In the shadow theory, a new description and a physical mean at a low grazing limit of incidence on gratings in the two dimensional scattering problem have been discussed. In this paper, by applying the shadow theory to the three dimensional problem of multilayered dielectric periodic gratings, we formulate the oblique primary excitation and introduce the scattering factors through our analytical method, by use of the matrix eigenvalues. In terms of the scattering factors, the diffraction efficiencies are defined for propagating and evanescent waves with linearly and circularly polarized incident waves. Numerical examples show that when an incident angle becomes low grazing, only specular reflection occurs with the reflection coefficient -1, regardless of the incident polarization. It is newly found that in a circularly polarized incidence case, the same circularly polarized wave as the incident wave is specularly reflected at a low grazing limit.

In the Coordinated Multi-Point (CoMP) system under the condition of limited feedback, a reasonable coordinated set relies heavily on the splitting factor that is used to divide the total feedback bits into channel direction information (CDI) feedback bits and channel quality information (CQI) feedback bits. The relation of splitting factor and coordinated set is examined in this paper. After defining a penalty factor, we derive the net ergodic capacity optimization problem, whose variables to be optimized are the number of coordinated BSs, the divided area's radius and the splitting factor. According to an existing codebook and the quantized channel error model, the downlink received signal model is updated after adding the splitting factor. Through random matrix knowledge, the stochastic property of this model is obtained. A close approximate expression including the splitting factor to be optimized related to coordinated set is given. In addition, a revised adaptive feedback scheme is proposed to split the feedback bits. Simulation results show that the proposed scheme provides a significant performance gain, especially as the user velocity is high.

To improve the data rate in OFDMA-based wireless networks, Carrier Aggregation (CA) technology has been included in the LTE-Advanced standard. Different Carrier Component (CC) capacities of users under the same eNodeB (eNB, i.e. Base Station) make it challenging to allocate resources with CA. In this paper, we jointly consider CC and Resource Block (RB) assignments, and power allocation to achieve proportional fairness in the long term. The goal of the problem is to maximize the overall throughput with fairness consideration. We consider a more general CC assignment framework that each User Equipment (UE) (i.e. Mobile Station) can support any number of CCs. Furthermore, we have proved the problem is NP-hard, even if power is equally allocated to RBs. Thus, first an optimal RB assignment and power allocation algorithm is proposed and then a carrier aggregation enabled joint resource allocation algorithm called CARA is proposed. By jointly considering CC and RB assignments, and power allocation, the proposed approach can achieve better performance. Simulation results show the proposed algorithm can significantly improve performance, e.g., total throughput compared with the existing algorithm.

Soccer player tracking and labeling suffer from the similar appearance of the players in the same team, especially in long-shot scenes where the faces and the numbers of the players are too blurry to identify. In this paper, we propose an efficient multi-player tracking system. The tracking system takes the detection responses of a human detector as inputs. To realize real-time player detection, we generate a spatial proposal to minimize the scanning scope of the detector. The tracking system utilizes the discriminative appearance models trained using the online Boosting method to reduce data-association ambiguity caused by the appearance similarity of the players. We also propose to build an online learned player recognition model which can be embedded in the tracking system to approach online player recognition and labeling in tracking applications for long-shot scenes by two stages. At the first stage, to build the model, we utilize the fast k-means clustering method instead of classic k-means clustering to build and update a visual word vocabulary in an efficient online manner, using the informative descriptors extracted from the training samples drawn at each time step of multi-player tracking. The first stage finishes when the vocabulary is ready. At the second stage, given the obtained visual word vocabulary, an incremental vector quantization strategy is used to recognize and label each tracked player. We also perform importance recognition validation to avoid mistakenly recognizing an outlier, namely, people we do not need to recognize, as a player. Both quantitative and qualitative experimental results on the long-shot video clips of a real soccer game video demonstrate that, the proposed player recognition model performs much better than some state-of-the-art online learned models, and our tracking system also performs quite effectively even under very complicated situations.

