In this paper, we introduce a framework of distributed orthogonal approximate message passing for recovering sparse vector based on sensing by multiple nodes. The iterative recovery process consists of local computation at each node, and global computation performed either by a particular node or joint computation on the overall network by exchanging messages. We then propose a method to reduce the communication cost between the nodes while maintaining the recovery performance.

In this paper, we propose a non-orthogonal multiple access with adaptive resource allocation. The proposed non-orthogonal multiple access assigns multiple frequency resources for each device to send packets. Even if the number of devices is more than that of the available frequency resources, the proposed non-orthogonal access allows all the devices to transmit their packets simultaneously for high capacity massive machine-type communications (mMTC). Furthermore, this paper proposes adaptive resource allocation algorithms based on factor graphs that adaptively allocate the frequency resources to the devices for improvement of the transmission performances. This paper proposes two allocation algorithms for the proposed non-orthogonal multiple access. This paper shows that the proposed non-orthogonal multiple access achieves superior transmission performance when the number of the devices is 50% greater than the amount of the resource, i.e., the overloading ratio of 1.5, even without the adaptive resource allocation. The adaptive resource allocation enables the proposed non-orthogonal access to attain a gain of about 5dB at the BER of 10-4.

Deep learning is playing an increasingly important role in signal processing field due to its excellent performance on many inference problems. Parametric bilinear generalized approximate message passing (P-BiG-AMP) is a new approximate message passing based approach to a general class of structure-matrix bilinear estimation problems. In this letter, we propose a novel feed-forward neural network architecture to realize P-BiG-AMP methodology with deep learning for the inference problem of compressive sensing under matrix uncertainty. Linear transforms utilized in the recovery process and parameters involved in the input and output channels of measurement are jointly learned from training data. Simulation results show that the trained P-BiG-AMP network can achieve higher reconstruction performance than the P-BiG-AMP algorithm with parameters tuned via the expectation-maximization method.

Positioning information plays a significant role in multi-unmanned aerial vehicles (UAVs) applications. Traditionally, the positioning information is widely provided by Global Navigation Satellite System (GNSS) due to its good performance and global coverage. However, owing to complicated flight environment or signal blockage, jamming and unintentional interference, the UAVs may fail to locate themselves by using GNSS alone. As a new method to resolve these problems, cooperative positioning, by incorporating peer-to-peer range measurements and assisted information, has attracted more and more attentions due to its ability to enhance the accuracy and availability of positioning. However, achieving good performance of cooperative positioning of multi-UAVs is challenging as their mobility, arbitrary nonlinear state-evolution, measurement models and limited computation and communication resources. In this paper, we present a factor graph (FG) representation and message passing methodology to solve cooperative positioning problem among UAVs in 3-dimensional environment where GNSS cannot provide services. Moreover, to deal with the nonlinear state-evolution and measurement models while decreasing the computation complexity and communication cost, we develop a distributed algorithm for dynamic and hybrid UAVs by means of Spherical-Radial Cubature Rules (CR) method with belief propagation (BP) and variational message passing (VMP) methods (CRBP-VMP) on the FG. The proposed CRBP deals with the highly non-linear state-evolution models and non-Gaussian distributions, the VMP method is employed for ranging message, gets the simpler message representation and can reduce communication cost in the joint estimation problem. Simulation results demonstrate that the higher positioning accuracy, the better convergence as well as low computational complexity and communication cost of the proposed CRBP-VMP algorithm, which can be achieved compared with sum-product algorithm over a wireless network (SPAWN) and traditional Cubature Kalman Filters (CKF) method.

Generalized approximate message passing (GAMP) is introduced into distributed compressed sensing (DCS) to reconstruct jointly sparse signals under the mixed support-set model. A GAMP algorithm with known support-set is presented and the matching pursuit generalized approximate message passing (MPGAMP) algorithm is modified. Then, a new joint recovery algorithm, referred to as the joint MPGAMP algorithm, is proposed. It sets up the jointly shared support-set of the signal ensemble with the support exploration ability of matching pursuit and recovers the signals' amplitudes on the support-set with the good reconstruction performance of GAMP. Numerical investigation shows that the joint MPGAMP algorithm provides performance improvements in DCS reconstruction compared to joint orthogonal matching pursuit, joint look ahead orthogonal matching pursuit and regular MPGAMP.

