Search Results (36)

Traffic accidents caused by black ice have become a serious public safety concern due to their high fatality rates and the limitations of conventional detection systems under low visibility. Millimeter-wave (mmWave) radar, capable of operating reliably in adverse weather and lighting conditions, offers a promising alternative for road surface monitoring. In this study, six representative road surface conditions—dry, wet, thin-ice, ice, snow, and sludge—were experimentally implemented on asphalt and concrete specimens using a temperature and humidity-controlled chamber. mmWave radar data were repeatedly collected to analyze the temporal variations in reflected signals. The acquired signals were transformed into range-based spectra using Range-Fast Fourier Transform (Range-FFT) and converted into statistical features and graphical representations. These features were used to train and evaluate classification models, including Extreme Gradient Boost (XGBoost), Light Gradient-Boosting Machine (LightGBM), Convolutional Neural Networks (CNN), and Vision Transformer (ViT). While machine learning models performed well under dry and wet conditions, their accuracy declined in hazardous states. Both CNN and ViT demonstrated superior performance across all conditions, with CNN showing consistent stability and ViT exhibiting competitive accuracy with enhanced global pattern-recognition capabilities. Comprehensive robustness evaluation under various noise and blur conditions revealed distinct characteristics of each model architecture. This study demonstrates the feasibility of mmWave radar for reliable road surface condition recognition and suggests potential for improvement through multimodal sensor fusion and time-series analysis. Full article

Toward the innovative design of tunable structures for energy generation, this paper presents an extended Floating Frame of Reference (FFR) formulation capable of modeling slope discontinuities in flexible multibody systems—overcoming a key limitation of conventional FFR methods that assume slope continuity. The model is validated using a spatial double-pendulum structure composed of circular beam elements, representative of out-of-plane energy harvesting systems. To investigate the influence of boundary constraints on dynamic behavior, three electromagnetic clamping configurations—Fixed–Free–Free (XFF), Fixed–Free–Fixed (XFX), and Free–Fixed–Free (FXF)—are implemented. Tri-axial accelerometer measurements are analyzed via Fast Fourier Transform (FFT), revealing natural frequencies spanning from 38.87 Hz (lower frequency range) to 149.01 Hz (higher frequency range). For the lower frequency range, the FFR results (38.76 Hz) show a close match with the experimental prediction (38.87 Hz) and ANSYS simulation (36.49 Hz), yielding 0.28% error between FFR and experiments and 5.85% between FFR and ANSYS. For the higher frequency range, the FFR model (148.17 Hz) achieves 0.56% error with experiments (149.01 Hz) and 0.85% with ANSYS (146.91 Hz). These high correlation percentages validate the robustness and accuracy of the proposed FFR formulation. The study further shows that altering boundary conditions enables effective frequency tuning in discontinuous structures—an essential feature for the optimization of application-specific systems such as wave energy converters. This validated framework offers a versatile and reliable tool for the design of vibration-sensitive devices with geometric discontinuities. Full article

Tool breakage in CNC machining often leads to reduced productivity and increased maintenance costs. This study proposes a non-contact tool breakage detection method using spindle current signals captured by an SCT013 current sensor. The sensor easily attaches to the motor line without any hardware modification and provides real-time current signals for frequency domain analysis. Fast Fourier Transform (FFT) is employed to extract spectral features, particularly focusing on high-frequency energy spikes at the moment of breakage. A total of 20 experiments were conducted, and consistent spectral anomalies were observed. Additionally, deep learning models including ANN, DNN, and CNN were compared for automated detection performance. The results indicate that the proposed system can reliably detect tool breakage by identifying frequency domain anomalies that emerge within 1–3 s after the actual event, based on processed current signals. While the inference time of deep learning models ranges from 15 to 58 s, the detection mechanism captures the breakage characteristics early in the signal, enabling timely tool condition evaluation. Full article

