Bolts in the bogie box of metro vehicles are fasteners which are significant for bogie box structure. Effective loosening bolts detection in early stage can avoid the bolt loss and accident occurrence. Recently, detection methods based on machine vision are developed for bolt loosening. But traditional image processing and machine learning methods have high missed rate and false rate for bolts detection due to the small size and complex background. To address this problem, a loosening bolts defection method based on deep learning is proposed. The proposed method cascades two stages in a coarse-to-fine manner, including location stage based on the Single Shot Multibox Detector (SSD) and the improved SSD sequentially localizing the bogie box and bolts and a semantic segmentation stage with the U-shaped Network (U-Net) to detect the looseness of the bolts. The accuracy and effectiveness of the proposed method are verified with images captured from the Shanghai Metro Line 9. The results show that the proposed method has a higher accuracy in detecting the bolts loosening, which can guarantee the stable operation of the metro vehicles.

Robust automatic language identification (LID) is the task of identifying the language from a short utterance spoken by an unknown speaker. The mainstream approaches include parallel phone recognition language modeling (PPRLM), support vector machine (SVM) and the general Gaussian mixture models (GMMs). These systems map the cepstral features of spoken utterances into high level scores by classifiers. In this paper, in order to increase the dimension of the score vector and alleviate the inter-speaker variability within the same language, multiple data groups based on supervised speaker clustering are employed to generate the discriminative language characterization score vectors (DLCSV). The back-end SVM classifiers are used to model the probability distribution of each target language in the DLCSV space. Finally, the output scores of back-end classifiers are calibrated by a pair-wise posterior probability estimation (PPPE) algorithm. The proposed language identification frameworks are evaluated on 2003 NIST Language Recognition Evaluation (LRE) databases and the experiments show that the system described in this paper produces comparable results to the existing systems. Especially, the SVM framework achieves an equal error rate (EER) of 4.0% in the 30-second task and outperforms the state-of-art systems by more than 30% relative error reduction. Besides, the performances of proposed PPRLM and GMMs algorithms achieve an EER of 5.1% and 5.0% respectively.

Erasure codes have been considered as one of the most promising techniques for data reliability enhancement and storage efficiency in modern distributed storage systems. However, erasure codes often suffer from a time-consuming coding process which makes them nearly impractical. The opportunity to solve this problem probably rely on the parallelization of erasure-code-based application on the modern multi-/many-core processors to fully take advantage of the adequate hardware resources on those platforms. However, the complicated data allocation and limited I/O throughput pose a great challenge on the parallelization. To address this challenge, we propose a general multi-threaded parallel coding approach in this work. The approach consists of a general multi-threaded parallel coding model named as MTPerasure, and two detailed parallel coding algorithms, named as sdaParallel and ddaParallel, respectively, adapting to different I/O circumstances. MTPerasure is a general parallel coding model focusing on the high level data allocation, and it is applicable for all erasure codes and can be implemented without any modifications of the low level coding algorithms. The sdaParallel divides the data into several parts and the data parts are allocated to different threads statically in order to eliminate synchronization latency among multiple threads, which improves the parallel coding performance under the dummy I/O mode. The ddaParallel employs two threads to execute the I/O reading and writing on the basis of small pieces independently, which increases the I/O throughput. Furthermore, the data pieces are assigned to the coding thread dynamically. A special thread scheduling algorithm is also proposed to reduce thread migration latency. To evaluate our proposal, we parallelize the popular open source library jerasure based on our approach. And a detailed performance comparison with the original sequential coding program indicates that the proposed parallel approach outperforms the original sequential program by an extraordinary speedups from 1.4x up to 7x, and achieves better utilization of the computation and I/O resources.

In this letter we focus on the task of selecting the melody track from a polyphonic MIDI file. Based on the intuition that music and language are similar in many aspects, we solve the selection problem by introducing an n-gram language model to learn the melody co-occurrence patterns in a statistical manner and determine the melodic degree of a given MIDI track. Furthermore, we propose the idea of using background model and posterior probability criteria to make modeling more discriminative. In the evaluation, the achieved 81.6% correct rate indicates the feasibility of our approach.

Device-to-device (D2D) multicast communication is a useful way to improve the communication efficiency of local services. This study considers a scenario of D2D multicast communication in a single frequency network (SFN) system and investigates the frequency resource allocation problem. Firstly, we propose that D2D user equipments (DUEs) do not share frequency with cellular user equipments (CUEs) in the same SFN, but reuse frequency with CUEs in other SFNs, by which the interference between D2D and cellular communications can be avoided. Then, under the principle that two nearest D2D multicast groups cannot reuse the same frequency, the study develops a distance-based fair frequency resource allocation (DFRA) algorithm. The DFRA algorithm ensures control of the interference within a reasonable range and fairly allocate the available frequency resources to the D2D multicast groups. Numerical simulation results show that the proposed resource allocation algorithm is effective in improving the data rate and reducing the outage probability for D2D communications.

