Signal Detection Performance Research Articles

Block-term tensor decomposition in array signal processing

The ability of tensor decomposition (TD)-based methods to recover latent information, including channel parameters and transmitted symbols in the array signal processing (ASP) context, in a deterministic manner and with little or no training overhead, fits well with the data efficiency needs of future-generation multi-user massive multiple-input multiple-output systems. However, such methods have mostly relied on a few classical TD models, notably the canonical polyadic decomposition (CPD), which can be quite restrictive in realistic scenarios. In this paper, a generalized CPD model, known as block-term decomposition (BTD), is re-visited in the context of ASP, and shown to be the natural choice in sensor arrays of increased dimensionality that also involve channel multipath. Semi-blind joint channel estimation/data detection (JCD) is addressed in this context via efficient algorithms that wed existing JCD schemes with BTD approximation. Robust to sensor failures and recursive versions are also developed. The special yet important case of the uniform rectangular array (URA) configuration is adopted to illustrate the ideas and results. The signal detection performance of the BTD-inspired semi-blind JCD schemes is evaluated under various conditions with the aid of simulations and seen to be favorably compared with that of the training-only-based solution.

Virtual Array-Based Signal Detection and Carrier Frequency Offset Estimation in a Multistatic Collaborative Passive Detection System

To tackle the problem of difficult signal detection and carrier frequency synchronization faced by wireless communication among stations of the multistatic passive detection system in interference environments, an adaptive signal detection and carrier frequency offset (CFO) estimation method based on a virtual array is proposed in this paper. This is a data-aided method that utilizes a training sequence composed of three segments of sub-training sequences with different symbols. This method first uses spatial spectrum estimation to obtain the coarse frequency estimations of interference signals and CFO from virtual array signals constructed from the first two sub-training sequences. Then, beamforming is conducted accordingly on the virtual array signals constructed from the third sub-training sequence to suppress the in-band interferences and protrude the expected signal. Finally, improved performance of signal detection and CFO estimation is obtained with the beamformed signals. Simulation experiments show that a missed detection probability as low as 1 × 10−4, with a false detection probability of 1 × 10−3, can be obtained under a signal-to-interference ratio (SIR) of −10 dB and Eb/N0 of 1 dB. Moreover, the proposed method can also simultaneously achieve a CFO estimation error that is lower than 3%, with the condition of Eb/N0 being as low as −5 dB under different SIRs. Simulation results validate the proposed method and demonstrate the promising application prospects of the proposed method in networked passive detection scenarios.

Design of intelligent detection method for electricity transmission line equipment defect based on data mining algorithm

Electricity transmission line is the most significant way of power transmission. Regular detection of it can find and eliminate its defects and hidden dangers in time and prevent major accidents, which is of great significance to the power system. In order to find the problems in the electricity transmission line in time, this paper applied the data mining algorithm to the intelligent detection method of electricity transmission line equipment defects. An electricity transmission line equipment defect intelligent detection and monitoring system was constructed, and the differences between clustering analysis image recognition technology in data mining algorithms and the XGBoost algorithm were analyzed. The results showed that compared with using XGBoost algorithms, the highest accuracy rate of the intelligent detection method of electricity transmission line equipment defects using data mining algorithm in the detection results was 98 %, which was generally higher than that of XGBoost algorithms, and could reduce the consumption of time. From the perspective of replication rate, the overall average value of XGBoost algorithms was 52.38 % and the overall average value of data mining algorithms was 7.63 %. The replica rate of data mining algorithm was much lower than that of XGBoost algorithm and the performance of fault signal detection was better. Therefore, the application of data mining algorithm to the intelligent detection method of electricity transmission line equipment defects can be more suitable, thus significantly improving the efficiency of all aspects. At the same time, the method has the advantages of simple operation, fast, reliable and not affected by region.

