Current image quality assessment (IQA) methods require the original images for evaluation. However, recently, IQA methods that use machine learning have been proposed. These methods learn the relationship between the distorted image and the image quality automatically. In this paper, we propose an IQA method based on deep learning that does not require a reference image. We show that a convolutional neural network with distortion prediction and fixed filters improves the IQA accuracy.

Direction of arrival (DOA) estimation as a fundamental issue in array signal processing has been extensively studied for many applications in military and civilian fields. Many DOA estimation algorithms have been developed for different application scenarios such as low signal-to-noise ratio (SNR), limited snapshots, etc. However, there are still some practical problems that make DOA estimation very difficult. One of them is the correlation between sources. In this paper, we develop a sparsity-based method to estimate the DOA of coherent signals with sparse linear array (SLA). We adopt the off-grid signal model and solve the DOA estimation problem in the sparse Bayesian learning (SBL) framework. By considering the SLA as a ‘missing sensor’ ULA, our proposed method treats the output of the SLA as a partial output of the corresponding virtual uniform linear array (ULA) to make full use of the expanded aperture character of the SLA. Then we employ the expectation-maximization (EM) method to update the hyper-parameters and the output of the virtual ULA in an iterative manner. Numerical results demonstrate that the proposed method has a better performance in correlated signal scenarios than the reference methods in comparison, confirming the advantage of exploiting the extended aperture feature of the SLA.

This paper presents an efficient wideband two-dimensional direction-of-arrival (DOA) estimation for an L-shaped microphone array. We propose a way to construct a wideband sample cross-correlation matrix without any process of DOA preliminary estimation, such as beamforming technique, by exploiting sample cross-correlation matrices of two different frequencies for all frequency bins. Subsequently, wideband DOAs can be estimated by using this wideband matrix along with a scheme of estimating DOA in a narrowband subspace method. Therefore, a contribution of our study is providing an alternative framework for recent narrowband subspace methods to estimating the DOA of wideband sources directly. It means that this framework enables cutting-edge techniques in the existing narrowband subspace methods to implement the wideband direction estimation for reducing the computational complexity and facilitating the estimation algorithm. Theoretical analysis and effectiveness of the proposed method are substantiated through numerical simulations and experiments, which are performed in reverberating environments. The results show that performance of the proposed method performs better than others over a range of signal-to-noise ratio with just a few microphones. All these advantages make the proposed method a powerful tool for navigation systems based on acoustic signal processing.

In this letter, we investigate a design of efficient antenna allocation at the full duplex receiver (FDR) in a multi-input multi-output multi-eavesdropper (MIMOME) wiretap channel for physical layer security improvement. Specifically, we propose the allocation which are feasible for the practical scenario with self-interference (SI) taken into account, because the jamming signals from FDR not only confuse the eavesdropper but also inevitably cause SI at the FDR. Due to the nolinear and coupling of the antenna allocation optimization problem, we transform the original problem into an integer programming problem. Then, we derive the optimal solution and the corresponding beamforming matrices in closed-form by means of combining spatial alignment and null-space projection method. Furthermore, we present the feasibility condition and full-protection condition, which offer insight into principles that enable more efficient and effective use of FDR in the wiretap channel for security improvement. From the simulation results, we validate the theoretical analysis and demonstrate the outstanding performance of the proposed antennas allocation at FDR.

The periodic disaster backup activity among geographically distributed multiple datacenters consumes huge network resources and therefore imposes a heavy burden on datacenters and transmission links. Previous work aims at least completion time, maximum utility or minimal cost, without consideration of load balance for limited network resources, likely to result in unfair distribution of backup load or significant impact on daily network services. In this paper, we propose a new progressive forwarding disaster backup strategy in the Software Defined Network scenarios to mitigate forwarding burdens on source datacenters and balance backup loads on backup datacenters and transmission links. We construct a new redundancy-aware time-expanded network model to divide time slots according to redundancy requirement, and propose role-switching method over time to utilize forwarding capability of backup datacenters. In every time slot, we leverage two-step optimization algorithm to realize capacity-constrained backup datacenter selection and fair backup load distribution. Simulations results prove that our strategy achieves good performance in load balance under the condition of guaranteeing transmission completion and backup redundancy.

