• Proceedings of the Korea Information Processing Society Conference
• /
• 2012.11a
• /
• pp.672-675
• /
• 2012

음성은 가장 익숙하고 편리한 의사 소통 수단으로 스마트폰과 같이 크기가 작은 모바일 기기의 입력 인터페이스로 적합하다. 서버 기반의 음성 인식은 서버를 방문하는 다양한 사용자들을 대상으로 음성 모델을 구축하기 때문에 음성 인식률을 높일 수 있고 상용화가 가능하다. 구글 음성인식, 아이폰의 시리(SiRi)가 대표적인 예이며 최근 스마트폰 사용자의 증가로 이에 대한 수요가 급증하고 있다. 서버 기반 음성 인식 기법에서 음성 인식은 스마트폰과 인터넷으로 연결되어 있는 원격지 서버에서 이루어진다. 따라서, 사용자는 스마트폰에 저장된 음성 데이터를 인터넷을 통하여 음성 인식 서버로 전달해야 된다[1, 2]. 음성 데이터는 사용자 고유 정보를 가지고 있으므로 개인 인증 및 식별을 위한 용도로 사용될 수 있으며 음성의 톤, 음성 신호의 피치, 빠르기 등을 통해서 사용자의 감정까지도 판단 할 수 있다[3]. 서버 기반 음성 인식에서 네트워크로 전송되는 사용자 음성 데이터는 제 3 자에게 쉽게 노출되기 때문에 화자의 신분 및 감정이 알려지게 되어 프라이버시 침해를 받게 된다. 본 논문에서는 화자의 프라이버시를 보호하기 위하여 사용자 음성 데이터로부터 개인의 고유 특징 및 현재 상태를 파악할 수 있는 감정 정보를 제거하는 기법을 설계 및 구현하였다.

• Structural Engineering and Mechanics
• /
• v.70 no.6
• /
• pp.671-681
• /
• 2019

This paper examines the applicability of artificial neural network (ANN) and multivariate adaptive regression splines (MARS) to predict the compressive strength of bacteria incorporated geopolymer concrete (GPC). The mix is composed of new bacterial strain, manufactured sand, ground granulated blast furnace slag, silica fume, metakaolin and fly ash. The concentration of sodium hydroxide (NaOH) is maintained at 8 Molar, sodium silicate ($Na_2SiO_3$) to NaOH weight ratio is 2.33 and the alkaline liquid to binder ratio of 0.35 and ambient curing temperature ($28^{\circ}C$) is maintained for all the mixtures. In ANN, back-propagation training technique was employed for updating the weights of each layer based on the error in the network output. Levenberg-Marquardt algorithm was used for feed-forward back-propagation. MARS model was developed by establishing a relationship between a set of predictors and dependent variables. MARS is based on a divide and conquers strategy partitioning the training data sets into separate regions; each gets its own regression line. Six models based on ANN and MARS were developed to predict the compressive strength of bacteria incorporated GPC for 1, 3, 7, 28, 56 and 90 days. About 70% of the total 84 data sets obtained from experiments were used for development of the models and remaining 30% data was utilized for testing. From the study, it is observed that the predicted values from the models are found to be in good agreement with the corresponding experimental values and the developed models are robust and reliable.

• Nuclear Engineering and Technology
• /
• v.51 no.3
• /
• pp.894-903
• /
• 2019

An approach for collapse risk assessment is proposed to evaluate the vulnerability of electric cabinet in nuclear power plants. The lognormal approaches, namely maximum likelihood estimation and linear regression, are introduced to establish the fragility curves. These two fragility analyses are applied for the numerical models of cabinets considering various boundary conditions, which are expressed by representing restrained and anchored models at the base. The models have been built and verified using the system identification (SI) technique. The fundamental frequency of the electric cabinet is sensitive because of many attached devices. To bypass this complex problem, the average spectral acceleration $S_{\bar{a}}$ in the range of period that cover the first mode period is chosen as an intensity measure on the fragility function. The nonlinear time history analyses for cabinet are conducted using a suite of 40 ground motions. The obtained curves with different approaches are compared, and the variability of risk assessment is evaluated for restrained and anchored models. The fragility curves obtained for anchored model are found to be closer each other, compared to the fragility curves for restrained model. It is also found that the support boundary conditions played a significant role in acceleration response of cabinet.

• Journal of the Mineralogical Society of Korea
• /
• v.32 no.1
• /
• pp.63-69
• /
• 2019

The oxidation states of structural Fe in minerals reflect the paleo-depositional redox conditions for the biologically or abiotically induced mineral formation. Particularly, nano-scale analysis using high-resolution transmission electron microscopy (HRTEM) and electron energy loss spectroscopy (EELS) is necessary to identify evidence for the microbial role in the biomineralization. HRTEM-EELS analysis of oxidation states of structural Fe and carbon bonding structure differentiate biological factors in mineralization by mapping the distribution of Fe(II)/Fe(III) and source of organic C. HRTEM-EELS technique provides geomicrobiologists with the direct nano-scale evidence of microbe-mineral interaction.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.33 no.6
• /
• pp.351-358
• /
• 2020

This paper presents a tuned mass damper (TMD) utilizing a parametric design technique to reduce the dynamic responses to seismic loads of retractable large spatial structures. An artificial intelligence algorithm was developed to automatically search for the installation position of the damping device. This enables confirming the dynamic response of the structure in real time while finding the optimum position for the damping device. Further, the optimum mass of the damping device is determined from among several alternatives, and a design that can be effectively applied to both open and closed conditions of the roof is obtained.

