• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.7 no.11
• /
• pp.2720-2736
• /
• 2013

Multi-view face detection has become an active area for research in the last few years. In this paper, a novel multi-view human face detection algorithm based on improved real Adaboost is presented. Real Adaboost algorithm is improved by weighted combination of weak classifiers and the approximately best combination coefficients are obtained. After that, we proved that the function of sample weight adjusting method and weak classifier training method is to guarantee the independence of weak classifiers. A coarse-to-fine hierarchical face detector combining the high efficiency of Haar feature with pose estimation phase based on our real Adaboost algorithm is proposed. This algorithm reduces training time cost greatly compared with classical real Adaboost algorithm. In addition, it speeds up strong classifier converging and reduces the number of weak classifiers. For frontal face detection, the experiments on MIT+CMU frontal face test set result a 96.4% correct rate with 528 false alarms; for multi-view face in real time test set result a 94.7 % correct rate. The experimental results verified the effectiveness of the proposed approach.

• Journal of Microbiology and Biotechnology
• /
• v.18 no.8
• /
• pp.1453-1458
• /
• 2008

For quantitative PCR assay of Salmonella enterica serovar Typhimurium in food samples, a real-time PCR method was developed, based on DNA genome equivalent. Specific primers and probe designed based on the STM4497 gene of S. Typhimurium LT2 showed the specificity to S. Typhimurium. Threshold cycle (Ct) values of real-time PCR were obtained from a quantitative standard curve with genomic DNA of Salmonella Typhimurium. In addition, the recovery of S. Typhimurium inoculated artificially to chicken samples with $4.5{\times}10^5$ to 4.5 CFU/ml was evaluated by using real-time PCR and plate-count methods. Result showed that the number of cells calculated from the real-time PCR method had good correlation with that of the plate-count method. This real-time PCR method could be applicable to the detection and quantification of S. Typhimurium in food samples.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.9 no.3
• /
• pp.25-32
• /
• 2006

Weapon systems composed of several subsystems execute various engagement missions in distributed combat environments in cooperation with a large number of subordinate/adjacent weapon systems as well as higher echelons through tactical data links. Such distributed weapon systems require distributed real-time simulation test beds to integrate and test their operational software, analyze their performance and effects of cooperated engagement, and validate their requirement specifications. These demands present significant challenges in terms of real-time constraints, time synchronization, complexity and development cost of an engagement simulation test bed, thus necessitate the use of high-performance distributed real-time simulation architectures, and modeling and simulation techniques. In this paper, in order to meet these demands, we presented a distributed real-time simulation system based on High Level Architecture(HLA) and Discrete Event System Specification(DEVS). We validated its performance by using it as a test bed for developing the Engagement Control System(ECS) of a surface-to-air missile system. The proposed technique can be employed to design a prototype or model of engagement-level distributed real-time simulation systems.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.35S no.1
• /
• pp.1-13
• /
• 1998

The next generation of wireless network will be problably developed as a mobile communications which will support ATM-based multiMedium traffic. We need to develop an dffective MAC protocol in order to support multimedia traffic having variety of QoS characteristics on wireless neteworks. In this paper, we propose a MAC protocol a MAC protocol where mobile terminals having cells to transmit, request slots to base station through requested slot then the base station analyze parameters from mobile and allocate slots to mobile according to priority. The multimedia slot allocation(MSA) protocol divides multimedias applications into real-time/ variant and non real-time services. Entire slots of the frameare partitioned proportionallyby sizeof bandwidth according to types of services, so that related services can use allocated-slots in priority. The proposed algorithm guarantees real time operation since real-time service share slots allocated for non real-real services. The algorithm whih divides slots of the frame is called as an Algorithm A, otherwise as an Algorithm B. The simulation compares by average delay time and cell loss probability between Algorithm and Algorithm B by increasing number of mobile terminal using the proposed MAC protocol. the simulation result for real-time services shows that average delay time and cell loss probability of Algorithm A is better than those of Algorithm B.

• Journal of Information Processing Systems
• /
• v.11 no.1
• /
• pp.39-56
• /
• 2015

Continuous multi-interval prediction (CMIP) is used to continuously predict the trend of a data stream based on various intervals simultaneously. The continuous integrated hierarchical temporal memory (CIHTM) network performs well in CMIP. However, it is not suitable for CMIP in real-time mode, especially when the number of prediction intervals is increased. In this paper, we propose a real-time integrated hierarchical temporal memory (RIHTM) network by introducing a new type of node, which is called a Zeta1FirstSpecializedQueueNode (ZFSQNode), for the real-time continuous multi-interval prediction (RCMIP) of data streams. The ZFSQNode is constructed by using a specialized circular queue (sQUEUE) together with the modules of original hierarchical temporal memory (HTM) nodes. By using a simple structure and the easy operation characteristics of the sQUEUE, entire prediction operations are integrated in the ZFSQNode. In particular, we employed only one ZFSQNode in each level of the RIHTM network during the prediction stage to generate different intervals of prediction results. The RIHTM network efficiently reduces the response time. Our performance evaluation showed that the RIHTM was satisfied to continuously predict the trend of data streams with multi-intervals in the real-time mode.

