• Journal of Sensor Science and Technology
• /
• v.33 no.3
• /
• pp.119-124
• /
• 2024

Effective fire sensing is important to protect lives and property from the disaster. In this paper, we present an intelligent visual sensing method for detecting fires based on machine learning techniques. The proposed method involves a two-step process. In the first step, fire and non-fire images are used to train a convolutional neural network (CNN), and in the next step, feature vectors consisting of 256 values obtained from the CNN are used for the learning of a support vector machine (SVM). Linear and nonlinear SVMs with different parameters are intensively tested. We found that the proposed hybrid method using an SVM with a linear kernel effectively increased the recall rate of fire image detection without compromising detection accuracy when an imbalanced dataset was used for learning. This is a major contribution of this study because recall is important, particularly in the sensing of disaster situations such as fires. In our experiments, the proposed system exhibited an accuracy of 96.9% and a recall rate of 92.9% for test image data.

• Journal of Information Management
• /
• v.37 no.1
• /
• pp.57-81
• /
• 2006

The new service of Korean public library, ASK_a service model suggests a new management practice in collaborative digital reference services. The model has three functions: input transaction, process transaction, and output transaction. The best form for input is the web form. The best form for process is a model with a hybrid type of public libraries(hierarchical and lateral type). The output suggests the archiving policy for gathering the query-answer data. The core of this model is providing an advanced information service to its users through cooperation with public libraries and external manpower.

• Journal of Sensor Science and Technology
• /
• v.15 no.5
• /
• pp.341-346
• /
• 2006

We have fabricated SOI CMOS active pixel image sensor with the pinned photodiode on handle wafer in order to reduce dark currents and improve spectral response. The structure of the active pixel image sensor is 4 transistors APS which consists of a reset and source follower transistor on seed wafer, and is comprised of the photodiode, transfer gate, and floating diffusion on handle wafer. The source of dark current caused by the interface traps located on the surface of a photodiode is able to be eliminated, as we apply the pinned photodiode. The source of dark currents between shallow trench isolation and the depletion region of a photodiode can be also eliminated by the planner process of the hybrid bulk/SOI structure. The photodiode could be optimized for better spectral response because the process of a photodiode on handle wafer is independent of that of transistors on seed wafer. The dark current was about 6 pA at 3.3 V of floating diffusion voltage in the case of transfer gate TX = 0 V and TX=3.3 V, respectively. The spectral response of the pinned photodiode was observed flat in the wavelength range from green to red.

• Transactions of Materials Processing
• /
• v.22 no.3
• /
• pp.133-142
• /
• 2013

Recently, electric vehicles and hybrid cars are being promoted as alternatives to reduce automobile emissions. Generally, thin sheet materials such as aluminum alloy AA300X and cold-rolled steel sheet such as JIS-G-3141 are used for the container for the lithium-ion secondary batteries. In this study, a multi-stage deep drawing process is used to produce a rectangular cup from thin stainless steel sheet material, SUS409L, with an initial blank thickness of 0.4mm for the battery container application. Numerical simulations of the first through the fifth stages for the multi-stage deep drawing with thin SUS409L sheet were conducted using LS-Dyna3D Implicit/Explicit. Special consideration was given to the deformation characteristics due to the normal anisotropy of the sheet material. The numerical simulations were conducted with both isotropic properties and the anisotropic properties of the initial blank material. An unexpected forming failure, barreling in the bottom region of the deep drawn rectangular cup, was observed. This failure mode can be avoided by additional ironing thickness control during the process.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.11 no.3
• /
• pp.116-121
• /
• 2012

In recent years, world is faced with a transportation energy dilemma, and the transportation is dependent on a single fuel - petroleum. However, Hybrid Electric Vehicle(HEV) technology holds more advantages to reduce the demand for petroleum in the transportation by efficiency improvements of petroleum consumption. Therefore, there is a trend that lower gear noise levels are demanded in HEV for drivers to avoid annoyance and fatigue during operation. And meshing transmission error(T.E.) is the excitation that leads to the tonal noise known as gear whine, and radiated gear whine is also the dominant source of noise in the whole gearbox. This paper presents a method for the analysis of gear tooth profile and lead modification, and the predictions of transmission error and load distribution are shown under one loaded torque for the 1st gear pair of HEV gearbox. The test is also obtained before tooth micro-modification under the torque. At last, the appropriate tooth modification is used to minimize the transmission error and load distribution under the loaded torque. It is a good approach which the simulated result is used to improve the design in order to minimize the radiation gear whine noise.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.11 no.5
• /
• pp.1-7
• /
• 2012

