Detection of Frequency-Hopping Signals With Deep Learning

In order to solve the problem of low detection rate of frequency hopping (FH) signal under low SNR, an FH signal detection technology based on deep neural network (vgg16 network) is proposed. Firstly, this paper introduces the principle of FH signal. Then, this paper presents the SSD deep neural network detection framework, and uses this framework to detect FH signal and estimate its parameters. Time-frequency distribution maps of FH signals are used as the input of deep neural network model to carry out tag learning and training, and then the trained model is used to realise FH signal detection. At the same time, aiming at the noise problem of time-frequency distribution map, the time-frequency graph correction method of K-means clustering algorithm is proposed. After modification, it is more tolerant to noise. The simulation results show that when the SNR is –4 dB, the detection rate of FH signal can reach more than 88%. Finally, the performance of parameter estimation of FH signal is analysed.

Frequency hopping (FH) signal is widely adopted by military communications as a kind of low probability interception signal. Therefore, it is very important to research the FH signal detection algorithm. The existing detection algorithm of FH signals based on the time-frequency analysis cannot satisfy the time and frequency resolution requirement at the same time due to the influence of window function. In order to solve this problem, an algorithm based on wavelet decomposition and Hilbert–Huang transform (HHT) was proposed. The proposed algorithm removes the noise of the received signals by wavelet decomposition and detects the FH signals by Hilbert–Huang transform. Simulation results show the proposed algorithm takes into account both the time resolution and the frequency resolution. Correspondingly, the accuracy of FH signals detection can be improved.

Deep learning (also known as deep structured learning, hierarchical learning, or deep machine learning) is a branch of machine learning based on a set of algorithms that attempt to model high-level abstractions in data by using a deep graph with multiple processing layers, composed of multiple linear and nonlinear transformations. Deep learning has been characterized as a class of machine learning algorithms with the following characteristics [257]: • They use a cascade of many layers of nonlinear processing units for feature extraction and transformation. Each successive layer uses the output from the previous layer as input. The algorithms may be supervised or unsupervised and applications include pattern analysis (unsupervised) and classification (supervised). • They are based on the (unsupervised) learning of multiple levels of features or representations of the data. Higher-level features are derived from lower-level features to form a hierarchical representation. • They are part of the broader machine learning field of learning representations of data. • They learn multiple levels of representations that correspond to different levels of abstraction; the levels form a hierarchy of concepts. These definitions have in common: multiple layers of nonlinear processing units and the supervised or unsupervised learning of feature representations in each layer, with the layers forming a hierarchy from low-level to high-level features. Various deep learning architectures such as deep neural networks, convolutional deep neural networks, deep belief networks (DBN), and recurrent neural networks have been applied to fields like computer vision, automatic speech recognition, natural language processing, audio recognition, and bioinformatics where they have been shown to produce state-of-the-art results on various tasks. In this chapter we start in Section 7.1 with an introduction, giving a brief history of this field, the relevant literature, and its applications. Then we study some basic concepts of deep learning such as convolutional neural networks, recurrent neural networks, backpropagation algorithm, restricted Boltzmann machines, and deep learning networks in Section 7.2. Then we illustrate three examples for Apache Spark implementation for mobile big data (MBD), user moving pattern extraction, and combination with nonparametric Bayesian learning, respectively, in Sections 7.3 through 7.5. Finally, we have summary in Section 7.6.

In differential frequency hopping (FH) wireless systems, data are expressed by frequency hopping pattern, and frequency detection involving the Fourier transform and widebands requires large numbers of Nyquist samples, which makes them difficult to implement. Due to the sparseness of FH signals in the frequency domain, compressive sampling (CS) techniques have been explored for the sampling and reconstruction of such signals. In CS, the number of measurements must satisfy $$M\ge {C}\cdot {\mu }^2(\varvec{\varPhi },\varvec{\varPsi })\cdot {K}\cdot {}log(N)$$M?C·μ2(?,?)·K·log(N), where $$C$$C and $$\mu (\varvec{\varPhi },\varvec{\varPsi })$$μ(?,?) are the constants, $$K$$K is the sparsity level, and $$N$$N is the dimension of the original signal. Because of the large number of channels in the operation band, many of these channels are often occupied by diverse frequency-fixed (FF) signals. For this reason, the band compression rate (BCR $$=N/M$$=N/M) may be greatly reduced. However, the FH signals only occupy a single frequency at a time. This means that $$K=1$$K=1, and the number of measurements can be far smaller than the number to restore the mixture of FH and FF signals. In this paper, a CS method that is not subject to the influence is presented, and the BCR can reach 1,000:6 when the FH signal is mixed with 50 interferences. The proposed algorithm covers the generation of the sampling matrix and signal reconstruction. Specifically, it maximizes the signal-to-noise ratio of the compressed signal with a white noise background. The new reconstruction algorithm was found to be 5 times faster than the OMP algorithm in the case of that $$K=4$$K=4, and it is not limited by the inequality given above.

