检索结果-内蒙古大学图书馆

Communication, Control and Intelligent Systems (CCIS)

作者： P. Balaji D. Devasena P. Rithick T. Karthi K. Rishmitha R. Roopa Dept. of. Electronics and Instrumentation Engineering Sri Ramakrishna Engineering College Coimbatore Tamilnadu Dept. of Robotics and Automation Engineering Sri Ramakrishna Engineering College Coimbatore Tamilnadu Dept. of Automobile Engineering Kongu Engineering College Erode India Dept. of Artificial Intelligence and Data Science Arjun College of Technology Coimbatore Tamilnadu

ISBN: (数字)9798331528201

ISBN: (纸本)9798331528218

The detection of Glial Fibrillary Acidic Protein (GFAP) is a crucial biomarker for diagnosing neurological conditions such as traumatic brain injuries (TBI) and astrocytoma. This paper presents the design and analysis of a novel microfluidic Lab-on-a-Chip (LoC) platform for GFAP biomarker detection. The system integrates microfluidic channels with embedded gold nanoparticle-functionalized electrochemical sensors for high-sensitivity biomarker capture. The microfluidic chip is designed using soft lithography and PDMS (Polydimethylsiloxane), allowing for precise fluid handling and minimal sample consumption. The electrochemical sensors generate voltage signals corresponding to GFAP concentration levels, which are processed using digital filtering techniques to mitigate noise and improve signal quality. For accurate biomarker quantification, machine learning algorithms, including Random Forest ,KNN and Support Vector Machine (SVM), are employed to classify sensor output data into clinically significant concentration ranges. The model is trained on both simulated and experimentally collected sensor data, achieving an accuracy of over 93 percent in distinguishing low (below 50 ng/mL) and high (above 50 ng/mL) GFAP concentrations. The combination of microfluidic precision, sensitive electrochemical detection, and data analysis enables rapid and reliable detection of GFAP , providing a scalable and portable solution for early diagnosis of brain injuries and neurodegenerative diseases. This system highlights the potential of integrating microfluidics and machine learning in next-generation point-of-care diagnostic devices.

关键词： Support vector machines Soft lithography Machine learning algorithms Accuracy data analysis Lab-on-a-chip Sensor systems Biosensors Microfluidics Brain injuries

来源：评论

学校读者我要写书评

暂无评论

XAI-PSSGAN: Perception-Enhanced Spectrum Shift Generative Adversarial Network with Explainable AI System for NIR-II Fluorescence Molecular Imaging 22

XAI-PSSGAN: Perception-Enhanced Spectrum Shift Generative Ad...

引用

22nd IEEE International Symposium on Biomedical Imaging, ISBI 2025

作者： Fu, Lidan Lu, Binchun Li, Lingbing Shi, Xiaojing Tian, Jie Hu, Zhenhua Cas Key Laboratory of Molecular Imaging Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China Department of Precision Instrument Tsinghua University Beijing China Interventional Radiology Department Chinese Pla General Hospital Beijing China Beijing Advanced Innovation Center for Big Data-based Precision Medicine School of Engineering Medicine Beihang University Beijing China Engineering Research Center of Molecular and Neuro Imaging of Ministry of Education School of Life Science and Technology Xidian University Xi'an China National Key Laboratory of Kidney Diseases Beijing China

ISBN: (纸本)9798331520526

Fluorescence imaging in the second near-infrared window (NIR-II) facilitates the real-time optical contrast for in vivo biomedical imaging. However, the detection noise is an inevitable byproduct of the real-time imaging process. Additionally, fluorescent probes currently approved for clinical use remain limited within the wavelength of NIR-IIa (1000-1300 nm). NIR-IIb (1500-1700 nm) imaging has the potential to deliver higher resolution than NIR-IIa, but relies on toxic fluorescent probes not approved for human use. To support clinical high-precision imaging, we propose a NIR-II fluorescence enhanced imaging method based on perception-enhanced spectrum shift generative adversarial network with explainable AI systems (xAI-PSSGAN). The proposed method tackles the problem of limited unpaired data training, and generates NIR-IIb resembling images with enhanced resolution and reduced noise. Experimental results demonstrate that proposed method effectively improves the imaging quality and surpasses competing alternatives, which is of great significance to promote the high-quality NIR-II imaging in clinical practice. © 2025 IEEE.

关键词： Molecular imaging

来源：评论

学校读者我要写书评

暂无评论

Unified Domain Adaptive Semantic Segmentation

arXiv

引用

arXiv 2023年

作者： Zhang, Zhe Wu, Gaochang Zhang, Jing Zhu, Xiatian Tao, Dacheng Chai, Tianyou State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang China School of Computer Science Wuhan University China The College of Computing & Data Science Nanyang Technological University Singapore Surrey Institute for People-Centred Artificial Intelligence Centre for Vision Speech and Signal Processing University of Surrey Guildford United Kingdom

