• Journal of KIISE:Computer Systems and Theory
• /
• v.37 no.5
• /
• pp.285-291
• /
• 2010

Flash memory has many good features such as small size, shock-resistance, and low power consumption, but the cost of flash memory is still high to substitute for hard disk entirely. Recently, some mobile devices, such as laptops, attempt to use both flash memory and hard disk together for taking advantages of merits of them. However, existing OSs (Operating Systems) are not optimized to use the heterogeneous storage media. This paper presents a new buffer cache management scheme. First, we allocate buffer cache space according to access patterns of block references and the characteristics of storage media. Second, we prefetch data blocks selectively according to the location of them and access patterns of them. Third, we moves destaged data from buffer cache to hard disk or flash memory considering the access patterns of block references. Trace-driven simulation shows that the proposed schemes enhance the buffer cache hit ratio by up to 29.9% and reduce the total I/O elapsed time by up to 49.5%.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.3
• /
• pp.297-305
• /
• 2008

Recently, kernel methods have attracted great interests in the areas of pattern classification, function approximation, and anomaly detection. The role of the kernel is particularly important in the methods such as SVM(support vector machine) and KPCA(kernel principal component analysis), for it can generalize the conventional linear machines to be capable of efficiently handling nonlinearities. This paper considers the problem of combining radar and rain gauge observations utilizing the regression approach based on the kernel-based gaussian process and support vector learning. The data-assimilation results of the considered methods are reported for the radar and rain gauge observations collected over the region covering parts of Gangwon, Kyungbuk, and Chungbuk provinces of Korea, along with performance comparison.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.12 no.7
• /
• pp.1173-1179
• /
• 2008

Since there are very strong clutter returns in airborne and ground weather radars used for the detection of low altitude weather hazards, the reliable weather data cannot be extracted from the weak Doppler weather signal without cancellation of these strong clutter returns. However, the clutter cancellation in Doppler frequency domain is not an easy task since even the fixed clutter returns not to mention the moving clutter can have Doppler shifts due to the antenna rotation and operational environment. Therefore, it was shown in this paper a simple array antenna system can be used for the efficient clutter cancellation in the spatial domain. The weather signal, various moving and fixed clutters were modelled and simulated to prove the performance of this adaptive array system. Also, the degree of accuracy in pulse-pair estimates of a weather radar was compared and analyzed from the simulated weather data.

• KIPS Transactions on Computer and Communication Systems
• /
• v.8 no.11
• /
• pp.251-262
• /
• 2019

In this paper, we propose a simulator that provides various algorithms of RBF networks on neuromorphic chips. To develop algorithms based on neuromorphic chips, the disadvantages of using simulators are that it is difficult to test various types of algorithms, although time is fast. This proposed simulator can simulate four times more types of network architecture than existing simulators, and it provides an additional a two-layer structure algorithm in particular, unlike RBF networks provided by existing simulators. This two-layer architecture algorithm is configured to be utilized for multiple input data and compared to the existing RBF for performance analysis and validation of utilization. The analysis showed that the two-layer structure algorithm was more accurate than the existing RBF networks.

• Journal of Practical Engineering Education
• /
• v.10 no.1
• /
• pp.41-47
• /
• 2018

Underwater acoustic sensors are mounted on unmanned underwater vehicles(UUV) and detect and process the underwater information. These underwater acoustic sensor designs are very important subject for understanding and applying engineering. Therefore, in this paper, it was designed and fabricated the acoustic sensors step by step, evaluated their performance, and then studied the suitability of such a series of design procedures and steps to apply them to the integrated design learning. The results of the questionnaire survey showed that the steps and methods of the proposed sensor design are suitable for the contents of the integrated design project, and they are easy to acquire the technology and are very interesting design topics. It is anticipated that when the design project is applied to the integrated design in the future, high educational achievement will be achieved.

