• 한국융합학회논문지
• /
• 제10권6호
• /
• pp.235-242
• /
• 2019

최근 딥러닝을 비롯한 인공지능 기술의 활용이 다양한 분야에서 활발해지고 있으며, 특히 딥러닝 기술 기반의 객체 인식 및 검출에 뛰어난 성능을 보이는 여러 알고리즘들이 발표되고 있다. 이에 본 논문에서는 사용자의 편의성이 효과적으로 반영된 모바일 헬스케어 애플리케이션 구현에 대한 적절한 방향성을 제시하고자 한다. 기존의 피트니스 애플리케이션들에 대한 이용 만족도 연구 및 모바일 헬스케어 애플리케이션에 대한 현황을 파악하여, 이로부터 피트니스 애플리케이션 시장에서의 생존과 우위를 확보하는 동시에, 최근 주목 받고 있는 인공지능 기술의 효과적인 적용에 의한 성능 개선을 통해 기존 이용자 유지 및 확대를 도모하고자 한다.

• 전력전자학회논문지
• /
• 제26권1호
• /
• pp.1-8
• /
• 2021

For the safe and reliable operation of lithium-ion batteries in electric vehicles or energy storage systems, having accurate information of the battery, such as the state of charge (SOC), is essential. Many different techniques of battery SOC estimation have been developed, such as the Kalman filter. However, when this filter is applied to multiple batteries, it has difficulty maintaining the accuracy of the estimation over all cells owing to the difference in parameter values of each cell. The difference in the parameter of each cell may increase as the operation time accumulates due to aging. In this paper, a novel deep neural network (DNN)-based SOC estimation method for multi-cell application is proposed. In the proposed method, DNN is implemented to determine the nonlinear relationships of the voltage and current at different SOCs and temperatures. In the training, the voltage and current data obtained at different temperatures during charge/discharge cycles are used. After the comprehensive training with the data obtained from the cycle test with a cell, the resulting algorithm is applied to estimate the SOC of other cells. Experimental results show that the mean absolute error of the estimation is 1.213% at 25℃ with the proposed DNN-based SOC estimation method.

• Advances in nano research
• /
• 제13권3호
• /
• pp.297-312
• /
• 2022

Coughing and breath shortness are common symptoms of nano (small) cell lung cancer. Smoking is main factor in causing such cancers. The cancer cells form on the soft tissues of lung. Deformation behavior and wave vibration of lung affected when cancer cells exist. Therefore, in the current work, phase velocity behavior of the small cell lung cancer as a main part of the body via an exact size-dependent theory is presented. Regarding this problem, displacement fields of small cell lung cancer are obtained using first-order shear deformation theory with five parameters. Besides, the size-dependent small cell lung cancer is modeled via nonlocal stress/strain gradient theory (NSGT). An analytical method is applied for solving the governing equations of the small cell lung cancer structure. The novelty of the current study is the consideration of the five-parameter of displacement for curved panel, and porosity as well as NSGT are employed and solved using the analytical method. For more verification, the outcomes of this reports are compared with the predictions of deep neural network (DNN) with adaptive optimization method. A thorough parametric investigation is conducted on the effect of NSGT parameters, porosity and geometry on the phase velocity behavior of the small cell lung cancer structure.

• 한국콘크리트학회:학술대회논문집
• /
• 한국콘크리트학회 2003년도 가을 학술발표회 논문집
• /
• pp.380-383
• /
• 2003

Deep pile caps usually contain no transverse shear reinforcement and only small percentages of longitudinal reinforcement. The current design procedures including ACI 318-02 for the pile caps do not provide engineers with a clear understanding of the physical behavior of deep pile caps. In this study, the failure strengths of nine pile cap specimens tested to failure were evaluated using 3-dimensional strut-tie models. The analysis results obtained from the present study were compared with those obtained from several design methods, and the validity of the present method implementing 3-dimensional strut-tie models was examined.