As the most basic mechanical components, bearing troubleshooting is essential to ensure the safe and reliable operation of rotating machinery. Bearing fault diagnosis is challenging due to the scarcity of bearing fault diagnosis samples and the susceptibility of fault signals to external noise. To address these issues, a ResNet-CACNN-BiGRU-SDPA bearing fault diagnosis method based on time–frequency bi-domain and feature fusion is proposed. First, the model takes the augmented time-domain signals as inputs and reconstructs them into frequency-domain signals using FFT, which gives the signals a bi-directional time–frequency domain receptive field. Second, the long sequence time-domain signal is processed by a ResNet residual block structure, and a CACNN method is proposed to realize local feature extraction of the frequency-domain signal. Then, the extracted time–frequency domain long sequence features are fed into a two-layer BiGRU for bidirectional deep global feature mining. Finally, the long-range feature dependencies are dynamically captured by SDPA, while the global dual-domain features are spliced and passed into Softmax to obtain the model output. In order to verify the model performance, experiments were carried out on the CWRU and JNU bearing datasets, and the results showed that the method had high accuracy under both small sample size and noise perturbation conditions, which verified the model’s good fault-feature-learning capability and noise immunity performance. Full article

Online monitoring of partial discharge (PD) is a complex task traditionally requiring specialized expertise. However, recent advancements in signal processing and machine learning have facilitated the development of automated tools to identify and categorize PD patterns, aiding those without extensive experience. This paper aims to identify PD types and estimate the density distribution of frequency characteristics for three PD types, internal PD, surface PD, and corona PD, using verified PD data. The proposed method employs a findpeaks algorithm based on Fast Fourier Transform (FFT) to extract frequency key features, denoted as f₁ and f₂, from the frequency spectrum. These features are used to estimate model parameters for each PD type, enabling the representation of their frequency density distributions in a 2D map (f₁, f₂) via Gaussian Mixture Models (GMMs). The optimal number of Gaussian components, determined as five using the Bayesian Information Criterion (BIC), ensures accurate modeling. For PD identification, log-likelihood and softmax functions are applied, achieving an evaluation accuracy of 96.68%. The model also demonstrates robust performance in identifying unknown PD data, with accuracy ranging from 78.10% to 95.11%. This approach enhances the distinction between PD types based on their frequency characteristics, providing a reliable tool for PD signal analysis and identification. Full article

In brain–computer interface (BCI) systems, steady-state visual-evoked potentials (SSVEP) and P300 responses have achieved widespread implementation owing to their superior information transfer rates (ITR) and minimal training requirements. These neurophysiological signals have exhibited robust efficacy and versatility in external device control, demonstrating enhanced precision and scalability. However, conventional implementations predominantly utilise liquid crystal display (LCD)-based visual stimulation paradigms, which present limitations in practical deployment scenarios. This investigation presents the development and evaluation of a novel light-emitting diode (LED)-based dual stimulation apparatus designed to enhance SSVEP classification accuracy through the integration of both SSVEP and P300 paradigms. The system employs four distinct frequencies—7 Hz, 8 Hz, 9 Hz, and 10 Hz—corresponding to forward, backward, right, and left directional controls, respectively. Oscilloscopic verification confirmed the precision of these stimulation frequencies. Real-time feature extraction was accomplished through the concurrent analysis of maximum Fast Fourier Transform (FFT) amplitude and P300 peak detection to ascertain user intent. Directional control was determined by the frequency exhibiting maximal amplitude characteristics. The visual stimulation hardware demonstrated minimal frequency deviation, with error differentials ranging from $0.15$% to $0.20$% across all frequencies. The implemented signal processing algorithm successfully discriminated between all four stimulus frequencies whilst correlating them with their respective P300 event markers. Classification accuracy was evaluated based on correct task intention recognition. The proposed hybrid system achieved a mean classification accuracy of $86.25$%, coupled with an average ITR of $42.08$ bits per minute (bpm). These performance metrics notably exceed the conventional 70% accuracy threshold typically employed in BCI system evaluation protocols. Full article

