• 한국ITS학회 논문지
• /
• 제21권3호
• /
• pp.83-95
• /
• 2022

본 논문은 자율주행 차량 적용을 위한 객체 검출과 거리 추정을 수행하는 시스템을 제안한다. 객체 검출은 최근 활발하게 사용되는 딥러닝 모델 YOLOv4의 특성을 이용해서 입력 이미지 비율에 맞춰 분할 grid를 조정하고 자체 데이터셋으로 전이학습된 네트워크로 수행한다. 검출된 객체까지의 거리는 bounding box와 homography를 이용해 추정한다. 실험 결과 제안하는 방법에서 전반적인 검출 성능 향상과 실시간에 가까운 처리 속도를 보였다. 기존 YOLOv4 대비 전체 mAP는 4.03% 증가했다. 도심로 주행시 빈출하는 보행자, 차량 및 공사장 고깔(cone), PE드럼(drum) 등의 객체 인식 정확도가 향상되었다. 처리 속도는 약 55 FPS이다. 거리 추정 오차는 X 좌표 평균 약 5.25m, Y 좌표 평균 0.97m으로 나타났다.

• 전자공학회논문지 IE
• /
• 제43권4호
• /
• pp.128-135
• /
• 2006

본 논문에서는 이동로봇 주변의 자기위치인식, 광학식 엔코더의 위치 데이터 및 초음파 센서의 환경 지도를 이용하여 퍼지 기반 센서융합 제어방식을 제시하였다. 영상 카메라를 이용하여 자기위치 인식성능을 높이고 초음파 센서에서 감지한 목표물의 형태, 거리와 특징을 퍼지 기반 제어기를 통하여 처리하여 이동로봇 주변의 환경지도를 만들어 자기위치 인식능력의 개선을 실험을 통하여 구현하였다.

• 한국정밀공학회지
• /
• 제31권4호
• /
• pp.287-295
• /
• 2014

Smart manufacturing (SM) considered as a new trend of modern manufacturing helps to meet objectives associated with the productivity, quality, cost and competiveness. It is characterized by decentralized, distributed, networked compositions of autonomous systems. The model of SM is inherited from the organization of the living systems in biology and nature such as ant colony, school of fish, bee's foraging behaviors, and so on. In which, the resources of the manufacturing system are considered as biological organisms, which are autonomous entities so that the manufacturing system has the advanced characteristics inspired from biology such as self-adaptation, self-diagnosis, and self-healing. To prove this concept, a cloud machining system is considered as research object in which internet of things and cloud computing are used to integrate, organize and allocate the machining resources. Artificial life tools are used for cooperation among autonomous elements in the cloud machining system.

• Journal of information and communication convergence engineering
• /
• 제12권2호
• /
• pp.128-134
• /
• 2014

In this paper, we present a graphics processing unit (GPU)-based matching technique for the purpose of fast feature matching between different images. The scale invariant feature transform algorithm developed by Lowe for various feature matching applications, such as stereo vision and object recognition, is computationally intensive. To address this problem, we propose a matching technique optimized for GPUs to perform computations in less time. We optimize GPUs for fast computation of keypoints to make our system quick and efficient. The proposed method uses a self-organizing map feature matching technique to perform efficient matching between the different images. The experiments are performed on various image sets to examine the performance of the system under varying conditions, such as image rotation, scaling, and blurring. The experimental results show that the proposed algorithm outperforms the existing feature matching methods, resulting in fast feature matching due to the optimization of the GPU.

• 제어로봇시스템학회논문지
• /
• 제5권2호
• /
• pp.189-199
• /
• 1999

This paper presents an optimization algorithm for a stable Self Dynamic Neural Network(SDNN) using genetic algorithm. Optimized SDNN is applied to a problem of controlling nonlinear dynamical systems. SDNN is dynamic mapping and is better suited for dynamical systems than static forward neural network. The real-time implementation is very important, and thus the neuro controller also needs to be designed such that it converges with a relatively small number of training cycles. SDW has considerably fewer weights than DNN. Since there is no interlink among the hidden layer. The object of proposed algorithm is that the number of self dynamic neuron node and the gradient of activation functions are simultaneously optimized by genetic algorithms. To guarantee convergence, an analytic method based on the Lyapunov function is used to find a stable learning for the SDNN. The ability and effectiveness of identifying and controlling a nonlinear dynamic system using the proposed optimized SDNN considering stability is demonstrated by case studies.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1995년도 하계학술대회 논문집 B
• /
• pp.983-985
• /
• 1995

In this paper, we propose a Self Organizing Feature Map (SOFM) Type Neural Computation Algorithm for the Travelling Salesman Problem(TSP). The actual best solution to the TSP problem is computatinally very hard. The reason is that it has many local minim points. Until now, in neural computation field, Hopield-Tank type algorithm is widely used for the TSP. SOFM and Elastic Net algorithm are other attempts for the TSP. In order to apply SOFM type neural computation algorithms to the TSP, the object function forms a euclidean norm between two vectors. We propose a Largrangian for the above request, and induce a learning equation. Experimental results represent that feasible solutions would be taken with the proposed algorithm.

