• The Journal of the Acoustical Society of Korea
• /
• v.15 no.2
• /
• pp.85-89
• /
• 1996

In this paper, transition constrained Hidden Markov Model(HMM) in which the transition between states occur only within prescribed time slot is proposed and the performance is evaluated in the noisy environment. The transition constrained HMM can explicitly limit the state durations and accurately de scribe the temporal structure of speech signal simply and efficiently. The transition constrained HMM is not only superior to the conventional HMM but also require much less computation time. In order to evaluate the performance of the transition constrained HMM, speaker independent isolated word recognition experiments were conducted using semi-continuous HMM with the noisy speech for 20, 10, 0 dB SNR. Experiment results show that the proposed method is robust to the environmental noise. The 81.08% and 75.36% word recognition rates for conventional HMM was increased by 7.31% and 10.35%, respectively, by using transition constrained HMM when two kinds of noises are added with 10dB SNR.

• Explosives and Blasting
• /
• v.31 no.1
• /
• pp.11-22
• /
• 2013

This study compared and analysed ground vibration, size of underwater background noise in fish farms and underwater object noise of blasting and obtained ground vibration prediction equation through a regression analysis and correlation equation between underwater object noises in order to predict degrees of underwater noise in blasting and organize underwater noise control regulations. Before the study, when background noise of fish and shellfish farms with different conditions was measured, levels of background noise were different according to environmental characteristics of each farm. Ground vibration which causes underwater noise was measured to obtain a correlation equation between ground vibration and underwater object noise. Therefore, if underwater noise is predicted for each construction with a use of a correlation and permissible standards appropriate for each condition are applied for design and construction, financial loss from damages to fish and shellfish caused by development of insufficient technological and engineering logic can be prevented and successful construction with safety of underwater creatures guaranteed can be achieved.

• Journal of the Korean Society of Safety
• /
• v.27 no.3
• /
• pp.153-160
• /
• 2012

Various social problems such as traffic congestion, car accidents and environmental problems(air pollution, noises etc.) have been happening in the Seoul metropolitan area that has the car oriented traffic system providing cars continuously. Along with this, the financial burden caused by current oil price anxiety made paradigm shift from caroriented to public transportation-oriented. Its typical example is an arterial branch bus system changing(bus lane through the center of main road) started in Seoul in July, 2004. But study on safety analysis of bus lane and characteristic of accidents are not sufficient enough to now. The bus lanes are expanded to provide roads for better traffic operation and accidents between buses and pedestrians or ordinary vehicles are considered main problems. This study divided each bus route of median bus lane(bus-only lane through the center of main roads) and bus lane at roadside by intersection and collected and analysed data about influence variables of bus accidents chosen in each section. We constructed a logistic model using collected data. As a result, bus lane at roadside are used by both buses and other kinds of vehicles differently from median bus lane and showed such characteristic in accident influence. Therefore access management to factors causing conflict and improvement of operation management are required. In case of median bus lane, the more buses moving general vehicle lane and traffic volume of section were, the more accidents happened. In case that stop line of center lane is not backward, view blocking of vehicles turning left caused accidents.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.33 no.2
• /
• pp.433-442
• /
• 2013

This paper presents experimental research work for the evaluation of one-dimensional and two-dimensional acoustic source locations with 50m length of a precast prestressed concrete box girder. Acoustic events are generated by the impacts of Schmidt Hammer and the impact signals are detected by acoustic emission sensors mounted on the concrete web surface of PSC box girder with the average spacing of 9.34m. Based on the amplitude of detected acoustic signals, considering the noises developed in PSC box girder bridges, the arrival times of acoustic signals are estimated by the first arrival times of 0Volt, 0.5Volt, and 1.0Volt amplitude in each signal. Using Least Square Method, the velocities and the source locations of acoustic signals are evaluated. Based on the test results, the spacing of AE sensors and the AE sensor networks are discussed to reduce the source location errors.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.5
• /
• pp.1055-1063
• /
• 2012

The noise of image is added by many environmental factors. Therefore, we need to remove these noises using the conventional filtering methods, which are optimized based on the statistical characteristic of noise. In direct restoration method, there is an inverse filter and the wiener filter. Here, the wiener filter is the optimized filter in the view of least square method. First, we are going to study the inverse filter, wiener filter, constraint least square filter. Second, in order to control the quantity, we use the parameters instead of the power spectrum ratio. But, these parameters have the conflicting condition, therefore, we optimized the variables using parametric wiener filter which adjust the application appropriately. In the simulation results, the contrast of the degraded image was enhanced and the noise was removed. Comparative experimentation was demonstrated edge preserving and noise removing property.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.9
• /
• pp.2129-2137
• /
• 2015

Lots of research and development works have been actively focused on the self-driving vehicles, locally and globally. In order to implement the self-driving vehicles, lots of fundamental core technologies need to be successfully developed and, specially, it is noted that traffic lights detection and recognition system is an essential part of the computer vision technologies in the self-driving vehicles. Up to nowadays, most conventional algorithm for detecting and recognizing traffic lights are mainly based on the color signal analysis, but these approaches have limits on the performance improvements that can be achieved due to the color signal noises and environmental situations. In order to overcome the performance limits, this paper introduces the morphological analysis for the traffic lights recognition. That is, by considering the color component analysis and the shape analysis such as rectangles and circles simultaneously, the efficiency of the traffic lights recognitions can be greatly increased. Through several simulations, it is shown that the proposed method can highly improve the recognition rate as well as the mis-recognition rate.

