Topic modeling as a well-known method is widely applied for not only text data mining but also multimedia data analysis such as video data analysis. However, existing models cannot adequately handle time dependency and multimodal data modeling for video data that generally contain image information and speech information. In this paper, we therefore propose a novel topic model, sequential symmetric correspondence hierarchical Dirichlet processes (Seq-Sym-cHDP) extended from sequential conditionally independent hierarchical Dirichlet processes (Seq-CI-HDP) and sequential correspondence hierarchical Dirichlet processes (Seq-cHDP), to improve the multimodal data modeling mechanism via controlling the pivot assignments with a latent variable. An inference scheme for Seq-Sym-cHDP based on a posterior representation sampler is also developed in this work. We finally demonstrate that our model outperforms other baseline models via experiments.

Early reviews, posted on online review sites shortly after products enter the market, are useful for estimating long-term evaluations of those products and making decisions. However, such reviews can be influenced easily by anomalous reviewers, including malicious and fraudulent reviewers, because the number of early reviews is usually small. It is therefore challenging to detect anomalous reviewers from early reviews and estimate long-term evaluations by reducing their influences. We find that two characteristics of heterogeneity on actual review sites such as Amazon.com cause difficulty in detecting anomalous reviewers from early reviews. We propose ideas for consideration of heterogeneity, and a methodology for computing reviewers' degree of anomaly and estimating long-term evaluations simultaneously. Our experimental evaluations with actual reviews from Amazon.com revealed that our proposed method achieves the best performance in 19 of 20 tests compared to state-of-the-art methodologies.

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.

Evolvable hardware (EHW) based on field-programmable gate arrays (FPGAs) opens up new possibilities towards building efficient adaptive system. State of the art EHW systems based on virtual reconfiguration and dynamic partial reconfiguration (DPR) both have their limitations. The former has a huge area overhead and circuit delay, and the later has slow configuration speed and low flexibility. Therefore a general low-cost fast hybrid reconfiguration architecture is proposed in this paper, which merges the high flexibility of virtual reconfiguration and the low resource cost of DPR. Moreover, the bitstream relocation technology is introduced to save the bitstream storage space, and the discrepancy configuration technology is adopted to reduce reconfiguration time. And an embedded RAM core is adopted to store bitstreams which accelerate the reconfiguration speed further. The proposed architecture is evaluated by the online evolution of digital image filter implemented on the Xilinx Virtex-6 FPGA development board ML605. And the experimental results show that our system has lower resource overhead, higher operating frequency, faster reconfiguration speed and less bitstream storage space in comparison with the previous works.

Self-paced learning (SPL) gradually trains the data from easy to hard, and includes more data into the training process in a self-paced manner. The advantage of SPL is that it has an ability to avoid bad local minima, and the system can improve the generalization performance. However, SPL's system needs an expert to judge the complexity of data at the beginning of training. Generally, this expert does not exist in the beginning, and is learned by gradually training the samples. Based on this consideration, we add an uncertainty of complexity judgment into SPL's system, and propose a self-paced learning with uncertainty prior (SPUP). For efficiently solving our system optimization function, an iterative optimization and statistical simulated annealing method are introduced. The final experimental results indicate that our SPUP has more robustness to the outlier and achieves higher accuracy and less error than SPL.

In this paper, we first propose two batch blind source separation and equalization algorithms based on support vector regression (SVR) for linear time-invariant multiple input multiple output (MIMO) systems. The proposed algorithms combine the conventional cost function of SVR with error functions of classical on-line algorithm for blind equalization: both error functions of constant modulus algorithm (CMA) and radius directed algorithm (RDA) are contained in the penalty term of SVR. To recover all sources simultaneously, the cross-correlations of equalizer outputs are included in the cost functions. Simulation experiments show that the proposed algorithms can recover all sources successfully and compensate channel distortion simultaneously. With the use of iterative re-weighted least square (IRWLS) solution of SVR, the proposed algorithms exhibit low computational complexity. Compared with traditional algorithms, the new algorithms only require fewer samples to achieve convergence and perform a lower residual interference. For multilevel signals, the single algorithms based on constant modulus property usually show a relatively high residual error, then we propose two dual-mode blind source separation and equalization schemes. Between them, the dual-mode scheme based on SVR merely requires fewer samples to achieve convergence and further reduces the residual interference.

