• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 1999.10a
• /
• pp.315-320
• /
• 1999

Obstacle Detection System(ODS) is a essential system for automated vehicle, such as AGV(Automatic Guided Vehicle), mobile robot. Automated vehicle must have a capability to detect and to avoid obstacles to guarantee a safe driving condition. To implement obstacle detection system, virtual bumper concept adapted. Like real bumper in a car, such as in the truck, it protects vehicle from collision using laser distance sensor. When an obstacle(such as other vehicle, building, etc) intrudes this virtual bumper area, a virtual force is calculated and produces necessary strategy to be able to avoid collision. In this paper, simplified virtual bumper concept is presented, and various problems when happens to implement are discussed.

• Smart Structures and Systems
• /
• v.23 no.1
• /
• pp.45-60
• /
• 2019

This paper is devoted to proposing a new approach for damage detection of structures. In this technique, the biconjugate gradient method (BCG) is employed. To remedy the noise effects, a new preconditioning algorithm is applied. The proposed preconditioner matrix significantly reduces the condition number of the system. Moreover, based on the characteristics of the damage vector, a new direct search algorithm is employed to increase the efficiency of the suggested damage detection scheme by reducing the number of unknowns. To corroborate the high efficiency and capability of the presented strategy, it is applied for estimating the severity and location of damage in the well-known 31-member and 52-member trusses. For damage detection of these trusses, the time history responses are measured by a limited number of sensors. The results of numerical examples reveal high accuracy and robustness of the proposed method.

• Smart Structures and Systems
• /
• v.23 no.1
• /
• pp.15-29
• /
• 2019

This paper addresses the problem of damage detection in suspension bridge hangers, with an emphasis on the modal flexibility method. It aims at evaluating the capability and the accuracy of the modal flexibility method to detect and locate single and multiple damages in suspension bridge hangers, with different level of severity and various locations. The study is conducted numerically and experimentally on a laboratory suspension bridge mock-up. First, the covariance-driven stochastic subspace identification is used to extract the modal parameters of the bridge from experimental data, using only output measurements data from ambient vibration. Then, the method is demonstrated for several damage scenarios and compared against other classical methods, such as: Coordinate Modal Assurance Criterion (COMAC), Enhanced Coordinate Modal Assurance Criterion (ECOMAC), Mode Shape Curvature (MSC) and Modal Strain Energy (MSE). The paper demonstrates the relative merits and shortcomings of these methods which play a significant role in the damage detection ofsuspension bridges.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.124-125
• /
• 2023

Defect detection during liquid crystal display (LCD) manufacturing has always been a critical challenge. This study aims to address this issue by proposing a data augmentation method based on generative adversarial networks (GAN) to improve defect identification accuracy in LCD production. By leveraging synthetically generated image data from GAN, we effectively augment the original dataset to make it more representative and diverse. This data augmentation strategy enhances the model's generalization capability and robustness on real-world data. Compared to traditional data augmentation techniques, the synthetic data from GAN are more realistic, diverse and broadly distributed. Experimental results demonstrate that training models with GAN-generated data combined with the original dataset significantly improves the detection accuracy of critical defects in LCD manufacturing, compared to using the original dataset alone. This study provides an effective data augmentation approach for intelligent quality control in LCD production.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.46 no.6
• /
• pp.18-26
• /
• 2009

In this paper, we proposed multipurpose signal detection methods for ECG (electrocardiogram) based u-healthcare systems. For ECG based u-healthcare system, QRS signal extraction for cardiovascular disease diagnosis is essential. Also, for security and convenience reasons, it is desirable if u-healthcare system support biometric identification directly from user's bio-signal such as ECG for this case. For this, from Lead II signal, we developed QRS signal detection method and also, we developed signal extraction method for biometric identification using Lead II signal which is relatively robust from signal alteration by aging and diseases. For QRS signal detection capability from Lead II signal, ECG signals from MIT-BIH database are used and it showed 99.36% of accuracy and 99.68% of sensitivity. Also, to show the performance of signal extraction capability for biometric diagnosis purpose, Lead III signals are measured after drinking, smoking, or exercise to consider various monitoring conditions and it showed 99.92% of accuracy and 99.97% of sensitivity.

• The KIPS Transactions:PartC
• /
• v.11C no.1
• /
• pp.109-114
• /
• 2004

A new code and its decoding scheme are proposed. With this code, we can correct and detect the errors in communication systems. To limit the runlength of data 0 and augment the minimum density of data 1, a (15, 7) BCH code is modified and an overall parity bit is added. The proposed code is a (16, 7) block code which has the bit clock signal regeneration capability and high error control capability. It is proved that the runlength of data 0 is less than or equal to 7, the density of data 1 is greater than or equal to 1/8, and the minimum Hamming distance is 6. The decoding error probability, the error detection probability and the correct decoding probability are presented for the proposed code. It is shown that the proposed code has better error control capability than the conventional schemes.

• Structural Engineering and Mechanics
• /
• v.49 no.2
• /
• pp.183-202
• /
• 2014

A new method of multiple damage detection in beam like structures is introduced. The mode shapes of both healthy and damaged structures are used in damage detection process (DDP). Multiple Damage Localization Index Based on Mode Shapes (MDLIBMS) is presented as a criterion in detecting damaged elements. A finite element modeling of structures is used to calculate the mode shapes parameters. The main advantages of the proposed method are its simplicity, flexibility on the number of elements and so the accuracy of the damage(s) position(s), sensitivity to small damage extend, capability in prediction of required number of mode shapes and low sensitivity to noisy data. In fact, because of differential and comparative form of MDLIBMS, using noise polluted data doesn't have major effect on the results. This makes the proposed method a powerful one in damage detection according to measured mode shape data. Because of its flexibility, damage detection process in multi span bridge girders with non-prismatic sections can be done by this method. Numerical simulations used to demonstrate these advantages.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.10
• /
• 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.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.15 no.6
• /
• pp.417-424
• /
• 2010

This paper proposes a new islanding detection method for a grid-connected photovoltaic system. It is based on the fact that the equivalent harmonic components vary according to the grid connection status. The advantage of the proposed method is the reduced Non-Detection Zone and fast detection time. Also it can have the robust detection capability against grid disturbances. The theoretic analysis using grid-harmonic modeling is performed and verified by test result using 32-bit high performance DSP processor.

• Journal of Information Processing Systems
• /
• v.6 no.4
• /
• pp.481-500
• /
• 2010

The Internet explosion and the increase in crucial web applications such as ebanking and e-commerce, make essential the need for network security tools. One of such tools is an Intrusion detection system which can be classified based on detection approachs as being signature-based or anomaly-based. Even though intrusion detection systems are well defined, their cooperation with each other to detect attacks needs to be addressed. Consequently, a new architecture that allows them to cooperate in detecting attacks is proposed. The architecture uses Software Agents to provide scalability and distributability. It works in two modes: learning and detection. During learning mode, it generates a profile for each individual system using a fuzzy data mining algorithm. During detection mode, each system uses the FuzzyJess to match network traffic against its profile. The architecture was tested against a standard data set produced by MIT's Lincoln Laboratory and the primary results show its efficiency and capability to detect attacks. Finally, two new methods, the memory-window and memoryless-window, were developed for extracting useful parameters from raw packets. The parameters are used as detection metrics.