• Korean Journal of Air-Conditioning and Refrigeration Engineering
• /
• v.17 no.1
• /
• pp.47-55
• /
• 2005

An experimental study has been peformed to develop a scheme for fault detection and diagnosis(FDD) in a vapor compression refrigeration system. This study is to analyze fault effect on the system performance and to find efficient diagnosis rules for easy determination of abnormal system operation. The refrigeration system was operated with a variable speed compressor to modulate cooling capacity. The FDD system was designed to consider transient load conditions. Four major faults were considered, and each fault was detected over wide operating load range by separating the system response to the load change. Rule-based method was used to diagnose and classify the system faults. From the experimental results, COP degradation due to the faults in a variable speed system is severer than that in a constant speed system. The method developed in this study can be used in the fault detection of refrigeration systems with a variable speed compressor.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.5
• /
• pp.1597-1610
• /
• 2022

At present, the main method of high-speed train chassis detection is using computer vision technology to extract keypoints from two related chassis images firstly, then matching these keypoints to find the pixel-level correspondence between these two images, finally, detection and other steps are performed. The quality and accuracy of image matching are very important for subsequent defect detection. Current traditional matching methods are difficult to meet the actual requirements for the generalization of complex scenes such as weather, illumination, and seasonal changes. Therefore, it is of great significance to study the high-speed train image matching method based on deep learning. This paper establishes a high-speed train chassis image matching dataset, including random perspective changes and optical distortion, to simulate the changes in the actual working environment of the high-speed rail system as much as possible. This work designs a convolutional neural network to intensively extract keypoints, so as to alleviate the problems of current methods. With multi-level features, on the one hand, the network restores low-level details, thereby improving the localization accuracy of keypoints, on the other hand, the network can generate robust keypoint descriptors. Detailed experiments show the huge improvement of the proposed network over traditional methods.

• Proceedings of the KSRS Conference
• /
• 2004.10a
• /
• pp.144-147
• /
• 2004

Two different sensors (here, KOMPSAT and RADARSAT) are considered for ship detection, and are used to delineate the detection performance for their data. The experiments are set for coastal regions of Mokpo Port and Ulsan Port and field experiments on board pilot boat are conducted to collect in situ ship validation information such as ship type and length. This paper introduce mainly the experiment result of ship detection by both RADARSAT SAR imagery and landbased RADAR data, operated by the local Authority of South Korea, so called vessel traffic system (VTS) radar. Fine imagery of Ulsan Port was acquired on June 19, 2004 and in-situ data such as wind speed and direction, taking pictures of ships and natural features were obtained aboard a pilot ship. North winds, with a maximum speed of 3.1 m/s were recorded. Ship's position, size and shape and natural features of breakwaters, oil pipeline and alongside ship were compared using SAR and VTS. It is shown that KOMPSAT/EOC has a good performance in the detection of a moving ship at a speed of 7 kts or more an hour that ship and its wake can be imaged. The detection capability of RADARSAT doesn't matter how fast ship is running and depends on a ship itself, e.g. its material, length and type. Our results indicate that SAR can be applicable to automated ship detection for a VTS and SAR combination service.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.12 no.6
• /
• pp.68-77
• /
• 2013

This study suggested experimental study results of congestion detection method for intruding vehicle enforcement system. This congestion detection method is developed to determine optimal operation criteria of intruding vehicle enforcement system as detecting traffic congestion. In ITS sector, traffic management systems generally have used a sectional travel speed for congestion detection. However, image sensors have high error rate of congestion detection because of speed error. This study suggested comprehensive congestion detection criteria based on speed and occupancy rate using field studies. As field study results, the proposed intruding vehicle enforcement system using image sensor is capable of accurately detecting the traffic congestion using sectional speed of 20km/h and occupancy rate of 60% as congestion detection criteria.

