Hyeon Bae

Real-time face detection and recognition using hybrid-information extracted from face space and facial features

This paper describes both face detection using the eigenface space and face recognition using neural networks. Real-time face detection from face images was performed in two steps. In the first step, a normalized skin color map based on the Gaussian function was applied to extract a face candidate region. The facial feature information in the candidate region was employed to detect the face region. In this step, face detection was sequentially accomplished using three methods. DFFS, a combination of DFFS and DIFS, and template matching were used. Facial features were extracted according to the Euclidian distance between the determined face region and the predefined eigenfaces from the face region. In the second step, neural network models were trained using 120 images for face recognition. In the experiments, three neural network models corresponding to input variables that included features from face spaces, facial features (geometrical features), and both, were constructed. The image of each person was obtained based on the various directions, poses, and facial expressions. The number of hidden layers was changed from 1 to 3 for several tests of the neural network models. The goal of this study was to reduce lighting effects in order to achieve high-performance of face recognition, because face recognition cannot cope with changes due to lighting.

Flame detection for the steam boiler using neural networks and image information in the Ulsan steam power generation plant

Several types of detectors such as ultraviolet (UV), infrared (IR), visible light (VL), different pressure, flame rod, and others are employed to detect a fire flame in power generation plants. However, these flame detectors have some performance problems. Therefore, this paper describes the image-processing method of fire detection as well as the neural-network modeling. Nowadays, the image-processing technique is broadly applied in the industrial fields. An extracted image information is taken into the inputs of the neural-network model. The neural-network model has strong adaptability and learning capability; therefore, this model can be suitable for pattern classification. The Ulsan Steam Power Generation Plant in Korea is employed as the test field. If this technique can be implemented in physical plants, the boilers can be operated economically and effectively.

Intelligent Methods to Extract Knowledge from Process Data in the Industrial Applications

Data are an expression of the language or numerical values that show some features. And the information is extracted from data for the specific purposes. The knowledge is utilized as information to construct rules that recognize patterns or make a decision. Today, knowledge extraction and application of that are broadly accomplished for the easy comprehension and the performance improvement of systems in the several industrial fields. The knowledge extraction can be achieved by some steps that include the knowledge acquisition, expression, and implementation. Such extracted knowledge is drawn by rules with data mining techniques. Clustering (CL), input space partition (ISP), neuro-fuzzy (NF), neural network (NN), extension matrix (EM), etc. are employed for the knowledge expression based upon rules. In this paper, the various approaches of the knowledge extraction are surveyed and categorized by methodologies and applied industrial fields. Also, the trend and examples of each approaches are shown in the tables and graphes using the categories such as CL, ISP, NF, NN, EM, and so on.

Application of time-series data mining for fault diagnosis of induction motors

The motor is the workhorse of industries. The issues of preventive and condition-based maintenance, online monitoring, system fault detection, diagnosis, and prognosis are of increasing importance. This paper introduces a technique to detect faults in induction motors. Stator currents are measured by current meters and stored by time domain. The time domain is not suitable for representing current signals, so the frequency domain is used to display the signals. Fourier transform is used to convert the signals onto frequency domain. After the signals have been converted, the features of the signals are extracted by the signal processing methods like the wavelet analysis, spectrum analysis, and other methods. The discovered features are entered to a pattern classification model such as a neural network model, a polynomial neural network, a fuzzy inference model, or other models. This paper describes the results of detecting fault using Fourier and wavelet analysis.

On-line fabric-defects detection based on wavelet analysis

This paper introduces a vision-based on-line fabric inspection methodology for woven textile fabrics. The current procedure for the determination of fabric defects in the textile industry is performed by humans in the off-line stage. The proposed inspection system consists of hardware and software components. The hardware components consist of CCD array camera, a frame grabber, and appropriate illumination. The software routines capitalize on vertical and horizontal scanning algorithms to reduce the 2-D image into a stream of 1-D data. Next, wavelet transform is used to extract features that are characteristic of a particular defect. The signal-to-noise ratio (SNR) calculation based on the results of the wavelet transform is performed to measure any defects. Defect detection is carried out by employing SNR and scanning methods. Learning routines are called upon to optimize the wavelet coefficients. Test results from different types of defect and different styles of fabric demonstrate the effectiveness of the proposed inspection system.

