• 제목/요약/키워드: Multi-level Learning

검색결과 204건 처리시간 0.03초

다중 공간정보 데이터의 점진적 조합에 의한 의미적 분류 딥러닝 모델 학습 성능 분석 (Training Performance Analysis of Semantic Segmentation Deep Learning Model by Progressive Combining Multi-modal Spatial Information Datasets)

  • 이대건;신영하;이동천
    • 한국측량학회지
    • /
    • 제40권2호
    • /
    • pp.91-108
    • /
    • 2022
  • 대부분의 경우 광학 RGB 영상을 딥러닝(DL: Deep learning)의 학습 데이터로 사용하여 객체탐지, 인식, 식별, 분류, 의미적 분할 및 객체 분할 등을 수행하지만, 실세계의 3차원 객체들을 2차원 영상으로 완전하게 파악하는 것은 한계가 있다. 그러므로 대표적인 3차원 지형 공간정보인 수치표면모델(DSM: Digital Surface Model)과 더불어 DSM에 내재된 특성정보를 이용하여 3차원 지형지물을 분석하는 것이 효과적이다. 건물과 같이 기하학적으로 정형화된 형태의 인공구조물은 3차원 공간데이터로부터 얻을 수 있는 기하학적 요소와 특성을 이용하여 객체의 분류와 형상 묘사가 가능하다. 이 연구는 고차원 시각정보(high-level visual information) 시스템에서 중요한 역할을 하는 내재된 고유의 특성정보(intrinsic information)를 기반으로 하며, 이를 위하여 객체의 기하학적 요소인 경사와 주향을 DSM으로부터 도출하고, 다방향에서 생성한 음영기복영상(SRI: Shaded Relief Image)과 함께 DL 모델의 학습 수행에 사용하였다. 실험은 ISPRS (International Society for Photogrammetry and Remote Sensing)에서 제공하는 데이터 셋 중에서 DSM과 레이블 데이터를 객체의 의미적 분류를 위해 개발된 합성곱 기반의 SegNet 학습에 사용하였다. 지형지물을 분류하고 분류 결과를 이용하여 건물을 추출하였다. 특히 DL 모델의 학습 성능 향상을 위해 학습 데이터의 여러 조합에 따른 시너지 효과를 분석하는 것에 핵심이다. 제안한 방법은 건물 분류와 추출에 효과적임을 보여주고 있다.

Feasibility of fully automated classification of whole slide images based on deep learning

  • Cho, Kyung-Ok;Lee, Sung Hak;Jang, Hyun-Jong
    • The Korean Journal of Physiology and Pharmacology
    • /
    • 제24권1호
    • /
    • pp.89-99
    • /
    • 2020
  • Although microscopic analysis of tissue slides has been the basis for disease diagnosis for decades, intra- and inter-observer variabilities remain issues to be resolved. The recent introduction of digital scanners has allowed for using deep learning in the analysis of tissue images because many whole slide images (WSIs) are accessible to researchers. In the present study, we investigated the possibility of a deep learning-based, fully automated, computer-aided diagnosis system with WSIs from a stomach adenocarcinoma dataset. Three different convolutional neural network architectures were tested to determine the better architecture for tissue classifier. Each network was trained to classify small tissue patches into normal or tumor. Based on the patch-level classification, tumor probability heatmaps can be overlaid on tissue images. We observed three different tissue patterns, including clear normal, clear tumor and ambiguous cases. We suggest that longer inspection time can be assigned to ambiguous cases compared to clear normal cases, increasing the accuracy and efficiency of histopathologic diagnosis by pre-evaluating the status of the WSIs. When the classifier was tested with completely different WSI dataset, the performance was not optimal because of the different tissue preparation quality. By including a small amount of data from the new dataset for training, the performance for the new dataset was much enhanced. These results indicated that WSI dataset should include tissues prepared from many different preparation conditions to construct a generalized tissue classifier. Thus, multi-national/multi-center dataset should be built for the application of deep learning in the real world medical practice.