Sparse code multiple access (SCMA) based on the message passing algorithm (MPA) for multiuser detection is a competitive non-orthogonal multiple access technique for fifth-generation wireless communication networks Among the existing multiuser detection schemes for uplink (UP) SCMA systems, the serial MPA (S-MPA) scheme, where messages are updated sequentially, generally converges faster than the conventional MPA (C-MPA) scheme, where all messages are updated in a parallel manner. In this paper, the optimization of message scheduling in the S-MPA scheme is proposed. Firstly, some statistical results for the probability density function (PDF) of the received signal are obtained at various signal-to-noise ratios (SNR) by using the Monte Carlo method. Then, based on the non-orthogonal property of SCMA, the data mapping relationship between resource nodes and user nodes is comprehensively analyzed. A partial codeword transmission of S-MPA (PCTS-MPA) with threshold decision scheme of PDF is proposed and verified. Simulations show that the proposed PCTS-MPA not only reduces the complexity of MPA without changing the bit error ratio (BER), but also has a faster convergence than S-MPA, especially at high SNR values.

Generalized approximate message passing (GAMP) can be applied to compressive phase retrieval (CPR) with excellent phase-transition behavior. In this paper, we introduced the cartoon-texture model into the denoising-based phase retrieval GAMP(D-prGAMP), and proposed a cartoon-texture model based D-prGAMP (C-T D-prGAMP) algorithm. Then, based on experiments and analyses on the variations of the performance of D-PrGAMP algorithms with iterations, we proposed a 2-stage D-prGAMP algorithm, which makes tradeoffs between the C-T D-prGAMP algorithm and general D-prGAMP algorithms. Finally, facing the non-convergence issues of D-prGAMP, we incorporated adaptive damping to 2-stage D-prGAMP, and proposed the adaptively damped 2-stage D-prGAMP (2-stage ADD-prGAMP) algorithm. Simulation results show that, runtime of 2-stage D-prGAMP is relatively equivalent to that of BM3D-prGAMP, but 2-stage D-prGAMP can achieve higher image reconstruction quality than BM3D-prGAMP. 2-stage ADD-prGAMP spends more reconstruction time than 2-stage D-prGAMP and BM3D-prGAMP. But, 2-stage ADD-prGAMP can achieve PSNRs 0.2∼3dB higher than those of 2-stage D-prGAMP and 0.3∼3.1dB higher than those of BM3D-prGAMP.

Massive multiple-input and multiple-output (MIMO) is a key technology to meet the increasing capacity demands that must be satisfied by next generation wireless systems. However, it is expensive to use linear power amplifiers when implementing a massive MIMO system as it will have hundreds of antennas. In this paper, considering that low peak-to-average power ratio (PAPR) of transmit signals can facilitate hardware-friendly equipment with nonlinear but power-efficient amplifiers, we first formulate the precoding scheme as a PAPR minimization problem. Then, in order to obtain the optimal solution with low complexity, the precoding problem is recast into a Bayesian estimation problem by leveraging belief propagation algorithm. Eventually, we propose a low-PAPR approximate message passing (LP-AMP) algorithm based on belief propagation to ensure the good transmission performance and minimize the PAPR to realize practical deployments. Simulation results reveal that the proposed method can get PAPR reduction and adequate transmission performance, simultaneously, with low computational complexity. Moreover, the results further indicate that the proposed method is suitable for practical implementation, which is appealing for massive multiuser MIMO (MU-MIMO) systems.

This paper proposes a novel matching pursuit generalized approximate message passing (MPGAMP) algorithm which explores the support of sparse representation coefficients step by step, and estimates the mean and variance of non-zero elements at each step based on a generalized-approximate-message-passing-like scheme. In contrast to the classic message passing based algorithms and matching pursuit based algorithms, our proposed algorithm saves a lot of intermediate process memory, and does not calculate the inverse matrix. Numerical experiments show that MPGAMP algorithm can recover a sparse signal from compressed sensing measurements very well, and maintain good performance even for non-zero mean projection matrix and strong correlated projection matrix.

Joint signal detection and channel estimation based on the expectation-maximization (EM) algorithm has been investigated for multiple-input multiple-output (MIMO) orthogonal frequency-division multiplexing (OFDM) mobile communications over fast-fading channels. The previous work in [20] developed a channel estimation method suitable for the EM-based iterative receiver. However, it remained possible for unreliable received signals to be repetitively used during the iterative process. In order to improve the EM-based iterative receiver further, this paper proposes spatial removal from the perspective of a message-passing algorithm on factor graphs. The spatial removal performs the channel estimation of a targeted antenna by using detected signals that are obtained from the received signals of all antennas other than the targeted antenna. It can avoid the repetitive use of unreliable received signals for consecutive signal detection and channel estimation. Appropriate applications of the spatial removal are also discussed to exploit both the removal effect and the spatial diversity. Computer simulations under fast-fading conditions demonstrate that the appropriate applications of the spatial removal can improve the packet error rate (PER) of the EM-based receiver thanks to both the removal effect and the spatial diversity.

