The explosive growth of time series gives rise to a large amount of data, which emphasizes the importance of data compression. The data compression not only reduces storage costs but also enhances data transmission efficiency and processing speed. However, traditional compression algorithms usually suffer an insufficient compression ratio and an excessive computational cost. To address these problems above, in this paper, we propose a two-stage compression algorithm for the large-scale time series data. In the first stage, we transform the time series data into low-volatility residual data by using Autoregressive Integrated Moving Average (ARIMA) modeling and apply adaptive precision quantization to improve compressibility. In the second stage, we implement a reinforcement learning-based compression strategy, which utilizes the Q-learning to select the number of blocks to divide the quantized data segment and achieves compression by storing the same content between the divided data blocks only once and storing the different content separately; and we incorporate the Upper Confidence Bound (UCB) to balance exploration and exploitation in order to track changes in data patterns and improve compression performance. Experimental results demonstrate that our algorithm achieves a higher compression ratio while maintaining a low computational complexity compared with traditional compression algorithms.

A lightweight model for perceptual image compression via implicit priors.

Emerging large models have achieved notable progress in the fields of natural language processing and computer vision. However, large models for neural video coding are still unexplored. In this paper, we try to explore how to build a large neural video coding model. Based on a small baseline model, we gradually scale up the model sizes of its different coding parts, including the motion encoder-decoder, motion entropy model, contextual encoder-decoder, contextual entropy model, and temporal context mining module, and analyze the influence of model sizes on video compression performance. Then, we explore using different architectures, including CNN, mixed CNN-Transformer, and Transformer architectures, to implement the neural video coding model and analyze the influence of model architectures on video compression performance. Based on our exploration results, we design the first neural video coding model having more than 1 billion parameters - NVC-1B. Experimental results show that our large model achieves a significant video compression performance improvement over recent state-of-the-art neural video compression models. With the continuous advancement in hardware and the successful on-device deployment of large models, we anticipate that our proposed large neural video coding model can bring video coding technologies to the next level.

Braided GFRP sleeving reinforced parallel bamboo strand lumber columns: an efficient way to improve compression performance

With the rapid growth of data volume in sensor networks, lossy source coding systems achieve high-efficiency data compression with low distortion under limited transmission bandwidth. However, conventional compression algorithms rely on a two-stage framework with high computational complexity and frequently struggle to balance compression performance with generalization ability. To address these issues, an end-to-end lossy compression method is proposed in this paper. The approach integrates an enhanced belief propagation algorithm with a multi-layer perceptron neural network, aiming to introduce a novel joint optimization architecture described as "encoding-structured encoding-decoding". In addition, a quantization module incorporating random perturbation and the straight-through estimator is designed to address the non-differentiability in the quantization process. Simulation results demonstrate that the proposed system significantly improves compression performance while offering superior generalization and reconstruction quality. Furthermore, the designed neural architecture is both simple and efficient, reducing system complexity and enhancing feasibility for practical deployment.

Electrocardiogram (ECG) signals are frequently acquired nowadays to detect various heart diseases. Nowadays, IoT-enabled wearable devices are in demand for distant or telemedicine-based healthcare applications. However, the acquisition process of ECG signals generates a huge amount of data, which negatively impacts the storage and transmission efficiency of these devices. As a result, an efficient compression algorithm is needed for effective ECG data management. Therefore, a compression algorithm for 2D ECG signals is proposed that employs the 1D Cohen-Daubechies-Feauveau 9/7 wavelet transform on 2D ECG signals. The proposed method effectively improves compression performance by increasing sparsity among the transform coefficients. Following that, obtained coefficients are quantized, and significant ones are retained using the target-based reconstruction error. The adaptive Huffman encoding is used to further enhance the compression once the quantized coefficients have been encoded. The experimental work is tested on MIT-BIH arrhythmia database, and the effect of different anomalies on compression performance is also assessed. The compression efficacy is evaluated in comparison to existing compression methods, and other wavelet transforms such as sym2, sym4, haar, db5, coif4, and beta wavelets. The proposed algorithm's performance is assessed in terms of quality score, percent root-mean-square difference, signal-to-noise ratio, and compression ratio. These factors were averaged out to get values of 30.23, 5.07, 26.78dB, and 7.21, respectively. Results are evident that the proposed method can significantly improve storage efficiency and may also improve bandwidth utilization during real-time data transfer.

