• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.37 no.1
• /
• pp.44-51
• /
• 2000

We have analyzed optical matched filters considering the third order signals in the optical code division multiple access (CDMA) system based on optical series coupler access encoder (SCAE) and series coupler access decoder (SCAD). In previous studies, the performance evaluation of the optical CDMA system using SCAE and SCAD was not sufficiently accurate because they analyzed system performance only considering the first order signals. Since optical SCAE and SCAD intrinsically have high order signals of various patterns as the number of coupler increases, they change auto- and cross-correlation intensities. Thus, it is necessary to investigate properties of the third order signals so that we may analyze the exact performance of system. In this paper, we mathematically interpret the optical signals up to the third order, and analyzed the effects of th third order signals on auto- and cross-correlation intensities. In result, as ${\alpha}$(coupling coefficient) value increases, the intensity of the third order signals increases. It is found that the peak to side-lobe ratio considering the third order signals is degraded by 3.75 dB at N(coupler number)=5 and ${\alpha}$=0.5. Also if threshold value in receiver is set by main-lobe peak of the first order signals, it is found that the number of users in an optical CDMA system is limited because the intensity peak of side-lobes is raised by the third order signals.

• 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%.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.6
• /
• pp.1516-1529
• /
• 2023

In this paper, a motor gearbox fault-detection system based on a hierarchical flow-based model is proposed. The proposed system is used for the anomaly detection of a motion sound-based actuator module. The proposed flow-based model, which is a generative model, learns by directly modeling a data distribution function. As the objective function is the maximum likelihood value of the input data, the training is stable and simple to use for anomaly detection. The operation sound of a car's side-view mirror motor is converted into a Mel-spectrogram image, consisting of a folding signal and an unfolding signal, and used as training data in this experiment. The proposed system is composed of an encoder and a decoder. The data extracted from the layer of the pretrained feature extractor are used as the decoder input data in the encoder. This information is used in the decoder by performing an interlayer cross-scale convolution operation. The experimental results indicate that the context information of various dimensions extracted from the interlayer hierarchical data improves the defect detection accuracy. This paper is notable because it uses acoustic data and a normalizing flow model to detect outliers based on the features of experimental data.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.27 no.7C
• /
• pp.712-722
• /
• 2002

We have investigated a novel optical decoder for a fiber-optic code division multiple access(CDMA) communication systems. The conventional optical encoder and decoder have the advantage of simple structure. However the number of users in the system is limited by the auto- and cross-correlation properties generated in decoding process. In previous studies, to improve the system performance, although they used an optical code that minimize the sidelobe and cross-correlation, could not yet find a novel methods for performance improvement in fiber-optic CDMA system. Thus, it is necessary to investigate the novel optical decode in order to improve the performance of system. In this paper, we schematize the AND gate logic element(AGLE) composed with 1$\times$2 or 1$\times$3 coupler and the optical thyristor and propose the novel optical decoder using K(weight) AGLE. The optical thyristor only passes the overlapped signal and clips other signals. Such a novel concept means that the optical thyristor can operate as a hard-limiter. We analyze the fiber-optic CDMA system using the novel optical decoder with simulation and is found that the novel optical decoder using the AGLE and optical thyristor excludes the sidelobe and cross-correlation intensity between any two sequences.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.40 no.6
• /
• pp.84-89
• /
• 2003

In this paper, we real-time implemented to the TMS320C5416 the vocoder of variable bit rate applied the SOLA-B algorithm by Henja to the ITU-T G.729A vocoder of 8kbps transmission rate. This proposed method using the SOLA-B algorithm is that it is reduced the duration of the speech in encoding and is played at the speed of normal by extending the duration of the speech in decoding. At this time, we bandied that the interval of cross correlation function if skipped every 3 sample for decreasing the computational amount of SOLA-B algorithm. The real-time implemented vocoder of C.729A and SOLA-B algorithm is represented the complexity of maximum that is 10.2MIPS in encoder and 2.8MIPS in decoder of 8kbps transmission rate. Also, it is represented the complexity of maximum that is 18.5MIPS in encoder and 13.1MIPS in decoder of 6kbps, it is 18.5MIPS in encoder and 13.1MIPS in decoder of 4kbps. The used memory is about program ROM 9.7kwords, table ROM 4.5kwords, RAM 5.1 kwords. The waveform of output is showed by the result of C simulator and Bit Exact. Also, for evaluation of speech quality of the vocoder of real-time implemented variable bit rate, it is estimated the MOS score of 3.69 in 4kbps.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.8
• /
• pp.341-354
• /
• 2023