Fault diagnostic of induction motors for equipment reliability and health maintenance based upon Fourier and wavelet analysis

The motor is the workhorse of industry. The issues of preventive and condition-based maintenance, on-line monitoring, system fault detection, diagnosis, and prognosis are of increasing importance. This paper introduces fault detection for induction motors. Stator currents are measured by current meters and stored by time domain. The time domain is not suitable for representing current signals, so the frequency domain is applied to display signals. The Fourier transform is employed to convert signals. After signal conversion, signal features must be extracted by signal processing such as wavelet and spectrum analysis. Features are entered in a pattern classification model such as a neural network model, a polynomial neural network, or a fuzzy inference model. This paper describes fault detection results that use Fourier and wavelet analysis. This combined approach is very useful and powerful for detection signal features.

e-prognosis and diagnosis for process management using data mining and artificial intelligence

In the past several decades, the huge amount of data was collected and processed by manufacturers to improve the quality and the productivity of products. Data collection mechanism as one of the process management system is an essential part in the manufacturing processes. Many researchers now devote substantial portions of their day to worrying about data handling that includes extracting information. But, the accumulated records in the real manufacturing processes are not effectively utilized to change operational conditions or remain unused condition. Therefore, the primary goal of this paper is to survey the existing KM techniques and apply the methods to two examples for e-prognosis and e-diagnosis purposes.

Fault Detection and Diagnosis of Winding Short in BLDC Motors Based on Fuzzy Similarity

The tum-to-tum short is one major fault of the motor faults of BLDC motors and can appear frequently. When the fault happens, the motor can be operated without breakdown, but it is necessary to maintain the motor for continuous working. In past research, several methods have been applied to detect winding faults. The representative approaches have been focusing on current signals, which can give important information to extract features and to detect faults. In this study, current sensors were installed to measure signals for fault detection of BLDC motors. In this study, the Parks vector method was used to extract the features and to isolate the faults from the current measured by sensors. Because this method can consider the three-phase current values, it is useful to detect features from one-phase and three-phase faults. After extracting two-dimensional features, the final feature was generated by using the two-dimensional values using the distance equation. The values were used in fuzzy similarity to isolate the faults. Fuzzy similarity is an available tool to diagnose the fault without model generation and the fault was converted to the percentage value that can be considered as possibility of the fault.

Wavelet Analysis to Real-Time Fabric Defects Detection in Weaving processes

This paper introduces a vision-based on-line fabric inspection methodology of woven textile fabrics. Current procedure for determination of fabric defects in the textile industry is performed by human in the off-line stage. The advantage of the on-line inspection system is not only defect detection and identification, but also 벼ality improvement by a feedback control loop to adjust set-points. The proposed inspection system consists of hardware and software components. The hardware components consist of CCD array cameras, a frame grabber and appropriate illumination. The software routines capitalize upon vertical and horizontal scanning algorithms characteristic of a particular deflect. The signal to noise ratio (SNR) calculation based on the results of the wavelet transform is performed to measure any deflects. The defect declaration is carried out employing SNR and scanning methods. Test results from different types of defect and different style of fabric demonstrate the effectiveness of the proposed inspection system.

Predictive fault detection and diagnosis of nuclear power plant using the two-step neural network models

Operating the nuclear power generations safely is not easy way because nuclear power generations are very complicated systems. In the main control room of the nuclear power generations, about 4000 numbers of alarms and monitoring devices are equipped to handle the signals corresponding to operating equipments. Thus, operators have to deal with massive information and to analyze the situation immediately. In this paper, the fault diagnosis system is designed using 2-steps neural networks. This diagnosis method is based on the pattern of the principal variables which could represent the type and severity of faults.