• Journal of Internet Computing and Services
• /
• v.10 no.4
• /
• pp.35-44
• /
• 2009

The emerging notion of data stream has brought many new challenges to the research communities as a consequence of its conceptual difference with conventional concepts of just data. One typical example is data stream processing in sensor networks. The range of data processing considerations in a sensor network is very wide, from physical resource restrictions such as bandwidth, energy, and memory to the peculiarities of query processing including continuous and specific types of queries. In this paper, as one of the physical constraints in data stream processing, we consider the problem of limited memory and propose a new scheme for data stream reduction based on the Principal Component Analysis (PCA) technique. PCA can transform a number of (possibly) correlated variables into a (smaller) number of uncorrelated variables. We adapt PCA for the data stream of a sensor network assuming the cooperation of a query engine (or application) with a network base station. Our method exploits the spatio-temporal correlation among multiple measurements from different sensors. Finally, we present a new framework for data processing and describe a number of experiments under this framework. We compare our scheme with the wavelet transform and observe the effect of time stamps on the compression ratio. We report on some of the results.

• Journal of Internet Computing and Services
• /
• v.10 no.4
• /
• pp.199-211
• /
• 2009

Recent advancements in wireless networks have enabled support for mobile applications to transfer data over heterogeneous wireless paths in parallel using data striping technique [2]. Traditionally, high performance data transfer requires tuning of multiple TCP sockets, at sender's end, based on bandwidth delay product (BDP). Moreover, traditional techniques like Automatic TCP Buffer Tuning (ATBT), which balance memory and fulfill network demand, is designed for wired infrastructure assuming single flow on a single socket. Hence, in this paper we propose a buffer tuning technique at senders end designed to ensure high performance data transfer by striping data at transport layer across heterogeneous wireless paths. Our mechanism has the capability to become a resource management system for transport layer connections running on multi-homed mobile host supporting features for wireless link i.e. mobility, bandwidth fluctuations, link level losses. We show that our proposed mechanism performs better than ATBT, in efficiently utilizing memory and achieving aggregate throughput.

• Journal of Internet Computing and Services
• /
• v.7 no.6
• /
• pp.105-112
• /
• 2006

This paper be composed to file system by making a new i_node structure which can decrease Write frequency because this's can improved the file system efficiency if reduced Write operation frequency of flash memory in respect of file system, i-node is designed to realize Cleaning policy of data in order to perform Write operation. This paper suggest Cleaning Algorithm for Write operation through a new i_node structure. In addition, this paper have mode the oldest data cleaned and the most recent data maintained longest as a result of experiment that the recent applied program and data tend to be implemented again through the concept of regional and time space which appears automatically when applied program is implemented. Through experiment and realization of the Flash file system, this paper proved the efficiency of NAND-type flash file system which is required in on Embedded system.

• Journal of KIISE
• /
• v.43 no.4
• /
• pp.411-418
• /
• 2016

In recent times, NAND flash memory has become widely used as secondary storage for computing devices. Accordingly, to take advantage of NAND flash memory, new file systems have been actively studied and proposed. The performance of these file systems is generally measured with benchmark tools. However, since benchmark tools are executed by software simulation methods, many researchers get non-uniform benchmark results depending on the system environments. In this paper, we use Filebench, one of the most popular and representative benchmark tools, to analyze benchmark results and study the reasons why the benchmark result variations occur. Our experimental results show the differences in benchmark results depending on the system environments. In addition, this study substantiates the fact that system performance is affected mainly by background I/O requests and fsync operations.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.19 no.3
• /
• pp.151-158
• /
• 2024

Although on-device artificial intelligence (AI) has gained attention to diagnosing machine faults in real time, most previous studies did not consider the model retraining and redeployment processes that must be performed in real-world industrial environments. Our study addresses this challenge by proposing an on-device AI-based real-time machine fault diagnosis system that utilizes continual learning. Our proposed system includes a lightweight convolutional neural network (CNN) model, a continual learning algorithm, and a real-time monitoring service. First, we developed a lightweight 1D CNN model to reduce the cost of model deployment and enable real-time inference on the target edge device with limited computing resources. We then compared the performance of five continual learning algorithms with three public bearing fault datasets and selected the most effective algorithm for our system. Finally, we implemented a real-time monitoring service using an open-source data visualization framework. In the performance comparison results between continual learning algorithms, we found that the replay-based algorithms outperformed the regularization-based algorithms, and the experience replay (ER) algorithm had the best diagnostic accuracy. We further tuned the number and length of data samples used for a memory buffer of the ER algorithm to maximize its performance. We confirmed that the performance of the ER algorithm becomes higher when a longer data length is used. Consequently, the proposed system showed an accuracy of 98.7%, while only 16.5% of the previous data was stored in memory buffer. Our lightweight CNN model was also able to diagnose a fault type of one data sample within 3.76 ms on the Raspberry Pi 4B device.

