Quantization Parameter Research Articles

Smart algorithm in wireless networks for video streaming based on adaptive quantization

SummaryNowadays, smart multimedia network services have become crucial in the healthcare system. The network parameters of Quality of Service (QoS) are widely affecting the efficiency and accuracy of multimedia streaming in wireless environments. This paper proposes an adaptation framework model, which makes a relation between the QP (quantization parameter) in H.264 and H.265 codecs and the QoS of 5G wireless technology. Besides, the effect of QP and packet loss have been studied because of their impact on video streaming. Packet loss of 5G wireless network characteristic is emulated to determine the impact of QP on the received video quality using objective and subjective quality metrics such as PSNR (peak signal to noise ratio), SSIM (structure similarity), and DMOS (differential mean opinion score). In this research, a Testbed is implemented to stream the encoded video from the server to the end users. The application model framework has automatically evaluated the QoE (Quality of Experience). Accordingly, the model detects the defect of network packet loss and selects the optimum QP value to enhance the QoE by the end‐users. The application has been tested on low and high video motions with full high definition (HD) resolution (1920 × 1080) which were taken from ( https://www.xiph.org/downloads/). Test results based on the objective and subjective quality measurements indicate that an optimal QP = 35 and QP = 30 have been chosen for low and high motion respectively to satisfy user QoE requirements.

Hydrodynamic characteristics of a pitching hydrofoil in unsteady uniform inflow with special emphasis on the hysteresis effect

Numerical flow simulations on a Clark-Y pitching hydrofoil are carried out to study the effect of an unsteady uniform inflow on the dynamic characteristics and the corresponding flow structure. The representative hysteresis phenomenon of pitching hydrofoil is observed and analyzed emphatically. In this study, the pitching motion trajectory is a triangular wave with mean incidence of α0 = 10° and amplitude of Δα0 = 5° at a pitching frequency f* of 2 Hz. The amplitude of unsteady uniform velocity ΔU is set 0, 0.75, 1.50, 3.0 respectively, and the frequency of unsteady uniform velocity f of 1, 2, 4 were chosen. The numerical method is validated through the experimental results at ΔU = 0. Results revealed that pitching motion and unsteady uniform inflow both lead to the occurrence of hysteresis effect, and two hysteresis effect quantization parameters (the hysteresis parameter εCL and hysteresis area SCL) were defined. Results showed that the relationship between ΔU, f and the two parameters is respectively linear and nonlinear. Meanwhile, the values of ΔU, f directly determine the contribution of unsteady uniform inflow to hydrodynamic hysteresis effect. In addition, ΔU and f have a significant impact on the flow structures and the development of vortices. However, ΔU and f don't change vortex structure directly, but affect the formation and dwell time of vortex structure significantly, thus leading to the different hydrodynamic characteristics.

Video coding deep learning-based modeling for long life video streaming over next network generation.

Availability is one of the primary goals of smart networks, especially, if the network is under heavy video streaming traffic. In this paper, we propose a deep learning based methodology to enhance availability of video streaming systems by developing a prediction model for video streaming quality, required power consumption, and required bandwidth based on video codec parameters. The H.264/AVC codec, which is one of the most popular codecs used in video steaming and conferencing communications, is chosen as a case study in this paper. We model the predicted consumed power, the predicted perceived video quality, and the predicted required bandwidth for the video codec based on video resolution and quantization parameters. We train, validate, and test the developed models through extensive experiments using several video contents. Results show that an accurate model can be built for the needed purpose and the video streaming quality, required power consumption, and required bandwidth can be predicted accurately which can be utilized to enhance network availability in a cooperative environment.

