• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.12
• /
• pp.4275-4291
• /
• 2021

With the unprecedented growth of textual information on the Internet, an efficient automatic summarization system has become an urgent need. Recently, the neural network models based on the encoder-decoder with an attention mechanism have demonstrated powerful capabilities in the sentence summarization task. However, for paragraphs or longer document summarization, these models fail to mine the core information in the input text, which leads to information loss and repetitions. In this paper, we propose an abstractive document summarization method by applying guidance signals of key sentences to the encoder based on the hierarchical encoder-decoder architecture, denoted as KI-HABS. Specifically, we first train an extractor to extract key sentences in the input document by the hierarchical bidirectional GRU. Then, we encode the key sentences to the key information representation in the sentence level. Finally, we adopt key information representation guided selective encoding strategies to filter source information, which establishes a connection between the key sentences and the document. We use the CNN/Daily Mail and Gigaword datasets to evaluate our model. The experimental results demonstrate that our method generates more informative and concise summaries, achieving better performance than the competitive models.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.9
• /
• pp.3823-3840
• /
• 2020

Recently, auto-encoder has emerged as the most popular method in convolutional neural network (CNN) based image compression and has achieved impressive performance. In the traditional auto-encoder based image compression model, the encoder simply sends the features of last layer to the decoder, which cannot allocate bits over different spatial regions in an efficient way. Besides, these methods do not fully exploit the contextual information under different receptive fields for better reconstruction performance. In this paper, to solve these issues, a novel auto-encoder model is designed for image compression, which can effectively transmit the hierarchical features of the encoder to the decoder. Specifically, we first propose an adaptive bit-allocation strategy, which can adaptively select an importance channel. Then, we conduct the multiply operation on the generated importance mask and the features of the last layer in our proposed encoder to achieve efficient bit allocation. Moreover, we present an additional novel perceptual loss function for more accurate image details. Extensive experiments demonstrated that the proposed model can achieve significant superiority compared with JPEG and JPEG2000 both in both subjective and objective quality. Besides, our model shows better performance than the state-of-the-art convolutional neural network (CNN)-based image compression methods in terms of PSNR.

• 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.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.36C no.1
• /
• pp.1-11
• /
• 1999

In this paper, we proposed a design method of parameterized viterbi decoder, which automatically synthsizes the diverse viterbi deciders used in the digital mobile communication systems. It is designed to synthesize a viterbi decoder specified by user-provided parameters. Those parameters are constraint length, code rate generator polynomials of teh convolutional encoder, data rate and bits/frame of the data transmission, and soft decision bits of viterbi decoder. For the design of the parameterized viterbi decoder, we designed a user interface module C-language, and a viterbi decoder module in a hierarchical atructure using VHDL language and its generic statement. For the verification of the parameterized viterbi decoder, we compared our synthesized viterbi decoder with the conventional viterbi decoder which is designed for the IS-95 CDMA system. The proposed design method of the viterbi decoder will be a new method to obtain a required viterbi decoder in a very short time only by supplying the design parameters.

• KIISE Transactions on Computing Practices
• /
• v.23 no.9
• /
• pp.542-549
• /
• 2017

Sequence-to-sequence models and similar pointer networks suffer from performance degradation when an input is composed of multiple sentences or when the length of the input sentence is long. To solve this problem, this paper proposes a hierarchical pointer network model that uses both the word level and sentence level information to encode input sequences composed of several sentences at the word level and sentence level. We propose a hierarchical pointer network based coreference resolution that performs a coreference resolution for all mentions. The experimental results show that the proposed model has a precision of 87.07%, recall of 65.39% and CoNLL F1 74.61%, which is an improvement of 21.83% compared to an existing rule-based model.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 1998.06b
• /
• pp.5-9
• /
• 1998

