• The Journal of the Acoustical Society of Korea
• /
• v.23 no.2
• /
• pp.173-179
• /
• 2004

Due to the insufficiency of training data in large vocabulary continuous speech recognition, similar context dependent phones can be clustered by decision trees to share the data. When the decision trees are built and used to predict unseen triphones, a phonetic question set is required. The phonetic question set, which contains categories of the phones with similar co-articulation effects, is usually generated by phonetic or linguistic experts. This knowledge-based approach for generating phonetic question set, however, may reduce the homogeneity of the clusters. Moreover, the experts must adjust the question sets whenever the language or the PLU (phone-like unit) of a recognition system is changed. Therefore, we propose a data-driven method to automatically generate phonetic question set. Since the proposed method generates the phone categories using speech data distribution, it is not dependent on the language or the PLU, and may enhance the homogeneity of the clusters. In large vocabulary speech recognition experiments, the proposed algorithm has been found to reduce the error rate by 14.3%.

• Journal of the Korean Society for information Management
• /
• v.35 no.1
• /
• pp.157-182
• /
• 2018

As data management and processing techniques have been developed rapidly in the era of big data, nowadays a lot of business companies and researchers have been interested in long tail data which were ignored in the past. This study proposes methods for generating and controlling a network of technical terms based on text mining technique to enhance data utilization in the distribution of long tail theory. Especially, an edit distance technique of text mining has given us efficient methods to automatically create an interlinking network of technical terms in the scholarly field. We have also used linked open data system to gather experimental data to improve data utilization and proposed effective methods to use data of LOD systems and algorithm to recognize patterns of terms. Finally, the performance evaluation test of the network of technical terms has shown that the proposed methods were useful to enhance the rate of data utilization.

• Journal of Advanced Navigation Technology
• /
• v.24 no.2
• /
• pp.61-66
• /
• 2020

Since the ocean accounts for 70.8 percent of the earth's surface, the success of IoT technology in the marine industry is to collect information from devices placed in a wider range. LPWA is a feature with a wide range of communication and is very suitable for deployment in the ocean. In this paper, the real-sea performance distance experiment was carried out based on Private LoRa, a key technology for executing the electronic phrase real-name system. A private LoRa module based on sx1276 was developed, and Gateway was developed to transfer data received by private LoRa to the server using SKT Cat. M1. After installing gateways at 599 meters above sea level and experimenting with data transmission and reception at 25 km, 40 km and 60 km, we were able to see that the communication success rate was obtained to be 96.1%. 97.1% and 96.2% respectively.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.35 no.5B
• /
• pp.794-800
• /
• 2010

It is necessary to accurate and efficient management for measured digital data from various sensors in digital marine vessel. It is not efficient that sensor network process input stream data of mass storage stored in database the same time. In this paper, We propose to improve the processing performance of multidimensional stream data continuous incoming from multiple sensor. We propose that we arrange some sensors (temperature, humidity, lighting, voice) and process query based on sliding window for efficient input stream and found multiple query plan to Mjoin method and we reduce stored data using SVM algorithm. We automatically delete that it isn't necessary to the data from the database and we used to ship diagnosis system for available data. As a result, we obtained to efficient result about 18.3% reduction rate of database using 35,912 data sets.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.43 no.10 s.352
• /
• pp.27-34
• /
• 2006

This paper has implemented a very small($1.4{\times}2.8[Cm^2]$) 13.56[MHz] RFID reader ensuring machine ID recognition correctly in a noise space of Tag-to-Reader within 3Cm. For operation of the RFID system, at first, this paper has designed the loop antenna of a reader and the fading model of back-scattering on microwave propagation following to 13.56[MHz] RFID Air Interface ISO/IEC specification. Secondly, this paper has proposed the automatically path selected RF switching circuit and the firmware operation relationship by measuring and analyzing the very small RFID RF issues. Finally, as a very small reader main body, this paper has shown the DSP board and software functions made for extraction of $1{\sim}2$ machine ID information and error prevention simultaneously with carrying of 13.56[MHz] RFID signals that the international standard specification ISO/IEC 18000-3 defined.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.47 no.4
• /
• pp.109-117
• /
• 2010

With the advent of new technologies such as HSDPA, WiBro(Wireless Broadband) and personal devices, we can access various contents and services anytime and anywhere. A location based service(LBS) is essential for providing personalized services with individual location information in ubiquitous computing environment. In this paper, we propose mapping algorithm for error compensation of indoor localization system. Also we explain filter and indoor localization system. we have developed mapping algorithms composed of a map recognition method and a position compensation method. The map recognition method achieves physical space recognition and map element relation extraction. We improved the accuracy of position searching. In addition, we reduced position errors using a dynamic scale factor.