• 한국해안해양공학회:학술대회논문집
• /
• 한국해안해양공학회 1995년도 정기학술강연회 발표논문 초록집
• /
• pp.16-19
• /
• 1995

Effects of the changes in bottom topography and non-linearity of the western boundary current on the separation position of the Tsushima Warm Current(TWC) are investigated using a primitive equation model in a simplified model domain which consists of a deep ocean, a continental shelf and a marginal sea(Fig. 1). (omitted)

• ETRI Journal
• /
• 제32권2호
• /
• pp.339-341
• /
• 2010

The fundamental transverse mode lasing of a hybrid laser diode is a prerequisite for efficient coupling to a single-mode silicon waveguide, which is necessary for a wavelength-division multiplexing silicon interconnection. We investigate the lasing mode profile for a hybrid laser diode consisting of silicon slab and InP/InGaAsP deep ridge waveguides. When the thickness of the top silicon is 220 nm, the fundamental transverse mode is lasing in spite of the wide waveguide width of $3.7{\mu}m$. The threshold current is 40 mA, and the maximum output power is 5 mW under CW current operation. In the case of a thick top silicon layer (1 ${\mu}m$), the higher modes are lasing. There is no significant difference in the thermal resistance of the two devices.

• 한국항해항만학회:학술대회논문집
• /
• 한국항해항만학회 2000년도 추계학술대회논문집
• /
• pp.17-20
• /
• 2000

This study is about a retrograde triple well employed in the Cell tr. of next DRAM and flash memory. triple well structure is formed deep n-well under the light p-well using MeV ion implantation. MeV P implanted deep n-well was observed to show greatly improved characteristics of electrical isolation and soft error. Junction leakage current, however, showed a critical behavior as a function of implantation and annealing conditions. {311} defects were observed to be responsible for the leakage current. {311} defects were generated near the R$\sub$p/ (projected range) region and grown upward to the surface during annealing. This is study on the defect behavior in device region as a function of implantation and annealing conditions.

• 한국전기전자재료학회:학술대회논문집
• /
• 한국전기전자재료학회 2000년도 추계학술대회 논문집
• /
• pp.17-20
• /
• 2000

This study is about a retrograde triple well employed in the Cell tr. of next DRAM and flash memory. Triple well structure is formed deep n-well under the light p-well using MeV ion implantation. MeV P implanted deep n-well was observed to show greatly improved characteristics of electrical isolation and soft error. Junction leakage current, however, showed a critical behavior as a function of implantation and annealing conditions. {311} defects were observed to be responsible for the leakage current. {311} defects were generated near the R$\_$p/ (Projected range) region and grown upward to the surface during annealing. This is study on the defect behavior in device region as a function of implantation and annealing conditions.

• KIEE International Transaction on Electrical Machinery and Energy Conversion Systems
• /
• 제4B권3호
• /
• pp.108-113
• /
• 2004

This paper presents methods to improve performance of the power supply system in a NASA deep space explorer. In the Stirling engine driven reciprocating Brushless DC (BLDC) generator, the accurate position information of the prime mover is important to diagnose the performance of the engine and prevent distortion of the output power. Since sensors to detect the position are fragile and unreliable, and conventional sensorless techniques have drawbacks in the low speed region, a novel sensorless position detection technique for the prime mover has been proposed and verified. Another major issue of the generator for the spacecraft is power density maximization. The mass of the power system is important to the mass of the satellite. Therefore, the components of the spacecraft should be lightweight. Conventional rectification methods cannot achieve the maximum power possible due to non-optimal current waveforms. The optimal current waveform for maximizing power density and minimizing machine size and weight in a nonsinusoidal power supply system has been derived, incorporated in a control system, and verified by simulation work.

• 대한조선학회논문집
• /
• 제41권3호
• /
• pp.28-34
• /
• 2004

This paper presents the results of the structural analysis and optimal design of the ROV to be operated at 6000m depth in the ocean. This will be the first domestic deep-sea ROV operating with an AUV and a launcher equipped with robot arms and the current weight is about 3 ton. initial optimal dimension of the frame is determined based on the stress analysis using FEA code ANSYS and design sensitivity and optimization results. The current design is the initial design and there is a possibility to change the design according to the modification of material, equipments and array of structure.