With the growth of positioning demand, fingerprintbased positioning, which utilizes multi-path information to improve positioning accuracy, has attracted academic and industrial attentions. Current position fingerprints often incur significant storage overhead and time complexity for machine learning due to their large dimension. This paper investigates positioning in massive multiple-input multiple-output (MIMO) communication systems using a low dimensional fingerprints called the angledelay power coordinates matrix (ADECM). We first use a dimensionality reduction algorithm for the widely used position fingerprint angle-delay channel power matrix (ADCPM) in existing works, and define the reduced matrix as the ADECM. Subsequently, recognizing the excellent performance of generative adversarial network in regression tasks, we propose the Feature Separation Generative Adversarial Network (FSGAN). This innovative network is specifically designed to accurately estimate the position of user terminals. Simulation results show that the proposed positioning method outperforms existing methods.

In this paper, we investigate the channel estimation for massive multiple-input multiple-output orthogonal frequency division multiplexing (MIMO-OFDM) systems. We revisit the information geometry approach (IGA) for massive MIMO-OFDM channel estimation. By using the constant magnitude property of the entries of the measurement matrix and the asymptotic analysis, we find that the second-order natural parameters (SONPs) of the distributions on all the auxiliary manifolds (AMs) are equivalent to each other at each iteration of IGA, and the first-order natural parameters (FONPs) of the distributions on all the AMs are asymptotically equivalent to each other at the fixed point. Motivated by these results, we simplify the iterative process of IGA and propose a simplified IGA for massive MIMO-OFDM channel estimation. It is proved that at the fixed point, the a posteriori mean obtained by the simplified IGA is asymptotically optimal. The simplified IGA allows efficient implementation with fast Fourier transformation (FFT). Simulations confirm that the simplified IGA can achieve near the optimal performance with low complexity in a limited number of iterations.

In this paper, we investigate the downlink robust precoding with imperfect channel state information (CSI) for massive multiple-input-multiple-output (MIMO) communications. With the estimated channel and channel error statistics, the general design of the robust precoder is to maximize the ergodic sum rate subject to the total transmit power constraint. To make the problem more tractable, we find a lower bound of the ergodic sum rate and propose the robust weighted minimum mean-squared-error (WMMSE) precoder to maximize the bound. We characterize the structure of the precoding vectors by low-dimensional parameters, which are learned directly from the available CSI through a neural network. As such, the precoding vectors can be immediately computed without iterations. To extend the deep learning design to multi-antennas users, we present a flexible approach that allows the various antenna configurations at the user side to be handled. Simulation results show that the deep learning design can significantly reduce the computational complexity compared with the existing precoder designs while achieving near optimal performance.

Passive microwave remote sensing can effectively capture the near-surface soil freeze/thaw onsets. Accurately understanding the transition of permafrost freeze/thaw state is helpful for us to respond to climate change in time. In order to improve the retrieval accuracy of freeze/thaw onsets, we propose an XGBoost modeling method that combines SMAP and AMSR2 for freeze/thaw onsets detection. We conducted experiments using data covering Alaska from 2015 to 2020 to demonstrate the effectiveness of our method. The proposed model was applied to the whole study area to obtain the spatial and temporal distribution of freezing periods. During the study period, the shortening of the freezing period has been most evident in 2018–2019. The variation of the freezing period is related to climate anomalies.

BACKGROUND: Protein-protein interactions are widespread in biological systems and play an important role in cell biology. Since traditional laboratory-based methods have some drawbacks, such as time-consuming, money-consuming, etc., a large number of methods based on deep learning have emerged. However, these methods do not take into account the long-distance dependency information between each two amino acids in sequence. In addition, most existing models based on graph neural networks only aggregate the first-order neighbors in protein-protein interaction (PPI) network. Although multi-order neighbor information can be aggregated by increasing the number of layers of neural network, it is easy to cause over-fitting. So, it is necessary to design a network that can capture long distance dependency information between amino acids in the sequence and can directly capture multi-order neighbor information in protein-protein interaction network. RESULTS: In this study, we propose a multi-hop neural network (LDMGNN) model combining long distance dependency information to predict the multi-label protein-protein interactions. In the LDMGNN model, we design the protein amino acid sequence encoding (PAASE) module with the multi-head self-attention Transformer block to extract the features of amino acid sequences by calculating the interdependence between every two amino acids. And expand the receptive field in space by constructing a two-hop protein-protein interaction (THPPI) network. We combine PPI network and THPPI network with amino acid sequence features respectively, then input them into two identical GIN blocks at the same time to obtain two embeddings. Next, the two embeddings are fused and input to the classifier for predict multi-label protein-protein interactions. Compared with other state-of-the-art methods, LDMGNN shows the best performance on both the SHS27K and SHS148k datasets. Ablation experiments show that the PAASE module and the construction of THPPI network are feasible and effective. CONCLUSIONS: In general terms, our proposed LDMGNN model has achieved satisfactory results in the prediction of multi-label protein-protein interactions.