• Journal of Advanced Navigation Technology
• /
• v.23 no.4
• /
• pp.273-280
• /
• 2019

There are many studies that use structure health monitoring to reduce maintenance costs for aircraft and to increase aircraft utilization. Many studies on FBG sensors are also being conducted. However, if the FBG sensor is installed inside the composite, voids will occur between the layers of the composite, resulting in signal split problem. In addition, the FBG sensor is not affected by electromagnetic waves, but will produce electromagnetic noise caused by electronic equipment during post-processing. In this paper, to reduce the error caused by these noises, the stationary wavelet transform, which has the characteristics of movement immutability and is efficient in nonlinear signal analysis, is presented. And in the above situation, we found that noise rejection performance of stationary wavelet transform was better compared with the wavelet packet transform.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.21 no.2
• /
• pp.132-151
• /
• 2022

Vehicle localization is one of the core technologies for autonomous driving. Image-based localization provides location information efficiently, and various related studies have been conducted. However, the image-based localization methods using feature points or lane information has a limitation that positioning accuracy may be greatly affected by road and driving environments. In this study, we propose a line segment matching framework for accurate vehicle localization. The proposed framework consists of four steps: line segment extraction, merging, overlap area detection, and MSLD-based segment matching. The proposed framework stably performed line segment matching at a sufficient level for vehicle positioning regardless of vehicle speed, driving method, and surrounding environment.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.2
• /
• pp.25-32
• /
• 2022

In this paper, we propose a pet monitoring system based on deep learning using an activity recognition device. The system consists of a pet's activity recognition device, a pet owner's smart device, and a server. Accelerometer and gyroscope data were collected from an Arduino-based activity recognition device, and the number of steps was calculated. The collected data is pre-processed and the amount of activity is measured by recognizing the activity in five types (sitting, standing, lying, walking, running) through a deep learning model that hybridizes CNN and LSTM. Finally, monitoring of changes in the activity, such as daily and weekly briefing charts, is provided on the pet owner's smart device. As a result of the performance evaluation, it was confirmed that specific activity recognition and activity measurement of pets were possible. Abnormal behavior detection of pets and expansion of health care services can be expected through data accumulation in the future.

• Journal of Korea Society of Industrial Information Systems
• /
• v.15 no.4
• /
• pp.17-27
• /
• 2010

Major IT vendors expect that cloud computing technology makes it possible to reduce the contents service cycle, speed up application deployment and skip the installation process, reducing operational costs, proactive management etc. However, cloud computing environment for massive content service solutions requires high-performance data processing to reduce the time of data processing and analysis. In this study, Efficient_Cloud_Processing_Scheme(ECPS) is proposed for allocation of resources for massive content services. For high-performance services, optimized resource allocation plan is presented using MapReduce programming techniques and association rules that is used to detect hidden patterns in data mining, based on levels of Hadoop platform(Infrastructure as a service). The proposed ECPS has brought more than 20% improvement in performance and speed compared to the traditional methods.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.46 no.4
• /
• pp.312-320
• /
• 2023

Recently, there has been an increasing attempt to replace defect detection inspections in the manufacturing industry using deep learning techniques. However, obtaining substantial high-quality labeled data to enhance the performance of deep learning models entails economic and temporal constraints. As a solution for this problem, semi-supervised learning, using a limited amount of labeled data, has been gaining traction. This study assesses the effectiveness of semi-supervised learning in the defect detection process of manufacturing using the MixMatch algorithm. The MixMatch algorithm incorporates three dominant paradigms in the semi-supervised field: Consistency regularization, Entropy minimization, and Generic regularization. The performance of semi-supervised learning based on the MixMatch algorithm was compared with that of supervised learning using defect image data from the metal casting process. For the experiments, the ratio of labeled data was adjusted to 5%, 10%, 25%, and 50% of the total data. At a labeled data ratio of 5%, semi-supervised learning achieved a classification accuracy of 90.19%, outperforming supervised learning by approximately 22%p. At a 10% ratio, it surpassed supervised learning by around 8%p, achieving a 92.89% accuracy. These results demonstrate that semi-supervised learning can achieve significant outcomes even with a very limited amount of labeled data, suggesting its invaluable application in real-world research and industrial settings where labeled data is limited.