• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.1
• /
• pp.63-68
• /
• 2018

Recently, safety accidents that occur in laboratories have occurred in various forms, so that a system that can reduce safety accidents in laboratories is required. The existing system identifies the danger situation according to the change of the temperature and the humidity, but the type of the danger situation is not known and the operation of the device is manually performed. Therefore, in this paper, we propose a system that identifies the danger situation of a reagent cabinet using multiple sensors and automatically operates the device. The internal environment of the reagent cabinet is measured in real time through the sensors and the sensor data is used to identify the danger situation. Also, when a danger situation is identified, the appropriate device is selected and operated automatically. In this way, identification of the danger situation of the reagent cabinet and automatic operation of the device will reduce the safety accidents occurring in the reagent cabinet.

• The KIPS Transactions:PartB
• /
• v.10B no.5
• /
• pp.497-502
• /
• 2003

Fingerprint classification plays a role of reduction of precise joining time and improvement of the accuracy in a large volume of database. Patterns of fingerprint are classified as 5 patterns : left loop, right loop, arch, whorl, and tented arch by numbers and the location of core point and delta point. The existing fingerprint classification is useful in a captured fingerprint image of core point and delta point using paper and ink. However, this system is unapplicable in modern Automatic Fingerprint Identification System (AFIS) because of problems such as size of input and way of input. To solve the problem, this study is to suggest the way of being able to improve accuracy of fingerprint by fingerprint classification based on the entropy of ridges using fingerprint captured mage of core point and prove this through the experiment.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.33 no.2C
• /
• pp.208-218
• /
• 2008

We are sure that RFID system should be a widely used automatic identification system because of its various advantages and applications. However, many people know that invasions of privacy in RFID system is still critical problem that makes it difficult to be used. Many works for solving this problem have focused on light-weight cryptographic functioning in the RFID tag. An agent scheme is another approach that an agent device controls communications between the tag and the reader for protecting privacy. Generally an agent device has strong security modules and enough capability to process high-level cryptographic protocols and can guarantees consumer privacy. In this paper, we present an enhanced mobile agent for RFID privacy protection. In enhanced MARP, we modified some phases of the original MARP to reduce the probability of successful eavesdropping and to reduce the number of tag's protocol participation. And back-end server can authenticate mobile agents more easily using public key cryptography in this scheme. It guarantees not only privacy protection but also preventing forgery.

• Journal of KIISE:Software and Applications
• /
• v.31 no.7
• /
• pp.911-921
• /
• 2004

Accurate minutiae extraction from input fingerprint images is one of the critical modules in robust automatic fingerprint identification system. However, the performance of a minutiae extraction is heavily dependent on the quality of the input fingerprint images. If the preprocessing is performed according to the fingerprint image characteristics in the image enhancement step, the system performance will be more robust. In this paper, we propose a knowledge-based preprocessing method, which extracts S features (the mean and variance of gray values, block directional difference, orientation change level, and ridge-valley thickness ratio) from the fingerprint images and analyzes image quality with Ward's clustering algorithm, and enhances the images with respect to oily/neutral/dry characteristics. Experimental results using NIST DB 4 and Inha University DB show that clustering algorithm distinguishes the image Quality characteristics well. In addition, the performance of the proposed method is assessed using quality index and block directional difference. The results indicate that the proposed method improves both the quality index and block directional difference.

• Journal of Embryo Transfer
• /
• v.30 no.3
• /
• pp.257-260
• /
• 2015

Reproductive disorders in cows cause economic loss in livestock farms. Reproductive diseases, such as follicular cyst, luteal cyst, endometritis, pyometra, and repeat breeding cause infertility. Among these diseases, endometritis and pyometra are uterine infections that are leading causes of infertility. This study was performed to investigate the causative agents of uterine diseases using bacterial culture. Bacteria were obtained from the reproductive organs (vagina, uterine cervix, and uterine horn) of dairy cow diagnosed with endometritis or pyometra, and cultured on blood agar. The colonies obtained from cultivation for 24 hours were passaged. To identify the bacteria, the colonies grown in passaged culture Gram stained and applied to an automatic biochemical microbial identification system. Escherichia coli were commonly detected in vagina, uterine cervix, and uterine horn of dairy cows diagnosed to pyometra. The cows having endometritis showed not only Escherichia coli but also Pantoea spp. and Klebsiella spp. strains. Dairy cows that were infected with Escherichia coli in uterus caused mastitis or digestive disease. These results suggest that sanitary feeding and management beforehand are needed to prevent bacterial infections.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2006.06b
• /
• pp.227-232
• /
• 2006

