检索结果-内蒙古大学图书馆

data compression for Advertising Billboards with Color Electronic Paper 11

Data Compression for Advertising Billboards with Color Elect...

11th ieee International conference on Consumer Electronics - Taiwan (ICCE-Taiwan) - Empower of Innovative Consumer Technology

作者： Kao, Wen-Chung Yu, Yu-Cheng Huang, Po-Han Cheng, Hsiang-Yuan Huang, Chiu-Kuei Natl Taiwan Normal Univ Taipei Taiwan

ISBN: (纸本)9798350386851;9798350386844

This paper discusses memory issues for advertising billboards with multi-pigment color electronic paper (e-paper). Enlarging the size of the electronic billboards increases the size of the memory buffer and flash memory used to store display content. Due to the specific display mechanism of the color e-paper, currently available image compression methods are not suitable for this specific application. An efficient image compression method for color e-paper with a low-cost decompression mechanism is presented in the paper. The display quality is good enough, and the total image buffer size could be significantly reduced.

关键词： Electronic paper

来源：评论

学校读者我要写书评

暂无评论

data compression Versus Signal Fidelity Tradeoff in Wired-OR Analog-to-Digital Compressive Arrays for Neural Recording

引用

ieee TRANSACTIONS ON BIOMEDICAL CIRCUITS AND SYSTEMS 2023年第4期17卷 754-767页

作者： Yan, Pumiao Akhoundi, Arash Shah, Nishal P. Tandon, Pulkit Muratore, Dante G. Chichilnisky, E. J. Murmann, Boris Stanford Univ Dept Elect Engn Stanford CA 94305 USA Delft Univ Technol Microelect Dept NL-2628 CD Delft Netherlands Stanford Univ Dept Neurosurg Stanford CA 94305 USA Stanford Univ Dept Neurosurg & Ophthalmol Hansen Expt Phys Lab Stanford CA 94305 USA

Future high-density and high channel count neural interfaces that enable simultaneous recording of tens of thousands of neurons will provide a gateway to study, restore and augment neural functions. However, building such technology within the bit-rate limit and power budget of a fully implantable device is challenging. The wired-OR compressive readout architecture addresses the data deluge challenge of a high channel count neural interface using lossy compression at the analog-to-digital interface. In this article, we assess the suitability of wired-OR for several steps that are important for neuroengineering, including spike detection, spike assignment and waveform estimation. For various wiring configurations of wired-OR and assumptions about the quality of the underlying signal, we characterize the trade-off between compression ratio and task-specific signal fidelity metrics. Using data from 18 large-scale microelectrode array recordings in macaque retina ex vivo, we find that for an event SNR of 7-10, wired-OR correctly detects and assigns at least 80% of the spikes with at least 50x compression. The wired-OR approach also robustly encodes action potential waveform information, enabling downstream processing such as cell-type classification. Finally, we show that by applying an LZ77-based lossless compressor (gzip) to the output of the wired-OR architecture, 1000x compression can be achieved over the baseline recordings.

关键词： A/D conversion analog-to-digital compression brain-machine interfaces compression algorithm neural interfaces

来源：评论

学校读者我要写书评

暂无评论

Impacts of Image compression on the Detection Quality of a Novel Real-Time Image Processing Platform 26

Impacts of Image Compression on the Detection Quality of a N...

引用

ieee 26th International conference on Intelligent Transportation Systems (ITSC)

作者： Mehrke, Jannik Volk, Georg Stumpp, Yannik Bringmann, Oliver Terzis, Anestis Ulm Univ Appl Sci Inst Commun Technol Ulm Germany Univ Tubingen Dept Comp Engn Tubingen Germany

ISBN: (纸本)9798350399462

Cloud-based data processing latency mainly depends on the transmission delay of data to the cloud and the used data processing algorithm. To minimize the transmission delay, it is important to compress the transferred data without reducing the quality of the data. When using data compression algorithms, it is important to validate the impact of these algorithms on the detection quality. This work evaluates the effects of image compression and transmission over wireless interfaces on state of the art neural networks. Therefore, a modern image processing platform for next generation automotive processing architectures, as used in software defined vehicles, is introduced. The impacts of different image encoders as well as data transmission parameters are investigated and discussed.

关键词： Image compression

来源：评论

学校读者我要写书评

暂无评论

GraVAC: Adaptive compression for Communication-Efficient Distributed DL Training 16

GraVAC: Adaptive Compression for Communication-Efficient Dis...

