• IEIE Transactions on Smart Processing and Computing
• /
• v.6 no.4
• /
• pp.262-268
• /
• 2017

Intelligent video surveillance systems have been developed to monitor global areas and find specific target objects using a large-scale database. However, person re-identification presents some challenges, such as pose change and occlusions. To solve the problems, this paper presents an improved person re-identification method using sparse representation and saliency-based dictionary construction. The proposed method consists of three parts: i) feature description based on salient colors and textures for dictionary elements, ii) orthogonal atom selection using cosine similarity to deal with pose and viewpoint change, and iii) measurement of reconstruction error to rank the gallery corresponding a probe object. The proposed method provides good performance, since robust descriptors used as a dictionary atom are generated by weighting some salient features, and dictionary atoms are selected by reducing excessive redundancy causing low accuracy. Therefore, the proposed method can be applied in a large scale-database surveillance system to search for a specific object.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.5
• /
• pp.2468-2483
• /
• 2017

The construction of completely random sensing matrices of Compressive Sensing requires a large number of random numbers while that of deterministic sensing operators often needs complex mathematical operations. Thus both of them have difficulty in acquiring large signals efficiently. This paper focuses on the enhancement of the practicability of the structurally random matrices and proposes a semi-deterministic sensing matrix called Partial Kronecker product of Identity and Hadamard (PKIH) matrix. The proposed matrix can be viewed as a sub matrix of a well-structured, sparse, and orthogonal matrix. Only the row index is selected at random and the positions of the entries of each row are determined by a deterministic sequence. Therefore, the PKIH significantly decreases the requirement of random numbers, which has a complex generating algorithm, in matrix construction and further reduces the complexity of sampling. Besides, in order to process large signals, the corresponding fast sampling algorithm is developed, which can be easily parallelized and realized in hardware. Simulation results illustrate that the proposed sensing matrix maintains almost the same performance but with at least 50% less random numbers comparing with the popular sampling matrices. Meanwhile, it saved roughly 15%-35% processing time in comparison to that of the SRM matrices.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.5
• /
• pp.2539-2554
• /
• 2017

Regression-based image super resolution (SR) methods have shown great advantage in time consumption while maintaining similar or improved quality performance compared to other learning-based methods. In this paper, we propose a novel single image SR method based on hierarchical regression to further improve the quality performance. As an improvement to other regression-based methods, we introduce a hierarchical scheme into the process of learning multiple regressors. First, training samples are grouped into different clusters according to their geometry similarity, which generates the structure layer. Then in each cluster, a compact dictionary can be learned by Sparse Coding (SC) method and the training samples can be further grouped by dictionary atoms to form the detail layer. Last, a series of projection matrixes, which anchored to dictionary atoms, can be learned by linear regression. Experiment results show that hierarchical scheme can lead to regression that is more precise. Our method achieves superior high quality results compared with several state-of-the-art methods.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.8
• /
• pp.3873-3887
• /
• 2018

In this paper, we propose a novel method to recover images corrupted by impulse noise. The proposed method uses two stages: noise detection and filtering. In the first stage, we use pixel values, rank-ordered logarithmic difference values, and median values to train a neural-network-based impulse noise detector. After training, we apply the network to detect noisy pixels in images. In the next stage, we use group-based weighted couple sparse representation to filter the noisy pixels. During this second stage, conventional methods generally use only clean pixels to recover corrupted pixels, which can yield unsuccessful dictionary learning if the noise density is high and the number of useful clean pixels is inadequate. Therefore, we use reconstructed pixels to balance the deficiency. Experimental results show that the proposed noise detector has better performance than the conventional noise detectors. Also, with the information of noisy pixel location, the proposed impulse-noise removal method performs better than the conventional methods, through the recovered images resulting in better quality.

• Journal of Information Processing Systems
• /
• v.16 no.6
• /
• pp.1359-1371
• /
• 2020

In transmitting and receiving such a large amount of data, reliable data communication is crucial for normal operation of a device and to prevent abnormal operations caused by errors. Therefore, in this paper, it is assumed that an error correction code (ECC) that can detect and correct errors by itself is used in an environment where massive data is sequentially received. Because an embedded system has limited resources, such as a low-performance processor or a small memory, it requires efficient operation of applications. In this paper, we propose using an accelerated ECC-decoding technique with a graphics processing unit (GPU) built into the embedded system when receiving a large amount of data. In the matrix-vector multiplication that forms the Hamming code used as a function of the ECC operation, the matrix is expressed in compressed sparse row (CSR) format, and a sparse matrix-vector product is used. The multiplication operation is performed in the kernel of the GPU, and we also accelerate the Hamming code computation so that the ECC operation can be performed in parallel. The proposed technique is implemented with CUDA on a GPU-embedded target board, NVIDIA Jetson TX2, and compared with execution time of the CPU.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.5
• /
• pp.1163-1185
• /
• 2024

