• 말소리와 음성과학
• /
• 제7권4호
• /
• pp.27-33
• /
• 2015

This paper proposes an audio event classification method using Deep Neural Networks (DNN). The proposed method applies Feed Forward Neural Network (FFNN) to generate event probabilities of ten audio events (dog barks, engine idling, and so on) for each frame. For each frame, mel scale filter bank features of its consecutive frames are used as the input vector of the FFNN. These event probabilities are accumulated for the events and the classification result is determined as the event with the highest accumulated probability. For the same dataset, the best accuracy of previous studies was reported as about 70% when the Support Vector Machine (SVM) was applied. The best accuracy of the proposed method achieves as 79.23% for the UrbanSound8K dataset when 80 mel scale filter bank features each from 7 consecutive frames (in total 560) were implemented as the input vector for the FFNN with two hidden layers and 2,000 neurons per hidden layer. In this configuration, the rectified linear unit was suggested as its activation function.

• 한국환경보건학회지
• /
• 제17권1호
• /
• pp.13-19
• /
• 1991

Interest in the studies of diesel exhaust emission has been increasing by the expected increase in the use of diesel powered automobiles out of concideration of fuel economy. It was well known that diesel exhaust emission was mutagenic in the bioassay as Ames test. The authors tried to find out the cytogenetic effect of diesel exhaust emission by the operational condition of engine such as speed and load. For the investigation of those effects, 66 male mice of ICR strain were used. The benzene-ethanol extracts of diesel exhaust emission were injected intra peritoneum 25rng/kg and 50mg/kg respectively. To evaluate the cytogenetic effect, mouse bone marrow micronucleus test was carried out. The frequency of micronucleus was different among the various groups according to the operational conditions of engine. The frequency of micronucleus in idling group was the highest of all the groups the subgroup of 50mg/kg showed the rate of 1.30%, 25rng/kg subgroup 0.55%. And the group of 2000rpm with 50% load showed the lowest rate of micronucleus appearance as 0.20% and 0.15%. In general, the frequency of micronucleus was shown higher in propotion to load and was shown inversely proportional to speed.

• 한국정밀공학회지
• /
• 제12권1호
• /
• pp.87-96
• /
• 1995

A new fungivle material named Epoxy-Granite composite is applied to the column structure of drilling center in order to investigate the advanced dynamic charateristics comparing with a conventional cast iron material. The dimensions of new column structure are adjusted to keep the same stiffness (EI value) and the manufacturing conditions are formulated based on the preceeding research experience about the development of Epoxy-Granite structural material. The two kinds of experiments are set up, one of which is for the measurement of natural mode and frequency using experimental modal analysis, and the other one is for the measurement of vibration amplitude during idling operation of a machine tool. The comparison of maximum accelerance values at each natural frequency of bending mode shows a Epoxy-Granite column have larger modal damping ratios(over 2times) than a cast iron column. The vibration amplitude of Epoxy-Granite column measrued on the bed, motor base, and top of column are also much smaller (up to 12%) than the case of cast iron column. It is therefore confirmed that a Epoxy-Granite material exhibits a good anti- vibrational propderty even if it is used under the actual operational environments of machine tool as a practical structural element.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2001년도 추계학술대회논문집B
• /
• pp.353-358
• /
• 2001

Turbo-charging or Super-charging has been used to boost engine power for Gasoline Engine and Diesel Engine came to the world at the beginning of $20^{th}$ century. So far Turbo-Charger has enjoyed a high reputation in the charging filed for its technical advantages such as no demand of operation power from engine and an excellent charging effect in the event of a static operation at mid- and high engine speed. A mechanically driven Super-Charger, however, is now emerging in order to meet demands of the age of speed such as high engine power for a quick change of the driving mode - high engine torque even at low engine speed. Since Super-Charger needs driving power from engine, it cannot improve its relatively higher fuel consumption against that of Turbo-Charger. This negative point is still an obstacle to the wide use of Super-Charger. Super-Charger using Screw-type compressor which has already had a considerable base in air compressor market will fulfill this purpose of improving fuel consumption by minimizing operation power owing to no charging at idling or partially loading driving. This study aims to develop power control concept to achieve this minimization of operation power.

• 제어로봇시스템학회논문지
• /
• 제3권1호
• /
• pp.101-108
• /
• 1997

The initial token value required to the optimal performance of discrete event systems can be decided by Sum of Delay Time and Synchronic Time ratio, which are new synchronic variables in Timed Place Petri Nets. For the system consisting of two Live-and-Bounded circuits(LB-circuits) fused in common Transition-Transition-Path or common Place-Place-Path, we prove that the Synchronic Time Ratio is the initial token ratio between two LB-circuits to optimally perform system functions. These results are generalized and formulated as a theorem. The initial tokens of a specific place can imply shared resources. Using the theorem, we can decide the minimum number of the shared resources to obtain the optimal performance, and minimize the idling time of resources. As an example, an automated assembly system is modeled by Timed Place Petri Net, and the initial tokens to achieve the optimal system performance are identified. All the values are verified by simulation.

