• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.42 no.11
• /
• pp.93-100
• /
• 2005

In this paper, we implement the embedded speech recognition system to support various application services such as audio and video control using speech recognition interface on cars. The embedded speech recognition system is implemented and ported in a DSP board. Because MIC type and speech codecs affect the accuracy of speech recognition. And also, we optimize the simulation and test environment to effectively remove the real noises on a car. We applied a noise suppression and feature compensation algorithm to increase an accuracy of sppech recognition on a car. And we used a context dependent tied-mixture acoustic modeling. The performance evaluation showed high accuracy of proposed system in office environment and even real car environment.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.38 no.12
• /
• pp.29-38
• /
• 2001

Recently, as Internet and its services grow rapidly, IETF(Internet Engineering Task Force) introduced a new switching mechanism, MPLS(Multi-Protocol Label Switching), to solve the problem of the scalability in Internet backbone. In this paper, we implemented the LSR loaded with VC-merging function, which causes LSR's management cost to be significantly reduced. We propose a new VC-merge function which supports differentiated services. In case of network congestion in the output buffer of each core LSR, appling link polices to the output modules of the LSR using the EPD algorithm can prevent the buffer from being overflowed. Simulation was performed for Diffserv by using multiple traffic models and investigated the impact of VC-merge method compared to non VC-merge method. The proposed switch is modeled in VHDL and fabricated using the SAMSUNG $0.5{\mu}m$ SOG process.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.2
• /
• pp.41-52
• /
• 2011

It is important to reduce computational complexity of de-blocking filter for real-time implementation, because it accounts for a great part of total computational complexity of the decoder. Because there are a lot of conditional branches and memory accesses in a decoding loop, it is not easy to speed up the de-blocking filter. Therefore, this paper presents a new algorithm of de-blocking filter minimizing conditional branches and memory accesses. The proposed structure of de-blocking filter enables filter operation to parallelize by software pipelining. The proposed optimization method was implemented on a TMS320DM6467 EVM board and we achieved approximately 46% cycle reduction, compared with that of FFmpeg.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.2
• /
• pp.116-124
• /
• 2011

In this paper, We implemented vessel USN middleware by server-side method considering characteristics of ocean environment. We designed multiple query process module in order to efficient process multidimensional sensor stream data and proposed optimized query plan using Mjoin query and hash table. This paper proposed method that context aware of vessel and manage considering characteristics of ocean. We decided to risk context using SVM algorithm in context awareness management module. As a result, we obtained about 87.5% average accuracy for fire case and about 85.1% average accuracy for vessel risk case by input 5,000 data sets and implemented vessel USN monitoring system.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.17 no.5
• /
• pp.1-8
• /
• 2017

Recently, with the development of ICT technology such as cloud and mobile, image utilization through social networks is increasing rapidly. These images contain personal information, and personal information leakage accidents may occur. As a result, studies are underway to recognize and mask personal information in images. However, optical character recognition, which recognizes personal information in images, varies greatly depending on brightness, contrast, and distortion, and Korean recognition is insufficient. Therefore, in this paper, we design and implement a personal information identification and masking system based on image recognition through deep learning application using CNN algorithm based on optical character recognition method. Also, the proposed system and optical character recognition compares and evaluates the recognition rate of personal information on the same image and measures the face recognition rate of the proposed system. Test results show that the recognition rate of personal information in the proposed system is 32.7% higher than that of optical character recognition and the face recognition rate is 86.6%.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.23 no.1
• /
• pp.47-55
• /
• 2012

This paper describes the developed HILS and test equipment in order to test the performances of MMW(Millimeter-Wave) seeker which can detect and track a high speed of short-range ballistic missile and aircraft. This system is used to 141 horn antenna array, array switching, and gain and phase control algorithm to simulate various kind of targets and trajectory of high speed and maneuver moving target. In addition, it simulates not only velocity and range for these targets but also clutter and jamming environments. System configuration and implementation and the measurement results of major subsystems such as target motion simulator, simulation signal generator, high speed data aquisition unit, and central control unit are presented. These systems could verify the detection and tracking performance of MMW seeker through dynamic real-time test based on simulation flight scenario.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.28 no.4
• /
• pp.347-350
• /
• 2017

