• Journal of Korea Multimedia Society
• /
• v.25 no.4
• /
• pp.583-599
• /
• 2022

Although the object detection accuracy with a single image has been significantly improved with the advance of deep learning techniques, the detection accuracy for pig monitoring is challenged by occlusion problems due to a complex structure of a pig room such as food facility. These detection difficulties with a single image can be mitigated by using a video data. In this research, we propose a method in pig detection for video monitoring environment with a static camera. That is, by using both image processing and deep learning techniques, we can recognize a complex structure of a pig room and this information of the pig room can be utilized for improving the detection accuracy of pigs in the monitored pig room. Furthermore, we reduce the execution time overhead by applying a pruning technique for real-time video monitoring on an embedded board. Based on the experiment results with a video data set obtained from a commercial pig farm, we confirmed that the pigs could be detected more accurately in real-time, even on an embedded board.

• The Journal of the Korea Contents Association
• /
• v.10 no.3
• /
• pp.53-63
• /
• 2010

Recently, various monitoring systems are implemented actively by using wireless sensor networks(WSN). When implementing WSN-based monitoring system, there are three important issues to consider. At First, we need to consider a sensor node failure detection method to support the ongoing monitoring. Secondly, because sensor nodes use limited battery power, we need an efficient data filtering method to reduce energy consumption. At Last, a reducing processing overhead method is necessary. The existing Kalman filtering scheme has good performance on data filtering, but it causes too much processing overhead to estimate sensed data. To solve these problems, we, in this paper, propose a new data filtering scheme based on data statical analysis. First, the proposed scheme periodically aggregates node survival massages to support a node failure detection. Secondly, to reduce energy consumption, it sends the sample data with a node survival massage and do data filtering based on those messages. Finally, it analyzes the sample data to estimate filtering range in a server. As a result, each sensor node can use only simple compare operation for filtering data. In addition, we show from our performance analysis that the proposed scheme outperforms the Kalman filtering scheme in terms of the number of sending messages.

• Journal of the Institute of Convergence Signal Processing
• /
• v.10 no.3
• /
• pp.207-213
• /
• 2009

The quality of tap water on the whole water-supply system, from a large filtration plant to a private faucet, has to be guaranteed the standards of drinking water. At this point in time, however, the supply process of the tap water has not been monitored and managed scientifically. The piped water, especially the most small-scale reservoirs(underground or overhead type) are always exposed to various contaminations and impurities. Recently monitoring systems of water-quality were spread on some large filtration plants or distributing reservoirs. In particular, the water quality monitoring method using the internet is adopted into some local government whose inhabitants can check up the water quality anytime and anywhere. The construction of this system that has to apply a large scale needs, and has a limitation on the small water-supply system, such as apartments, public facilities and small-scale underground or overhead reservoirs. In this work, we suggest the integration system of individual water-quality sensor modules that have a low price. By using the developed integration system and online monitoring program operated on the internet, the system managers of reservoirs can monitor and manage water-quality characteristic values of drinking water in online. Since the proposed system was modularized, the system can be applied easily into various reservoirs with a low cost and regardless of its scale, small or large.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2008.04c
• /
• pp.98-102
• /
• 2008

Methods and analysis of a simple wireless sensor concept for detecting and locating faults as well as for load monitoring are presented. The concept is based on distributed wireless sensors that are attached to the incoming and outgoing power lines of secondary substations. A sensor measures only phase current characteristics of the wire it is attached to, is not synchronized to other sensors and does not need configuration of triggering levels. The main novelty of the concept is in detecting and locating faults by combining power distribution network characteristics on system level with low power sampling methods for individual sensors. This concept enables the sensor design to be simple, energy efficient and thus applicable in new installations and for retrofit purposes in both overhead and underground electrical distribution systems.

• ETRI Journal
• /
• v.23 no.2
• /
• pp.77-84
• /
• 2001

The detection of open defects in CMOS SRAM has been a time consuming process. This paper proposes a new dynamic power supply current testing method to detect open defects in CMOS SRAM cells. By monitoring a dynamic current pulse during a transition write operation or a read operation, open defects can be detected. In order to measure the dynamic power supply current pulse, a current monitoring circuit with low hardware overhead is developed. Using the sensor, the new testing method does not require any additional test sequence. The results show that the new test method is very efficient compared with other testing methods. Therefore, the new testing method is very attractive.