Checkpoint-rollback recovery, which is a universal method for restoring distributed systems after faults, requires a sophisticated snapshot algorithm especially if the systems are large-scale, since repeatedly taking global snapshots of the whole system requires unacceptable communication cost. As a sophisticated snapshot algorithm, a partial snapshot algorithm has been introduced that takes a snapshot of a subsystem consisting only of the nodes that are communication-related to the initiator instead of a global snapshot of the whole system. In this paper, we modify the previous partial snapshot algorithm to create a new one that can take a partial snapshot more efficiently, especially when multiple nodes concurrently initiate the algorithm. Experiments show that the proposed algorithm greatly reduces the amount of communication needed for taking partial snapshots.

This letter presents a scheme to improve the running time of exemplar-based image inpainting, first proposed by Criminisi et al. In the exemplar-based image inpainting, a patch that contains unknown pixels is compared to all the patches in the known region in order to find the best match. This is very time-consuming and hinders the practicality of Criminisi's method to be used in real time. We show that a simple bounding algorithm can significantly reduce number of distance calculations, and thus the running time. Performance of the bounding algorithm is affected by the order of patches that are compared, as well as the order of pixels in a patch. We present pixel and patch ordering schemes that improve the performance of bounding algorithms. Experiments with well-known images used in inpainting literature show that the proposed reordering scheme can reduce running time of the bounding algorithm up to 50%.

Most of scientists except computer scientists do not want to make efforts for performance tuning with rewriting their MPI applications. In addition, the number of processing elements which can be used by them is increasing year by year. On large-scale parallel systems, the number of accumulated messages on a message buffer tends to increase in some of their applications. Since searching message queue in MPI is time-consuming, system side scalable acceleration is needed for those systems. In this paper, a support function named LHS (Limited-length Head Separation) is proposed. Its performance in searching message buffer and hardware cost are evaluated. LHS accelerates searching message buffer by means of switching location to store limited-length heads of messages. It uses the effects such as increasing hit rate of cache on host with partial off-loading to hardware. Searching speed of message buffer when the order of message reception is different from the receiver's expectation is accelerated 14.3 times with LHS on FPGA-based network interface card (NIC) named DIMMnet-2. This absolute performance is 38.5 times higher than that of IBM BlueGene/P although the frequency is 8.5times slower than BlueGene/P. LHS has higher scalability than ALPU in the performance per frequency. Since these results are obtained with partially on loaded linear searching on old Pentium®4, performance gap will increase using state of art CPU. Therefore, LHS is more suitable for larger parallel systems. The discussions for adopting proposed method to state of art processors and systems are also presented.

This paper proposes a novel practical path planning framework for autonomous parking in cluttered environments with narrow passages. The proposed global path planning method is based on an improved Fast Marching algorithm to generate a path while considering the moving forward and backward maneuver. In addition, the Support Vector Machine is utilized to provide the maximum clearance from obstacles considering the vehicle dynamics to provide a safe and feasible path. The algorithm considers the most critical points in the map and the complexity of the algorithm is not affected by the shape of the obstacles. We also propose an autonomous parking scheme for different parking situation. The method is implemented on autonomous vehicle platform and validated in the real environment with narrow passages.

Face verification is the task of determining whether two given face images represent the same person or not. It is a very challenging task, as the face images, captured in the uncontrolled environments, may have large variations in illumination, expression, pose, background, etc. The crucial problem is how to compute the similarity of two face images. Metric learning has provided a viable solution to this problem. Until now, many metric learning algorithms have been proposed, but they are usually limited to learning a linear transformation. In this paper, we propose a nonlinear metric learning method, which learns an explicit mapping from the original space to an optimal subspace using deep Independent Subspace Analysis (ISA) network. Compared to the linear or kernel based metric learning methods, the proposed deep ISA network is a deep and local learning architecture, and therefore exhibits more powerful ability to learn the nature of highly variable dataset. We evaluate our method on the Labeled Faces in the Wild dataset, and results show superior performance over some state-of-the-art methods.

