检索结果-内蒙古大学图书馆

Learned, uncertainty-driven adaptive acquisition for photon-efficient scanning microscopy

Optics Express 2025年第6期33卷 12269-12287页

作者： Ye, Cassandra Tong Han, Jiashu Liu, Kunzan Angelopoulos, Anastasios Griffith, Linda Monakhova, Kristina You, Sixian The Department of Electrical Engineering and Computer Science CambridgeMA02139 United States Fu Foundation School of Engineering and Applied Science Columbia University in The City of New York New YorkNY10027 United States University of California Berkeley Department of Electrical Engineering and Computer Science BerkeleyCA94720 United States Department of Biological Engineering Massachusetts Institute of Technology CambridgeMA02139 United States

Scanning microscopy systems, such as confocal and multiphoton microscopy, are powerful imaging tools for probing deep into biological tissue. However, scanning systems have an inherent trade-off between acquisition time, field of view, phototoxicity, and image quality. This often results in noisy measurements when fast, large field of view, and/or gentle imaging is needed. Deep learning could be used to denoise noisy microscopy measurements, but these algorithms can be prone to hallucination, which can be disastrous for medical and scientific applications. We propose a method to simultaneously denoise and predict pixel-wise uncertainty for scanning microscopy systems, improving algorithm trustworthiness and providing statistical guarantees for deep learning predictions. Furthermore, we propose to leverage this learned, pixel-wise uncertainty to drive an adaptive acquisition technique that rescans only the most uncertain regions of a sample, saving time and reducing the total light dose to the sample. We demonstrate our method on experimental confocal and multiphoton microscopy systems, showing that our uncertainty maps can pinpoint hallucinations in the deep learned predictions. Finally, with our adaptive acquisition technique, we demonstrate up to 16× reduction in acquisition time and total light dose while successfully recovering fine features in the sample and reducing hallucinations. We are the first to demonstrate distribution-free uncertainty quantification for a denoising task with real experimental data and the first to propose adaptive acquisition based on reconstruction uncertainty. © 2025 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Global Color-Aware Arbitrary Style Transfer with Discrete Wavelet Transform 20th

Global Color-Aware Arbitrary Style Transfer with Discrete W...

引用

20th IFIP WG 10.3 International Conference on Network and Parallel Computing, NPC 2024

作者： Chen, Bochao Tan, Junhao Li, Xiaoqiang Pei, Songwen School of Computer Engineering and Science Shanghai University Shanghai200444 China School of Optical-Electrical and Computer Engineering University of Shanghai for Science and Technology Shanghai200093 China

ISBN: (纸本)9789819628292

The purpose of image arbitrary style transfer is to apply a given artistic or photorealistic style to a target content image. While existing methods can effectively transfer style information, the variability in color brightness features between the style and content images can significantly impact the quality of the style transfer. Specifically, traditional arbitrary style transfer relies on an encoder-decoder architecture of spatial-aware neural networks operating in the RGB domain, which typically preserves only local color brightness information and lacks a global color perception compared to the wavelet frequency domain. In this paper, we address the issue of insufficient global color perception in images from the perspective of image enhancement. We propose Global Color-aware Arbitrary Style Transfer with Discrete Wavelet Transform (GCAST), which achieves a balance between the global color characteristics of style images and the local details of content images. Our approach involves an encoder that integrates preliminary feature encoding through cross-layer attention fusion, while the decoder modifies frequency features using a wavelet-based adjustment block. To maintain a balance between content and style in the stylized images, we design a comprehensive loss function that incorporates multiple restoration loss, double style loss, and noise regularization loss. Extensive experiments comparing our method with state-of-the-art techniques demonstrate that our proposed model generates stylized images with superior results in terms of global color perception and human perceptual studies. © IFIP International Federation for Information Processing 2025.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Solving dynamic optimization problems using parent–child multi-swarm clustered memory (PCSCM) algorithm

引用

Neural Computing and Applications 2024年第31期36卷 19549-19583页

作者： Mohammadpour, Majid Mostafavi, Seyedakbar Mirjalili, Seyedali Department of Computer Engineering Yazd University Yazd Iran Center for Artificial Intelligence Research and Optimization Torrens University Australia Brisbane Australia Faculty of Electrical Engineering and Computer Science VŠB-TU Ostrava Czech Republic