When individuals make a purchase from online sources, they may lack first-hand knowledge of the product. In such cases, they will judge the quality of the item by the reviews other consumers have posted. Therefore, it is significant to determine whether comments about a product are credible. Most often, conventional research on comment credibility has employed supervised machine learning methods, which have the disadvantage of needing large quantities of training data. This paper proposes an unsupervised method for judging comment credibility based on the Biterm Sentiment Latent Dirichlet Allocation (BS-LDA) model. Using this approach, first we derived some distributions and calculated each comment's credibility score via them. A comment's credibility was judged based on whether it achieved a threshold score. Our experimental results using comments from Amazon.com demonstrated that the overall performance of our approach can play an important role in determining the credibility of comments in some situation.

Semi-bent functions have important applications in cryptography and coding theory. 2-rotation symmetric semi-bent functions are a class of semi-bent functions with the simplicity for efficient computation because of their invariance under 2-cyclic shift. However, no construction of 2-rotation symmetric semi-bent functions with algebraic degree bigger than 2 has been presented in the literature. In this paper, we introduce four classes of 2m-variable 2-rotation symmetric semi-bent functions including balanced ones. Two classes of 2-rotation symmetric semi-bent functions have algebraic degree from 3 to m for odd m≥3, and the other two classes have algebraic degree from 3 to m/2 for even m≥6 with m/2 being odd.

MIMO technology, which uses multiple antennas, has been introduced to the mobile terminal to increase communication capacity per unit frequency. However, MIMO suffers from the problem of mutual coupling. If MIMO antennas are closely packed, as in a small wireless terminal, a strong mutual coupling occurs. The mutual coupling degrades radiation efficiency and channel capacity. As modern terminals are likely to use three MIMO antennas, reducing the mutual coupling 3×3 MIMO is essential. Some decoupling methods for three elements have been proposed. Unfortunately, these methods demand that the elements be cross-wired, which complicates fabrication and raises the cost. In this paper, we propose a non-connected decoupling method that uses short stubs and an insertion inductor and confirms that the proposed model offers excellent decoupling and increased radiation efficiency.

Many studies have revealed that the performance of software-based Virtual Network Functions (VNFs) is insufficient for mission-critical networks. Scaling-out approaches, such as auto-scaling of VNFs, could handle a huge amount of traffic; however, the exponential traffic growth confronts us the limitations of both expandability of physical resources and complexity of their management. In this paper, we propose a fast datapath processing method called Packet Aggregation Flow (PA-Flow) that is based on hop-by-hop packet aggregation for more efficient Service Function Chaining (SFC). PA-Flow extends a notion of existing intra-node packet aggregation toward network-wide packet aggregation, and we introduce following three novel features. First, packet I/O overheads at intermediate network devices including NFV-nodes are mitigated by reduction of packet amount. Second, aggregated packets are further aggregated as going through the service chain in a hop-by-hop manner. Finally, next-hop aware packet aggregation is realized using OpenFlow-based flow tables. PA-Flow is designed to be available with various VNF forms (e.g. VM/container/baremetal-based) and virtual I/O technologies (e.g. vhost-user/SR-IOV), and its implementation does not bring noticeable delay for aggregation. We conducted two evaluations: (i) a baseline evaluation for understanding fundamental performance characteristics of PA-Flow (ii) a simulation-based SFC evaluation for proving PA-Flow's effect in a realistic environment. The results showed that throughput of short packet forwarding was improved by 4 times. Moreover, the total number of packets was reduced by 93% in a large-scale SFC.

