• Journal of Auto-vehicle Safety Association
• /
• v.11 no.2
• /
• pp.29-34
• /
• 2019

This paper presents a new method for construction of a static obstacle map. A static obstacle is important since it is utilized to path planning and decision. Several established approaches generate static obstacle map by grid method and counting algorithm. However, these approaches are occasionally ineffective since the density of LiDAR layer is low. Our approach solved this problem by applying probability theory. First, we converted all LiDAR point to Gaussian distribution to considers an uncertainty of LiDAR point. This Gaussian distribution represents likelihood of obstacle. Second, we modeled dynamic transition of a static obstacle map by adopting the Hidden Markov Model. Due to the dynamic characteristics of the vehicle in relation to the conditions of the next stage only, a more accurate map of the obstacles can be obtained using the Hidden Markov Model. Experimental data obtained from test driving demonstrates that our approach is suitable for mapping static obstacles. In addition, this result shows that our algorithm has an advantage in estimating not only static obstacles but also dynamic characteristics of moving target such as driving vehicles.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2004.05a
• /
• pp.123-127
• /
• 2004

In this paper, we propose that the chaotic behavior analysis in the several Arnold chaos mobile robot of embedding some chaotic such as Arnold equation with obstacle. In order to analysis of chaotic behavior in the mobile robot, we apply not only qualitative analysis such as time-series, embedding phase plane, but also quantitative analysis such as Lyapunov exponent in the mobile robot with obstacle. We consider that there are two type of obstacle, one is fixed obstacle and the other is hidden obstacle which have an unstable limit cycle. In the hidden obstacles case, we only assume that all obstacles in the chaos trajectory surface in which robot workspace has an unstable limit cycle with Van der Pol equation.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2005.11a
• /
• pp.197-204
• /
• 2005

In this paper, we propose a method to an obstacle avoidance of chaotic robots that have unstable limit cycles in a chaos trajectory surface in the ubiquitous environment. We assume all obstacles in the chaos trajectory surface have a Van der Pol equation with an unstable limit cycle. We also show computer simulation results of Chua's equation, Lorenz equation, Hamilton and Hyper-chaos equation trajectories with one or more Van der Pol as an obstacles. We proposed and verified the results of the method to make the embedding chaotic mobile robot to avoid with the chaotic trajectory in any plane.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2004.05a
• /
• pp.100-105
• /
• 2004

In this paper, we propose a method to avoid obstacles that have unstable limit cycles in a chaos trajectory surface. We assume all obstacles in the chaos trajectory surface have a Van der Pol equation with an unstable limit cycle. When a chaos robot meets an obstacle in a Lorenz equation or Hamilton equation trajectory, the obstacle reflects the robot. We also show computer simulation results for avoidance obstacle which fixed obstacles and hidden obstacles of Lorenz equation and Hamilton equation chaos trajectories with one or more Van der Pol obstacles

• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.2
• /
• pp.259-264
• /
• 2007

In this paper, we composed chaos mobile robot by embedding many type of chaos circuit including Arnold Equation and Chua's Equation and proposed method of evaluation of obstacles when it meets or approaches an obstacle while the mobile robot searches an any plane with chaos trajectory and method of concentrating search when it faces target and verified these results. For obstacles avoidance, we developed algorithm that evades an obstacles with chaos trajectory by assuming fixed obstacle, obstacles using VDP model, hidden obstacles using BVP model as obstacles and for searching an object, we developed algorithm of searching with a chaos trajectory by assuming BVP model as an object, verified the results and confirmed reasonability of them.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.10
• /
• pp.407-420
• /
• 2021

Deep neural networks are widely used to solve various problems. However, the deep neural network with a deep hidden layer frequently has a vanishing gradient or exploding gradient problem, which is a major obstacle to learning the deep neural network. In this paper, we propose a parametric activation function to alleviate the vanishing gradient problem that can be caused by nonlinear activation function. The proposed parametric activation function can be obtained by applying a parameter that can convert the scale and location of the activation function according to the characteristics of the input data, and the loss function can be minimized without limiting the derivative of the activation function through the backpropagation process. Through the XOR problem with 10 hidden layers and the MNIST classification problem with 8 hidden layers, the performance of the original nonlinear and parametric activation functions was compared, and it was confirmed that the proposed parametric activation function has superior performance in alleviating the vanishing gradient.