A virtual machine (VM) migration is useful for improving flexibility and maintainability in cloud computing environments. However, VM monitor (VMM)-bypass I/O technologies, including PCI passthrough and SR-IOV, in which the overhead of I/O virtualization can be significantly reduced, make VM migration impossible. This paper proposes a novel and practical mechanism, called Symbiotic Virtualization (SymVirt), for enabling migration and checkpoint/restart on a virtualized cluster with VMM-bypass I/O devices, without the virtualization overhead during normal operations. SymVirt allows a VMM to cooperate with a message passing layer on the guest OS, then it realizes VM-level migration and checkpoint/restart by using a combination of a user-level dynamic device configuration and coordination of distributed VMMs. We have implemented the proposed mechanism on top of QEMU/KVM and the Open MPI system. All PCI devices, including Infiniband, Ethernet, and Myrinet, are supported without implementing specific para-virtualized drivers; and it is not necessary to modify either of the MPI runtime and applications. Using the proposed mechanism, we demonstrate reactive and proactive FT mechanisms on a virtualized Infiniband cluster. We have confirmed the effectiveness using both a memory intensive micro benchmark and the NAS parallel benchmark.

We analyze a power adaptation method to maximize the achievable rate under the finite block length regime, for MIMO block fading channel with channel state information available at both the transmitter and receiver side. We find a convex approximation to the lower bound of the achievable rate, and it leads to a simple power and rate adaptation method. We show that the method achieves near optimal channel rate under the finite block length regime. Compared to the classical waterfilling method, the proposed method can further improve achievable rate especially for short block lengths.

Open faults are difficult to test since the voltage at the floating line is unpredictable and depends on the voltage at the adjacent lines. The effect of open faults can be easily excited if a test pattern provides the opposite logic value to most of the adjacent lines. In this paper, we present a procedure to generate as high a quality test as possible. We define the test quality for evaluating the effect of adjacent lines by assigning an opposite logic value to the faulty line. In our proposed test generation method, we utilize the SAT-based ATPG method. We generate test patterns that propagate the faulty effect to primary outputs and assign logic values to adjacent lines opposite that of the faulty line. In order to estimate test quality for open faults, we define the excitation effectiveness Eeff. To reduce the test volume, we utilize the open fault simulation. We calculate the excitation effectiveness by open fault simulation in order to eliminate unnecessary test patterns. The experimental results for the benchmark circuits prove the effectiveness of our procedure.

This paper proposes a novel design method involving the stages from analog circuit design to layout synthesis in hope of suppressing the process-induced variations with a design style called transistor array. We manage to decompose the transistors into unified sub-transistors, and arrange the sub-transistors on a uniform placement grid so that a better post-CMP profile is expected to be achieved, and that the STI-stress is evened up to alleviate the process variations. However, since lack of direct theoretical support to the transistor decomposition, we analyze and evaluate the errors arising from the decomposition in both large and small signal analysis. A test chip with decomposed transistors on it confirmed our analysis and suggested that the errors are negligibly small and the design with transistor array is applicable. Based on this conclusion, a design flow with transistor array covering from circuit design to layout synthesis is proposed, and several design cases, including three common-source amplifiers, three two-stage OPAMPS and a nano-watt current reference, are implemented on a test chip with the proposed method, to demonstrate the feasibility of our idea. The measurement results from the chip confirmed that the designs with transistor array are successful, and the proposed method is applicable.

We propose a new face relighting method using an illuminance template generated from a single reference portrait. First, the reference is wrapped according to the shape of the target. Second, we employ a new spatially variant edge-preserving smoothing filter to remove the facial identity and texture details of the wrapped reference, and obtain the illumination template. Finally, we relight the target with the template in CIELAB color space. Experiments show the effectiveness of our method for both grayscale and color faces taken from different databases, and the comparisons with previous works demonstrate a better relighting effect produced by our method.

Increasing demand for multicast transmission necessitates service-specific and precise quality-of-service (QoS) control. Since existing works provided limited methodologies such as best path selection, their ability is restricted by the given topology and the congestion status of the network. This paper proposes a fanout set partition (FSP) scheme to realize QoS-guaranteed multicast transmission. The FSP scheme adjusts the delay of the multicast flow by dividing its fanout set into smaller subsets. Since it is carried out based on the service requirement, service-specific QoS control is implemented. Mathematical analysis investigates the trade-offs, and the performance evaluation results show significant improvements under various traffic conditions.