MMORPG에서 결정트리 학습을 적용한 자동 프로그램 확인 기법 (Identification of Auto Programs by Using Decision Tree Learning for MMORPG)

  • 홍성우;김준태;김형일
    • 한국멀티미디어학회논문지
    • /
    • 제9권7호
    • /
    • pp.927-937
    • /
    • 2006
  • 자동 게임 프로그램(auto-playing game programs)은 게임 플레이어를 대신하여 게임 캐릭터를 조종하는 프로그램으로 MMORPG(massively multi-player online role playing game)에서 빈번히 사용되고 있다. MMORPG에서 게임 캐릭터의 레벨을 올리기 위해서는 경험치가 필요하며, 경험치 증가 과정에서 아이템을 구매할 때 사용되는 게임 머니와 특정한 기술을 사용할 수 있는 아이템을 획득한다. 이러한 레벨-업 과정에서 게임 플레이어들은 지루함을 느끼게 되고, 빠른 게임 캐릭터의 성장을 위해 자동 프로그램을 사용하여 게임 캐릭터의 레벨을 증가시키는 경우가 빈번히 발생한다 그러나 자동 프로그램은 게임상에서 비정상적으로 자원을 독점하여 게임 시스템을 황폐화시킬 뿐만 아니라, 불법적인 수익사업으로 악용되어 건전한 게임산업 육성을 방해한다. 본 논문에서는 이러한 자동 게임 프로그램을 찾아내기 위하여 게임 캐릭터에 의해 발생되는 마우스와 키보드를 포함한 윈도우 이벤트 시퀀스를 분석하고, 이벤트 시퀀스로부터 속성 벡터를 생성하여 결정트리 학습을 수행하였다. 결정트리 학습은 윈도우 이벤트 시퀀스에 의해 생성된 속성 벡터들을 이용하여 자동 프로그램을 분류한다. 본 논문에서는 윈도우 이벤트 시퀀스를 활용하여 생성한 26개의 속성들을 결정트리 학습에 적용함으로써 MMORPG에서 자동 프로그램을 효과적으로 분류할 수 있다는 것을 MMORPG에 속하는 몇 가지 게임에 대한 실험을 통해 확인하였다.

  • PDF

Human Activity Recognition Based on 3D Residual Dense Network

  • Park, Jin-Ho;Lee, Eung-Joo
    • 한국멀티미디어학회논문지
    • /
    • 제23권12호
    • /
    • pp.1540-1551
    • /
    • 2020
  • Aiming at the problem that the existing human behavior recognition algorithm cannot fully utilize the multi-level spatio-temporal information of the network, a human behavior recognition algorithm based on a dense three-dimensional residual network is proposed. First, the proposed algorithm uses a dense block of three-dimensional residuals as the basic module of the network. The module extracts the hierarchical features of human behavior through densely connected convolutional layers; Secondly, the local feature aggregation adaptive method is used to learn the local dense features of human behavior; Then, the residual connection module is applied to promote the flow of feature information and reduced the difficulty of training; Finally, the multi-layer local feature extraction of the network is realized by cascading multiple three-dimensional residual dense blocks, and use the global feature aggregation adaptive method to learn the features of all network layers to realize human behavior recognition. A large number of experimental results on benchmark datasets KTH show that the recognition rate (top-l accuracy) of the proposed algorithm reaches 93.52%. Compared with the three-dimensional convolutional neural network (C3D) algorithm, it has improved by 3.93 percentage points. The proposed algorithm framework has good robustness and transfer learning ability, and can effectively handle a variety of video behavior recognition tasks.

