Source-channel Coding Research Articles

Improved Nonlinear Transform Source-Channel Coding to Catalyze Semantic Communications

Improved Nonlinear Transform Source-Channel Coding to Catalyze Semantic Communications

High-Resolution Data Acquisition and Joint Source-Channel Coding in Underwater IoT

Reliable and persistent water monitoring is a challenging problem in smart Underwater Internet of Things (UW IoT) due to its harsh, unexplored, and unpredictable nature. Given the need for high-resolution spatio-temporal sensing in such environments, traditional digital sensors are not suitable due to their high cost, high power consumption, and non-biodegradable nature. Further, reliable and low latency communication techniques that avoid data packet retransmissions, if the feedback is available, are crucial for reconstructing the phenomenon being monitored in a timely manner at the fusion center, such as a drone. To address the above challenges, we propose a novel architecture consisting of a substrate of densely deployed underwater all-analog biodegradable sensors that enable persistent sensing and continually transmitting data to the surface digital buoys. The analog nodes are designed to be energy efficient by implementing analog Joint Source-Channel Coding (JSCC), a low-complexity compression-communication technique, using biodegradable Field Effect Transistors (FETs). We then propose a correlation-aware Hybrid Automatic Repeat Request (HARQ) technique to transmit data from the surface buoys to the fusion center. Such HARQ technique leverages JSCC and the redundancy in the buoy data (arising from the correlation of the phenomenon at the analog nodes) to avoid retransmissions, thus saving energy and time.

Design of Low-Density Parity-Check Code Pair for Joint Source-Channel Coding Systems Based on Graph Theory.

In this article, a graph-theoretic method (taking advantage of constraints among sets associated with the corresponding parity-check matrices) is applied for the construction of a double low-density parity-check (D-LDPC) code (also known as LDPC code pair) in a joint source-channel coding (JSCC) system. Specifically, we pre-set the girth of the parity-check matrix for the LDPC code pair when jointly designing the two LDPC codes, which are constructed by following the set constraints. The constructed parity-check matrices for channel codes comprise an identity submatrix and an additional submatrix, whose column weights can be pre-set to be any positive integer numbers. Simulation results illustrate that the constructed D-LDPC codes exhibit significant performance improvement and enhanced flexible frame length (i.e., adaptability under various channel conditions) compared with the benchmark code pair.

Predictive and Adaptive Deep Coding for Wireless Image Transmission in Semantic Communication

Semantic communication is a newly emerged communication paradigm that exploits deep learning (DL) models to realize communication processes like source coding and channel coding. Recent advances have demonstrated that DL-based joint source-channel coding (DeepJSCC) can achieve exciting data compression and noise-resiliency performances for wireless image transmission tasks, especially in environments with low channel signal-to-noises (SNRs). However, existing DeepJSCC-based semantic communication frameworks still cannot achieve adaptive code rates for different channel SNRs and image contents, which reduces its flexibility and bandwidth efficiency. In this paper, we propose a predictive and adaptive deep coding (PADC) framework for realizing flexible code rate optimization with a given target transmission quality requirement. PADC is realized by a variable code length enabled DeepJSCC (DeepJSCC-V) model for realizing flexible code length adjustment, an Oracle Network (OraNet) model for predicting peak-signal-to-noise (PSNR) value for an image transmission task according to its contents, channel signal to noise ratio (SNR) and the compression ratio (CR) value, and a CR optimizer aims at finding the minimal data-level or instance-level CR with a PSNR quality constraint. By using the above three modules, PADC can transmit the image data with minimal CR, which greatly increases bandwidth efficiency. Simulation results demonstrate that the proposed DeepJSCC-V model can achieve similar PSNR performances compared with the state-of-the-art Attention-based DeepJSCC (ADJSCC) model, and the proposed OraNet model is able to predict high-quality PSNR values with an average error lower than 0.5dB. Results also demonstrate that the proposed PADC can use nearly minimal bandwidth consumption for wireless image transmission tasks with different channel SNR and image contents, at the same time guaranteeing the PSNR constraint for each image data.

A Task-Guided Normalized Min-Sum Decoding Network for LDPC Codes-Based DJSCC

Distributed joint source-channel coding (DJSCC) refers to the correlated sources which are encoded separately and reconstructed in the centre node by joint decoding. Therefore, the challenging problem involves designing a simple and efficient decoding algorithm to utilize the correlations among distributed sources. In this letter, a multi-task deep learning decoder is proposed for the low-density parity-check (LDPC) code-based DJSCC system to improve the performance. This proposal is based on the shared neural normalized min-sum (SNNMS) decoding network and the log likelihood ratio (LLR) shared unit is added to further exploit the source correlation. Moreover, an adaptive multi-loss function is proposed to prevent the network tilting the balance in favor of one certain task. Simulation results indicate that the proposed decoder can achieve a significant performance improvement with almost the same complexity compared with the separated SNNMS decoders.