• International Journal of Control, Automation, and Systems
• /
• v.4 no.5
• /
• pp.601-614
• /
• 2006

In this paper, a study on task assignment strategies for a complex real-time network system is presented. Firstly, two task assignment strategies are proposed to improve previous strategies. The proposed strategies assign tasks with meeting end-to-end real-time constraints, and also with optimizing system utilization through period modulation of the tasks. Consequently, the strategies aim at the optimizationto optimize of system performance with while still meeting real-time constraints. The proposed task assignment strategies are devised using the genetic algorithmswith heuristic real-time constraints in the generation of new populations. The strategies are differentiated by the optimization method of the two objectives-meeting end-to-end real-time constraints and optimizing system utilization: the first one has sequential genetic algorithm routines for the objectives, and the second one has one multiple objective genetic algorithm routine to find a Pareto solution. Secondly, the performances of the proposed strategies and a well-known existing task assignment strategy using the BnB(Branch and Bound) optimization are compared with one other through some simulation tests. Through the comparison of the simulation results, the most adequate task assignment strategies are proposed for some as system requirements-: the optimization of system utilization, the maximization of running tasktasks, and the minimization of the number of network node nodesnumber for a network system.

• Korean Journal of Food Science and Technology
• /
• v.43 no.1
• /
• pp.119-123
• /
• 2011

In this study, performances of culture methods using two selective media and real-time PCR were evaluated for detection of Campylobacter jejuni (C. jejuni) in various food samples. Sausage, ground beef, and radish sprouts inoculated with C. jejuni were enriched in Hunt broth and then streaked onto modified cefoperazone charcoal deoxycholate agar and Preston agar, followed by incubation under microaerobic conditions. The enriched Hunt broth (1 mL) was used in real-time PCR assay. No statistical differences were observed in sensitivity among the two selective media and real-time PCR for sausage and ground beef. However, the number of positives by real-time PCR in radish sprouts was much higher than the two selective media (p<0.05). It appears that real-time PCR could be used as an effective screening tool to detect C. jejuni, particularly in foods with a high number of background microflora such as fresh vegetables.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.142-145
• /
• 2003

Many control applications using Neural Network need a priori information about the objective system. But it is impossible to get exact information about the objective system in real world. To solve this problem, several control methods were proposed. Reinforcement learning control using neural network is one of them. Basically reinforcement learning control doesn't need a priori information of objective system. This method uses reinforcement signal from interaction of objective system and environment and observable states of objective system as input data. But many methods take too much time to apply to real-world. So we focus on faster learning to apply reinforcement learning control to real-world. Two data types are used for reinforcement learning. One is reinforcement signal data. It has only two fixed scalar values that are assigned for each success and fail state. The other is observable state data. There are infinitive states in real-world system. So the number of observable state data is also infinitive. This requires too much learning time for applying to real-world. So we try to reduce the number of observable states by classification of states with Self-Organizing Map. We also use neural dynamic programming for controller design. An inverted pendulum on the cart system is simulated. Failure signal is used for reinforcement signal. The failure signal occurs when the pendulum angle or cart position deviate from the defined control range. The control objective is to maintain the balanced pole and centered cart. And four states that is, position and velocity of cart, angle and angular velocity of pole are used for state signal. Learning controller is composed of serial connection of Self-Organizing Map and two Multi-layer Feed-Forward Neural Networks.

• Proceedings of the KIEE Conference
• /
• 2005.05a
• /
• pp.215-217
• /
• 2005

There are two types of packet loss probabilities used in both the network layer and the physical layer within the wireless transmitter such as a queueing discard probability and transmission loss probability. We analyze these loss performances in order to guarantee Quality of Service (QoS) which is the basic of the future network. The queuing loss probability is caused by a maximum allowable delay time and the transmission loss probability is caused by a wireless channel error. These two types of packet loss probabilities are not easily analyzed due to recursive feedback which, originates as a result at a queueing delay and a number of retransmission attempts. We consider a wireless transmitter to a M/D/1 queueing model. We configurate the model to have a finite-size FIFO buffer in order to analyze the real-time traffic streams. Then we present the approaches used for evaluating the loss probabilities of this M/D/1/K queueing model. To analyze the two types of probabilities which have mutual feedbacks with each other, we drive the solutions recursively. The validity and accuracy of the analysis are confirmed by the computer simulation. From the following solutions, we suggest a minimum of 'a Maximum Allowable Delay Time' for real-time traffic in order to initially guarantee the QoS. Finally, we analyze the required service rate for each type utilizing real-time traffic and we apply our valuable analysis to a N-user's wireless network in order to get the fundamental information (types of supportable real-type traffics, types of supportable QoS, supportable maximum number of users) for network design.

• Journal of Institute of Control, Robotics and Systems
• /
• v.16 no.4
• /
• pp.403-410
• /
• 2010

The switched Ethernet has many features for real-time communications such as providing traffic isolation, large bandwidth, and full-duplex links, and so on. The switched Ethernet, however, cannot guarantee the timely delivery of a real-time message because message delay increases when collisions occurs at the output ports and message loss can even occur due to the overflow at the output buffer. Recently, many research efforts have been done to use the switched Ethernet as an industrial control network. In the industrial control network, sensors periodically sense the physical environment and transmit the sensed data to an actuator, and the periodic messages from sensors to actuators have typically real-time requirements such that those messages must be transmitted within their deadlines. This paper first suggests a feasible condition for EDF (Earliest Deadline First)-based scheduling of periodic messages on a synchronized switched Ethernet and a message scheduling algorithm which satisfies the proposed feasible condition. Pedreiras, et al. [10] suggested a feasible condition for message scheduling on the Ethernet (shared media Ethernet), but there has been no research result on the scheduling condition on the switched Ethernet until now. We compared the real-time message scheduling capacity between the Ethernet and the switched Ethernet by simulation. The simulation result shows that the message scheduling capacity of the Ethernet has almost remained constant as the number of nodes on the network increases, but, in the case of the switched Ethernet, the message scheduling capacity has increased linearly according to the number of nodes on the network.