• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.5
• /
• pp.1396-1412
• /
• 2023

Conversation modeling is an important and challenging task in the field of natural language processing because it is a key component promoting the development of automated humanmachine conversation. Most recent research concerning conversation modeling focuses only on the current utterance (considered as the current question) to generate a response, and thus fails to capture the conversation's logic from its beginning. Some studies concatenate the current question with previous conversation sentences and use it as input for response generation. Another approach is to use an encoder to store all previous utterances. Each time a new question is encountered, the encoder is updated and used to generate the response. Our approach in this paper differs from previous studies in that we explicitly separate the encoding of the question from the encoding of its context. This results in different encoding models for the question and the context, capturing the specificity of each. In this way, we have access to the entire context when generating the response. To this end, we propose a deep neural network-based model, called the Context Model, to encode previous utterances' information and combine it with the current question. This approach satisfies the need for context information while keeping the different roles of the current question and its context separate while generating a response. We investigate two approaches for representing the context: Long short-term memory and Convolutional neural network. Experiments show that our Context Model outperforms a baseline model on both ConvAI2 Dataset and a collected dataset of conversational English.

• Journal of The Institute of Information and Telecommunication Facilities Engineering
• /
• v.11 no.1
• /
• pp.16-22
• /
• 2012

Wireless data communication is easy to be affected by channel noise and degrade reliability and stability by the multipath fading and ISI compared with wired data communication. In this paper, we designed and implemented indoor wireless modem adopted DQPSK modulation scheme for improvement of bandwidth efficiency, and convolutional encoding, Viterbi decoding and hybrid ARQ algorithm combinig FEC with CRC for efficient error control in indoor wireless channel. Testing the implemented wireless modem, we verified the proposed scheme is proper to efficient and reliable indoor wireless data communication.

• Journal of information and communication convergence engineering
• /
• v.16 no.3
• /
• pp.148-152
• /
• 2018

Adversarial attacks on artificial intelligence (AI) systems use adversarial examples to achieve the attack objective. Adversarial examples consist of slightly changed test data, causing AI systems to make false decisions on these examples. When used as a tool for attacking AI systems, this can lead to disastrous results. In this paper, we propose an ensemble of degraded convolutional neural network (CNN) modules, which is more robust to adversarial attacks than conventional CNNs. Each module is trained on degraded images. During testing, images are degraded using various degradation methods, and a final decision is made utilizing a one-hot encoding vector that is obtained by summing up all the output vectors of the modules. Experimental results show that the proposed ensemble network is more resilient to adversarial attacks than conventional networks, while the accuracies for normal images are similar.

• Journal of Communications and Networks
• /
• v.7 no.1
• /
• pp.13-20
• /
• 2005

In this paper, a new multi carrier, direct sequence code division multiple access (MC-DS-CDMA) system is proposed. Our new signal construction is based on convolutional encoding of the transmitted data, serial-to-parallel (S/P) conversion of the encoded data, Walsh-Hadamard-transformation (WHT), a second S/P conversion of the WHT outputs, spread spectrum (SS) modulation with a common pseudo-noise (PN) sequence, and then multicarrier transmission. The system bit error rate (BER) performance in frequency selective fading channel in the presence of additive white Gaussian noise (AWGN) and a jamming tone is analyzed and simulated. The numerical results are compared with those from an orthogonal MC-DS-CDMA system of Sourour and Nakagawa [7]. It is shown that the two systems have almost the same BER performance, but the proposed scheme has better anti-jamming ability.

• Journal of Information Processing Systems
• /
• v.15 no.5
• /
• pp.1171-1178
• /
• 2019

This study proposes a deep neural network model based on an encoder-decoder structure for visual dialogs. Ongoing linguistic understanding of the dialog history and context is important to generate correct answers to questions in visual dialogs followed by questions and answers regarding images. Nevertheless, in many cases, a visual understanding that can identify scenes or object attributes contained in images is beneficial. Hence, in the proposed model, by employing a separate person detector and an attribute recognizer in addition to visual features extracted from the entire input image at the encoding stage using a convolutional neural network, we emphasize attributes, such as gender, age, and dress concept of the people in the corresponding image and use them to generate answers. The results of the experiments conducted using VisDial v0.9, a large benchmark dataset, confirmed that the proposed model performed well.