Versatile Video Coding-Based Coding Tree Unit Level Image Compression With Dual Quantization Parameters for Hybrid Vision

Image analysis based on machine vision is hugely manipulated in the smart industry. Good-quality images are required for outstanding machine analysis results, but handling high-definition images could be problematic in a constrained environment such as a low-bandwidth network or low-capacity storage. Lowering the image resolution might be a straightforward solution for reducing image data, but it would occasion much information loss, leading to the deterioration of machine vision. Moreover, human supervision could be necessary for a contingency that machine vision cannot control.Therefore, an innovative image compression method considering machine and human vision is required; more compression efficiency than the state-of-the-art codec, praiseworthy machine vision performance, and human-recognizable quality. In this paper, we propose Versatile video coding(VVC) based image compression for hybrid vision, i.e., machine vision and human vision. Our work provides a coding tree unit(CTU) level image compression with dual quantization parameters (QPs) according to the quantization parameter map and the saliency extracted by the object detection network; in the salient region, the proposed method maintains high quality with low QP but degrades the quality with high QP in the non-salient region.Compared with VVC, the proposed compression method achieves a bitrate reduction of up to 25.5% in machine vision tasks, proving more compression efficiency and still admirable machine vision performance. From the perspective of human vision, the proposed method provides human-perceptible image quality, preserving acceptable objective quality values.

Bitstream-based Perceptual Quality Assessment of Compressed 3D Point Clouds.

With the increasing demand of compressing and streaming 3D point clouds under constrained bandwidth, it has become ever more important to accurately and efficiently determine the quality of compressed point clouds, so as to assess and optimize the quality-of-experience (QoE) of end users. Here we make one of the first attempts developing a bitstream-based no-reference (NR) model for perceptual quality assessment of point clouds without resorting to full decoding of the compressed data stream. Specifically, we first establish a relationship between texture complexity and the bitrate and texture quantization parameters based on an empirical rate-distortion model. We then construct a texture distortion assessment model upon texture complexity and quantization parameters. By combining this texture distortion model with a geometric distortion model derived from Trisoup geometry encoding parameters, we obtain an overall bitstream-based NR point cloud quality model named streamPCQ. Experimental results show that the proposed streamPCQ model demonstrates highly competitive performance when compared with existing classic full-reference (FR) and reduced-reference (RR) point cloud quality assessment methods with a fraction of computational cost.

No-Reference Bitstream-Layer Model for Perceptual Quality Assessment of V-PCC Encoded Point Clouds

No-reference bitstream-layer models for point cloud quality assessment (PCQA) use the information extracted from a bitstream for real-time and nonintrusive quality monitoring. We propose a no-reference bitstream-layer model for the perceptual quality assessment of video-based point cloud compression (V-PCC) encoded point clouds. First, we describe the fundamental relationship between perceptual coding distortion and the texture quantization parameter (TQP) when geometry encoding is lossless. Then, we incorporate the texture complexity (TC) into the proposed model while considering the fact that the perceptual coding distortion of a point cloud depends on the texture characteristics. TC is estimated using TQP and the texture bitrate per pixel (TBPP), both of which are extracted from the compressed bitstream without resorting to complete decoding. Then, we construct a texture distortion assessment model upon TQP and TBPP. By combining this texture distortion model with the geometry quantization parameter (GQP), we obtain an overall no-reference bitstream-layer PCQA model that we call bitstreamPCQ. Experimental results show that the proposed model markedly outperforms existing models in terms of widely used performance criteria, including the Pearson linear correlation coefficient (PLCC), the Spearman rank order correlation coefficient (SRCC) and the root mean square error (RMSE). The dataset developed in this study is publicly available at https://github.com/qdushl/Waterloo-Point-Cloud-Database-3.0.