Depth tracking of occluded ships based on SIFT feature matching

  • Yadong Liu;Yuesheng Liu;Ziyang Zhong;Yang Chen;Jinfeng Xia;Yunjie Chen
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • 제17권4호
    • /
    • pp.1066-1079
    • /
    • 2023
  • Multi-target tracking based on the detector is a very hot and important research topic in target tracking. It mainly includes two closely related processes, namely target detection and target tracking. Where target detection is responsible for detecting the exact position of the target, while target tracking monitors the temporal and spatial changes of the target. With the improvement of the detector, the tracking performance has reached a new level. The problem that always exists in the research of target tracking is the problem that occurs again after the target is occluded during tracking. Based on this question, this paper proposes a DeepSORT model based on SIFT features to improve ship tracking. Unlike previous feature extraction networks, SIFT algorithm does not require the characteristics of pre-training learning objectives and can be used in ship tracking quickly. At the same time, we improve and test the matching method of our model to find a balance between tracking accuracy and tracking speed. Experiments show that the model can get more ideal results.

Demand Forecasting with Discrete Choice Model Based on Technological Forecasting

  • 김원준;이정동;김태유
    • 기술경영경제학회:학술대회논문집
    • /
    • 기술경영경제학회 2003년도 제22회 동계학술발표회 논문집
    • /
    • pp.173-190
    • /
    • 2003
  • 수요예측은 국가와 기업의 전략수립과 효율적인 자원활용에 있어서 필수적인 사전기획요소이다. 본 논문은 이산선택모델과 확산모델을 복합적으로 고려하여 다세대 제품의 수요를 예측하였다. 이산선택모델은 정적인 관점에서 소비자들의 제품에 대한 평가를 분석하는 모델이다. 본 논문에서는 이러한 이산선택모델에 수요의 동적인 변화양상을 고려할 수 있는 확산모델을 결합하였다. 실증분석으로서 1999년에서 2005년까지의 세계 DRAM시장 수요를 예측하였다. 또한, DRAM의 가격과 기억용량에 대해 '무어의 법칙' 과 '학습곡선'을 각각 적용한 기술예측을 시도하였으며, 이를 바탕으로 보다 정교한 예측모델을 전개하였다. 제시된 모델은 산업수준의 자료를 이용하였으므로, 이산선택모델을 inversion 하여 분석을 시도하였다. 이를 통해 기존세대의 DRAM 제품에 대한 수요뿐만 아니라, 새로운 세대의 DRAM 제품에 대한 수요를 비교적 정확히 예측할 수 있었다.

  • PDF

Analysis of suitable evacuation routes through multi-agent system simulation within buildings

  • Castillo Osorio, Ever Enrique;Seo, Min Song;Yoo, Hwan Hee
    • 한국측량학회지
    • /
    • 제39권5호
    • /
    • pp.265-278
    • /
    • 2021
  • When a dangerous event arises for people inside a building and an immediate evacuation is required, it is important that suitable routes have been previously defined. These situations can happen especially when buildings are crowded, making the occupants have a very high vulnerability and can be trapped if they do not evacuate quickly and safely. However, in most cases, routes are considered based just on their proximity or short distance to the exit areas, and evacuation simulations that include more variables are not performed. This work aims to propose a methodology for building's indoor evacuation activities under the premise of processing simulation scenarios in multi-agent environments. In the methodology, importance indexes of simplified and validated geometry data from a BIM (Building Information Modeling) are considered as heuristic input data in a proposed algorithm. The algorithm is based on AP-Theta* pathfinding and collision avoidance machine learning techniques. It also includes conditioning variables such as the number of people, speed of movement as well as reaction ability of the agents that influence the evacuation times. Moreover, collision avoidance is applied between people or with objects along the route. The simulations using the proposed algorithm are tested in NetLogo for diverse scenarios, showing feasible evacuation routes and calculating evacuation times in a multi-agent environment. The experimental results are obtained by applying the method in a study case and demonstrate the level of effectiveness of the algorithm, and the influence of the conditioning variables analyzed together when performing safe evacuation routes.