During the execution of software, tremendous amounts of data can be recorded. By exploiting the execution data, one can discover behavioral models to describe the actual software execution. As a well-known open-source process mining toolkit, ProM integrates quantities of process mining techniques and enjoys a variety of applications in a broad range of areas. How to develop a better ProM software, both from user experience and software performance perspective, are of vital importance. To achieve this goal, we need to investigate the real execution behavior of ProM which can provide useful insights on its usage and how it responds to user operations. This paper aims to propose an effective approach to solve this problem. To this end, we first instrument existing ProM framework to capture execution logs without changing its architecture. Then a two-layered framework is introduced to support accurate ProM behavior discovery by characterizing both user interaction behavior and plug-in calling behavior separately. Next, detailed discovery techniques to obtain user interaction behavior model and plug-in calling behavior model are proposed. All proposed approaches have been implemented.

A new hybrid brain-computer interface (BCI), which is based on sequential controls by eye tracking and steady-state visual evoked potentials (SSVEPs), has been proposed for high-speed spelling in virtual reality (VR) with a 40-target virtual keyboard. During target selection, gaze point was first detected by an eye-tracking accessory. A 4-target block was then selected for further target selection by a 4-class SSVEP BCI. The system can type at a speed of 1.25 character/sec in a cue-guided target selection task. Online experiments on three subjects achieved an averaged information transfer rate (ITR) of 360.7 bits/min.

Huynen has already provided a method to decompose a Mueller matrix in order to retrieve detailed target information in a polarimetric radar system. However, this decomposition sometimes fails in the presence of small error or noise in the elements of a Mueller matrix. This paper attempts to improve Huynen's decomposition method. First, we give the definition of stable decomposition and present an example, showing a problem of Huynen's approach. Then two methods are proposed to carry out stable decompositions, based on the nonlinear least square method and the Newton's method. Stability means the decomposition is not sensitive to noise. The proposed methods overcomes the problems on the unstable decomposition of Mueller matrix, and provides correct information of a target.

Intelligent transportation system (ITS) makes use of vehicle position to decrease the heavy traffic and improve service reliability of public transportation system. Many existing systems, such as global positioning system (GPS) and cellular communication systems, can be used to estimate vehicle location. The objective of wireless location is to determine the mobile station (MS) location in a wireless cellular communications system. The non-line-of-sight (NLOS) problem is the most crucial factor that it causes large measured error. In this paper, we present a novel positioning algorithm based on genetic algorithm (GA) to locate MS when three BSs are available for location purpose. Recently, GA are widely used as many various optimization problems. The proposed algorithm utilizes the intersections of three time of arrival (TOA) circles based on GA to estimate the MS location. The simulation results show that the proposed algorithms can really improve the location accuracy, even under severe NLOS conditions.

In order to improve the frequency band utilization and avoid mutual interference between signals, the BD3 satellite signals adopt Binary Offset Carrier (BOC) modulation. On one hand, BOC modulation has a narrow main peak width and strong anti-interference ability; on the other hand, the phenomenon of false acquisition locking caused by the multi-peak characteristic of BOC modulation itself needs to be resolved. In this context, this paper proposes a new BOC(n,n) unambiguous acquisition algorithm based on segmentation reconstruction. The algorithm is based on splitting the local BOC signal into four parts in each subcarrier period. The branch signal and the received signal are correlated with the received signal to generate four branch correlation signals. After a series of combined reconstructions, the final signal detection function completely eliminates secondary peaks. A simulation shows that the algorithm can completely eliminate the sub-peak interference for the BOC signals modulated by subcarriers with different phase. The characteristics of narrow correlation peak are retained. Experiments show that the proposed algorithm has superior performance in detection probability and peak-to-average ratio.

Gaze following is the task of estimating where an observer is looking inside a scene. Both the observer and scene information must be learned to determine the gaze directions and gaze points. Recently, many existing works have only focused on scenes or observers. In contrast, revealed frameworks for gaze following are limited. In this paper, a gaze following method using a hybrid transformer is proposed. Based on the conventional method (GazeFollow), we conduct three developments. First, a hybrid transformer is applied for learning head images and gaze positions. Second, the pinball loss function is utilized to control the gaze point error. Finally, a novel ReLU layer with the reborn mechanism (reborn ReLU) is conducted to replace traditional ReLU layers in different network stages. To test the performance of our developments, we train our developed framework with the DL Gaze dataset and evaluate the model on our collected set. Through our experimental results, it can be proven that our framework can achieve outperformance over our referred methods.

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.