The Particle Swarm Optimization (PSO) algorithm faces several inherent challenges when applied to dynamic and large-scale optimization problems. These challenges encompass the issues of outdated particle memory, inadequate scalability in high-dimensional search spaces, the incapability to detect environmental changes, a continual trade-off between exploration and exploitation, and the potential loss of population diversity within the problem space. To address these challenges, we propose a novel hybrid PSO algorithm, denoted as Parent–Child Multi-Swarm Clustered Memory (PCSCM). PCSCM is explicitly designed to leverage an enhanced memory system, capable of mitigating the issue of outdated particle memory after convergence, and efficiently adapting to changing environmental conditions. This innovative memory system retains and retrieves promising solutions from the past when environmental alterations occur. Additionally, PCSCM introduces clustering mechanisms for particles within each swarm, aimed at augmenting diversity within the problem space. This clustering strategy substantially bolsters the algorithm’s performance in tracking evolving optimal solutions and positively contributes to its scalability. Crucially, the clustering approach is implemented not only for the main population but also for stored solutions in memory, which collectively strike a balance between exploration and exploitation. In the proposed method, particle swarms are divided into parent and child swarms, with parent swarms dedicated to preserving diversity;while, child swarms focus on identifying local solutions. These clustering and memory strategies are consistently applied within each sub-swarm to effectively address the challenges posed by high-dimensional search spaces. In addition to addressing challenges related to dynamic optimization, our proposed Parent–Child Multi-Swarm Clustered Memory (PCSCM) algorithm introduces an innovative mechanism for detecting environmental changes. This n

关键词： Chaos theory

来源：评论

学校读者我要写书评

暂无评论

Social Force Embedded Mixed Graph Convolutional Network for Multi-class Trajectory Prediction

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年第9期9卷 1-11页

作者： Du, Quancheng Wang, Xiao Yin, Shouguo Li, Lingxi Ning, Huansheng School of Computer and Communication Engineering University of Science and Technology Beijing Beijing China School of Artificial Intelligence Anhui University Hefei China School of Electrical and Computer Engineering Indiana University-Purdue University Indianapolis Indianapolis IN USA

Accurate prediction of agent motion trajectories is crucial for autonomous driving, contributing to the reduction of collision risks in human-vehicle interactions and ensuring ample response time for other traffic participants. Current research predominantly focuses on traditional deep learning methods, including convolutional neural networks (CNNs) and recurrent neural networks (RNNs). These methods leverage relative distances to forecast the motion trajectories of a single class of agents. However, in complex traffic scenarios, the motion patterns of various types of traffic participants exhibit inherent randomness and uncertainty. Relying solely on relative distances may not adequately capture the nuanced interaction patterns between different classes of road users. In this paper, we propose a novel multi-class trajectory prediction method named the social force embedded mixed graph convolutional network (SFEM-GCN). The primary goal is to extract social interactions among agents more accurately. SFEM-GCN comprises three graph topologies: the semantic graph (SG), position graph (PG), and velocity graph (VG). These graphs encode various of social force relationships among different classes of agents in complex scenes. Specifically, SG utilizes one-hot encoding of agent-class information to guide the construction of graph adjacency matrices based on semantic information. PG and VG create adjacency matrices to capture motion interaction relationships between different classes agents. These graph structures are then integrated into a mixed graph, where learning is conducted using a spatio-temporal graph convolutional neural network (ST-GCNN). To further enhance prediction performance, we adopt temporal convolutional networks (TCNs) to generate the predicted trajectory with fewer parameters. Experimental results on publicly available datasets demonstrate that SFEM-GCN surpasses state-of-the-art methods in terms of accuracy and robustness. IEEE

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Efficient Evaluation Methods for Neural Architecture Search: A Survey

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第12期5卷 5990-6011页

作者： Song, Xiaotian Xie, Xiangning Lv, Zeqiong Yen, Gary G. Ding, Weiping Lv, Jiancheng Sun, Yanan Sichuan University College of Computer Science Chengdu610065 China Oklahoma State University School of Electrical and Computer Engineering StillwaterOK74078 United States Nantong University School of Artificial Intelligence and Computer Science Nantong226019 China City University of Macau Faculty of Data Science 999078 China

Neural architecture search (NAS) has received increasing attention because of its exceptional merits in automating the design of deep neural network (DNN) architectures. However, the performance evaluation process, as a key part of NAS, often requires training a large number of DNNs. This inevitably makes NAS computationally expensive. In past years, many efficient evaluation methods (EEMs) have been proposed to address this critical issue. In this article, we comprehensively survey these EEMs published up to date, and provide a detailed analysis to motivate the further development of this research direction. Specifically, we divide the existing EEMs into four categories based on the number of DNNs trained for constructing these EEMs. The categorization can reflect the degree of efficiency in principle, which can in turn help quickly grasp the methodological features. In surveying each category, we further discuss the design principles and analyze the strengths and weaknesses to clarify the landscape of existing EEMs, thus making easily understanding the research trends of EEMs. Furthermore, we also discuss the current challenges and issues to identify future research directions in this emerging topic. In summary, this survey provides a convenient overview of EEM for interested users, and they can easily select the proper EEM method for the tasks at hand. In addition, the researchers in the NAS field could continue exploring the future directions suggested in the article. © 2020 IEEE.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

Diamagnetically Levitated and Trapped Graphite Mechanical Resonators 38

Diamagnetically Levitated and Trapped Graphite Mechanical Re...

