• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.7A
• /
• pp.705-711
• /
• 2004

We propose novel OCDMA system with the structure of reconfigurable may encoder/decoder(RAE/ RAD), which are able to reallocate the 2-D optical codes to each subscriber and recover the transmitted data at all the receiving nodes. We have first implemented the double hard limiters composed of limiting amplifier(first hard limiter) that maintain a level of the encoded data from receiving node and AND detector(second hard limiter) for detecting the position of the encoded data and recovering the data. With the proposed system, it was successfully implemented to recover a specific channel data out of 16 code-multiplxed channels using FPGA and 4 DFB-LDs having distinct wavelengths. From experimental results, the code length resulted from increasing the number of the simultaneously connected channels has been reduced by using 2-D OCDMA multiplexed in time and wavelength instead of 1-D OCDMA. In addition, bit errors phenomenon on account of deterioration of autocorrelation peak-to-side lobe ratio is enhanced by using the double hard limiters composed of AND detector and limiting amplifiers.

• Smart Media Journal
• /
• v.9 no.2
• /
• pp.9-15
• /
• 2020

In this paper, we propose a network model composed of Multi path Encoder-Decoder branches that can recognize each instance from the image. The network has two branches, Dot branch and Segmentation branch for finding the center point of each instance and for recognizing area of the instance, respectively. In the experiment, the CVPPP dataset was studied to distinguish leaves from each other, and the center point detection branch(Dot branch) found the center points of each leaf, and the object segmentation branch(Segmentation branch) finally predicted the pixel area of each leaf corresponding to each center point. In the existing segmentation methods, there were problems of finding various sizes and positions of anchor boxes (N > 1k) for checking objects. Also, there were difficulties of estimating the number of undefined instances per image. In the proposed network, an effective method finding instances based on their center points is proposed.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.5
• /
• pp.37-46
• /
• 2020

Recently, studies of facial attribute editing have obtained realistic results using generative adversarial net (GAN) and encoder-decoder structure. Spatial attention GAN (SaGAN), one of the latest researches, is the method that can change only desired attribute in a face image by spatial attention mechanism. However, sometimes unnatural results are obtained due to insufficient information on face areas. In this paper, we propose an improved SaGAN (MSaGAN) using a guide mask for learning and applying multitask learning approach to improve the limitations of the existing methods. Through extensive experiments, we evaluated the results of the facial attribute editing in therms of the mask loss function and the neural network structure. It has been shown that the proposed method can efficiently produce more natural results compared to the previous methods.

• Journal of the Korea Society of Computer and Information
• /
• v.15 no.6
• /
• pp.1-9
• /
• 2010

This paper proposes a test method for compliance of SMS encoder and decoder modules with 3GPP (3rd Generation Partnership Project) specification on SMS PDU (Protocol Data Unit). The existing tools have focused on providing an SMS gateway and on helping to view and edit a single SMS PDU, which rarely help to resolve the compliance test problem. The proposed compliance test method is based on an automatic generation of SMS PDUs fully compliant with the 3GPP specification by using QuickCheck library written in Haskell. By applying the proposed method to a C-based SMS encoder and decoder in Linux Mobile platform, we have found out several critical bugs such as wrong interpretation of time stamps in BCD format. The automatic SMS PDU generator is reusable in that it only depends on the 3GPP SMS specification. The QuickCheck library is also applicable for testing other network protocol data encoders and decoders, as used in this paper.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.40 no.11
• /
• pp.29-36
• /
• 2003

In this paper, an efficient VLSI architecture for DCTQ module, which consists of 2D-DCT, quantization, AC/DC prediction block, scan conversion, inverse quantization and 2D-IDCT, is presented. The architecture of the module is designed to handle a macroblock data within 1064 cycles and suitable for MPEG-4 video codec handling 30 frame CIF image for both encoder and decoder simultaneously. Only single 1-D DCT/IDCT cores are used for the design instead of 2-D DCT/IDCT, respectively. 1-bit serial distributed arithmetic architecture is adopted for 1-D DCT/IDCT to reduce the hardware area in this architecture. To reduce the power consumption of DCTQ modu1e, we propose the method not to operate the DCTQ modu1e exploiting the SAE(sum of absolute error) value from motion estimation and cbp(coded block pattern). To reduce the AC/DC prediction memory size, the memory architecture and memory access method for AC/DC prediction block is proposed. As the result, the maximum utilization of hardware can be achieved, and power consumption can be minimized. The proposed design is operated on 27MHz clock. The experimental results show that the accuracy of DCT and IDCT meet the IEEE specification.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.39 no.2
• /
• pp.56-68
• /
• 2002