AANet: Adjacency auxiliary network for salient object detection

  • Li, Xialu;Cui, Ziguan;Gan, Zongliang;Tang, Guijin;Liu, Feng
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • 제15권10호
    • /
    • pp.3729-3749
    • /
    • 2021
  • At present, deep convolution network-based salient object detection (SOD) has achieved impressive performance. However, it is still a challenging problem to make full use of the multi-scale information of the extracted features and which appropriate feature fusion method is adopted to process feature mapping. In this paper, we propose a new adjacency auxiliary network (AANet) based on multi-scale feature fusion for SOD. Firstly, we design the parallel connection feature enhancement module (PFEM) for each layer of feature extraction, which improves the feature density by connecting different dilated convolution branches in parallel, and add channel attention flow to fully extract the context information of features. Then the adjacent layer features with close degree of abstraction but different characteristic properties are fused through the adjacent auxiliary module (AAM) to eliminate the ambiguity and noise of the features. Besides, in order to refine the features effectively to get more accurate object boundaries, we design adjacency decoder (AAM_D) based on adjacency auxiliary module (AAM), which concatenates the features of adjacent layers, extracts their spatial attention, and then combines them with the output of AAM. The outputs of AAM_D features with semantic information and spatial detail obtained from each feature are used as salient prediction maps for multi-level feature joint supervising. Experiment results on six benchmark SOD datasets demonstrate that the proposed method outperforms similar previous methods.

Multi-Class Multi-Object Tracking in Aerial Images Using Uncertainty Estimation

  • Hyeongchan Ham;Junwon Seo;Junhee Kim;Chungsu Jang
    • 대한원격탐사학회지
    • /
    • 제40권1호
    • /
    • pp.115-122
    • /
    • 2024
  • Multi-object tracking (MOT) is a vital component in understanding the surrounding environments. Previous research has demonstrated that MOT can successfully detect and track surrounding objects. Nonetheless, inaccurate classification of the tracking objects remains a challenge that needs to be solved. When an object approaching from a distance is recognized, not only detection and tracking but also classification to determine the level of risk must be performed. However, considering the erroneous classification results obtained from the detection as the track class can lead to performance degradation problems. In this paper, we discuss the limitations of classification in tracking under the classification uncertainty of the detector. To address this problem, a class update module is proposed, which leverages the class uncertainty estimation of the detector to mitigate the classification error of the tracker. We evaluated our approach on the VisDrone-MOT2021 dataset,which includes multi-class and uncertain far-distance object tracking. We show that our method has low certainty at a distant object, and quickly classifies the class as the object approaches and the level of certainty increases.In this manner, our method outperforms previous approaches across different detectors. In particular, the You Only Look Once (YOLO)v8 detector shows a notable enhancement of 4.33 multi-object tracking accuracy (MOTA) in comparison to the previous state-of-the-art method. This intuitive insight improves MOT to track approaching objects from a distance and quickly classify them.

도형 학습을 위한 어드벤처 게임형 학습 프로그램 개발 (Development of Adventure-Game style Program for Figure Learning)

  • 이재무;김민희
    • 한국게임학회 논문지
    • /
    • 제6권3호
    • /
    • pp.33-42
    • /
    • 2006
  • 본 연구는 초등학교 수학과 도형 영역에서의 수준별 학습을 지원하기 위한 어드벤처 게임형 학습 프로그램을 개발하는 것이다. 제7차 교육과정에서는 학생의 능력, 적성, 필요, 흥미 에 대한 개인차를 최대로 고려하는 수업을 통하여 학생 개개인의 성장 잠재력과 교육의 효율성을 극대화할 수 있도록 수준별 교육과정을 도입하였다. 그러나 수준차가 심한 다인수 학급체제에서 학생들의 개인차를 고려한 개별화 학습을 실시하여 교육의 수월성을 추구하기에는 많은 어려움이 있다. 따라서, 본 연구는 van Hiele 이론을 적용한 수준별 게임 학습을 제공하고, 학습자들의 흥미와 관심을 높일 수 있는 어드벤처 게임형 학습 프로그램을 개발하였다. 본 프로그램은 심화 보충학습이 필요한 학습자들에게 개인차를 고려한 수준별 학습을 지원하여 학업 성취도를 높일 수 있을 것이며 공간 지각 능력이 필요한 도형 학습에서 다양한 조작활동을 제공함으로써 학습자들의 공간 감각을 기를 수 있을 것이다.

  • PDF