The goal of multi-modal learning is to use complementary information on the relevant task provided by the multiple modalities to achieve reliable and robust performance. Recently, deep learning has led significant improvement in multi-modal learning by allowing for fusing high level features obtained at intermediate layers of the deep neural network. This paper addresses a problem of designing robust deep multi-modal learning architecture in the presence of the modalities degraded in quality. We introduce deep fusion architecture for object detection which processes each modality using the separate convolutional neural network (CNN) and constructs the joint feature maps by combining the intermediate features obtained by the CNNs. In order to facilitate the robustness to the degraded modalities, we employ the gated information fusion (GIF) network which weights the contribution from each modality according to the input feature maps to be fused. The combining weights are determined by applying the convolutional layers followed by the sigmoid function to the concatenated intermediate feature maps. The whole network including the CNN backbone and GIF is trained in an end-to-end fashion. Our experiments show that the proposed GIF network offers the additional architectural flexibility to achieve the robust performance in handling some degraded modalities.

1 - Congruence of deep learning in biomedical engineering: future prospects and challenges

Frequency hopping (FH) signal has been widely used in military and civilian fields because of its superior anti-jamming performance. Meanwhile, its natural characteristics, i.e., hopped carrier frequency, brings a great challenge to the reconnaissance of FH emitters. To locate a high-speed moving FH emitter, the estimation of range difference (RD) and range rate difference (RRD) is a key process in passive localization. This paper proposes a joint RD and RRD estimation algorithm with the consideration of range migration (RM) during observation time. In this method, a new operation named frequency reversing transform is first presented to remove the random phase of the FH signal. Then, RD and RRD can be coherently estimated after RM correction via the scaled Fourier transform. This method accomplishes the RD and RRD estimation without knowing the hopped carrier frequencies of received FH signals, and it can be fast implemented by complex multiplications, fast Fourier transform (FFT) and inverse FFT operations without any searching process. Numerical experiments indicate that compared with several representative methods, the proposed estimation method achieves a better anti-noise performance with lower computational cost.

[ACCESS RESTRICTED TO THE UNIVERSITY OF MISSOURI AT REQUEST OF AUTHOR.] Camera traps are a popular tool to sample animal populations because they are noninvasive, detect a variety of species, and can record many thousands of animal detections per deployment. Cameras are typically set to take bursts of multiple images for each detection, and are deployed in arrays of dozens or hundreds of sites, often resulting in millions of images per study. The task of converting images to animal detection records from such large image collections is daunting, and made worse by situations that generate copious empty pictures from false triggers (e.g. camera malfunction or moving vegetation) or pictures of humans. We offer the first widely available computer vision tool for processing camera trap images. Our results show that the tool is accurate and results in substantial time savings for processing large image datasets, thus improving our ability to monitor wildlife across large scales with camera traps. In this dissertation, we have developed new image/video processing and computer vision algorithms for efficient and accurate object detection and sequence-level classiffication from natural scene camera-trap images. This work addresses the following five major tasks: (1) Human-animal detection. We develop a fast and accurate scheme for human-animal detection from highly cluttered camera-trap images using joint background modeling and deep learning classification. Specifically, first, We develop an effective background modeling and subtraction scheme to generate region proposals for the foreground objects. We then develop a cross-frame image patch verification to reduce the number of foreground object proposals. Finally, We perform complexity-accuracy analysis of deep convolutional neural networks (DCNN) to develop a fast deep learning classification scheme to classify these region proposals into three categories: human, animals, and background patches. The optimized DCNN is able to maintain high level of accuracy while reducing the computational complexity by 14 times. Our experimental results demonstrate that the proposed method outperforms existing methods on the camera-trap dataset. (2) Object segmentation from natural scene. We first design and train a fast DCNN for animal-human-background object classification, which is used to analyze the input image to generate multi-layer feature maps, representing the responses of different image regions to the animal-human-background classifier. From these feature maps, we construct the so-called deep objectness graph for accurate animal-human object segmentation with graph cut. The segmented object regions from each image in the sequence are then verfied and fused in the temporal domain using background modeling. Our experimental results demonstrate that our proposed method outperforms existing state-of-the-art methods on the camera-trap dataset with highly cluttered natural scenes. (3) DCNN domain background modeling. We replaced the background model with a new more efficient deep learning based model. The input frames are segmented into regions through the deep objectness graph then the region boundaries of the input frames are multiplied by each other to obtain the regions of movement patches. We construct the background representation using the temporal information of the co-located patches. We propose to fuse the subtraction and foreground/background pixel classiffcation of two representation : a) chromaticity and b) deep pixel information. (4) Sequence-level object classiffcation. We proposed a new method for sequence-level video recognition with application to animal species recognition from camera trap images. First, using background modeling and cross-frame patch verification, we developed a scheme to generate candidate object regions or object proposals in the spatiotemporal domain. Second, we develop a dynamic programming optimization approach to identify the best temporal subset of object proposals. Third, we aggregate and fuse the features of these selected object proposals for efficient sequence-level animal species classification.