Given an edge-weighted bipartite digraph G=(A,B;E), the Bipartite Traveling Salesman Problem (BTSP) asks to find the minimum cost of a Hamiltonian cycle of G, or determine that none exists. When |A|=|B|=n, the BTSP can be solved using polynomial space in O*(42nnlog n) time by using the divide-and-conquer algorithm of Gurevich and Shelah (SIAM Journal of Computation, 16(3), pp.486-502, 1987). We adapt their algorithm for the bipartite case, and show an improved time bound of O*(42n), saving the nlog n factor.

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.

Microblog data contains rich information of real-world events with great commercial values, so microblog-oriented natural language processing (NLP) tasks have grabbed considerable attention of researchers. However, the performance of microblog-oriented Chinese Word Segmentation (CWS) based on deep neural networks (DNNs) is still not satisfying. One critical reason is that the existing microblog-oriented training corpus is inadequate to train effective weight matrices for DNNs. In this paper, we propose a novel active learning method to extend the scale of the training corpus for DNNs. However, due to a large amount of partially overlapped sentences in the microblogs, it is difficult to select samples with high annotation values from raw microblogs during the active learning procedure. To select samples with higher annotation values, parameter λ is introduced to control the number of repeatedly selected samples. Meanwhile, various strategies are adopted to measure the overall annotation values of a sample during the active learning procedure. Experiments on the benchmark datasets of NLPCC 2015 show that our λ-active learning method outperforms the baseline system and the state-of-the-art method. Besides, the results also demonstrate that the performances of the DNNs trained on the extended corpus are significantly improved.

A purpose of password-based anonymous authentication schemes is to provide not only password-based authentication but also user anonymity. In [19], Yang et al., proposed a password-based anonymous authentication scheme (we call it YZWB10 scheme) using the password-protected credentials. In this paper, we discuss user anonymity of the YZWB10 scheme [19] against a third-party attacker, who is much weaker than a malicious server. First, we show that a third-party attacker in the YZWB10 scheme can specify which user actually sent the login request to the server. This attack also indicates that the attacker can link different login requests to be sent later by the same user. Second, we give an effective countermeasure to this attack which does not require any security for storing users' password-protected credentials.

This letter presents a novel tensor voting mechanism — analytic tensor voting (ATV), to get rid of the difficulties in original tensor voting, especially the efficiency. One of the main advantages is its explicit voting formulations, which benefit the completion of tensor voting theory and computational efficiency. Firstly, new decaying function was designed following the basic spirit of decaying function in original tensor voting (OTV). Secondly, analytic stick tensor voting (ASTV) was formulated using the new decaying function. Thirdly, analytic plate and ball tensor voting (APTV, ABTV) were formulated through controllable stick tensor construction and tensorial integration. These make the each voting of tensor can be computed by several non-iterative matrix operations, improving the efficiency of tensor voting remarkably. Experimental results validate the effectiveness of proposed method.

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.

By tracking the changing rate of hard decisions during every two consecutive iterations of the alternating direction method of multipliers (ADMM) penalized decoding, an efficient early termination (ET) criterion is proposed to improve the convergence rate of ADMM penalized decoder for low-density parity-check (LDPC) codes. Compared to the existing ET criterion for ADMM penalized decoding, the proposed method can reduce the average number of iterations significantly at low signal-to-noise ratios with negligible performance degradation.

The integration of VANETs with Internet is required if vehicles are to access IP-based applications. A vehicle must have an IP address, and the IP mobility service should be supported during the movement of the vehicle. VANET standards such as WAVE or C-ITS use IPv6 address auto configuration to allocate an IP address to a vehicle. In C-ITS, NEMO-BS is used to support IP mobility. The vehicle moves rapidly, so reallocation of IP address as well as binding update occurs frequently. The vehicle' communication, however, may be disrupted for a considerable amount of time, and the packet loss occurs during these events. Also, the finding of the home address of the peer vehicle is not a trivial matter. We propose a network based identifier locator separation scheme for VANETs. The scheme uses a vehicle identity based address generation scheme. It eliminates the frequent address reallocation and simplifies the finding of the peer vehicle IP address. In the scheme, a network entity tracks the vehicles in its coverage and the vehicles share the IP address of the network entity for their locators. The network entity manages the mapping between the vehicle's identifier and its IP address. The scheme excludes the vehicles from the mobility procedure, so a vehicle needs only the standard IPv6 protocol stack, and mobility signaling does not occur on the wireless link. The scheme also supports seamlessness, so packet loss is mitigated. The results of a simulation show that the vehicles experience seamless packet delivery.

