• Journal of the Semiconductor & Display Technology
• /
• v.17 no.1
• /
• pp.6-11
• /
• 2018

With the development of the Internet of Things technology, a system that ensures the self-adaptability of an environment that includes various IoT devices is attracting public attention. The rules for determining behavior rules in existing self-adaptation systems are based on the assumption of changes in system members and environment. However, in the IoT environment, flexibility is required to determine the behavior rules of various types of IoT devices that change in real time. In this paper, we propose a rule configuration in a self-adaptive system using SWRL based on OWL ontology. The self-adaptive system using the OWL - SWRL rule configuration has two advantages. The first is based on OWL ontology, so we can define the characteristics and behavior of various types of IoT devices as an integrated concept. The second is to define the concept of a rule as a specific language type, and to add, modify and delete a rule at any time as needed. Through the rule configuration in the adaptive system, we have shown that the rule defined in SWRL can provide flexibility and deeper concept expression function to adaptability to IoT environment.

• Journal of Communications and Networks
• /
• v.9 no.1
• /
• pp.18-27
• /
• 2007

The conventional normalized least mean square (NLMS) algorithm is the most widely used for adaptive identification within a non-stationary input context. The convergence of the NLMS algorithm is independent of environmental changes. However, its steady state performance is impaired during input sequences with low dynamics. In this paper, we propose a new NLMS algorithm which is, in the steady state, insensitive to the time variations of the input dynamics. The square soot (SR)-NLMS algorithm is based on a normalization of the LMS adaptive filter input by the Euclidean norm of the tap-input. The tap-input power of the SR-NLMS adaptive filter is then equal to one even during sequences with low dynamics. Therefore, the amplification of the observation noise power by the tap-input power is cancelled in the misadjustment time evolution. The harmful effect of the low dynamics input sequences, on the steady state performance of the LMS adaptive filter are then reduced. In addition, the square root normalized input is more stationary than the base input. Therefore, the robustness of LMS adaptive filter with respect to the input non stationarity is enhanced. A performance analysis of the first- and the second-order statistic behavior of the proposed SR-NLMS adaptive filter is carried out. In particular, an analytical expression of the step size ensuring stability and mean convergence is derived. In addition, the results of an experimental study demonstrating the good performance of the SR-NLMS algorithm are given. A comparison of these results with those obtained from a standard NLMS algorithm, is performed. It is shown that, within a non-stationary input context, the SR-NLMS algorithm exhibits better performance than the NLMS algorithm.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.4
• /
• pp.73-81
• /
• 2011

In this paper, an improved block-based background modeling technique using adaptive parameter estimation that judiciously adjusts the number of model histograms at each frame sequence is proposed. The conventional block-based background modeling method has a fixed number of background model histograms, resulting to false negatives when the image sequence has either rapid illumination changes or swiftly moving objects, and to false positives with motionless objects. In addition, the number of optimal model histogram that changes each type of input image must have found manually. We demonstrate the proposed method is promising through representative performance evaluations including the background modeling in an elevator environment that may have situations with rapid illumination changes, moving objects, and motionless objects.

• Journal of Korean Society for Geospatial Information Science
• /
• v.19 no.3
• /
• pp.49-56
• /
• 2011

Because urban areas change rapidly, it is necessary to reflect urban changes in a digital map database in a timely manner. To address these issues, LiDAR data was used to detect changes in urban area buildings. The purpose of this study is to detect object-based building change using LiDAR data and existing digital maps, and classify change types. In the study, we classified change type using overlay and shape comparison with building layer of the digital maps and point-based extracted building outline from the LiDAR data. When applying the overlay method, we were able to increase the accuracy and objectivity of the change detection process throughout an adaptive threshold applied to each object. In the experiments, it was demonstrated that classifying and detecting changes in urban areas using the proposed method can provide superior classification accuracy compared with the existing methodology.

• Journal of Sensor Science and Technology
• /
• v.19 no.5
• /
• pp.375-384
• /
• 2010

In this paper, we proposed a new shaft distortion correction system having an adaptive PID controller using displacement sensors, which is adaptively reflecting variations of shaft strength owing to irregular heat treatment during an annealing process and sensitivity to the seasonal temperature changes. Generally, the shafts are annealed by heat treatment in order to enlarge the strength of the shaft, which causes an distortion of a shaft such as irregular bending of the shaft. In order to correct such a distortion of the shaft, a mechanical pressure is properly impacted to the distorted shaft. However, the strength of every shaft is different from each other owing to irregular annealing and seasonal temperature changes. Especially, the strength of a thin shaft such as a car transmission shaft is much more sensitive than that of a thick shaft. Therefore, it is very important for considering the strength of each shaft during correction of the car transmission shaft distortion in order to generate proper mechanical pressure. The conventional PID controller for the shaft distortion correction system does not consider each different strength of each shaft, which causes low productivity. Therefore, we proposed a new PID controller considering variations of shaft strength caused by seasonal temperature changes as well as irregular heat treatment and different cooling time. Three displacement sensors are used to measure a degree of distortion of the shaft at three different location. The proposed PID controller generates adaptively different coefficients according to different strength of each shaft using appropriately obtained pressure times from long-term experiments. Consequently, the proposed shaft distortion correction system increases the productivity about 30 % more than the conventional correction system in the real factory.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.39B no.6
• /
• pp.341-349
• /
• 2014