MIMO Signal Detection Based on IM-LSTMNet Model

Signal detection is crucial in multi-input multi-output orthogonal frequency division multiplexing (MIMO-OFDM) systems, yet classical detection methods often struggle with nonlinear issues in wireless channels. To handle this challenge, we propose a novel signal detection method for MIMO-OFDM system based on the fractional Fourier transform (FrFT), leveraging the robust time series processing capabilities of long short-term memory (LSTM) networks. Our innovative approach, termed IM-LSTMNet, integrates LSTM with convolutional neural networks (CNNs) and incorporates a Squeeze and Excitation Network to emphasize critical information, enhancing neural network performance. The proposed IM-LSTMNet is applied to the FrFT-based MIMO-OFDM system to improve signal detection performance. We compare the detection results of IM-LSTMNet with zero forcing (ZF), minimum mean square error (MMSE), simple LSTM neural network, and CNN–LSTM network by evaluating the bit error rate. Experimental results demonstrate that IM-LSTMNet outperforms ZF, MMSE, LSTM, and other methods, significantly enhancing system signal detection performance. This work offers a promising advancement in MIMO-OFDM signal detection, presenting a deep learning-based solution that effectively improves the system signal detection performance.

Orthogonal double V‐linear frequency modulation waveform for simultaneous polarimetric measurement and its non‐linear processing

AbstractIt has become an interesting topic for modern radar possessing capabilities of polarimetric measurement, high‐resolution imaging, and good delay‐Doppler resolution. The linear frequency modulation (LFM) scheme is widely used in radar systems as it can achieve both high Doppler tolerance and resolution. Based on the LFM scheme, a novel waveform is proposed, namely, the orthogonal double V‐linear frequency modulation (ODV‐LFM), which exhibits the capability to mitigate the influence of delay‐Doppler coupling and reduces the risk of false targets and ghosts in multiple‐target scenes. Based on the ODV‐LFM signal, a simultaneous polarimetric measurement method is proposed to obtain fully polarimetric information of the target. According to the unique chirp rate characteristic of the ODV‐LFM signal, the pointwise linear and non‐linear processing methods are proposed to enhance delay‐Doppler resolution, suppress sidelobes, and achieve high‐resolution imaging without substantially compromising the signal detection performance. Finally, simulated experiments are conducted to demonstrate the superiority of the proposed waveform and methods.

Statistical Signal Detection Algorithm in Safety Data: A Proprietary Method Compared to Industry Standard Methods.

Several quantitative methods have been established, in pharmacovigilance, to detect signals of disproportionate reporting (SDRs) from databases containing reports of adverse drug reactions (ADRs). The signal detection algorithms (SDAs) and the source of the reporting per product vary, but it is unclear whether any algorithm can provide satisfactory performance using data with such large variance factors. Determine the appropriate SDA for Biogen's internal Global Safety Database (GSD) given the characteristics of the database including frequencies of events, data skewness, outliers, and missing information. Compare performance of standard approaches (EBGM, EB05, PRR, and ROR), well accepted by industry, to a Biogen-developed Machine Learning (ML) Regression Decision Tree (RDT) model, across several Biogen products, to determine a champion SDA. All data associated with seven marketed Biogen products were chosen and a historical subset of reported ADRs were considered. Six SDAs (five common industry disproportionality methods) and RDT were evaluated. The SDRs were calculated on training and test data composed of quarterly reporting intervals from 2004-2019. The performance measures used were sensitivity, precision, time to detect new events, and frequency of detected cases for each algorithm for each product. Outcomes in the test data are known a priori and easily compared to predicted outcomes. Validation was performed via rates of misclassification. This work solely represents Biogen's internal information, intentionally chosen to serve the performance review of its signal detection systems, and results will not necessarily be generalizable to other external sources. Several algorithms performed differently among products, but no one method dominated any other. Performance was dependent on the thresholds used to define a signal according to different criteria. However, those different statistics subtly influenced the achievable performance. The relative performance of RDT and Medicines and Healthcare products Regulatory Agency (MHRA) algorithms were superior and paired across products. A reduction in precision for all methods spanning the products was present. Hence, companies evaluating signal detection approaches, search for innovative methods to minimize this effect. In designing signal detection systems, careful consideration should be given to the criteria that are used to define SDRs. The choice of disproportionality statistics does not affect the achievable range of signal detection performance. These choices should consider mainly ease of implementation and interpretation. The implementation of a method is specific to its accuracy. The RDT attempted to take advantage of known methods and compare results on a per-product basis. Many factors influencing ADRs may improve RDT in future efforts. In this experiment, RDT demonstrated superiority in terms of quickest time to detect and capturing of the highest number of ADRs. Next steps include expansion of data for products representing other indications and testing models in external databases to investigate generalizability of estimates when comparing SDAs.

