• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.21 no.8
• /
• pp.2003-2012
• /
• 1996

The 16- and 32-state Trellis-coded M-ary 4-dimensional (4-D) orthogonal modulation scheme with a frequency-reuse technique have been investigated. Here, 5 coded bits form a rate 4/5 convolutional encoder provide 32 possible symbols. Then the signals are mapped by a M-ary 4-D orthogonal modulator, where each signal has equal energy and is PSK modulated. In the M-ary 4-D modulator, we have employed the vectors which is derived by the optimization technique of signal waveforms in a 4-D sphere. This technique is usedin maximizing the minimum Euclidean distance between a set of signal poits on a multidimensional sphere. By combinig trellis coding with M-ary 4-D modulation and proper set-partitioning, we have obtained a considerable impeovement in the free minimum distance of the system over an AWGN channel. The 16-state scheme obtains coding gains up to 5.5 dB over the uncoded two-independent QPSK scheme and 2.5 dB over the two-independent 2-D TCM scheme. And, the 32-state scheme obtains coding gains up to 6.4 dB over the uncoded two-independent QPSK schemeand 3.4 dB over the two-independent 2-D TCM scheme.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.5 no.9
• /
• pp.1528-1543
• /
• 2011

With increasing the using of wireless technologies in essential fields such as the medical application, this paper proposes different scenarios for the transmission of images over wireless networks. The paper uses the IEEE ZigBee 802.15.4 for applying the proposed schemes. It is a Wireless Personal Area Network (WPAN). This paper presents a novel chaotic interleaving scheme against error bursts. Also, the paper studies the proposed interleaver with the convolutional code with different constraint lengths (K). A comparison study between the standard scheme and proposed schemes for image transmission over a correlated fading channel is presented. The simulation results show the superiority of the proposed chaotic interleaving scheme over the traditional schemes. Also, the chaotic interleaver packet-by-packet basis gives a high quality image with (K=3) and reduces the need for the complex encoder with K=7.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.14 no.1
• /
• pp.1-9
• /
• 2019

In this paper, we propose a method of generating a 2D gray image from LiDAR 3D reflection intensity. The proposed method uses the Fully Convolutional Network (FCN) to generate the gray image from 2D reflection intensity which is projected from LiDAR 3D intensity. Both encoder and decoder of FCN are configured with several convolution blocks in the symmetric fashion. Each convolution block consists of a convolution layer with $3{\times}3$ filter, batch normalization layer and activation function. The performance of the proposed method architecture is empirically evaluated by varying depths of convolution blocks. The well-known KITTI data set for various scenarios is used for training and performance evaluation. The simulation results show that the proposed method produces the improvements of 8.56 dB in peak signal-to-noise ratio and 0.33 in structural similarity index measure compared with conventional interpolation methods such as inverse distance weighted and nearest neighbor. The proposed method can be possibly used as an assistance tool in the night-time driving system for autonomous vehicles.

• International Journal of Computer Science & Network Security
• /
• v.21 no.9
• /
• pp.203-211
• /
• 2021

Image tampering detection and localization have become an active area of research in the field of digital image forensics in recent times. This is due to the widespread of malicious image tampering. This study presents a new method for image tampering detection and localization that combines the advantages of dilated convolution, residual network, and UNET Architecture. Using the UNET architecture as a backbone, we built the proposed network from two kinds of residual units, one for the encoder path and the other for the decoder path. The residual units help to speed up the training process and facilitate information propagation between the lower layers and the higher layers which are often difficult to train. To capture global image tampering artifacts and reduce the computational burden of the proposed method, we enlarge the receptive field size of the convolutional kernels by adopting dilated convolutions in the residual units used in building the proposed network. In contrast to existing deep learning methods, having a large number of layers, many network parameters, and often difficult to train, the proposed method can achieve excellent performance with a fewer number of parameters and less computational cost. To test the performance of the proposed method, we evaluate its performance in the context of four benchmark image forensics datasets. Experimental results show that the proposed method outperforms existing methods and could be potentially used to enhance image tampering detection and localization.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.6 no.4
• /
• pp.3-38
• /
• 1996

The mobile station shall convolutionally encode the data transmitted on the reverse traffic channel and the access channel prior to interleaving. Code symbols output from the convolutional encoder are repeated before being interleaved except the 9600 bps data rate. All the symbols are then interleaved, 64-ary orthogonal modulation, direct-sequence spreading, quadrature spreading, baseband filtering and QPSK transmission. The sync, paging, and forward traffic channel except the pilot channel in the forward CDMA channel are convolutionally encoded, block interleaved, spread with Walsh function at a fixed chip rate of 1.2288 Mcps to provide orthogonal channelization among all code channels. Following the spreading operation, the I and Q impulses are applied to respective baseband filters. After that, these impulses shall be transmitted by QPSK. Authentication in the CDMA system is the process for confirming the identity of the mobile station by exchanging information between a mobile station and the base station. The authentication scheme is to generate a 18-bit hash code from the 152-bit message length appended with 24-bit or 40-bit padding. Several techniques are proposed for the authentication data computation in this paper. To protect sensitive subscriber information, it shall be required enciphering ceratin fields of selected traffic channel signaling messages. The message encryption can be accomplished in two ways, i.e., external encryption and internal encryption.