With the sharp increase in the volume of literature data, researchers must spend considerable time and energy locating desired papers. A paper recommendation is the means necessary to solve this problem. Unfortunately, the large amount of data combined with sparsity makes personalizing papers challenging. Traditional matrix decomposition models have cold-start issues. Most overlook the importance of information and fail to consider the introduction of noise when using side information, resulting in unsatisfactory recommendations. This study proposes a paper recommendation method (PR-SLSMF) using document-level representation learning with citation-informed transformers (SPECTER) and low-rank and sparse matrix factorization; it uses SPECTER to learn paper content representation. The model calculates the similarity between papers and constructs a weighted heterogeneous information network (HIN), including citation and content similarity information. This method combines the LSMF method with HIN, effectively alleviating data sparsity and cold-start issues and avoiding topic drift. We validated the effectiveness of this method on two real datasets and the necessity of adding side information.

• KIPS Transactions on Computer and Communication Systems
• /
• v.6 no.11
• /
• pp.463-468
• /
• 2017

To sense a wide area with mobile nodes, the uniformity of node deployment is a very important issue. In this paper, we consider the coverage problem to sense big data in sparse mobile ad hoc networks. In most existing works on the coverage problem, it has been assumed that the number of nodes is large enough to cover the area in the network. However, the coverage problem in sparse mobile ad hoc networks differs in the sense that a long-distance between nodes should be formed to avoid the overlapping coverage areas. We formulate the sensor coverage problem in sparse mobile ad hoc networks and provide the solution to the problem by a self-organized approach without a central authority. The experimental results show that our approach is more efficient than the existing ones, subject to both of coverage areas and energy consumption.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.53 no.11
• /
• pp.9-14
• /
• 2016

In the holographic data storage system, the data can be stored more than one bit per pixel and the storage capacity and transmission rate can be increased. In this paper, we proposed a sparse-ON pixel 4/6 balanced-modulation code that the code rate is 1.33 (bit/pixel) with uniform page density. Even though the performance of the proposed sparse-ON pixel 4/6 balanced-code is similar to 2/3 and 6/9 modulation codes, it can increase the storage capacity more than these modulation codes and also store more pages in a volume by reducing the rate of ON pixels to mitigate IPI (inter-page interference).

• Journal of Information Processing Systems
• /
• v.16 no.1
• /
• pp.6-29
• /
• 2020

Biometrics identification using multiple modalities has attracted the attention of many researchers as it produces more robust and trustworthy results than single modality biometrics. In this paper, we present a novel multimodal recognition system that trains a deep learning network to automatically learn features after extracting multiple biometric modalities from a single data source, i.e., facial video clips. Utilizing different modalities, i.e., left ear, left profile face, frontal face, right profile face, and right ear, present in the facial video clips, we train supervised denoising auto-encoders to automatically extract robust and non-redundant features. The automatically learned features are then used to train modality specific sparse classifiers to perform the multimodal recognition. Moreover, the proposed technique has proven robust when some of the above modalities were missing during the testing. The proposed system has three main components that are responsible for detection, which consists of modality specific detectors to automatically detect images of different modalities present in facial video clips; feature selection, which uses supervised denoising sparse auto-encoders network to capture discriminative representations that are robust to the illumination and pose variations; and classification, which consists of a set of modality specific sparse representation classifiers for unimodal recognition, followed by score level fusion of the recognition results of the available modalities. Experiments conducted on the constrained facial video dataset (WVU) and the unconstrained facial video dataset (HONDA/UCSD), resulted in a 99.17% and 97.14% Rank-1 recognition rates, respectively. The multimodal recognition accuracy demonstrates the superiority and robustness of the proposed approach irrespective of the illumination, non-planar movement, and pose variations present in the video clips even in the situation of missing modalities.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.49 no.9
• /
• pp.138-144
• /
• 2012

In this paper, we introduce the time-domain equalizer in orthogonal frequency division multiplexing (OFDM) systems using orthogonal matching pursuit (OMP) algorithm. Since OFDM system inserts guard intervals, it shows robust performance against multi-path fading. However, in Doppler channel, inter-carrier interference (ICI) occurs because an orthogonality of sub-carriers does not maintain. A least squares (LS) algorithm is common method of time-domain equalizer, but if a channel length is longer, the performance deteriorates by noise. The multi-path fading is a summation of the different delay signal. And that has sparse properties in time-domain. Because the OMP algorithm of the compressive sensing (CS) algorithm restores the channel by choosing the important elements of sparse channel, it can reduce the influence of noise. We simulate the performance of time-domain equalizer in OFDM system with various channel environments using OMP algorithm compared with other equalization method.