Weighted Dual-Channel Model for Arrhythmia Detection using Single Electrocardiogram Signal

The single-lead method plays a central role in arrhythmia warning, and its anomaly detection is of practical significance for the prevention of heart diseases. However, the detection performance is often limited due to the limited information content of single-lead electrocardiogram (ECG) signals. To address this issue, this paper proposes a weighted dualchannel arrhythmia classification model aimed at improving the detection performance of single-lead ECG signals. The model employs a parallel structure of CNN-LSTM and Transformer to capture both local and global features of the ECG signals. By applying weighted learning to the features from the two channels, the model achieves precise arrhythmia classification. Additionally, to alleviate the class imbalance problem, a weighted cross-entropy loss function is introduced, further enhancing the classification performance. Experimental results based on the MIT-BIH arrhythmia database demonstrate that the proposed model exhibits excellent performance in terms of overall accuracy, F1 score, and sensitivity, achieving 99.33%, 94.71%, and 99.33%, respectively. Compared with existing classification models, the proposed model shows superior classification performance and significant practical value, providing solid technical support for the auxiliary diagnosis of arrhythmias and bringing new possibilities for actual clinical applications.

High-Porosity Sieve-Type Neural Electrodes for Motor Function Recovery and Nerve Signal Acquisition.

In this study, the effects of electrode porosity on nerve regeneration and functional recovery after sciatic nerve transection in rats was investigated. A sieve-type neural electrode with 70% porosity was designed and compared with an electrode with 30% porosity. Electrodes were fabricated from photosensitive polyimide and implanted into the transected sciatic nerves. Motor function recovery was evaluated using the Sciatic Function Index. The number of active channels and their signal quality were recorded and analyzed to assess the sensory neural signal acquisition. Electrical impedance spectroscopy was used to evaluate the electrode performance. The group implanted with the 70% porosity electrode demonstrated significantly enhanced nerve regeneration and motor function recovery, approaching control group levels by the fifth week. In contrast, the group with the 30% porosity electrode exhibited limited improvement. Immunohistochemical analysis confirmed extensive nerve fiber growth within the 70% porous structure. Moreover, the 70% porosity electrode consistently acquired neural signals from more channels compared to the 30% porosity electrode, demonstrating its superior performance in sensory signal detection. These findings emphasize the importance of optimizing electrode porosity in the development of advanced neural interfaces, with the potential to enhance clinical outcomes in peripheral nerve repair and neuroprosthetic applications.

Co-Frequency Interference Suppression of Integrated Detection and Jamming System Based on 2D Sparse Recovery

The integrated detection and jamming system employs integrated signals devoid of typical radar signal characteristics for detection and jamming. This allows for the sharing of resources such as waveform, frequency, time, and aperture, significantly enhancing the overall utilization rate of system resources. However, to achieve effective interference, the integrated waveform must overlap with the adversary radar signal within the frequency band. Consequently, the detection echoes are susceptible to the strong co-frequency direct wave generated by the adversary signals. This paper proposes a co-frequency direct wave interference suppression algorithm based on 2D generalized smoothed-l0 norm sparse recovery. The algorithm exploits a joint dictionary comprising our integrated signals and adversary signals, along with the sparsity of 2D range-Doppler maps. The direct solution of the sparse decomposition optimization problem, formulated for the entire echo matrix, enhances the target detection performance for integrated signals even in the presence of robust co-frequency direct wave interference. Furthermore, the proposed method achieves robustness to interference of varying intensities through the adaptive updating and adjustment of relevant parameters. The effectiveness of the proposed method is validated through simulation and experimental results.