Human activity recognition (HAR) using radar technology is becoming increasingly valuable for applications in areas such as smart security systems, healthcare monitoring, and interactive computing. This study investigates the integration of convolutional neural networks (CNNs) with conventional radar signal processing methods to improve the accuracy and efficiency of HAR. Three distinct, two-dimensional radar processing techniques, specifically range-fast Fourier transform (FFT)-based time-range maps, time-Doppler-based short-time Fourier transform (STFT) maps, and smoothed pseudo-Wigner–Ville distribution (SPWVD) maps, are evaluated in combination with four state-of-the-art CNN architectures: VGG-16, VGG-19, ResNet-50, and MobileNetV2. This study positions radar-generated maps as a form of visual data, bridging radar signal processing and image representation domains while ensuring privacy in sensitive applications. In total, twelve CNN and preprocessing configurations are analyzed, focusing on the trade-offs between preprocessing complexity and recognition accuracy, all of which are essential for real-time applications. Among these results, MobileNetV2, combined with STFT preprocessing, showed an ideal balance, achieving high computational efficiency and an accuracy rate of 96.30%, with a spectrogram generation time of 220 ms and an inference time of 2.57 ms per sample. The comprehensive evaluation underscores the importance of interpretable visual features for resource-constrained environments, expanding the applicability of radar-based HAR systems to domains such as augmented reality, autonomous systems, and edge computing. Full article

The consecutive submesoscale sea surface processes observed by an unmanned aerial vehicle (UAV) were used to decompose into spatial waves and current features. For the image decomposition, the Fast and Adaptive Multidimensional Empirical Mode Decomposition (FA-MEMD) method was employed to disintegrate multicomponent signals identified in sea surface optical images into modulated signals characterized by their amplitudes and frequencies. These signals, referred to as Bidimensional Intrinsic Mode Functions (BIMFs), represent the inherent two-dimensional oscillatory patterns within sea surface optical data. The BIMFs, separated into seven modes and a residual component, were subsequently reconstructed based on the physical frequencies. A two-dimensional Fast Fourier Transform (2D FFT) for each high-frequency mode was used for surface wave analysis to illustrate the wave characteristics. Wavenumbers (K_x, K_y) ranging between 0.01–0.1 radm⁻¹ and wave directions predominantly in the northeastward direction were identified from the spectral peak ranges. The Optical Flow (OF) algorithm was applied to the remaining consecutive low-frequency modes as the current signal under 0.1 Hz for surface current analysis and to estimate a current field with a 1 m spatial resolution. The accuracy of currents in the overall region was validated with in situ drifter measurements, showing an R-squared (R²) value of 0.80 and an average root-mean-square error (RMSE) of 0.03 ms⁻¹. This study proposes a novel framework for analyzing individual sea surface dynamical processes acquired from high-resolution UAV imagery using a multidimensional signal decomposition method specialized in nonlinear and nonstationary data analysis. Full article

Image dehazing aims to reconstruct potentially clear images from corresponding images corrupted by haze. With the rapid development of deep learning-related technologies, dehazing methods based on deep convolutional neural networks have gradually become mainstream. We note that existing dehazing methods often accompany an increase in computational overhead while improving the performance of dehazing. We propose a novel lightweight dehazing neural network to balance performance and efficiency: the g2D-Net. The g2D-Net borrows the design ideas of input-adaptive and long-range information interaction from Vision Transformers and introduces two kinds of convolutional blocks, i.e., the g2D Block and the FFT-g2D Block. Specifically, the g2D Block is a residual block with second-order gated units, which inherit the input-adaptive property of a gated unit and can realize the second-order interaction of spatial information. The FFT-g2D Block is a variant of the g2D Block, which efficiently extracts the global features of the feature maps through fast Fourier convolution and fuses them with local features. In addition, we employ the SK Fusion layer to improve the cascade fusion layer in a traditional U-Net, thus introducing the channel attention mechanism and dynamically fusing information from different paths. We conducted comparative experiments on five benchmark datasets, and the results demonstrate that the g2D-Net achieves impressive dehazing performance with relatively low complexity. Full article