• Journal of Internet Computing and Services
• /
• v.22 no.3
• /
• pp.9-16
• /
• 2021

This study aims to develop a human activity recognition (HAR) system as a Deep-Learning (DL) classification model, distinguishing various human activities. We solely rely on the signals from a wristband accelerometer worn by a person for the user's convenience. 3-axis sequential acceleration signal data are gathered within a predefined time-window-slice, and they are used as input to the classification system. We are particularly interested in developing a Deep-Learning model that can outperform conventional machine learning classification performance. A total of 13 activities based on the laboratory experiments' data are used for the initial performance comparison. We have improved classification performance using the Convolutional Neural Network (CNN) combined with an auto-encoder feature reduction and parameter tuning. With various publically available HAR datasets, we could also achieve significant improvement in HAR classification. Our CNN model is also compared against Recurrent-Neural-Network(RNN) with Long Short-Term Memory(LSTM) to demonstrate its superiority. Noticeably, our model could distinguish both general activities and near-identical activities such as sitting down on the chair and floor, with almost perfect classification accuracy.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.5
• /
• pp.265-272
• /
• 2022

As the risk of lung cancer has increased, early-stage detection and treatment of cancers have received a lot of attention. Among various medical imaging approaches, computer tomography (CT) has been widely utilized to examine the size and growth rate of lung nodules. However, the process of manual examination is a time-consuming task, and it causes physical and mental fatigue for medical professionals. Recently, many computer-aided diagnostic methods have been proposed to reduce the workload of medical professionals. In recent studies, encoder-decoder architectures have shown reliable performances in medical image segmentation, and it is adopted to predict lesion candidates. However, localizing nodules in lung CT images is a challenging problem due to the extremely small sizes and unstructured shapes of nodules. To solve these problems, we utilize atrous spatial pyramid pooling (ASPP) to minimize the loss of information for a general U-Net baseline model to extract rich representations from various receptive fields. Moreover, we propose mixed-up attention mechanism of reverse, boundary and convolutional block attention module (CBAM) to improve the accuracy of segmentation small scale of various shapes. The performance of the proposed model is compared with several previous attention mechanisms on the LIDC-IDRI dataset, and experimental results demonstrate that reverse, boundary, and CBAM (RB-CBAM) are effective in the segmentation of small nodules.

• Information Systems Review
• /
• v.23 no.1
• /
• pp.23-43
• /
• 2021

Recently, many studies have been conducted to increase the accuracy of stock price prediction by analyzing candlestick charts using artificial intelligence techniques. However, these studies failed to consider the time-series characteristics of candlestick charts and to take into account the emotional state of market participants in data learning for stock price prediction. In order to overcome these limitations, this study produced input data by combining volatility index and candlestick charts to consider the emotional state of market participants, and used the data as input for a new method proposed on the basis of combining variantion autoencoder (VAE) and attention mechanisms for considering the time-series characteristics of candlestick chart. Fifty firms were randomly selected from the S&P 500 index and their stock prices were predicted to evaluate the performance of the method compared with existing ones such as convolutional neural network (CNN) or long-short term memory (LSTM). The results indicated the method proposed in this study showed superior performance compared to the existing ones. This study implied that the accuracy of stock price prediction could be improved by considering the emotional state of market participants and the time-series characteristics of the candlestick chart.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.4
• /
• pp.1594-1617
• /
• 2018

In this paper, we consider a spectrum access scenario which consists of two groups of users, namely Primary Users (PUs) and Secondary Users (SUs) in Cooperative Cognitive Radio Networks (CCRNs). SUs cooperatively relay PUs messages based on Amplify-and-Forward (AF) and Decode-and-Forward (DF) cooperative techniques, in exchange for accessing some of the spectrum for their secondary communications. From the literatures, we found that the Conventional Distributed Algorithm (CDA) and Pragmatic Distributed Algorithm (PDA) aim to maximize the PU sum-rate resulting in a lower sum-rate for the SU. In this contribution, we have investigated a suit of distributed matching algorithms. More specifically, we investigated SU-based CDA (CDA-SU) and SU-based PDA (PDA-SU) that maximize the SU sum-rate. We have also proposed the All User-based PDA (PDA-ALL), for maximizing the sum-rates of both PU and SU groups. A comparative study of CDA, PDA, CDA-SU, PDA-SU and PDA-ALL is conducted, and the strength of each scheme is highlighted. Different schemes may be suitable for different applications. All schemes are investigated under the idealistic scenario involving perfect coding and perfect modulation, as well as under practical scenario involving actual coding and actual modulation. Explicitly, our practical scenario considers the adaptive coded modulation based DF schemes for transmission flexibility and efficiency. More specifically, we have considered the Self-Concatenated Convolutional Code (SECCC), which exhibits low complexity, since it invokes only a single encoder and a single decoder. Furthermore, puncturing has been employed for enhancing the bandwidth efficiency of SECCC. As another enhancement, physical layer security has been applied to our system by introducing a unique Advanced Encryption Standard (AES) based puncturing to our SECCC scheme.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.9A
• /
• pp.694-701
• /
• 2003

In this paper, we present a hardware structure and new features of a smart antenna BTS (Base Transceiver Station) for CDMA2000 1X system. The proposed smart antenna BTS is a composite system consisting of many subsystems, i.e., array antenna element, frequency up/down converters, AD (Analog-to-Digital) and DA (Digital-to-Analog) converters, spreading/despreading units, convolutional encoder/Viterbi decoder, searcher, tracker, beamformer, calibration unit etc. Through the experimental tests, we found that the desired beam-pattern in both uplink and downlink communications is provided through the calibration procedure. Also it has been confirmed that the adaptive beamforming algorithm adopted to our smart antenna BTS is fast and accurate enough to support 4 fingers to each user. In our experiments, commercial mobile terminals operating PCS (Personal Communication System) band have been used. It has been confirmed that the smart antenna BTS tremendously improves the FER (Frame Error Rate) performance compared to the conventional 2-antenna diversity system.