Epilepsy detection based on multi-head self-attention mechanism.

CNN has demonstrated remarkable performance in EEG signal detection, yet it still faces limitations in terms of global perception. Additionally, due to individual differences in EEG signals, the generalization ability of epilepsy detection models is week. To address this issue, this paper presents a cross-patient epilepsy detection method utilizing a multi-head self-attention mechanism. This method first utilizes Short-Time Fourier Transform (STFT) to transform the original EEG signals into time-frequency features, then models local information using Convolutional Neural Network (CNN), subsequently captures global dependency relationships between features using the multi-head self-attention mechanism of Transformer, and finally performs epilepsy detection using these features. Meanwhile, this model employs a light multi-head attention mechanism module with an alternating structure, which can comprehensively extract multi-scale features while significantly reducing computational costs. Experimental results on the CHB-MIT dataset show that the proposed model achieves accuracy, sensitivity, specificity, F1 score, and AUC of 92.89%, 96.17%, 92.99%, 94.41%, and 96.77%, respectively. Compared to the existing methods, the method proposed in this paper obtains better performance along with better generalization.

Physics-inspired spatiotemporal-graph AI ensemble for the detection of higher order wave mode signals of spinning binary black hole mergers

We present a new class of AI models for the detection of quasi-circular, spinning, non-precessing binary black hole mergers whose waveforms include the higher order gravitational wave modes (ℓ,|m|)={(2,2),(2,1),(3,3),(3,2),(4,4)} , and mode mixing effects in the ℓ=3,|m|=2 harmonics. These AI models combine hybrid dilated convolution neural networks to accurately model both short- and long-range temporal sequential information of gravitational waves; and graph neural networks to capture spatial correlations among gravitational wave observatories to consistently describe and identify the presence of a signal in a three detector network encompassing the Advanced LIGO and Virgo detectors. We first trained these spatiotemporal-graph AI models using synthetic noise, using 1.2 million modeled waveforms to densely sample this signal manifold, within 1.7 h using 256 NVIDIA A100 GPUs in the Polaris supercomputer at the Argonne Leadership Computing Facility. This distributed training approach exhibited optimal classification performance, and strong scaling up to 512 NVIDIA A100 GPUs. With these AI ensembles we processed data from a three detector network, and found that an ensemble of 4 AI models achieves state-of-the-art performance for signal detection, and reports two misclassifications for every decade of searched data. We distributed AI inference over 128 GPUs in the Polaris supercomputer and 128 nodes in the Theta supercomputer, and completed the processing of a decade of gravitational wave data from a three detector network within 3.5 h. Finally, we fine-tuned these AI ensembles to process the entire month of February 2020, which is part of the O3b LIGO/Virgo observation run, and found 6 gravitational waves, concurrently identified in Advanced LIGO and Advanced Virgo data, and zero false positives. This analysis was completed in one hour using one NVIDIA A100 GPU.

Assessment of plasma cell-free DNA fragmentation for multi-cancer early detection: An independent clinical validation study.