The transportation is almost dependent on a single fuel petroleum with transportation energy dilemma. Hybrid Electric Vehicle(HEV) technology holds more advantages on efficiency improvements for petroleum consumption at the transportation. And bearing is recognized as the important component of gearbox. Gearboxes for HEV transmission have been ensured the highest reliability over some years in withstanding high dynamic loads. At the same time, the demands of lightweight design and cost minimization are required by thought-out design, high-quality material, superior production quality and maintenance. In order to design a reliable and lightweight gearbox, it is necessary to analyze bearing rating life methods between standard and different bearing companies with calculation methods for modification factors. In this paper, the influence of life time of bearings will be pointed out. Bearing contact stress and load stress distribution of HEV gearbox are obtained and compared with Romaxdesigner and BearinX. And the unequal wear of the left bearing for the gearbox intermediate shaft is investigated between simulation and test.

• Carbon letters
• /
• v.16 no.4
• /
• pp.247-254
• /
• 2015

To improve photocatalytic efficiency, graphene/Ag/TiO₂ nanotube catalyst was synthesized, and its surface characteristics and photocatalytic activity investigated. For deposition of Ag nanoparticles on the TiO₂ nanotubes, a polymer compound containing CH₃COOAg/poly(L-lactide) was utilized, and the silver particles were precipitated by reducing the silver ions during the annealing process. Graphene deposition on the Ag/TiO₂ nanotubes was achieved using an electrophoretic deposition process. Based on the dye degradation results, it was determined that the photocatalytic efficiency was significantly affected by deposition of silver particles and graphene on the TiO₂ catalyst. Highly efficient destruction of the dye was obtained with the new graphene/Ag/TiO₂ nanotube photocatalyst. This may be attributed to a synergistic effect of the graphene and Ag nanoparticles on the TiO₂ nanotubes.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.11 no.4
• /
• pp.25-30
• /
• 2012

The transportation is almost dependent on a single fuel petroleum with transportation energy dilemma. Hybrid Electric Vehicle(HEV) technology holds more advantages on efficiency improvements for petroleum consumption at the transportation. And bearing is recognized as the important component of gearbox. Gearboxes for HEV transmission have been ensured the highest reliability over some years in withstanding high dynamic loads. At the same time, the demands of lightweight design and cost minimization are required by thought-out design, high-quality material, superior production quality and maintenance. In order to design a reliable and lightweight gearbox, it is necessary to analyze bearing rating life methods between standard and different bearing companies with calculation methods for modification factors. In this paper, the influence of life time of bearings will be pointed out. Bearing contact stress and load stress distribution of HEV gearbox are obtained and compared with Romaxdesigner and BearinX. And the unequal wear of the left bearing for the gearbox intermediate shaft is investigated between simulation and test.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.16 no.4
• /
• pp.97-103
• /
• 2017

The objective of this study is to develop and commercialize an on-board fuel storage system for CNG vehicles. A type 4 vessel is made of resin-impregnated continuous filament windings on a polyamide (PA6) liner. In particular, this study localized the PA6 liner's fabrication and development. To analyze the filament winding, a specimen test was performed, and the results were verified values obtained using finite element analysis. In this study, the filament winding and fibers were optimized for a 207 bar composite cylinder in a compressed natural gas vehicle.

• Transactions of Materials Processing
• /
• v.4 no.4
• /
• pp.375-389
• /
• 1995

In H shape rolling, accurate predictions of deformation and temperature distribution in a billet are quite important because they are the main factors in determining roll calibers and roll pass schedules. Many researches have been performed to achieve the predictions, but most of them are limited to single pass or isothermal assumptions. In the present investigation, it is attempted to develop a method to predict the deformation and temperature distributions which is applicable to a complete rolling process that usually consists of several rollings under different rolls for a period of time. The method works by coupling two analyses : one is an approximate analysis for temperature distribution prediction and the other is the slab-FEM hybrid analysis for deformation prediction. The method is applied to analyze a "H" shape rolling process consisting of nine passes under four different rolls. In the present paper, basic ideas of the method are presented. Also, shapes of cross sections, strain and temperature distributions, roll separating force and roll torque predicted by the method are discussed.