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.

The main target of compressed sensing is recovery of one-dimensional signals, because signals more than two-dimension can also be treated as one-dimensional ones by raster scan, which makes the sensing matrix huge. This is unavoidable for general sensing processes. In separable cases like discrete Fourier transform (DFT) or standard wavelet transforms, however, the corresponding sensing process can be formulated using two matrices which are multiplied from both sides of the target two-dimensional signals. We propose an approximate message passing (AMP) algorithm for the separable sensing process. Typically, we suppose DFT for the sensing process, in which the measurements are complex numbers. Therefore, the formulation includes cases in which both target signal and measurements are complex. We show the effectiveness of the proposed algorithm by computer simulations.

In this paper, we present a transmission scheme for a multiple-input multiple-output (MIMO) quasi-static fading channel with imperfect channel state information at the transmitter (CSIT). In this scheme, we develop a precoder structure to exploit the available CSIT and apply spatial coupling for further performance enhancement. We derive an analytical evaluation method based on extrinsic information transfer (EXIT) functions, which provides convenience for our precoder design. Furthermore, we observe an area property indicating that, for a spatially coupled system, the iterative receiver can perform error-free decoding even the original uncoupled system has multiple fixed points in its EXIT chart. This observation implies that spatial coupling is useful to alleviate the uncertainty in CSIT which causes difficulty in designing LDPC code based on the EXIT curve matching technique. Numerical results are presented, showing an excellent performance of the proposed scheme in MIMO fading channels with imperfect CSIT.

This paper proposes an iterative maximum a posteriori (MAP) receiver for orthogonal frequency division multiplexing (OFDM) mobile communications under fast-fading conditions. The previous work in [21] developed a MAP receiver based on the expectation-maximization (EM) algorithm employing the differential model, which can allow correlated time-variation of channel impulse responses. In order to make such a MAP receiver more robust against time-variant channels, this paper proposes two new message-passing algorithms derived from factor graphs; subcarrier removal and partial turbo processing. The subcarrier removal estimates the channel frequency response by using all subcarriers other than the targeted subcarrier. Such channel estimate can be efficiently calculated by removing information on the targeted subcarrier from the estimate of the original EM algorithm that uses all the subcarriers. This modification can avoid the repetitive use of incorrectly detected signals for the channel estimation. On the other hand, the partial turbo processing performs symbol-by-symbol channel decoding by using a symbol interleaver. Owing to this process, the current channel estimate, which is more accurate due to the decoding gain, can be used as the initial channel estimate for the next symbol. Computer simulations under fast multipath fading conditions demonstrate that the subcarrier removal and the partial turbo processing can improve the error floor and the convergence speed, respectively, compared to the conventional MAP receiver.

In this paper, we propose a partially-parallel irregular LDPC decoder based on IEEE 802.11n standard targeting high throughput and small area applications. The design is based on a novel sum-delta message passing algorithm characterized as follows: (i) Decoding throughput is greatly improved by utilizing the difference value between the updated and the original value to remove redundant computations. (ii) Registers and memory are optimized to store only the frequently used messages to decrease the hardware cost. (iii) Techniques such as binary sorting, parallel column operation, high performance pipelining are used to further speed up the message passing procedure. The synthesis result in TSMC 0.18 CMOS technology demonstrates that for (648,324) irregular LDPC code, our decoder achieves 7.5X improvement in throughput, which reaches 402 Mbps at the frequency of 200 MHz, with 11% area reduction. The synthesis result also demonstrates the competitiveness to the fully-parallel regular LDPC decoders in terms of the tradeoff between throughput, area and power.