In this paper, a Kalman filter application for GDSS(Group Digital Surveillance System) developed to protect an aquaculture farms is discussed GDSS is composed by a WIWAS(Watching, Identification, Warning, and Action System) and a FDS(Fishery Detection System) that will monitor incoming and outgoing vessels in the aquaculture farms. In the FDS, a tracking function to track vessels without F-AIS(Fishery Automatic Identification System) is needed and the Kalman filter is applied to track vessels around the aquaculture farms. Some simulation results for the multi-objects with white noise is presented and the adaptation possibility for tracking system is discussed.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.20 no.4
• /
• pp.117-134
• /
• 2010

A passive RFID tag which received attention as a future technology for automatic and quick identification faces some difficulties about security problems such as tag authentication, reader authentication, data protection, and untraceability in addition to cost and reliable identification. A representative passive RFID technology is the ISO/IEC 18000-6 Type C which is an international standard for 900 MHz UHF-band. This standard has some difficulties in applying to the security services such as originality verification, tag's internal information protection, and untraceability, because it does not provide high-level security solution. In this paper, we summarize security requirements of ISO/IEC ITC 1/SC 31 international standardization group, propose security protocols suitable for the UHF-band passive RFID system using a crypto engine, and analyze its security strength. In addition, we verify that it is possible to implement a tag conforming with the proposed security protocols by presenting concrete command/response pairs and cryptographic method.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.374-376
• /
• 2021

For the diagnosis of cancer-related diseases in clinical practice, pathological examination using biopsy is essential after basic diagnosis using imaging equipment. In order to proceed with such a biopsy, the assistance of an oncologist, clinical pathologist, etc. with specialized knowledge and the minimum required time are essential for confirmation. In recent years, research related to the establishment of a system capable of automatic classification of cancer cells using artificial intelligence is being actively conducted. However, previous studies show limitations in the type and accuracy of cells based on a limited algorithm. In this study, we propose a method to identify a total of 4 cancer cells through a convolutional neural network, a kind of deep learning. The optical images obtained through cell culture were learned through EfficientNet after performing pre-processing such as identification of the location of cells and image segmentation using OpenCV. The model used various hyper parameters based on EfficientNet, and trained InceptionV3 to compare and analyze the performance. As a result, cells were classified with a high accuracy of 96.8%, and this analysis method is expected to be helpful in confirming cancer.

• Asian-Australasian Journal of Animal Sciences
• /
• v.30 no.8
• /
• pp.1093-1098
• /
• 2017

Objective: The aim of the current study was to describe the relationship between milk yield and lactation number, stage, length and milking frequency in Korean Holstein dairy cows using an automatic milking system (AMS). Methods: The original data set consisted of observations from April to October 2016 of 780 Holstein cows, with a total of 10,751 milkings. Each time a cow was milked by an AMS during the 24 h, the AMS management system recorded identification numbers of the AMS unit, the cow being milking, date and time of the milking, and milk yield (kg) as measured by the milk meters installed on each AMS unit, date and time of the lactation, lactation stage, milking frequency (NoM). Lactation stage is defined as the number of days milking per cows per lactation. Milk yield was calculated per udder quarter in the AMS and was added to 1 record per cow and trait for each milking. Milking frequency was measured the number of milkings per cow per 24 hour. Results: From the study results, a significant relationship was found between the milk yield and lactation number (p<0.001), with the maximum milk yield occurring in the third lactation cows. We recorded the highest milk yield, in a greater lactation length period of early stage (55 to 90 days) at a $4{\times}$ milking frequency/d, and the lowest milk yield was observed in the later stage (>201 days) of cows. Also, milking frequency had a significant influence on milk yield (p<0.001) in Korean Holstein cows using AMS. Conclusion: Detailed knowledge of these factors such as lactation number, stage, length, and milking frequency associated with increasing milk yield using AMS will help guide future recommendations to producers for maximizing milk yield in Korean Dairy industries.

• Journal of Korean Society of Transportation
• /
• v.23 no.5 s.83
• /
• pp.123-134
• /
• 2005

This research aims at developing a new method which can replace the existing method. known as the quality factor(Q factor) method by an L-R-C test for use in the performance test of inductive loop detectors(ILD) being installed and maintained. In this study, a sensor to detect a magnetic field in terms of frequency and intensity, a method to collect field data, the method of analysis, and the method of diagnosis were developed. An automatic diagnosis system which was developed to overcome those drawbacks has the following features : First, field data is collected automatically by a test vehicle equipped with magnetic field sensors that is running can be said to along the roadway and. thus, the new system completely overcome the roadway and, thus, the new system can be said to completely overcome the inefficiency of the existing method second, since the magnetic fold generated from the ILD is the final output of the whole system of ILD, the existing problem has been solved. third. since each of the detection area by height is collected by the magnetic sensors installed by height. a basic for the identification of the vehicle types to be detectable and the setting of adjustment factors has been made. For the automatic diagnosis system developed during in this study, a reliability test was carried out by comparing vehicle times of ILD installed ideally.