 위한 숫자 모델링에 관한 연구)

  • 김기성
    • Proceedings of the Acoustical Society of Korea Conference
    • /
    • 1998.08a
    • /
    • pp.293-297
    • /
    • 1998
  • 전화망에서의 연결 숫자 인식 시스템의 개발에 대한 내용을 다루며, 이 시스템에서 다양한 숫자 모델링 방법들을 구현하고 비겨하였다. Word 모델의 경우 문맥독립 whole-word 모델을 구현하였으며, sub-word 모델로는 triphone 모델과 불파음화 자음을 모음에 포함시킨 modified triphone 모델을 구현하였다. 그리고 tree-based clustering 방법을 sub-word 모델과 문맥종속 whole-word 모델에 적용하였다. 이와 같은 숫자모델들에 대해 연속 HMM을 이용하여 화자독립 연결숫자 인식 실험을 수행한 결과, 문맥종속 단어 모델이 문맥독립 단어 모델보다 우수한 성능을 나타냈으며, triphone 모델과 modified triphone 모델은 유사한 성능을 나타냈다. 특히 tree-based clustering 방법을 적용한 문맥종속 단어 모델이 4연 숫자열에 대해 99.8%의 단어 dsltlr률 및 99.1%의 숫자열 인식률로서 가장 우수한 성능을 나타내었다.

  • PDF

A Vehicle Scheduling System for Efficient Delivery (효율적 수배송을 위한 배차계획시스템의 개발)

  • Park, Byung-Chun;Park, Jong-Youn
    • IE interfaces
    • /
    • v.11 no.1
    • /
    • pp.67-74
    • /
    • 1998
  • This study is to develop a vehicle scheduling system for the efficient delivery of goods to places of business. For gathering data and testing the system developed, we have chosen a company which is located in Taegu city and has more than 700 delivery points over Taegu city and Kyungbuk province. We consider multiple vehicle types, travel time restrictions on vehicles, vehicle acceptance restrictions at delivery points, and other operational restrictions. We divide the whole delivery points into 44 regions and generate a region-based shortest path tree. Based on the shortest path tree, we perform vehicle assignment sequentially for each vehicle used. Then vehicle routings are determined. We have implemented the whole procedure on computer system. The system developed is flexible enough to be applicable to other companies by just changing the standard data.

  • PDF

FIRE WATER SYSTEM RELIABILITY IN INDUSTRIAL APPLICATIONS

  • James M. Dewey;Kim, Yong-Dal
    • Proceedings of the Korea Institute of Fire Science and Engineering Conference
    • /
    • 1997.11a
    • /
    • pp.526-533
    • /
    • 1997
  • Reliability of fire protection systems is often discussed, written about, and even put into codes and standards. However, reliability is seldom considered for the fire protection system as a whole. Why does this happen and why should the designer consider the system as a whole\ulcorner Existing codes and standards incorporate the concept of reliability usually In the form of key component redundancy for some parts of a system. The "Fire Safety Concepts Tree" presented in the National Fire Protection Association Guide 550, Guide to the Fire Safety Concepts Tree, provides a starting point for considering the performance of a water based fire suppression system. Considering fire protection objectives for water based fire suppression systems, means of evaluating system reliability can be developed. This development requires identification of system components that are significant to the overall system reliability.

  • PDF

MRI Predictors of Malignant Transformation in Patients with Inverted Papilloma: A Decision Tree Analysis Using Conventional Imaging Features and Histogram Analysis of Apparent Diffusion Coefficients