Sequential recommendation is a fundamental task for network applications, and it usually suffers from the item cold start problem due to the insufficiency of user feedbacks. There are currently three kinds of popular approaches which are respectively based on matrix factorization (MF) of collaborative filtering, Markov chain (MC), and recurrent neural network (RNN). Although widely used, they have some limitations. MF based methods could not capture dynamic user's interest. The strong Markov assumption greatly limits the performance of MC based methods. RNN based methods are still in the early stage of incorporating additional information. Based on these basic models, many methods with additional information only validate incorporating one modality in a separate way. In this work, to make the sequential recommendation and deal with the item cold start problem, we propose a Multi-View Rrecurrent Neural Network (MV-RNN) model. Given the latent feature, MV-RNN can alleviate the item cold start problem by incorporating visual and textual information. First, At the input of MV-RNN, three different combinations of multi-view features are studied, like concatenation, fusion by addition and fusion by reconstructing the original multi-modal data. MV-RNN applies the recurrent structure to dynamically capture the user's interest. Second, we design a separate structure and a united structure on the hidden state of MV-RNN to explore a more effective way to handle multi-view features. Experiments on two real-world datasets show that MV-RNN can effectively generate the personalized ranking list, tackle the missing modalities problem, and significantly alleviate the item cold start problem.

In this paper, the design of robust linear precoders for the massive multi-input-multi-output (MIMO) downlink with imperfect channel state information (CSI) is investigated. The imperfect CSI for each UE obtained at the BS is modeled as statistical CSI under a jointly correlated channel model with both channel mean and channel variance information, which includes the effects of channel estimation error, channel aging, and spatial correlation. The design objective is to maximize the expected weighted sum-rate. By combining the minorize-maximize (MM) algorithm with the deterministic equivalent method, an algorithm for robust linear precoder design is derived. The proposed algorithm achieves a stationary point of the expected weighted sum-rate maximization problem. To reduce the computational complexity, two low-complexity algorithms are then derived. One for the general case, and the other for the case when all the channel means are zeros. For the later case, it is proved that the beam domain transmission is optimal, and thus the precoder design reduces to the power allocation optimization in the beam domain. Simulation results show that the proposed robust linear precoder designs apply to various mobile scenarios and achieve high spectral efficiency.

For real-world learning tasks (e.g., classification), graph-based models are commonly used to fuse the information distributed in diverse data sources, which can be heterogeneous, redundant, and incomplete. These models represent the relations in different datasets as pairwise links. However, these links cannot deal with high-order relations which connect multiple objects (e.g., in public health datasets, more than two patient groups admitted by the same hospital in 2014). In this article, we propose a visual analytics approach for the classification on heterogeneous datasets using the hypergraph model. The hypergraph is an extension to traditional graphs in which a hyperedge connects multiple vertices instead of just two. We model various high-order relations in heterogeneous datasets as hyperedges and fuse different datasets with a unified hypergraph structure. We use the hypergraph learning algorithm for predicting missing labels in the datasets. To allow users to inject their domain knowledge into the model-learning process, we augment the traditional learning algorithm in a number of ways. In addition, we also propose a set of visualizations which enable the user to construct the hypergraph structure and the parameters of the learning model interactively during the analysis. We demonstrate the capability of our approach via two real-world cases.

The equipment faults of the interlocking system in rail transit system has occurred frequently, and these faults can cause serious accidents.The modeling of the interlocking system must aim at the stochasticity and real-time characteristics of equipment faults.Therefore, this paper proposes to model the interlocking system using stochastic hybrid automata.In order to improve model efficiency, we try to extract the pattern of the interlocking system model, and reuses these patterns in system modeling.The main contributions include: (1) Based on the business analysis of the interlocking system, 12 model patterns of the interlocking system are extracted; and (2) the modeling process of the interlocking system based on patterns reuse is given to guide system modeling.Finally, a case study is presented to illustrate the feasibility and effectiveness of our approach.

X-ray images obtained from synchrotron beamlines are large-scale, high-resolution and high-dynamic-range grayscale data encoding multiple complex properties of the measured materials. They are typically associated with a variety of metadata which increases their inherent complexity. There is a wealth of information embedded in these data but so far scientists lack modern exploration tools to unlock these hidden treasures. To bridge this gap, we propose MultiSciView , a multivariate scientific x-ray image visualization and exploration system for beamline-generated x-ray scattering data. Our system is composed of three complementary and coordinated interactive visualizations to enable a coordinated exploration across the images and their associated attribute and feature spaces . The first visualization features a multi-level scatterplot visualization dedicated for image exploration in attribute, image, and pixel scales. The second visualization is a histogram-based attribute cross filter by which users can extract desired subset patterns from data. The third one is an attribute projection visualization designed for capturing global attribute correlations. We demonstrate our framework by ways of a case study involving a real-world material scattering dataset. We show that our system can efficiently explore large-scale x-ray images, accurately identify preferred image patterns, anomalous images and erroneous experimental settings, and effectively advance the comprehension of material nanostructure properties.