While pruning methods effectively maintain model performance without extra training costs, they often focus solely on preserving crucial connections, overlooking the impact of pruned weights on subsequent fine-tuning or distillation, leading to inefficiencies. Moreover, most compression techniques for generative models have been developed primarily for GANs, tailored to specific architectures like StyleGAN, and research into compressing Diffusion models has just begun. Even more, these methods are often applicable only to GANs or Diffusion models, highlighting the need for approaches that work across both model types. In this paper, we introduce Singular Value Scaling (SVS), a versatile technique for refining pruned weights, applicable to both model types. Our analysis reveals that pruned weights often exhibit dominant singular vectors, hindering fine-tuning efficiency and leading to suboptimal performance compared to random initialization. Our method enhances weight initialization by minimizing the disparities between singular values of pruned weights, thereby improving the fine-tuning process. This approach not only guides the compressed model toward superior solutions but also significantly speeds up fine-tuning. Extensive experiments on StyleGAN2, StyleGAN3 and DDPM demonstrate that SVS improves compression performance across model types without additional training costs.

High-efficiency Video Coding (HEVC) is a widely used video coding standard, and it has recently gained widespread adoption in various applications, such as video streaming, broadcasting, real-time conferencing, and storage. The adoption of Generative Adversarial Networks (GANs) into HEVC compression has shown significant improvements in compression performance by reducing the video size while maintaining the original quality. In this work, we explore the application of Knowledge Distillation to reduce the energy consumption associated with GAN-based HEVC. By training a smaller student model that imitates the larger teacher model's behavior, we significantly improved energy efficiency. In this paper, we provide a detailed study comparing the traditional HEVC algorithm, GAN-based HEVC, and GAN-based HEVC with Knowledge Distillation. The experimental results demonstrate a reduction in energy consumption of up to 30% while preserving video quality, making it an effective solution for video streaming platforms and energy-constrained devices and a sustainable solution for video compression without diminishing video quality.

In medicine, high-quality images are crucial for accurate clinical diagnosis, making lossless compression essential to preserve image integrity. Neural networks, with their powerful probabilistic estimation capabilities, seamlessly integrate with entropy encoders to achieve lossless compression. Recent studies have demonstrated that this approach outperforms traditional compression algorithms. However, existing methods have yet to adequately address the issue of inaccurate probabilistic estimation by neural networks when processing edge or complex textured regions. This limitation leaves significant room for improvement in compression performance. To address these challenges, this study proposes a novel lossless image compression method that employs a flexible tree-structured image segmentation mechanism. Due to the close relationships between subimages, this mechanism allows neural networks to fully exploit the prior knowledge of encoded subimages, thereby improving the accuracy of probabilistic estimation in complex textured regions of unencoded subimages. In terms of network architecture, we have introduced an attention mechanism into the UNet network to enhance the accuracy of probabilistic estimation across the entire subimage regions. Additionally, the flexible tree-structured image segmentation mechanism enabled us to implement variable-speed compression. We provide benchmarks for both fast and slow compression modes. Experimental results indicate that the proposed method achieves state-of-the-art compression speed in the fast mode. In the slow mode, it attains state-of-the-art performance.