• Journal of the Korea Safety Management & Science
• /
• v.21 no.1
• /
• pp.1-7
• /
• 2019

Along with industrial development, various architectural structures have become bigger and higher, leading to an expansion in the size and capacity of construction equipment. And with the development of public transportation, the use of subways as a means of transportation in the city center is increasing, so that vibrations and structural noises are emerging as a new environmental issue. Considering that architectural structures may be used from several decades to hundreds of years after the time of construction, they can be seen as semi-permanent. Due to changes in the vibration-proof polyurethane mats installed in the foundation of these structures, settling may occur and vibration reduction may become inadequate. Therefore, in view of service life, it is necessary to have a high-level standard of reliability and stability. In accordance with this, the Floating Floor System, which uses soft polyurethane foam and can be constructed within a relatively short period of time, has excellent vibration resistant characteristics. It is presented as a great alternative solution to the issue of vibrations caused by subways, railways and building structures. At present, vibration-proof polyurethane mats have been developed up to the same product level as in other advanced countries. However, in the construction of structure foundations, the physical properties of this product and its shape incur changes. If they are installed as such in the structure of a building, it may cause significant impact on stability, requiring that this cause be urgently identified and improved.

• Journal of the Earthquake Engineering Society of Korea
• /
• v.25 no.2
• /
• pp.71-81
• /
• 2021

This paper presents a real-time, false-pick filter based on deep learning to reduce false alarms of an onsite Earthquake Early Warning (EEW) system. Most onsite EEW systems use P-wave to predict S-wave. Therefore, it is essential to properly distinguish P-waves from noises or other seismic phases to avoid false alarms. To reduce false-picks causing false alarms, this study made the EEWNet Part 1 'False-Pick Filter' model based on Convolutional Neural Network (CNN). Specifically, it modified the Pick_FP (Lomax et al.) to generate input data such as the amplitude, velocity, and displacement of three components from 2 seconds ahead and 2 seconds after the P-wave arrival following one-second time steps. This model extracts log-mel power spectrum features from this input data, then classifies P-waves and others using these features. The dataset consisted of 3,189,583 samples: 81,394 samples from event data (727 events in the Korean Peninsula, 103 teleseismic events, and 1,734 events in Taiwan) and 3,108,189 samples from continuous data (recorded by seismic stations in South Korea for 27 months from 2018 to 2020). This model was trained with 1,826,357 samples through balancing, then tested on continuous data samples of the year 2019, filtering more than 99% of strong false-picks that could trigger false alarms. This model was developed as a module for USGS Earthworm and is written in C language to operate with minimal computing resources.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.5D
• /
• pp.731-738
• /
• 2006

Facing congestion, people want to know traffic information about their routes, especially real-time link travel time (LTT). In this paper, as a sequel paper of the previous non-taxi based LTT generating study by Choi et al. (1998), taxi based GPS probes have been tried to produce LTT for urban arterials. Taxis in itself are good deployment mode of GPS probes although it by nature experiences boarding and alighting time noises which should be accounted. A heuristic real-time dynamic outlier filter algorithm for taxi GPS probe has been developed focusing on urban arterials. An actual traffic survey for dynamic link travel times has been conducted using license plate method for the test arterials of Seoul city transportation network. With the algorithm, it is estimated that 70% of outliers have been filtered and the relative error has been improved by 73.7%. The filtering algorithm developed here would be expected to be in use for other spatial sites with some calibration efforts. Some limitations and future research agenda have also been discussed.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.30 no.3A
• /
• pp.257-264
• /
• 2010

Generally, estimations on the displacement as an important factor in evaluating the safety of large structures could be a barometer assessing whether the condition of the structure is deteriorating. Practically, it is not easy how to measure the displacement response to large structures like suspension bridges. In this study, as a method for estimation displacement response from strain signals, mode decomposition technique is proposed. Total displacement response is estimated by superposing quasistatic displacement response and modal displacement responses in dominant modes with larger contributions after estimating the modal displacement responses. If foiled strain gauges are used to measure strain signals, there would likely to generate electric noise, what's more, the more measuring points there are the more economic burden it could be. In order to solve such problems, fiber optic bragg-grating(FBG) sensors were used, which have multi-point measurements with no effect on electric noises. Therefore, the experiment was performed through dynamic load test of suspension bridge and plate-girder bridge to review the possibility for using mode decomposition technique.