检索结果-内蒙古大学图书馆

Fixed-Quality Compression of Remote Sensing images With neural networks

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2024年 17卷 12169-12180页

作者： Mijares i Verdu, Sebastia Chabert, Marie Oberlin, Thomas Serra-Sagrista, Joan Univ Autnoma Barcelona Dept Informat & Commun Engn Cerdanyola Valls 08193 Spain Univ Toulouse IRIT INP ENSEEIHT F-31071 Toulouse France Univ Toulouse Federat ENAC ISAE SUPAERO ONERA F-31055 Toulouse France

Fixed-quality image compression is a coding paradigm where the tolerated introduced distortion is set by the user. This article proposes a novel fixed-quality compression method for remote sensing images. It is based on a neural architecture we have recently proposed for multirate satellite image compression. In this article, we show how to efficiently estimate the reconstruction quality using an appropriate statistical model. The performance of our approach is assessed and compared against recent fixed-quality coding techniques and standards in terms of accuracy and rate-distortion, as well as with recent machine learning compression methods in rate-distortion, showing competitive results. In particular, the proposed method does not introduce artifacts even when coding neighboring areas at different qualities.

关键词： Data compression neural network applications neural networks optical data processing remote sensing Data compression neural network applications neural networks optical data processing remote sensing

来源：评论

学校读者我要写书评

暂无评论

Joint Exit Selection and Offloading Decision for applications Based on Deep neural networks

引用

IEEE INTERNET OF THINGS JOURNAL 2024年第23期11卷 38098-38112页

作者： Narmeen, Ramsha Mach, Pavel Becvar, Zdenek Ahmad, Ishtiaq Czech Tech Univ Fac Elect Engn Prague 16627 Czech Republic

User applications based on the deep neural networks (DNNs), such as object or anomaly detection, image recognition, or language processing, running on computation- and energy-constrained user equipment (UE) can be partially or fully processed in the edge computing servers to reduce a processing time and save an energy in the UE. To further reduce the processing time and the UE's energy consumption, DNN with multiple exit points can be incorporated. In this article, we address the problem of the decision on whether the computation should be offloaded from the UE to the edge computing server or processed locally by the UE and we solve this problem jointly and "on-the-fly" together with DNN exit selection. Since the formulated problem is very complex, we exploit the deep deterministic policy gradient for the exit selection and the offloading decisions (labeled DDPG-EOD) for the DNN-based applications. To this end, we first convert the problem into the Markov decision process, and then, we employ an end-to-end learning via DDPG with the actor-critic architecture. Second, we use a knowledge distillation-based technique to efficiently select the DNN's exit to minimize the delay and energy consumption. Simulation results show that the proposal is highly scalable, converges very quickly, and surpasses the best performing state-of-the-art approach by up to 120% and 100% in terms of the overall DNN processing delay and the energy consumption, respectively.

关键词： Delays Task analysis Servers artificial neural networks Computer architecture Accuracy Energy consumption Deep neural network (DNN) delay edge computing energy exit selection offloading

来源：评论

学校读者我要写书评

暂无评论

Robust pattern retrieval in an optical Hopfield neural network

引用

OPTICS LETTERS 2025年第1期50卷 225-228页

作者： Katidis, Michael Musa, Khalid Kumar, Santosh Li, Zhaotong Long, Frederick Qu, Chunlei Huang, Yu-ping Stevens Inst Technol Dept Phys Hoboken NJ 07030 USA Stevens Inst Technol Ctr Quantum Sci & Engn Hoboken NJ 07030 USA US Army DEVCOM Armaments Ctr Picatinny Arsenal NJ 07806 USA

Hopfield neural networks (HNNs) promise broad applications in areas such as combinatorial optimization, memory storage, and pattern recognition. Among various implementations, optical HNNs are particularly interesting because they can take advantage of fast optical matrix-vector multiplications. Yet their studies so far have mostly been on the theoretical side, and the effects of optical imperfections and robustness against memory errors remain to be quantified. Here we demonstrate an optical HNN in a simple experimental setup using a spatial light modulator with 100 neurons. It successfully stores and retrieves 13 patterns, which approaches the critical capacity limit of alpha c = 0.138. It is robust against random phase flipping errors of the stored patterns, achieving high fidelity in recognizing and storing patterns even when 30% pixels are randomly flipped. Our results highlight the potential of optical HNNs in practical applications such as real-time image processing for autonomous driving, enhanced AI with fast memory retrieval, and other scenarios requiring efficient data processing. (c) 2024 Optica Publishing Group. All rights, including for text and data mining (TDM), artificial Intelligence (AI) training, and similar technologies, are reserved.

