• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2008년도 하계종합학술대회
• /
• pp.769-770
• /
• 2008

Mani Memory DataBase(MMDB) system store their data in main physical memory and provide very high-speed access. Conventional database system are optimized for the particular characteristics of disk storage mechanism. Memory resident systems, on the other hand, use different optimizations to structure and organize data, as well as to make it reliable. This paper provides a brief overview on MMDBs and the results after evaluating the performance of our simple MMDB based on Embedded system.

• 대한임베디드공학회논문지
• /
• 제10권2호
• /
• pp.101-108
• /
• 2015

In this paper, a robust traffic light detection method is proposed by using vision sensor and DGPS(Difference Global Positioning System). The conventional vision-based detection methods are very sensitive to illumination change, for instance, low visibility at night time or highly reflection by bright light. To solve these limitations in visual sensor, DGPS is incorporated to determine the location and shape of traffic lights which are available from traffic light database. Furthermore the geometric relationship between traffic light and vision sensor is used to locate the traffic light in the image by using DGPS information. The empirical results show that the proposed method improves by 51% in detection rate for night time with marginal improvement in daytime environment.

• 대한임베디드공학회논문지
• /
• 제10권2호
• /
• pp.65-71
• /
• 2015

It has been known that GMM (Gaussian Mixture Model) based speaker identification systems using ML (Maximum Likelihood) and WMR (Weighting Model Rank) demonstrate very high performances. However, such systems are not so effective under practical environments, in terms of real time processing, because of their high calculation costs. In this paper, we propose a new speaker-pruning algorithm that effectively reduces the calculation cost. In this algorithm, we select 20% of speaker models having higher likelihood with a part of input speech and apply MWMR (Modified Weighted Model Rank) to these selected speaker models to find out identified speaker. To verify the effectiveness of the proposed algorithm, we performed speaker identification experiments using TIMIT database. The proposed method shows more than 60% improvement of reduced processing time than the conventional GMM based system with no pruning, while maintaining the recognition accuracy.

• 대한임베디드공학회논문지
• /
• 제3권1호
• /
• pp.1-7
• /
• 2008

In this paper, a MSS-NOVO method that combines the HMM composition method with a noise reduction method is proposed for speech recognition in noisy environments. This combined method starts with noise reduction with modified spectral subtraction (MSS) to enhance the input noisy speech, then the noise and voice composition (NOVO) method is applied for making noise adapted models by using the noise in the non-utterance regions of the enhanced noisy speech. In order to evaluate the effectiveness of our proposed method, we compare MSS-NOVO method with other methods, i.e., SS-NOVO, MWF-NOVO. To set up the noisy speech for test, we add White noise to KLE 452 database with different SNRs range from 0dB to 15dB, at 5dB intervals. From the tests, MSS-NOVO method shows average improvement of 66.5% and 13.6% compared with the existing SS-NOVO method and MWF-NOVO method, respectively. Especially our proposed MSS-NOVO method shows a big improvement at low SNRs.

• 대한임베디드공학회논문지
• /
• 제13권6호
• /
• pp.329-335
• /
• 2018

Offline-first strategy is that it allows data to be saved while offline, and when connected online, data is synchronized to ensure that all devices have the same data. Multi-device is a term that shares data through synchronization on various platforms on Android, ios, etc. First, all of the data is stored in the local repository like SQLite and then on the server via HTTP communication. Then, the synchronization is completed by receiving the changed data from the server and storing it in the local repository at the time of the synchronization, and sending the changes to the server from the client. We proposed and implemented a database structure, APIs, and a illustrative application running on PC and Android phone.

• 대한임베디드공학회논문지
• /
• 제17권1호
• /
• pp.67-76
• /
• 2022

Monostatic/Bistatic inverse synthetic aperture radar (ISAR) images are two-dimensional radar cross section (RCS) distributions of a target. When there are many targets in a single radar beam, ISAR images are generated with targets overlapped, so it is difficult to perform the targets identification using the trained database. In addition, it is inefficient to perform target identification using only single monostatic and bistatic ISAR images separately because each method has its own advantages and weaknesses. Therefore, this paper analyzes multiple targets identification performances using monostatic/bistatic ISAR images and proposes a method of identification through fusion of two ISAR images. To identify multiple targets, we use image combination technique using trained single target images. Simulation results show effectiveness of proposed method.

• 대한임베디드공학회논문지
• /
• 제17권3호
• /
• pp.177-183
• /
• 2022

To measure the size and weight of the fish, we developed an automatic fish size measurement system using a deep neural network, where the YOLO (You Only Look Once)v3 model was used. To detect fish, an IP camera with infrared function was installed over the fish pool to acquire image data and used as input data for the deep neural network. Using the bounding box information generated as a result of detecting the fish and the structure for which the actual length is known, the size of the fish can be obtained. A GUI (Graphical User Interface) program was implemented using LabVIEW and RTSP (Real-Time Streaming protocol). The automatic fish size measurement system shows the results and stores them in a database for future work.

• 대한임베디드공학회논문지
• /
• 제19권2호
• /
• pp.101-106
• /
• 2024

For the commercialization of automated vehicles, it is necessary to create various scenarios that can evaluate driving safety and establish a data system that can verify them. Depending on the vehicle's ODD (Operational Design Domain), there are numerous scenarios with various parameters indicating vehicle driving conditions, but no systematic methodology has been proposed to create and combine scenarios to test them. Therefore, projects are actively underway abroad to establish a scenario library for real-world testing or simulation of autonomous vehicles. However, since it is difficult to obtain data, research is being conducted based on simulations that simulate real road. Therefore, in this study, parameters calculated through individual vehicle trajectory data extracted based on roadside CCTV image-based driving environment DB was proposed through the extracted data. This study can be used as basic data for safety standards for scenarios representing various driving behaviors.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2012년도 춘계학술대회
• /
• pp.114-116
• /
• 2012

스마트 모바일 기기의 보편화로 개인 위치 정보에 기반한 다양한 서비스가 가능해졌다. 또한 모바일 기기를 이용한 소셜 미디어 이용자수가 대폭 증가함에 따라 위치에 기반한 다양한 소셜 미디어 서비스에 대한 수요가 증대되고 있다. 이 논문에서는 위치에 기반한 소셜 미디어 데이터베이스에 표준 API를 사용한 접근과 결과의 분석으로 사용자가 필요로 하는 정보를 생성하고 실시간 모바일 서비스를 하기 위한 기술적 기법들에 대하여 소개하고 연구 결과를 보인다.

• 한국경영과학회:학술대회논문집
• /
• 대한산업공학회/한국경영과학회 2000년도 춘계공동학술대회 논문집
• /
• pp.290-293
• /
• 2000

Knowledge discovery refers to the overall process of discovering useful knowledge from data. The linear programming model is a special form of useful knowledge that is embedded in a database. Since formulating models from scratch requires knowledge-intensive efforts, knowledge-based formulation support systems have been proposed in the DSS area. However, they rely on the strict assumption that sufficient domain knowledge should already be captured as a specific knowledge representation form. Hence, the purpose of this paper is to propose a methodology that finds useful knowledge on building linear programming models from a database. The methodology consists of two parts. The first part is to find s first-cut model based on a data dictionary. To do so, we applied the GPS algorithm. The second part is to discover a second-cut model by applying neural network technique. An illustrative example is described to show the feasibility of the proposed methodology.