Sound event detection in real-life audio using joint spectral and temporal features

Typical methods for overlapping sound event detection (SED) do not fully consider the joint spectral and temporal transition characteristics of the audio signal. They are generally based on training models using either separate data from each event class or mixed signals containing simultaneous sound events. This paper introduced a new approach for SED in real-life audio using Nonnegative Matrix Factor 2-D Deconvolution and RUSBoost techniques. The idea is to capture the two-dimensional joint spectral and temporal information from the time-frequency representation while possibly separating the sound mixture into several sources. In addition, the RUSBoost technique is utilized to address the class imbalance problem of the training data. The proposed approach is evaluated using the TUT Sound Event 2016 and 2017 datasets. The results showed that the proposed method outperformed the baseline methods. For the TUT Sound Event 2016 dataset, the proposed method reduced the total error rate by 5% while increasing the F1 score by 13.8%. For the TUT Sound Event 2017 dataset, the proposed method reduced the total error rate by 3% while increasing the F1 score by 8.1%.     

A new video magnification technique using complex wavelets with Radon transform application

Magnifying micro-movements of natural videos that are undetectable by human eye has recently received considerable interests, due to its impact in numerous applications. In this paper, we use dual tree complex wavelet transform (DT-CWT), to analyze video frames in order to detect and magnify micro-movements to make them visible. We use DT-CWT, due to its excellent edge-preserving and nearly-shift invariant features. In order to detect any minor change in object’s spatial position, the paper proposes to modify the phases of the CWT coefficients decomposition of successive video frames. Furthermore, the paper applies Radon transform to track frame micro-movements without any temporal band-pass filtering. The paper starts by presenting a simple technique to design orthogonal filters that construct this CWT system. Next, it is shown that modifying the phase differences between the CWT coefficients of arbitrary frame and a reference one results in image spatial magnification. This in turn, makes these micro-movements seen and observable. Several simulation results are given, to show that the proposed technique competes very well to the existing micro-magnification approaches. In fact, as it manages to yield superior video quality in far less computation time.     

An enhanced deterministic beacon advertising algorithm for building TSCH networks

In this paper, we focus first on the time needed by a node to join a Time Slotted Channel Hopping (TSCH) network, this time is called joining time. Second, we are also interested in the network building time. Since the data generated by a sensor node remain unavailable as long as this node has not yet joined the wireless sensor network, these times are of prime importance for applications having strong latency requirements on data gathering. The joining time depends on the beacon advertising policy that has been left unspecified by the standard. The contribution of this paper is triple. First, we propose an Enhanced Deterministic Beacon Advertising algorithm, called EDBA, that ensures a collision-free advertising of beacons and minimizes the average joining time. Second, we model the behavior of a joining node by a Markov chain, validated by NS3 simulations, and compute the average joining time. Third, we compare the performance of EDBA with this of MBS, considered as the best beacon advertising algorithm in the literature.     

Properties of Indium-Doped ZnO Films Prepared in an Oxygen-Rich Plasma

Indium-doped zinc oxide (ZnO:In) films were prepared in an Ar:O₂ plasma by reactive magnetron sputtering. The x-ray diffraction (XRD) patterns presented the crystal structures of ZnO:In films, while transmission spectra and photoluminescence (PL) spectra showed the changed band gap and the visible emission from defects, as compared to the PL spectra of undoped ZnO films. It was concluded that the increase of substrate temperature enhanced the crystal quality of ZnO:In films; the incorporation of In made the c-axis constant of the samples larger than that of undoped ZnO films; the blue emission was due to the transition from an unknown donor level by indium doping to the valance band; and the orange-green emission originated from acceptor defects (O_Zn) formed in the O-rich plasma. Meanwhile, the current- voltage characteristics and persistent photoconductivity phenomenon also could be explained by the increased acceptor defects (O_Zn) that formed when the substrate temperature was increased.     

