• 로봇학회논문지
• /
• 제17권4호
• /
• pp.417-424
• /
• 2022

In this paper, the developed trunk cargo unloading automation system is introduced, and the RGB-D sensor-based box loading situation recognition method and unloading plan applied to this system are suggested. First of all, it is necessary to recognize the position of the box in a truck. To do this, we first apply CNN-based YOLO, which can recognize objects in RGB images in real-time. Then, the normal vector of the center of the box is obtained using the depth image to reduce misrecognition in parts other than the box, and the inner wall of the truck in an image is removed. And a method of classifying the layers of the boxes according to the distance using the recognized depth information of the boxes is suggested. Given the coordinates of the boxes on the nearest layer, a method of generating the optimal path to take out the boxes the fastest using this information is introduced. In addition, kinematic analysis is performed to move the conveyor to the position of the box to be taken out of the truck, and kinematic analysis is also performed to control the robot arm that takes out the boxes. Finally, the effectiveness of the developed system and algorithm through a test bed is proved.

• ETRI Journal
• /
• 제44권2호
• /
• pp.286-299
• /
• 2022

Human activity recognition in real time is a challenging task. Recently, a plethora of studies has been proposed using deep learning architectures. The implementation of these architectures requires the high computing power of the machine and a massive database. However, handcrafted features-based machine learning models need less computing power and very accurate where features are effectively extracted. In this study, we propose a handcrafted model based on three-dimensional sequential skeleton data. The human body skeleton movement over a frame is computed through joint positions in a frame. The joints of these skeletal frames are projected into two-dimensional space, forming a "movement polygon." These polygons are further transformed into a one-dimensional space by computing amplitudes at different angles from the centroid of polygons. The feature vector is formed by the sampling of these amplitudes at different angles. The performance of the algorithm is evaluated using a support vector machine on four public datasets: MSR Action3D, Berkeley MHAD, TST Fall Detection, and NTU-RGB+D, and the highest accuracies achieved on these datasets are 94.13%, 93.34%, 95.7%, and 86.8%, respectively. These accuracies are compared with similar state-of-the-art and show superior performance.

• 국제학술발표논문집
• /
• The 1th International Conference on Construction Engineering and Project Management
• /
• pp.569-574
• /
• 2005

This paper presents the core technology of Construction Business Process Automation to model and automate construction business processes. Business Process Reengineering (BPR) and Automation (BPA) have been recognized as one of the important aspects in construction business management. However, BPR requires a lot of efforts to identify, document, implement, execute, maintain, and keep track thousands of business processes to deliver a project. Moreover, existing BPA technologies used in existing Enterprise Resource Planning (ERP) systems do not lend themselves to effective scalability for construction business process management. Application of Workflow and Object Technologies would be quite effective in implementing a scalable enterprise application for construction community. This paper present the technologies and methodologies for automating construction business processes by addressing how: 1) Automated construction management tasks are developed as software components, 2) The process modeling is facilitated by dragging-and dropping task components in a network, 3) Raising business requests and instantiating corresponding process instances are delivered, and 4) Business process instances are executed by using workflow technology based on real-time simulation engine. This paper presents how the construction business process automation is achieved by using equipment reservation and cancellation processes simplified intentionally.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권9호
• /
• pp.2334-2347
• /
• 2023

Metaverse services generate text data, data of ubiquitous computing, in real-time to analyze user emotions. Analysis of user emotions is an important task in metaverse services. This study aims to classify user sentiments using deep learning and pre-trained language models based on the transformer structure. Previous studies collected data from a single platform, whereas the current study incorporated the review data as "Metaverse" keyword from the YouTube and Google Play Store platforms for general utilization. As a result, the Bidirectional Encoder Representations from Transformers (BERT) and Robustly optimized BERT approach (RoBERTa) models using the soft voting mechanism achieved a highest accuracy of 88.57%. In addition, the area under the curve (AUC) score of the ensemble model comprising RoBERTa, BERT, and A Lite BERT (ALBERT) was 0.9458. The results demonstrate that the ensemble combined with the RoBERTa model exhibits good performance. Therefore, the RoBERTa model can be applied on platforms that provide metaverse services. The findings contribute to the advancement of natural language processing techniques in metaverse services, which are increasingly important in digital platforms and virtual environments. Overall, this study provides empirical evidence that sentiment analysis using deep learning and pre-trained language models is a promising approach to improving user experiences in metaverse services.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권4호
• /
• pp.1603-1623
• /
• 2020

