Multi-task joint sparse representation (MTJSR) is one kind of efficient multi-task learning (MTL) method for solving different problems together using a shared sparse representation. Based on the learning mechanism in human, which is a self-paced learning by gradually training the tasks from easy to difficult, I apply this mechanism into MTJSR, and propose a multi-task joint sparse representation with self-paced learning (MTJSR-SP) algorithm. In MTJSR-SP, the self-paced learning mechanism is considered as a regularizer of optimization function, and an iterative optimization is applied to solve it. Comparing with the traditional MTL methods, MTJSR-SP has more robustness to the noise and outliers. The experimental results on some datasets, i.e. two synthesized datasets, four datasets from UCI machine learning repository, an oxford flower dataset and a Caltech-256 image categorization dataset, are used to validate the efficiency of MTJSR-SP.
In this paper we extend hyperparameter-free sparse signal reconstruction approaches to permit the high-resolution time delay estimation of spread spectrum signals and demonstrate their feasibility in terms of both performance and computation complexity by applying them to the ISO/IEC 24730-2.1 real-time locating system (RTLS). Numerical examples show that the sparse asymptotic minimum variance (SAMV) approach outperforms other sparse algorithms and multiple signal classification (MUSIC) regardless of the signal correlation, especially in the case where the incoming signals are closely spaced within a Rayleigh resolution limit. The performance difference among the hyperparameter-free approaches decreases significantly as the signals become more widely separated. SAMV is sometimes strongly influenced by the noise correlation, but the degrading effect of the correlated noise can be mitigated through the noise-whitening process. The computation complexity of SAMV can be feasible for practical system use by setting the power update threshold and the grid size properly, and/or via parallel implementations.
Lei ZHANG Qingfu FAN Guoxing ZHANG Zhizheng LIANG
Existing trajectory prediction methods suffer from the “data sparsity” and neglect “time awareness”, which leads to low accuracy. Aiming to the problem, we propose a fast time-aware sparse trajectories prediction with tensor factorization method (TSTP-TF). Firstly, we do trajectory synthesis based on trajectory entropy and put synthesized trajectories into the original trajectory space. It resolves the sparse problem of trajectory data and makes the new trajectory space more reliable. Then, we introduce multidimensional tensor modeling into Markov model to add the time dimension. Tensor factorization is adopted to infer the missing regions transition probabilities to further solve the problem of data sparsity. Due to the scale of the tensor, we design a divide and conquer tensor factorization model to reduce memory consumption and speed up decomposition. Experiments with real dataset show that TSTP-TF improves prediction accuracy generally by as much as 9% and 2% compared to the Baseline algorithm and ESTP-MF algorithm, respectively.
Sae IWATA Tomoyuki NITTA Toshinori TAKAYAMA Masao YANAGISAWA Nozomu TOGAWA
Cell phones with GPS function as well as GPS loggers are widely used and users' geographic information can be easily obtained. However, still battery consumption in these mobile devices is main concern and then obtaining GPS positioning data so frequently is not allowed. In this paper, a stayed location estimation method for sparse GPS positioning information is proposed. After generating initial clusters from a sequence of measured positions, the effective radius is set for every cluster based on positioning accuracy and the clusters are merged effectively using it. After that, short-time clusters are removed temporarily but measured positions included in them are not removed. Then the clusters are merged again, taking all the measured positions into consideration. This process is performed twice, in other words, two-stage short-time cluster removal is performed, and finally accurate stayed location estimation is realized even when the GPS positioning interval is five minutes or more. Experiments demonstrate that the total distance error between the estimated stayed location and the true stayed location is reduced by more than 33% and also the proposed method much improves F1 measure compared to conventional state-of-the-art methods.
Seitaro KOYAMA Shunsuke AOKI Toshimichi SAITO
A dynamic neural network has ternary connection parameters and can generate various binary periodic orbits. In order to analyze the dynamics, we present two feature quantities which characterize stability and transient phenomenon of a periodic orbit. Calculating the feature quantities, we investigate influence of connection sparsity on stability of a target periodic orbit corresponding to a circuit control signal. As the sparsity increases, at first, stability of a target periodic orbit tends to be stronger. In the next, the stability tends to be weakened and various transient phenomena exist. In the most sparse case, the network has many periodic orbits without transient phenomenon.
Jinguang HAO Gang WANG Lili WANG Honggang WANG
In this paper, an optimal method is proposed to design sparse-coefficient notch filters with principal basic vectors in the column space of a matrix constituted with frequency samples. The proposed scheme can perform in two stages. At the first stage, the principal vectors can be determined in the least-squares sense. At the second stage, with some components of the principal vectors, the notch filter design is formulated as a linear optimization problem according to the desired specifications. Optimal results can form sparse coefficients of the notch filter by solving the linear optimization problem. The simulation results show that the proposed scheme can achieve better performance in designing a sparse-coefficient notch filter of small order compared with other methods such as the equiripple method, the orthogonal matching pursuit based scheme and the L1-norm based method.
