Search Results (9)

To deal with the insufficient recognition accuracy of traditional signal modulation recognition methods, this paper proposes a new communication signal modulation recognition method with a deep neural network that integrates a multi-feature multi-channel ResNet and BiLSTM neural network (MF-MC ResNet-BiLSTM). By converting the original modulation data into three different vector formats, which are IQ format, AP format, and FFT format, we obtained the model inputs which contain various feature information. After inputting three types of vector signals into the multi-channel feature fusion module, the network converts these input signals into a high-dimensional feature space for feature fusion, and extracts features we need from different signal sources. Meanwhile, we designed a multi-channel model that integrates ResNet-BiLSTM to perform feature fusion, extracting key features of the modulation signal to avoid the degradation of orthogonality caused by parameter imbalance. To further enhance modulation recognition performance, an adaptive multi-head attention network was designed to extract features through weighted integration. Simulation results demonstrate that this method exhibits model generalization capabilities and good robustness. Experimental data validate that the method achieves a recognition rate of 95.67% and a recall rate of 94.56% in low signal-to-noise ratio (SNR) environments (−22 dB–2 dB), significantly outperforming existing networks like MMF(multimodal fusion), FGDNN(fusion GRU deep learning neural network), and LightMFFS(redlightweight multi-feature fusion structure). Full article

Background/Objectives: Closed-loop phase-locked TMS aims to deliver stimulation at targeted EEG phases, but real-time phase prediction remains a practical bottleneck. Timing errors are especially harmful near peaks and troughs, where small offsets can substantially degrade phase targeting. We benchmark representative predictors and develop models that improve phase consistency while reducing peak/trough lag. Methods: Using the publicly available Monash University TEPs–MEPs dataset, we benchmark classical predictors (AR- and FFT-based) and recurrent baselines (LSTM, GRU). To quantify extremum-specific behavior critical for closed-loop triggering, we propose Mean Lag Time (MLT), defined as the average temporal offset between predicted and ground-truth extrema, alongside PLV, APE, MAE, and RMSE. We further propose a parallel DSC-Attention-GRU architecture combining depthwise separable convolutions for efficient multi-channel spatio-temporal feature extraction with self-attention for spatial reweighting and dependency modeling, followed by a GRU phase predictor. A lightweight SqueezeNet-Attention-GRU variant is also designed for real-time constraints. Results: LSTM/GRU outperform AR/FFT in capturing temporal dynamics but retain residual peak/trough lag. Across stimulation intensities and frequency bands, DSC-Attention-GRU consistently improves phase consistency and prediction accuracy and reduces extremum lag, lowering MLT from ~7.77–7.79 ms to ~7.50–7.56 ms. The lightweight variant maintains stable performance with an average 3.7% inference speedup. Conclusions: Explicitly optimizing extremum timing via MLT and enhancing multi-channel modeling with DSC and attention reduces peak/trough lag and improves phase-consistent prediction, supporting low-latency closed-loop phase-locked TMS. Full article

We investigate analog and digital pre-emphasis for ultra-high-bit-rate coherent dual-polarization 64-QAM (DP-64QAM) transmission using OptiSystem. Two representative single-wavelength configurations are studied: 64 Gbaud (600 Gb/s payload, 768 Gb/s line rate) and 100 Gbaud (1000 Gb/s payload, 1.2 Tb/s line rate). The transmitter employs raised-cosine pulse shaping (roll-off 0.1) and a 9-bit DAC, while the receiver uses a 9-bit ADC; bandwidth-limiting Bessel/Gaussian filters emulate practical transmitter (Tx) and receiver (Rx) front-end constraints. Analog pre-emphasis (APE) is realized by uploading a measured analog filter response immediately after the DAC to compensate high-frequency roll-off. Digital pre-emphasis (DPE) is implemented before the DAC as a finite-impulse-response (FIR) pre-distortion stage, with taps obtained from the measured frequency response via spectrum mirroring, inverse FFT, Hamming-window smoothing, and normalization. We compare four cases: (i) ideal reference without bandwidth limits; (ii) bandwidth-limited without pre-emphasis; (iii) APE; and (iv) DPE. Bit-error-rate–versus–optical signal-to-noise ratio (OSNR) results show that both APE and DPE substantially mitigate bandwidth-induced penalties and approach the theoretical bound, reducing the OSNR gap to 5.8 dB at 64 Gbaud and 6.6 dB at 100 Gbaud, with operation near the forward error correction (FEC) threshold ($\mathrm{BER}={10}^{-2}$). While DPE offers full programmability, it increases peak-to-average power ratio (PAPR) and may require additional gain headroom. Overall, APE provides an effective rapid-prototyping step prior to DPE deployment, confirming the feasibility of 768 Gb/s and 1.2 Tb/s DP-64QAM links with commercially realistic components, including a 150 GSa/s DAC operating at 1.5 samples/symbol for 100 Gbaud. Full article