  • Chong Hyun Suh;Jeong Hyun Lee;Mi Sun Chung;Xiao Quan Xu;Yu Sub Sung;Sae Rom Chung;Young Jun Choi;Jung Hwan Baek
    • Korean Journal of Radiology
    • /
    • v.22 no.5
    • /
    • pp.751-758
    • /
    • 2021
  • Objective: Preoperative differentiation between inverted papilloma (IP) and its malignant transformation to squamous cell carcinoma (IP-SCC) is critical for patient management. We aimed to determine the diagnostic accuracy of conventional imaging features and histogram parameters obtained from whole tumor apparent diffusion coefficient (ADC) values to predict IP-SCC in patients with IP, using decision tree analysis. Materials and Methods: In this retrospective study, we analyzed data generated from the records of 180 consecutive patients with histopathologically diagnosed IP or IP-SCC who underwent head and neck magnetic resonance imaging, including diffusion-weighted imaging and 62 patients were included in the study. To obtain whole tumor ADC values, the region of interest was placed to cover the entire volume of the tumor. Classification and regression tree analyses were performed to determine the most significant predictors of IP-SCC among multiple covariates. The final tree was selected by cross-validation pruning based on minimal error. Results: Of 62 patients with IP, 21 (34%) had IP-SCC. The decision tree analysis revealed that the loss of convoluted cerebriform pattern and the 20th percentile cutoff of ADC were the most significant predictors of IP-SCC. With these decision trees, the sensitivity, specificity, accuracy, and C-statistics were 86% (18 out of 21; 95% confidence interval [CI], 65-95%), 100% (41 out of 41; 95% CI, 91-100%), 95% (59 out of 61; 95% CI, 87-98%), and 0.966 (95% CI, 0.912-1.000), respectively. Conclusion: Decision tree analysis using conventional imaging features and histogram analysis of whole volume ADC could predict IP-SCC in patients with IP with high diagnostic accuracy.

An Efficient Parallel Construction Scheme of An R-Tree using Hadoop (Hadoop을 이용한 R-트리의 효율적인 병렬 구축 기법)

  • Cong, Viet-Ngu Huynh;Kim, Jongmin;Kwon, Oh-Heum;Song, Ha-Joo
    • Journal of Korea Multimedia Society
    • /
    • v.22 no.2
    • /
    • pp.231-241
    • /
    • 2019
  • Bulk-loading an R-tree can be a good approach to build an efficient one. However, it takes a lot of time to bulk-load an R-tree for huge amount of data. In this paper, we propose a parallel R-tree construction scheme based on a Hadoop framework. The proposed scheme divides the data set into a number of partitions for which local R-trees are built in parallel via Map-Reduce operations. Then the local R-trees are merged into an global R-tree that covers the whole data set. While generating the partitions, it considers the spatial distribution of the data into account so that each partition has nearly equal amounts of data. Therefore, the proposed scheme gives an efficient index structure while reducing the construction time. Experimental tests show that the proposed scheme builds an R-tree more efficiently than the existing approaches.

Design and Implementation of a Trajectory-based Index Structure for Moving Objects on a Spatial Network (공간 네트워크상의 이동객체를 위한 궤적기반 색인구조의 설계 및 구현)

  • Um, Jung-Ho;Chang, Jae-Woo
    • Journal of KIISE:Databases
    • /
    • v.35 no.2
    • /
    • pp.169-181
    • /
    • 2008
  • Because moving objects usually move on spatial networks, efficient trajectory index structures are required to achieve good retrieval performance on their trajectories. However, there has been little research on trajectory index structures for spatial networks such as FNR-tree and MON-tree. But, because FNR-tree and MON-tree are stored by the unit of the moving object's segment, they can't support the whole moving objects' trajectory. In this paper, we propose an efficient trajectory index structure, named Trajectory of Moving objects on Network Tree(TMN Tree), for moving objects. For this, we divide moving object data into spatial and temporal attribute, and preserve moving objects' trajectory. Then, we design index structure which supports not only range query but trajectory query. In addition, we divide user queries into spatio-temporal area based trajectory query, similar-trajectory query, and k-nearest neighbor query. We propose query processing algorithms to support them. Finally, we show that our trajectory index structure outperforms existing tree structures like FNR-Tree and MON-Tree.