• Journal of the Semiconductor & Display Technology
• /
• v.21 no.4
• /
• pp.156-162
• /
• 2022

Image compression plays an important role in encoding and improving various forms of images in the digital era. Recent researches have focused on the principle of deep learning as one of the most exciting machine learning methods to show that it is good scheme to analyze, classify and compress images. Various neural networks are able to adapt for image compressions, such as deep neural networks, artificial neural networks, recurrent neural networks and convolution neural networks. In this review paper, we discussed how to apply the rule of deep learning to obtain better image compression with high accuracy, low loss-ness and high visibility of the image. For those results in performance, deep learning methods are required on justified manner with distinct analysis.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.11a
• /
• pp.143-144
• /
• 2020

VVC (Versatile Video Coding)는 HEVC이후 차세대 표준 비디오 코딩으로 JVET(Joint Video Exploration)에 의해 2018년 표준화를 시작하였다. VVC에는 복원픽쳐의 변환-양자화에러에 의해 발생한 블로어, 블로킹, 링잉 아티팩트를 감소시키기 위하여 deblocking filter (DF), sample adaptive offset (SAO), adaptive loop filter(ALF)와 같은 모듈을 사용한다. 한편 CNN (Convolutional Neural Network)은 최근 이미지와 비디오 복원에 높은 성능을 보이고 있다. VVC에서 픽쳐는 CTU (Coding Tree Unit)으로 분할되고 각 CTU는 다시 CU (Coding Unit)으로 분할된다. 그리고 인코딩을 위한 중요한 정보들이 Picture, CTU, CU단위로 디코더에 전송된다. 이 논문에서는 화면 간 예측으로 인코딩 된 픽처에서 블록과 픽처정보를 이용한 딥러닝 기반의 인루프 필터 모델을 제안한다. 제안하는 모델은 화면 간 예측에서 QP, 4×4 블록단위의 모션벡터, 참조블록과의 시간적거리, CU의 깊이를 모델에 추가적인 정보로 이용한다.

• Smart Media Journal
• /
• v.12 no.1
• /
• pp.9-16
• /
• 2023

Recently, a convolutional neural network (CNN) based system is being developed to overcome the limitations of human resources in the apple quality classification of farmhouse. However, since convolutional neural networks receive only images of the same size, preprocessing such as sampling may be required, and in the case of oversampling, information loss of the original image such as image quality degradation and blurring occurs. In this paper, in order to minimize the above problem, to generate a image patch based graph of an original image and propose a random walk-based positional encoding method to apply the graph transformer model. The above method continuously learns the position embedding information of patches which don't have a positional information based on the random walk algorithm, and finds the optimal graph structure by aggregating useful node information through the self-attention technique of graph transformer model. Therefore, it is robust and shows good performance even in a new graph structure of random node order and an arbitrary graph structure according to the location of an object in an image. As a result, when experimented with 5 apple quality datasets, the learning accuracy was higher than other GNN models by a minimum of 1.3% to a maximum of 4.7%, and the number of parameters was 3.59M, which was about 15% less than the 23.52M of the ResNet18 model. Therefore, it shows fast reasoning speed according to the reduction of the amount of computation and proves the effect.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.46 no.7
• /
• pp.13-23
• /
• 2009

In this paper, the network performance of a turbo coded optical code division multiple access (CDMA) system with cross-layer, which is between physical and network layers, concept is analyzed and simulated. We consider physical and MAC layers in a cross-layer concept. An intensity-modulated/direct-detection (IM/DD) optical system employing pulse position modulation (PPM) is considered. In order to increase the system performance, turbo codes composed of parallel concatenated convolutional codes (PCCCs) is utilized. The network performance is evaluated in terms of bit error probability (BEP). From the simulation results, it is demonstrated that turbo coding offers considerable coding gain with reasonable encoding and decoding complexity. Also, it is confirmed that the performance of such an optical CDMA network can be substantially improved by increasing e interleaver length and e number of iterations in e decoding process. The results of this paper can be applied to implement the indoor optical wireless LANs.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.35 no.3C
• /
• pp.255-263
• /
• 2010

In this paper, we present an efficient cooperative transmission scheme for high speed 60GHz WPAN system. In 60GHz, the cooperative transmission with relay is effective scheme because signals are exceedingly attenuated according to the distance and the transmission is impossible when there is no LOS between transmitter and receiver. Moreover, the reliability of signal in destination can be improved by receiving data from a relay as well as a transmitter. However, the overall data rate is reduced because transmission time is more required for relay. To solve this problem, we propose a cooperative transmission scheme with RS-CC serial concatenated codes. In the proposed cooperative transmission scheme, the relay can reduce the transmission data size because the only parity bits of systematic RS code are transmitted after encoding by CC. But the computational complexity is increased at the relay and the destination.