• Journal of Auto-vehicle Safety Association
• /
• v.12 no.4
• /
• pp.70-77
• /
• 2020

In this study, we estimate the vehicle speed by analyzing the acoustic data recorded in a single microphone of a surveillance camera. The frequency analysis of the acoustic data corrects the Doppler effect, which is a characteristic of the moving sound source, and reflects the geometric relationship according to the location of the sound source and the microphone on the two-dimensional plane. The acoustic data is selected from the horn sound that is mainly observed in an urgent situation among various sound sources that may occur in a traffic accident, and the characteristics of the monotone source are considered. We verified the reliability of the proposed method by time domain acoustic analysis and actual vehicle evaluation. This method is effective and can be used for traffic accident analysis in the blind spot of the camera using a single microphone built into the existing surveillance camera.

• Journal of Korea Multimedia Society
• /
• v.25 no.2
• /
• pp.157-165
• /
• 2022

As the stock market is affected by various circumstances including economic and political variables, predicting the stock market is considered a still open problem. When combined with corporate financial statement data analysis, which is used as fundamental analysis, and technical analysis with a short data generation cycle, there is a problem that the time domain does not match. Our proposed method, LSTE the operating profit and market outlook of a petrochemical company and estimates the sales and operating profit of the company, it was possible to solve the above-mentioned problems and improve the accuracy of stock price prediction. Extensive experiments on real-world stock data show that our method outperforms the 8.58% relative improvements on average w.r.t. accuracy.

• Proceedings of the IEEK Conference
• /
• 2004.08c
• /
• pp.729-734
• /
• 2004

The e-Logistics means the virtual business activity and service architecture among the logistics companies based on the Internet technology. The management of vehicles' location in most conventional vehicle tracking system has some critical defects when it deals with data which are continuously changed. It means the conventional vehicle tracking system based on the conventional database is unable eventually to cope with the environment that should manage the frequently changed location of vehicles. The important things in the evaluation of the vehicle tracking system is to determine the threshold of cost of database ,update period and communication period between vehicles and the system. In other words, the difference between the reallocation of vehicle and the data in database can evaluate the overall performance of vehicle tracking systems. Most of the previous works considers only the information that is valid at the current time, and is hard to manage efficiently the past and future information. To overcome this problem, the efforts on moving objects management system(MOMS) and uncertainty processing have been started from a few years ago. In this paper, we propose an uncertainty processing model and system implementation of moving object that tracks the location of the vehicles. We adopted both linear-interpolation method and trigonometric function to chase up the location of vehicles for the past time as well as future time, respectively. We also explain the comprehensive examples of MOMS and uncertainty processing in parcel application that is one of major application of e-Logistics domain.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.34 no.1
• /
• pp.25-33
• /
• 2021

With the development of machine learning techniques, various types of data such as vibration, temperature, and flow rate can be used to detect and diagnose abnormalities in machine conditions. In particular, in the field of the state monitoring of rotating machines, the fault diagnosis of machines using vibration data has long been carried out, and the methods are also very diverse. In this study, an experiment was conducted to collect vibration data from normal and abnormal compressors by installing accelerometers directly on rotary compressors used in household air conditioners. Data segmentation was performed to solve the data shortage problem, and the main features for the fault classification model were extracted through the chi-square test after statistical and physical features were extracted from the vibration data in the time domain. The support vector machine (SVM) model was developed to classify the normal or abnormal conditions of compressors and improve the classification accuracy through the hyperparameter optimization of the SVM.

• Journal of Advanced Navigation Technology
• /
• v.17 no.6
• /
• pp.804-809
• /
• 2013

The current state monitoring system at a semiconductor manufacturing process is based on the manually collected sensor data, which involves limitations when it comes to complex malfunction detection and real time monitoring. This study aims to design a situation recognition algorithm to form a network over time by creating a domain ontology and to suggest a system to provide users with services by generating events upon finding risk factors in the semiconductor process. To this end, a multiple sensor node for situational inference was designed and tested. As a result of the experiment, events to which the rule of time inference was applied occurred for the contents formed over time with regard to a quantity of collected data while the events that occurred with regard to malfunction and external time factors provided log data only.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.6 s.38
• /
• pp.75-84
• /
• 2005

Bulletin board systems have evolved to support diverse multimedia data as well as text. However, current board systems have an weakness : it takes much time and efforts for users to figure out contents of articles. Most board systems provide a searching function with lexical level data access for solving that problem, however it fails to serve users' intented searching results. Moreover, it is nearly impossible to search proper articles if they contain multimedia data. This paper proposed a bulletin board system adopting the Semantic Web to solve this issue. The proposed system provides users with new ontology which is used for describing articles' domain knowledge and multimedia features. Users can describe their own board ontology using the proposed ontology. To support semantic-based searching for diverse domain knowledge without modification of the system, the system dynamically generated input/query interface and RDF data access module according to the board ontology written by administrators. The proposed board system shows that semantic-based searching is feasible and effective for users to find their intended articles.

