• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.3
• /
• pp.1450-1463
• /
• 2019

The problem towards crowd behavior recognition in a serious clustered scene is extremely challenged on account of variable scales with non-uniformity. This paper aims to propose a crowed behavior classification framework based on a transferring hybrid network blending 3D res-net with inception-v3. First, the 3D res-inception network is presented so as to learn the augmented visual feature of UCF 101. Then the target dataset is applied to fine-tune the network parameters in an attempt to classify the behavior of densely crowded scenes. Finally, a transferred entropy function is used to calculate the probability of multiple labels in accordance with these features. Experimental results show that the proposed method could greatly improve the accuracy of crowd behavior recognition and enhance the accuracy of multiple label classification.

• Journal of Electrical Engineering and Technology
• /
• v.9 no.3
• /
• pp.893-898
• /
• 2014

Recently, the interior permanent synchronous motor (IPMSM) has been applied to an integrated starter and generator (ISG) for hybrid electric vehicles. In the design of such a motor, thermal analysis is necessary to maximize the power density because the loss is proportional to the power of a motor. Therefore, a cooling device as a heat sink is required internally. Generally, a cooling system designed with a water jacket structure is widely used for electric motors because it has advantages of simple structure and cooling effectiveness. An effective approach to analyze an electric machine with a water jacket is a thermal equivalent network. This network is composed of thermal resistance, a heat source, and thermal capacitance that consider the conduction, convection, and radiation. In particular, modeling of the cooling channel in a network is challenging owing to the flow of the coolant. In this paper, temperature prediction using a thermal equivalent network is performed in an ISG that has a water cooled system. Then, an experiment is conducted to verify the thermal equivalent network.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.3
• /
• pp.1030-1050
• /
• 2021

The edges with "bridge characteristic" play the role of connecting the communication between regions in power optical cable network. To solve the problem of mining edges with "bridge characteristic" in provincial power optical cable network, the complex power optical cable network model is constructed. Firstly, to measure the generated potential energy of all nodes in n-level neighborhood local structure for one edge, the n-level neighborhood local structure topological potential is designed. And the minimum connected chain attenuation is designed to measure the attenuation degree caused by substituted edges. On the basis of that, the minimum connected chain attenuation topological potential based measurement is designed. By using the designed measurement, a bridge-edges mining algorithm is proposed to mine edges with "bridge characteristic". The experiments are conducted on the physical topology of the power optical cable network in Jilin Province. Compared with that of other three typical methods, the network efficiency and connectivity of the proposed method are decreased by 3.58% and 28.79% on average respectively. And the proposed method can not only mine optical cable connection with typical "bridge characteristic" but also can mine optical cables without obvious characteristics of city or voltage, but it have "bridge characteristic" in the topology structure.

• 한국정보통신설비학회:학술대회논문집
• /
• 2009.08a
• /
• pp.115-116
• /
• 2009

Home-network gateway always powered on, while network data is not transferred. And the Power consumption of networked electric devices are greatly increased, to support higher speed data transfer. To reduce the power consumption of networked electric devices, some ideas were proposed. Such as ALR, Proxying, Subset-PHY. In this paper we propose a scheme to reduce power consumption of Home-Network Gateway. Proposed Home-network Gateway architecture consumes less than 1W in passive standby mode.

• Journal of Institute of Control, Robotics and Systems
• /
• v.22 no.2
• /
• pp.147-152
• /
• 2016

This paper proposes a new TPC (Transmission Priority Change) algorithm which is used to diagnose failures of a CAN (Controller Area Network) based network system for the oil tank monitoring. The TPC algorithm is aimed to increase the total amount of data transmission and to minimize the latency for an urgent message by changing transmission priority. The urgency of the data transmission has been determined by the conditions of sensors. There are multiple sensors inside of the oil tank, such as temperature, valve, pressure and level sensors. When the sensors operate normally, the sensory data can be collected through the CAN network by the monitoring system. However when there is a dangerous situation or failure situation happened at a sensor, the data need to be handled quickly by the monitoring system, which is implemented by using the TPC algorithm. The effectiveness of the TPC algorithm has been verified by the real experiments. In addition, this paper introduces a method that people can figure out the condition of oil tanks and also can perform the fault diagnosis in real-time by using transmitted packet data. By applying this TPC algorithm to various industries, the convenience and reliability of multiple sensors network system can be improved.

• Proceedings of the KIEE Conference
• /
• 2008.11a
• /
• pp.44-46
• /
• 2008

K-WAMS based on i-PIU as a synchro-phasor data acquisition device using GPS can treat a monitoring and evaluation of wide area power system to detect a various symptoms of wide area disturbances and prevent large blackout. This paper introduced the development of K-WAMS such like WAMS(Wide Area Monitoring System).

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.66 no.7
• /
• pp.1001-1006
• /
• 2017

In this study the NARX was proposed as a novel approach to forecast electric load more accurately. The NARX model is a recurrent dynamic network. ISO-NewEngland dataset was employed to evaluate and validate the proposed approach. Obtained results were compared with NAR network and some other popular statistical methods. This study showed that the proposed approach can be applied to forecast electric load and NARX has high potential to be utilized in modeling dynamic systems effectively.

• Proceedings of the Earthquake Engineering Society of Korea Conference
• /
• 2003.09a
• /
• pp.66-73
• /
• 2003

The technique for the seismic reliability evaluation of the electric power network is presented. In the previous study, the state of the substations was represented by the bi-state which is classified as failure or survival. However, the hi-state model can result in oversimplified analysis, because substations are worked by the parallel operating system. In this paper, Considering the characteristics of the parallel operating system, the damage of the substation is expressed by the multi-state for the more realistic seismic reliability evaluation. Using Monte-Carlo simulation method, the seismic reliability for Korean 345㎸ electric power network is evaluated. Analysis results show that reliability levels of the network by the multi-state analysis is higher than that by the hi-state analysis and the electric power network in southeastern area of the Korean Peninsular may be vulnerable to earthquakes.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.14 no.3
• /
• pp.65-73
• /
• 2015

This paper presents a method of predicting the machining parameters on the turning process of low carbon steel using a neural network with back propagation (BP) and particle swarm optimization (PSO). Cutting speed, feed rate, and depth of cut are used as input variables, while surface roughness and electric current consumption are used as output variables. The data from experiments are used to train the neural network that uses BP and PSO to update the weights in the neural network. After training, the neural network model is run using test data, and the results using BP and PSO are compared with each other.

• Proceedings of the KIEE Conference
• /
• 1999.07b
• /
• pp.1013-1016
• /
• 1999

In this paper, a real-time communication method using a PICNET-NP(Plant Instrumentation and Control Network for Nuclear Power plant) is proposed with an analysis of the control network requirements of DCS (Distributed Control System) in nuclear power plants. The method satisfies deadline in case of worst data traffics by considering aperiodic and periodic real-time data and others. In addition, the method was used to analyze the data characteristics of the DCS in existing nuclear power plant. The result shows that use of this method meets the response time requirement(100ms)