关键词： image processing neural networks Optical neural systems Pattern recognition Real time imaging Spatial light modulators

来源：评论

学校读者我要写书评

暂无评论

Accelerating Convolutional processing by Harnessing Channel Shifts in Arrayed Waveguide Gratings

引用

LASER & PHOTONICS REVIEWS 2025年第1期19卷

作者： Yi, Dan Zhao, Caiyue Zhang, Zunyue Xu, Hongnan Tsang, Hon Ki Chinese Univ Hong Kong Dept Elect Engn Shatin Hong Kong Peoples R China Tianjin Univ Sch Precis Instrument & Optoelect Engn Tianjin 300072 Peoples R China

Convolutional neural networks are a powerful category of artificial neural networks that can extract features from raw data to provide greatly reduced parametric complexity and enhance pattern recognition and the accuracy of prediction. Optical neural networks offer the promise of dramatically accelerating computing speed while maintaining low power consumption even when using high-speed data streams running at hundreds of gigabit/s. Here, we propose an optical convolutional processor (CP) that leverages the spectral response of an arrayed waveguide grating (AWG) to enhance convolution speed by eliminating the need for repetitive element-wise multiplication. Our design features a balanced AWG configuration, enabling both positive and negative weightings essential for convolutional kernels. A proof-of-concept demonstration of an 8-bit resolution processor is experimentally implemented using a pair of AWGs with a broadband Mach-Zehnder interferometer (MZI) designed to achieve uniform weighting across the whole spectrum. Experimental results demonstrate the CP's effectiveness in edge detection and achieved 96% accuracy in a convolutional neural network for MNIST recognition. This approach can be extended to other common operations, such as pooling and deconvolution in Generative Adversarial networks. It is also scalable to more complex networks, making it suitable for applications like autonomous vehicles and real-time video recognition. A novel convolutional processor is proposed using the shifted spectral response of a pair of arrayed waveguide gratings (AWGs) to mimic the kernel shifts during image convolution. This inherent mixing of inputs in the AWG's spectral response eliminates the need for repetitive element-wise computations while enabling the simultaneous generation of convolved output maps. image

关键词： array waveguide grating convolutional processor deep learning image processing optical computing

来源：评论

学校读者我要写书评

暂无评论

applications of Pruning Methods in Natural Language processing

引用

IEEE ACCESS 2024年 12卷 89418-89438页

作者： Touheed, Marva Zubair, Urooj Sabir, Dilshad Hassan, Ali Butt, Muhammad Fasih Uddin Riaz, Farhan Abdul, Wadood Ayub, Rashid COMSATS Univ Islamabad Dept Elect & Comp Engn Islamabad 45550 Pakistan Natl Univ Sci & Technol Coll Elect & Mech Engn Dept Comp & Software Engn Islamabad 44000 Pakistan COMSATS Univ Islamabad Next Generat Commun Res Grp Islamabad 45550 Pakistan Univ Lincoln Coll Hlth & Sci Sch Comp Sci Lincoln LN6 7DL England King Saud Univ Coll Comp & Informat Sci Dept Comp Engn Riyadh 11543 Saudi Arabia King Saud Univ Coll Comp & Informat Sci Dept Sci Technol & Innovat Riyadh 11543 Saudi Arabia

Deep neural networks (DNN) are in high demand because of their widespread applications in natural language processing, image processing, and a lot of other domains. However, due to their computational expense, over-parameterization, and large memory requirements, DNN applications often require the use of substantial model resources. This strict requirement of latency and limited memory availability are hurdles in the device deployment of these technologies. Therefore, a common idea could be to mitigate the DNN-based models' size without any performance degradation using different compression techniques. During the last few years, a great deal of progress has been made in the field of Natural Language processing (NLP) using deep learning approaches. The objective of this research is to offer a thorough overview of the various pruning methods applied in the context of NLP. In this paper, we review several recent pruning-based schemes used for converting standard networks into their compact and accelerated versions. Traditionally, pruning is a technique for improving latency, reducing model size, and computational complexity which is a viable approach to deal with the above-mentioned challenges. In general, these techniques are divided into two main categories: structural and unstructured pruning methods. Structural pruning methods are further classified into filter, channel, layer, block, and movement pruning. Whereas, neuron, magnitude-based, and iterative pruning lie in the category of unstructured pruning. For each method, we discuss the related metrics and benchmarks. Then recent work on each method is discussed in detail, which provides insightful analysis of the performance, related applications, and pros and cons. Then, a comparative analysis is provided to analyze the differences among approaches. Finally, the paper concludes with possible future directions and some technical challenges.