Oftentimes multivariate data are not available as sets of equally multivariate tuples, but only as sets of projections into subspaces spanned by subsets of these attributes. For example, one may find data with five attributes stored in six tables of two attributes each, instead of a single table of five attributes. This prohibits the visualization of these data with standard high-dimensional methods, such as parallel coordinates or MDS, and there is hence the need to reconstruct the full multivariate (joint) distribution from these marginal ones. Most of the existing methods designed for this purpose use an iterative procedure to estimate the joint distribution. With insufficient marginal distributions and domain knowledge, they lead to results whose joint errors can be large. Moreover, enforcing smoothness for regularizations in the joint space is not applicable if the attributes are not numerical but categorical. We propose a visual analytics approach that integrates both anecdotal data and human experts to iteratively narrow down a large set of plausible solutions. The solution space is populated using a Monte Carlo procedure which uniformly samples the solution space. A level-of-detail high dimensional visualization system helps the user understand the patterns and the uncertainties. Constraints that narrow the solution space can then be added by the user interactively during the iterative exploration, and eventually a subset of solutions with narrow uncertainty intervals emerges.

Ensemble methods for classification have been effectively used for decades, while for outlier detection it has only been studied recently. In this work, we design a new ensemble approach for outlier detection in multi-dimensional point data, which provides improved accuracy by reducing error through both bias and variance by considering outlier detection as a binary classification task with unobserved labels. In this paper, we propose a sequential ensemble approach called CARE that employs a two-phase aggregation of the intermediate results in each iteration to reach the final outcome. Unlike existing outlier ensembles, our ensemble incorporates both the parallel and sequential building blocks to reduce bias as well as variance by (i) successively eliminating outliers from the original dataset to build a better data model on which outlierness is estimated (sequentially), and (ii) combining the results from individual base detectors and across iterations (parallelly). Through extensive experiments on 16 real-world datasets mainly from the UCI machine learning repository [1], we show that CARE performs significantly better than or at least similar to the individual baselines as well as the existing state-of-the-art outlier ensembles.

This paper investigates low-complexity multi-user detectors for massive MIMO systems in practical channels. Beam domain message passing algorithm on the sparse-graph is proposed by exploiting the channel sparsity in beam domain, which has much lower computational complexity compared to the dense-graph based detections. As the massive MIMO channels are usually not i.i.d Gaussian distribution and central limit theorem (CLT) will no longer apply, conventional approximate message passing detector (AMP) may diverge. To improve the performance of AMP in practical channels, we further propose energy spread transform (EST) based massive MIMO transmission, which guarantee that the equivalent channels are i.i.d. distributed. Furthermore, by deriving the state evolution (SE) equations, the convergence analysis of the proposed detector is also provided. Simulation results show that, the proposed detector outperforms the conventional AMP and minimum mean square error (MMSE) detectors, and has fast convergence rate.

In this paper, we propose a user scheduling and beam allocation algorithm for massive MIMO frequency-division-duplexing (FDD) systems by using a two-stage precoding method. We demonstrate that the precoding in beam domain is optimal when different users transmit data in non-overlapping beams. To satisfy the condition of optimality, a greedy algorithm with low complexity is proposed to select users and allocate beams for transmission based on statistical channel state information (CSI) by maximizing the deterministic equivalent approximation of the average sum rate. Simulations demonstrate the near-optimal performance of the proposed two-stage precoding method.

In this paper, we derive the Bayes-Optimal estimator based on approximate message passing (AMP) algorithm in massive multiple-input multiple-output (MIMO) systems, which requires statistical channel state information (CSI). According to the analysis of channel model in beam domain, the covariance matrix is derived for CSI acquisition. With the aid of statistical CSI, the convergence of the proposed algorithm has significant improvement in comparison with which use the expectation-maximization (EM) algorithm to fit the statistical CSI. Simulations show great mean squared error (MSE) performance that approximates the Minimum Mean Square Error (MMSE) estimator, and better convergence performance than other AMP algorithm can be achieved. Besides, the results prove that performance of the random pilot in this algorithm is close to that of the orthogonal pilot based on Zadoff-Chu sequences.