e15037 Background: Cell-free DNA (cfDNA) in the circulation has gained significant attention due to its potential applications for non-invasive early cancer detection. Fragmentomics of cfDNA is emerging as a promising field of biomarker research, exhibiting the capability to sensitively detect multiple cancer types. In previous retrospective research, we developed an approach called PatternWGS for comprehensive analysis of cfDNA fragmentation patterns and presented a multi-cancer detection model. In this study, we aim to evaluate the performance of PatternWGS in an independent validation cohort including lung, breast, colorectal, liver, and gastric cancers from a new clinical center. Methods: Participants with confirmed diagnosis of lung, breast, colorectal or liver cancer were enrolled in the cancer group. Non-cancer participants without known presence of malignancies were recruited from the same clinical center. Plasma samples from patients with lung (n=47), breast (n=19), colorectal (n=14), liver (n=8) and gastric (n=6) cancers, along with 101 non-cancer individuals were collected in this study. cfDNA was isolated from plasma and stored within a month prior to the whole genome sequencing. The characteristics of cfDNA fragmentation integrating fragment size profiles, motif patterns, genomic coverage distributions were utilized to evaluate the performance for cancer signal detection. In addition, the performance of estimated cfDNA tumor fraction, using copy number aberrations (ichorCNA), was compared with our approach. Results: 94 patients with one of five types of cancers and 101 non-cancer controls were prospectively enrolled between July 2023 and November 2023. Among the cancer group, 64% were at early stages (Stage I: 48%, Stage II: 16%). A significantly higher proportion of shorter fragments was observed in cancer group, and the degree increased with increasing cancer stage. Overall sensitivity across cancer types and stages was 72.3%, and the specificity for non-cancer controls was 80%. As expected, the sensitivity of cancer detection is higher in late-stage patients compared to those in the early-stages (61% in stage I, 80% in stage II, 84.6% in stage III, and 91.7% in stage IV). The sensitivity of detecting lung (72% had stage I cancer), breast, colorectal, liver, and gastric cancers reached 57.4%, 84.2%, 85.7%, 87.5% and 100% respectively. The detection performance using cfDNA tumor fraction by ichorCNA demonstrated a relatively low overall sensitivity of 28.7% (24.6% for stage I-II, 44% for stage III-IV). Conclusions: This independent clinical validation study, which focused on exploring plasma cfDNA fragmentation, demonstrated ideal performance in early-stage cancer detection. The cfDNA fragmentation-based approach exhibited a superior sensitivity in detecting early cancer signals compared with copy number aberrations-based approach.

An Advanced Scheme for Radar Clutter Suppression Scheme Based on Blind Source Separation

In cluttered electromagnetic environments, radar is often disturbed by varied clutter, making target detection challenging. Therefore, achieving effective clutter suppression is crucial for radar target detection. However, traditional clutter suppression methods face three key challenges: (1) significant degradation in target signal detection performance when the clutter’s Doppler spectrum completely masks the target signal; (2) heavy reliance on prior knowledge for optimal performance; and (3) inherent signal energy loss during clutter suppression. To address these challenges, we propose a clutter suppression scheme based on blind source separation (BSS). Initially, the scheme utilizes parallel principal skewness analysis (PPSA) to process the echo signals in the range domain, which helps in identifying the position of moving targets. Subsequently, PPSA is applied once more to process the moving targets in the Doppler domain, allowing for the precise determination of their relative velocities. Subsequently, we evaluate the scheme’s performance with simulated and real data, comparing it with traditional clutter suppression methods and other BSS techniques. The results confirm the effectiveness of the scheme in clutter suppression.

Research on an Alpha Navigation Signal Detection Method Based on Multichannel Orthogonal Correlation

The Alpha navigation system is the only operating radio system based on very-low-frequency (VLF) signals that can be used to research VLF navigation, timing, and ionospheric characteristics. The detection of the Alpha navigation signal is the key step in the Alpha receiver; however, the received Alpha navigation signal is susceptible to noise and mutual interference, which deteriorates signal detection performance. This paper presents a multichannel orthogonal correlation method for Alpha navigation signal detection. Once the three frequency signals of the Alpha navigation system are obtained using a notch filter, station identification is realized using a multichannel orthogonal correlation method and signal format. The selection of key parameters and the detection performance under noise and mutual interference are analyzed. This method’s detection probability exceeds 90% when the signal-to-noise ratio (SNR) is greater than −10 dB. The influence of mutual interference on the signal correlation peak is less than 1% when the signal-to-interference ratio (SIR) of the mutual interference is greater than −28 dB. The proposed method is verified using an actual signal collected using an Alpha receiver. The results show that an Alpha signal can be detected at an extremely low SNR. This method has strong practicability and satisfies the application requirements of an Alpha receiver.