The separating redundancy is an important concept in the analysis of the error-and-erasure decoding of a linear block code using a parity-check matrix of the code. In this letter, we derive new constructive upper bounds on the second separating redundancies of low-density parity-check (LDPC) codes constructed from projective and Euclidean planes over the field Fq with q even.

This paper presents experimental results of our proposed null-space expansion scheme for multiuser massive multiple-input multiple-output (MIMO) in time varying channels. Multiuser MIMO transmission with the proposed scheme can suppress the inter-user interference (IUI) caused by outdated channel state information (CSI). The excess degrees of freedom (DoFs) of massive MIMO is exploited to perform additional null-steering using past estimated CSI. The signal-to-interference power ratio (SIR) and spectral efficiency performances achieved by the proposed scheme that uses measured CSI is experimentally evaluated. It is confirmed that the proposed scheme shows performance superior to the conventional channel prediction scheme. In addition, IUI can be stably suppressed even in high mobility environments by further increasing the null-space dimension.

Finding linear functions that maximize AUC scores is important in ranking research. A typical approach to the ranking problem is to reduce it to a binary classification problem over a new instance space, consisting of all pairs of positive and negative instances. Specifically, this approach is formulated as hard or soft margin optimization problems over pn pairs of p positive and n negative instances. Solving the optimization problems directly is impractical since we have to deal with a sample of size pn, which is quadratically larger than the original sample size p+n. In this paper, we reformulate the ranking problem as variants of hard and soft margin optimization problems over p+n instances. The resulting classifiers of our methods are guaranteed to have a certain amount of AUC scores.

IoT (Internet of Things) services are emerging and the bandwidth requirements for rich media communication services are increasing exponentially. We propose a virtual edge architecture comprising computation resource management layers and path bandwidth management layers for easy addition and reallocation of new service node functions. These functions are performed by the Virtualized Network Function (VNF), which accommodates terminals covering a corresponding access node to realize fast VNF migration. To increase network size for IoT traffic, VNF migration is limited to the VNF that contains the active terminals, which leads to a 20% reduction in the computation of VNF migration. Fast dynamic bandwidth allocation for dynamic bandwidth paths is realized by proposed Hierarchical Time Slot Allocation of Optical Layer 2 Switch Network, which attain the minimum calculation time of less than 1/100.

We present a GPU (graphics processing unit) accelerated stochastic algorithm implementation for simulating biochemical reaction networks using the latest NVidia architecture. To effectively utilize the massive parallelism offered by the NVidia Pascal hardware, we apply a set of performance tuning methods and guidelines such as exploiting the architecture's memory hierarchy in our algorithm implementation. Based on our experimentation results as well as comparative analysis using CPU-based implementations, we report our initial experiences on the performance of modern GPUs in the context of scientific computing.

A cograph (complement reducible graph) is a graph which can be generated by disjoint union and complement operations on graphs, starting with a single vertex graph. Cographs arise in many areas of computer science and are studied extensively. With the goal of developing an effective data mining method for graph structured data, in this paper we introduce a graph pattern expression, called a cograph pattern, which is a special type of cograph having structured variables. Firstly, we show that a problem whether or not a given cograph pattern g matches a given cograph G is NP-complete. From this result, we consider the polynomial time learnability of cograph pattern languages defined by cograph patterns having variables labeled with mutually different labels, called linear cograph patterns. Secondly, we present a polynomial time matching algorithm for linear cograph patterns. Next, we give a polynomial time algorithm for obtaining a minimally generalized linear cograph pattern which explains given positive data. Finally, we show that the class of linear cograph pattern languages is polynomial time inductively inferable from positive data.