Video Coding for Machines (VCM) aims to compress visual signals for machine analysis. However, existing methods only consider a few machines, neglecting the majority. Moreover, the machine's perceptual characteristics are not leveraged effectively, resulting in suboptimal compression efficiency. To overcome these limitations, this paper introduces Satisfied Machine Ratio (SMR), a metric that statistically evaluates the perceptual quality of compressed images and videos for machines by aggregating satisfaction scores from them. Each score is derived from machine perceptual differences between original and compressed images. Targeting image classification and object detection tasks, we build two representative machine libraries for SMR annotation and create a large-scale SMR dataset to facilitate SMR studies. We then propose an SMR prediction model based on the correlation between deep feature differences and SMR. Furthermore, we introduce an auxiliary task to increase the prediction accuracy by predicting the SMR difference between two images in different quality. Extensive experiments demonstrate that SMR models significantly improve compression performance for machines and exhibit robust generalizability on unseen machines, codecs, datasets, and frame types.

Bioresorbable stents (BRSs) offer significant advantages in treating congenital heart disease-related vascular stenoses, especially for pediatric patients. However, the insufficient mechanical performance of polymeric BRSs remains a critical challenge. In this study, Poly(p-dioxanone) (PPDO) was incorporated with graphene oxide (GO) for the first time to improve both mechanical properties and biocompatibility. PPDO/GO composites with varying GO contents were fabricated via solution mixing and solvent casting, and tensile tests revealed that lower GO content levels (0.2% and 0.5%) significantly improved the Young’s modulus, tensile strength, and elongation at break of PPDO due to hydrogen bonding and increased degree of crystallinity. 3D-printed PPDO/GO sliding-lock stents with optimal GO contents were fabricated by fused deposition modeling and demonstrated superior compression force compared to pristine PPDO stents. In vitro hemocompatibility and cytocompatibility assessments showed that 3D-printed PPDO/GO stents exhibited low hemolysis rate, reduced platelet adhesion, and enhanced adhesion and proliferation of endothelial cells. In vivo evaluation further demonstrated improved endothelialization in rat abdominal aortas implanted with 3D-printed PPDO/GO filaments for 4 weeks. Overall, PPDO/0.5%GO exhibited superior performance in compression force, hemocompatibility, cytocompatibility, and in vivo endothelialization. This study, for the first time, combines PPDO with GO and explains the mechanism of the enhanced mechanical properties of PPDO/GO composite material. Using 3D printing, PPDO/GO BRS with improved compression performance and biocompatibility were developed, highlighting its potential value for treating pediatric patients with CHD-related vascular stenoses.

Learned video compression has drawn great attention and shown promising compression performance recently. In this article, we focus on the two components in the learned video compression framework, the conditional entropy model and quality enhancement module, to improve compression performance. Specifically, we propose an adaptive spatial-temporal entropy model for image, motion, and residual compression, which introduces a temporal prior to reduce temporal redundancy of latents and an additional modulated mask to evaluate the similarity and perform refinement. In addition, a quality enhancement module is proposed for predicted frame and reconstructed frame to improve frame quality and reduce the bitrate cost of residual coding. The module reuses decoded optical flow as a motion prior and utilizes deformable convolution to mine high-quality information from the reference frame in a bit-free manner. The two proposed coding tools are integrated into a pixel-domain residual coding–based compression framework to evaluate their effectiveness. Experimental results demonstrate that our framework achieves competitive compression performance in the low-delay scenario compared with recent learning-based methods and traditional H.265/HEVC in terms of Peak Signal-to-Noise Ratio (PSNR) and Multi-Scale Structural Similarity Index (MS-SSIM). The code is available at OpenLVC.

Preparation of tomato peel pomace powder/polylactic acid foams under supercritical CO2 conditions: Improvements in cell structure and foaming behavior

Recently, end-to-end light field image compression methods have been explored to improve compression efficiency. However, these methods have difficulty in efficiently utilizing multi-domain features and their correlation, resulting in limited improvement in compression performance. To address this problem, a novel multi-domain feature learning-based light field image compression network (MFLFIC-Net) is proposed to improve compression efficiency. Specifically, an EPI-based angle completion module (E-ACM) is developed to obtain a complete angle feature by fully exploring the angle information with a large disparity contained in the epipolar plane image (EPI) domain. Furthermore, in order to effectively reduce redundant information in the light field image, a spatial-angle joint transform module (SAJTM) is proposed to reduce redundancy by modeling the intrinsic correlation between spatial and angle features. Experimental results demonstrate that MFLFIC-Net achieves superior performance on MS-SSIM and PSNR metrics compared to public state-of-the-art methods.