The title of a document is the brief summarization of the document. Readers can easily understand a document if we provide them with its title in their preferred styles and the languages. In this research, we propose a cross-lingual and style-based title generation model using multiple adapters. To train the model, we need a parallel corpus in several languages with different styles. It is quite difficult to construct this kind of parallel corpus; however, a monolingual title generation corpus of the same style can be built easily. Therefore, we apply a zero-shot strategy to generate a title in a different language and with a different style for an input document. A baseline model is Transformer consisting of an encoder and a decoder, pre-trained by several languages. The model is then equipped with multiple adapters for translation, languages, and styles. After the model learns a translation task from parallel corpus, it learns a title generation task from monolingual title generation corpus. When training the model with a task, we only activate an adapter that corresponds to the task. When generating a cross-lingual and style-based title, we only activate adapters that correspond to a target language and a target style. An experimental result shows that our proposed model is only as good as a pipeline model that first translates into a target language and then generates a title. There have been significant changes in natural language generation due to the emergence of large-scale language models. However, research to improve the performance of natural language generation using limited resources and limited data needs to continue. In this regard, this study seeks to explore the significance of such research.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.41 no.4
• /
• pp.11-16
• /
• 2004

A simple stopping criterion for iterative decoding based on min-sum processing is presented. While most stopping criteria suggested in the literature, are based on Cross Entropy (CE) and its simplification, the proposed stopping criterion is to check if a decoded sequence is a valid codeword along the encoder trellis structure. This new stopping criterion requires less computational complexity and saves mem4)ry compared to the conventional stopping rules. The numerical results are presented on the 3GPP turbo code and a Serially Concatenated Convolutional Cods (SCCC).

• Journal of the Korean Society for Precision Engineering
• /
• v.16 no.6
• /
• pp.58-65
• /
• 1999

The spinning machine has been developed for a bus and truck wheel disc which is manufactured by spinning process method. This machine has the mechanical structure with bed, 2-column, cross head, 2-vertical slide, 2-horizontal slide with forming roller, clamp slide and main spindle similar to large size vertical lathe. Main spindle attached the mandrel is rotated about 500rpm drived by 280kW power DC motor, and a rotating black material pressed on the mandrel with the clamp slide is spinformed by 2-forming rollers which are attached inner end of the 2-horizontal slides. The 2-vertical and 2-horizontal slides are actuated by the hydraulic cylinder which is controlled by the servo valve individially, and these servo valves are controlled by control signal of the CNC controller which is computed with position signal feedbacked from the encoder sensor. The developed machine can manufacture wheel disc of various section profile without mandrel change because section profile is easily modified using program editing in the CNC controller processor. The wheel disc manufactured by spinning process method has many advantages that the endurance is increased by 2 times and the weight is decreased by 30% compared with a conventional disc.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.221-235
• /
• 2022

Manual inspection of steel box girders on long span bridges is time-consuming and labor-intensive. The quality of inspection relies on the subjective judgements of the inspectors. This study proposes an automated approach to detect and segment cracks in high-resolution images. An end-to-end cascaded framework is proposed to first detect the existence of cracks using a deep convolutional neural network (CNN) and then segment the crack using a modified U-Net encoder-decoder architecture. A Naïve Bayes data fusion scheme is proposed to reduce the false positives and false negatives effectively. To generate the binary crack mask, first, the original images are divided into 448 × 448 overlapping image patches where these image patches are classified as cracks versus non-cracks using a deep CNN. Next, a modified U-Net is trained from scratch using only the crack patches for segmentation. A customized loss function that consists of binary cross entropy loss and the Dice loss is introduced to enhance the segmentation performance. Additionally, a Naïve Bayes fusion strategy is employed to integrate the crack score maps from different overlapping crack patches and to decide whether a pixel is crack or not. Comprehensive experiments have demonstrated that the proposed approach achieves an 81.71% mean intersection over union (mIoU) score across 5 different training/test splits, which is 7.29% higher than the baseline reference implemented with the original U-Net.

• Journal of KIBIM
• /
• v.14 no.2
• /
• pp.1-12
• /
• 2024

The paper proposes a methodology that combines the Random Sample Consensus (RANSAC) algorithm and the Point Cloud Encoder-Decoder Network (PCEDNet) algorithm to automatically extract the length of infrastructure elements from point cloud data acquired through 3D LiDAR scans of retaining walls. This methodology is expected to significantly improve time and cost efficiency compared to traditional manual measurement techniques, which are crucial for the data-driven analysis required in the precision-demanding construction sector. Additionally, the extracted positional and dimensional data can contribute to enhanced accuracy and reliability in Scan-to-BIM processes. The results of this study are anticipated to provide important insights that could accelerate the digital transformation of the construction industry. This paper provides empirical data on how the integration of digital technologies can enhance efficiency and accuracy in the construction industry, and offers directions for future research and application.