• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 1990.10a
• /
• pp.34-39
• /
• 1990

For the analysis of structures, specifically if it is large-scale, in which case it can not be solved within the core memory, the majority of computation time is consumed In the solution of simultaneous linear equation. In this study an efficient in- and out-of-core column solver for sparse symmetric matrix utilizing memory moving scheme is developed. Compare with existing blocking methods the algorithm is simple, therefore the coding and computational efficiencies are greatly enhanced. Upon available memory size, the solver automatically performs solution within the core or outside core. Analysis example shows that the proposed method efficiently solve the large structural problem on the small-memory microcomputer.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.2
• /
• pp.832-854
• /
• 2019

Action recognition has been studied in computer vision field for years. We present an effective approach to recognize actions using a dimension reduction method, which is applied as a crucial step to reduce the dimensionality of feature descriptors after extracting features. We propose to use sparse matrix and randomized kd-tree to modify it and then propose modified Local Fisher Discriminant Analysis (mLFDA) method which greatly reduces the required memory and accelerate the standard Local Fisher Discriminant Analysis. For feature encoding, we propose a useful encoding method called mix encoding which combines Fisher vector encoding and locality-constrained linear coding to get the final video representations. In order to add more meaningful features to the process of action recognition, the convolutional neural network is utilized and combined with mix encoding to produce the deep network feature. Experimental results show that our algorithm is a competitive method on KTH dataset, HMDB51 dataset and UCF101 dataset when combining all these methods.

• Journal of Korea Multimedia Society
• /
• v.24 no.2
• /
• pp.186-198
• /
• 2021

Security control using surveillance cameras is established when people observe all surveillance videos directly. However, this task is labor-intensive and it is difficult to detect all abnormal situations. In this paper, we propose a deep neural network model, called AT-Net, that automatically detects abnormal situations in the surveillance video, and introduces an automatic video surveillance system developed based on this network model. In particular, AT-Net alleviates the ambiguity of existing abnormal situation detection methods by mapping features representing relationships between people and objects in surveillance video to the new tensor structure based on sparse coding. Through experiments on actual surveillance videos, AT-Net achieved an F1-score of about 89%, and improved abnormal situation detection performance by more than 25% compared to existing methods.

• Journal of IKEEE
• /
• v.23 no.3
• /
• pp.910-916
• /
• 2019

Non-local similarity of natural images is one of highly exploited features in various applications dealing with images. Unique edges, texture, and pattern of the images are frequently repeated over the entire image. Once the similar image blocks are classified into a cluster, representative features of the image blocks can be extracted from the cluster. The bigger the size of the cluster is the better the additive white noise can be separated. Denoising is one of major research topics in the image processing field suppressing the additive noise. In this paper, a denoising algorithm is proposed which first clusters the noisy image blocks based on similarity, extracts the feature of the cluster, and finally recovers the original image. Performance experiments with several images under various noise strengths show that the proposed algorithm recovers the details of the image such as edges, texture, and patterns while outperforming the previous methods in terms of PSNR in removing the additive Gaussian noise.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.31 no.10C
• /
• pp.1000-1010
• /
• 2006

This paper proposes a new architecture for DCT-based motion estimation and compensation. Previous methods do riot take sufficient advantage of the sparseness of 2-D DCT coefficients to reduce execution time. We first derive a recursion equation to perform DCT domain motion estimation more efficiently; we then use it to develop a wavefront array processor (WAP) consisting of processing elements. In addition, we show that the recursion equation enables motion predicted images with different frequency bands, for example, from the images with low frequency components to the images with low and high frequency components. The wavefront way Processor can reconfigure to different motion estimation algorithms, such as logarithmic search and three step search, without architectural modifications. These properties can be effectively used to reduce the energy required for video encoding and decoding. The proposed WAP architecture achieves a significant reduction in computational complexity and processing time. It is also shown that the motion estimation algorithm in the transform domain using SAD (Sum of Absolute Differences) matching criterion maximizes PSNR and the compression ratio for the practical video coding applications when compared to tile motion estimation algorithm in the spatial domain using either SAD or SSD.