• The KIPS Transactions:PartB
• /
• v.8B no.6
• /
• pp.705-717
• /
• 2001

In this paper, we propose a rapid lane detection method to extract a preceding vehicle from sequential images captured by a single monocular CCD camera. We detect positions of lanes for an individual image within the limited area that would not be hidden and thereby compute the slopes of the detected lanes. Then we find a search area where vehicles would exist and extract the position of the preceding vehicle within the area with edge component by applying a structured method. To verify the effects of the proposed method, we capture the road images with a notebook PC and a CCD camera for PC and present the results such as processing time for lane detection, accuracy and vehicles detection against the images.

• Journal of Biomedical Engineering Research
• /
• v.42 no.5
• /
• pp.232-240
• /
• 2021

Heterogeneity in cancer is the major obstacle for precision medicine and has become a critical issue in the field of a cancer diagnosis. Many attempts were made to disentangle the complexity by molecular classification. However, multi-dimensional information from dynamic responses of cancer poses fundamental limitations on biomolecular marker-based conventional approaches. Cell morphology, which reflects the physiological state of the cell, can be used to track the temporal behavior of cancer cells conveniently. Here, we first present a hybrid learning-based platform that extracts cell morphology in a time-dependent manner using a deep convolutional neural network to incorporate multivariate data. Feature selection from more than 200 morphological features is conducted, which filters out less significant variables to enhance interpretation. Our platform then performs unsupervised clustering to unveil dynamic behavior patterns hidden from a high-dimensional dataset. As a result, we visualize morphology state-space by two-dimensional embedding as well as representative morphology clusters and trajectories. This cell morphology profiling strategy by hybrid learning enables simplification of the heterogeneous population of cancer.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.1
• /
• pp.257-263
• /
• 2011

Recently as AR(Augmented Reality) is focus of attention, AR is applied to various fields and is expected its valuable use. In this paper, we implemented the system based on Goblin XNA which supports high resolution model file and higher AR. We confirmed the relation of model output among the number of marker, the location and changes of camera distance. And we produced the infantile studying contents using AR and embodied. In implemented contents, we showed the familiar character to infants on each page marker. As the result of it, we can raise their concentration and at a time studying supporters can use the contents easily as well. Also we put 3 marker on each page of contents to recognize it smoothly in case one part of it is hidden by any obstacle. Finally we maximized the learning effect such as presence and immersion in studying through reinforcing 3D models according to the every situation.

• The Korean Journal of Archival Studies
• /
• no.81
• /
• pp.5-44
• /
• 2024

This paper is an experience and observation report on the activities of Jeonju citizens, who are 'kleine leutes'. Text or Born-digital materials such as diaries, group chat rooms, memos, and interviews showing citizens' contemporary and daily history (Alltagsgeschichite) were used for this purpose. These civic groups are reading groups we can find easily and they also enjoy walking, hiking, and movies, and so to speak ordinary local people are their members. One team read Choi Myung-hee's "Honbul" for about a year and a half, while another team read several books under the theme of "commons," and enjoyed exploring, exhibiting, or watching movies together. The main text is composed of three parts. First, I looked at the methods and perspectives to examine the daily life of local people. To this end, the views of Detlev Peukert and Alf Lüdtke, who captured the prospects and the possibilities of theories of daily history, and James C. Scott, who provided insight into infra-politics, were reviewed. This work was to find the perspective and method of daily history research that could observe the activities of Jeonju citizens. Second, we looked at the experience of the "Honbool" meeting. The reading of "Honbool" which took place during the period of confrontation with Covid19 began in connection with its intense locality. As the criticism of "a great writer born in our local land" relieved the uncomfortable feelings, the members' critical mind was revealed after Volume3 of "Honbool" and stood out after Volume6. It seemed to show the characteristics of the self-consciousness (Eigensinn) of citizens who choose dynamics rather than being stuck to a specific form of empathy (Betroffenheit). I think it showed the difficulty and hope to face in the description and research of local history at the same time. Third, I observed citizens who gathered on the subject of public land. This meeting showed the actuality and accumulation process of the infra-political capabilities of citizens in Jeonju. Reading-commons did not suffer from 'heart trouble' as a local citizen compared to "Honbool". Rather, the difficulty of related books was an obstacle, and the difficulty was easily resolved. As the meeting progressed, awareness of the commons became more sophisticated and issues and discussions were independently shared with each other, and a wealth of hidden transcripts were accumulated through its practice and problem consciousness. It is difficult to think about modern daily life apart from the capitalist era. More fundamentally, it is here and now in everyday life that humans enjoy or suffer from. All history passes through my body here and now. This is the universality of daily history. It depends on the ability of citizens to create daily history to experience and at the same time maintain the distance of criticism.