In this paper we compare various parallel preconditioners such as Point-SSOR (Symmetric Successive OverRelaxation), ILU(0) (Incomplete LU) in the Wavefront ordering, ILU(0) in the Multi-color ordering, Multi-Color Block SOR (Successive OverRelaxation), SPAI (SParse Approximate Inverse) and pARMS (Parallel Algebraic Recursive Multilevel Solver) for solving large sparse linear systems arising from two-dimensional PDE (Partial Differential Equation)s on structured grids. Point-SSOR is well-known, and ILU(0) is one of the most popular preconditioner, but it is inherently serial. ILU(0) in the Wavefront ordering maximizes the parallelism in the natural order, but the lengths of the wavefronts are often nonuniform. ILU(0) in the Multi-color ordering is a simple way of achieving a parallelism of the order N, where N is the order of the matrix, but its convergence rate often deteriorates as compared to that of natural ordering. We have chosen the Multi-Color Block SOR preconditioner combined with direct sparse matrix solver, since for the Laplacian matrix the SOR method is known to have a nondeteriorating rate of convergence when used with the Multi-Color ordering. By using block version we expect to minimize the interprocessor communications. SPAI computes the sparse approximate inverse directly by least squares method. Finally, ARMS is a preconditioner recursively exploiting the concept of independent sets and pARMS is the parallel version of ARMS. Experiments were conducted for the Finite Difference and Finite Element discretizations of five two-dimensional PDEs with large meshsizes up to a million on an IBM p595 machine with distributed memory. Our matrices are real positive, i.e., their real parts of the eigenvalues are positive. We have used GMRES(m) as our outer iterative method, so that the convergence of GMRES(m) for our test matrices are mathematically guaranteed. Interprocessor communications were done using MPI (Message Passing Interface) primitives. The results show that in general ILU(0) in the Multi-Color ordering and ILU(0) in the Wavefront ordering outperform the other methods but for symmetric and nearly symmetric 5-point matrices Multi-Color Block SOR gives the best performance, except for a few cases with a small number of processors.

Reliability-based hybrid ARQ (RB-HARQ) is a kind of incremental-redundancy ARQ recently introduced. In the RB-HARQ, the receiver returns both NAK signal and set of unreliable bit indices if the received sequence is not accepted. Since each unreliable bit index is determined by the bitwise posterior probability, better approximation of that probability becomes crucial as the number of retransmissions increases. Assuming the systematic code for the initial transmission, the proposed RB-HARQ scheme has the following two features: (a) the sender retransmits newly encoded and interleaved parity bits corresponding to the unreliable information bits; (b) the retransmitted parity bits as well as the initial received sequence are put all together to perform the message passing decoding i.e. the suboptimal MAP decoding. Finally, simulation results are shown to evaluate the above two features.

In this paper, we present the interlaced fast Fourier transform (FFT) method to parallelize the adaptive integral method (AIM) algorithm for the radar cross-section (RCS) computation of large scattering objects in free space. It is noted that the function obtained after convolution is smoother as compared to the original functions. Utilizing this concept, it is possible to interlace the grid current and charge sources in AIM and compute the potentials on each set of interlaced grid independently using FFT. Since the potentials on each interlaced grid are smooth functions in space, we can then interpolate the potentials to every other nodes on the original grid. The final solution of the potentials on the original grid is obtained by summing the total contributions of all the computed and interpolated potentials from every individual interlaced grid. Since the potentials of each interlaced grid can be computed independently without much communication overheads between the processes, such an algorithm is suitable for parallelizing the AIM solver to run on distributed parallel computer clusters. It is shown that the overall computation complexity of the newly proposed interlaced FFT scheme is still of O(N log N).

This paper describes the design and implementation of a testbed for predicting master/slave (M/S) programs written using Message Passing Interface (MPI) programs. The testbed, named M/S Emulator (MSE), aims at assisting developers in evaluating the performance of M/S programs and dynamic load-balancing strategies on clusters of PCs. In order to realize this, MSE predicts the communication time by using a realistic parallel computational model, an extension of the LogGPS model. This extended model improves the prediction accuracy on a large number of processors, because it captures the master's bottleneck: the overhead required for retrieving arrival messages from the slaves. Current MSE also employs a best effort emulation method for predicting the calculation time. In our experiments, MSE demonstrated an accurate prediction on clusters, especially on a larger number of nodes. Therefore, we believe that our extended model enables us to analyze the scalability of the M/S program performance.

We conducted research and development of Distributed Supercomputing Environment (DSE) based on distributed shared memory model to serve as a cluster computing environment to provide parallel processing facilities. Shared memory model and message passing model are well-known typical models of parallel processing. It is desired that hybrid programming environment will make the best use of the prominent features of both models. Consequently, we add a new message passing mechanism to present DSE, and create a prototype called Hybrid DSE as a hybrid model based cluster computing environment. In this paper, we describe the implementation of a message passing mechanism on DSE and performance evaluation of Hybrid DSE.