Adaptive Deep Learning Aided Digital Predistorter Considering Dynamic Envelope
TL;DR: This paper proposes an adaptive deep learning aided digital predistortion model by optimizing a deep regression neural network and makes the linearization architecture more adaptive by using multiple sub-DPD modules and an ensemble predicting process.
Abstract: Memory effects of radio frequency power amplifiers (PAs) can interact with dynamic transmitting signals, dynamic operations, and dynamic environment, resulting in complicated nonlinear problems of the PAs. Recently, deep learning based schemes have been proposed to deal with the memory effects. Although these schemes are powerful in constructing complex nonlinear structures, they are still direct learning-based and are relatively static. In this paper, we propose an adaptive deep learning aided digital predistortion (DL-DPD) model by optimizing a deep regression neural network. Thanks to the sequence structure of the proposed DL-DPD, we then make the linearization architecture more adaptive by using multiple sub-DPD modules and an ensemble predicting process. The results show the effectiveness of the proposed adaptive DL-DPD, and reveals that the online system handovers the sub-DPD modules more frequently than expected.
Citations
More filters
TL;DR: This paper proposes a transfer learning (TL)-based semi-supervised AMC (TL-AMC) in a zero-forcing aided multiple-input and multiple-output (ZF-MIMO) system and shows that it performs better than CNN-based AMC under the limited samples.
Abstract: Automatic modulation classification (AMC) is an essential technology for the non-cooperative communication systems, and it is widely applied into various communications scenarios. In the recent years, deep learning (DL) has been introduced into AMC due to its outstanding identification performance. However, it is almost impossible to implement previously proposed DL-based AMC algorithms without large number of labeled samples, while there are generally few labeled sample and large unlabel samples in the realistic communication scenarios. In this paper, we propose a transfer learning (TL)-based semi-supervised AMC (TL-AMC) in a zero-forcing aided multiple-input and multiple-output (ZF-MIMO) system. TL-AMC has a novel deep reconstruction and classification network (DRCN) structure that consists of convolutional auto-encoder (CAE) and convolutional neural network (CNN). Unlabeled samples flow from CAE for modulation signal reconstruction, while labeled samples are fed into CNN for AMC. Knowledge is transferred from the encoder layer of CAE to the feature layer of CNN by sharing their weights, in order to avoid the ineffective feature extraction of CNN under the limited labeled samples. Simulation results demonstrated the effectiveness of TL-AMC. In detail, TL-AMC performs better than CNN-based AMC under the limited samples. What’s more, when compared with CNN-based AMC trained on massive labeled samples, TL-AMC also achieved the similar classification accuracy at the relative high SNR regime.
56 citations
TL;DR: In this paper , a CITS DTs model is constructed based on CNN-SVR, whose security performance and effect are analyzed through simulation experiments. And the proposed DL algorithm model can lower the data transmission delay of the system, increase the prediction accuracy, and reasonably changes the paths to suppress the sprawl of traffic congestions, providing an experimental reference for developing and improving urban transportation.
Abstract: The purpose is to solve the security problems of the Cooperative Intelligent Transportation System (CITS) Digital Twins (DTs) in the Deep Learning (DL) environment. The DL algorithm is improved; the Convolutional Neural Network (CNN) is combined with Support Vector Regression (SVR); the DTs technology is introduced. Eventually, a CITS DTs model is constructed based on CNN-SVR, whose security performance and effect are analyzed through simulation experiments. Compared with other algorithms, the security prediction accuracy of the proposed algorithm reaches 90.43%. Besides, the proposed algorithm outperforms other algorithms regarding Precision, Recall, and F1. The data transmission performances of the proposed algorithm and other algorithms are compared. The proposed algorithm can ensure that emergency messages can be responded to in time, with a delay of less than 1.8s. Meanwhile, it can better adapt to the road environment, maintain high data transmission speed, and provide reasonable path planning for vehicles so that vehicles can reach their destinations faster. The impacts of different factors on the transportation network are analyzed further. Results suggest that under path guidance, as the Market Penetration Rate (MPR), Following Rate (FR), and Congestion Level (CL) increase, the guidance strategy’s effects become more apparent. When MPR ranges between 40% ~ 80% and the congestion is level III, the ATT decreases the fastest, and the improvement effect of the guidance strategy is more apparent. The proposed DL algorithm model can lower the data transmission delay of the system, increase the prediction accuracy, and reasonably changes the paths to suppress the sprawl of traffic congestions, providing an experimental reference for developing and improving urban transportation.
