• Journal of the Korean Society of Industry Convergence
• /
• v.27 no.4_2
• /
• pp.1001-1007
• /
• 2024

Recent deep learning algorithms for object detection in real-time play a crucial role in various applications such as autonomous driving, traffic monitoring, health care, and water quality monitoring. The size of small objects, in particular, significantly impacts the accuracy of detection models. However, data containing small objects can lead to underfitting issues in models. Therefore, this study developed a deep learning model capable of quickly detecting small objects to provide more accurate predictions. The RE-SOD (Residual block based Small Object Detector) developed in this research enhances the detection performance for small objects by using RGB separation preprocessing and residual blocks. The model achieved an accuracy of 1.0 in image classification and an mAP50-95 score of 0.944 in object detection. The performance of this model was validated by comparing it with real-time detection models such as YOLOv5, YOLOv7, and YOLOv8.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.14 no.4
• /
• pp.267-275
• /
• 2004

This research is concerned with the development of a real-time adaptive PPF controller for the active vibration suppression of smart structure. In general, the tuning of the PPF controller is carried out off-line. In this research, the real-time learning algorithm is developed to find the optimal filter frequency of the PPF controller in real time and the efficacy of the algorithm is proved by implementing it in real time. To this end, the adaptive algorithm is developed by applying the gradient descent method to the predefined performance index, which is similar to the method used popularly in the optimization and neural network controller design. The experiment was carried out to verify the validity of the adaptive PPF controller developed in this research. The experimental results showed that adaptive PPF controller is effective for active vibration control of the structure which is excited by either impact or harmonic disturbance. The filter frequency of the PPF controller is tuned in a very short period of time thus proving the efficiency of the adaptive PPF controller.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.63 no.9
• /
• pp.1259-1265
• /
• 2014

In this paper, the real-time attitude determination based Matlab using low-cost receivers was designed and evaluated. The GNSS attitude determination system was implemented to operation in real-time by TimerCallback in MATLAB. The TTM(Transmission Time Misalignment) of U-blox receiver was confirmed through zero baseline tests and this problem was revised. The computed attitude by the high-cost NovAtel receiver was compared to the computed attitude by the low-cost U-blox receiver. As a result of this, the performance of attitude determination systems by low-cost receiver was confirmed. To determine baseline, LAMBDA and BC-LAMBDA for integer ambiguities search methods were used. To confirm suitable integer ambiguity search method in real-time attitude determination algorithm, determined baselines by two methods were compared, and it was confirmed that BC-LAMBDA is more suitable. As a result of this, the operation of real-time attitude determination system was confirmed using 3 low-cost receivers.

• Journal of Computing Science and Engineering
• /
• v.7 no.1
• /
• pp.67-80
• /
• 2013

The worst-case execution time (WCET) of each real-time task in multicore processors with shared caches can be significantly affected by inter-thread cache interferences. The worst-case inter-thread cache interferences are dependent on how tasks are scheduled to run on different cores. Therefore, there is a circular dependence between real-time task scheduling, the worst-case inter-thread cache interferences, and WCET in multicore processors, which is not the case for single-core processors. To address this challenging problem, we present an offline real-time scheduling approach for multicore processors by considering the worst-case inter-thread interferences on shared L2 caches. Our scheduling approach uses a greedy heuristic to generate safe schedules while minimizing the worst-case inter-thread shared L2 cache interferences and WCET. The experimental results demonstrate that the proposed approach can reduce the utilization of the resulting schedule by about 12% on average compared to the cyclic multicore scheduling approaches in our theoretical model. Our evaluation indicates that the enhanced scheduling approach is more likely to generate feasible and safe schedules with stricter timing constraints in multicore real-time systems.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.8
• /
• pp.1820-1831
• /
• 2011

When both types of periodic and aperiodic tasks are required to run on a sensor node platform with limited energy resources, we propose an energy-efficient hybrid task scheduling technique that guarantees the deadlines of real-time tasks and provides non-real-time tasks with good average response time. The proposed hybrid task scheduling technique achieved better performance than existing EDF-based DVS scheduling techniques available in the literature, the FIFO-based TinyOS scheduling technique, and the task-clustering based non-preemptive real-time scheduling technique.

