• The Journal of the Acoustical Society of Korea
• /
• v.16 no.5
• /
• pp.112-121
• /
• 1997

In this paper, we study a model parameter compensation method for noise-robust speech recognition. We study model parameter compensation on a sentence by sentence and no other informations are used. Parallel model combination(PMC), well known as a model parameter compensation algorithm, is implemented and used for a reference of performance comparision. We also propose a modified PMC method which tunes model parameter with an association factor that controls average variability of gaussian mixtures and variability of single gaussian mixture per state for more robust modeling. We obtain a re-estimation solution of environmental variables based on the expectation-maximization(EM) algorithm in the cepstral domain. To evaluate the performance of the model compensation methods, we perform experiments on speaker-independent isolated word recognition. Noise sources used are white gaussian and driving car noise. To get corrupted speech we added noise to clean speech at various signal-to-noise ratio(SNR). We use noise mean and variance modeled by 3 frame noise data. Experimental result of the VTS approach is superior to other methods. The scheme of the zero order VTS approach is similar to the modified PMC method in adapting mean vector only. But, the recognition rate of the Zero order VTS approach is higher than PMC and modified PMC method based on log-normal approximation.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.27 no.1
• /
• pp.67-73
• /
• 2021

The purpose of this study is to obtain a safe area for a passing vessel between anchored vessels by developing a model to predict the collision risk, frequent collisions occur between the anchored vessel and the passing vessel through the anchorage. For this, this study selected the southern anchorage of Busan port, which is the largest harbor in Korea, as the target area and extracted and analyzed VTS (Vessel Traffic Service) data during the period in which anchored vessels were the most waited. The ratio of D/L for each bearing was obtained to determine the safe distance (D) passes based on the length (L) of the passing vessel between anchored vessels. Based on the average domain of the D/L ratio distribution, the percentage of anchored vessels within the scope of the pre-studied ship's domain was analyzed to obtain a domain reflecting the degree of risk of VTSOs. Further research will evaluate and analyze the collision risk of a passing vessel using Domain-watch, the minimum safe distance between anchored vessels, and the safe domain of a passing vessel through anchorage, to develop a model for VTS to manage anchorages more efficiently and safely.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.14 no.4
• /
• pp.303-307
• /
• 2008

The tug boat is restricted in her maneuvering ability due to the towed barge, and tug-barge has been strongly affected by the external forces, i.e. the wind, wave, currents, and so on. Therefore, it is difficult to get the safety of tug-barge operation. It is necessary for the captain of tug boat, VTS and operation department to develope the system which can keep observing the course, speed and position of the towed barge in actual sea and prevent the marine accidents in advance. In this study, we proposed the basic method to develope the safety towing system for barge using portable GPS which was easily movable and relatively inexpensive. Then we conducted the test on the real barge. As a result, we could obtain diverse navigation data to make a safety towing work. It was noted that these data could be used for carious purposes.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2009.10a
• /
• pp.62-63
• /
• 2009

A monitoring system of collision risk among multiple ships is newly-designed in order to reduce human error and make vessel traffic control more effective. By using AIS data as ships' navigational information, an estimation algorithm of collision risk among multiple ships is newly-designed. To consider ships' course of now and future, collision risks of multiple ships can be calculated by using fuzzy algorithm. To test the performance of new algorithm, replay simulations are carried out on actual AIS data collected from VTS center of Ulsan harbor in Korea. The AIS data include 25 ships' information for two hours. In this paper, the features of newly-designed estimation algorithm of collision risk and the results of replay simulation are discussed.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2019.11a
• /
• pp.24-25
• /
• 2019

최근 빅데이터 기술 개발로 방대한 데이터의 유의미한 분석 및 예측이 용이해졌다. 선박교통관제센터에서는 각종 센서와 다양한 정보를 기반으로 VHF 교신을 통해 선박교통관제를 수행한다. 관제사가 활용하는 레이더, AIS, Port-MIS. 센서 등의 데이터들이 디지털로 저장되고 있으며, 관제사의 VHF 교신내용은 디지털파일로 저장되어 선박교통관제센터의 서버 2개월간 보관된다. 본 논문에서는 관제 결과로 저장되고 있는 관제 로그 데이터를 활용하여 빅데이터를 구성하고 이를 기반으로 유의미한 정보를 생성할 수 있는 방안을 연구하였다.