Maoshen JIA Jundai SUN Feng DENG Junyue SUN
In this work, a multiple source separation method with joint sparse and non-sparse components recovery is proposed by using dual similarity determination. Specifically, a dual similarity coefficient is designed based on normalized cross-correlation and Jaccard coefficients, and its reasonability is validated via a statistical analysis on a quantitative effective measure. Thereafter, by regarding the sparse components as a guide, the non-sparse components are recovered using the dual similarity coefficient. Eventually, a separated signal is obtained by a synthesis of the sparse and non-sparse components. Experimental results demonstrate the separation quality of the proposed method outperforms some existing BSS methods including sparse components separation based methods, independent components analysis based methods and soft threshold based methods.
Muhammad ELSHEIKH Mohamed TOLBA Amr M. YOUSSEF
SPARX-128/256 is one of the two versions of the SPARX-128 block cipher family. It has 128-bit block size and 256-bit key size. SPARX has been developed using ARX-based S-boxes with the aim of achieving provable security against single-trail differential and linear cryptanalysis. In this letter, we propose 20-round impossible differential distinguishers for SPARX-128. Then, we utilize these distinguishers to attack 24 rounds (out of 40 rounds) of SPARX-128/256. Our attack has time complexity of 2232 memory accesses, memory complexity of 2160.81 128-bit blocks, and data complexity of 2104 chosen plaintexts.
Xiaoying TAN Yuchun GUO Yishuai CHEN Wei ZHU
The Collaborative Filtering (CF) algorithms work fairly well in personalized recommendation except in sparse data environment. To deal with the sparsity problem, researchers either take into account auxiliary information extracted from additional data resources, or set the missing ratings with default values, e.g., video popularity. Nevertheless, the former often costs high and incurs difficulty in knowledge transference whereas the latter degrades the accuracy and coverage of recommendation results. To our best knowledge, few literatures take advantage of users' preference on video popularity to tackle this problem. In this paper, we intend to enhance the performance of recommendation algorithm via the inference of the users' popularity preferences (PPs), especially in a sparse data environment. We propose a scheme to aggregate users' PPs and a Collaborative Filtering based algorithm to make the inference of PP feasible and effective from a small number of watching records. We modify a k-Nearest-Neighbor recommendation algorithm and a Matrix Factorization algorithm via introducing the inferred PP. Experiments on a large-scale commercial dataset show that the modified algorithm outperforms the original CF algorithms on both the recommendation accuracy and coverage. The significance of improvement is significant especially with the data sparsity.
Wenhua SHI Xiongwei ZHANG Xia ZOU Meng SUN Wei HAN Li LI Gang MIN
A monaural speech enhancement method combining deep neural network (DNN) with low rank analysis and speech present probability is proposed in this letter. Low rank and sparse analysis is first applied on the noisy speech spectrogram to get the approximate low rank representation of noise. Then a joint feature training strategy for DNN based speech enhancement is presented, which helps the DNN better predict the target speech. To reduce the residual noise in highly overlapping regions and high frequency domain, speech present probability (SPP) weighted post-processing is employed to further improve the quality of the speech enhanced by trained DNN model. Compared with the supervised non-negative matrix factorization (NMF) and the conventional DNN method, the proposed method obtains improved speech enhancement performance under stationary and non-stationary conditions.
Rajesh RAMANATHAN Partha Sharathi MALLICK Thiruvengadam SUNDARAJAN JAYARAMAN
In this letter, we propose a generalized quadrature spatial modulation technique (GQSM) which offers additional bits per channel use (bpcu) gains and a low complexity greedy detector algorithm, structured orthogonal matching pursuit (S-OMP)- GQSM, based on compressive sensing (CS) framework. Simulation results show that the bit error rate (BER) performance of the proposed greedy detector is very close to maximum likelihood (ML) and near optimal detectors based on convex programming.
Ryohei SASAKI Katsumi KONISHI Tomohiro TAKAHASHI Toshihiro FURUKAWA
This letter deals with an audio declipping problem and proposes a multiple matrix rank minimization approach. We assume that short-time audio signals satisfy the autoregressive (AR) model and formulate the declipping problem as a multiple matrix rank minimization problem. To solve this problem, an iterative algorithm is provided based on the iterative partial matrix shrinkage (IPMS) algorithm. Numerical examples show its efficiency.
Shilei CHENG Song GU Maoquan YE Mei XIE
Human action recognition in videos draws huge research interests in computer vision. The Bag-of-Word model is quite commonly used to obtain the video level representations, however, BoW model roughly assigns each feature vector to its nearest visual word and the collection of unordered words ignores the interest points' spatial information, inevitably causing nontrivial quantization errors and impairing improvements on classification rates. To address these drawbacks, we propose an approach for action recognition by encoding spatio-temporal log Euclidean covariance matrix (ST-LECM) features within the low-rank and sparse representation framework. Motivated by low rank matrix recovery, local descriptors in a spatial temporal neighborhood have similar representation and should be approximately low rank. The learned coefficients can not only capture the global data structures, but also preserve consistent. Experimental results showed that the proposed approach yields excellent recognition performance on synthetic video datasets and are robust to action variability, view variations and partial occlusion.