48 citations
TL;DR: A depthwise separable convolutional strategy is introduced to build a lightweight deep neural network to reduce its computational cost and detection accuracy and the proposed INES method is applied into the practical construction site for the validation of a specific IIoT application.
Abstract: Decentralized edge computing techniques have been attracted strongly attentions in many applications of intelligent Internet of Things (IIoT). Among these applications, intelligent edge surveillance (INES) methods play a very important role to recognize object feature information automatically from surveillance video by virtue of edge computing together with image processing and computer vision. Traditional centralized surveillance techniques recognize objects at the cost of high latency, high cost and also require high occupied storage. In this paper, we propose a deep learning-based INES technique for a specific IIoT application. First, a depthwise separable convolutional strategy is introduced to build a lightweight deep neural network to reduce its computational cost. Second, we combine edge computing with cloud computing to reduce network traffic. Third, our proposed INES method is applied into the practical construction site for the validation of a specific IIoT application. The detection speed of the proposed INES reaches 16 frames per second in the edge device. After the joint computing of edge and cloud, the detection precision can reach as high as 89%. In addition, the operating cost at the edge device is only one-tenth of that of the centralized server. Experiment results are given to confirm the proposed INES method in terms of both computational cost and detection accuracy.
37 citations
TL;DR: In this paper, a software-defined radio (SDR) based transceiver system is designed and implemented on the system-on-chip (SoC) platform, which consists of a high-speed Arm embedded processor and a reconfigurable field-programmable gate array (FPGA).
Abstract: In this paper, a software-defined radio (SDR) based transceiver system is designed and implemented on the system-on-chip (SoC) platform, which consists of a high-speed Arm embedded processor and a reconfigurable field-programmable gate array (FPGA). In the proposed SDR transceiver, the real-time baseband signal generation and adaptive digital predistortion (ADPD) units are implemented on the SoC platform. Memory polynomial model based ADPD solution is implemented to linearize the radio frequency (RF) power amplifiers (PAs). The implementation of the ADPD on a reconfigurable FPGA platform makes the system flexible and cost-effective. The PA characterization, in terms of model extraction and coefficient calculation, is done in real-time. These calculated coefficients are updated in the transmission path to precondition the transmitted signal before it is applied to the PA. The proposed ADPD is applied at the baseband level. Therefore, it can be used for different classes of PA operating at different RF carrier frequencies. A long-term evolution (LTE) signal with 20 MHz bandwidth and 11 dB peak to average power ratio (PAPR) is used for simulation and measurement purposes. The LTE signal is amplified using a GaN-based harmonically tuned continuous Class-F PA in measurement. The performance of the implemented ADPD scheme is analyzed in terms of NMSE, ACPR and EVM.
16 citations
TL;DR: The results demonstrate that the proposed self-adaptive SVM model can autonomously provide a suitable kernel for given marine environmental factor prediction, and outperform the alternative with the linear combination of multiple kernels.