Multisensor Collaboration Network for Video Compression Based on Wavelet Decomposition

Multi-sensor data has significant advantages over single sensor data due to the unique property of each sensor. We discover that multi-sensor collaboration can save bits and achieve stable compression performance according to quantization parameter (QP). In this paper, we propose a multi-sensor collaboration network for video compression based on wavelet decomposition, called MSCN. We introduce MSCN into 3D video coding based on color and depth sensors. The images acquired by a color sensor represent color and texture of the scene, while the images obtained by a depth sensor represent 3D geometric shape of the scene objects. Two sensor data are complementary, and color images help to reconstruct their corresponding depth images. First, we perform uniform sampling on the input depth video. Then, we compress the color and downsampled depth videos using 3D-HEVC codec. Finally, we reconstruct the depth video from the decoded color and depth videos by color guided depth super-resolution (SR). Experimental results show that MSCN achieves average BD-rate reductions of {−9.3%, −65.6%, −66.3%} and {−6.2%, −67.7%, and −69.2%} on 3D-HEVC test datasets for sampling factors 1, 2 and 4 in Random Access (RA) and All Intra (AI) configurations, respectively. Moreover, they verify that multi-sensor collaboration remarkably saves bits in video compression.

BL-JUNIPER: A CNN-Assisted Framework for Perceptual Video Coding Leveraging Block-Level JND

Just Noticeable Distortion (JND) finds the minimum distortion level perceivable by humans. This can be a natural solution for setting the compression for each video region in perceptual video coding. However, existing JND-based solutions estimate JND levels for each video frame and ignore the fact that different video regions have different perceptual importance. To address this issue, we propose a Block-Level Just Noticeable Distortion-based Perceptual (BL-JUNIPER) framework for video coding. The proposed four-stage framework combines different perceptual information to further improve the prediction accuracy. The JND mapping in the first stage derives block-level JNDs from frame-level information without the need to collect a new bock-level JND dataset. In the second stage, an efficient CNN-based model is proposed to predict JND levels for each block according to spatial and temporal characteristics. Unlike existing methods, BL-JUNIPER works on raw video frames and avoids re-encoding each frame several times, making it computationally practical. Third, the visual importance of each block is measured using a visual attention model. Finally, a proposed quantization control algorithm uses both JND levels and visual importance to adjust the Quantization Parameter (QP) for each block. The specific algorithm for each stage of the proposed framework can be changed, as long as the input and output formats of each block are followed, without the need to change other stages, based on any current or future methods, providing a flexible and robust solution. Extensive experimental results demonstrate that BL-JUNIPER achieves a mean bitrate reduction of 27.75% with a Delta Mean Opinion Score (DMOS) close to zero and BD-Rate gains of 25.44% based on MOS, compared to the baseline encoding, and also gains a better performance compared to competing methods.

Hybrid Post-Training Quantization for Super-Resolution Neural Network Compression

Quantization is a widely adopted technique to reduce the storage cost of neural networks. However, existing methods primarily focus on minimizing the quantization error of neural network parameters without considering the correlation between the quantization error and performance of quantized neural networks. Motivated by this consideration, we propose a hybrid post-training quantization (HPTQ) method for super-resolution neural networks. Layer-wise quantization and piecewise quantization are integrated based on error sensitivity and the quantization error of parameters. In HPTQ, we utilize Taylor expansion to demonstrate that the performance distortion of quantized neural networks is a weighted average of parameter quantization errors with respect to gradients. To reduce the quantization error, we apply uniform and clustered quantization to parameters in dense and sparse regions, respectively. Furthermore, we allocate larger bit-widths to layers with higher error sensitivity indicated by gradients. Numerical experiments show that the super-resolution neural networks perform better under the proposed quantization approach compared to existing quantization methods.

Fixed‐time fault‐tolerant control of uncertain MIMO switched interconnected systems subject to state delay, unknown control directions, and quantized nonlinear inputs