Generative Joint Source-Channel Coding for Semantic Image Transmission

Recent works have shown that joint source-channel coding (JSCC) schemes using deep neural networks (DNNs), called DeepJSCC, provide promising results in wireless image transmission. However, these methods mostly focus on the distortion of the reconstructed signals with respect to the input image, rather than their perception by humans. However, focusing on traditional distortion metrics alone does not necessarily result in high perceptual quality, especially in extreme physical conditions, such as very low bandwidth compression ratio (BCR) and low signal-to-noise ratio (SNR) regimes. In this work, we propose two novel JSCC schemes that leverage the perceptual quality of deep generative models (DGMs) for wireless image transmission, namely InverseJSCC and GenerativeJSCC. While the former is an inverse problem approach to DeepJSCC, the latter is an end-to-end optimized JSCC scheme. In both, we optimize a weighted sum of mean squared error (MSE) and learned perceptual image patch similarity (LPIPS) losses, which capture more semantic similarities than other distortion metrics. InverseJSCC performs denoising on the distorted reconstructions of a DeepJSCC model by solving an inverse optimization problem using the pre-trained style-based generative adversarial network (StyleGAN). Our simulation results show that InverseJSCC significantly improves the state-of-the-art DeepJSCC in terms of perceptual quality in edge cases. In GenerativeJSCC, we carry out end-to-end training of an encoder and a StyleGAN-based decoder, and show that GenerativeJSCC significantly outperforms DeepJSCC both in terms of distortion and perceptual quality.

Robust Information Bottleneck for Task-Oriented Communication With Digital Modulation

Task-oriented communications, mostly using learning-based joint source-channel coding (JSCC), aim to design a communication-efficient edge inference system by transmitting task-relevant information to the receiver. However, only transmitting task-relevant information without introducing any redundancy may cause robustness issues in learning due to the channel variations, and the JSCC which directly maps the source data into continuous channel input symbols poses compatibility issues on existing digital communication systems. In this paper, we address these two issues by first investigating the inherent tradeoff between the informativeness of the encoded representations and the robustness to information distortion in the received representations, and then propose a task-oriented communication scheme with digital modulation, named discrete task-oriented JSCC (DT-JSCC), where the transmitter encodes the features into a discrete representation and transmits it to the receiver with the digital modulation scheme. In the DT-JSCC scheme, we develop a robust encoding framework, named robust information bottleneck (RIB), to improve the communication robustness to the channel variations, and derive a tractable variational upper bound of the RIB objective function using the variational approximation to overcome the computational intractability of mutual information. The experimental results demonstrate that the proposed DT-JSCC achieves better inference performance than the baseline methods with low communication latency, and exhibits robustness to channel variations due to the applied RIB framework.

Toward Adaptive Semantic Communications: Efficient Data Transmission via Online Learned Nonlinear Transform Source-Channel Coding

The emerging field semantic communication is driving the research of end-to-end data transmission. By utilizing the powerful representation ability of deep learning models, learned data transmission schemes have exhibited superior performance than the established source and channel coding methods. While, so far, research efforts mainly concentrated on architecture and model improvements toward a static target domain. Despite their successes, such learned models are still suboptimal due to the limitations in model capacity and imperfect optimization and generalization, particularly when the testing data distribution or channel response is different from that adopted for model training, as is likely to be the case in real-world. To tackle this, in this paper, we propose a novel online learned joint source and channel coding approach that leverages the deep learning model’s overfitting property. Specifically, we update the off-the-shelf pre-trained models after deployment in a lightweight online fashion to adapt to the distribution shifts in source data and environment domain. We take the overfitting concept to the extreme, proposing a series of implementation-friendly methods to adapt the codec model or representations to an individual data or channel state instance, which can further lead to substantial gains in terms of the end-to-end rate-distortion performance. Accordingly, the streaming ingredients include both the semantic representations of source data and the online updated decoder model parameters. The system design is formulated as a joint optimization problem whose goal is to minimize the loss function, a tripartite trade-off among the data stream bandwidth cost, model stream bandwidth cost, and end-to-end distortion. The proposed methods enable the communication-efficient adaptation for all parameters in the network without sacrificing decoding speed. Extensive experiments, including user study, on continually changing target source data and wireless channel environments, demonstrate the effectiveness and efficiency of our approach, on which we outperform existing state-of-the-art engineered transmission scheme (VVC combined with 5G LDPC coded transmission).