Traditional block-based spatially scalable video coding has been studied for over twenty years. While significant advancements have been made, the scope for further improvement in compression performance is limited. Inspired by the success of learned video coding, we propose an end-to-end learned spatially scalable video coding scheme, LSSVC, which provides a new solution for scalable video coding. In LSSVC, we propose to use the motion, texture, and latent information of the base layer (BL) as interlayer information for compressing the enhancement layer (EL). To reduce interlayer redundancy, we design three modules to leverage the upsampled interlayer information. Firstly, we design a contextual motion vector (MV) encoder-decoder, which utilizes the upsampled BL motion information to help compress high-resolution MV. Secondly, we design a hybrid temporal-layer context mining module to learn more accurate contexts from the EL temporal features and the upsampled BL texture information. Thirdly, we use the upsampled BL latent information as an interlayer prior for the entropy model to estimate more accurate probability distribution parameters for the high-resolution latents. Experimental results show that our scheme surpasses H.265/SHVC reference software by a large margin. Our code is available at https://github.com/EsakaK/LSSVC.

Remote sensing image compression networks aim to enhance the similarity between the input image and the reconstructed image. The current network rarely considers the potential relationship between the compression features of different levels and the reconstruction features of the corresponding levels, which limits the improvement of remote sensing image compression performance. In this article, a concept of multilevel domain similarity is first proposed, which fully develops the multilevel domain similarity between the encoding and decoding processes to improve the quality of reconstructed images. On this basis, a multilevel domain similarity enhancement guided network (MDSNet) is proposed for remote sensing image compression. First, an efficient compression baseline network (BaselineA) was proposed, which realizes efficient image compression with low computational complexity. Second, a multilevel domain similarity enhancement module (MDEM) was designed, which improved the quality of the reconstructed image by enhancing the multilevel domain similarity. Third, a global information-enhanced attention module (GIE-AM) was constructed to enhance channel features and global features. Finally, under the guidance of the total loss (LossTotal), which is constructed by the proposed MDEM loss (MDEM-Loss), an effective compression was implemented by the whole network for remote sensing image compression. Experimental results show that compared with some advanced compression models, the proposed MDSNet can significantly improve compression performance with lower computational complexity. In addition, the reconstructed images obtained by the proposed method can provide better classification performance, which further proves that the proposed MDSNet helps to preserve more important features of remote sensing images during the compression process.

ObjectiveTo improve breast radiographers’ individual performance by using automated software to assess the correctness of breast positioning and compression in tomosynthesis screening.Materials and methodsIn this retrospective longitudinal analysis of prospective cohorts, six breast radiographers with varying experience in the field were asked to use automated software to improve their performance in breast compression and positioning. The software tool automatically analyzes craniocaudal (CC) and mediolateral oblique (MLO) views for their positioning quality by scoring them according to PGMI classifications (perfect, good, moderate, inadequate) and checking whether the compression pressure is within the target range. The positioning and compression data from the studies acquired before the start of the project were used as individual baselines, while the data obtained after the training were used to test whether conscious use of the software could help the radiographers improve their performance. The percentage of views rated perfect or good and the percentage of views in target compression were used as overall metrics to assess changes in performance.ResultsFollowing the use of the software, all radiographers significantly increased the percentage of images rated as perfect or good in both CCs and MLOs. Individual improvements ranged from 7 to 14% for CC and 10 to 16% for MLO views. Moreover, most radiographers exhibited improved compression performance in CCs, with improvements up to 16%.ConclusionActive use of a software tool to automatically assess the correctness of breast compression and positioning in breast cancer screening can improve the performance of radiographers.Clinical relevance statementThis study suggests that the use of a software tool for automatically evaluating correctness of breast compression and positioning in breast cancer screening can improve the performance of radiographers on these metrics, which may ultimately lead to improved screening outcomes.Key Points• Proper breast positioning and compression are critical in breast cancer screening to ensure accurate diagnosis.• Active use of the software increased the quality of craniocaudal and mediolateral oblique views acquired by all radiographers.• Improved performance of radiographers is expected to improve screening outcomes.

