With the rise of component-based software development, its reliability has attracted much attention from both academic and industry communities. Component-based software development focuses on architecture design, and thus it is important for reliability analysis to emphasize software architecture. Existing approaches to architecture-based software reliability analysis don't model the usage profile explicitly, and they ignore the difference between the testing profile and the practical profile of components, which limits their applicability and accuracy. In response to these issues, a new reliability modeling and prediction approach is introduced. The approach considers reliability-related architecture factors by explicitly modeling the system usage profile, and transforms the testing profile into the practical usage profile of components by representing the profile with input sub-domains. Finally, the evaluation experiment shows the potential of the approach.

This paper presents some effective methods for improving the performance of a speaker identification system. Based on the multiresolution property of the wavelet transform, the input speech signal is decomposed into various frequency subbands in order not to spread noise distortions over the entire feature space. For capturing the characteristics of the vocal tract, the linear predictive cepstral coefficients (LPCC) of the lower frequency subband for each decomposition process are calculated. In addition, a hard threshold technique for the lower frequency subband in each decomposition process is also applied to eliminate the effect of noise interference. Furthermore, cepstral domain feature vector normalization is applied to all computed features in order to provide similar parameter statistics in all acoustic environments. In order to effectively utilize all these multiband speech features, we propose a modified vector quantization as the identifier. This model uses the multilayer concept to eliminate the interference among the multiband speech features and then uses the principal component analysis (PCA) method to evaluate the codebooks for capturing a more detailed distribution of the speaker's phoneme characteristics. The proposed method is evaluated using the KING speech database for text-independent speaker identification. Experimental results show that the recognition performance of the proposed method is better than those of the vector quantization (VQ) and the Gaussian mixture model (GMM) using full-band LPCC and mel-frequency cepstral coefficients (MFCC) features in both clean and noisy environments. Also, a satisfactory performance can be achieved in low SNR environments.

This paper presents a long length discrete Hartley transform (DHT) design with a new hardware efficient distributed arithmetic (DA) approach. The new DA design approach not only explores the constant property of coefficients as the conventional DA, but also exploits its cyclic property. To efficiently apply this approach to long length DHT, we first decompose the long length DHT algorithm to short ones using the prime factor algorithm (PFA), and further reformulate it by using Agarwal-Cooley algorithm such that all the partitioned short DHT still consists of the cyclic property. Besides, we also exploit the scheme of computation sharing on the content of ROM to reduce the hardware cost with the trade-off in slowing down the computing speeds. Comparing with the existing designs shows that the proposed design can reduce the area-delay product from 52% to 91% according to a 0.35 µm CMOS cell library.

In the era of e-commerce, purchase behavior prediction is one of the most important issues to promote both online companies' sales and the consumers' experience. The previous researches usually use the feature engineering and ensemble machine learning algorithms for the prediction. The performance really depends on designed features and the scalability of algorithms because the large-scale data and a lot of categorical features lead to huge samples and the high-dimensional feature. In this study, we explore an alternative to use tree-based Feature Transformation (FT) and simple machine learning algorithms (e.g. Logistic Regression). Random Forest (RF) and Gradient Boosting decision tree (GB) are used for FT. Then, the simple algorithm, rather than ensemble algorithms, is used to predict purchase behavior based on transformed features. Tree-based FT regards the leaves of trees as transformed features, and can learn high-order interactions among original features. Compared with RF, if GB is used for FT, simple algorithms are enough to achieve better performance.

Cross correlation is a general way to estimate time delay of arrival (TDOA), with a computational complexity of O(n log n) using fast Fourier transform. However, since only one spike is required for time delay estimation, complexity can be further reduced. Guided by Chinese Remainder Theorem (CRT), this paper presents a new approach called Co-prime Aliased Sparse FFT (CASFFT) in O(n1-1/d log n) multiplications and O(mn) additions, where m is smooth factor and d is stage number. By adjusting these parameters, it can achieve a balance between runtime and noise robustness. Furthermore, it has clear advantage in parallelism and runtime for a large range of signal-to-noise ratio (SNR) conditions. The accuracy and feasibility of this algorithm is analyzed in theory and verified by experiment.