SummaryThis paper investigates design of an adaptive fixed‐time fault‐tolerant decentralized controller for a class of uncertain multi‐input multi‐output (MIMO) switched large‐scale non‐strict interconnected systems under arbitrary switching subject to unknown control directions, quantized nonlinear inputs, actuator failures unknown external disturbances, and unmodeled dynamics. In addition to interconnected terms, time‐varying delayed interconnected terms have been considered in the system model which makes it more general than previous works in the literature. The proposed controller can handle switched systems with unknown switching signal and different types of input nonlinearities including, saturation, backlash, and dead‐zone. The singularity problem in designing the fixed time controller has been solved. The quantizer and actuators fault parameters are assumed to be unknown. The Razumikhin lemma has been used to deal with the delayed interconnected terms. To cope with the system unknown dynamics, neural networks (NNs) have been applied and by updating the maximum norms of the networks weight vectors the computational load has been reduced. The explosion of complexity occurring in the traditional back‐stepping technique has been avoided by applying dynamic surface control (DSC). Finally, by defining an appropriate common Lyapunov function (CLF), fixed‐time convergence of system outputs and the closed‐loop system stability have been established. The effectiveness of the proposed controller has been shown via simulation study.

Implementing ultra-lightweight co-inference model in ubiquitous edge device for atrial fibrillation detection

Implementing internet of things technologies in health monitoring systems attracts a lot of attention. Running the model at edge can continuously and in real-time monitor the user’s physiological information, which can be adopted in universal medical care. However, this task is challenging and rarely discussed due to its limited computational capacities and storage resources. This work propose a novel framework for neural network training on resource-constrained embedded systems. Based on feature engineering, the lightweight neural network is implemented on embedded devices, including the training and testing. By losing some certainty, an ultra-lightweight model can be realized through parameter quantization to get further memory saving and reduce the storage burden of the device. The method is implemented and tested on a cheap AVR-based 8-bit micro-controller for atrial fibrillation detection from electrocardiogram (ECG) features. The results prove the feasibility of 100 samples training on-device with test performance comparable to models developed on a computer. The trained lightweight model can be compressed to about 0.3 of the original size with negligible rebuilt performance loss. It can be combined with wearable devices for chronic diseases and long-term monitoring.

Quantized control for finite-time synchronization of delayed fractional-order memristive neural networks: The Gronwall inequality approach

This paper is concerned with the finite-time synchronization (FTS) of delayed fractional-order memristive neural networks (FMNNs) by using quantized control. Firstly, two kinds of quantized controllers are designed to eliminate the residual synchronization errors that appear owing to the characteristics of memristive connection weights. Then, to derive α-dependent FTS criteria for drive–response FMNNs, the Gronwall inequality technique is used by combination with the direct estimation method. Compared with the existing results, the advantages of the derived synchronization criteria are discussed from the aspects of both theory and simulation. In addition, the relationships between the finite-time parameter and the quantization parameters are displayed. It reveals that there is a compromise between the admissible finite-time and the saved network bandwidth. Finally, two examples are given to illustrate the effectiveness of the obtained results.

Protocol-Based Control for Semi-Markov Jump Systems With Dynamic Quantization

This brief is devoted to protocol-based control method design for semi-Markov switching systems with dynamic quantization. Essential different from the semi-Markov process with arbitrary switchings, by proposing a novel semi-Markov process subjected to a deterministic switching signal, a generalized framework of semi-Markov switching systems is set up. With respect to the quantization range of the dynamic quantizer, an improved event-triggered protocol associated with the quantizer parameter is proposed. On account of mode-dependent Lyapunov theory, sufficient conditions are established to ensure the stochastic finite-time boundedness of the resulting system. In the end, a tunnel diode circuit model shows the practicability and effectiveness of the presented method.

Cooperative Constrained Control of Autonomous Vehicles With Nonuniform Input Quantization