The distinctive feature of hyperspectral images (HSIs) is their large number of spectral bands, which allows us to identify categories of ground objects by capturing discrepancies in spectral information. Convolutional neural networks (CNN) with attention modules effectively improve the classification accuracy of HSI. However, CNNs are not successful in capturing long-range spectral–spatial dependence. In recent years, Vision Transformer (VIT) has received widespread attention due to its excellent performance in acquiring long-range features. However, it requires calculating the pairwise correlation between token embeddings and has the complexity of the square of the number of tokens, which leads to an increase in the computational complexity of the network. In order to cope with this issue, this paper proposes a multi-scale spectral–spatial attention network with frequency-domain lightweight Transformer (MSA-LWFormer) for HSI classification. This method synergistically integrates CNN, attention mechanisms, and Transformer into the spectral–spatial feature extraction module and frequency-domain fused classification module. Specifically, the spectral–spatial feature extraction module employs a multi-scale 2D-CNN with multi-scale spectral attention (MS-SA) to extract the shallow spectral–spatial features and capture the long-range spectral dependence. In addition, The frequency-domain fused classification module designs a frequency-domain lightweight Transformer that employs the Fast Fourier Transform (FFT) to convert features from the spatial domain to the frequency domain, effectively extracting global information and significantly reducing the time complexity of the network. Experiments on three classic hyperspectral datasets show that MSA-LWFormer has excellent performance. Full article

This paper presents the development and signal analysis of surface plasmon resonance (SPR)-based sensors in D-shaped polymer optical fibers (POFs). A gold-palladium (Au-Pd) coating was applied to the D-shaped region to obtain the SPR signal in the transmitted spectrum of the POFs, where different samples were fabricated using the same methods and parameters. In this case, the transmitted spectra of three sets of samples were compared, which indicated variations in the SPR signature that can influence the sensors’ application and reproducibility. Then, the intensity of and wavelength shift in the SPR signals were analyzed as a function of the refractive index variation, where it was possible to observe differences in the sensors’ sensitivities and the linearity of the different samples. In this regard, additional features, namely the area below the curve and the peak amplitude of the fast Fourier transform (FFT) applied to the transmitted spectra, were used to enhance the sensors’ accuracy and precision. To verify the use of such additional features in the sensor analysis, an unsupervised approach based on k-means clustering was used considering a single dataset with the results of all the sensors. The results showed clustering with the number of different refractive indices tested, which motivated the use of these features (intensity, wavelength, area and FFT amplitude) in the refractive index assessment. In this context, random forest was the supervised algorithm with the smallest root mean squared error (RMSE) among the algorithms tested, where an RMSE of 0.0057 was obtained considering all the datasets. For the analysis of each sensor (considering the three sets of sensor samples), the mean RMSE using random forest applied to the multifeature approach returned relative errors below 9%, considering the entire tested range of refractive index variation. Full article

The stable operation of a variable frequency pump is of great importance to the management of a water supply project. Analyzing the operation performance based on monitoring data is necessary for maintaining the stable operation of a variable frequency pump. Several sensors are installed at six monitoring points on the pump to collect signals including vibration velocity, vibration acceleration and vibration displacement. Monitoring signals are preprocessed by smoothing, adjusting waveform trend and filtering on the basis of Fast Fourier Transform (FFT). Then, the vibration features are extracted by power spectrum analysis and cepstrum analysis methods. According to the extracted features, the vibration law and actual operation performance of a variable frequency pump under different operating conditions are analyzed. Results indicate that the vibration amplitude of the pump varies sharply under the operating conditions of [15 Hz, 20 Hz] and [30 Hz, 35 Hz]. The operating condition of [0 Hz, 15 Hz] is the restricted operating area of the pump. The vibration and noise continue increasing under the operating conditions of [35 Hz, 50 Hz] and reach the maximum values at 50 Hz. Therefore, the optimal operating is within the range of [20 Hz, 30 Hz]. Finally, by analyzing the critical values of the operating conditions, the fault diagnosis and the evaluation of the operating status are conducted. Full article