• Journal of Internet Computing and Services
• /
• v.25 no.1
• /
• pp.1-8
• /
• 2024

In the API gateway, API composition is an essential function that can reduce the number of client calls and prevent over-fetching and under-fetching. API composition that operate with IMJ (In-Memory Join) consume a lot of resources, putting a burden on the performance of the API gateway. In this paper, to improve the problem of IMJ-style API composition, we propose SAPIC (Stream-based API Composition), which delivers the data to be composed to the client by streaming. SAPIC calls each MSA API that makes up the client response data and immediately streams the received response data to the client, reducing the resource consumption of the API gateway and providing faster response time compared to IMJ. As a result of a comparison experiment with GraphQL, a representative API combination technology, SAPIC recorded a maximum CPU occupancy rate of approximately 21 to 70 % lower, a maximum heap usage rate of approximately 16 to 74 % lower, and a throughput rate that was 1 to 2.3 times higher than GraphQL.

• Journal of Korean Society for Geospatial Information Science
• /
• v.20 no.2
• /
• pp.81-91
• /
• 2012

As the recent development of the ubiquitous computing environment, u-GIS is being highlighted as the core technology of the ubiquitous computing environment, and thereby, studies on spatio-temporal data are being actively conducted. In this u-GIS environment, it is still difficult for existing mobile devices to efficiently manage the massive spatio-temporal data of u-GIS that are increasing day by day. Therefore, this paper develops a spatio-temporal query processing system for mobile devices in order to solve the problem. The system provides various spatio-temporal operators to insert/delete/update/search spatio-temporal data and supports a query optimization function that uses a spatio-temporal index for the flash memory and a spatio-temporal histogram for guaranteeing query execution speed. Lastly, by applying the spatio-temporal query processing system developed in this paper to the virtual scenario, this paper has proved that the system can be utilized in various application fields necessary to process spatio-temporal data in the mobile environment.

• The Journal of Korean Institute of Next Generation Computing
• /
• v.14 no.6
• /
• pp.75-86
• /
• 2018

The DDS (Data Distribution Service) specification defines a discovery method for finding participants and endpoints in a DDS network. The standard discovery mechanism uses the multicast protocol and finds all the endpoints in the network. Because of using multicasting, discovery may fail in a network with different segments. Other problems include that memory space wastes due to storing information of all the endpoints. The Topic Name Service (TNS) solves these problems by unicasting only the endpoints, which are required for communication. However, an extra delay time is inevitable in components of TNS, i.e, a front-end server, topic name servers, and a terminal server. In this paper, we analyze the performance of TNS. Delay times in the servers of TNS and time required to receive endpoint information are measured. Time to finish discovery and number of receiving endpoints compare with the standard discovery method.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.43 no.6 s.348
• /
• pp.23-29
• /
• 2006

It is difficult to apply conventional security algorithms to the wireless sensor networks composed of nodes that have resource constraints such as memory, computing, power resources limitation. Generally, shared key based algorithms with low resource consumption and short key length are used for broadcast packets in authentication of base station. But it is not suitable that all the nodes hold the same shared key only for packet authentication. Recently, broadcast authentication algorithm for sensor network is proposed, which uses key chain generation by one-way hash function, Message Authentication Code generation by each keys of the key chains and delayed key disclosure. It provides suitable authentication method for wireless sensor networks but may leads to inefficient consequence with respect to network conditions such as broadcast ratio, key chain level, and so on. In this paper, we propose an improved broadcast authentication algorithm that uses key chain link and periodical key disclosure. We evaluated the performance of proposed algorithm using TOSSIM(TinyOS Simulator) in TinyOS. The results show that the proposed algorithm ensures low authentication delay, uses memory and computing resource of receiving nodes efficiently and reduces the amount of packet transmitting/receiving.

• The Journal of the Convergence on Culture Technology
• /
• v.3 no.4
• /
• pp.165-169
• /
• 2017

CNN(Convolutional Nerual Network) is one of the algorithms that show superior performance in image recognition and classification among machine learning algorithms. CNN is simple, but it has a large amount of computation and it takes a lot of time. Consequently, in this paper we performed an parallel processing unit for the convolution layer, pooling layer and the fully connected layer, which consumes a lot of handling time in the process of CNN, through the SIMT(Single Instruction Multiple Thread)'s structure of GPGPU(General-Purpose computing on Graphics Processing Units).And we also expect to improve performance by reducing the number of memory accesses and directly using the output of convolution layer not storing it in pooling layer. In this paper, we use MNIST dataset to verify this experiment and confirm that the proposed CNN structure is 12.38% better than existing structure.