• Journal of Korea Multimedia Society
• /
• v.25 no.6
• /
• pp.807-818
• /
• 2022

In order to further improve the accuracy and time efficiency of behavior recognition in intelligent monitoring scenarios, a human behavior recognition algorithm based on YOLO combined with LSTM and CNN is proposed. Using the real-time nature of YOLO target detection, firstly, the specific behavior in the surveillance video is detected in real time, and the depth feature extraction is performed after obtaining the target size, location and other information; Then, remove noise data from irrelevant areas in the image; Finally, combined with LSTM modeling and processing time series, the final behavior discrimination is made for the behavior action sequence in the surveillance video. Experiments in the MSR and KTH datasets show that the average recognition rate of each behavior reaches 98.42% and 96.6%, and the average recognition speed reaches 210ms and 220ms. The method in this paper has a good effect on the intelligence behavior recognition.

• 제어로봇시스템학회:학술대회논문집
• /
• 1991.10a
• /
• pp.332-336
• /
• 1991

Network management is responsible for gathering information on the usage of the network media by the network devices, ensuring the correct operation of the network, and providing reports. MAP network management must provide the high reliability of the media and signaling method, even in very harsh environments, providing a very low bit error rate and minimum number of retransmission. In this paper, we analysed the framework of OSI management and MAP network management and discussed the implementation method of fault management and remote management mechanism in the Mini-MAP controller developed for IBM-PC.

• Proceedings of the KSR Conference
• /
• 2008.06a
• /
• pp.2015-2020
• /
• 2008

Real-time communication network is important for KTX high speed train system because small problem can make a huge accident. Communication network for KTX high speed train system consists of IEEE 802.4 token bus network and FM0 encoding. The network device is developed by using MC68824 TBC, MC68185 TPM and MC68020 MPU. The network device make available to analysis of the network protocol among vehicles for Kyung-Boo high-speed train system.

• Journal of Biomedical Engineering Research
• /
• v.18 no.4
• /
• pp.381-388
• /
• 1997

In this paper, we present the design and implementation of the interbed network communication protocol, which links patient monitors, central stations, DB servers, and clinical workstations together in a patient monitoring system. We describe the requirements to be met thor real-time patient monitoring, propose 2 services Patient Locator Service(PL:7) and Remote Patient Monitoring Service( RPMS). PLS provides the information about how many patients are currently being monitored and where they are located, while RPMS allows the doctors to monitor their patients'vital sign in real-time. The messages for the services, their formats and exchange scheme are also presented with a whole picture of how they are implemented. We adopted the object-oriented programming paradigm in all the analysis and design processes. In the experiment performed in a real clinical setting, the services turned out to meet all the requirements needed for real-time patient monitoring.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.10 no.4
• /
• pp.7-15
• /
• 2010

Recently, there are many home network applications using the convergence between mobile platforms and home network system. As smart phones which are called small PC in the hand becoming popular, the development of home network application beyond the one of cellular phones is required. Android mobile platform of Google includes OS, middleware and primary applications. Also, in addition to smart phones, it can be mounted on various devices such as set-top box and household appliances. In this paper, home network services on smart phones of Android platform are designed and implemented. The services provide real-time monitoring information (temperature, humidity, real-time video) of rooms and appliance control in a house.

• Journal of Power System Engineering
• /
• v.12 no.6
• /
• pp.18-23
• /
• 2008

This paper describes development of real-time condition monitoring system to observe state of a container crane in a port. To analyze the state of a crane, the strength and the direction of wind are measured with sensors along with the load resulted a crane at the moment. The measured signals are processed by especially developed conditioning board and converted into digital data. Measured data are analyzed to define the state of the crane at an indicator. For transmission of these data to the indicator, we implemented wireless sensor network based on IEEE 802.15.4 MAC(Media Access Control) protocol and Bluetooth network protocol. To extend the networking distance between the indicator and sensor nodes, the shortest path routing algorithm was applied for WSN(Wireless Sensor Network) networks. The indicator sends the state information of the crane to monitoring server through IEEE 802.11 b wireless LAN(Local Area Network). Monitoring server decides whether alarm should be issued or not. The performance of developed WSN and Bluetooth network were evaluated and analyzed in terms of communication delay and throughput.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• v.2
• /
• pp.251-254
• /
• 2006

A precise real-time method of using the IGS ultra rapid products (IGU) and the GPS broadcast ephemeris to calculate the VRS orbit corrections was presented here which was suited for GPS/VRS reference station network based positioning. Test data acquired from both the SGRSN (Sichuan GPS Reference Station Network) and SCIGN (Southern California integrated GPS network) were used to evaluate the performance of the modeling techniques. The new method was proven to be more precise and reliable compared with the existing conventional network-based orbit error interpolation method. It was shown that 0.004ppm relative accuracy was reached, namely the influence from the orbit bias for the RTK positioning within 100km area can be of sub-millimeter level.

• ETRI Journal
• /
• v.29 no.6
• /
• pp.823-825
• /
• 2007

In this letter, we propose a novel algorithm to predict MPEG-coded real-time variable bit rate (VBR) video traffic. From the frame size measurement, the algorithm extracts the statistical property of video traffic and utilizes it for the prediction of the next frame for I-, P-, and B- frames. The simulation results conducted with real-world MPEG-4 VBR video traces show that the proposed algorithm is capable of providing more accurate prediction than those in the research literature.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.129.2-129
• /
• 2001

Visual effects are important cues for providing occupant s with virtual reality in a vehicle simulator which imitates real driving. The viewpoint of an occupant is sensitively dependent upon the occupant´s posture, therefore, the total body motion must be considered in a graphic simulator. A real time simulation is required for the dynamic analysis of complex human body motion. This study attempts to apply a neural network to the motion analysis in various driving situations. A full car of medium-sized vehicles was selected and modeled, and then analyzed using ADAMS in such driving conditions as bump-pass and acceleration. A multibody system analysis software, MADYMO, was used in the motion analysis of an adult male dummy in the seated position. Position data of the head were collected as inputs to the viewpoint movement. Based on these data, a back- propagation neural network was ...

• International Journal of Advanced Culture Technology
• /
• v.11 no.4
• /
• pp.464-469
• /
• 2023

As modern society develops, the number of diseases caused by bad smells is increasing. As it can harm people's health, it is important to predict in advance the extent to which bad smells may occur, inform the public about this, and take preventive measures. In this paper, we propose a hybrid neural network structure of CNN and LSTM that can be used to detect or predict the occurrence of odors, which are most required in manufacturing or real life, using odor complex sensors. In addition, the proposed learning model uses a complex odor sensor to receive four types of data, including hydrogen sulfide, ammonia, benzene, and toluene, in real time, and applies this data to the inference model to detect and predict the odor state. The proposed model evaluated the prediction accuracy of the training model through performance indicators based on accuracy, and the evaluation results showed an average performance of more than 94%.