• Journal of Communications and Networks
• /
• 제6권3호
• /
• pp.245-257
• /
• 2004

Driven by the growing number of the mobile subscribers, efficient channel resource management plays a key role for provisioning multimedia service in the next generation personal communication systems. To reuse limited channel resources, diminishing the coverage areas of cells seems to be the ultimate solution. Thus, however, causes more handover events. To provide seamless connection environment for mobile terminals and applications, this article presents a novel handover scheme called the intelligent channel reservation (ICR) scheme, which exploits the location prediction technologies to accurately reserve channel resources for handover connections. Considering the fact that each mobile terminal has its individual mobility characteristic, the ICR scheme utilizes a channel reserving notification procedure (CRNP) to collect adequate parameters for predicting the future location of individual mobile terminals. These parameters will be utilized by the handover prediction function to estimate the expected handover blocking rate and the expected number of idle channels. Based on the handover prediction estimations, a cost function for calculating the damages from blocking the handover connections and idling channel resources, and a corresponding algorithm for minimizing the cost function are proposed. In addition, a guard channel decision maker (GCDM) determines the appropriate number of guard channels. The experimental results show that the ICR scheme does reduce the handover-blocking rate while keeping the number of idle channels small.

• 한국소성가공학회:학술대회논문집
• /
• 한국소성가공학회 2002년도 금형가공 심포지엄
• /
• pp.180-186
• /
• 2002

The simulated die-casting process in which the traditional plaster casting process is combined with Rapid Prototyping technology is being used to produce Al, Mg, and Zn die-casting prototypes. Unlike in the die-casting process, molten metal in the conventional plaster casting process is fed via a gravity pour into a mold and the mold does not cool as quickly as a die-casting mold. The plaster castings have much larger and grosser grain structure as compared as the die-castings and the thin walls of the plaster mold cavity may not be completely fillet Because of lower mechanical properties induced by the large grain structure and incomplete Idling, the conventional plaster casting process is not suitable for the trial die-casting Process. In this work, an enhanced trial die-casting process has been developed in which molten metal in the plaster mold cavity is vibrated and pressurized simultaneously. Patterns for the casting are made by Rapid Prototyping technologies and then plaster molds, which have runner system, are made using these patterns. Imparted pressurized vibration to molten metal has made grain structure of castings much finer and improved fluidity of the molten metal enough to obtain complete filling at thin walls which can not be filled in the conventional plaster casting process.

• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 1995년도 춘계학술대회 논문집
• /
• pp.158-165
• /
• 1995

A new fungible materal named Epoxy-Granite composite is applied to the column structure of drilling center in order to investigate the advanced dynamic chatateristics comparing with a conventional cast iron material. The dimensions of new colum structure are adjusted to keep the same stiffness (El value) and the manufacturing conditions are formulated based on the preceeding research experience about the development of Epoxy-Granite structural material. The two kinds of experiments are set up. one of which is for the measurement of natural mode and frequency using experimental modal analysis and the other one is for the measurement of vibration amplitude during idling operation of a machine fool. The comparison of maximum, accelerance values at each natural frequency of bending mode shows a Epoxy-Granite column have larger modal damping ratios(over 2times) than a cast iron column. The vibration amplitude of Epoxy-Granite column measued on the bed motor base and top of column are also much smaller (up to 12%) than the case of cast iron column. It is therefore confirmed that a Epoxy-Granite materal exhibits a good anti-vibrational property even if it is used under the actual operational environments of machine eool as a practical structural element.

• 국제초고층학회논문집
• /
• 제2권4호
• /
• pp.331-340
• /
• 2013

The main topic of this paper is to show a possibility of indoor air quality enhancement and the fan energy savings in underground parking facilities by applying the demand-controlled ventilation (DCV) strategy based on the real-time variation of the traffic load. The established ventilation rate is estimated by considering the passing distance, CO emission rate, idling time of a vehicle, and the floor area of the parking facility. However, they are hard to be integrated into the real-time DCV control. As a solution to this problem, the minimum ventilation rate per a single vehicle is derived in this research based on the actual ventilation data acquired from several existing underground parking facilities. And then its applicability to the DCV based on the real-time variation of the traffic load is verified by simulating the real-time carbon monoxide concentration variation. The energy saving potentials of the proposed DCV strategy is also checked by comparing it with those for the current underground parking facility ventilation systems found in the open literature.

• 드라이브 ㆍ 컨트롤
• /
• 제11권4호
• /
• pp.53-60
• /
• 2014

This paper proposes a control scheme to reduce the power consumption of a variable displacement swash-plate type piston pump supplying oil to a valve-controlled hydraulic cylinder at constant pressure. Whenever flow rate demand was absent, the swash plate angle and the pump speed were changed to the minimum values required to compensate for the internal leakage flow. In response to command signals, the pump speed was changed in proportion to the absolute mean value of the speed component for position commands. At the same time, a pressure regulator was activated to maintain constant system pressure by precisely adjusting the pump speed with the swash plate angle fixed at the maximum. The conventional system consisting of a pressure-compensated variable displacement type pump is driven at a constant speed of 1,800rpm. By comparison, computer simulation and experimental results showed that idling power at stand-by status could be reduced by up to 70% by reducing the pump speed from 1,800rpm to 300rpm and the swash plate angle to the minimum.