Application of composite helical springs (CHSs) is constrained by their poor static compression performance. In this study, a novel composite helical spring with a braided nested structure (BNCHS) is proposed. The fiber volume fraction (Vf) of BNCHS with braided angle of 15° and 30° (BNCHS15° and BNCHS30°) only increases by 0.9% and 1.8% respectively comparing with that of unidirectional composite helical spring with Vf of 55% (UCHS55%). The compression experimental results show that the spring constant of BNCHS15° and BNCHS30° can reach 105.4% and 171.4% higher than that of UCHS55% respectively. The internal mechanism of significantly improving compression performance of BNCHS is revealed by using a meso model. Numerical result shows that the mises stress of BNCHS15° and BNCHS30° can be 2.43 and 3.14 times higher than that of UCHS55% respectively. Finally, the resilience and specific spring stiffness of BNCHS and steel are compared, highlighting the obvious advantage of static performance of BNCHS.

Deep convolutional neural networks (CNNs) generate intensive inter-layer data during inference, which results in substantial on- chip memory size and off-chip bandwidth. To solve the memory constraint, this paper proposes an accelerator adopting a compression technique that can reduce the inter-layer data by removing both intra- and inter-channel redundant information. Principal component analysis (PCA) is utilized in the compression process to concentrate inter-channel information. The spatial differences, truncation, and reconfigurable bit-width coding are implemented inside every feature map to eliminate the intra-channel data redundancy. Moreover, a particular data arrangement is introduced to enhance data continuity to optimize PCA analysis and improve compression performance. A CNN accelerator with the proposed compression technique is designed to support the on- the-fly compression process by pipelining the reconstruction, CNN computation, and compression operation. The prototype accelerator is implemented using 28-nm CMOS technology. It achieves 819.2GOPS peak throughput and 3.75TOPS/W energy efficiency with 218.5mW. Experiments show that the proposed compression technique achieves compression ratios of 21.5% <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\sim $ </tex-math></inline-formula> 43.0% (8-bit mode) and 9.8% <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\sim $ </tex-math></inline-formula> 19.3% (16-bit mode) on state-of-the-art CNNs with a negligible accuracy loss.

Image privacy protection and management face many challenges, such as privacy disclosure, copyright dispute, and traceability difficulties, with the development of big data. Reversible data hiding in encrypted images (RDHEI) has been widely considered as an effective means to tackle these challenges. In this paper, a RDHEI based on time-varying Huffman coding table (TV-HCT) method is proposed to improve the security, embedding rate (ER) and efficiency. First, the initial HCT is generated according to the prediction errors of an image, which can improve compression performance. And then, the TV-HCT is obtained by scrambling equal-length codewords in the initial HCT using timestamps. This realizes the time variability of compression coding stream (CCS) of an image in that the image TV-HCT has large change space. Analysis shows that the average change space of TV-HCT in UCID is 3.97×10 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">327</sup> , and the average ER of three databases is more than 0.44 bpp higher than the existing algorithms. Finally, the CCS is encrypted using the designed index class scrambling method to balance complexity and security. The proposed method not only strengthens the security against brute force attack and differential attack, but also improves ER and efficiency of the RDHEI technique. Experimental results and performance analysis demonstrate that the proposed algorithm outperforms the state-of-the-art RDHEI algorithms in terms of the security, ER and complexity.