User profiling is crucial to many online services. Several recent studies suggest that demographic attributes are predictable from different online behavioral data, such as users' "Likes" on Facebook, friendship relations, and the linguistic characteristics of tweets. But location check-ins, as a bridge of users' offline and online lives, have by and large been overlooked in inferring user profiles. In this paper, we investigate the predictive power of location check-ins for inferring users' demographics and propose a simple yet general location to profile (L2P) framework. More specifically, we extract rich semantics of users' check-ins in terms of spatiality, temporality, and location knowledge, where the location knowledge is enriched with semantics mined from heterogeneous domains including both online customer review sites and social networks. Additionally, tensor factorization is employed to draw out low dimensional representations of users' intrinsic check-in preferences considering the above factors. Meanwhile, the extracted features are used to train predictive models for inferring various demographic attributes.

In this paper, we propose a coordinated pilot reuse (CPR) scheme for multi-cell massive multi-input multi-output systems to reduce the pilot overhead. Unlike the conventional pilot reuse scheme which allows pilots to be reused only among different cells, CPR allows inter- and/or intra-cell user equipments to reuse the same pilots, efficiently reducing the pilot overhead. For the spatially correlated Rayleigh fading channels, we first present the CPR-based channel estimation and a greedy pilot allocation algorithm. With the channel estimation errors due to CPR taken into account, we then develop a statistically robust transceiver which can guarantee the transmission performance. Monte-Carlo simulations show that compared to the conventional multi-cell pilot reuse scheme, the proposed CPR scheme provides significant performance gains in terms of the net spectral efficiency.

Multiple base station (BS) cooperation and denser BS deployment have been recognized as two promising ways to improve the system capacity of the next generation wireless communication systems. In practice, to avoid the formidable overhead of the whole network cooperation, BSs can form disjoint or overlapped groups (i.e., clusters) and adopt limited cooperation. In this paper, we investigate the performance of BS clustering in homogeneous small cell networks (SCNs). Based on the clustering methods for macrocell networks, a dynamic clustering algorithm is proposed to adapt to the SCN where the number of BSs is much larger than the scheduled users'. Simulations show that the dynamic clustering with proper beamforming method leads to significant sum-rate gains over the non-cooperative one and the proposed algorithm outperforms the conventional channel strength based ones in our network structure. Performance of dynamic clustering in a SCN where each BS schedules a single user is also evaluated.

The discrete Fourier transmission spread OFDM (DFTS-OFDM) based single-carrier frequency division multiple access (SC-FDMA) has been widely adopted due to its lower peak-to-average power ratio (PAPR) of transmit signals compared with OFDM. However, the offset modulation, which has lower PAPR than general modulation, cannot be directly applied into the existing SC-FDMA. When pulse-shaping filters are employed to further reduce the envelope fluctuation of transmit signals of SC-FDMA, the spectral efficiency degrades as well. In order to overcome such limitations of conventional SC-FDMA, this paper for the first time investigated cyclic prefixed OQAM-OFDM (CP-OQAM-OFDM) based SC-FDMA transmission with adjustable user bandwidth and space-time coding. Firstly, we propose CP-OQAM-OFDM transmission with unequally-spaced subbands. We then apply it to SC-FDMA transmission and propose a SC-FDMA scheme with the following features: a) the transmit signal of each user is offset modulated single-carrier with frequency-domain pulse-shaping; b) the bandwidth of each user is adjustable; c) the spectral efficiency does not decrease with increasing roll-off factors. To combat both inter-symbol-interference and multiple access interference in frequency-selective fading channels, a joint linear minimum mean square error frequency domain equalization using {a prior} information with low complexity is developed. Subsequently, we construct space-time codes for the proposed SC-FDMA. Simulation results confirm the powerfulness of the proposed CP-OQAM-OFDM scheme (i.e., effective yet with low complexity).

We investigate channel estimation for long term evolution (LTE) uplink over frequency-selective fading multiple-input multiple-output (MIMO) channels. As the conventional DFT-based channel estimation algorithm used for obtaining the channel impulse response (CIR) in wide band may not be applicable in narrow band of LTE uplink, which results an irreducible error floor, we propose an novel channel estimation based on discrete cosine transform (DCT), assuming only two users transmit simultaneously in the same frequency band (or SDMA). By exploiting the properties of reference signals of each user, type I DCT can separate channel response of each user in DCT-domain completely. Then, optimal channel estimation in the linear minimal mean square error (MMSE) sense in DCT-domain is derived. Finally, the performance of the proposed channel estimation is verified via simulation.

We propose the application of a modified transiently chaotic neural network to solve the optimum detection problem in DS/CDMA systems. The optimum detection problem is formulated as an energy minimization problem. It can be minimized by a modified transiently chaotic neural network (MTCNN). The MTCNN-based detector offers performance improvement over the existing Hopfield neural network detector with a little increase in computational complexity. Numerical results show that the proposed detector can approximate the optimum detector closely.