• International Journal of Safety
• /
• v.11 no.2
• /
• pp.15-21
• /
• 2012

This paper is aimed to develop an electrical fire detection system (EFDS) which can analyze the possibility of electrical fire for overcurrent, leakage current and arc signals of panel board in traditional market shop. The EFDS adopted fuzzy logic and precursory data for overcurrent, leakage current and arc signals to evaluate the possibility of electrical fire. The signals are obtained directly from panel board in traditional market shops and fuzzy membership function is obtained from experiment, simulation, expert's advice. The overcurrent data is acquired by thermal data of normal and abnormal states (partial disconnection) on the insulated electrical wire, in accordance with the increase of the current signal, The leakage current data is obtained under various environments. The arc signal is acquisited by waveforms of instantaneous value in time domain and frequency band in frequency domain. The Fuzzy algorithm for DB of EFDS consists of fuzzification, inference engine by Mamdani's method and defuzzification by center of gravity method. In order to verify the performance and reliability of EFDS, it was applied to Jeon-Ju traditional market shops (90 shops) in Korea. Results show that EFDS in this paper is useful in alarming the fire case, which will prevent severe damage to human beings and properties, and reduce the electrical fires in a vulnerable area of electrical disaster.

• KIEAE Journal
• /
• v.7 no.4
• /
• pp.147-152
• /
• 2007

Numerous non-destructive tests(NDT) to assess the safety of real structures have been developed. System identification(SI) techniques using dynamic responses and behaviors of structural systems become an outstanding issue of researchers. However the conventional SI techniques are identified to be non-practical to the complex and tall buildings, due to limitation of the availability of an accurate data that is magnitude or location of external loads. In most SI approaches, the information on input loading and output responses must be known. In many cases, measuring the input information may take most of the resources, and it is very difficult to accurately measure the input information during actual vibrations of practical importance, e.g., earthquakes, winds, micro seismic tremors, and mechanical vibration. However, the desirability and application potential of SI to real structures could be highly improved if an algorithm is available that can estimate structural parameters based on the response data alone without the input information. Thus a technique to estimate structural properties of building without input measurement data and using limited response is essential in structural health monitoring. In this study, shaking table tests on three-story plane frame steel structures were performed. Out-put only model analysis on the measured data was performed, and the dynamic properties were inverse analyzed using least square method in time domain. In results damage detection was performed in each member level, which was performed at story level in conventional SI techniques of frequency domain.

• Smart Structures and Systems
• /
• v.17 no.2
• /
• pp.209-230
• /
• 2016

The Canton Tower is a high-rise slender structure with a height of 610 m. A structural health monitoring system has been instrumented on the structure, by which data is continuously monitored. This paper presents an investigation on the identified modal properties of the Canton Tower using ambient vibration data collected during a whole day (24 hours). A recently developed Fast Bayesian FFT method is utilized for operational modal analysis on the basis of the measured acceleration data. The approach views modal identification as an inference problem where probability is used as a measure for the relative plausibility of outcomes given a model of the structure and measured data. Focusing on the first several modes, the modal properties of this supertall slender structure are identified on non-overlapping time windows during the whole day under normal wind speed. With the identified modal parameters and the associated posterior uncertainty, the distribution of the modal parameters in the future is predicted and assessed. By defining the modal root-mean-square value in terms of the power spectral density of modal force identified, the identified natural frequencies and damping ratios versus the vibration amplitude are investigated with the associated posterior uncertainty considered. Meanwhile, the correlations between modal parameters and temperature, modal parameters and wind speed are studied. For comparison purpose, the frequency domain decomposition (FDD) method is also utilized to identify the modal parameters. The identified results obtained by the Bayesian method, the FDD method and a finite element model are compared and discussed.

• The Journal of the Acoustical Society of Korea
• /
• v.22 no.8
• /
• pp.727-739
• /
• 2003

In this paper, we propose a generation method of regression classes for adaptation in the HM-Net (Hidden Markov Network) system. The MLLR (Maximum Likelihood Linear Regression) adaptation approach is applied to the HM-Net speech recognition system for expressing the characteristics of speaker effectively and the use of HM-Net in various tasks. For the state level sharing, the context domain state splitting of PDT-SSS (Phonetic Decision Tree-based Successive State Splitting) algorithm, which has the contextual and time domain clustering, is adopted. In each state of contextual domain, the desired phoneme classes are determined by splitting the context information (classes) including target speaker's speech data. The number of adaptation parameters, such as means and variances, is autonomously controlled by contextual domain state splitting of PDT-SSS, depending on the context information and the amount of adaptation utterances from a new speaker. The experiments are performed to verify the effectiveness of the proposed method on the KLE (The center for Korean Language Engineering) 452 data and YNU (Yeungnam Dniv) 200 data. The experimental results show that the accuracies of phone, word, and sentence recognition system increased by 34∼37%, 9%, and 20%, respectively, Compared with performance according to the length of adaptation utterances, the performance are also significantly improved even in short adaptation utterances. Therefore, we can argue that the proposed regression class method is well applied to HM-Net speech recognition system employing MLLR speaker adaptation.