• Journal of Urban Science
• /
• v.9 no.2
• /
• pp.1-11
• /
• 2020

The purpose of this study was to assess needs for housing improvement of children group homes in Cheongju-si through interviews with the group home directors and staffs. From April 6, 2018, to April 25, 2018, a series of face-to-face interviews with four directors and three staffs working in four children group homes was conducted. The results were analyzed using thematic analysis technique. Highlights of major findings and implications were as follow: (1) Bedroom: Needs for independent bedrooms and desks for each child were dominant. (2) Common activity space: Interviewees showed somewhat different opinions on common activity spaces according to group home types and/or between directors and staffs. (3) Between "a big and good-quality house" and "a house in good location", interviewees were found to prefer "a big and good-quality house" in order for children to have enough space to run and play. (4) Interviewees insisted that to provide proper group home services and protection similar to a real family, current policy to accommodate up to eight children in one group home should be improved.

• Mass Spectrometry Letters
• /
• v.11 no.4
• /
• pp.118-124
• /
• 2020

An analytical method was developed for hypoxia-inducible factor (HIF) stabilizers based on QuEChERS (Quick, Easy, Cheap, Effective, Rugged, and Safe) sample preparation and liquid chromatography-high resolution mass spectrometry analysis. HIF stabilizers potentially enhance the performance of athletes, and hence, they have been prohibited. However, the analysis of urinary HIF stabilizers is not easy owing to their unique structure and characteristics. Hence, we developed the QuEChERS preparation technique for a complementary method and optimized the pH, volume of extraction solvent, and number of extractions. We found that double extraction with 1% of formic acid in acetonitrile provided the highest recovery of HIF stabilizers. Moreover, the composition of the mobile phase was also optimized for better separation of molidustat and IOX4. The developed method was validated in terms of its precision, detection limit, matrix effect, and recovery for ISO accreditation. To the best of our knowledge, this is the first demonstration of the application of the QuEChERS method, which is suitable as a complementary analytical method, in antidoping.

• Journal of the Korean institute of surface engineering
• /
• v.54 no.3
• /
• pp.133-138
• /
• 2021

Ternary Ti-X-N coatings, where X = Al, Si, Cr, O, etc., have been widely used for machining tools and cutting tools such as inserts, end-mills, and etc. Ti-Al-N-O coatings were deposited onto silicon wafer and WC-Co substrates by a cathodic arc evaporation (CAE) technique at various negative substrate bias voltages. In this study, the influence of substrate bias voltages during deposition on the microstructure and mechanical properties of Ti-Al-N-O coatings were systematically investigated to optimize the CAE deposition condition. Based on results from various analyses, the Ti-Al-N-O coatings prepared at substrate bias voltage of -80 V in the process exhibited excellent mechanical properties with a higher compressive residual stress. The Ti-Al-N-O (-80 V) coating exhibited the highest hardness around 30 GPa and elastic modulus around 303 GPa. The improvement of mechanical properties with optimized bias voltage of -80 V can be explained with the diminution of macroparticles, film densification and residual stress induced by ion bombardment effect. However, the increasing bias voltage above -80 V caused reduction in film deposition rate in the Ti-Al-N-O coatings due to re-sputtering and ion bombardment phenomenon.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.18 no.2
• /
• pp.9-16
• /
• 2022

The nodes constituting the vehicle ad hoc network (VANET) are vehicles moving along the road and road side units (RSUs) installed around the road. The vehicle ad hoc network is used to collect the status, speed, and location information of vehicles driving on the road, and to communicate with vehicles, vehicles, and RSUs. Today, as the number of vehicles continues to increase, urban roads are suffering from traffic jams, which cause various problems such as time, fuel, and the environment. In this paper, we propose a method to solve traffic congestion problems on urban roads and demonstrate that the method can be applied to solve traffic congestion problems through performance evaluation using two typical protocols of vehicle ad hoc networks, AODV and GPSR. The performance evaluation used ns-2 simulator, and the average number of traffic jams and the waiting time due to the average traffic congestion were measured. Through this, we demonstrate that the vehicle ad hoc-based traffic congestion management technique proposed in this paper can be applied to urban roads in smart cities.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.32 no.6
• /
• pp.1035-1043
• /
• 2022

With the spread of the Internet of Things (IoT), cloud computing, and big data, the need for high-speed encryption for applications is emerging. GPU optimization can be used to validate cryptographic analysis results or reduced versions theoretically obtained by the GPU in a reasonable time. In this paper, PIPO lightweight encryption implemented in various environments was implemented on GPU. Optimally implemented considering the brute force attack on PIPO. In particular, the optimization implementation applying the bit slicing technique and the GPU elements were used as much as possible. As a result, the implementation of the proposed method showed a throughput of about 19.5 billion per second in the RTX 3060 environment, achieving a throughput of about 122 times higher than that of the previous study.