.Significance: Automatic and accurate classification of three-dimensional (3-D) retinal optical coherence tomography (OCT) images is essential for assisting ophthalmologist in the diagnosis and grading of macular diseases. Therefore, more effective OCT volume classification for automatic recognition of macular diseases is needed.Aim: For OCT volumes in which only OCT volume-level labels are known, OCT volume classifiers based on its global feature and deep learning are designed, validated, and compared with other methods.Approach: We present a general framework to classify OCT volume for automatic recognizing macular diseases. The architecture of the framework consists of three modules: B-scan feature extractor, two-dimensional (2-D) feature map generation, and volume-level classifier. Our architecture could address OCT volume classification using two 2-D image machine learning classification algorithms. Specifically, a convolutional neural network (CNN) model is trained and used as a B-scan feature extractor to construct a 2-D feature map of an OCT volume and volume-level classifiers such as support vector machine and CNN with/without attention mechanism for 2-D feature maps are described.Results: Our proposed methods are validated on the publicly available Duke dataset, which consists of 269 intermediate age-related macular degeneration (AMD) volumes and 115 normal volumes. Fivefold cross-validation was done, and average accuracy, sensitivity, and specificity of 98.17%, 99.26%, and 95.65%, respectively, are achieved. The experiments show that our methods outperform the state-of-the-art methods. Our methods are also validated on our private clinical OCT volume dataset, consisting of 448 AMD volumes and 462 diabetic macular edema volumes.Conclusions: We present a general framework of OCT volume classification based on its 2-D feature map and CNN with attention mechanism and describe its implementation schemes. Our proposed methods could classify OCT volumes automatically and effectively with high accuracy, and they are a potential practical tool for screening of ophthalmic diseases from OCT volume.

Deep learning (DL) has shown explosive growth in its application to bioinformatics and has demonstrated thrillingly promising power to mine the complex relationship hidden in large-scale biological and biomedical data. A number of comprehensive reviews have been published on such applications, ranging from high-level reviews with future perspectives to those mainly serving as tutorials. These reviews have provided an excellent introduction to and guideline for applications of DL in bioinformatics, covering multiple types of machine learning (ML) problems, different DL architectures, and ranges of biological/biomedical problems. However, most of these reviews have focused on previous research, whereas current trends in the principled DL field and perspectives on their future developments and potential new applications to biology and biomedicine are still scarce. We will focus on modern DL, the ongoing trends and future directions of the principled DL field, and postulate new and major applications in bioinformatics.

Channelized intercept receivers with fast Fourier transform (FFT) front-end preprocessors are often used to detect frequency-hopped (FH) signals. Ideally, the FFT frequency band should coincide with the entire FH spread-spectrum bandwidth. However, in some practical implementations, hardware and/or real-time computational signal processing capabilities limit the FFT to a fraction of the total band of interest. In this case, the preprocessor will only intercept some of the received hops, but the FH signal can still be successfully detected assuming that enough hops are observed. If the receiver front end is tunable, an alternative approach is to step the FFT band within each hop such that more or all of the FH signal bandwidth is covered. The tradeoff is that more of the hops will be intercepted but the receiver will detect only part of each hop. This paper analyzes this partial-band FH detection scheme and determines the optimum performance strategy. >