引用

ieee 16th International conference on Cloud Computing (ieee CLOUD)

作者： Tyagi, Sahil Swany, Martin Indiana Univ Bloomington IN 47405 USA

ISBN: (纸本)9798350304817

Distributed data-parallel (DDP) training improves overall application throughput as multiple devices train on a subset of data and aggregate updates to produce a globally shared model. The periodic synchronization at each iteration incurs considerable overhead, exacerbated by the increasing size and complexity of state-of-the-art neural networks. Although many gradient compression techniques propose to reduce communication cost, the ideal compression factor that leads to maximum speedup or minimum data exchange remains an open-ended problem since it varies with the quality of compression, model size and structure, hardware, network topology and bandwidth. We propose GraVAC, a framework to dynamically adjust compression factor throughout training by evaluating model progress and assessing gradient information loss associated with compression. GraVAC works in an online, black-box manner without any prior assumptions about a model or its hyperparameters, while achieving the same or better accuracy than dense SGD (i.e., no compression) in the same number of iterations/epochs. As opposed to using a static compression factor, GraVAC reduces end-to-end training time for ResNet101, VGG16 and LSTM by 4.32x, 1.95x and 6.67x respectively. Compared to other adaptive schemes, our framework provides 1.94x to 5.63x overall speedup.

关键词： deep learning data-parallel training gradient compression sparsification adaptive systems

来源：评论

学校读者我要写书评

暂无评论

Mixed-precision Deep Neural Network Quantization With Multiple compression Rates

Mixed-precision Deep Neural Network Quantization With Multip...

引用

data compression conference (DCC)

作者： Wang, Xuanda Fei, Wen Dai, Wenrui Li, Chenglin Zou, Junni Xiong, Hongkai Shanghai Jiao Tong Univ Sch Elect Informat & Elect Engn Shanghai 200240 Peoples R China

ISBN: (纸本)9798350347951

Quantizing one single deep neural network into multiple compression rates (precisions) has been recently considered for flexible deployments in real-world scenarios. In this paper, we propose a novel scheme that achieves progressive bit-width allocation and joint training to simultaneously optimize mixed-precision quantized networks under multiple compression rates. Specifically, we develop a progressive bit-width allocation with switchable quantization step size to enable mixed-precision quantization based on analytic sensitivity of network layers under multiple compression rates. Furthermore, we achieve joint training for quantized networks under different compression rates via knowledge distillation to exploit their correlations based on the shared network structure. Experimental results show that the proposed scheme outperforms AdaBits [1] in various networks on CIFAR-10 and ImageNet. © 2023 ieee.

关键词： deep neural network joint training multiple compression rates quantization

来源：评论

学校读者我要写书评

暂无评论

Agnostic Feature compression with Semantic Guided Channel Importance Analysis

Agnostic Feature Compression with Semantic Guided Channel Im...

引用

ieee International conference on Multimedia and Expo (ICME)

作者： Tang, Ying Yang, Wei Yu, Junqing Song, Zikai HUST Sch Comp Sci & Technol Wuhan Peoples R China

ISBN: (纸本)9798350390155;9798350390162

Distributing the computational workload of neural networks across cloud servers and local devices is an effective strategy for deploying resource-intensive deep models to edge devices. Therefore, compressing the deep features without compromising performance is crucial for saving server storage and transmission bandwidth. However, existing feature compression approaches are model or task specific and require training from scratch. In this paper, we propose a general and efficient framework for compressing deep features without requiring any prior knowledge of the semantics or task of the features. Our key observation is that different parts of the the feature map have different importance levels for a specific task. We can apply compression operation to a deeper degree for less irrelevant parts to achieve a high compression rate, while preserving the performance by applying a lower compression ratio to the more important parts. Focusing on this idea, we use the activation map generated by GradCAM [1] to classify each deep feature channel into essential and peripheral categories. To improve classification accuracy, we utilise semantic segmentations to provide natural boundaries for scoring each semantic channel. Peripheral channels are compressed using binary compression to achieve a high compression rate, while essential channels are compressed using mask compression. To effectively separate the essential and peripheral channels for a given input feature, we adopt a data-driven approach to identify the essential channels from datasets. Experimental results demonstrate that our method outperforms the state-of-the-art feature compression methods and is generalizable for various deep models.