• Interdisciplinary Bio Central
• /
• v.4 no.4
• /
• pp.14.1-14.6
• /
• 2012

Splice site prediction in DNA sequence is a basic search problem for finding exon/intron and intron/exon boundaries. Removing introns and then joining the exons together forms the mRNA sequence. These sequences are the input of the translation process. It is a necessary step in the central dogma of molecular biology. The main task of splice site prediction is to find out the exact GT and AG ended sequences. Then it identifies the true and false GT and AG ended sequences among those candidate sequences. In this paper, we survey research works on splice site prediction based on support vector machine (SVM). The basic difference between these research works is nucleotide encoding technique and SVM kernel selection. Some methods encode the DNA sequence in a sparse way whereas others encode in a probabilistic manner. The encoded sequences serve as input of SVM. The task of SVM is to classify them using its learning model. The accuracy of classification largely depends on the proper kernel selection for sequence data as well as a selection of kernel parameter. We observe each encoding technique and classify them according to their similarity. Then we discuss about kernel and their parameter selection. Our survey paper provides a basic understanding of encoding approaches and proper kernel selection of SVM for splice site prediction.

• Annual Conference on Human and Language Technology
• /
• 2018.10a
• /
• pp.652-657
• /
• 2018

With the rapid development of e-commerce, many customers can now express their opinion on various kinds of product at discussion groups, merchant sites, social networks, etc. Discerning a consensus opinion about a product sold online is difficult due to more and more reviews become available on the internet. Opinion Mining, also known as Sentiment analysis, is the task of automatically detecting and understanding the sentimental expressions about a product from customer textual reviews. Recently, researchers have proposed various approaches for evaluation in sentiment mining by applying several techniques for document, sentence and aspect level. Aspect-based sentiment analysis is getting widely interesting of researchers; however, more complex algorithms are needed to address this issue precisely with larger corpora. This paper introduces an approach of knowledge representation for the task of analyzing product aspect rating. We focus on how to form the nature of sentiment representation from textual opinion by utilizing the representation learning methods which include word embedding and compositional vector models. Our experiment is performed on a dataset of reviews from electronic domain and the obtained result show that the proposed system achieved outstanding methods in previous studies.

• Journal of KIISE:Software and Applications
• /
• v.31 no.10
• /
• pp.1412-1417
• /
• 2004

Sparse coding or independent component analysis (ICA) which is a holistic representation, was successfully applied to elucidate early auditor${\gamma}$ processing and to the task of sound classification. In contrast, parts-based representation is an alternative way o) understanding object recognition in brain. In this thesis we employ the non-negative matrix factorization (NMF) which learns parts-based representation in the task of sound classification. Methods of feature extraction from the spectro-temporal sounds using the NMF in the absence or presence of noise, are explained. Experimental results show that NMF-based features improve the performance of sound classification over ICA-based features.

• Journal of the Institute of Convergence Signal Processing
• /
• v.11 no.3
• /
• pp.226-231
• /
• 2010

This paper proposes a new coding technique for constructing error correcting high rate DC-free multimode code using a generator matrix generated from a sparse parity-check matrix. The scheme exploits high rate generator matrixes for producing distinct candidate codewords. The decoding complexity depends on whether the syndrome of the received codeword is zero or not. If the syndrome is zero, the decoding is simply performed by expurgating the redundant bits of the received codeword. Otherwise, the decoding is performed by a sum-product algorithm. The performance of the proposed scheme can achieve a reasonable DC-suppression and a low bit error rate.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.39A no.12
• /
• pp.746-755
• /
• 2014

Compressive sensing (CS) has drawn much interest as a new sampling technique that enables signals to be sampled at a much lower than the Nyquist rate. By noting that the block-based compressive sensing can still keep spatial correlation in measurement domain, in this paper, we propose a novel encoding technique for measurement data obtained in the block-based CS of natural image. We apply discrete wavelet transform (DWT) to decorrelate CS measurements and then assign a proper quantization scheme to those DWT coefficients. Thus, redundancy of CS measurements and bitrate of system are reduced remarkably. Experimental results show improvements in rate-distortion performance by the proposed method against two existing methods of scalar quantization (SQ) and differential pulse-code modulation (DPCM). In the best case, the proposed method gains up to 4 dB, 0.9 dB, and 2.5 dB compared with the Block-based CS-Smoothed Projected Landweber plus SQ, Block-based CS-Smoothed Projected Landweber plus DPCM, and Multihypothesis Block-based CS-Smoothed Projected Landweber plus DPCM, respectively.