Small object detection in aerial imagery remains challenging due to sparse feature representation, limited spatial resolution, and complex background interference. Current deep learning approaches enhance detection performance through multi-scale feature fusion, leveraging convolutional operations to expand the receptive field or self-attention mechanisms for global context modeling. However, these methods primarily rely on spatial-domain features, while self-attention introduces high computational costs, and conventional fusion strategies (e.g., concatenation or addition) often result in weak feature correlation or boundary misalignment. To address these challenges, we propose a unified spatial-frequency modeling and multi-scale alignment fusion framework, termed USF-DETR, for small object detection. The framework comprises three key modules: the Spatial-Frequency Interaction Backbone (SFIB), the Dual Alignment and Balance Fusion FPN (DABF-FPN), and the Efficient Attention-AIFI (EA-AIFI). The SFIB integrates the Scharr operator for spatial edge and detail extraction and FFT/IFFT for capturing frequency-domain patterns, achieving a balanced fusion of global semantics and local details. The DABF-FPN employs bidirectional geometric alignment and adaptive attention to enhance the significance expression of the target area, suppress background noise, and improve feature asymmetry across scales. The EA-AIFI streamlines the Transformer attention mechanism by removing key-value interactions and encoding query relationships via linear projections, significantly boosting inference speed and contextual modeling. Experiments on the VisDrone and TinyPerson datasets demonstrate the effectiveness of USF-DETR, achieving improvements of 2.3% and 1.4% mAP over baselines, respectively, while balancing accuracy and computational efficiency. The framework outperforms state-of-the-art methods in small object detection. Full article

Partial discharge (PD) fault diagnosis is of great importance for ensuring the safe and stable operation of power transformers. To address the issues of low accuracy in traditional PD fault diagnostic methods, this paper proposes a novel method for the power transformer PD fault diagnosis. It incorporates the approximate entropy (ApEn) of symplectic geometry mode decomposition (SGMD) into the optimized bidirectional long short-term memory (BILSTM) neural network. This method extracts dominant PD features employing SGMD and ApEn. Meanwhile, it improves the diagnostic accuracy with the optimized BILSTM by introducing the golden jackal optimization (GJO). Simulation studies evaluate the performance of FFT, EMD, VMD, and SGMD. The results show that SGMD–ApEn outperforms other methods in extracting dominant PD features. Experimental results verify the effectiveness and superiority of the proposed method by comparing different traditional methods. The proposed method improves PD fault recognition accuracy and provides a diagnostic rate of 98.6%, with lower noise sensitivity. Full article

Effective control of the micro- and nanostructure of thermal barrier coatings is essential to enhance the thermal radiation performance of the coating, which helps to determine the remaining service life of the coating. This paper proposed a method to measure the radiation properties of thermal barrier coatings by terahertz nondestructive testing technique, using APS-prepared thermal barrier coatings as the object of study. Radiative properties were a comprehensive set of properties characterized by the diffuse reflectance, transmittance, and absorptance of the thermal barrier coating. The coating data in actual service were obtained by scanning electron microscopy and metallographic experiments, and the data were used as the simulation model critical value. The terahertz time-domain simulation data of coatings with different microstructural features were obtained using the finite-different time-domain (FDTD) method. In simulating the real test signals, white noise with a signal-to-noise ratio of 20 dB was added, and fast Fourier transform (FFT), short-time Fourier transform (STFT), and wavelet transform (WT) were used to reduce the noise and compare their noise reduction effects. Different machine learning methods were used to build the model, including support vector machine algorithm (SVM) and k-nearest neighbor algorithm (KNN). The principal component algorithm (PCA) was used to reduce the dimensionality of terahertz time-domain data, and the SVM algorithm and KNN algorithm were optimized using the particle swarm optimization algorithm (PSO) and the ant colony optimization algorithm (ACO), respectively, to improve the robustness of the system. The K-fold cross-validation method was used to construct the model to improve the adaptability of the model. It could be clearly seen that the novel hybrid PCA-ACO-SVM model had superior prediction performance. Finally, this work proposed a novel, convenient, nondestructive, online, safe and highly accurate method for measuring the radiation performance of thermal barrier coatings, which could be used for the judgment of the service life of thermal barrier coatings. Full article

