• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 1997년도 추계학술대회논문집; 한국과학기술회관; 6 Nov. 1997
• /
• pp.222-226
• /
• 1997

The reproducibility of measured level is a prior condition for the reliable assessment of the sound insulation performance. To review the reproducibility of impact sound level, 20 floors were selected in highrise apartment house, and then impact sound levels of two kinds of typical floors were measured with 10 times in each receiving point. The impact sound insulation class values were derived with a standard tapping machine and bang machine. Inspection of the result showed that smaller scale of the room caused to lower the reproducibility and that the higher values of standard deviation in lower frequency caused to deteriorate the reliability of assesment. Thus to enhance the reproducibility of the impact sound insulation class, greater allowable deviation of measured level is required in lower frequency than in higher one.

• Computers and Concrete
• /
• 제33권4호
• /
• pp.409-423
• /
• 2024

Using an extensive database, a sensitivity analysis across fifteen machine learning (ML) classifiers was conducted to evaluate the impact of various data manipulation techniques, evaluation metrics, and explainability tools. The results of this sensitivity analysis reveal that the examined models can achieve an accuracy ranging from 72-93% in predicting the fire-induced spalling of concrete and denote the light gradient boosting machine, extreme gradient boosting, and random forest algorithms as the best-performing models. Among such models, the six key factors influencing spalling were maximum exposure temperature, heating rate, compressive strength of concrete, moisture content, silica fume content, and the quantity of polypropylene fiber. Our analysis also documents some conflicting results observed with the deep learning model. As such, this study highlights the necessity of selecting suitable models and carefully evaluating the presence of possible outcome biases.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제2권2호
• /
• pp.95-99
• /
• 2002

The Loose Part Monitoring System(LPMS) has been designed to detect. locate and evaluate detached or loosened parts and foreign objects in the reactor coolant system. In this paper, at first, we presents an application of the back propagation neural network. At the preprocessing step, the moving window average filter is adopted to reject the reject the low frequency background noise components. And then, extracting the acoustic signature such as Starting point of impact signal. Rising time. Half period. and Global time, they are used as the inputs to neural network . Secondly, we applied the neural network algorithm to LPMS in order to estimate the mass of loose parts. We trained the impact test data of YGN3 using the backpropagation method. The input parameter for training is Rising clime. Half Period amplitude. The result shored that the neural network would be applied to LPMS. Also, applying the neural network to thin practical false alarm data during startup and impact test signal at nuclear power plant, the false alarms are reduced effectively.

• 대한기계학회논문집A
• /
• 제24권12호
• /
• pp.2945-2951
• /
• 2000

Because of the inherent flexibility in their design for improved material properties, composites have wide applications in aerospace vehicles and automobiles. The purpose of this study is to investigate the energy absorption characteristics of CFRP( Carbon Fiber Reinforced Plastics); tubes on static and impact tests. Static compression tests have been carried out using the static testing machine(Shin-gang buckling testing machine)and impact compression tests have been carried out using the vertival crushing testing machine. When such tubes were subjected to crushing loads, the response is complex and depends on the interaction between the different mechanisms that control the crushing process. The collapse characteristics and energy absorption were examined. Trigger and interlaminar number affect energy absorption capability of CFRP tubes.

• 한국공작기계학회논문집
• /
• 제13권6호
• /
• pp.23-28
• /
• 2004

Impact behavior of polycarbonate in various defect state was investigated using an instrumented impact tester. A method of analyzing raw impact data was developed and successfully demonshsted the impact behavior in terms of load-displacement and energy-displacement curves. This technique was shown to be capable of separating defect no-defect initiated fractures as well as their propagation behaviors.