• Proceedings of the KSR Conference
• /
• 2010.06a
• /
• pp.1918-1923
• /
• 2010

In electic railway, 25kV is applied to AC sections of overhead contact lines and pantographs of Korea Train eXpress(KTX) make contact at speeds of 300km/h. Thus, there is a need to utilize wireless, optic, contact-less sensors to implement condition monitoring systems. This paper is based on describing and analyzing the condition monitoring system implementation technologies for efficient catenary current ratio characteristic assessment. The conclusion of this paper should be widely applied to design, diagnosis, completion of construction, current collection status, fault diagnosis, and selection of contact wires and suspension wires.

• JSTS:Journal of Semiconductor Technology and Science
• /
• v.13 no.1
• /
• pp.71-78
• /
• 2013

In highly reliable and durable systems, failures due to aging might result in catastrophes. Aging monitoring techniques to prevent catastrophes by predicting such a failure are required. Aging can be monitored by performing a delay test at faster clocks than functional clock in field and checking the current delay state from the test clock frequencies at which the delay test is passed or failed. In this paper, we focus on test clock control scheme for a system-on-chip (SoC) with multiple clock domains. We describe limitations of existing at-speed test clock control methods and present an on-chip faster-than-at-speed test clock control scheme for intra/inter-clock domain test. Experimental results show our simulation results and area analysis. With a simple control scheme, with low area overhead, and without any modification of scan architecture, the proposed method enables faster-than-at-speed test of SoCs with multiple clock domains.

• The Journal of Korean Institute of Next Generation Computing
• /
• v.15 no.1
• /
• pp.86-98
• /
• 2019

Recently, the trend of building container-based PaaS (Platform-as-a-Service) is expanding. Container-based platform technology has been a core technology for realizing a PaaS. Containers have lower operating overhead than virtual machines, so hundreds or thousands of containers can be run on a single physical machine. However, recording and monitoring the storage logs for a large number of containers running in cloud computing environment occurs significant overhead. This work has identified two problems that occur when detecting a file system change event of a container running in a cloud computing environment. This work also proposes a system for container file system event detection in the environment by solving the problem. In the performance evaluation, this work performed three experiments on the performance of the proposed system. It has been experimentally proved that the proposed monitoring system has only a very small effect on the CPU, memory read and write, and disk read and write speeds of the container.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.8
• /
• pp.3888-3910
• /
• 2018

As an increasing number of defense methods against control-data attacks are deployed in practice, control-data attacks have become challenging, and non-control-data attacks are on the rise. However, defense methods against non-control-data attacks are still deficient even though these attacks can produce damage as significant as that of control-data attacks. We present a method to defend against non-control-data attacks using influence domain monitoring (IDM). A definition of the data influence domain is first proposed to describe the characteristics of a variable during its life cycle. IDM extracts security-critical non-control data from the target program and then instruments the target for monitoring these variables' influence domains to ensure that corrupted variables will not be used as the attackers intend. Therefore, attackers may be able to modify the value of one security-critical variable by exploiting certain memory corruption vulnerabilities, but they will be prevented from using the variable for nefarious purposes. We evaluate a prototype implementation of IDM and use the experimental results to show that this method can defend against most known non-control-data attacks while imposing a moderate amount of performance overhead.

• The KIPS Transactions:PartA
• /
• v.12A no.6 s.96
• /
• pp.471-476
• /
• 2005

Exception mechanism in Java allows programmers to define, throw and catch exceptional conditions. It is important for the development of reliable programs to make sure that exceptions are handled appropriately at run-time. In this paper, we develop an exception monitoring system, which can help programmers trace and handle exceptions effectively. Using this system, programmers can examine exception handling process in detail by tracing only interesting exceptions, and can handle exceptions more effectively. To reduce performance overhead, we design the system based on code instrumentation. Moreover, we show the effectiveness of the system by experiments on benchmark programs.