An integrated waveform design method for underwater acoustic detection and communication

AbstractIn recent years, the integrated system for underwater detection and communication (ISUDC) has become one of the important research directions. At present, the efficiency of the existing shared signals carrying communication information is low, and the synchronization performance needs to be further improved. So, this paper proposes an integrated waveform design scheme for ISUDC based on the carrier with good detection performance and binary phase shift differential keying (DBPSK). In this scheme, the signal with better underwater detection performance (e.g. Linear Frequency Modulation, LFM) is selected as the carrier, and DBPSK is used as the modulation mode to modulate the communication symbols into the carrier. However, the correlation of the detection signal will be destroyed. Thus, the down‐frequency detection signal (e.g. ngLFM) is superimposed into the signal to form a shared signal (LFM‐DBPSK‐ng, LDN). The detection performance, synchronization performance and communication performance of the shared signal are analyzed by ambiguity function, cross‐correlation and BER, respectively. In addition, according to the proposed scheme, the shared signal HFM‐DBPSK‐ng (HDN) is generated by using HFM as carrier. The comparative simulation experiments are carried out with the existing LFM‐BPSK signals. Experiments show that both LDN and HDN have better performance compared to the other shared signals, which proves the effectiveness of the integrated waveform design scheme for ISUDC proposed in this paper.

Machine learning classifiers for signal detection in ambient backscatter communication under time-selective fading

In the world of the Internet of Things (IoT), ambient backscatter communication, or AmBaC, is a cutting-edge technology that has attracted a lot of interest. It meets the requirement for low-power communication in IoT devices, which are often located in a multitude of settings and scenarios where power efficiency is essential. In the literature, most signal detection is carried out using an energy detector or Minimum Mean Square Error (MMSE) detector under static conditions. In this work, we perform signal detection using multiple supervised machine learning (ML) classifiers, namely random forest, K-nearest neighbors (KNN), and support vector machine (SVM), and we examine the system performance in terms of bit error rate (BER) for both stationary and moving radio-frequency (RF) source. The simulation findings demonstrate that the proposed supervised ML classifiers surpass the conventional signal detector. In particular, the performance of the SVM classifier is best among all the other ML classifiers. Additionally, we examined the performance of different kernels of the SVM classifier and discovered that the Gaussian kernel offers the highest performance when it comes to SVM classifier performance.

Comparison of sparse arrays that maximize detection and optimize beampatterns

In a standard uniform linear array (ULA), the sensors are uniformly spaced on a grid with half wavelength intersensor spacing. The beampattern of an array shows the gain applied by the conventional beamformer to a plane wave arriving at the array from various possible directions. The main lobe width, peak side lobe height, and the side lobe area are important beampattern parameters. Many sparse arrays have been widely studied because of their ability to provide one or more of the same beampattern parameters as a full array using fewer sensors. Examples of such arrays are coprime [Vaidyanathand and Pal 2011] and nested [Pal and Vaidyanathan 2010] arrays. Recently, an exact way to design sparse sampling schemes to maximize detection performance of a known signal in first-order autoregressive noise was introduced [Adhikari and Kay 2023]. In this research, we compare the beampatterns and detection performances of these detection maximizing arrays with the sparse arrays that are designed to optimize beampattern metrics. We analyze beampatterns and detection performances under various conditions using simulated and real underwater acoustic data.

Matched Filter for Acoustic Emission Monitoring in Noisy Environments: Application to Wire Break Detection