This paper presents a new scalable method to considerably reduce the rollback propagation effect of the conventional optimistic message logging by utilizing positive features of reliable FIFO group communication links. To satisfy this goal, the proposed method forces group members to replicate different receive sequence numbers (RSNs), which they assigned for each identical message to their group respectively, into their volatile memories. As the degree of redundancy of RSNs increases, the possibility of local recovery for each crashed process may significantly be higher. Experimental results show that our method can outperform the previous one in terms of the rollback distance of non-faulty processes with a little normal time overhead.

RCP (Reconfigurable Computing Processor) is intended to fill the gap between ASIC and GPP (General Purpose processor), which achieves much higher energy efficiency than GPP, while is much more flexible than ASIC. In this paper, one organization of on-chip data memory called LIBODM (LIfetime Based On-chip Data Memory) is proposed to reduce the reference delay for data and on-chip data memory size in RCP. In the LIBODM, the allocation of data is based on the data dependency. The data with low data dependency are stored off-chip to save the storage costs, while the data with high data dependency are stored on-chip to reduce the reference delay. Besides, in the LIBODM, the on-chip data are classified into two types, and the classification is based on the lifetime of data. For short lifetime data, they are preferred to be stored into FIFO to increase the reuse ratio of memory space naturally. For long lifetime data, they are preferred to be stored into RAM for several time references. The LIBODM has been testified in one CGRA (Coarse Grained Reconfigurable Architecture) called RPU (Reconfigurable Processing Unit), and two RPUs has been integrated in a RCP-REMUS_HP (High Performance version of Reconfigurable MUlti-media System) focused on video decoding. Thanks to the LIBODM, although the size of on-chip data memory in REMUS_HP is small, a high performance can still be achieved. Compared with XPP and ADRES, in REMUS_HP, the on-chip data memory size at same performance level is only 23.9% and 14.8%. REMUS_HP is implemented on a 48.9mm2 silicon with TSMC 65nm technology. Simulation shows that 1920*1088 @30fps can be achieved for H.264 high-profile decoding when exploiting a 200MHz working frequency. Compared with the high performance version of XPP, the performance is 150% boosted, while the energy efficiency is 17.59x boosted.

In this paper, we propose a jointly optimized predictive-adaptive partitioned block transform to exploit the spatial characteristics of intra residuals and improve video coding performance. Under the assumptions of traditional Markov representations, the asymmetric discrete sine transform (ADST) can be combined with a discrete cosine transform (DCT) for video coding. In comparison, the interpolative Markov representation has a lower mean-square error for images or regions that have relatively high contrast, and is insensitive to changes in image statistics. Hence, we derive an even discrete sine transform (EDST) from the interpolative Markov model, and use a coding scheme to switch between EDST and DCT, depending on the prediction direction and boundary information. To obtain an implementation independent of multipliers, we also propose an orthogonal 4-point integer EDST, which consists solely of adds and bit-shifts. We implement our hybrid transform coding scheme within the H.264/AVC intra-mode framework. Experimental results show that the proposed scheme significantly outperforms standard DCT and ADST. It also greatly reduces the blocking artifacts typically observed around block edges, because the new transform is more adaptable to the characteristics of intra-prediction residuals.

The outage performance of a multiuser two-way amplify-and-forward (AF) relaying network, where N-th best selection scheme with the consideration to the feedback delay, is investigated. Specifically, the new closed-form expressions for cumulative distribution function (CDF) and outage probability (OP) are presented over time varying Rayleigh-fading channels. Furthermore, simple approximate OP is derived assessing the high signal-to-noise-ratio (SNR), which identifies the diversity behavior. Numerical results show excellent agreement with theoretical results.

Ocean surface current radar is a Doppler radar to observe oceanographic information using the Bragg scattering resonance mechanism. In this paper, we consider angular resolution improvement of the radar. The radar employs an antenna array with FMICW operation, then it can resolve angular distribution by Digital Beam Forming (DBF) and distance by Fourier transform of the beat signal obtained by the FMICW radar. In order to obtain sufficient angular resolution, large array length or aperture with increasing the number of elements is needed, that is often difficult to realize in the HF/VHF ocean surface current radar. In this paper we propose to apply the Khatri-Rao (KR) product array processing to the radar. To verify effectiveness of the KR product array processing in angular resolution enhancement for the ocean surface current radar, we apply the KR product array to actual experimental data set of the radar, and show that the method is available to angular resolution enhancement and Doppler spectrum improvement.