Dynamic adaptive streaming over HTTP (DASH) is the most recent and promising technology to support high quality streaming services. In dynamic adaptive streaming over HTTP (DASH), a client consecutively estimates the available network bandwidth and decides the transmission rate for the forthcoming video chunks to be downloaded. In this paper, we propose a novel rate adaptation algorithm called quality of experience QoE-enhanced adaptation algorithm over DASH (QAAD), which preserves the minimum buffer length to avoid interruption and minimizes the video quality changes during the playback. We implemented a DASH test bed and conducted extensive experiments. Experimental results demonstrate that under fluctuating network conditions, QAAD provides seamless streaming with stabilized video quality while the previous buffer-aware algorithm (i.e., QDASH[9]) frequently changes the video quality and undergoes the interruption.

• Journal of KIISE
• /
• v.45 no.1
• /
• pp.86-93
• /
• 2018

When multiple clients share bandwidth and receive a streaming service, HTTP Adaptive Streaming has a problem in that the bandwidth is measured inaccurately due to the ON-OFF pattern of the segment request. To solve the problem caused by the ON-OFF pattern, the proposed PANDA (Probe AND Adapt) determines the quality of the segment to be requested while increasing the target bandwidth. However, since the target bandwidth is increased by a fixed amount, there is a problem in low bandwidth utilization and a slow response to changes in bandwidth. In this paper, we propose a video quality control scheme that improves the low bandwidth utilization and slow responsiveness of PANDA. The proposed scheme adjusts the amount of increase in the target bandwidth according to the bandwidth utilization after judging the bandwidth utilization by comparing the segment download time and the request interval. Experimental results show that the proposed scheme can fully utilize the bandwidth and can quickly respond to changes in bandwidth.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.8 no.3
• /
• pp.637-644
• /
• 2004

This paper proposed and implemented the adaptive transmission middleware for video streaming, which is able to support the adaptive transmission of video data to the fluctuating changes of network environment in the packet-based network and the properties of transmitted video data. The adaptive transmission middleware is made up SR-RTP-based transfer module and TFRC(TCP Friendly Rate Control)-based transfer-rate control module. The SR-RTP-based transfer module supports RTP-based real-time transfer of video data and packet retransmission scheme retransmitting the high-priority packets selectively in the damaged video data to reduce the error induced by the packet loss. Sharing the transmission bandwidth of network with the TCP-based data transfer, the TFRC-based transfer-rate control module controls the transfer rate of video data according to the most allowable transmission bandwidth in the network, so that the transfer rate is controlled adaptively to the fluctuating changes of transmission bandwidth. This paper, for the experiment, applied the adaptive transmission middleware to video streaming in the external Internet environment, and analyzed the effective frame transfer rate and the degree of the streaming jitter to evaluate the performance of packet-loss recovery and adaptive transfer rate control. In the external Internet environment where the packet-loss rate is high a bit, the relatively high streaming performance was showed compared with the case that didn't apply the adaptive transmission middleware.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.2
• /
• pp.155-160
• /
• 2014

There are many image processing based algorithms and applications that fail when illumination change occurs. Therefore, the illumination change has to be detected then the illumination change occurred images need to be enhanced in order to keep the appropriate algorithm processing in a reality. In this paper, a new method for detecting illumination changes efficiently in a real time by using local region information and fuzzy logic is introduced. The effective way for detecting illumination changes in lighting area and the edge of the area was selected to analyze the mean and variance of the histogram of each area and to reflect the changing trends on previous frame's mean and variance for each area of the histogram. The ways are used as an input. The changes of mean and variance make different patterns w hen illumination change occurs. Fuzzy rules were defined based on the patterns of the input for detecting illumination changes. Proposed method was tested with different dataset through the evaluation metrics; in particular, the specificity, recall and precision showed high rates. An automatic parameter selection method was proposed for contrast limited adaptive histogram equalization method by using entropy of image through adaptive neural fuzzy inference system. The results showed that the contrast of images could be enhanced. The proposed algorithm is robust to detect global illumination change, and it is also computationally efficient in real applications.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.7 no.2
• /
• pp.96-101
• /
• 2007

Neural networks are known as kinds of intelligent strategies since they have learning capability. There are various their applications from intelligent control fields; however, their applications have limits from the point that the stability of the intelligent control systems is not usually guaranteed. In this paper we propose an adaptive tracking control for robot manipulators using the radial basis function network (RBFN) that is e. kind of neural networks. Adaptation laws for parameters of the RBFN are developed based on the Lyapunov stability theory to guarantee the stability of the overall control scheme. Filtered tracking errors between actual outputs and desired outputs are discussed in the sense of the uniformly ultimately boundedness(UUB). Additionally, it is also shown that parameters of the RBFN are bounded. Experimental results for a SCARA-type robot manipulator show that the proposed adaptive tracking controller is adaptable to the environment changes and is more robust than the conventional PID controller and the neuro-controller based on the multilayer perceptron.