The centralized controller of SDN enables a global topology view of the underlying network. It is possible for the SDN controller to achieve globally optimized resource composition and utilization, including optimized end-to-end paths. Currently, resource composition in SDN arena is usually conducted in an imperative manner where composition logics are explicitly specified in high level programming languages. It requires strong programming and OpenFlow backgrounds. This paper proposes declarative path composition, namely Compass, which offers a human-friendly user interface similar to natural language. Borrowing methodologies from Semantic Web, Compass models and stores SDN resources using OWL and RDF, respectively, to foster the virtualized and unified management of the network resources regardless of the concrete controller platform. Besides, path composition is conducted in a declarative manner where the user merely specifies the composition goal in the SPARQL query language instead of explicitly specifying concrete composition details in programming languages. Composed paths are also reused based on similarity matching, to reduce the chance of time-consuming path composition. The experiment results reflect the applicability of Compass in path composition and reuse.
Zhi ZHENG Yuxuan YANG Wen-Qin WANG Guangjun LI Jiao YANG Yan GE
This paper proposes a novel method for two-dimensional (2-D) direction-of-arrival (DOA) estimation of multiple signals employing a sparse L-shaped array structured by a sparse linear array (SLA), a sparse uniform linear array (SULA) and an auxiliary sensor. In this method, the elevation angles are estimated by using the SLA and an efficient search approach, while the azimuth angle estimation is performed in two stages. In the first stage, the rough azimuth angle estimates are obtained by utilizing a noise-free cross-covariance matrix (CCM), the estimated elevation angles and data from three sensors including the auxiliary sensor. In the second stage, the fine azimuth angle estimates can be achieved by using the shift-invariance property of the SULA and the rough azimuth angle estimates. Without extra pair-matching process, the proposed method can achieve automatic pairing of the 2-D DOA estimates. Simulation results show that our approach outperforms the compared methods, especially in the cases of low SNR, snapshot deficiency and multiple sources.
Pei CHEN Dexiu HU Yongjun ZHAO Chengcheng LIU
Aiming at solving the performance degradation caused by the covariance matrix mismatch in wideband beamforming for conformal arrays, a novel adaptive beamforming algorithm is proposed in this paper. In this algorithm, the interference-plus-noise covariance matrix is firstly reconstructed to solve the desired signal contamination problem. Then, a sparse reconstruction method is utilized to reduce the high computational cost and the requirement of sampling data. A novel cost function is formulated by the focusing matrix and singular value decomposition. Finally, the optimization problem is efficiently solved in a second-order cone programming framework. Simulation results using a cylindrical array demonstrate the effectiveness and robustness of the proposed algorithm and prove that this algorithm can achieve superior performance over the existing wideband beamforming methods for conformal arrays.
Jun WANG Guoqing WANG Zaiyu PAN
Gender classification with hand-dorsa vein information, a new soft biometric trait, is solved with the proposed unsupervised sparse feature learning model, state-of-the-art accuracy demonstrates the effectiveness of the proposed model. Besides, we also argue that the proposed data reconstruction model is also applicable to age estimation when comprehensive database differing in age is accessible.
Jun WANG Guoqing WANG Leida LI
A quantized index for evaluating the pattern similarity of two different datasets is designed by calculating the number of correlated dictionary atoms. Guided by this theory, task-specific biometric recognition model transferred from state-of-the-art DNN models is realized for both face and vein recognition.
Takumi KIMURA Norikazu TAKAHASHI
Nonnegative Matrix Factorization (NMF) with sparseness and smoothness constraints has attracted increasing attention. When these properties are considered, NMF is usually formulated as an optimization problem in which a linear combination of an approximation error term and some regularization terms must be minimized under the constraint that the factor matrices are nonnegative. In this paper, we focus our attention on the error measure based on the Euclidean distance and propose a new iterative method for solving those optimization problems. The proposed method is based on the Hierarchical Alternating Least Squares (HALS) algorithm developed by Cichocki et al. We first present an example to show that the original HALS algorithm can increase the objective value. We then propose a new algorithm called the Gauss-Seidel HALS algorithm that decreases the objective value monotonically. We also prove that it has the global convergence property in the sense of Zangwill. We finally verify the effectiveness of the proposed algorithm through numerical experiments using synthetic and real data.
Naoki YAMADA Yuji YAMAGATA Naoki FUKUTA
On an inference-enabled Linked Open Data (LOD) endpoint, usually a query execution takes longer than on an LOD endpoint without inference engine due to its processing of reasoning. Although there are two separate kind of approaches, query modification approaches, and ontology modifications have been investigated on the different contexts, there have been discussions about how they can be chosen or combined for various settings. In this paper, for reducing query execution time on an inference-enabled LOD endpoint, we compare these two promising methods: query rewriting and ontology modification, as well as trying to combine them into a cluster of such systems. We employ an evolutionary approach to make such rewriting and modification of queries and ontologies based on the past-processed queries and their results. We show how those two approaches work well on implementing an inference-enabled LOD endpoint by a cluster of SPARQL endpoints.