• 한국인공지능학회지
• /
• 제11권1호
• /
• pp.9-15
• /
• 2023

As mobile devices such as smartphones, tablets, and kiosks become increasingly prevalent, there is growing interest in developing alternative input systems in addition to traditional tools such as keyboards and mouses. Many people use their own bodies as a pointer to enter simple information on a mobile device. However, methods using the body have limitations due to psychological factors that make the contact method unstable, especially during a pandemic, and the risk of shoulder surfing attacks. To overcome these limitations, we propose a simple information input system that utilizes gaze-tracking technology to input passwords and control web surfing using only non-contact gaze. Our proposed system is designed to recognize information input when the user stares at a specific location on the screen in real-time, using intelligent gaze-tracking technology. We present an analysis of the relationship between the gaze input box, gaze time, and average input time, and report experimental results on the effects of varying the size of the gaze input box and gaze time required to achieve 100% accuracy in inputting information. Through this paper, we demonstrate the effectiveness of our system in mitigating the challenges of contact-based input methods, and providing a non-contact alternative that is both secure and convenient.

• 응용통계연구
• /
• 제33권5호
• /
• pp.603-614
• /
• 2020

본 연구는 이미지 데이터에 대한 예측 모형으로 뛰어난 성능을 보여온 convolutional neural networks (CNN) 모형을 이용하여 서울 아파트 가격의 예측과 서울 각 지역 아파트들의 가격결정요인들을 연구한다. 이를 위해 강, 녹지, 고도와 같은 자연환경요인, 버스정류장, 지하철역, 상권, 학교 등과 같은 기반시설요소, 일자리수, 범죄율 등의 사회경제요소들을 설명변수로 고려하고, CNN 모형이 이미지 데이터에 좋은 성능을 보여온 것을 기반으로 이 설명변수들의 값들을 CNN 모형 입력층으로써 이미지 채널의 픽셀값과 같은 역할을 하도록 변환하여 아파트 가격의 예측과 가격결정요인에 대한 해석을 시도한다. 덧붙여 본 연구에서 사용된 CNN 모형은 자연환경요인과 기반시설요인 변수들을 각 아파트를 중심으로 하는 각 입력층의 채널에 이진의 이미지로 표현함으로써 각 아파트의 공간적인 특성을 고려할 수 있다.

• 한국소성가공학회:학술대회논문집
• /
• 한국소성가공학회 2007년도 춘계학술대회 논문집
• /
• pp.285-288
• /
• 2007

The use of commercial finite element analysis software to perform the entire process analysis and springback analysis has increased fast for last decade. Pamstamp2G is one of commercial software to be used widely in the world but it has still not been perfected in the springback prediction accuracy. We must select the combination of input parameters for the highest springback prediction accuracy in Pamstamp2G because springback prediction accuracy is sensitive to input parameters. Then we study the affect of input parameters to use member part for acquiring high springback prediction accuracy in Pamstamp2G. First, we choose important four parameters which are adaptive mesh level at drawing stage and cam flange stage, Gauss integration point number through the thickness and cam offset on basis of experiment. Second, we make a orthogonal array table L82[(7)] which is consist of 8 cases to be combined 4 input parameters, compare to tryout result and select main factors after analyzing affect factors of input parameters by Taguchi's method in 6 sigma. Third, we simulate after changing more detail the conditions of parameters to have big affect. At last, we find the best combination of input parameters for the highest springback prediction accuracy in Pamstamp2G. The results of the study provide the selection of input parameters to Pamstamp2G users who want to Increase the springback prediction accuracy.

• 한국멀티미디어학회논문지
• /
• 제24권10호
• /
• pp.1414-1424
• /
• 2021

In this paper, the importance of input factors of a DNN (Deep Neural Network) PM_2.5 forecasting model using LRP(Layer-wise Relevance Propagation) is analyzed, and forecasting performance is improved. Input factor importance analysis is performed by dividing the learning data into time and PM_2.5 concentration. As a result, in the low concentration patterns, the importance of weather factors such as temperature, atmospheric pressure, and solar radiation is high, and in the high concentration patterns, the importance of air quality factors such as PM_2.5, CO, and NO₂ is high. As a result of analysis by time, the importance of the measurement factors is high in the case of the forecast for the day, and the importance of the forecast factors increases in the forecast for tomorrow and the day after tomorrow. In addition, date, temperature, humidity, and atmospheric pressure all show high importance regardless of time and concentration. Based on the importance of these factors, the LRP_DNN prediction model is developed. As a result, the ACC(accuracy) and POD(probability of detection) are improved by up to 5%, and the FAR(false alarm rate) is improved by up to 9% compared to the previous DNN model.