关键词： Computational modeling Data models Task analysis neural networks Training Sentiment analysis Natural language processing Convolutional neural networks artificial neural networks Pruning convolution neural networks natural language processing DNN model compression acceleration

来源：评论

学校读者我要写书评

暂无评论

DiffStyler: Controllable Dual Diffusion for Text-Driven image Stylization

引用

IEEE TRANSACTIONS ON neural networks AND LEARNING SYSTEMS 2025年第2期36卷 3370-3383页

作者： Huang, Nisha Zhang, Yuxin Tang, Fan Ma, Chongyang Huang, Haibin Dong, Weiming Xu, Changsheng Chinese Acad Sci Inst Automat State Key Lab Multimodal Artificial Intelligence Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 100049 Peoples R China Chinese Acad Sci Inst Comp Technol Beijing 100190 Peoples R China Kuaishou Technol Beijing 100085 Peoples R China

Despite the impressive results of arbitrary image-guided style transfer methods, text-driven image stylization has recently been proposed for transferring a natural image into a stylized one according to textual descriptions of the target style provided by the user. Unlike the previous image-to-image transfer approaches, text-guided stylization progress provides users with a more precise and intuitive way to express the desired style. However, the huge discrepancy between cross-modal inputs/outputs makes it challenging to conduct text-driven image stylization in a typical feed-forward CNN pipeline. In this article, we present DiffStyler, a dual diffusion processing architecture to control the balance between the content and style of the diffused results. The cross-modal style information can be easily integrated as guidance during the diffusion process step-by-step. Furthermore, we propose a content image-based learnable noise on which the reverse denoising process is based, enabling the stylization results to better preserve the structure information of the content image. We validate the proposed DiffStyler beyond the baseline methods through extensive qualitative and quantitative experiments. The code is available at https://***/haha-lisa/Diffstyler.

关键词： Arbitrary image stylization diffusion textual guidance neural network applications

来源：评论

学校读者我要写书评

暂无评论

A hardware accelerator to support deep learning processor units in real-time image processing

引用

ENGINEERING applications OF artificial INTELLIGENCE 2025年 145卷

作者： Cittadini, Edoardo Marinoni, Mauro Buttazzo, Giorgio Scuola Super Sant Anna Pisa Italy

Deep neural networks are becoming crucial in many cyber-physical systems involving complex perceptual tasks. For those embedded systems requiring real-time interactions with dynamic environments, as autonomous robots and drones, it is of paramount importance that such algorithms are efficiently executed onboard on properly designed hardware accelerators to meet the required performance specifications. In particular, some neural network architectures for object detection and tracking, as You Only Look Once (YOLO), include heavy computational stages that need to be executed before and after the model inference. Such stages are typically not incorporated in traditional accelerators and are executed on general-purpose processors, thus introducing a bottleneck in the overall processing pipeline. To overcome such a problem, this paper presents a generalpurpose accelerator on a field-programmable gate array (FPGA) able to run pre-processing and post-processing operations typically required by vision tasks. The proposed solution has been tested in combination with a YOLO object detector accelerated on an Advanced Micro Devices (AMD) Xilinx Kria KR260 board mounting an UltraScale+ multiprocessor system-on-chip, achieving a significant improvement in terms of both timing performance and power consumption, and enabling onboard visual processing into drones. The proposed solution is able to boost the traditional object detection process by a factor of 4.4, allowing the execution of the full processing pipeline at 60 frames per second (fps), versus 13.6 fps reachable without the proposed accelerator. Asa result, this work enables the use of high-speed cameras for developing more reactive systems that can respond to incoming events with lower latency.

关键词： Hardware acceleration Object detection Deep neural networks Real-time processing image pre-processing acceleration Deep processing unit

来源：评论

学校读者我要写书评

暂无评论

Advanced deep learning algorithms in oral cancer detection: Techniques and applications

引用

JOURNAL OF ENVIRONMENTAL SCIENCE AND HEALTH PART C-TOXICOLOGY AND CARCINOGENESIS 2025年第2期43卷 133-158页

作者： Wankhade, Dipali Dhawale, Chitra Meshram, Mrunal Datta Meghe Inst Higher Educ & Res Wardha Nagpur Nagpur India Datta Meghe Inst Higher Educ & Res Deemed Univ Fac Sci & Technol Wardha India Sharad Pawar Dent Collage Dept Oral Med & Radiol Wardha India