The Universal Variable Length Coding(UVLC) scheme in H.26L has nice features such as error resiliency and two-way decodability. However, it has lower coding efficiency than the conventional Huffman coding. To improve the coding efficiency of UVLC, we Propose to use a dynamic codeword mapping that changes association between symbols and codewords in order to utilize the statistical characteristics of symbols as much as possible but without losing any features of the UVLC. Both encoder and decoder use the same re-association table, and hence the encoder need not send additional overhead for the re-mapping relationship to the decoder. Simulation results show that without significant change of the current H.26L coding scheme, the proposed method additionally attains up to about 8% and about 5% bit reductions respectively in intra and inter frames over the current H.26L encoding method.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 1999.11a
• /
• pp.199-203
• /
• 1999

This paper is on the DSP system design and implementation for real time MPEG-2 AAC multichannel audio, and MPEG-4 object oriented audio coding. This DSP system employs two DSPs of the state of the art TMS320C6701, developed by TI semiconductor. DSP board has PCI interface for downloading application program and control the system. DSP board was designed to use for both encoder and decoder, by setting several switches. The system contains external input and output box also, for A/D and D/A conversion for eight channel audio. The input box converts multi channel digital audio to ADI format, that provides serial interface for eight channel digital audio. And the output box converts ADI format signal to multi channel audio. Through this ADI interface, DSP boards can be connected to input, output box. Implemented DSP system was tested for integration with MPEG-2 AAC encoder and decoder S/W. Currently the DSP system performs realtime AAC 4-channel audio encoding with two DSPs, and 8-channel decoding with one DSP.

• Journal of Korea Multimedia Society
• /
• v.24 no.8
• /
• pp.979-987
• /
• 2021

Multiple Sclerosis (MS) can be early diagnosed by detecting lesions in brain magnetic resonance images (MRI). Unsupervised anomaly detection methods based on autoencoder have been recently proposed for automated detection of MS lesions. However, these autoencoder-based methods were developed only for 2D images (e.g. 2D cross-sectional slices) of MRI, so do not utilize the full 3D information of MRI. In this paper, therefore, we propose a novel 3D autoencoder-based framework for detection of the lesion volume of MS in MRI. We first define a 3D convolutional neural network (CNN) for full MRI volumes, and build each encoder and decoder layer of the 3D autoencoder based on 3D CNN. We also add a skip connection between the encoder and decoder layer for effective data reconstruction. In the experimental results, we compare the 3D autoencoder-based method with the 2D autoencoder models using the training datasets of 80 healthy subjects from the Human Connectome Project (HCP) and the testing datasets of 25 MS patients from the Longitudinal multiple sclerosis lesion segmentation challenge, and show that the proposed method achieves superior performance in prediction of MS lesion by up to 15%.

• Journal of Ocean Engineering and Technology
• /
• v.35 no.4
• /
• pp.287-295
• /
• 2021

This paper describes a recurrent neural network (RNN) for the fault classification of a blade pitch system of a spar-type floating wind turbine. An artificial neural network (ANN) can effectively recognize multiple faults of a system and build a training model with training data for decision-making. The ANN comprises an encoder and a decoder. The encoder uses a gated recurrent unit, which is a recurrent neural network, for dimensionality reduction of the input data. The decoder uses a multilayer perceptron (MLP) for diagnosis decision-making. To create data, we use a wind turbine simulator that enables fully coupled nonlinear time-domain numerical simulations of offshore wind turbines considering six fault types including biases and fixed outputs in pitch sensors and excessive friction, slit lock, incorrect voltage, and short circuits in actuators. The input data are time-series data collected by two sensors and two control inputs under the condition that of one fault of the six types occurs. A gated recurrent unit (GRU) that is one of the RNNs classifies the suggested faults of the blade pitch system. The performance of fault classification based on the gate recurrent unit is evaluated by a test procedure, and the results indicate that the proposed scheme works effectively. The proposed ANN shows a 1.4% improvement in its performance compared to an MLP-based approach.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.11
• /
• pp.501-512
• /
• 2021

Recently, a breakthrough has been made in the NLP area by Transformer techniques based on encoder-decoder. However, this only can be used in mainstream languages where millions of dataset are well-equipped, such as English and Chinese, and there is a limitation that it cannot be used in non-mainstream languages where dataset are not established. In addition, there is a deflection problem that focuses on the beginning of the document in mechanical summarization. Therefore, these methods are not suitable for documents with flows such as fairy tales and novels. In this paper, we propose a hybrid summarization method that does not require a dataset and improves the deflection problem using GAN with two adaptive discriminators. We evaluate our model on the CNN/Daily Mail dataset to verify an objective validity. Also, we proved that the model has valid performance in Korean, one of the non-mainstream languages.