• 대한산업공학회지
• /
• 제39권5호
• /
• pp.361-366
• /
• 2013

Prediction of process parameters is very important in parameter design. If predictions are fairly accurate, the quality improvement process will be useful to save time and reduce cost. The concept of dual response approach based on response surface methodology has widely been investigated. Dual response approach may take advantages of optimization modeling for finding optimum setting of input factor by separately modeling mean and variance responses. This study proposes an alternative dual response approach based on machine learning techniques instead of statistical analysis tools. A hybrid neural network-genetic algorithm has been proposed for the purpose of parameter design. A neural network is first constructed to model the relationship between responses and input factors. Mean and variance responses correspond to output nodes while input factors are used for input nodes. Using empirical process data, process parameters can be predicted without performing real experimentations. A genetic algorithm is then applied to find the optimum settings of input factors, where the neural network is used to evaluate the mean and variance response. A drug formulation example from pharmaceutical industry has been studied to demonstrate the procedures and applicability of the proposed approach.

• Earthquakes and Structures
• /
• 제26권3호
• /
• pp.219-228
• /
• 2024

This study examines damping modification factors (DMFs) of elastic input energy spectra corresponding to a set of 116 earthquake ground motions. Mean input energy per mass spectra and mean DMFs are presented for both considered ground motion components. Damping ratios of 3%, 5%, 10%, 20%, and 30% are used and the 5% damping ratio is considered the benchmark for DMF computations. The geometric mean DMFs of the two horizontal components of each ground motion are computed and coefficients of variation are presented graphically. The results show that the input energy spectra-based DMFs exhibit a dependence on the damping ratio at very short periods and they tend to be nearly constant for larger periods. In addition, mean DMF variation is obtained graphically for also the damping ratio, and mathematical functions are fitted as a result of statistical analyses. A strong correlation between the computed DMFs and the ones from predicted equations is observed.

• 한국산업보건학회지
• /
• 제29권3호
• /
• pp.358-367
• /
• 2019

Objectives: This study aimed to review model algorithms and input parameters applied to some exposure models and to compare the simulated estimates using an exposure scenario from each model. Methods: A total of five exposure models which can estimate inhalation exposure were selected; the Korea Ministry of Environment(KMOE) exposure model, European Centre for Ecotoxicology and Toxicology of Chemicals Targeted Risk Assessment(ECETOC TRA), SprayExpo, and ConsExpo model. Algorithms and input parameters for exposure estimation were reviewed and the exposure scenario was used for comparing the modeled estimates. Results: Algorithms in each model commonly consist of the function combining physicochemical properties, use characteristics, user exposure factors, and environmental factors. The outputs including air concentration ($mg/m^3$) and inhaled dose(mg/kg/day) are estimated applying input parameters with the common factors to the algorithm. In particular, the input parameters needed to estimate are complicated among the models and models need more individual input parameters in addition to common factors. In case of CEM, it can be obtained more detailed exposure estimates separating user's breathing zone(near-field) and those at influencing zone(far-field) by two-box model. The modeled exposure estimates using the exposure scenario were similar between the models; they were ranged from 0.82 to $1.38mg/m^3$ for concentration and from 0.015 to 0.180 mg/kg/day for inhaled dose, respectively. Conclusions: Modeling technique can be used for a useful tool in the process of exposure assessment if the exposure data are scarce, but it is necessary to consider proper input parameters and exposure scenario which can affect the real exposure conditions.

• 한국안전학회지
• /
• 제26권4호
• /
• pp.96-101
• /
• 2011

In previous studies, a system was developed for classifying items of uninsured cost and for generating factors and formulas by item for calculating accident loss costs. However, the loss cost of stopped production was not considered when the system was being developed. In addition, the system which was developed in previous studies had problems such as input error and data collection, owing to numerous input items. Therefore, this study developed a Revised system which considers the loss cost of stopped production, and a Simple system for improving the problems in input errors and data collection. In this study, unquantifiable factors were not considered. Further study that takes these factors into consideration is necessary.

• 기술혁신학회지
• /
• 제2권2호
• /
• pp.249-265
• /
• 1999

This study examines the efficiency of engineering education using DEA(data envelopment analysis) which is often used in the efficiency evaluation of public services. We evaluate 27 mechanical engineering departments according to academy-basis, general basis, and employment-basis considering students' academic level and input costs as input factors. Our empirical results suggest that an evaluation method using DEA can give us useful informations such as benchmarks to improve education specialization where it is desirable, decisions about whether a department should expand its gross input or not, and proper directions about which input factors should be controlled and how much control is needed.

• Transactions on Electrical and Electronic Materials
• /
• 제10권5호
• /
• pp.156-160
• /
• 2009

In an ultrasonic motor, a piezoelectric ceramic material forms the active element which vibrates the stator, thus initiating the rotational motion. In the operation of ultrasonic motors, many factors exist that can affect the resonance characteristics of the piezoelectric ceramic component. For examples, these factors are the bonding conditions with the piezoelectric element, the magnitude of the input voltage, the normal force in the frictional drive and the emission of heat due to vibration and friction etc. Therefore, it is important to research properly the inclination for variation of piezoelectric ceramics in the circumstance where complex elements are involved. In this paper, we focus on the analysis of the resonance characteristics of an ultrasonic motor as a function of the magnitude of the input voltage and the normal force.