This paper provides a prototype neural prosthesis system dedicated to restoring continence and micturition function for patients with lower urinary tract diseases, such as detrusor hyperreflexia and detrusor-sphincter dyssynergia. This system consists of an ultra low-noise electroneurogram (ENG) signal recording module, a bi-phasic electrical stimulator module and a control unit for closed-loop bladder monitoring and controlling. In order to record extremely weak ENG signal from extradural sacral nerve roots, the system provides a programmable gain from 80 dB to 117 dB. By combining of advantages of commercial-off-the-shelf (COTS) electronics and custom designed IC, the recording front-end acquires a fairly low input-referred noise (IRN) of 0.69 μVrms under 300 Hz to 3 kHz and high area-efficiency. An on-chip multi-steps single slope analog-to-digital converter (ADC) is used to digitize the ENG signals at sampling rate of 10 kSPS and achieves an effective number of bits (ENOB) of 12.5. A bi-phasic current stimulus generator with wide voltage supply range (±0.9 V to ±12.5 V) and variable output current amplitude (0-500 μA) is introduced to overcome patient-depended impedance between electrode and tissue electrolyte. The total power consumption of the entire system is 5.61 mW. Recording and stimulation function of this system is switched by control unit with time division multiplexing strategy. The functionality of this proposed prototype system has been successfully verified through in-vivo experiments from dogs extradural sacral nerve roots.

For the completely polarized wave case, this paper presents the explicit formulae of the characteristic polarization states in the co-polarized radar channel, from which one can obtain the CO-POL Max, the CO-POL Saddle and the CO-POL Nulls in the Stokes vector form. Then the problem on the polarimetric contrast optimization is discussed, and the explicit formula of the optimal polarization state for contrast enhancement is presented in the Stokes vector form for the first time. To verify these formulae, we give some numerical examples. The results are completely identical with other authors', which shows the validity of the presented method.

In this letter, we propose a two-stage object-based error-concealment technique for MPEG-2 video transmitted in a burst-packet-loss environment. A burst packet loss typically destroys a large area of MPEG-2 coded video. In the first stage, the missing area is intra-picture estimated and concealed in terms of a region-based approach. In the second stage, irregular-moving objects with respect to the background are identified and compensated from the predictive picture. As compared with conventional concealment approaches, the proposed method achieves better PSNR performance and reduces the visual artifacts.

This paper discusses the problems of largest similar substructures (in short, LSS) in rooted and unordered trees (in short, R-trees) and those in unrooted and unordered trees (in short, trees). For two R-trees (or trees) Ta and Tb, LSS in Tb to Ta is defined, and two algorithms for finding one of the LSSs for R-trees and that for trees are proposed. The time and space complexities of both algorithms are OT (m3NaNb) and OS(mNaNb), respectively, where m is the largest degree of a vertex of Ta and Tb, and Na(Nb)is the number of vertices of Ta(Tb).

We regard a De Bruijn sequence of order n as a bijection on $mathbb{F}_2^n$ and consider the transition mappings between them. It is shown that there are only two conjugate transformations that always transfer De Bruijn sequences to De Bruijn sequences.

A low-voltage and low-power RF mixer for WCDMA applications is presented. The paper presents a novel topology mixer that leads to a better performance in terms of isolation and power consumption for low supply voltage. The measuring results of the proposed mixer achieve: 7 dB power conversion gain, 10.4 dB double side band (DSB) noise figure, -2 dBm input third-order intercept point (IIP3), and the total dc power consumption of this mixer including output buffers is 2.2 mW from a 1 V supply voltage. The current output buffer is about 1.96 mW, the excellent LO-RF, LO-IF and RF-IF isolation achieved up to 49 dB, 39.5 dB and 57.3 dB, respectively.

Bistatic multi-input multi-output (MIMO) radar has the capability of measuring the transmit angle from the receiving array, which means the existence of information redundancy and benefits data association. In this paper, a data association decision for bistatic MIMO radar is proposed and the performance advantages of bistatic MIMO radar in data association is analyzed and evaluated. First, the parameters obtained by receiving array are sent to the association center via coordinate conversion. Second, referencing the nearest neighbor association (NN) algorithm, an improved association decision is proposed with the transmit angle and target range as association statistics. This method can evade the adverse effects of the angle system errors to data association. Finally, data association probability in the presence of array directional error is derived and the correctness of derivation result is testified via Monte Carlo simulation experiments. Besides that performance comparison with the conventional phased array radar verifies the excellent performance of bistatic MIMO Radar in data association.

This paper, presents a high-speed full swing driver for a heavy-load flat-panel scan-line circuit. The high driving capability is achieved using the proposed Complementary Dual-Bootstrap (CDUB) technique. The scan-line CDUB driver was fabricated in a 0.35-µm CMOS technology. The measured results, under the flat-panel scan-line load model, indicate that the delay time is within 2.8µs and the average power is 0.74mW for a 5V supply voltage.