• Journal of the Korean Society for Precision Engineering
• /
• v.32 no.11
• /
• pp.989-995
• /
• 2015

In the literature, various stochastic anomaly detection methods, such as limit checking and PCA-based approaches, have been applied to weld defect detection. However, it is still a challenge to identify meaningful defect patterns from very limited sensor signals of laser welding, characterized by intermittent, discontinuous, very short, and non-stationary random signals. In order to effectively analyze the physical characteristics of laser weld signals: plasma intensity, weld pool temperature, and back reflection, we first transform the raw data of laser weld signals into the form of event logs. This is done by multidimensional discretization and event-codification, after which the event logs are decoded to extract weld defect patterns by $Na{\ddot{i}}ve$ Bayes classifier. The performance of the proposed method is examined in comparison with the commercial solution of PRECITEC's LWM$^{TM}$ and the most recent PCA-based detection method. The results show higher performance of the proposed method in terms of sensitivity (1.00) and specificity (0.98).

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.63-75
• /
• 2022

The raw data collected by structural health monitoring (SHM) systems may suffer multiple patterns of anomalies, which pose a significant barrier for an automatic and accurate structural condition assessment. Therefore, the detection and classification of these anomalies is an essential pre-processing step for SHM systems. However, the heterogeneous data patterns, scarce anomalous samples and severe class imbalance make data anomaly detection difficult. In this regard, this study proposes a convolutional neural network-based data anomaly detection method. The time and frequency domains data are transferred as images and used as the input of the neural network for training. ResNet18 is adopted as the feature extractor to avoid training with massive labelled data. In addition, the focal loss function is adopted to soften the class imbalance-induced classification bias. The effectiveness of the proposed method is validated using acceleration data collected in a long-span cable-stayed bridge. The proposed approach detects and classifies data anomalies with high accuracy.

• Journal of information and communication convergence engineering
• /
• v.4 no.4
• /
• pp.151-154
• /
• 2006

In this work, a novel optimal multiuser detection (MUD) approach, which not only achieves the optimal maximum-likelihood (ML)-like performance but also has reasonably low computational complexity, for Space-time coded OFDM (ST-OFDM) systems is presented. In the proposed detection scheme, the signal model is firstly re-expressed into linearly equivalent one. Then, with the linearly equivalent signal model, a new jointly MUD algorithm is proposed to detect signals. The ML-like bit-error-rate (BER) performance and reasonably low complexity of the proposed detection are verified by computer simulations.

• Journal of Institute of Control, Robotics and Systems
• /
• v.8 no.9
• /
• pp.818-826
• /
• 2002

Since multipath phenomenon frequently occurs when a Global Positioning System receiver is placed in urban area crowded with large buildings, efficient mitigation of multipath effects is necessary to resolve. In this paper, we propose a new multipath detection technique that is useful in real-time positioning with a general Global Positioning System receiver. The proposed technique is based on a channelwise multipath test statistic that efficiently indicates the degree of fluctuations induced by multipath error. The proposed multipath test statistic is operationally advantageous because it does not require any specialized hardware nor any pre-computation of receiver position, it is directly related to standard $\chi$$^2$-distributions, and it can adjust the detection resolution by increasing the number of successive measurements. Simulation and experiment results verify the performance of the proposed multipath detection technique.

• Journal of Institute of Control, Robotics and Systems
• /
• v.12 no.4
• /
• pp.353-357
• /
• 2006

The vehicle detection method using pulse radar has the advantage of maintenance in comparison with loop detection method. We propose the pulse radar signal processing algorithm in which we devide the trace. data from pulse radar into segments by using SSC concept, and then construct the sectors in accordance with period and amplitude of segments, and finally decide the vehicle detection probability by applying the SSC parameters of each sectors into the discriminant function. We also improve the signal processing time by reducing the quantities of processing data and processing routines.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.974-977
• /
• 2003

The GPS/INS integration system navigation can provide improved navigation performance and has been widely used as a main navigation system for military and commercial vehicles. When two navigation systems are tightly coupled and the structure is complicated, a fault in either the GPS or the INS can lead to a disastrous failure of the whole integration system. This paper proposes a real-time fault detection method for an AGPS/INS integration system. The proposed fault detection method comprises a BIT and a fault detection algorithm based on chi-square test. It is implemented by real-time software modules to apply the AGPS/INS integration system and van test is carried out to evaluate its performance.

• Journal of Institute of Control, Robotics and Systems
• /
• v.17 no.1
• /
• pp.17-21
• /
• 2011

This paper presents a real- time detection of on-road succeeding vehicles based on low level edge features and a boosted cascade of Haar-like features. At first, the candidate vehicle location in an image is found by low level horizontal edge and symmetry characteristic of vehicle. Then a boosted cascade of the Haar-like features is applied to the initial hypothesized vehicle location to extract the refined vehicle location. The initial hypothesis generation using simple edge features speeds up the whole detection process and the application of a trained cascade on the hypothesized location increases the accuracy of the detection process. Experimental results on real world road scenario with processing speed of up to 27 frames per second for $720{\times}480$ pixel images are presented.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.11
• /
• pp.83-96
• /
• 1996

On PR-IV magnetic recording systems, the maximum likelihood sequence detection (MLSD) method is optimum. But it has the problem of the complexity of the structure. The three level detection (TLD) method can be used, which has simpler structure than MLSD, but requires almost twice of power to achieve the same probbility of error as MLSD does. Therefore a new detection method (error controlled detection: ECD) is proposed which has much simpler structure than MLSD and gives much better performance than TLD. The simulation resutls show that the performance of ECD is better than that of TLD by approximaterly 0.5~1.3dB both in linear and nonlinear channels.

• Journal of Information Processing Systems
• /
• v.12 no.1
• /
• pp.100-108
• /
• 2016

In this paper, we propose a method to achieve improved number plate detection for mobile devices by applying a multiple convolutional neural network (CNN) approach. First, we processed supervised CNN-verified car detection and then we applied the detected car regions to the next supervised CNN-verifier for number plate detection. In the final step, the detected number plate regions were verified through optical character recognition by another CNN-verifier. Since mobile devices are limited in computation power, we are proposing a fast method to recognize number plates. We expect for it to be used in the field of intelligent transportation systems.

• Journal of Information Processing Systems
• /
• v.13 no.3
• /
• pp.590-598
• /
• 2017

Recently, there has been an increase in the number of hazardous events, such as fire accidents. Monitoring systems that rely on human resources depend on people; hence, the performance of the system can be degraded when human operators are fatigued or tensed. It is easy to use fire alarm boxes; however, these are frequently activated by external factors such as temperature and humidity. We propose an approach to fire detection using an image processing technique. In this paper, we propose a fire detection method using multichannel information and gray level co-occurrence matrix (GLCM) image features. Multi-channels consist of RGB, YCbCr, and HSV color spaces. The flame color and smoke texture information are used to detect the flames and smoke, respectively. The experimental results show that the proposed method performs better than the previous method in terms of accuracy of fire detection.