Deep Learning and Beyond: AI’s New Horizons” is an expansive monograph that delves into the dynamic and rapidly evolving field of deep learning, a key area of artificial intelligence. This comprehensive work provides an insightful exploration of the revolutionary developments, foundational concepts, and future directions of deep learning, positioning itself as a crucial resource for understanding this transformative technology. The monograph commences with an introductory chapter that lays the groundwork by elucidating the background of machine learning and chronicling the ascent of deep learning. This foundational perspective is vital for comprehending the underlying principles and methodologies that have propelled deep learning to the forefront of technological innovation. Subsequent chapters delve into the “Historical Evolution” of AI, tracing the origins of neural networks from their early inception to the Renaissance period of deep learning. This historical analysis is pivotal in understanding the field’s trajectory and significant milestones. The “Foundations of Deep Learning” chapter presents an in-depth analysis of neural networks, covering their basic architecture, activation functions, layers, and the critical process of backpropagation and gradient descent. This is followed by examining “Advanced Neural Network Architectures,” where the focus shifts to state-of-the-art models such as convolutional neural networks, recurrent neural networks, and groundbreaking transformers and attention mechanisms. In addressing the “Training Deep Models,” the monograph explores regularization techniques, optimization strategies, and the increasingly significant role of transfer learning and pre-trained models. The application-oriented chapter, “Applications of Deep Learning,” showcases real-world implementations in domains like image recognition, natural language viii processing, and autonomous systems, illustrating deep learning technologies’ vast potential and versatility. The monograph also tackles the “Challenges in Deep Learning,” including overfitting, interpretability, and the ethical considerations surrounding AI deployment. It then ventures into the “Future of Deep Learning,” contemplating emerging trends such as integrating quantum computing, neural architecture search, and the convergence of neuroscience and deep learning. “Case Studies” provide practical insights and empirical evidence of the impact of deep learning. At the same time, the concluding chapter synthesizes the current state of deep learning, offers predictions for the future, and provides reflective thoughts on this transformative field. “Deep Learning and Beyond: AI’s New Horizons” educates and informs readers about the vast potential and future possibilities of deep learning and artificial intelligence. Keywords: Deep Learning, Artificial Intelligence, Neural Networks, Machine Learning, Convolutional Neural Networks, Recurrent Neural Networks, Transformers, Quantum Computing, Ethical AI, Neural Architecture Search, Natural Language Processing, Autonomous Systems, AI in Healthcare, Future of AI, AI Applications, AI Challenges.

In deep learning, convolutional neural networks (CNNs) are a class of artificial neural networks (ANNs), most commonly applied to analyze visual imagery. They are also known as Shift-Invariant or Space-Invariant Artificial Neural Networks (SIANNs), based on the shared-weight architecture of the convolution kernels or filters that slide along input features and provide translation-equivariant responses known as feature maps. Recently, various architectures for CNN based on FPGA platform have been proposed because it has the advantages of high performance and fast development cycle. However, some key issues including how to optimize the performance of CNN layers with different structures, high-performance heterogeneous accelerator design, and how to reduce the neural network framework integration overhead need to be improved. To overcome and improve these problems, we propose dynamic cycle pipeline tiling, data layout optimization, and a pipelined software and hardware (SW–HW)-integrated architecture with flexibility and integration. Some benchmarks have been tested and implemented on the FPGA board for the proposed architecture. The proposed dynamic tiling and data layout transformation improved by 2.3 times in the performance. Moreover, with two-level pipelining, we achieve up to five times speedup and the proposed system is 3.8 times more energy-efficient than the GPU.

Long-time coherent integration using frequency hopping signals is a challenging problem for passive bistatic radar due to its frequency hopping characteristics. Apart from range walk, range curve, and Doppler frequency migration, Doppler diffusion caused by frequency hopping characteristics occurs within the observation time, which also lowers the detection performance. To deal with this problem, a novel coherent integration method for frequency hopping signals based on passive bistatic radar is proposed in this paper. In this novel method, range curve and range walk are eliminated by applying generalized Keystone transform. Then, Doppler frequency migration caused by the target's acceleration is compensated for by a parameter search with a designed search scope. Finally, Doppler frequency migration caused by frequency hopping characteristics is compensated for by designing a new acceleration compensation function and a revised rotation factor for Fourier transform. Since migration effects caused by frequency hopping characteristics are considered and compensated for when using frequency hopping signals, the weak target echo can be better integrated in the observation time compared to when using the existing methods. The simulation results and performance analysis illustrate the effectiveness of the proposed method.

Deep learning has been successfully deployed to a broad range of applications with its outstanding performance. Supporting an efficient hardware architecture is critical to making effective use of a deep learning approach with proven algorithm performance. One challenge in implementation of deep learning algorithm is to reduce memory bandwidth because a single memory access normally consumes 100* more energy than an arithmetic operation. To reduce the memory bandwidth, deep learning data could be compressed and decompressed before memory write/read operations. Especially, feature maps, which account for a significant portion of the convolutional neural network (CNN), could be compressed further by reducing the correlations between feature map planes. This paper proposes a compression method for feature maps in CNN that adaptively exploits the varying correlation between feature map planes. For every feature map plane, the proposed method searches the most similar plane among nearby planes in the same layer, and compresses the residual of the two planes instead of the plane itself. Experimental results show that the average bit length to store feature maps is reduced by 14.2% compared to the compression without correlation reduction, and the CNN accuracy does not change and additional training is also not required because the proposed method applies lossless compression.