This paper proposes a novel Depth From Defocus (DFD) technique based on the property that two images having different focus settings coincide if they are reblurred with the opposite focus setting, which is referred to as the “cross reblurring” property in this paper. Based on the property, the proposed technique estimates the block-wise depth profile for a target object by minimizing the mean squared error between the cross-reblurred images. Unlike existing DFD techniques, the proposed technique is free of lens parameters and independent of point spread function models. A compensation technique for a possible pixel disalignment between images is also proposed to improve the depth estimation accuracy. The experimental results and comparisons with the other DFD techniques show the advantages of our technique.

An R-peak detection method with a high noise tolerance is presented in this paper. This method utilizes a customized deep convolution neural network (DCNN) to extract morphological and temporal features from sliced electrocardiogram (ECG) signals. The proposed network adopts multiple parallel dilated convolution layers to analyze features from diverse fields of view. A sliding window slices the original ECG signals into segments, and then the network calculates one segment at a time and outputs every point's probability of belonging to the R-peak regions. After a binarization and a deburring operation, the occurrence time of the R-peaks can be located. Experimental results based on the MIT-BIH database show that the R-peak detection accuracies can be significantly improved under high intensity of the electrode motion artifact or muscle artifact noise, which reveals a higher performance than state-of-the-art methods.

The capacity of optical transport networks has been increasing steadily and the networks are becoming more dynamic, complex, and transparent. Though it is common to use worst case assumptions for estimating the quality of transmission (QoT) in the physical layer, over provisioning results in high margin requirements. Accurate estimation on the QoT for to-be-established lightpaths is crucial for reducing provisioning margins. Machine learning (ML) is regarded as one of the most powerful methodological approaches to perform network data analysis and enable automated network self-configuration. In this paper, an artificial neural network (ANN) framework, a branch of ML, to estimate the optical signal-to-noise ratio (OSNR) of to-be-established lightpaths is proposed. It takes account of both nonlinear interference between spectrum neighboring channels and optical monitoring uncertainties. The link information vector of the lightpath is used as input and the OSNR of the lightpath is the target for output of the ANN. The nonlinear interference impact of the number of neighboring channels on the estimation accuracy is considered. Extensive simulation results show that the proposed OSNR estimation scheme can work with any RWA algorithm. High estimation accuracy of over 98% with estimation errors of less than 0.5dB can be achieved given enough training data. ANN model with R=4 neighboring channels should be used to achieve more accurate OSNR estimates. Based on the results, it is expected that the proposed ANN-based OSNR estimation for new lightpath provisioning can be a promising tool for margin reduction and low-cost operation of future optical transport networks.

This paper deals with the problem of minimizing roundoff noise and pole sensitivity simultaneously subject to l2-scaling constraints for state-space digital filters. A novel measure for evaluating roundoff noise and pole sensitivity is proposed, and an efficient technique for minimizing this measure by jointly optimizing state-space realization and error feedback is explored, namely, the constrained optimization problem at hand is converted into an unconstrained problem and then the resultant problem is solved by employing a quasi-Newton algorithm. A numerical example is presented to demonstrate the validity and effectiveness of the proposed technique.

Fill-a-Pix is a pencil-and-paper puzzle, which is popular worldwide since announced by Conceptis in 2003. It provides a rectangular grid of squares that must be filled in to create a picture. Precisely, we are given a rectangular grid of squares some of which has an integer from 0 to 9 in it, and our task is to paint some squares black so that every square with an integer has the same number of painted squares around it including the square itself. Despite its popularity, computational complexity of Fill-a-Pix has not been known. We in this paper show that the puzzle is NP-complete, ASP-complete, and #P-complete via a parsimonious reduction from the Boolean satisfiability problem. We also consider the fewest clues problem of Fill-a-Pix, where the fewest clues problem is recently introduced by Demaine et al. for analyzing computational complexity of designing “good” puzzles. We show that the fewest clues problem of Fill-a-Pix is Σ2P-complete.

We propose a novel decoding algorithm called “sampling decoding”, which is constructed using a Markov Chain Monte Carlo (MCMC) method and implements Maximum a Posteriori Probability decoding in an approximate manner. It is also shown that sampling decoding can be easily extended to universal coding or to be applicable for Markov sources. In simulation experiments comparing the proposed algorithm with the sum-product decoding algorithm, sampling decoding is shown to perform better as sample size increases, although decoding time becomes proportionally longer. The mixing time, which measures how large a sample size is needed for the MCMC process to converge to the limiting distribution, is evaluated for a simple coding matrix construction.

