• Journal of Intelligence and Information Systems
• /
• v.10 no.2
• /
• pp.15-37
• /
• 2004

With the growth in the size of datasets, data mining has recently become an important research topic. Especially, interests about spatio-temporal data mining has been increased which is a method for analyzing massive spatio-temporal data collected from a wide variety of applications like GPS data, trajectory data of surveillance system and earth geographic data. In the former approaches, conventional clustering algorithms are applied as spatio-temporal data mining techniques without any modification. In this paper, we focused to SOM that is the most common clustering algorithm applied to clustering analysis in data mining wet and develop the spatio-temporal data mining module based on it. In addition, we analyzed the clustering results of developed SOM module and compare them with those of K-means and Agglomerative Hierarchical algorithm in the aspects of homogeneity, separation, separation, silhouette width and accuracy. We also developed specialized visualization module fur more accurate interpretation of mining result.

• Journal of Advanced Navigation Technology
• /
• v.20 no.1
• /
• pp.79-85
• /
• 2016

Network traffic is increased rapidly, due to mobile and social network, such as smartphones and facebook, in recent web environment. In this paper, we improved web response time of existing system using direct buffer of NIO and DMA. This solved the disadvantage of JAVA, such as CPU performance reduction due to the blocking of I/O, garbage collection of buffer. Key values circulated many data due to priority change put on a hash map operated easily and apply a priority modification algorithm. Large response data is separated and stored at a fast direct buffer and improved performance. This paper showed that the proposed method using NIO was much improved performance, in many test situations of cache hit and cache miss.

• Journal of IKEEE
• /
• v.23 no.4
• /
• pp.1321-1327
• /
• 2019

This paper describes an efficient hardware implementation of modular square root (MSQR) computation over GF(p), which is the operation needed to map plaintext messages to points on elliptic curves for elliptic curve (EC)-ElGamal public-key encryption. Our method supports five sizes of elliptic curves over GF(p) defined by the National Institute of Standards and Technology (NIST) standard. For the Koblitz curves and the pseudorandom curves with 192-bit, 256-bit, 384-bit and 521-bit, the Euler's Criterion based on the characteristic of the modulo values was applied. For the elliptic curves with 224-bit, the Tonelli-Shanks algorithm was simplified and applied to compute MSQR. The proposed method was implemented using the finite field arithmetic circuit with 32-bit datapath and memory block of elliptic curve cryptography (ECC) processor, and its hardware operation was verified by implementing it on the Virtex-5 field programmable gate array (FPGA) device. When the implemented circuit operates with a 50 MHz clock, the computation of MSQR takes about 18 ms for 224-bit pseudorandom curves and about 4 ms for 256-bit Koblitz curves.

• The Korean Journal of Applied Statistics
• /
• v.29 no.6
• /
• pp.1077-1094
• /
• 2016

Apache Spark is a fast and general-purpose cluster computing package. It provides a new abstraction named resilient distributed dataset, which is capable of support for fault tolerance while keeping data in memory. This type of abstraction results in a significant speedup compared to legacy large-scale data framework, MapReduce. In particular, Spark framework is suitable for iterative machine learning applications such as logistic regression and K-means clustering, and interactive data querying. Spark also supports high level libraries for various applications such as machine learning, streaming data processing, database querying and graph data mining thanks to its versatility. In this work, we introduce the concept and programming model of Spark as well as show some implementations of simple statistical computing applications. We also review the machine learning package MLlib, and the R language interface SparkR.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.12
• /
• pp.3029-3034
• /
• 2014

The paper describes the scleral diagnostic system implementation for human eyes by using the scleral color code and vessels sign pattern code generations. The system is based on the high performance DSP image signal processor, programmable gain control for preprocessing and RISC SD frames storage. RGB image signals are optimized by PGC, the edge image is detected form the gray image converted. The processing algorithms are executed by scleral color code generation and scleral vessels sign pattern code creation for discriminating and matching. The scleral symptomatic color code is generated by YCbCr values at memory map tolerated and the vessel sign pattern code is created by digitizing the 24 clock and 13 ring zones, overlay matching and tolerances. The experimental results for performance are that the system runs 40ms, and the color and pattern for diagnostic errors are around 20% and 24% on average. The system and technique enable a scleral diagnosis with subdividing the patterns and patient database.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.12
• /
• pp.2885-2890
• /
• 2014