In this paper, we implemented a real-time 2.4 GHz direction finding system using a time-modulated array(TMA) and an Universal Software Radio Peripheral(USRP). Our system consists of two commercial monopole antennas, self-designed switch board, and an USRP, and it is controlled using LabVIEW program in real-time. From measured results, it is verified that our system can exactly detect the incident angle within 4 degree in the range of 30 degree. Our direction finding system has advantages of a simple hardware architecture than conventional one with multiple receivers, and a simple algorithm only by using a main lobe and a first side-lobe of switching frequency.

• Journal of Korea Game Society
• /
• v.7 no.3
• /
• pp.59-66
• /
• 2007

Ray tracing is one of the classical global illumination methods to generate a photo-realistic rendering image with various lighting effects such as reflection and refraction. However, there are some restrictions on real-time applications because of its computation load. In order to overcome these limitations, many researches of the ray tracing based on GPU (Graphics Processing Unit) have been presented up to now. In this paper, we implement the ray tracing algorithm by J. Purcell and combine it with two methods in order to improve the rendering performance for interactive applications. First, intersection points of the primary ray are determined efficiently using rasterization on graphics hardware. We then construct the acceleration structure of 3D objects to improve the rendering performance. There are few researches on a detail analysis of improved performance by these considerations in ray tracing rendering. We compare the rendering system with environment mapping based on GPU and implement the wireless remote rendering system. This system is useful for interactive applications such as the realtime composition, augmented reality and virtual reality.

• Structural Engineering and Mechanics
• /
• v.72 no.6
• /
• pp.689-712
• /
• 2019

Time-series models like AR-ARX and ARMAX, provide a robust way to capture the dynamic properties of structures, and their residuals can be effectively used as features for damage detection. Even though several research papers discuss the implementation of AR-ARX and ARMAX models for damage diagnosis, they are basically been exploited so far for detecting the time instant of damage and also the spatial location of the damage. However, the inverse problem associated with damage quantification i.e. extent of damage using time series models is not been reported in the literature. In this paper, an approach to detect the extent of damage by combining the ARMAX model by formulating the inverse problem as a multi-constrained optimization problem and solving using a newly developed hybrid adaptive differential search with dynamic interaction is presented. The proposed variant of the differential search technique employs small multiple populations which perform the search independently and exchange the information with the dynamic neighborhood. The adaptive features and local search ability features are built into the algorithm in order to improve the convergence characteristics and also the overall performance of the technique. The multi-constrained optimization formulations of the inverse problem, associated with damage quantification using time series models, attempted here for the first time, can considerably improve the robustness of the search process. Numerical simulation studies have been carried out by considering three numerical examples to demonstrate the effectiveness of the proposed technique in robustly identifying the extent of the damage. Issues related to modeling errors and also measurement noise are also addressed in this paper.

• The Journal of the Korea Contents Association
• /
• v.11 no.8
• /
• pp.1-13
• /
• 2011

In order to create an intelligent autonomous agent in virtual world, we need a sophisticated design for perception, recognition, judgement and behavior. We develop the perception and recognition functions for such an autonomous agent. Our perception mechanism identifies lines based on differences in color, the primitive visible data, and exploits those lines to grasp shapes and regions in the scene. We develop an inferencing algorithm that can infer the original shape from a damaged or partially hidden shape using its characteristics from the ontology in order to intelligently recognize the perceived shape. Several individually recognized 2D shapes and their spatial relations form 3D shapes and those 3D shapes in turn constitute a scene. Each 3D shape occupies its respective region, and an agent analyzes the associated objects and relevant scenes to recognize things and phenomena. We also develop a mechanism by which an agent uses this recognition function to accumulate and use her knowledge on the scene in the historical context. We implement these functions presented above against an example situation to demonstrate their sophistication and realism.