关键词： Feature compression Semantic Analysis Deep Video Feature Understanding Collaborative Intelligence

来源：评论

学校读者我要写书评

暂无评论

Towards Analysis-aware EEG compression in Wearable Computing 19

Towards Analysis-aware EEG Compression in Wearable Computing

引用

ieee 19th International conference on Body Sensor Networks (ieee BSN)

ISBN: (纸本)9798350338416

EEG signals are known for their high temporal resolution and data volume, posing challenges in storage, transmission, and analysis. With the increasing prevalence of wearable mobile BCI devices replacing large medical-grade recording devices, the need for efficient on-device processing and wireless transmission has grown. We propose a novel analyzability-aware EEG compression scheme optimized for machine consumption, facilitating efficient, real-time wearable processing while allowing reconstruction for detailed analysis and human understanding. Our method employs a wavelet-based compression technique that considers the compression Factor, reconstruction error, and the impact of compression on on-device processing and data transmission. Experimental results using publicly available datasets demonstrate that machine learning models trained on compressed data using our method achieve performance comparable to the winning solution of BCI Competition II. Moreover, our approach offers multiple compression configurations suitable for various wearable computing scenarios.

关键词： EEG compression Analyzability Wearable Computing compression Domain Analysis

来源：评论

学校读者我要写书评

暂无评论

Key compression Limits for k-Minimum Value Sketches

Key Compression Limits for k-Minimum Value Sketches

引用

2024 ieee International conference on Big data, Bigdata 2024

作者： Dickens, Charlie Bax, Eric Saydakov, Alexander Yahoo! United States

ISBN: (纸本)9798350362480

The k-Minimum Values (KMV) data sketch algorithm stores the k least hash keys generated by hashing the items in a dataset. We show that compression based on ordering the keys and encoding successive differences can offer O(log n) bits per key in expected storage savings, where n is the number of unique values in the data set. We also show that O(log n) expected bits saved per key is optimal for any form of compression for the k least of n random values - that the encoding method is near-optimal among all methods to encode a KMVsketch. We present a practical method to perform that compression, show that it is computationally efficient, and demonstrate that its average savings in practice is within about five percent of the theoretical minimum based on entropy. We verify that our method outperforms off-the-shelf compression methods, and we demonstrate that it is practical, using real and synthetic data. © 2024 ieee.

关键词： Encoding (symbols)

来源：评论

学校读者我要写书评

暂无评论

SALIENCY-AWARE END-TO-END LEARNED VARIABLE-BITRATE 360-DEGREE IMAGE compression 31

SALIENCY-AWARE END-TO-END LEARNED VARIABLE-BITRATE 360-DEGRE...

引用

2024 International conference on Image Processing

作者： Gungordu, Oguzhan Tekalp, A. Murat Koc Univ Dept Elect & Elect Engn TR-34450 Istanbul Turkiye

ISBN: (纸本)9798350349405;9798350349399

Effective compression of 360 degrees images, also referred to as omnidirectional images (ODIs), is of high interest for various virtual reality (VR) and related applications. 2D image compression methods ignore the equator-biased nature of ODIs and fail to address oversampling near the poles, leading to inefficient compression when applied to ODI. We present a new learned saliency-aware 360 degrees image compression architecture that prioritizes bit allocation to more significant regions, considering the unique properties of ODIs. By assigning fewer bits to less important regions, significant data size reduction can be achieved while maintaining high visual quality in the significant regions. To the best of our knowledge, this is the first study that proposes an end-to-end variable-rate model to compress 360 degrees images leveraging saliency information. The results show significant bit-rate savings over the state-of-the-art learned and traditional ODI compression methods at similar perceptual visual quality. Supplementary materials are available at [Supplementary URL].

关键词： Virtual reality omnidirectional images saliency prediction end-to-end image compression variable-rate coding

来源：评论

学校读者我要写书评

暂无评论

Application of Lossless compression Method in Image compression 7

Application of Lossless Compression Method in Image Compress...

引用

7th ieee International conference on Information Systems and Computer Aided Education, ICISCAE 2024

作者： Ni, Weifeng Pu, Tianqiu Wang, Yuxi College of Information Science and Engineering Hohai University Changzhou China

ISBN: (纸本)9798350350760

—This paper is based on the application of lossless compression algorithms in image compression, aiming to solve problems such as insufficient storage space, low transmission efficiency, and heavy data processing burden. In order to optimize the image lossless compression algorithm, a combination of Huffman encoding and LZW compression algorithm is proposed. The implementation process and advantages and disadvantages of the two are compared, and the compression ratio and encoding efficiency of image lossless compression technology are discussed. We need to optimize decoding speed, image quality, and other aspects to improve overall image lossless compression capability. By applying Huffman encoding and LZW compression algorithms to images separately, the results show that Huffman encoding can dynamically construct the optimal encoding based on the frequency of characters appearing in image data, while LZW technology is good at utilizing repeated patterns and contextual information in image data to further improve compression efficiency by establishing dictionaries. The complementary advantages of the two can further improve the lossless compression ability of images. ©2024 ieee.

关键词： Image compression

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：