• Journal of Microbiology and Biotechnology
• /
• v.27 no.4
• /
• pp.816-824
• /
• 2017

Human noroviruses are widespread and contagious viruses causing nonbacterial gastroenteritis. Real-time reverse transcription quantitative PCR (real-time RT-qPCR) is currently the gold standard for the sensitive and accurate detection of these pathogens and serves as a critical tool in outbreak prevention and control. Different surveillance teams, however, may use different assays, and variability in specimen conditions may lead to disagreement in results. Furthermore, the norovirus genome is highly variable and continuously evolving. These issues necessitate the re-examination of the real-time RT-qPCR's robustness in the context of accurate detection as well as the investigation of practical strategies to enhance assay performance. Four widely referenced real-time RT-qPCR assays (Assays A-D) were simultaneously performed to evaluate characteristics such as PCR efficiency, detection limit, and sensitivity and specificity with RT-PCR, and to assess the most accurate method for detecting norovirus genogroups I and II. Overall, Assay D was evaluated to be the most precise and accurate assay in this study. A ZEN internal quencher, which decreases nonspecific fluorescence during the PCR, was added to Assay D's probe, which further improved the assay performance. This study compared several detection assays for noroviruses, and an improvement strategy based on such comparisons provided useful characterizations of a highly optimized real-time RT-qPCR assay for norovirus detection.

• Journal of KIISE:Databases
• /
• v.27 no.1
• /
• pp.42-52
• /
• 2000

In many real time applications that the system maintains sensitive information to be shared by multiple users with different security levels, security is another important requirement. A secure real time database system must satisfy not only logical data consistency but also timing constrains and security requirements associated with transactions. Even though an optimistic concurrency control method outperforms locking based method in firm real time database systems, where late transactions are immediately discarded, most existing secure real time concurrency control methods are based on locking. In this paper, we propose a new optimistic concurrency control protocol for secure real time database systems, and compare the performance characteristics of our protocol with locking based method while varying workloads. The result shoes that our proposed O.C.C protocol has good performance in case of many data conflict.

• Journal of the Korea Society of Computer and Information
• /
• v.13 no.4
• /
• pp.213-220
• /
• 2008

The purpose of this paper is to improve efficiency in the construction and operation of a total management system for the national technical qualification through the design and development of a real-time data sharing system which is connected with the management system of external consignment. The current a total management system for the national technical qualification precesses the work depend on information and results which pass over by external IT company. But this method of processing has some unstable elements with regards to information reprocessing, functional supplement, system stability, etc. The proposed system's technological concepts have been tested through a basic simulation pilot program. The pilot program will be expanded to include the local Chamber of Commerce and Industry because the stability of the system was proved through its application to the real-time national technical qualification examination of KCCI(Korea Chamber of Commerce and Industry). The real-time data sharing system has shown great efficiency in terms of system management, and has solved problems of developmental period for information reprocessing and functional supplement. The real-time data sharing system has been given good evaluations with regard to the convenience of their use and the management system for operators and supervisors.

• The KIPS Transactions:PartC
• /
• v.8C no.6
• /
• pp.805-814
• /
• 2001

In this paper, we propose a new scheduling algorithm that guarantees the delay property of real-time traffic, not considered in previous DWRR(Dynamic Weighted Round Robin) algorithm and also transmits non-real-time traffic efficiently. The proposed scheduling algorithm is a variation of DWRR algorithm to guarantee the delay property of real-time traffic by adding cell transmission method based on delay priority. It also uses the threshold to prevent the cell loss of non-real-time traffic due to cell transmission method based on delay priority. Proposed scheduling algorithm may increase some complexity over conventional DWRR scheme because of cell transmission method based on delay priority. However, the consideration of delay priority can minimize cell delay and require less size of temporary buffer. Also, the results of our performance study shows that the proposed scheduling algorithm has better performance than conventional DWRR scheme due to reliable ABR service and congestion avoidance capacity.

• Convergence Security Journal
• /
• v.22 no.2
• /
• pp.3-8
• /
• 2022

Security threats occur from the outside, but more often from the inside. In particular, since the internal user knows about the information service, the security threat damage caused by the internal user is greater. In this environment, the actions of all users accessing information services should be monitored and recorded in real-time. However, the current operating system records only the logs of system and application execution, so there is a limit to monitoring user behavior in real-time. In such a security environment, damage may occur due to user's unauthorized actions. To solve this problem, this study proposes an architecture that monitors user behavior in real-time in a Linux environment. As a result of verifying the function to confirm the effectiveness of the proposed architecture, the console input values and output angles of all users who have access to the operating system are monitored in real-time and stored. Although the performance of the proposed architecture is somewhat slower than the identification and authentication functions provided by the operating system, it was confirmed that the performance was not at a level that users would recognize, and thus it was judged to be sufficiently effective. However, since this study focuses on monitoring the console behavior, it is impossible to monitor the behavior of user applications running in the background, so additional research is needed.