Design and Optimization of Linking Matrix for a JSCC System Based on DP-LDPC Codes.

Although extensive optimization of encoding and decoding schemes for joint source-channel coding (JSCC) systems has been conducted, efficient optimization schemes are still required for designing and optimizing the linking matrix between variable nodes of the source code and check nodes of the channel code. A scheme has been proposed for design and optimization of linking matrix with multi-edges by analyzing the performance of the JSCC system using the joint protograph extrinsic information transfer algorithm to calculate decoding thresholds. The proposed scheme incorporates structural constraints and is effective in designing and optimizing the multi-edges in linking matrix for the JSCC system. Experimental results have demonstrated that the designed and optimized linking matrix significantly improves the performance of the JSCC system. Furthermore, the proposed scheme reduces the complexity of the solution space for the optimized example.

Reliability Function for Streaming Over a DMC With Feedback

Conventionally, posterior matching is investigated in channel coding and block encoding contexts – the source symbols are equiprobably distributed and are entirely known by the encoder before the transmission. In this paper, we consider a streaming source, whose symbols progressively arrive at the encoder at a sequence of deterministic times. We derive the joint source-channel coding (JSCC) reliability function for streaming over a discrete memoryless channel (DMC) with feedback. We propose a novel <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">instantaneous encoding phase</i> that operates during the symbol arriving period and achieves the JSCC reliability function for streaming when followed by a block encoding scheme that achieves the JSCC reliability function for a classical source whose symbols are fully accessible before the transmission. During the instantaneous encoding phase, the evolving message alphabet is partitioned into groups whose priors are close to the capacity-achieving distribution, and the encoder determines the group index of the actual sequence of symbols arrived so far and applies randomization to exactly match the distribution of the transmitted index to the capacity-achieving one. Surprisingly, the JSCC reliability function for streaming is equal to that for a fully accessible source, implying that the knowledge of the entire symbol sequence before the transmission offers no advantage in terms of the reliability function. For streaming over a symmetric binary-input DMC, we propose a one-phase <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">instantaneous small-enough difference (SED) code</i> that not only achieves the JSCC reliability function, but also, thanks to its single-phase time-invariant coding rule, can be used to stabilize an unstable linear system over a noisy channel. For equiprobably distributed source symbols, we design low complexity algorithms to implement both the instantaneous encoding phase and the instantaneous SED code. The algorithms group the source sequences into sets we call types, which enable the encoder and the decoder to track the priors and the posteriors of source sequences jointly, leading to a log-linear complexity in time. While the reliability function is derived for non-degenerate DMCs, i.e., DMCs whose transition probability matrix has all positive entries, for degenerate DMCs, we design a code with instantaneous encoding that achieves zero error for all rates below Shannon’s joint source-channel coding limit.

Semantic Communications With Discrete-Time Analog Transmission: A PAPR Perspective

Recent progress in deep learning (DL)-based joint source-channel coding (DeepJSCC) has led to a new paradigm of semantic communications. Two salient features of DeepJSCC-based semantic communications are the exploitation of semantic-aware features directly from the source signal, and the discrete-time analog transmission (DTAT) of these features. Compared with traditional digital communications, semantic communications with DeepJSCC provide superior reconstruction performance at the receiver and graceful degradation with diminishing channel quality, but also exhibit a large peak-to-average power ratio (PAPR) in the transmitted signal. An open question has been whether the gains of DeepJSCC come at the expense of high-PAPR continuous-amplitude signal, which can limit its adoption in practice. In this letter, we first show that conventional DeepJSCC does suffer from high PAPR. Then, we explore three PAPR reduction techniques and confirm that the superior image reconstruction performance of DeepJSCC can be retained while the PAPR is suppressed to an acceptable level. This is an important step towards the implementation of DeepJSCC in practical semantic communication systems.

