• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.6
• /
• pp.267-272
• /
• 2016

Microscope cell image is an important indicator for obtaining the biological information in a bio-informatics fields. Since human observers have been examining the cell image with microscope, a lot of time and high concentration are required to analyze cell images. Furthermore, It is difficult for the human eye to quantify objectively features in cell images. In this study, we developed HCS algorithm for automatic analysis of cell image using an OpenCV library. HCS algorithm contains the cell image preprocessing, cell counting, cell cycle and mitotic index analysis algorithm. We used human cancer cell (MKN-28) obtained by the confocal laser microscope for image analysis. We compare the value of cell counting to imageJ and to a professional observer to evaluate our algorithm performance. The experimental results showed that the average accuracy of our algorithm is 99.7%.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.21 no.11
• /
• pp.1214-1219
• /
• 2010

In this paper, a software radio system, supporting the physical layer of IEEE 802.15.4 standard, has been developed using USRP(Universal Software Radio Peripheral) board and GNU Radio package of an open source development kit for software radio. The software radio system supports the standards of BPSK and OQPSK modulations for 868/915 MHz band and OQPSK modulation for 2.45 GHz band. To verify the operation of the developed system, it has been tested under the standard signals according to the frequency band and packet structures for the transmitting and receiving operation. At 2.4 GHz, the Smart RF EV board and CC2430 modules are used to check the proper operation of the software radio system. The system performance test shows that the emission power spectrum, the eye-pattern, and PER(Packet Error Rate) meet the standard. It has been confirmed that the developed system supports the PHY layer of IEEE 802.15.4.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.12 no.1
• /
• pp.89-95
• /
• 2016

Recent growth of hacking threats and development in software and technology put Network security under threat, In addition, intrusion, malware and worm virus have been increased due to the existence of variety of sophisticated hacking methods. The goal of this study is to compare Snort Alpha version with Suricata 2.0.11 version whereas previous study focuses on comparison between snort 2. x version under thread environment and Suricata under multi-threading environment. This thesis' experiment environment is set as followed. Intel (R) Core (TM) i5-4690 3. 50GHz (4threads) of CPU, 16GB of RAM, 3TB of Seagate HDD, Ubuntu 14.04 are used. According to the result, Snort Alpha version is superior to Suricata in performance, but Snort Alpha had some glitches when executing pcap files which created core dump errors. Therefore this experiment seeks to analyze which performs better between Snort Alpha version that supports multi packet processing threads and Suricata that supports multi-threading. Through this experiment, one can expect the better performance of beta and formal version of Snort in the future.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.2
• /
• pp.107-112
• /
• 2013

With the progress of NGS technologies, large genome data have been exploded recently. To analyze such data effectively, the assistance of HPC technique is necessary. In this paper, we organized a genome analysis pipeline to call SNP from NGS data. To organize the pipeline efficiently under HPC environment, we analyzed the CPU utilization pattern of each pipeline steps. We found that sequence alignment is computing centric and suitable for parallelization. We also analyzed the performance of parallel open source alignment tools and found that alignment method utilizing many-core processor can improve the performance of genome analysis pipeline.

• International Journal of Computer Science & Network Security
• /
• v.22 no.3
• /
• pp.273-275
• /
• 2022

Deep Learning is used nowadays in Nuclei segmentation. While recent developments in theory and open-source software have made these tools easier to implement, expert knowledge is still required to choose the exemplary model architecture and training setup. We compare two popular segmentation frameworks, U-Net and Mask-RCNN, in the nuclei segmentation task and find that they have different strengths and failures. we compared both models aiming for the best nuclei segmentation performance. Experimental Results of Nuclei Medical Images Segmentation using U-NET algorithm Outperform Mask R-CNN Algorithm.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.11 no.8
• /
• pp.3005-3011
• /
• 2010

As soon as high-performanced smart phones is rapidly emerging in recent, its security problems come to the front. Especially in case of an open platform, it is easy to be a target of virus. Many security solution industries such as Symantec and Ahnlab are developing a mobile security system, but they have not yet a commercial product. We developed the effective security function of Android system based on SELinux to solve this problem, and verified its performance by applying the user applications developed to S3C6410 board.

• Journal of Software Assessment and Valuation
• /
• v.15 no.1
• /
• pp.63-70
• /
• 2019

These days, as Interest in Image recognition with deep learning is increasing, there has been a lot of research in image recognition using deep learning. In this study, we propose a system for classifying rocks through rock images of 18 types of rock(6 types of igneous, 6 types of metamorphic, 6 types of sedimentary rock) which are addressed in the high school curriculum, using CNN model based on Tensorflow, deep learning open source framework. As a result, we developed a classifier to distinguish rocks by learning the images of rocks and confirmed the classification performance of rock classifier. Finally, through the mobile application implemented, students can use the application as a learning tool in classroom or on-site experience.

• Proceedings of the KSR Conference
• /
• 2008.06a
• /
• pp.603-609
• /
• 2008

Nowadays, double-system of TFM(Track-side Functional Modules) developed instead of single-system in use of high speed line to acquisition more availability. Safety Law for Railroad recommend to quality certification of development and general railway machines. It is important to select metrics which form the bases for testing software products. A number of package software development part do not open source cords, so testing external characteristic vectors having relationship with metrics. In this paper, review the process for the TFM Point Modules, Universal Modules and Switchers, think about the test methode of circuit boards output performance by using TFM tester and Simulators.

• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.7
• /
• pp.327-332
• /
• 2016

This study is a leading research project to develop an automatic grade decision making algorithm of a 6-years-old fresh ginseng. For this work, we developed a Ginseng image acquiring instrument which can take 4-direction's images of a Ginseng at the same time and obtained 245 jingen images using the instrument. The 12 parameters were extracted for each image by a manual way. Lastly, 4 parameters were selected depending on a Ginseng grade classification criteria of KGC Ginseng research institute and a survey result which a distribution of averaging 12 parameters. A pattern recognition classifier was used as a support vector machine, designed to "k-class classifier" using the OpenCV library which is a open-source platform. We had been surveyed the algorithm performance(Correct Matching Ratio, False Acceptance Ratio, False Reject Ratio) when the training data number was controlled 10 to 20. The result of the correct matching ratio is 94% of the $1^{st}$ ginseng grade, 98% of the $2^{nd}$ ginseng grade, 90% of the $3^{rd}$ ginseng grade, overall, showed high recognition performance with all grades when the number of training data are 10.

• KIPS Transactions on Software and Data Engineering
• /
• v.4 no.1
• /
• pp.1-8
• /
• 2015

Safety critical systems require exhaustive verification of safety properties, because even a single corner-case fault can cause a critical safety failure. However, existing verification approaches are too costly in terms of time and computational resource required, making it hard to be applied in practice. In this paper, we implemented a tool for minimizing the size of the verification target w.r.t. verification properties to check, based on program slicing technique[1]. The efficacy of program slicing using our tool is demonstrated in a case study with a verification target Trampoline[3], which is an open source automotive operating system compliant with OSEK/VDX[2]. Experiments have shown enhanced performance in verification, with a 71% reduction in the size of the code.