• 한국안전학회지
• /
• 제24권1호
• /
• pp.69-77
• /
• 2009

This paper reports the aging driver traffic accident severity modeling results. For the modeling, Poisson regression approach is applied using the data set obtained from the Korea Transportation Safety Authority's simulator-based driver aptitude test results. The test items include the estimations of moving objects' speed and stopping distance, drivers' multi-task capability, and kinetic depth perception and so on. The resulting model with the response variable of equivalent property damage only(EPDO) indicated that EPDO is significantly influenced by moving objects' speed estimation and drivers' multi-task capabilities. More interestingly, a comparison with the younger driver model revealed that the degradation of such capabilities may result in severer crashes for older drivers as suggested by the higher estimated parameters for the older driver model.

• 한국정밀공학회지
• /
• 제10권3호
• /
• pp.175-181
• /
• 1993

In this paper, a practical method to generate task strategies applicable to chamferless and high-precision assembly, is proposed. The difficulties in devising reliable assembly strategies result from various forms of uncertainty such as imperfect knowledge on the parts being assembled and functional limitations of the assembly devices. In approach to cope with these problems, the robot is provided with the capability of learning the corrective motion in response to the force signal trrough iterative task execution. The strategy is realized by adopting a learning algorithm and represented in a binary tree type database. To verify the effectiveness of the proposed algorithm, a series of simulations and experiments are carried out under assimilated real production environments. The results show that the sensory signal-to-robot action mapping can be acquired effectively and, consequently, the chamferless assembly can be performed successfully.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.1162-1167
• /
• 2003

This paper presents a simple sensor network consists of a group of sensors, RF components, and microprocessors, to perform a distributed sensing and information transmission using wireless links. In the proposed sensor network, though each sensor node has a limited capability and a simple signal-processing engine, a group of sensor nodes can perform a various tasks through coordinated information sharing and wireless communication in a large working area. Using the capability of self-localization and tracking, we show the sensor network can be applied to localization and navigation of mobile robot in which the robot has to be coordinated effectively to perform given task in real time.

• 시스템엔지니어링학술지
• /
• 제15권2호
• /
• pp.9-16
• /
• 2019

The most important task in acquiring the weapon system is to determine the required performance and to test & evaluate it. The importance of the weapon system by ROC (Required Operational Capability) is not considered, and system development and test evaluation are carried out. In addition, technical incidental performance is tested on the same basis as ROC in the test evaluation and determined according to the result. Development test and evaluation that evaluates technical ability is very important, but development agency is supervised and performed. In this paper, we propose a method to give weights considering the importance of ROC, a technical incidental performance determination and test procedure, and a improvement plan for the development and operational test & evaluation.

• 한국컴퓨터정보학회논문지
• /
• 제23권9호
• /
• pp.7-13
• /
• 2018

Recent advancement in data gathering technique improves the capability of information collecting, thus allowing the learning process between gathered data patterns and application sub-tasks. A pattern can be associated with multiple labels, demanding multi-label learning capability, resulting in significant attention to multi-label feature selection since it can improve multi-label learning accuracy. However, existing evolutionary multi-label feature selection methods suffer from ineffective search process. In this study, we propose a evolutionary search process for the task of multi-label feature selection problem. The proposed method creates large set of offspring or new feature subsets and then retains the most promising feature subset. Experimental results demonstrate that the proposed method can identify feature subsets giving good multi-label classification accuracy much faster than conventional methods.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2007년도 춘계학술대회A
• /
• pp.939-944
• /
• 2007

Generally, development of a robot capable of fast movements or high payloads is progressed by the analysis of dynamic characteristics, DOF positioning, actuator selection, structure of links, and so on. This paper highlights the design of a robot manipulator handled by a human for man-machine cooperation. The requirements of the proposed system include its having multi-DOF(Degree of Freedom)and the capacity for a high payload in the condition of its maximum reach. The primary investigation factors are motion range, performance within the motion area, and reliabilityduring the handling of heavy materials. Traditionally, the mechanical design of robots has been viewed as a problem of packaging motors and electronics into a reasonable structure. This process usually transpires with heavy reliance of designerexperience. Not surprisingly, the traditional design process contains no formally defined rules for achieving desirable results, as there is little opportunity for quantitative feedback during the formative stages. This work primarily focuses on the selection of proper joint types and link lengths, considering a specific task type and motion requirements of the heavy material handling.