Aiming at the problem of spatial focus regions distribution dispersion and dislocation in feature pyramid networks and insufficient feature dependency acquisition in both spatial and channel dimensions, this paper proposes a spatial-temporal aggregated shuffle attention for video instance segmentation (STASA-VIS). First, an mixed subsampling (MS) module to embed activating features from the low-level target area of feature pyramid into the high-level is designed, so as to aggregate spatial information on target area. Taking advantage of the coherent information in video frames, STASA-VIS uses the first ones of every 5 video frames as the key-frames and then propagates the keyframe feature maps of the pyramid layers forward in the time domain, and fuses with the non-keyframe mixed subsampled features to achieve time-domain consistent feature aggregation. Finally, STASA-VIS embeds shuffle attention in the backbone to capture the pixel-level pairwise relationship and dimensional dependencies among the channels and reduce the computation. Experimental results show that the segmentation accuracy of STASA-VIS reaches 41.2%, and the test speed reaches 34FPS, which is better than the state-of-the-art one stage video instance segmentation (VIS) methods in accuracy and achieves real-time segmentation.

Purchase behavior prediction is one of the most important issues to promote both e-commerce companies' sales and the consumers' satisfaction. The prediction usually uses features based on the statistics of items. This kind of features can lead to the loss of detailed information of items. While all items are included, a large number of features has the negative impact on the efficiency of learning the predictive model. In this study, we propose to use the most popular items for improving the prediction. Experiments on the real-world dataset have demonstrated the effectiveness and the efficiency of our proposed method. We also analyze the reason for the performance of the most popular items. In addition, our work also reveals if interactions among most popular items are taken into account, the further significant improvement can be achieved. One possible explanation is that online retailers usually use a variety of sales promotion methods and the interactions can help to predict the purchase behavior.

Pedestrian detection is an essential but challenging task in computer vision, especially in crowded scenes due to heavy intra-class occlusion. In human visual system, head information can be used to locate pedestrian in a crowd because it is more stable and less likely to be occluded. Inspired by this clue, we propose a dual-task detector which detects head and human body simultaneously. Concretely, we estimate human body candidates from head regions with statistical head-body ratio. A head-body alignment map is proposed to perform relational learning between human bodies and heads based on their inherent correlation. We leverage the head information as a strict detection criterion to suppress common false positives of pedestrian detection via a novel pull-push loss. We validate the effectiveness of the proposed method on the CrowdHuman and CityPersons benchmarks. Experimental results demonstrate that the proposed method achieves impressive performance in detecting heavy-occluded pedestrians with little additional computation cost.

The increase in computation cost and storage of convolutional neural networks (CNNs) severely hinders their applications on limited-resources devices in recent years. As a result, there is impending necessity to accelerate the networks by certain methods. In this paper, we propose a loss-driven method to prune redundant channels of CNNs. It identifies unimportant channels by using Taylor expansion technique regarding to scaling and shifting factors, and prunes those channels by fixed percentile threshold. By doing so, we obtain a compact network with less parameters and FLOPs consumption. In experimental section, we evaluate the proposed method in CIFAR datasets with several popular networks, including VGG-19, DenseNet-40 and ResNet-164, and experimental results demonstrate the proposed method is able to prune over 70% channels and parameters with no performance loss. Moreover, iterative pruning could be used to obtain more compact network.

Hybrid analog/digital precoding has attracted growing attention for millimeter wave (mmWave) communications, since it can support multi-stream data transmission with limited hardware cost. A main challenge in implementing hybrid precoding is that the channels will exhibit frequency-selective fading due to the large bandwidth. To this end, we propose a practical hybrid precoding scheme with finite-resolution phase shifters by leveraging the correlation among the subchannels. Furthermore, we utilize the sparse feature of the mmWave channels to design a low-complexity algorithm to realize the proposed hybrid precoding, which can avoid the complication of the high-dimensionality eigenvalue decomposition. Simulation results show that the proposed hybrid precoding can approach the performance of unconstrained fully-digital precoding but with low hardware cost and computational complexity.