Multiple Mobile Robots System (MMRS) has shown many attractive features in lots of real-world applications that motivate their rapid and wide diffusion. In MMRS, the Cooperative Localization (CL) is the basis and premise of its high-performance task. However, the statistical characteristics of the system noise should be already known in traditional CL algorithms, which is difficult to satisfy in actual MMRS because of the numerous of disturbances form the complex external environment. So the CL accuracy will be reduced. To solve this problem, an improved Adaptive Active Cooperative Localization (A²CL) algorithm based on information optimization strategy for MMRS is proposed in this manuscript. In this manuscript, an adaptive information fusion algorithm based on the variance component estimation under Extended Kalman filter (VCEKF) method for MMRS is introduced firstly to enhance the robustness and accuracy of information fusion by estimating the covariance matrix of the system noise or observation noise in real time. Besides, to decrease the effect of observation uncertainty on CL accuracy further, an observation optimization strategy based on information theory, the Model Predictive Control (MPC) strategy, is used here to maximize the information amount from observations. And semi-physical simulation experiments were carried out to verity the A²CL algorithm's performance finally. Results proved that the presented A²CL algorithm based on information optimization strategy for MMRS cannot only enhance the CL accuracy effectively but also have good robustness.

• 대한산업공학회지
• /
• 제41권1호
• /
• pp.34-42
• /
• 2015

Modeling and control of human-involved manufacturing systems poses a huge challenge on how to model all possible interactions among system components within the time and space dimensions. As the manufacturing environment are getting complicated, the importance of human in the manufacturing system is getting more and more spotlighted to incorporate the manufacturing flexibility. This paper presents a formal modeling methodology of affordance-based MPSG (Message-based Part State Graph) for a human-machine collaboration system incorporating supervisory control scheme for flexible manufacturing systems in automotive industry. Basically, we intend to extend the existing model of affordance-based MPSG to the real industrial application of humanmachine cooperative environments. The suggested extension with the real industrial example is illustrated in three steps; first, the manufacturing process and relevant data are analyzed in perspectives of MABA-MABA and the supervisory control; second, the manufacturing processes and task allocation between human and machine are mapped onto the concept of MABA-MABA; and the last, the affordance-based MPSG of humanmachine collaboration for the manufacturing process is presented with UMLs for verification.

• 인터넷정보학회논문지
• /
• 제21권5호
• /
• pp.49-56
• /
• 2020

Detecting shadows in images and restoring or removing them was a very challenging task in computer vision. Traditional researches used color information, edges, and thresholds to detect shadows, but there were errors such as not considering the penumbra area of shadow or even detecting a black area that is not a shadow. Deep learning has been successful in various fields of computer vision, and research on applying deep learning has started in the field of shadow detection and removal. However, it was very difficult and time-consuming to collect data for network learning, and there were many limited conditions for shooting. In particular, it was more difficult to obtain shadow data from buildings and satellite images, which hindered the progress of the research. In this paper, we propose a method for generating shadow data from buildings and satellites using Unity3D. In the virtual Unity space, 3D objects existing in the real world were placed, and shadows were generated using lights effects to shoot. Through this, it is possible to get all three types of images (shadow-free, shadow image, shadow mask) necessary for shadow detection and removal when training deep learning networks. The method proposed in this paper contributes to helping the progress of the research by providing big data in the field of building or satellite shadow detection and removal research, which is difficult for learning deep learning networks due to the absence of data. And this can be a suboptimal method. We believe that we have contributed in that we can apply virtual data to test deep learning networks before applying real data.