Responsive and highly controlled autonomous vehicles (AVs) on the road easily form platoons with small inter-vehicle gaps to increase traffic throughput and reduce energy consumption. Unlike human drivers, AVs typically employ discrete quantization signals and only generate finite discrete acceleration. Finite discrete acceleration easily causes unstable inter-vehicle gaps and inter-vehicle collisions, especially when there are inaccurate quantization parameters due to quantizer aging. Based on the backstepping technique, this paper proposes the cooperative constrained control algorithm under unknown quantization parameters for AVs with nonuniform input quantization and motion uncertainties. The control laws of each AV in the platoon only depend on the state information of its consecutive AVs. The position trajectories of consecutive AVs are constructed as inter-vehicle collision-free constraints to avoid emergency braking and inter-vehicle collisions. In addition, the consistent characteristic of two types of nonuniform quantizers (i.e., logarithmic quantizers and hysteresis quantizers) is proposed, and unknown disturbances in vehicle motion are compensated. The Lyapunov based local stability and string stability are proved. Numerical simulation shows that the control algorithm is applicable to AVs with either logarithmic quantizers or hysteresis quantizers. Compared with the previous control algorithms without considering input quantization and inter-vehicle collision avoidance, the control algorithm proposed reduces inter-vehicle spacing errors, avoids high acceleration, and avoids inter-vehicle collisions.

Latency-Efficient Wireless Federated Learning With Quantization and Scheduling

Federated learning (FL) protects data privacy through local training and parameter aggregation. However, there is no need that all users are required to train their local models, and the parameter needs to be quantized via wireless channels in practice. In this letter, we investigate and analyze how to improve the model prediction accuracy with the system latency guarantee. Specifically, our goal is to minimize the loss function under the latency constraint by taking the parameter quantization, user scheduling, and channel bandwidth and transmit power into account. To make the optimization problem tractable, we first derive an upper bound on the loss function with joint quantization and scheduling and an upper bound on the number of bits for parameter aggregation, and then solve the reformulated problem based on the derived upper bounds to obtain closed-form expressions for the quantization level, the scheduling number, the optimized bandwidth and power allocation. Simulation results confirm the convergence and the effectiveness of the proposed algorithm.

Exploring Model Stability of Deep Neural Networks for Reliable RRAM-Based In-Memory Acceleration

RRAM-based in-memory computing (IMC) effectively accelerates deep neural networks (DNNs). Furthermore, model compression techniques, such as quantization and pruning, are necessary to improve algorithm mapping and hardware performance. However, in the presence of RRAM device variations, low-precision and sparse DNNs suffer from severe post-mapping accuracy loss. To address this, in this work, we investigate a new metric, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">model stability</i> , from the loss landscape to help shed light on accuracy loss under variations and model compression, which guides an algorithmic solution to maximize model stability and mitigate accuracy loss. Based on statistical data from a CMOS/RRAM 1T1R test chip at 65nm, we characterize wafer-level RRAM variations and develop a cross-layer benchmark tool that incorporates quantization, pruning, device variations, model stability, and IMC architecture parameters to assess post-mapping accuracy and hardware performance. Leveraging this tool, we show that a loss-landscape-based DNN model selection for stability effectively tolerates device variations and achieves a post-mapping accuracy higher than that with 50% lower RRAM variations. Moreover, we quantitatively interpret why model pruning increases the sensitivity to variations, while a lower-precision model has better tolerance to variations. Finally, we propose a novel variation-aware training method to improve model stability, in which there exists the most stable model for the best post-mapping accuracy of compressed DNNs. Experimental evaluation of the method shows up to 19%, 21%, and 11% post-mapping accuracy improvement for our 65nm RRAM device, across various precision and sparsity, on CIFAR-10, CIFAR-100, and SVHN datasets, respectively.

Quantized extended dissipative synchronization for semi-Markov switching Lur’e systems with time delay under deception attacks

This paper is dedicated to the quantized extended dissipative synchronization for time-delay Lur’e systems with semi-Markov jump parameters subject to deception attacks. Two types of dynamic quantizers are utilized to quantize the measurement output and the control input in the time-variant delay and time-invariant delay cases, respectively. By choosing a suitable Lyapunov–Krasovskii functional and applying several inequalities, a novel synchronization criterion is developed under which the resulting error system is stochastically stable and extended dissipative. Then, a joint design method is provided for the desired controller gain matrices and the dynamic quantizer parameters. Finally, the applicability of the designed approach is verified by three simulation examples.

