• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.05a
• /
• pp.536-539
• /
• 2018

In this paper, we propose a system that analyzes environment information by using deep learning and then provides a suitable environment for users by predicting environmental information change. As the level of living improves, interest in improving the quality of life is increasing. In particular, as the air quality deteriorated due to the recent occurrence of dust, smog, fine dust, and ultrafine dust, the indoor air quality as well as the outdoor air became a serious problem. The increase of indoor pollution due to the lack of ventilation and the use of chemicals is a serious problem for modern people who have a lot of indoor living. In order to solve this indoor air pollution, a system has been proposed that measures the state of air quality through sensors and maintains proper temperature and humidity. However, existing system has a difficulty to apply most of the atmospheric environment information to various users depending on sensors only. The system proposed in this paper predicts the indoor environment by analyzing the indoor pollution information collected through the sensor using the deep learning. Then, the predicted indoor environment is modeled and learned in this system, and the environment suitable for the user is suggested. Afterwards, the system receives feedback from the user and repeats the process of re-learning the proposed environment so that it can create the optimal environment for the user.

• The KIPS Transactions:PartB
• /
• v.9B no.1
• /
• pp.1-6
• /
• 2002

Many customers consult the Internet before making purchase goods and using contents. The systems in the Internet could store a lot of data and classify the data into information to get relationship between a company and customers. To do that, let's consider a knowledge-assisted hybrid system that utilizes individually a customer's preference to make an optimal solution in the his/her decision making. The knowledge made by using the preference is employed to select an domain set appropriate to him/her business, and the process of selecting definitely provides the customer some benefits: elimination of discomfort from unknown information and reduction of costs and search time for forming an suitable domain set. To effectively adopt individual customer's preference and actively adapt change of business situation, this study propose an architecture of the system which includes rule presentations and an inference engine, and integrates a knowledge-based component into a quadratic programming component. In the experimental results, it is found that a knowledge-assisted hybrid system implemented by this idea is more flexible than existing systems in extension of knowledge about an customer's preference and goes beyond the traditional models.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.19 no.2 s.72
• /
• pp.195-202
• /
• 2006

Thin-walled structures are efficiently utilized an automobiles, aircraft, satellite and ship as well as needed light weight simultaneously. This paper presents new shape of automobile hood reinforcement that rotating parts as engine, transmission are protected by thin-walled structures. The automobile hood is concerned about the resonance occurs due to the frequency of the rotating parts. The hood must be designed by supporting the stiffness of design loads and considering the natural frequencies. Hence, it is sustained the stiffness and considered the vibration by resonance. It is deep related to ride. Therefore, the topology, shape and size optimization methods are used to design the automobile hood. Topology technique is applied to determine the layout of a structural component optimum size with maximized natural frequency by volume reduction. In this research, The optimal structure layout of an inner reinforcement of an automobile hood for the natural frequency of a designated mode is obtained by using topology optimization method. The optimum size and the optimum shape are determined by PLBA(Pshenichny-Lim-Belegundu-Arora) algorithm.

• International Journal of Naval Architecture and Ocean Engineering
• /
• v.10 no.4
• /
• pp.491-498
• /
• 2018

The cost evaluation for voyage route planning in an ice-covered sea is one of the major topics among ship owners. Information of the ice properties, such as ice type, concentration of ice, ice thickness, strength of ice, and speed-power relation under ice conditions are important for determining the optimal route in ice and low operational cost perspective. To determine achievable speed at any designated pack ice condition, a model test of resistance, self-propulsion, and overload test in ice and ice-free water were carried out in a KRISO ice tank and towing tank. The available net thrust for ice and an estimation of the ice resistance under any pack ice condition were also performed by I-RES. The in-house code called 'I-RES', which is an ice resistance estimation tool that applies an empirical formula, was modified for the pack ice module in this study. Careful observations of underwater videos of the ice model test made it possible to understand the physical phenomena of underneath of the hull bottom surface and determine the coverage of buoyancy. The clearing resistance of ice can be calculated by subtracting the buoyance and open water resistance form the pre-sawn ice resistance. The model test results in pack ice were compared with the calculation results to obtain a correlation factor among the pack ice resistance, ice concentration, and ship speed. The resulting correlation factors were applied to the calculation results to determine the pack ice resistance under any pack ice condition. The pack ice resistance under the arbitrary pack ice condition could be estimated because software I-RES could control all the ice properties. The available net thrust in ice, which is the over thrust that overcomes the pack ice resistance, will change the speed of a ship according to the bollard pull test results and thruster characteristics (engine & propulsion combination). The attainable speed at a certain ice concentration of pack ice was determined using the interpolation method. This paper reports a procedure to determine the attainable speed in pack ice and the sample calculation using the Araon vessel was performed to confirm the entire process. A more detailed description of the determination of the attainable speed is described. The attainable speed in 1.0 m, 90% pack ice and 540 kPa strength was 13.3 knots.

• Journal of Advanced Marine Engineering and Technology
• /
• v.41 no.3
• /
• pp.202-208
• /
• 2017

The recently developed marine engines for propulsion of ships have higher torsional exciting force than previous engines to improve the propulsion efficiency and to reduce specific fuel oil consumption. As a result, a viscous damper or viscous-spring damper is installed in front of marine engine to control the torsional vibration. In the case of viscous damper, it is supposed that there is no elastic connection in the silicon oil, which is filled between the damper housing and inertia ring. However, In reality, the silicon oil with high viscosity possesses torsional stiffness and has non-linear dynamic characteristics according to the operating temperature and frequency of the viscous damper. In this study, the damping characteristics of a viscous damper used to control the torsional vibration of the shafting system have been reviewed and the characteristics of torsional vibration of the shafting system equipped with a corresponding viscous damper have been examined. In addition, it is examined how to interpret the theoretically optimal dynamic characteristics of a viscous damper for this purpose, and the optimum design for the propulsion shafting system has been suggested considering the operating temperature and aging. when the torsional vibration of the shafting system is controlled by a viscous damper filled with highly viscous silicon oil.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.10a
• /
• pp.481-484
• /
• 2013