Purchase behavior prediction is one of the most important issues for the precision marketing of e-commerce companies. This Letter presents our solution to the purchase behavior prediction problem in E-commerce, specifically the task of Big Data Contest of China Computer Federation in 2014. The goal of this task is to predict which users will have the purchase behavior based on users' historical data. The traditional methods of recommendation encounter two crucial problems in this scenario. First, this task just predicts which users will have the purchase behavior, rather than which items should be recommended to which users. Second, the large-scale dataset poses a big challenge for building the empirical model. Feature engineering and Factorization Model shed some light on these problems. We propose to use Factorization Machines model based on the multiple classes and high dimensions of feature engineering. Experimental results on a real-world dataset demonstrate the advantages of our proposed method.

In the era of e-commerce, purchase behavior prediction is one of the most important issues to promote both online companies' sales and the consumers' experience. The previous researches usually use traditional features based on the statistics and temporal dynamics of items. Those features lead to the loss of detailed items' information. In this study, we propose a novel kind of features based on temporally popular items to improve the prediction. Experiments on the real-world dataset have demonstrated the effectiveness and the efficiency of our proposed method. Features based on temporally popular items are compared with traditional features which are associated with statistics, temporal dynamics and collaborative filter of items. We find that temporally popular items are an effective and irreplaceable supplement of traditional features. Our study shed light on the effectiveness of the combination of popularity and temporal dynamics of items which can widely used for a variety of recommendations in e-commerce sites.

In this letter, a Simple but Effective Congestion Control scheme (SECC) in VANET has been proposed to guarantee the successful transmissions for safety-related nodes. The strategy derive a Maximum Beacon Load Activity Indicator (MBLAI) to restrain the neighboring general periodical beacon load for the investigated safety-related “observation nodes”, i.e., the nodes associated with some emergent events. This mechanism actually reserves some bandwidth for the safety-related nodes to make them have higher priorities than periodical beacons to access channel. Different from the static congestion control scheme in IEEE802.11p, this strategy could provide dynamic control strength for congestion according to tolerant packets drop ratio for different applications.

This paper studies the performance of quantized massive multiple-input multiple-output (MIMO) systems with superimposed pilots (SP), using linear minimum mean-square-error (LMMSE) channel estimation and maximum ratio combining (MRC) detection. In contrast to previous works, arbitrary-bit analog-to-digital converters (ADCs) are considered. We derive an accurate approximation of the uplink achievable rate considering the removal of estimated pilots. Based on the analytical expression, the optimal pilot power factor that maximizes the achievable rate is deduced and an expression for energy efficiency (EE) is given. In addition, the achievable rate and the optimal power allocation policy under some asymptotic limits are analyzed. Analysis shows that the systems with higher-resolution ADCs or larger number of base station (BS) antennas need to allocate more power to pilots. In contrast, more power needs to be allocated to data when the channel is slowly varying. Numerical results show that in the low signal-to-noise ratio (SNR) region, for 1-bit quantizers, SP outperforms time-multiplexed pilots (TP) in most cases, while for systems with higher-resolution ADCs, the SP scheme is suitable for the scenarios with comparatively small number of BS antennas and relatively long channel coherence time.

Most existing deterministic multithreading systems are costly on pipeline parallel programs due to load imbalance. In this letter, we propose a Load-Balanced Deterministic Runtime (LBDR) for pipeline parallelism. LBDR deterministically takes some tokens from non-synchronization-intensive threads to synchronization-intensive threads. Experimental results show that LBDR outperforms the state-of-the-art design by an average of 22.5%.