On the Performance Evaluation of Energy-Aware Sleep Scheduling (EASS) in Energy Harvesting WSN (EH-WSN)

  • Encarnacion, Nico N.;Yang, Hyun-Ho
    • Journal of information and communication convergence engineering
    • /
    • v.10 no.3
    • /
    • pp.264-268
    • /
    • 2012
  • Tree-based structures offer assured optimal paths from the data source to the sink. Shortest routes are disregarded since these do not consider the remaining energy level of the nodes. This shortens the lifetime of the whole network. Most tree-based routing protocols, although aware of the nodes' energy, do not consider an energy aware sleep scheduling scheme. We propose an energy-aware sleep scheduling (EASS) scheme that will improve the sleep scheduling scheme of an existing tree-based routing protocol. An energy harvesting structure will be implemented on the wireless sensor network. The depth of sleep of every node will be based on the harvested energy.

Cooperative behavior and control of autonomous mobile robots using genetic programming (유전 프로그래밍에 의한 자율이동로봇군의 협조행동 및 제어)

  • 이동욱;심귀보
    • 제어로봇시스템학회:학술대회논문집
    • /
    • 1996.10b
    • /
    • pp.1177-1180
    • /
    • 1996
  • In this paper, we propose an algorithm that realizes cooperative behavior by construction of autonomous mobile robot system. Each robot is able to sense other robots and obstacles, and it has the rule of behavior to achieve the goal of the system. In this paper, to improve performance of the whole system, we use Genetic Programming based on Natural Selection. Genetic Programming's chromosome is a program of tree structure and it's major operators are crossover and mutation. We verify the effectiveness of the proposed scheme from the several examples.

  • PDF

Solving Cluster Based Multicast Routing Problems Using A Simulated Annealing Algorithm (시뮬레이티디 어닐링 알고리즘을 이용한 클러스터 기반의 멀티캐스트 라우팅 문제 해법)

  • Kang Myung-Ju
    • Journal of the Korea Society of Computer and Information
    • /
    • v.9 no.3
    • /
    • pp.189-194
    • /
    • 2004
  • This paper proposes a Simulated Annealing(SA) algorithm for cluster-based Multicast Routing problems. Multicasting, the transmission of data to a group, can be solved from constructing multicast tree, that is. the whole network is partitioned to some clusters and the clusters are constructed by multicast tree. Multicast tree can be constructed by minimum-cost Steiner tree. In this paper, an SA algorithm is used in the minimum-cost Steiner tree. Especially, in SA, the cooling schedule is an important factor for the algorithm. Hence, in this paper, a cooling schedule is proposed for SA for multicast routing problems and analyzed the simulation results.

  • PDF

A Study on the growth Characteristics of the landscape Trees in the Apartment Housing Areas (공동주택단지내 녹화용 수목의 생장특성)

  • 윤근영;안건광
    • Journal of Environmental Science International
    • /
    • v.5 no.3
    • /
    • pp.337-346
    • /
    • 1996
  • The purpose of this study was to provide basic data of the growth characteristics of the landscape trees for better landscape planting design, construction and maintenance through the prediction of landscape change as time passes fly the analysis of survival rate, distribution patterns & increment percent of tree height, width, stem diameter (breast or surface) of widely used six tree species in Seongnam-si Eunhang-jugong apartment housing areas (8 years have passed after landsape alanting work). The main results can be summarized as followed. The tree survival rate of Pinus parviflora was the highest rate 89.2% than any other species, but Acer buergerianum showed the lowest survival rate at that of it 35.0%, & that of Picea abies 70.5 %, Metasequoia glyptostroboides 71.6%, Maknolia denudata 38.9%, Acer paimatum was 71.7%, As a whole, the tree survival rate of coniferous trees were relatively high. The tree height increment percent of the deciduous species wert relatively high. And that of Metasequoia glyptostroboides was the highest rate 11.61% than any other species, but that of Magnolia denudata was the lowest rate 5.59% than any other species. According to this results, the increment percent of trees in this apartment areas were comparatively lower than that of each related species planted in nursery area. And this results would be considered when landscape experts do landscape planting design, construction & maintenance. The distribution patterns of present tree size showed a Normal Distribution like any other biological features.

  • PDF