• 대한전기학회논문지:전력기술부문A
• /
• 제55권9호
• /
• pp.351-358
• /
• 2006

In this paper, DSPOCS(Digital Switchgear-Panel Operation and Control Solution) is designed, which is the intelligent inference based operation and control solution to obtain the safety and reliability of electric power supply in substation based on IED. DSPOCS is designed as a scheduled monitoring and control task and a real-time alarm inference task, and is interlinked with BRES(Bus Reconfiguration Expert System) in the required case. The intelligent alarm inference task consists of the alarm knowledge generation part and the real-time pattern matching part. The alarm knowledge generation part generates automatically alarm knowledge from DB saves it in alarm knowledge base. On the other hand, the pattern matching part inferences the real-time event by comparing the real-time event information furnished from IEDs of substation with the patterns of the saved alarm knowledge base.; Especially, alarm knowledge base includes the knowledge patterns related with fault alarm, the overload alarm and the diagnosis alarm. In order to design the database independently in substation structure, busbar is represented as a connectivity node which makes the more generalized graph theory possible. Finally, DSPOCS is implemented in MS Visual $C^{++}$, MFC, the effectiveness and accuracy of the design is verified by simulation study to the typical distribution substation.

• The Journal of Korean Physical Therapy
• /
• 제27권2호
• /
• pp.112-117
• /
• 2015

Purpose: The purpose of this study was to examine the effects of a task-specific obstacle crossing rehabilitation program on functional gait ability in patients with cerebellar ataxia. Overall, we sought to provide ataxia-specific locomotor rehabilitation guidelines for use in clinical practice based on quantitative evidence using relevant analysis of gait kinematics including valid clinical tests. Methods: Patients with cerebellar disease (n=13) participated in obstacle crossing training focusing on maintenance of dynamic balance and posture, stable transferring of body weight, and production of coordinated limb movements for 8 weeks, 2 times per week, 90 minutes per session. Throughout the training of body weight transfer, the instructions emphasized conscious perception and control of the center of body stability, trunk and limb alignment, and stepping kinematics during the practice of each walking phase. Results: According to the results, compared with pre-training data, foot clearance, pre-&post-obstacle distance, delay time, and total obstacle crossing time were increased after intervention. In addition, body COM measures indicated that body sway and movement variability, therefore posture stability during obstacle crossing, showed improvement after training. Based on these results, body sway was reduced and stepping pattern became more consistent during obstacle crossing gait after participation in patients with cerebellar ataxia. Conclusion: Findings of this study suggest that task-relevant obstacle crossing training may have a beneficial effect on recovery of functional gait ability in patients with cerebellar disease.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권10호
• /
• pp.4080-4097
• /
• 2020

In recent years, convolutional neural network (CNN) has become the primary method for face detection. But its shortcomings are obvious, such as expensive calculation, heavy model, etc. This makes CNN difficult to use on the mobile devices which have limited computing and storage capabilities. Therefore, the design of lightweight CNN for face detection is becoming more and more important with the popularity of smartphones and mobile Internet. Based on the CPU real-time face detector FaceBoxes, we propose a multi-task lightweight face detector, which has low computing cost and higher detection precision. First, to improve the detection capability, the squeeze and excitation modules are used to extract attention between channels. Then, the textual and semantic information are extracted by shallow networks and deep networks respectively to get rich features. Finally, the landmark detection module is used to improve the detection performance for small faces and provide landmark data for face alignment. Experiments on AFW, FDDB, PASCAL, and WIDER FACE datasets show that our algorithm has achieved significant improvement in the mean average precision. Especially, on the WIDER FACE hard validation set, our algorithm outperforms the mean average precision of FaceBoxes by 7.2%. For VGA-resolution images, the running speed of our algorithm can reach 23FPS on a CPU device.

• Journal of Electrical Engineering and Technology
• /
• 제3권3호
• /
• pp.293-299
• /
• 2008

One of the problems with the fault diagnosis of transformers based on dissolved gas is the inability to match the result of the different standards of fault diagnosis with real world standards. In this paper, the results of the different standards are analyzed using fuzzy logic and then compared with the empirical test. The proposed method is based on the standards and guidelines of the International Electrotechnical Commission (IEC), the Central Electric Generating Board (CEGB), and the American Society for Testing and Material (ASTM) and its main task is to assist the conventional gas ratio method. The comparison between the suggested method and existing methods indicates the capability of the suggested method in the on-line fault diagnosis of transformers. In addition, in some cases the existing standards are not able to diagnose the fault. For theses instances, the presented method has the potential of diagnosing the fault. In this paper, the information of three real transformers is used to show the capability of the suggested method in diagnosing the fault. The results validate the capability of the presented method in fault diagnosis of the transformer.