EMU (electric multiple unit) traction motors are powered by converters whose output voltage increases the voltage stress borne by the insulation system, making the ITSC (inter-turn short-circuit) fault more prominent. An index based on short-circuit thermal power is proposed in the article to evaluate the non-metallic ITSC faults extent. The apFFT (all-phase FFT) time-shift phase difference correction with double Hanning windows is used to calculate fault features to train the SVM (support vector machine) fault diagnosis model whose hyper-parameters C and g are optimized using grid search methods. The experimental verification was carried out on the EMU electric traction simulation experimental platform. According to the fault extent index proposed in this article, the experimental samples were divided into three categories, normal, incipient and serious fault samples. The ITSC fault diagnosis accuracy was 100% on the training dataset and 93.33% on the test dataset. There was no misclassification between normal and serious ITSC fault samples. Full article

Fiber optic oxygen sensors based on fluorescence quenching play an important role in oxygen sensors. They have several advantages over other methods of oxygen sensing—they do not consume oxygen, have a short response time and are of high sensitivity. They are often used in special environments, such as hazardous environments and in vivo. In this paper, a new fiber optic oxygen sensor is introduced, which uses the all-phase fast Fourier transform (apFFT) algorithm, instead of the previous lock-in amplifier, for the phase detection of excitation light and fluorescence. The excitation and fluorescence frequency was 4 KHz, which was conducted between the oxygen-sensitive membrane and the photoelectric conversion module by the optical fiber and specially-designed optical path. The phase difference of the corresponding oxygen concentration was obtained by processing the corresponding electric signals of the excitation light and the fluorescence. At 0%, 5%, 15%, 21% and 50% oxygen concentrations, the experimental results showed that the apFFT had good linearity, precision and resolution—0.999°, 0.05° and 0.0001°, respectively—and the fiber optic oxygen sensor with apFFT had high stability. When the oxygen concentrations were 0%, 5%, 15%, 21% and 50%, the detection errors of the fiber optic oxygen sensor were 0.0447%, 0.1271%, 0.3801%, 1.3426% and 12.6316%, respectively. Therefore, the sensor that we designed has greater accuracy when measuring low oxygen concentrations, compared with high oxygen concentrations. Full article

This paper proposes an interference detection method for multiuser-multiple input multiple output (MU-MIMO) transmission, which utilizes periodical preamble signals in the frequency domain and the concept of full-duplex transmission when assuming idle antennas at the access point (AP) in MU-MIMO. In the propose method, collision detection (CD) of MU-MIMO is achieved by utilizing asynchronous MU-MIMO called random access MU-MIMO. In random access MU-MIMO, several antennas that are not used for the transmission exist, due to asynchronous MU-MIMO. Hence, idle antennas at the AP can receive preamble signals while the transmit antennas at the AP transmit the preamble signals: this procedure is regarded as full-duplex transmission, which cancels the self-interference between AP antennas. The interference can be detected by subtracting the short preamble signal, which is multiplied by the estimated channel response using the received signal after the FFT processing. Moreover, we utilize dual polarization to reduce the mutual coupling between transmit and receive antennas at the AP. Through a computer simulation, it is shown that the proposed method can successfully detect collision from other user terminals (UTs) with OFDM signals when the interfering power from the interfering user terminal (IT) is greater than the noise power. In addition, the interfering power from IT at the AP and the desired user terminal (DT) is measured in an actual indoor environment, and the possibility of using the proposed method at the AP is discussed by using the measurement results. Full article