Analysis and Optimization of a General Linking Matrix for JSCC Scheme Based on Double LDPC Codes

A key component of the joint source-channel coding (JSCC) scheme based on double low-density parity-check (D-LDPC) codes is the introduction of a linking matrix between the source LDPC code and channel LDPC code, by which the decoding information including the source redundancy and channel state information can be transferred iteratively. However, the linking matrix is a fixed one-to-one mapping, i.e., an identity matrix in a conventional D-LDPC code system, which may not take full advantage of the decoding information. Therefore, this paper introduces a general linking matrix, i.e., a non-identity linking matrix, connecting the check nodes (CNs) of the source LDPC code and the variable nodes (VNs) of the channel LDPC code. Further, the encoding and decoding algorithms of the proposed D-LDPC coding system are generalized. A joint extrinsic information transfer (JEXIT) algorithm is derived for calculating the decoding threshold of the proposed system with a general linking matrix. In addition, several general linking matrices are optimized with the aid of the JEXIT algorithm. Finally, the simulation results demonstrate the superiority of the proposed D-LDPC coding system with general linking matrices.

Design and Analysis of Joint Group Shuffled Scheduling Decoding Algorithm for Double LDPC Codes System.

In this paper, a joint group shuffled scheduling decoding (JGSSD) algorithm for a joint source-channel coding (JSCC) scheme based on double low-density parity-check (D-LDPC) codes is presented. The proposed algorithm considers the D-LDPC coding structure as a whole and applies shuffled scheduling to each group; the grouping relies on the types or the length of the variable nodes (VNs). By comparison, the conventional shuffled scheduling decoding algorithm can be regarded as a special case of this proposed algorithm. A novel joint extrinsic information transfer (JEXIT) algorithm for the D-LDPC codes system with the JGSSD algorithm is proposed, by which the source and channel decoding are calculated with different grouping strategies to analyze the effects of the grouping strategy. Simulation results and comparisons verify the superiority of the JGSSD algorithm, which can adaptively trade off the decoding performance, complexity and latency.

Global Design of Double Protograph LDPC Codes for Joint Source-Channel Coding

In this letter, a global design of double protograph low-density parity-check (DP-LDPC) codes is proposed for joint source-channel coding (JSCC) system. The maximum number of degree-2 variable nodes (VNs), which is very important for the performance of the system, is determined from a global perspective that considers the joint protograph as a whole. Based on the allocation of degree-2 VNs, the new guidelines with this more comprehensive perspective are summarized and the global optimized DP-LDPC codes are designed. The simulation results that are in consistent with the joint protograph extrinsic information transfer (P-EXIT) analysis indicate that the optimized DP-LDPC codes have better performance compared with the existing re-designed DP-LDPC codes.

Signal Recovery Performance Analysis in Wireless Sensing With Rectangular-Type Analog Joint Source-Channel Coding

The signal recovery performance of the rectangular-type Analog Joint Source-Channel Coding (AJSCC) is analyzed in this work for high and medium/low Signal-to-Noise Ratio (SNR) scenarios in a wireless sensing system with the Doppler channel. The analytical formulations of the Mean Square Error (MSE) performance are derived based on the geometry of the rectangular-type AJSCC on analog sensing and system with Doppler effects. The comprehensive listing of all cases in the three-dimensional geometric signal mapping curve is provided to obtain the theoretical formulations for the medium/low SNR scenario. Evaluation results indicate that there are optimal parameters in the rectangular-type AJSCC to minimize the signal recovery MSE for analog sensing and system with Doppler effects in both high and medium/low SNR scenarios. The analysis of the work provides insights on the optimization of the rectangular-type AJSCC in practical wireless sensing systems.

Adaptive Decoding Algorithm With Variable Sliding Window for Double SC-LDPC Coding System

In this letter, an adaptive decoding algorithm with a variable sliding window for joint source-channel coding (JSCC) scheme based on double spatially coupled low-density parity-check (DSC-LDPC) codes is investigated. For the traditional sliding window decoding (SWD) algorithm, one or more errors occurring in a decoding window may affect the decoding of the next window, which will trigger error propagation. To mitigate the effects, a window extension algorithm based on average log-likelihood ratios (LLRs) will be proposed, but the implement of extension implies higher decoding complexity. In order to trade-off the error rate performance and complexity, the source and channel threshold that determines the window extension are analyzed. In the simulation, the proposed SWD algorithm with acceptable complexity has better error rate performance in the water fall region and the error floor region.