• Journal of Korea Society of Industrial Information Systems
• /
• v.5 no.1
• /
• pp.77-86
• /
• 2000

Even manual materials handling tasks(MMHT) is decreasing by adopt of automatic manufacturing system & transportation supporting machine because of increase of productivity, wage lack of labor, safety, in fact working at inclined & complicated slope such as farm, orchard, harbor loading & unloading, logging place and mining place can't be substituted by machine perfectly. So, workers should do MMHT at this place by themselves, lifting on slope can cause much of hazard, include falling. Keeping balance net to slip can be a reason of low back pain(LBP) by overloaded musculoskeletal system but, there's no enough study about lift on slope. Therefore, In this study, we assessed and analyzed change of center of pressure(COP) when lifting on slope by force platform. The result showed that the length lengthen as increasing angle of slope. Especially, the length extremely increased over 15°. Through These basic result, present proper angle boundary, prevent industrial accidents and give proper data not only lifting but also pushing and pulling on slope someday.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.12 no.6
• /
• pp.279-283
• /
• 2012

In is paper, we design and implement the low power, high speed touch screen controller that calculates and outputs the coordinate of touch point on the touch screen of mobile devices. The system clock is 10HMz, the number of input channels is 21, standby current is $20{\mu}A$, dynamic range of input is 140pF~400pF and the response time is 0.1ms/frame. It contains the power management unit for low power, automatic impedance calibration unit in order to adapt to humidity, temperature and evaluation board, adjacent key and pattern interference suppression unit, serial interface unit of I2C and SPI. The function and performance is verified by using FPGA and $0.18{\mu}m$ CMOS standard process. The implemented touch screen is designed for using in the double layer ITO(Indium Thin Oxide) module with diamond pattern and single layer ITO module for cost-effective which are applied to mobile phone or smart remote controller.

• Journal of Veterinary Clinics
• /
• v.15 no.2
• /
• pp.450-454
• /
• 1998

These studies were performed to find out the possibility of automatic detection of the diseased animal with fever by farmers themselves. Firstly, the body temperature of 331 dairy cows was investigated according to major disease symptoms manifested. Secondly, AD 590 thermometer was used to take the teat temperature of the milking cows to determine the possibility of automatic taking of body temperature while milking. The temperatures of scapha of ear and coccygeal artery part were also taken fur the non-milking dairy cows and Korean native cowl 1. The average body temperature of dairy cows associated with respiratory diseases puerperal disease, or mastitis was higher than normal temperature denoting respectively 39.8,39.6, and $39.3{\circ}C.2.$ The teat temperaure of the milking dairy cows with fever($39.5~39.6{\circ}C$) and the cows with mastitis was respectively 1.02 and 0.56${\circ}C$ higher than that of normal cows. 3. The average teat temperature taken by AD 590 was 33.91, 34.93, and 34.50${\circ}C$ in normal milking dairy cows, cows with fever(39.5~39.6${\circ}C$), and cows with mastitis, respectively. 4. The mean temperatures at scapha and coccygeal part of non-milking dairy cows and Korean native cows were 35.62 and 36.63${\circ}C$, respectively. It was concluded that AD 590 thermometer would be usable for the farmers to automatirally detect the body temperature of dairy cows while milking and subsquently to find the diseased cow with fever and that the scapha of ear and coccygeal artery part of the cattle could be the body parts of simply detecting body temperature of non-milking cattle.

• Journal of Korea Technical Association of The Pulp and Paper Industry
• /
• v.46 no.3
• /
• pp.11-19
• /
• 2014

Reliability of the novel automatic system capable of measuring both St$\ddot{o}$ckigt sizing degree and contact angle at a time was evaluated through the calculation of its repeatability and reproducibility based on TAPPI Standard Method T 1200. As the basis weight of paper specimen increased, the repeatability and reproducibility of the automatic system became more improved than those from Hercules sizing test and contact angle test designated on TAPPI Standard Method T 530 and T 558. The more improved repeatability and reproducibility implies that a single tester can obtain the similar results under similar test conditions in spite of repetitive testing using the automatic system, and likewise that multiple testers can respectively reproduce similar data without big variation from the same paper specimen using the automatic system. In conclusion, this study is greatly meaningful in having developed the world's first automatic system to measure both St$\ddot{o}$ckigt sizing degree and contact angle simultaneously with excellent repeatability and reproducibility.