• Journal of Navigation and Port Research
• /
• v.27 no.6
• /
• pp.645-652
• /
• 2003

A virtual vessel traffic control system is introduced to contribute to prevent a marine accident such as collision and stranding from happening. Existing VTS has its limit. The virtual vessel traffic control system consists of both data acquisition by satellite remote sensing and a simulation of traffic environment stress based on the satellite data, remotely sensed data And it could be used to provide timely and detailed information about the marine safety, including the location, speed and direction of ships, and help us operate vessels safely and efficiently. If environmental stress values are simulated for the ship information derived from satellite data, proper actions can be taken to prevent accidents. Since optical sensor has a high spatial resolution, JERS satellite data are used to track ships and extract their information. We present an algorithm of automatic identification of ship size and velocity. It lastly is shown that based on ship information extracted from JERS data, a qualitative evaluation method of environmental stress is introduced.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2017.11a
• /
• pp.36-38
• /
• 2017

The advent of the era of data age and advances inartificial intelligence technology has led to innovations in various business areas. In particular, many attempts have been made to improve the stability of the marine accident, which has not previously been applied by a data-drive approach. Most of the marine accidents happen at a time when the vessel isapproaching a port and preparing for berthing. Although the cause of the accident has many factors, it is often caused by the difficulties of communication between the ship navigator and the control center. In particular, communication in English makes difficulties for navigators, not English astheir first language. To do this, proper English conversation education forsailors is very important. In order to support the issue, this study presents data and framework for the development of a chatbot for ship safety education.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.10a
• /
• pp.856-859
• /
• 2013

Ships and marine structures(lighthouses and buoys for AtoN) have AIS(Automatic Identification System) for transmission messages which include navigational and environmental information. VTS Center and surrounding ships receive and apply the information to safety navigation. A main characteristic of AIS messages is open to general people, so many researches are in progress. In this paper, we design an information management system which considers marine vessel traffic and environmental information in korean littoral sea. The system gathers and processes the information, and stores the processed data to multi-stage database. Also the system visualizes the stored data to use analysis and statistics based on ENC.

• Journal of the Korean Institute of Navigation
• /
• v.22 no.2
• /
• pp.13-22
• /
• 1998

Shipbome Automatic Identification System (AIS) will be an important manne equipment used for identification, surveillance and communication in the 21st century, which is currently being researched in developed countries. A technical scheme of AlS is proposed in this paper. The main component of the AlS is a broadcast transponder, and the core technology is a VHF radio data link with high capacity, named STDMA (Self-organized Time Division Multiple Access). The ships installed the AlS, which will automatically and periodically broadcast their positions and identities in the marine VHF channels, can be displayed on a screen of an ECDIS on board or in VTS centers. The AlS is able to support not only broadcast service but also point-to-point communication service. This paper presents the configuration, operation principle and functionality of the AlS as well as the scenario of STDMA. In addition, the standardization work of AlS in IMO is introduced in this pauer, too.

• Spatial Information Research
• /
• v.21 no.6
• /
• pp.23-32
• /
• 2013

Recently, there has been much interest in the converged platform that enables the harmonized collection, integration, exchange, presentation and analysis of various kinds of marine information by using the ICT means. Regarding such the converged platform, S-100 standards including the international hydrographic data model are being announced and various studies have been published based on the S-100 standards. However, the existing studies have presented simple solutions for only given problems on the converged service of the maritime information. They could not propose the design concept of the converged platform which makes it possible to provide the standardized and integrated services among the geospatial data, the real-time maritime data, and the next ENC. Therefore, we propose design and implementation details of the converged service platform for the geospatial and the maritime data based on the S-100, WMS, WMTS, WPS, SOS standards. The proposed platform has advantages of supporting both the S-57 and the S-101, supporting the converged services of heterogeneous geospatial data and ENC data, supporting the real-time services of sensor data such as weather, AIS, and CCTV, and supporting the development of various kinds of maritime systems such as ECDIS, ECS, VTS based on the WebApp service. Finally, we proved the effectiveness of our proposed platform through the actual implementation of the converged service of geospatial data, S-101 data, and KWeather data.