Abstract: Support vector machine (SVM) is a powerful machine learning (ML) technology and the distinctive generalization ability makes it one of the most popular approximation tools in the field of Internet-of-Things (IoT)-based marine data processing. However, SVM has been criticized for trial and error of parameters, especially, kernel function. How to determine a suitable kernel for SVM in a specific problem has been rather tricky. To give a systematic research of the field, we concentrate on the self-adaptive selection of kernel functions in the framework of SVM for IoT-based marine data prediction. Specifically, we adopt the optimal kernel for obtaining competitive SVM and devises a kernel selection criteria of such high-efficiency models. Experiments are conducted via IoT-based real-world marine data sets of different characteristics. The results demonstrate that our proposed self-adaptive SVM model can autonomously provide a suitable kernel for given marine environmental factor prediction, and outperform the alternative with the linear combination of multiple kernels. Besides, the superior performance is verified from the perspective of statistic analysis.
13 citations
References
More filters
Proceedings Article•
01 Jan 2015TL;DR: This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.
Abstract: We introduce Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments. The method is straightforward to implement, is computationally efficient, has little memory requirements, is invariant to diagonal rescaling of the gradients, and is well suited for problems that are large in terms of data and/or parameters. The method is also appropriate for non-stationary objectives and problems with very noisy and/or sparse gradients. The hyper-parameters have intuitive interpretations and typically require little tuning. Some connections to related algorithms, on which Adam was inspired, are discussed. We also analyze the theoretical convergence properties of the algorithm and provide a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework. Empirical results demonstrate that Adam works well in practice and compares favorably to other stochastic optimization methods. Finally, we discuss AdaMax, a variant of Adam based on the infinity norm.
111,197 citations
"Adaptive Deep Learning Aided Digita..." refers methods in this paper
...We use the Adam [39] as the optimizer, and it can achieve better performance than the SGD [40] in our implementation....
[...]
TL;DR: A novel, efficient, gradient based method called long short-term memory (LSTM) is introduced, which can learn to bridge minimal time lags in excess of 1000 discrete-time steps by enforcing constant error flow through constant error carousels within special units.
Abstract: Learning to store information over extended time intervals by recurrent backpropagation takes a very long time, mostly because of insufficient, decaying error backflow. We briefly review Hochreiter's (1991) analysis of this problem, then address it by introducing a novel, efficient, gradient based method called long short-term memory (LSTM). Truncating the gradient where this does not do harm, LSTM can learn to bridge minimal time lags in excess of 1000 discrete-time steps by enforcing constant error flow through constant error carousels within special units. Multiplicative gate units learn to open and close access to the constant error flow. LSTM is local in space and time; its computational complexity per time step and weight is O. 1. Our experiments with artificial data involve local, distributed, real-valued, and noisy pattern representations. In comparisons with real-time recurrent learning, back propagation through time, recurrent cascade correlation, Elman nets, and neural sequence chunking, LSTM leads to many more successful runs, and learns much faster. LSTM also solves complex, artificial long-time-lag tasks that have never been solved by previous recurrent network algorithms.
72,897 citations
"Adaptive Deep Learning Aided Digita..." refers background in this paper
...However, the proposed long short-term memory (LSTM) [35] or bidirectional long short-term memory (BiLSTM) [36] based DPD architectures are all offline (static) direct learning-based....
[...]
TL;DR: In this article, the authors consider the problem of minimizing the differentiable functional (x) in Hilbert space, so long as this problem reduces to the solution of the equation grad(x) = 0.
Abstract: For the solution of the functional equation P (x) = 0 (1) (where P is an operator, usually linear, from B into B, and B is a Banach space) iteration methods are generally used. These consist of the construction of a series x0, …, xn, …, which converges to the solution (see, for example [1]). Continuous analogues of these methods are also known, in which a trajectory x(t), 0 ⩽ t ⩽ ∞ is constructed, which satisfies the ordinary differential equation in B and is such that x(t) approaches the solution of (1) as t → ∞ (see [2]). We shall call the method a k-step method if for the construction of each successive iteration xn+1 we use k previous iterations xn, …, xn−k+1. The same term will also be used for continuous methods if x(t) satisfies a differential equation of the k-th order or k-th degree. Iteration methods which are more widely used are one-step (e.g. methods of successive approximations). They are generally simple from the calculation point of view but often converge very slowly. This is confirmed both by the evaluation of the speed of convergence and by calculation in practice (for more details see below). Therefore the question of the rate of convergence is most important. Some multistep methods, which we shall consider further, which are only slightly more complicated than the corresponding one-step methods, make it possible to speed up the convergence substantially. Note that all the methods mentioned below are applicable also to the problem of minimizing the differentiable functional (x) in Hilbert space, so long as this problem reduces to the solution of the equation grad (x) = 0.