引用

38th IEEE International Conference on Micro Electro Mechanical Systems, MEMS 2025

作者： Wang, Yunong Gage, Alexander Lee, Jaesung Feng, Philip X.-L. University of Florida Herbert Wertheim College of Engineering Department of Electrical and Computer Engineering GainesvilleFL32611 United States University of Central Florida College of Engineering & Computer Science Department of Electrical and Computer Engineering OrlandoFL32816 United States

ISBN: (纸本)9798331508890

We report on studying diamagnetic levitation and rigid body resonances of millimeter- to centimeter-scale trapped graphite mechanical resonators, by combining theoretical analysis with experimental demonstrations. Harnessing the strong diamagnetic susceptibility of pyrolytic graphite, we demonstrate stable levitation of square graphite thin plates with varying dimensions and masses above permanent magnets, without the need of active control. The resonance motions are excited by dielectric gradient forces and detected via an ultrasensitive optical interferometry system at room temperature. We observe rigid body resonance modes with frequencies between 25 Hz and 50 Hz and with their quality (Q) factors from 30 to 70. The Q factors are primarily constrained by air damping and eddy current damping. This work represents an initial step toward developing high-stability, anchor-less levitating resonant systems with large masses, paving the way for high-performance resonant sensors with minimal energy dissipation and exceptional thermal and mechanical isolation with very small power consumption. © 2025 IEEE.

关键词： Damping

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of Cell Free-Massive MIMO with Hybrid RF/FSO Fronthaul Links

Performance Analysis of Cell Free-Massive MIMO with Hybrid R...

引用

2025 IEEE SoutheastCon, SoutheastCon 2025

作者： Mannil, Jasni Areepatta Ahmed, Imtiaz Rubaai, Ahmed Hasan, Kamrul Howard University Department of Electrical Engineering and Computer Science WashingtonDC United States Tennessee State University Department of Electrical and Computer Engineering NashvilleTN United States

ISBN: (纸本)9798331504847

In this paper, we analyze the performance of fronthaul communication links configured with hybrid radio frequency (RF) / free space optics (FSO) communication systems for a cell-free (CF) communication network. The fronthaul links are designed from access points (APs) to central processing unit (CPU) and selection combining (SC) is performed at CPU for the uplink data transmission. We derive the closed-form outage probability expression by considering Rician fading for the RF link and Gamma-Gamma fading for the FSO link. The closed-form expressions are validated with Monte Carlo simulation framework for a wide-range of use cases. Numerical results show the effectiveness of the considered hybrid RF-FSO communication links for fronthaul communications of CF communication systems. © 2025 IEEE.

关键词： Radio communication

来源：评论

学校读者我要写书评

暂无评论

Full-model-free Adaptive Graph Deep Deterministic Policy Gradient Model for Multi-terminal Soft Open Point Voltage Control in Distribution Systems

引用

Journal of Modern Power Systems and Clean Energy 2024年第6期12卷 1893-1904页

作者： Huayi Wu Zhao Xu Minghao Wang Youwei Jia Department of Electrical and Electronic Engineering The Hong Kong Polytechnic UniversityHong KongChina Shenzhen Research Institute The Hong Kong Polytechnic UniversityShenzhenChina Department of Electrical and Computer Engineering University of MacaoMacaoChina Department of Electrical and Electronic Engineering Southern University of Science and TechnologyShenzhenChina

High penetration of renewable energy sources(RESs)induces sharply-fluctuating feeder power,leading to volt-age deviation in active distribution *** prevent voltage violations,multi-terminal soft open points(M-sOPs)have been integrated into the distribution systems to enhance voltage con-trol ***,the M-SOP voltage control recalculated in real time cannot adapt to the rapid fluctuations of photovol-taic(PV)power,fundamentally limiting the voltage controllabili-ty of *** address this issue,a full-model-free adaptive graph deep deterministic policy gradient(FAG-DDPG)model is proposed for M-SOP voltage ***,the attention-based adaptive graph convolutional network(AGCN)is lever-aged to extract the complex correlation features of nodal infor-mation to improve the policy learning ***,the AGCN-based surrogate model is trained to replace the power flow cal-culation to achieve model-free ***,the deep deterministic policy gradient(DDPG)algorithm allows FAG-DDPG model to learn an optimal control strategy of M-SOP by continuous interactions with the AGCN-based surrogate *** tests have been performed on modified IEEE 33-node,123-node,and a real 76-node distribution systems,which demonstrate the effectiveness and generalization ability of the proposed FAG-DDPGmodel.