LDPC Coded Compressive Sensing for Joint Source-Channel Coding in Wireless Sensor Networks

The novel concept of joint Compressive Sensing (CS) and Low Density Parity Check (LDPC) coding is conceived for Joint Source-Channel Coding (JSCC) in Wireless Sensor Networks (WSNs) supporting a massive number of signals. More explicitly, we demonstrate this concept for a specific scheme, which supports a massive number of signals simultaneously, using a small number of Internet of Things Nodes (IoTNs) based on the concept of CS. The compressed signals are LDPC coded in order to protect them from poor transmission channels. We also propose the new iterative joint source-channel decoding philosophy for exchanging soft <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">extrinsic</i> information, which combines CS decoding and LDPC decoding by merging their respective factor graphs. We then characterize this scheme using Extrinsic Information Transfer (EXIT) chart analysis. Our BLock Error Rate (BLER) results show that the proposed iterative joint LDPC-CS decoding scheme attains about 1.5 dB gain at a BLER of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$10^{-3}$</tex-math></inline-formula> compared to a benchmarker, which employs separate CS and LDPC decoding. Naturally, this gain is achieved at the cost of approximately doubling the complexity of the proposed iterative joint LDPC-CS decoding scheme.

Deep Joint Source-Channel Coding for CSI Feedback: An End-to-End Approach

The increased throughput brought by MIMO technology relies on the knowledge of channel state information (CSI) acquired in the base station (BS). To make the CSI feedback overhead affordable for the evolution of MIMO technology (e.g., massive MIMO and ultra-massive MIMO), deep learning (DL) is introduced to deal with the CSI compression task. In traditional communication systems, the compressed CSI bits is treated equally and expected to be transmitted accurately over the noisy channel. While the errors occur due to the limited bandwidth or low signal-to-noise ratios (SNRs), the reconstruction performance of the CSI degrades drastically. As a branch of semantic communications, deep joint source-channel coding (DJSCC) scheme performs better than the separate source-channel coding (SSCC) scheme—the cornerstone of traditional communication systems—in the limited bandwidth and low SNRs. In this paper, we propose a DJSCC based framework for the CSI feedback task. In particular, the proposed method can simultaneously learn from the CSI source and the wireless channel. Instead of truncating CSI via Fourier transform in the delay domain in existing methods, we apply non-linear transform networks to compress the CSI. Furthermore, we adopt an SNR adaption mechanism to deal with wireless channel variations. The extensive experiments demonstrate the validity, adaptability, and generality of the proposed framework.

Wireless Deep Video Semantic Transmission

In this paper, we design a new class of high-efficiency deep joint source-channel coding methods to achieve end-to-end video transmission over wireless channels. The proposed methods exploit nonlinear transform and conditional coding architecture to adaptively extract semantic features across video frames, and transmit semantic feature domain representations over wireless channels via deep joint source-channel coding. Our framework is collected under the name deep video semantic transmission (DVST). In particular, benefiting from the strong temporal prior provided by the feature domain context, the learned nonlinear transform function becomes temporally adaptive, resulting in a richer and more accurate entropy model guiding the transmission of current frame. Accordingly, a novel rate adaptive transmission mechanism is developed to customize deep joint source-channel coding for video sources. It learns to allocate the limited channel bandwidth within and among video frames to maximize the overall transmission performance. The whole DVST design is formulated as an optimization problem whose goal is to minimize the end-to-end transmission rate-distortion performance under perceptual quality metrics or machine vision task performance metrics. Across standard video source test sequences and various communication scenarios, experiments show that our DVST can generally surpass traditional wireless video coded transmission schemes. The proposed DVST framework can well support future semantic communications due to its video content-aware and machine vision task integration abilities.

Low-Delay Analog Joint Source-Channel Coding With Deep Learning

We consider the design of low-delay joint source-channel coding (JSCC) schemes for the transmission of discrete-time analog sources over noisy channels based on deep neural networks. The design problem is addressed as optimization of an autoencoder model, and several scenarios are discussed. For point-to-point communication of independent and identically distributed (i.i.d) Gaussian sources and Gauss-Markov sources over additive-white Gaussian noise (AWGN) channels, the encoder and decoder are constructed using recurrent neural networks (RNNs). With minimum prior knowledge used for design, the performance of these RNNs-based models is optimized using fine tuning techniques during training. Sinusoidal representation networks (SIRENs)-based models are proposed and optimized for three JSCC problems namely, transmitting multivariate Gaussian sources over AWGN channels, transmitting i.i.d Gaussian sources with side information at the decoder, and for communicating correlated sources over orthogonal Gaussian channels. We show that these deep learning-based JSCC schemes perform comparably or better than state-of-the-art (SOTA) traditional schemes. The proposed scheme can extend flexibly to different pairs of source and channel dimensions. Moreover, the spontaneously learned encoder mappings exhibit structured patterns that are interpretable.