Localization of a sensor network node using machine learning has been recently studied. It is easy for Support vector machines algorithm to implement in high level language enabling parallelism. Raspberrypi is a linux system which can be used as a sensor node. Pi can be used to construct IP based Hadoop clusters. In this paper, we realized Support vector machine using python language and built a sensor network cluster with 5 Pi's. We also established a Hadoop software framework to employ MapReduce mechanism. In our experiment, we implemented the test sensor network with a variety of parameters and examined based on proficiency, resource evaluation, and processing time. The experimentation showed that with more execution power and memory volume, Pi could be appropriate for a member node of the cluster, accomplishing precise classification for sensor localization using machine learning.

• Korean Journal of Agricultural Science
• /
• v.47 no.2
• /
• pp.205-217
• /
• 2020

In this study, a deep learning-based tillage boundary detection method for autonomous tillage by a tractor was developed, which consisted of image cropping, object classification, area segmentation, and boundary detection methods. Full HD (1920 × 1080) images were obtained using a RGB camera installed on the hood of a tractor and were cropped to 112 × 112 size images to generate a dataset for training the classification model. The classification model was constructed based on convolutional neural networks, and the path boundary was detected using a probability map, which was generated by the integration of softmax outputs. The results show that the F1-score of the classification was approximately 0.91, and it had a similar performance as the deep learning-based classification task in the agriculture field. The path boundary was determined with edge detection and the Hough transform, and it was compared to the actual path boundary. The average lateral error was approximately 11.4 cm, and the average angle error was approximately 8.9°. The proposed technique can perform as well as other approaches; however, it only needs low cost memory to execute the process unlike other deep learning-based approaches. It is possible that an autonomous farm robot can be easily developed with this proposed technique using a simple hardware configuration.

• The KIPS Transactions:PartD
• /
• v.16D no.4
• /
• pp.507-516
• /
• 2009

In stream data processing system, generally the interval queries are in advance registered in the system. When a data is input to the system continuously, for realtime processing, a query indexing method is used to quickly search queries. Thus, a main memory-based query index with a small storage cost and a fast search time is needed for searching queries. In this paper, we propose a LVC-based(Limited Virtual Construct-based) query index method using a hashing to meet the both needs. In LVC-based query index, we divide the range of a stream into limited virtual construct, or LVC. We map each interval query to its corresponding LVC and the query ID is stored on each LVC. We have compared with the CEI-based query indexing method through the simulation experiment. When the range of values of input stream is broad and there are many short interval queries, the LVC-based indexing method have shown the performance enhancement for the storage cost and search time.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.8
• /
• pp.1005-1012
• /
• 2021

Recently, the use of various location-based services-based location information systems using maps on the web has been expanding, and there is a need for a monitoring system that can check power demand in real time as an alternative to energy saving. In this study, we developed a deep learning real-time virtual power demand prediction web system using open source-based mapping service to analyze and predict the characteristics of power demand data using deep learning. In particular, the proposed system uses the LSTM(Long Short-Term Memory) deep learning model to enable power demand and predictive analysis locally, and provides visualization of analyzed information. Future proposed systems will not only be utilized to identify and analyze the supply and demand and forecast status of energy by region, but also apply to other industrial energies.

• Journal of the Korea Society for Simulation
• /
• v.19 no.4
• /
• pp.129-137
• /
• 2010

Currently used shortest path search algorithms involve graphs with vertices and weighted edges between each vertex. However, when finding the shortest path with a randomly shaped obstacle(an island, for instance) positioned in between the starting point and the destination, using such algorithms involves high memory inefficiency and is significantly time consuming - all positions in the map should be considered as vertices and every line connecting any of the two adjacent vertices should be considered an edge. Therefore, we propose a new method for finding the shortest path in such conditions without using weighted graphs. This algorithm will allow finding the shortest obstacle bypass given only the positions of the obstacle boundary, the starting point and the destination. When the row and column size of the minimum boundary rectangle to include an obstacle is m and n, respectively, the proposed algorithm has the maximum time complexity, O(mn). This performance shows the proposed algorithm is very efficient comparing with the currently used algorithms.