In this paper, we propose an error-resilient transmission technique for the H.263 video data stream over wireless networks. The proposed algorithm employs bit rearrangement hierarchically, providing the robust and exact synchronization against the bit errors, without requiring extra redundant information. In addition, we propose the recovery algorithm for the lost or erroneous motion vectors. We implement the encoder and decoder, based on the H.263 standard, and evaluate the proposed algorithm through intensive computer simulation. The experimental results demonstrate that the proposed algorithm yields good image quality, in spite of the channel errors, and prevents the error propagation both in the spatial and the temporal domain efficiently.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.16 no.1
• /
• pp.46-56
• /
• 1991

In this paper, 16word X 8bit Content Addressable and Reentrant Memory(CARM) is described. This device has 4 operation modes(read, write, match, reentrant). The read and write operation of CARM is like that of static RAM, CARM has the reentrant mode operation where the on chip garbage collection is accomplished conditionally. Thus function can be used for high speed matching unit of dynamic data flow computer. And CARM also can encode matching address sequentially according to therir priority. CARM consists of 8 blocks(CAM cell, Sequential Address Encoder(S.A.E). Reentrant operation. Read/Write control circuit, Data/Mask Register, Sense Amplifier, Encoder. Decoder). Designed DARM can be used in data flow computer, pattern, inspection, table look-up, image processing. The simulation is performed using the QUICKSIM logic simulator and Pspice circuit simulator. Having hierarchical structure, the layout was done using the 3{\;}\mu\textrm{m} n well CMOS technology of the ETRI design rule.

• Journal of Korea Multimedia Society
• /
• v.24 no.1
• /
• pp.21-29
• /
• 2021

With the recent increase in the number of households raising pets, various engineering studies have been underway for pets. The final purpose of this study is to automatically generate situation-sensitive captions that can express implicit intentions based on the behavior and sound of cats by embedding the already mature behavioral detection technology of pets as basic element technology in the video capturing research. As a pilot project to this end, this paper proposes a high-level capturing system using optical-flow, RGB, and sound information of cat videos. That is, the proposed system uses video datasets collected in an actual breeding environment to extract feature vectors from the video and sound, then through hierarchical LSTM encoder and decoder, to identify the cat's behavior and its implicit intentions, and to perform learning to create context-sensitive captions. The performance of the proposed system was verified experimentally by utilizing video data collected in the environment where actual cats are raised.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.1
• /
• pp.37-43
• /
• 2023

Compressed still image or video bitstreams require protection from channel errors in a wireless channel. Embedded Zerotree Coding(EZW), SPIHT could have provided unprecedented high performance in image compression with low complexity. If bit error is generated by dint of wireless channel transmission problem, the loss of synchronization on between encoder and decoder causes serious performance degradation. But wavelet zerotree coding algorithms are producing variable-length codewords, extremely sensitive to bit errors. The idea is to partition the lifting coefficients. A many partition of lifting transform coefficients distributes channel error from wireless channel to each partition. Therefore synchronization problem that caused quality deterioration in still image and video stream was improved.

• JSTS:Journal of Semiconductor Technology and Science
• /
• v.17 no.3
• /
• pp.446-457
• /
• 2017

In order to reduce the size of frame memory or bus bandwidth, frame memory compression (FMC) recompresses reconstructed or reference frames of video codecs. This paper proposes a novel FMC design based on discrete wavelet transform (DWT) - set partitioning in hierarchical trees (SPIHT), which supports fine-scalable throughput and is area-efficient. In the proposed design, multi-cores with small block sizes are used in parallel instead of a single core with a large block size. In addition, an appropriate pipelining schedule is proposed. Compared to the previous design, the proposed design achieves the processing speed which is closer to the target system speed, and therefore it is more efficient in hardware utilization. In addition, a scheme in which two passes of SPIHT are merged into one pass called merged refinement pass (MRP) is proposed. As the number of shifters decreases and the bit-width of remained shifters is reduced, the size of SPIHT hardware significantly decreases. The proposed FMC encoder and decoder designs achieve the throughputs of 4,448 and 4,000 Mpixels/s, respectively, and their gate counts are 76.5K and 107.8K. When the proposed design is applied to high efficiency video codec (HEVC), it achieves 1.96% lower average BDBR and 0.05 dB higher average BDPSNR than the previous FMC design.