Millimeter-wave Detectors Based on Antenna-coupled Low-barrier Schottky Diodes

The principles of construction of millimeter wave detectors based on low-barrier Schottky diodes and planar antennas are discussed. The modified planar slot antenna with low beam spillover at the resonant frequency of 94 GHz has been developed. Experiments have been carried out to investigate detecting characteristics of the diodes with differential contact resistances \( R_{j} = 1 \div 1000\;{\text{k}}\Omega \) at zero bias. Experimental data are well correspond to calculations in a simple model of detector. At \( R_{j} = 20 \div 100\;{\text{k}}\,\OmegaΩ \) the maximum of rf-to-dc voltage sensitivity - more than 10000 V/W - is obtained. At lower values of \( R_{j} = 2 \div 6\;{\text{k}}\,\Omega Ω \) a better noise equivalent power (NEP), around 10^?12 W Hz^?1/2, is predicted.     

Solution-Processed High-<Emphasis Type="Italic">k</Emphasis> Dielectric,ZrO<Subscript>2</Subscript>, and Integration in Thin-Film Transistors

We report a sol–gel method to deposit a high-k dielectric, zirconium oxide (ZrO₂). This solution-based approach has advantages of easy processing and low fabrication cost. Effects of annealing temperatures on dielectric properties, such as tunneling current density and capacitance density, are reported. Morphological and chemical characterizations suggest that the process temperature can be kept at or below 300°C. We have employed the solution-processed ZrO₂ dielectric in a zinc tin oxide thin-film transistor. Saturation mobility of 4.0 cm²/V s at operating voltage of 2 V has been observed. The measured subthreshold swing is 74 mV/decade, which is the result of the combination of an electronically clean dielectric/semiconductor interface and high insulator capacitance.     

Multiple LDPC-Encoder Layered Space-Time-Frequency Architectures for OFDM MIMO Multiplexing

This paper is focused on the study of layered space-time-frequency (LSTF) architectures with channel coding for orthogonal frequency division multiplexing (OFDM) multiple-input multiple-output (MIMO) multiplexing systems for high speed wireless communications over a frequency-selective fading channel. In order to achieve the available spatial, temporal and frequency diversities, and also make the system implementation feasible for high speed OFDM MIMO multiplexing, a novel LSTF architecture with multiple channel encoders is proposed with each independently coded layer being threaded in the three-dimensional space-time-frequency transmission resource array. Non-iterative receiver is adopted which consists of list sphere detector and irregular low-density parity-check codes as the constituent codes. Simulation results show that the performance of the proposed multiple-encoder LSTF architecture is very close to that of the conventional single-encoder LSTF where coding is applied across the whole information stream. However, due to the use of multiple parallel encoders/decoders with a shorter codeword length, the proposed LSTF architecture has much lower hardware processing speed and complexity than the conventional LSTF.     

Recognition of the Communication Signals Using Particle Swarm Optimization and Support Vector Machine Based on the Multi-Resolution Wavelet Analysis

Automatic recognition of the communication signals plays an important role for various applications. This paper presents a novel intelligent system for recognition of digital communication signals. This system includes three main modules: feature extraction module, classifier module and optimization module. In the feature extraction module, multi-resolution wavelet analysis is proposed for extraction the suitable features. In the classifier module, a multi-class support vector machine (SVM) based classifier is proposed as the multi-class classifier. For optimization module, a particle swarm optimization algorithm is proposed to improve the generalization performance of the recognizer. In this module, it is optimized the SVM classifier design by searching for the best value of the parameters that tune its discriminant function, and upstream by looking for the best subset of features that feed the classifier. Simulation results show that the proposed hybrid intelligent system has high performance even at very low signal to noise ratios (SNRs).     

New Criteria of Robust $$H_\infty $$ Stability for Fuzzy Mixed-Delay Systems with Nonlinear Noise Disturbances

This paper investigates new criteria of the robust \(H_\infty \) stability for a class of uncertain stochastic fuzzy mixed-delay systems with nonlinear noise disturbances by employing an improved free-weighting matrix approach. The fuzzy system is based on the Takagi–Sugeno model that is often used to represent the complex nonlinear systems in terms of fuzzy sets and fuzzy reasoning. To reflect more realistic dynamical behaviors of the system, both the parameter uncertainties and stochastic disturbances are considered, the stochastic disturbances are given in the form of a Brownian motion. The mixed delays comprise both discrete and distributed time-varying delays. In terms of a stochastic fuzzy Lyapunov functional, a sufficient criterion is proposed to investigate dynamical behaviors of the system in the mean-square sense with an \(H_\infty \) performance index.