Vortex electromagnetic (EM) waves, with different orbital angular momentum (OAM) modes, have the ability to distinguish the azimuth of radar targets, and then the two-dimensional reconstruction of the targets can be achieved. However, the vortex EM wave imaging methods in published research have no ability to obtain the elevation of the targets, and thus, the three-dimensional spatial structure and richer feature information of the radar target cannot be obtained. Therefore, a three-dimensional imaging method of vortex EM waves with integer- and fractional-order OAM modes is proposed in this paper, which can realize a three-dimensional reconstruction of a radar target based on a uniform circular array (UCA) with two-step imaging. First, the vortex EM wave with integer- and fractional-order OAM modes is generated, and the echo model with different OAM mode types is established. Thereafter, the echo with integer order is processed to obtain the range-azimuth image by fast Fourier transform (FFT). Then, in order to realize the three-dimensional reconstruction, the echo with fractional order is processed by utilizing the butterfly operation and analyzing the characteristics of the fractional Bessel function. Moreover, the resolution and reconstruction precision of the azimuth and elevation are analyzed. Finally, the effectiveness of the proposed method is verified by simulation experiments. Full article

Millimeter wave radars in frequency-modulated continuous wave (FMCW) systems are widely used in the field of noncontact life signal detection; however, large errors still persist when determining the distance dimension of the target to be measured with the radar echo signal. The processing of the signals in the target environment is blind. We propose a method of using binocular vision to lock the distance dimension of the radar life signal and to determine the target distance by using the principle of the binocular camera parallax method, as this reduces the influence of the noise in the environment when determining the distance dimension of the target to be measured. First, the Yolo (you only look once: unified, real-time object detection) v5s neural network is used to call the binocular camera to detect the human body, where the resolution of the single lens is 1280 × 1200, and the DeepSORT (deep simple online real-time tracking) algorithm is used to extract the features of the target and track and register them. Additionally, the binocular vision parallax ranging method is used to detect the depth information of the target, search for the depth information in the range-dimensional FFT (frequency Fourier transform) spectrum of the radar echo signal, and take the spectral peak with the largest energy within the search range to determine it as the target. Then, the target is measured, the range gate of the target is determined, and the life signal is then separated through operations such as phase information extraction, unwrapping, and filtering. The test results showed that this method can be used to directionally separate and register corresponding life signals in a multiliving environment. By conducting an analysis using the Pearson correlation coefficient, we found that the correlation between the breathing frequency collected using this method and a breathing sensor reached 84.9%, and the correlation between the heartbeat frequency and smart bracelet results reached 93.6%. The target range gate was locked to separate and match the life signal. Full article

In this work, we study the characteristics of femtosecond-filament-laser–matter interactions and laser-induced periodic surface structures (LIPSS) at a beam-propagation distance up to 55 m. The quantification of the periodicity of filament-induced self-organized surface structures was accomplished by SEM and AFM measurements combined with the use of discrete two-dimensional fast Fourier transform (2D-FFT) analysis, at different filament propagation distances. The results show that the size of the nano-scale surface features increased with ongoing laser filament processing and, further, periodic ripples started to form in the ablation-spot center after irradiation with five spatially overlapping pulses. The effective number of irradiating filament pulses per spot area affected the developing surface texture, with the period of the low spatial frequency LIPSS reducing notably at a high pulse number. The high regularity of the filament-induced ripples was verified by the demonstration of the angle-of-incidence-dependent diffraction of sunlight. This work underlines the potential of long-range femtosecond filamentation for energy delivery at remote distances, with suppressed diffraction and long depth focus, which can be used in biomimetic laser surface engineering and remote-sensing applications. Full article