2,320 citations
"Adaptive Deep Learning Aided Digita..." refers methods in this paper
...We use the Adam [39] as the optimizer, and it can achieve better performance than the SGD [40] in our implementation....
[...]
TL;DR: The proposed DNN approach can well suppress highly nonstationary noise, which is tough to handle in general, and is effective in dealing with noisy speech data recorded in real-world scenarios without the generation of the annoying musical artifact commonly observed in conventional enhancement methods.
Abstract: In contrast to the conventional minimum mean square error (MMSE)-based noise reduction techniques, we propose a supervised method to enhance speech by means of finding a mapping function between noisy and clean speech signals based on deep neural networks (DNNs). In order to be able to handle a wide range of additive noises in real-world situations, a large training set that encompasses many possible combinations of speech and noise types, is first designed. A DNN architecture is then employed as a nonlinear regression function to ensure a powerful modeling capability. Several techniques have also been proposed to improve the DNN-based speech enhancement system, including global variance equalization to alleviate the over-smoothing problem of the regression model, and the dropout and noise-aware training strategies to further improve the generalization capability of DNNs to unseen noise conditions. Experimental results demonstrate that the proposed framework can achieve significant improvements in both objective and subjective measures over the conventional MMSE based technique. It is also interesting to observe that the proposed DNN approach can well suppress highly nonstationary noise, which is tough to handle in general. Furthermore, the resulting DNN model, trained with artificial synthesized data, is also effective in dealing with noisy speech data recorded in real-world scenarios without the generation of the annoying musical artifact commonly observed in conventional enhancement methods.
1,250 citations
"Adaptive Deep Learning Aided Digita..." refers methods in this paper
...The contribution of this paper is listed as follows: To deal with the PAs nonlinear behavior with memory effects, a direct learning-based DPD is proposed by optimizing a deep regression neural network [37]....
[...]
TL;DR: An overview of the state-of-the-art deep learning architectures and algorithms relevant to the network traffic control systems, and a new use case, i.e., deep learning based intelligent routing, which is demonstrated to be effective in contrast with the conventional routing strategy.
Abstract: Currently, the network traffic control systems are mainly composed of the Internet core and wired/wireless heterogeneous backbone networks. Recently, these packet-switched systems are experiencing an explosive network traffic growth due to the rapid development of communication technologies. The existing network policies are not sophisticated enough to cope with the continually varying network conditions arising from the tremendous traffic growth. Deep learning, with the recent breakthrough in the machine learning/intelligence area, appears to be a viable approach for the network operators to configure and manage their networks in a more intelligent and autonomous fashion. While deep learning has received a significant research attention in a number of other domains such as computer vision, speech recognition, robotics, and so forth, its applications in network traffic control systems are relatively recent and garnered rather little attention. In this paper, we address this point and indicate the necessity of surveying the scattered works on deep learning applications for various network traffic control aspects. In this vein, we provide an overview of the state-of-the-art deep learning architectures and algorithms relevant to the network traffic control systems. Also, we discuss the deep learning enablers for network systems. In addition, we discuss, in detail, a new use case, i.e., deep learning based intelligent routing. We demonstrate the effectiveness of the deep learning-based routing approach in contrast with the conventional routing strategy. Furthermore, we discuss a number of open research issues, which researchers may find useful in the future.
643 citations
"Adaptive Deep Learning Aided Digita..." refers background in this paper
...Recently, machine learning [22] provides an alternative option in the domain of wireless communications, for example, the 5G and beyond [23]–[32]....
[...]