Regular inspections of important civil infrastructures are mandatory to ensure structural safety and reliability. Until today, these inspections are primarily conducted manually, which has several deficiencies. In context of prestressed concrete structures, steel tendons can be susceptible to stress corrosion cracking, which may result in breakage of individual wires that is visually not observable. Recent research therefore suggests Acoustic Emission Monitoring for wire break detection in prestressed concrete structures. However, in noisy environments, such as wind turbines, conventional acoustic emission detection based on user-defined amplitude thresholds may not be suitable. Thus, we propose the use of matched filters for acoustic emission detection in noisy environments and apply the proposed method to the task of wire break detection in post-tensioned wind turbine towers. Based on manually conducted wire breaks and rebound hammer tests on a large-scale test frame, we employ a brute-force search for the most suitable query signal of a wire break event and a rebound hammer impact, respectively. Then, we evaluate the signal detection performance on more than 500 other wire break signals and approximately one week of continuous acoustic emission recordings in an operating wind turbine. For a signal-to-noise ratio of 0 dB, the matched filter approach shows an improvement in AUC by up to 0.78 for both, the wire break and the rebound hammer query signal, compared to state-of-the-art amplitude-based detection. Even for the unscaled wire break measurements originally recorded at the 12 m large laboratory test frame, the improvement in AUC still lies between 0.01 and 0.25 depending on the wind turbine noise recordings considered for evaluation. Matched filters may therefore be a promising alternative to amplitude-based detection algorithms and deserve particular consideration with regard to Acoustic Emission Monitoring, especially in noisy environments or when sparse senor networks are required.

ZPW-2000 frequency-shift signal detection algorithm based on nonlinear least squares method

Aiming at the problems of spectrum leakage, difficulty in guaranteeing demodulation accuracy, and endangering driving safety in signal detection algorithm based on periodogram with limited sampling duration, this paper proposes for the first time a kind of ZPW-20000 frequency-shift signal detection algorithm based on nonlinear least squares, so as to improve the detection performance of ZPW-2000 frequency-shift signal, to ensure the safe operation of trains, and to improve the operational efficiency. The mathematical model of ZPW-2000 frequency-shift signal is established, the Cramér-Rao bound (CRB) for carrier-frequency and low-frequency estimation are derived, and a nonlinear least squares algorithm containing three processes, namely, the coarse estimation, the grid search based on Fast Fourier Transform (FFT), and the exact search, is designed, which is applied to the detection of ZPW-2000 frequency-shift signal. The research results show that the accuracy of carrier-frequency and low-frequency estimation of the proposed algorithm is better than that of the periodogram method for different sampling durations, and the number of decoding errors of the proposed algorithm and the periodogram method is reduced to zero when the sampling durations are greater than or equal to 0.11 s and 0.19 s, respectively, and the proposed algorithm reduces the limitation on the sampling durations. As the signal-to-noise ratio (SNR) increases, the root mean square error (RMSE) of carrier-frequency and low-frequency estimation of the proposed algorithm can approach the CRB. when the SNR of −2 dB, the number of decoding errors of the proposed algorithm is reduced to zero, while the periodogram method requires the SNR of 2 dB to achieve the same effect. The proposed algorithm performs well in detection accuracy, real-time and anti-interference ability, which is of great significance for ensuring driving safety and improving the reliability of the vehicle-ground communication mode based on ZPW-2000 track circuit.

Underwater object detection and temporal signal detection in turbid water using 3D-integral imaging and deep learning.

Underwater scattering caused by suspended particles in the water severely degrades signal detection performance and poses significant challenges to the problem of object detection. This paper introduces an integrated dual-function deep learning-based underwater object detection and classification and temporal signal detection algorithm using three-dimensional (3D) integral imaging (InIm) under degraded conditions. The proposed system is an efficient object classification and temporal signal detection system for degraded environments such as turbidity and partial occlusion and also provides the object range in the scene. A camera array captures the underwater objects in the scene and the temporally encoded binary signals transmitted for the purpose of communication. The network is trained using a clear underwater scene without occlusion, whereas test data is collected in turbid water with partial occlusion. Reconstructed 3D data is the input to a You Look Only Once (YOLOv4) neural network for object detection and a convolutional neural network-based bidirectional long short-term memory network (CNN-BiLSTM) is used for temporal optical signal detection. Finally, the transmitted signal is decoded. In our experiments, 3D InIm provides better image reconstruction in a degraded environment over 2D sensing-based methods. Also, reconstructed 3D images segment out the object of interest from occlusions and background which improves the detection accuracy of the network with 3D InIm. To the best of our knowledge, this is the first report that combines deep learning with 3D InIm for simultaneous and integrated underwater object detection and optical signal detection in degraded environments.