• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.5 no.1
• /
• pp.41-51
• /
• 2001

In this paper, we presented that the performance of the TCM(Trellis Coded Modulation) using the Euclidean distance is better than that of the convolutional code using the hamming distance under the same bandwidth efficiency. And the TCM DECODER for next generation mobile communication replacing the using convolutional decoder is implemented. Also, for the implementation of the TCM DECODER, the convolutional decoder and the TCM decoder were made by C-language and simulated under AWGN channel with respect to the hard decision and the soft decision. So we proved that performance of the TCM is better than that of the convolutional code. From this result, TCM DECODER, of which constraint length is 3, 5 or 7 and which use the soft decision method, was implemented using the AHDL(Altera Hardware Description Language) and fortified using the Max+plus H version 8.2 of Altera corporation.

• Journal of information and communication convergence engineering
• /
• v.1 no.4
• /
• pp.177-182
• /
• 2003

Conventional multilayer feedforward artificial neural networks are very effective in dealing with spatial problems. To deal with problems with time dependency, some kinds of memory have to be built in the processing algorithm. In this paper we show how the newly proposed Serial Input Neuron (SIN) convolutional decoders can be derived. As an example, we derive the SIN decoder for rate code with constraint length 3. The SIN is tested in Gaussian channel and the results are compared to the results of the optimal Viterbi decoder. A SIN approach to decode convolutional codes is presented. No supervision is required. The decoder lends itself to pleasing implementations in hardware and processing codes with high speed in a time. However, the speed of the current circuits may set limits to the codes used. With increasing speeds of the circuits in the future, the proposed technique may become a tempting choice for decoding convolutional coding with long constraint lengths.

• 제어로봇시스템학회:학술대회논문집
• /
• 2002.10a
• /
• pp.89.1-89
• /
• 2002

Conventional multilayer feedforward artificial neural networks are very effective in dealing with spatial problems. To deal with problems with time dependency, some kinds of memory have to be built in the processing algorithm. In this paper we show how the newly proposed Serial Input Neuron (SIN) convolutional decoders can be derived. As an example, we derive the SIN decoder for \ulcornerrate code with constraint length 3. The SIN is tested in Gaussian channel and the results are compared to the results of the optimal Viterbi decoder. A SIN approach to decode convolutional codes is presented. No supervision is required. The decoder lends itself to pleasing implementations in hardware and processing...

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.8
• /
• pp.3790-3803
• /
• 2018

Content-based image retrieval is an approach used to query images based on their semantics. Semantic based retrieval has its application in all fields including medicine, space, computing etc. Semantically generated binary hash codes can improve content-based image retrieval. These semantic labels / binary hash codes can be generated from unlabeled data using convolutional autoencoders. Proposed approach uses semi-supervised deep hashing with semantic learning and binary code generation by minimizing the objective function. Convolutional autoencoders are basis to extract semantic features due to its property of image generation from low level semantic representations. These representations of images are more effective than simple feature extraction and can preserve better semantic information. Proposed activation and loss functions helped to minimize classification error and produce better hash codes. Most widely used datasets have been used for verification of this approach that outperforms the existing methods.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.33 no.2C
• /
• pp.155-160
• /
• 2008

In this letter, we propose a new design of recursive systematic convolutional (RSC) codes based on the distance spectrum properties which can maximize the performance. Good constituent RSC codes of code rate 1/2 are searched by computer and presented in a table. Their performances are shown by computer simulation. New designed codes shows faster convergences according to iterative decoding and good performances.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.23 no.5
• /
• pp.591-596
• /
• 1986

A binary continuous phase frequency shift keying (CPFSK), whose phase is a continuous function of time and instantaneous frequency is constant, is a bandwidth efficient constant envelope signalling scheme. A transmitting signal is formed by combined coding of a convolutional encoder and a binary CPFSK modulator. The signal is transmitted throuth additive white Gaussian noise(AWGN) channel. If the received signal is detected by a coherent maximum likelihood(ML) receiver, error probability can be expressed approximately in terms of minimum Euclidean distance. We propose rate 2/4 codes for the improvement of error performance without increating the data rate per bandwidth and the receiver complexity. Its minimum Euclidean distances are compared with those of rate \ulcornercodes as a function of modulation index and observation interval.

• ETRI Journal
• /
• v.46 no.4
• /
• pp.633-647
• /
• 2024

In e-commerce platforms, sentiment analysis on an enormous number of user reviews efficiently enhances user satisfaction. In this article, an automated product recommendation system is developed based on machine and deep-learning models. In the initial step, the text data are acquired from the Amazon Product Reviews dataset, which includes 60 000 customer reviews with 14 806 neutral reviews, 19 567 negative reviews, and 25 627 positive reviews. Further, the text data denoising is carried out using techniques such as stop word removal, stemming, segregation, lemmatization, and tokenization. Removing stop-words (duplicate and inconsistent text) and other denoising techniques improves the classification performance and decreases the training time of the model. Next, vectorization is accomplished utilizing the term frequency-inverse document frequency technique, which converts denoised text to numerical vectors for faster code execution. The obtained feature vectors are given to the modified convolutional neural network model for sentiment analysis on e-commerce platforms. The empirical result shows that the proposed model obtained a mean accuracy of 97.40% on the APR dataset.

• Proceedings of the IEEK Conference
• /
• 1999.11a
• /
• pp.83-86
• /
• 1999

In this paper, a serially concatenated space-time code (SCSTC) with bandwidth efficiency and high data rate is studied. The suggested SCSTC is composed of space-time code, the convolutional code and Interleaver. The SCSTC has a very high BER performance than the conventional space-time code. The BER performance of the suggested SCSTC can be proven by using computer simulation through the iterative decoding method. The first decoder uses Symbol-MAP algorithm and the second decoder uses Bit-MAP algorithm for decoding tile information bits. The simulation results show the performance of the suggested SCSTC is better than the conventional Space-Time Code.

• 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 the Institute of Internet, Broadcasting and Communication
• /
• v.8 no.5
• /
• pp.181-186
• /
• 2008

Wireless data transmission is vulnerable to attackers and hackers. Recently, the fast development of wireless communication systems seamlessly increase the demand for security in this area. Moreover, error correction is especially important because various kinds of interferences among wireless devices. In order to solve two above problems, we propose to apply MCC (M-sequence Convolutional Code) in the system which is able to protect information and correct errors. The proposed system can obtain higher secure property by randomly changing the output connections by the proposed M-sequence. Performance of the system is analyzed according to BER (Bit Error Rate) and secure levels. The simulation results revealed that we can get the coding gain of 0.1 dB over conventional convolution coding technique. The proposed algorithm is installed in physical layer and easily implemented. Another advantage of our proposed (M-sequence and convolutional code) is that it can be applied to CDMA (Code Division Multiple Access) communication system.