• Journal of Information Processing Systems
• /
• v.18 no.3
• /
• pp.428-442
• /
• 2022

A reliable automatic passenger counting (APC) system is a key point in transportation related to the efficient scheduling and management of transport routes. In this study, we introduce a lightweight head detection network using deep learning applicable to an embedded system. Currently, object detection algorithms using deep learning have been found to be successful. However, these algorithms essentially need a graphics processing unit (GPU) to make them performable in real-time. So, we modify a Tiny-YOLOv3 network using certain techniques to speed up the proposed network and to make it more accurate in a non-GPU environment. Finally, we introduce an APC system, which is performable in real-time on embedded systems, using the proposed head detection algorithm. We implement and test the proposed APC system on a Samsung ARTIK 710 board. The experimental results on three public head datasets reflect the detection accuracy and efficiency of the proposed head detection network against Tiny-YOLOv3. Moreover, to test the proposed APC system, we measured the accuracy and recognition speed by repeating 50 instances of entering and 50 instances of exiting. These experimental results showed 99% accuracy and a 0.041-second recognition speed despite the fact that only the CPU was used.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.1 no.1
• /
• pp.12-19
• /
• 1996

The purpose of this paper is the improvement of the speed control characteristics of induction machines suited the low resolution incremental-type encoder in a low speed region. In order to improve the control characteristics in a low speed range, we propose that the instantaneous speed control method by the instantaneous speed detection which is implemented by the disturbance torque observer. Also, in case of the speed control by the instantaneous speed detection, the simple estimation method of the mechanical inertia moment is proposed. We will the carry out the mathematical verification of the proposed theory by the theoretic advisement connected with the convergence relationship of the estimated inertia moment to the real mechanical inertia moment. Computer simulations and experiments by the IGBT inverter adopting DSP is performed to verify the proposed method.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.8 no.3
• /
• pp.137-143
• /
• 2013

This paper describes an implementation of face detection technology for a real-time application on the Android platform. Java class of Face-Detection for detection of human face is provided by the Android API. However, this function is not suitable to apply for the real-time applications due to inadequate detection speed and accuracy. In this paper, the AdaBoost based classification method which utilizes Local Binary Pattern (LBP) histogram is employed for face detection. The face detection module has been developed by C/C++ language for high-speed image processing, and this module is included to the Android platform using the Java Native Interface (JNI). The experiments were carried out in the Java-based environment and JNI-based environment. The experimental results have shown that the performance of JNI-based is faster than Java-based method and our system is well enough to apply for real-time applications.

• Journal of Information Processing Systems
• /
• v.12 no.3
• /
• pp.502-510
• /
• 2016

Considering video copy transform diversity, a multi-feature video copy detection algorithm based on a Speeded-Up Robust Features (SURF) local descriptor is proposed in this paper. Video copy coarse detection is done by an ordinal measure (OM) algorithm after the video is preprocessed. If the matching result is greater than the specified threshold, the video copy fine detection is done based on a SURF descriptor and a box filter is used to extract integral video. In order to improve video copy detection speed, the Hessian matrix trace of the SURF descriptor is used to pre-match, and dimension reduction is done to the traditional SURF feature vector for video matching. Our experimental results indicate that video copy detection precision and recall are greatly improved compared with traditional algorithms, and that our proposed multiple features algorithm has good robustness and discrimination accuracy, as it demonstrated that video detection speed was also improved.

• The KIPS Transactions:PartC
• /
• v.11C no.2
• /
• pp.157-162
• /
• 2004

Recently, the growth of information infrastructure is getting fatter and faster. At the same time, the security accidents are increasing together. We have problem that do not handle traffic because we have the Intrusion Detection Systems in low speed environment. In order to overcome this, we need effective security analysis techniques that ran Processed data of high-capacity because high speed network environment. In this paper we proposed the Gigabit Intrusion Detection System for coordinated security function such as intrusion detection, response on the high speed network. We suggested the detection mechanism in high speed network environment that have pattern matching function based packet header and based packet data that is proceeded in system kernel area, we are shown that this mechanism was excellent until maximum 20 times than existing system in traffic processing performance.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.3 no.2
• /
• pp.42-50
• /
• 1995

This paper proposes a new method to investigate combustion phenomena using the variation of crankshaft speed, From the idea that the variation of crankshaft speed contains the information of combustion, the energy method is applied as a single degree of freedom. Through the comparison of measured and calculated crankshaft speed, the proposed energy model is proved to be effective. When the crankshaft speed is used in the energy equation, filtering of the speed is required. The frequency components of cylinder pressure are analyzed and the coefficients of Fourier series above the twelfth frequency of engine speed are considered as a noise. As an example of application of this research, some combustion analyses like mean effective pressure, heat release rate, and misfire detection were carried out.