• 한국컴퓨터정보학회논문지
• /
• 제17권4호
• /
• pp.11-18
• /
• 2012

침입 탐지에 가장 시간이 많이 소요되는 작업은 패킷 데이터에 침입 패턴이 있는지를 검사하는 심층 패킷검사이다. 고속 네트워크에서 이 작업을 실시간으로 처리하기 위해서는 하드웨어 기반 패턴매칭이 필요하다. 본 논문에서는 침입탐지 시스템 구현에 하드웨어 기반 패턴매칭을 사용할 수 있도록 네트워크의 패킷을 수집하여 Snort 패턴규칙에 따라서 패턴매칭을 수행하고 결과를 소프트웨어에게 제공할 수 있도록 하는 하드웨어를 Virtex-6 FPGA를 사용하여 Microblaze 기반의 SoC 형태로 설계하여 구현하였다. 구현된 시스템은 인위적인 트래픽 생성과 실제 트래픽을 사용하여 동작을 검증하였고 패킷이 네트워크 인터페이스에서 메모리로 복사되는 동안 패턴매칭 동작을 정확하게 수행하여 소프트웨어에게 결과를 제공하였다. 본 연구 결과는 실시간 처리가 가능하도록 침입탐지 시스템을 고속화 하기위한 하드웨어로 사용될 수 있다.

• KIEE International Transactions on Power Engineering
• /
• 제4A권4호
• /
• pp.171-177
• /
• 2004

In the current age of the information oriented society in which we live, many people use PCs and are dependant on the databases provided by the network server. However, online data can be missed during the occurrence of a blackout and furthermore, power failure can greatly effect Power Quality. This has resulted in the trend of using interruption-free live-line work when trouble occurs in a power system. However, 83% of the population receives an electric shock experience when a laborer is performing interruption-free live-line work. In the interruption-free method, education and training problems have been pinpointed. However, there are few instructors to implement the necessary training. Furthermore, the trainees undergo only a short training period of just 4 weeks. In this paper, to develop a method with no restrictions on time and place and to ensure a reduction in the misuse of materials, immersion type virtual reality (or environment) technology is used. The users of a 3D immersion type VR training system can interact with the system by performing the equivalent action in a safe environment. Thus, it can be valuable to apply this training system to such dangerous work as 'Interruption-free live-line work exchanging COS (Cut-Out-Switch)'. In this program, the user carries out work according to instructions displayed through the window and speaker and cannot perform other tasks until each part of the task is completed in the proper sequence. The workers using this system can utilize their hands and viewpoint movement since they are in a real environment but the trainee cannot use all parts and senses of a real body with the current VR technology. Despite these weak points, when we consider the trends of improvement in electrical devices and communication technology, we can say that 3D graphic VR application has high potentiality.

• 한국지리정보학회지
• /
• 제7권1호
• /
• pp.1-8
• /
• 2004

우리가 살아가고 있는 현실공간에서 사라진 과거의 지형공간을 복원한다는 것은 매우 의미가 있는 실험연구이다. 본 연구는 20여 년 전에 다목적 대형 댐의 건설로 대부분 물속으로 사라진 청풍호수 주변의 마을을 대상으로 원격탐사기법으로 3차원 지형을 복원하기 위한 연구이다. 수몰 이전의 비교적 해상도가 높은 인공위성 사진과 영상 및 지도를 이용하여 과거의 새로운 영상을 복원하는 실험을 실시하였다. 이로써 영상과 영상의 좌표변환, 영상과 지도와의 정밀기하보정, 과거지도와 참조지도 및 좌표변환을 통하여 DEM과의 중첩오차를 최소화시키고, 영상 복원 시에 손실정보를 최소화하는 최적채널 선정을 통하여 수몰이전을 가장 잘 보여주는 퓨젼영상을 복원할 수 있었다.