关键词： Soft open point graph attention graph convolutional network reinforcement learning voltage control distribution system deep deterministic policy gradient

来源：评论

学校读者我要写书评

暂无评论

The Development of Dental Problem Detection Device Using Inception V3 and Data Augmentation 8

The Development of Dental Problem Detection Device Using Inc...

引用

8th International Conference on electrical, Telecommunication and computer engineering, ELTICOM 2024

作者： Almodovar, Jacob P. Gloria, Germaine Beatrix A. Paglinawan, Charmaine C. School of Electrical Electronics and Computer Engineering Bachelor of Science in Electronics Engineering Manila Philippines

ISBN: (纸本)9798331531249

This study focuses on the development of a dental problem detection device using the Inception V3 deep learning model and advanced data augmentation techniques. Dental problems such as cavities, impacted wisdom teeth, and crowded teeth pose significant health risks, often requiring advanced imaging for accurate diagnosis. The proposed device utilizes an intraoral camera to capture digital tooth images, which are then processed using the Inception V3 model to identify three dental problems- dental caries, crowded teeth, and partially erupted wisdom teeth. By employing image data augmentation and leveraging datasets from various dental repositories, the study seeks to enhance the accuracy and reliability of dental diagnostics. As a result, the model achieved a total accuracy of 87.2%, in which the model attained a precision of 92%, a recall of 93%, and an Fl-score of 92.5% for caries detection. In detecting crowded teeth, it recorded a precision of 81.1 %, a recall of 90.9%, and an Fl-score of 85.7%. For partially erupted wisdom teeth detection, the precision was 88.8%, the recall 78%, and the Fl-score 83 %. These results indicate that while the model demonstrates strong overall performance, further improvements are necessary to improve the detection of crowded teeth and partially erupted wisdom teeth. This innovative approach endeavors to provide a non-invasive, efficient, and precise tool for dentists, potentially revolutionizing dental healthcare through the integration of advanced AI technologies into routine dental practices. © 2024 IEEE.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Image-based Plant Diseases Detection using Deep Learning

引用

Materials Today: Proceedings 2023年 80卷 3500-3506页

作者： Panchal, Adesh V. Patel, Subhash Chandra Bagyalakshmi, K. Kumar, Pankaj Khan, Ihtiram Raza Soni, Mukesh Department of Computer Science & Engineering GEC Patan India School of Computer Science and Engineering VIT Bhopal University Sehore MP Bhopal India Electrical and Electronics Engineering SRI Ranganathar Institute of Engineering and Technology Coimbatore India Department of Computer Science & Engineering Institute of Engineering & Technology Uttar Pradesh Greater Noida India Jamia Hamdard Computer Science Department Delhi India Jagran Lakecity University Bhopal India

Agriculture plays a major role in developing countries like India, however the food security still remains a vital issue. Most of the crops get wasted due to lack of storage facility, transportation, and plant diseases. More than 15% of the crops get wasted in India due to diseases and hence it has become one of the major concern to be resolved. There is a need of automatic system that can identify these diseases and help farmers to take appropriate steps to get rid of crop loss. Farmers have followed the conventional method of identifying the plant disease with their naked eyes, and it not possible for all the farmers to identify these diseases the same way. With the advance in Artificial Intelligence, there is a need to incorporate the facilities of the computer vision in the field of agriculture. Deep Learning rich libraries and user as well as developer friendly environment to work with, all these qualities make Deep Learning as the favorable method to get started with this problem. In this paper we have used Deep Learning because of the advantages it offers to work with images especially in image classification to get improvised results. The methodology includes taking leaves of infected crops and label them as per the disease pattern. The images of infected leaves are processed pixel based operations are applied to improve the information from the image. As a next step feature extraction is done followed by image segmentation and at the last classification of crop diseases based on the patterns extracted from the diseased leaves. The CNN (Convolutional Neural Network) is used for the classification of diseases, for the demonstration purpose the public dataset is used consisting of around 87 K images (RGB type images) including healthy as well as diseased leaves. © 2021

关键词： Crops

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：