A Novel Separable Scheme for Encryption and Reversible Data Hiding

With the increasing emphasis on security and privacy, video in the cloud sometimes needs to be stored and processed in an encrypted format. To facilitate the indexing and tampering detection of encrypted videos, data hiding is performed in encrypted videos. This paper proposes a novel separable scheme for encryption and reversible data hiding. In terms of encryption method, intra-prediction mode and motion vector difference are encrypted by XOR encryption, and quantized discrete cosine transform block is permutated based on logistic chaotic mapping. In terms of the reversible data hiding algorithm, difference expansion is applied in encrypted video for the first time in this paper. The encryption method and the data hiding algorithm are separable, and the embedded information can be accurately extracted in both encrypted video bitstream and decrypted video bitstream. The experimental results show that the proposed encryption method can resist sketch attack and has higher security than other schemes, keeping the bit rate unchanged. The embedding algorithm used in the proposed scheme can provide higher capacity in the video with lower quantization parameter and good visual quality of the labeled decrypted video, maintaining low bit rate variation. The video encryption and the reversible data hiding are separable and the scheme can be applied in more scenarios.

A quality enhancement network with coding priors for constant bit rate video coding

Video coding can effectively compress data, while the introduction of compression artifacts degrades the visual quality and the performance of artificial intelligence video applications. Video quality enhancement (VQE) methods can improve compressed video quality without modifying the coding standard’s main modules. The existing VQE works mainly aim to improve video quality in the constant quantization parameter (CQP) coding mode. However, constant bit rate (CBR) coding mode is widely used in some streaming playback video applications, and VQE at CBR is more challenging than that at CQP. This article presents a novel Constant bit rate Video quality enhancement Network combined with Coding priors (CVCN). The proposed CVCN can be inserted into High Efficiency Video Coding (HEVC) codec as a CNN-based in-loop filter (LF) module or a post-processing module out of the codec. Moreover, we design a two-pass training strategy for the LF module to overcome multiple filtering. To adapt the QP diversity of CBR videos, we utilize the coding unit (CU)-wise QP prior by constructing a CU-wise QP adaptive module (CQAM) and a QP adaptive multi-scale residual block (QAMSRB) based on CQAM. We construct the CU-partition prior (CPP) by exploiting the relationship between the compression noise and CU partition information. A novel CPP spatial-attention block is proposed to combine the CPP with the self-attention module. Furthermore, the proposed CVCN can effectively enhance CBR videos at different bits per pixel (BPP) via a single model. Extensive experimental results show the superiority of the CVCN over state-of-the-art VQE approaches for CBR videos.

Multiple hierarchical compression for deep neural network toward intelligent bearing fault diagnosis

Deep Neural Network (DNN) models have been extensively developed for intelligent bearing fault diagnosis. The superior performance of DNN-based fault diagnosis methods is attributed to the deepening network structure, which increases the complexity of the deep models and causes difficulties to deploy them in industrial environments with constrained resources. To address the problems, this paper proposes a multi-hierarchical compression to compact the deep neural network for intelligent fault diagnosis. It combines network pruning, parameter quantization, and matrix compression to process the deep model from different perspectives, which achieves a considerable reduction of parameter volume and acceleration of training and response. Firstly, structured pruning is employed to prune the inconsequential filters in the convolutional layer, and unstructured pruning is utilized to eliminate the trivial connections in the fully connected layer. Then, parameter quantization is applied to minimize the number of bits that are required for parameter representation. Finally, the matrix compression storage is taken advantage of to reduce the requirements of storage capacity and further alleviate the excessive demands for the monitoring system. Experimental results and comparisons on two bearing datasets validate the effectiveness of the proposed method. The results show that for two CNN networks with different depths, the integrated network compression method can achieve considerable reductions in the number of parameters and the floating-point operations while almost no decrease in recognition accuracy. The proposed method makes an inspiring exploration for the application of intelligent fault diagnosis in the practical industry.