Turbo codes and LDPC (Low-Density Parity-Check) codes are two of the most powerful error correction codes that can approach Shannon limit in many communication systems. But there are little architecture presented to support both LDPC and Turbo codes, especially by the means of ASIC. This paper have implemented a common architecture that can decode LDPC and Turbo codes, and it is capable of supporting the WiMAX, WiFi, 3GPP-LTE standard on the same hardware. In this paper, we will carefully describe how to share memory and logic devices in different operation mode. The chip is design in a 130 nm CMOS technology, and the maximum clock frequency can reach up to 160 MHz. The maximum throughput is about 104 Mbps@5.5 iteration for Turbo codes and 136 Mbps@10iteration for LDPC codes. Comparing to other existing structure, the design speed, area have significant advantage.

The parallel interference cancellation (PIC) multiple input multiple output (MIMO) detection algorithm has bit error ratio (BER) performance comparable to the maximum likelihood (ML) algorithm but with complexity close to the simple linear detection algorithm such as zero forcing (ZF), minimum mean squared error (MMSE), and successive interference cancellation (SIC), etc. However, the throughput of PIC MIMO detector on central processing unit (CPU) cannot meet the requirement of wireless protocols. In order to reach the throughput required by the standards, the graphics processing unit (GPU) is exploited in this paper as the modem processor to accelerate the processing procedure of PIC MIMO detector. The parallelism of PIC algorithm is analyzed and the two-stage PIC detection is carefully developed to efficiently match the multi-core architecture. Several optimization methods are employed to enhance the throughput, such as the memory optimization and asynchronous data transfer. The experiment shows that our MIMO detector has excellent BER performance and the peak throughput is 337.84 Mega bits per second (Mbps), about 7x to 16x faster than that of CPU implementation with SSE2 optimization methods. The implemented MIMO detector has better computing throughput than recent GPU-based implementations.

In this paper, we report the recent progress in visible light positioning and communication systems using light-emitting diodes (LEDs). Due to the wide deployment of LEDs for indoor illumination, visible light positioning (VLP) and visible light communication (VLC) using existing LEDs fixtures have attracted great attention in recent years. Here, we review our recent works on visible light positioning and communication, including image sensor-based VLP, photodetector-based VLP, integrated VLC and VLP (VLCP) systems, and heterogeneous radio frequency (RF) and VLC (RF/VLC) systems.

Strongly deterministic multithreading provides determinism for multithreaded programs even in the presence of data races. A common way to guarantee determinism for data races is to isolate threads by buffering shared memory accesses. Unfortunately, buffering all shared accesses is prohibitively costly. We propose an approach called DRDet to efficiently make data races deterministic. DRDet leverages the insight that, instead of buffering all shared memory accesses, it is sufficient to only buffer memory accesses involving data races. DRDet uses a sound data-race detector to detect all potential data races. These potential data races, along with all accesses which may access the same set of memory objects, are flagged as data-race-involved accesses. Unsurprisingly, the imprecision of static analyses makes a large fraction of shared accesses to be data-race-involved. DRDet employs two optimizations which aim at reducing the number of accesses to be sent to query alias analysis. We implement DRDet on CoreDet, a state-of-the-art deterministic multithreading system. Our empirical evaluation shows that DRDet reduces the overhead of CoreDet by an average of 1.6X, without weakening determinism and scalability.

System scenarios that derived from system design specification play an important role in the reliability engineering of component-based software systems. Several scenario-based approaches have been proposed to predict the reliability of a system at the design time, most of them adopt flat construction of scenarios, which doesn't conform to software design specifications and is subject to introduce state space explosion problem in the large systems. This paper identifies various challenges related to scenario modeling at the early design stages based on software architecture specification. A novel scenario-based reliability modeling and prediction approach is introduced. The approach adopts hierarchical scenario specification to model software reliability to avoid state space explosion and reduce computational complexity. Finally, the evaluation experiment shows the potential of the approach.