Many people today are interested in Machine to Machine (M2M) as the new-generation growth engine of mobile communications service providers in Korea. Its use and application are broadening to various areas and the number of devices used for it is increasing to increase the number of information transmitted for each object. When the traffic reaches its limit while each set of data is transmitted from the devices divided into each group through the mobile network, M2M communications service might not be processed smoothly. This study used the Knapsack Problem algorithm to create a virtual simulator for a smooth M2M service when the mobile network used for the M2M communications reaches its limit. The virtual simulator applies smooth processing of services from the M2M communications that should be processed first to other subsequent services when data comes to each group of devices. As the M2M technology develops to make many objects more compact in size, it would help with smoother processing of M2M services for the mobile network with fast-increasing traffic.

• The Korean Journal of Malacology
• /
• v.26 no.2
• /
• pp.185-188
• /
• 2010

The Web-based the genus Haliotis SNP database was constructed on the basis of Intel Server Platform ZSS130 dual Xeon 3.2 GHz cpu and Linux-based (Cent OS) operating system. Haliotis related sequences (2,830 nucleotide sequences, 9,102 EST sequences) were downloaded through NCBI taxonomy browser. In order to eliminate vector sequences, we conducted vector masking step using cross match software with vector sequence database. In addition, poly-A tails were removed using Trimmest software from EMBOSS package. The processed sequences were clustered and assembled by TGICL package (TIGR tools) equipped with CAP3 software. A web-based interface (Haliotis SNP Database, http://www.haliotis.or.kr) was developed to enable optimal use of the clustered assemblies. The Clustering Res. menu shows the contig sequences from the clustering, the alignment results and sequences from each cluster. And also we can compare any sequences with Haliotis related sequences in BLAST menu. The search menu is equipped with its own search engine so that it is possible to search all of the information in the database using the name of a gene, accession number and/or species name. Taken together, the Web-based SNP database for Haliotis will be valuable to develop SNPs of Haliotis in the future.

• Journal of the Society of Naval Architects of Korea
• /
• v.34 no.1
• /
• pp.122-129
• /
• 1997

Thermo-elastic-plastic analyses used in solving plate forming process are often computationally expensive. To obtain an optimal process of line heating typically requires numerous iterations between the simulation and a finite element analysis. This process often becomes prohibitive due to the amount of computer time required for numerical simulation of line heating process. Therefore, a new techniques that could significantly reduce the computer time required to solve a complex analysis problem would be beneficial. In this paper, we considered factors that influence the bending effect by line heating and developed inference engine by using the concept of artificial neural network. To verify the validity of the neural network, we used results obtained from numerical analysis. We trained the neural network with the data made from numerical analysis and experiments varying the structure of neural network, in other words varying the number of hidden layers and the number of neurons in each hidden layers. From that we concluded that if the number of neurons in each hidden layers is large enough neural network having two hidden layers can be trained easily and errors between exact value and results obtained from trained network are not so large. Consequently, if there are enough number of training pairs, artificial neural network can infer similar results. Based on the numerical results, we applied the artificial neural network technique to deal with mechanical behavior of line heating at simulation stage effectively.

• Journal of Korean Society of Environmental Engineers
• /
• v.32 no.10
• /
• pp.957-964
• /
• 2010

The deactivated catalyzed diesel particulate filter-trap (DPF) was remanufactured by ultrasonic wave treatment with various prepared solutions, followed by active component re-impregnation, and the emission control performance and surface properties of remanufactured DPF were studied at various remanufacturing conditions. The proper ultrasonic wave cleaning time at various prepared solutions and optimal re-impregnation amounts of active component for the best emission control performance of DPF were investigated and its performance tests were also carried out with various temperatures for the conversions of CO, THC (total hydrocarbon) and PM (particulate matter) by catalytic reaction test unit using bypass gas from the diesel engine dynamo system. It was found that the emission control performance of DPF remanufactured with the high-temperature air washing, ultrasonic wave cleaning at acid/base solutions and active component re-impregnation method was recovered to 95% level of its activity compared to that of the fresh DPF, which was caused by removing the deactivating materials from the surface of the DPF, through the analyses of performance test and their surface characterization by Optical microscope, EDX, ICP, TGA, and porosimeter.

• Journal of Korean Society of Transportation
• /
• v.20 no.7
• /
• pp.177-183
• /
• 2002

Current state-of-the-art of VMS control is based upon simple knowledge-based inference engine with message set and each message's priority. And R&Ds of the VMS control are focused on the accurate detection and estimation of traffic condition of the subject roadways. However VMS display itself cannot achieve a desirable traffic allocation among alternative routes in the network In this context, VMS display strategy is the most crucial part in the VMS control. VMS itself has several limitations in its nature. It is generally known that VMS causes overreaction and concentration problems, which may be more serious in urban network than highway network because diversion should be more easily made in urban network. A feedback control algorithm is proposed in this paper to address the above-mentioned issues. It is generally true that feedback control approach requires low computational effort and is less sensitive to models inaccuracy and disturbance uncertainties. Major features of the proposed algorithm are as follows: Firstly, a regulator is designed to attain system optimal traffic allocation among alternative routes for each VMS in the network. Secondly, strategic messages should be prepared to realize the desirable traffic allocation, that is, output of the above regulator. VMS display strategy module is designed in this context. To evaluate Probable control benefit and to detect logical errors of the Proposed feedback algorithm, a offline simulation test is performed using real network in Daejon, Korea.