In conventional video streaming systems, various kind of video streams are delivered from a dedicated server (e.g., edge server) to the subscribers so that a video stream of higher quality level is encoded with a higher bitrate. In this paper, we consider the problem of delivering those video streams with the assistance of Peer-to-Peer (P2P) technology with as small server cost as possible while keeping the performance of video streaming in terms of the throughput and the latency. The basic idea of the proposed method is to divide a given video stream into several sub-streams called stripes as evenly as possible and to deliver those stripes to the subscribers through different tree-structured overlays. Such a stripe-based approach could average the load of peers, and could effectively resolve the overloading of the overlay for high quality video streams. The performance of the proposed method is evaluated numerically. The result of evaluations indicates that the proposed method significantly reduces the server cost necessary to guarantee a designated delivery hops, compared with a naive tree-based scheme.

We propose an efficient coding scheme for a dense light field, i.e., a set of multi-viewpoint images taken with very small viewpoint intervals. The key idea behind our proposal is that a light field is represented using only weighted binary images, where several binary images and corresponding weight values are chosen so as to optimally approximate the light field. The proposed coding scheme is completely different from those of modern image/video coding standards that involve more complex procedures such as intra/inter-frame prediction and transforms. One advantage of our method is the extreme simplicity of the decoding process, which will lead to a faster and less power-hungry decoder than those of the standard codecs. Another useful aspect of our proposal is that our coding method can be made scalable, where the accuracy of the decoded light field is improved in a progressive manner as we use more encoded information. Thanks to the divide-and-conquer strategy adopted for the scalable coding, we can also substantially reduce the computational complexity of the encoding process. Although our method is still in the early research phase, experimental results demonstrated that it achieves reasonable rate-distortion performances compared with those of the standard video codecs.

An HDR (High Dynamic Range) image synthesis is a method which is to photograph scenes with wide luminance range and to reproduce images close to real visual scenes on an LDR (Low Dynamic Range) display. In general, HDR images are reproduced by taking images with various camera exposures and using the tone synthesis of several images. In this paper, we propose an HDR image tone mapping method based on a visual brightness function using dual exposed images and a synthesis algorithm based on local surround. The proposed algorithm has improved boundary errors and color balance compared with existing methods. Also, it improves blurring and noise amplification due to image mixing.

Recently, more and more people start investing. Understanding the factors affecting financial products is important for making investment decisions. However, it is difficult to understand factors for novices because various factors affect each other. Various technique has been studied, but conventional factor analysis methods focus on revealing the impact of factors over a certain period locally, and it is not easy to predict net asset values. As a reasonable solution for the prediction of net asset values, in this paper, we propose a trend shift model for the global analysis of factors by introducing trend change points as shift interference variables into state space models. In addition, to realize the trend shift model efficiently, we propose an effective trend detection method, TP-TBSM (two-phase TBSM), by extending TBSM (trend-based segmentation method). Comparing with TBSM, TP-TBSM could detect trends flexibly by reducing the dependence on parameters. We conduct experiments with eleven investment trust products and reveal the usefulness and effectiveness of the proposed model and method.

Since the development of food diaries could enable people to develop healthy eating habits, food image recognition is in high demand to reduce the effort in food recording. Previous studies have worked on this challenging domain with datasets having fixed numbers of samples and classes. However, in the real-world setting, it is impossible to include all of the foods in the database because the number of classes of foods is large and increases continually. In addition to that, inter-class similarity and intra-class diversity also bring difficulties to the recognition. In this paper, we solve these problems by using deep convolutional neural network features to build a personalized classifier which incrementally learns the user's data and adapts to the user's eating habit. As a result, we achieved the state-of-the-art accuracy of food image recognition by the personalization of 300 food records per user.