• Human Ecology Research
• /
• 제56권1호
• /
• pp.99-108
• /
• 2018

This study develops a scale to measure the practice of consideration and sharing by adolescents. This data as an object of high school students in regards to items generated from the content validity test and preliminary study stage based on the consideration scale, literature review and expert for elementary school students on a 5-point Likert scale. The factor analysis of the collected data using SPSS 20.0 2 indicated the final fators. The three fanal factors designated by the measuring items are: 'practice of consideration and sharing', 'recognition of consideration and sharing', and 'self-recognition'. As a result of analyzing students' individual variables, this study found that family relationship satisfaction and school life satisfaction had positive relationship in self-recognition, recognition of consideration and sharing, practice of consideration and sharing, and total personality score. The measurement tools developed in this study, are expected to act as valid tools to develop a program that can increase the practice of consideration and sharing activities.

• ETRI Journal
• /
• 제44권3호
• /
• pp.438-449
• /
• 2022

This study proposes a dependency grammar-based self-attention multilayered bidirectional long short-term memory (DG-M-Bi-LSTM) model for subject-predicate-object (SPO) tuple recognition from natural language (NL) sentences. To add recent knowledge to the knowledge base autonomously, it is essential to extract knowledge from numerous NL data. Therefore, this study proposes a high-accuracy SPO tuple recognition model that requires a small amount of learning data to extract knowledge from NL sentences. The accuracy of SPO tuple recognition using DG-M-Bi-LSTM is compared with that using NL-based self-attention multilayered bidirectional LSTM, DG-based bidirectional encoder representations from transformers (BERT), and NL-based BERT to evaluate its effectiveness. The DG-M-Bi-LSTM model achieves the best results in terms of recognition accuracy for extracting SPO tuples from NL sentences even if it has fewer deep neural network (DNN) parameters than BERT. In particular, its accuracy is better than that of BERT when the learning data are limited. Additionally, its pretrained DNN parameters can be applied to other domains because it learns the structural relations in NL sentences.

• 정신신체의학
• /
• 제3권2호
• /
• pp.207-213
• /
• 1995

비만환자들의 정신역동과 정신분석치료의 기법을 문헌 고찰하였다. 비만의 원인은 구강기 고착과 충동조절을 못하는, 자아와 초자아의 결함에 있었다. 비만환자들은 사랑의 상실에 의한 고통을 해결하는 방법으로 음식을 사용한다. 먹음으로 자신을 달래주고(self-soothing), 대리만족을 취한다. 부모의 양육태도가 문제인데, 비만아의 부모는 아이를 통하여 자신의 욕망을 이루려는 분들이어서 지배적이고 음식을 강요하며 어린이의 성취에 대한 기재가 높다. 어린이에게 따뜻한 보살핌이 필요할 때에도 부모의 목표가 더 우선되기 때문에 어린이는 늘 욕구불만에 빠지게 된다. 가정에서 어린이에게 사랑이 필요할 때마다 사랑 대신에 음식을 먹이는 부모였다. 그래서 성장후에 사회적 좌절을 당하면 음식에서 위로를 받고, 음식을 씹음으로 공격욕구도 발산한다(Stunkard, 1985). 또한 비만환자의 부모는 정상적인 부모역할을 전반적으로 소홀히 하는 편이었다. 절제를 가르치지 못하는 부모였다. 그것은 부모 자신의 초자아에 문제가 있어서 요구할 것을 요구하지 못하기 때문이기도 했고, 특별히 어떤 자식을 유난히 무관심 속에 방치해 두어서 비만을 만들기도 한다(Wilson, 1992). 이처럼 비만환자들은 전에디푸스기에 병의 원인(preoedipal pathology)을 가지고 있기 때문에 이런 갈등을 가지고 있는 환자들을 치료할 때는 언제나 그렇듯이 분석가는 좀더 적극적인 해석을 해주어야 한다. 또한 전이대상만으로는 안되고, 이에 추가하여 아이를 잘 키우는 새로운 대상(new and different object)이 되어 줘야한다(Wilson 1989). 비만환자들의 거구를 대하면서 치료자들은 위축되는 역전이에 빠질 수가 있다는 것도 염두에 두어야 한다.

• 한국실내디자인학회논문집
• /
• 제17권3호
• /
• pp.86-93
• /
• 2008

The purpose of this study is to find out how the otherness philosophy reveals itself in the principle of F.O.A construction space creation. The traditional philosophy of totality is self-centered and thoughts are based on the subject. It couldn't escape from the world associated with the self, and has subordinated the other to the main body. But the philosophy of otherness transcends the subject, to the open, creative way of thinking which acknowledges deconstruction, decentralization, and non-hierarchy. This is very similar to contemporary architecture, which pursuits change, and also to the current state of society. In construction by the construction group F.O.A, which is doing notable activity this generation, there is an attempt to transcend the fixed subject which is seen in the otherness discussion, and realize recategorization by overcoming the boundaries of subject and object. First, by the realization of landscape architecture using a topographical folding technique, boundaries of the subject and object are demolished in the relationship of the landscape construction, and recategorization. Second, by breaking up the meaning of the surface which is a visual and physical boundary for both the internal and external, recategorization is being done. Third, by making the boundary between the interior and exterior indistinct, cognitive threshold is dissolved, and the relationship between the subject and object is being recategorization. In conclusion, we can see that the many recategorization phenomenons that are happening in the F.O.A construction show the otherness that escapes from the conventional and stationary relationship, and recognizes each other at the same time, forming new relationships.