• Asia pacific journal of information systems
• /
• 제34권1호
• /
• pp.209-225
• /
• 2024

This research aims to use machine learning technology in human resource management to predict employees' work-life balance. The study utilized a dataset from IBM Watson Analytics in the IBM Community for the machine learning analysis. Multinomial dependent variables concerning workers' work-life balance were examined, categorized into continuous and categorical types using the Generalized Linear Model. The complexity of assessing variable roles and their varied impact based on the type of model used was highlighted. The study's outcomes are academically and practically relevant, showcasing how machine learning can offer further understanding of psychological variables like work-life balance through analyzing employee profiles.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2007년도 춘계학술대회논문집
• /
• pp.964-968
• /
• 2007

The measurement of floor impact sound have been standardized in KS 2810-1 and 2. The height of receiving microphones position is specified in the standard as 1.2m which is almost half height of apartment rooms as a listening position. In this study, receiving positions are investigated by measuring the distribution of sound pressure levels at 792 receiving microphone positions in the standard testing building. Standard impact sources, tapping machine and impact ball, are driven on the center position in the source room where is located at the above floor. It was found that the distribution of sound pressure levels in the receiving room indicates significant deviation at different frequencies there is more than 5dB drop at 63Hz but 2dB rise at 125Hz at a height of 1.2m when the impact ball is driven, in the other case of a generating tapping machine there is more than 2dB rise at 125Hz at a height of 1.2m due to room modes.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2001년도 춘계학술대회논문집E
• /
• pp.223-228
• /
• 2001

This study was obtained the pressure distribution of a falling body that is deadrise angle $0^{\circ}$ and deadrise angle $5^{\circ}$ upon a water surface by the experiment with the impact machine. The theoretical equation was obtained the air region and the interface and the water region which devide 3 parties between the body and the water surface for an investigation of the complete phenomena. Pressure distributions and histories compare favorably with available experimental data. The numerical results are similar to the experimental results for the impact force type with $Fo(1+cos{\pi}t/tc)$.

• 한국지능시스템학회논문지
• /
• 제22권6호
• /
• pp.774-779
• /
• 2012

본 논문은 brain-computer interface (BCI)를 통해 움직임 상상 시 측정된 뇌-활동전위신호(EEG)에 내포된 행동의도의 패턴을 보다 정확하게 분류하기 위한 최적 EEG 채널 선택 기법을 제안한다. 기존의 EEG 측정실험에서는 실험 설계자에 의해 대뇌 기능적 피질 분류를 이용하여 인위적으로 선별된 채널을 활용하거나 측정기기가 수용 가능한 전체 채널을 사용해왔으며, 일정 수준의 패턴분류 정확도를 얻을 수 있었지만 다수의 채널로 인해 Common Spatial Pattern (CSP) 등의 패턴특징 추출 시 overfit 및 계산 복잡도 증가의 문제가 발생되었다. 이를 극복하기 위하여 방안으로 본 논문에서는 binary particle swarm optimization (BPSO)을 기반으로 다수의 채널 중 최적 채널을 자동으로 선택하고, 각각의 채널에 대한 impact factor를 부여함으로써 중요 채널 부근의 채널들에 가중치를 부여하는 선택방법을 제안하였으며, Support Vector Machine (SVM)을 이용하여 다수의 채널을 사용 하였을 때의 정확도와 channel impact factor를 고려한 BPSO를 적용시켰을 때의 정확도를 비교, 분석하였다.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2002년도 춘계학술대회논문집
• /
• pp.592-597
• /
• 2002

The purpose of this study was to analyze the characteristics of a new heavy weight impactor, the Rubber Ball. Until now Bang-machine has been used to measure the heavy impact noise in accordance with JIS A 1418-1. However, various kinds of examination methods have been needed to make an objective observation of insulation capacity for floor impact noises. Two types of experiments were undertaken. First, the experiment about noise was carried out about an apartment building in actual living condition. Then. vibration noises from the impactors were analyzed. The results of this study were as follows : the result of experiment carried out with bonded area of bail was closer to practical experiment than that of non bonded area. In addition, the result about bonded area of ball was more similar to the result which is claimed by H. Tachibana than that about non bonded area. Moreover, it was found that Rubber Ball has more similar vibration characteristics to the real impact noise source than Bang-machine.