As the 16th most common cancer globally, oral cancer yearly accounts for some 355,000 new cases. This study underlines that an early diagnosis can improve the prognosis and cut down on mortality. It discloses a multifaceted approach to the detection of oral cancer, including clinical examination, biopsies, imaging techniques, and the incorporation of artificial intelligence and deep learning methods. This study is distinctive in that it provides a thorough analysis of the most recent AI-based methods for detecting oral cancer, including deep learning models and machine learning algorithms that use convolutional neural networks. By improving the precision and effectiveness of cancer cell detection, these models eventually make early diagnosis and therapy possible. This study also discusses the importance of techniques in image pre-processing and segmentation in improving image quality and feature extraction, an essential component of accurate diagnosis. These techniques have shown promising results, with classification accuracies reaching up to 97.66% in some models. Integrating the conventional methods with the cutting-edge AI technologies, this study seeks to advance early diagnosis of oral cancer, thus enhancing patient outcomes and cutting down on the burden this disease is imposing on healthcare systems.

关键词： Oral cancer detection artificial intelligence deep learning convolutional neural networks machine learning early diagnosis medical imaging image processing oral squamous cell carcinoma predictive modeling

来源：评论

学校读者我要写书评

暂无评论

Estimating Water Levels through Smartphone-imaged Gauges: A Comparative Analysis of ANN, DL, and CNN Models

引用

WATER RESOURCES MANAGEMENT 2025年第4期39卷 1639-1654页

作者： Santos, Celso Augusto Guimaraes Ghorbani, Mohammad Ali Abdi, Erfan Patel, Utkarsh Sadeddin, Siria Univ Fed Paraiba Dept Civil & Environm Engn BR-58051900 Joao Pessoa PB Brazil Univ Tabriz Dept Water Engn Tabriz Iran Indian Inst Technol IIT Bhilai Main Campus Durg 491001 Chhattisgarh India Univ Nacl Colombia Math Dept Bogota Colombia

Understanding and monitoring water levels are essential for various applications, including environmental protection, public safety, and resource management. Water level estimation, a critical aspect of hydrological monitoring, is often constrained by challenges such as resource scarcity, high costs, and time-intensive processes. This research addresses these limitations by developing a machine learning-based system for automatic and real-time water level control. Specifically, it investigates the effectiveness of a non-contact, image-based water level measurement approach, leveraging recent advancements in mobile imaging technology. images were captured using a standard smartphone equipped with an RGB camera for water level analysis. Through precise image alignment processing under both clear and turbid conditions, the water's edge on a gauge was accurately detected. The study centers on the development and comparison of three computational models: artificial neural networks (ANN), Deep Learning (DL), and Convolutional neural networks (CNN). These models were trained to estimate water levels from processed image data. Results demonstrated varying levels of accuracy across models, with the CNN model outperforming others, achieving the lowest error rate of 24.36 mm and the highest correlation of 0.986. In contrast, the ANN model yielded the highest error rate at 30.76 mm and the lowest correlation of 0.968, highlighting the relative effectiveness of CNN in this application. Given the high accuracy (92.6%) of the image processing method and CNN model in detecting water surface edges and determining water levels, this system has substantial potential to enhance water resource management and control efficiency.

关键词： Computational Hydrology Convolutional neural networks Hydrological Monitoring image Analysis Non-contact Measurement

来源：评论

学校读者我要写书评

暂无评论

Improved spectral filtering of broadband diffractive neural network by loss function engineering

引用

APPLIED PHYSICS LETTERS 2025年第8期126卷

作者： Li, Bolin Luan, Guangrui Zhu, Yinfei Fei, Jinlei Gu, Min Lin, Jian Univ Shanghai Sci & Technol Sch Artificial Intelligence Sci & Technol Shanghai Peoples R China Univ Shanghai Sci & Technol Inst Photon Chips Shanghai Peoples R China

We engineer the loss function by removing the conventional physics-based energy constraint during the training of broadband diffractive neural networks (DNNs) to enhance their spectral filtering capabilities of supercontinuum light. Simulations show that compared to DNNs trained with conventional loss function, the suppression of out-of-band spectral intensities can be improved by three orders of magnitude, resulting in an extinction coefficient of 10(-6). Additionally, the spectral resolution can be enhanced by over 50% with a 6.6% improvement of energy efficiency. These findings are corroborated by experiments conducted with a two-layer DNN. The proposed method holds promise for enhancing the performance of broadband DNNs across various applications, including spectral reconstruction, spectrum classification, and color image processing, among others.

关键词： Color image processing

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：