Unsupervised Domain Adaptive Semantic Segmentation (UDA-SS) aims to transfer the supervision from a labeled source domain to an unlabeled and shifted target domain. The majority of existing UDA-SS works typically consider images whilst recent attempts have extended further to tackle videos by modeling the temporal dimension. Although two lines of research share the major challenges – overcoming the underlying domain distribution shift, their studies are largely independent. It causes several issues: (1) The insights gained from each line of research remain fragmented, leading to a lack of holistic understanding of the problem and potential solutions. (2) Preventing the unification of methods and best practices across two scenarios (images and videos) will lead to redundant efforts and missed opportunities for cross-pollination of ideas. (3) Without a unified approach, the knowledge and advancements made in one scenario may not be effectively transferred to the other, leading to suboptimal performance and slower progress. Under this observation, we advocate unifying the study of UDA-SS across video and image scenarios, enabling a more comprehensive understanding, synergistic advancements, and efficient knowledge sharing. To that end, we explore the unified UDA-SS from a general domain augmentation perspective, serving as a unifying framework, enabling improved generalization, and potential for cross-pollination, ultimately contributing to the practical impact and overall progress. Specifically, we propose a Quad-directional Mixup (QuadMix) method, characterized by tackling intra-domain discontinuity, fragmented gap bridging, and feature inconsistencies through four-directional paths designed for intra- and inter-domain mixing within an explicit feature space. To deal with temporal shifts within videos, we incorporate optical flow-guided feature aggregation across spatial and temporal dimensions for fine-grained domain alignment, which is extendable to image scenarios

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Constrained Coverage of Unknown Environment Using Safe Reinforcement Learning

Constrained Coverage of Unknown Environment Using Safe Reinf...

引用

IEEE Conference on Decision and Control

作者： Yunlin Zhang Junjie You Lei Shi Jinliang Shao Wei Xing Zheng School of Automation Engineering University of Electronic Science and Technology of China Chengdu China School of Artificial Intelligence Henan University Zhengzhou China Laboratory of Electromagnetic Space Cognition and Intelligent Control Beijing China School of Computer Data and Mathematical Sciences Western Sydney University Sydney NSW Australia

Achieving a connected, collision-free and time-efficient coverage in unknown environments is challenging for multi-agent systems. Particularly, agents with second-order dynamics are supposed to efficiently search and reach the optimal deployment positions over targets whose distribution is unknown, while preserving the distributed connectivity and avoiding collision. In this paper, a safe reinforcement learning based shield method is proposed for unknown environment exploration while correcting actions of agents for safety guarantee and avoiding invalid samples into policy updating. The shield is achieved distributively by a control barrier function and its validity is proved in theory. Moreover, policies of the optimal coverage are centrally learned via reward engineering and executed distributively. Numerical results show that the proposed approach not only achieves zero safety violations during training, but also speeds up the convergence of learning.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Cross-Feature Mutual Learning Framework to Integrate Functional Connectivity and Activity for Brain Disorder Classification

A Cross-Feature Mutual Learning Framework to Integrate Funct...

引用

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

作者： Min Zhao Rongtao Xu Dongmei Zhi Shan Yu Vince D Calhoun Jing Sui Brainnetome Center Institute of Automation Chinese Academy of Sciences School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China State Key Laboratory of Cognitive Neuroscience Beijing Normal University Beijing China Laboratory of Brain Atlas and Brain-Inspired Intelligence Institute of Automation Chinese Academy of Sciences Beijing China Tri-Institutional Center for Translational Research in Neuroimaging and Data Science (TReNDS) Center Georgia State University Atlanta GA USA IDG/McGovern Institute for Brain Research State Key Laboratory of Cognitive Neuroscience and Learning Beijing Normal University Beijing China

ISBN: (数字)9798350371499

ISBN: (纸本)9798350371505

Time courses (TC) and functional network connectivity (FNC) features, derived from functional magnetic resonance imaging, show considerable potential in the study of brain disorders. Despite significant advancements, most deep learning approaches tend to either directly concatenate complementary MRI features at the input level or ensemble decisions after separately learning each feature, whereas an end-to-end, mixed feature learning framework is still lacking. To bridge this gap, we introduce a cross-feature mutual learning (CFML) to enable collaborative learning of TC-specific and FNC-specific models and facilitate mutual knowledge transfer to distill shared and robust characteristics from the high-level representations of TC and FNC, thereby enhancing brain disorder classification performance. Specifically, we first develop a recurrent neural network-based TC-specific encoder to capture temporal dynamic dependencies within TCs, alongside a transformer-based FNC-specific encoder to discern global high-order functional dependencies among independent components in FNCs. Subsequently, we design a cross-modal module for the adaptive integration of TC-specific and FNC-specific features. Additionally, the CFML strategy is proposed to collaboratively train these modules, incorporating feature-specific loss, feature-exchange loss, and joint loss. Empirical results reveal that CFML achieves an accuracy of 85.1% in differentiating healthy controls (HC) from schizophrenia (SZ) patients, surpassing 12 comparative models by a margin of 3.0-9.2% accuracy using either static FNC or TCs or both. These findings underscore the efficacy of CFML in classifying brain disorders, highlighting its potential in advancing this field.

关键词： Representation learning Deep learning Neuroimaging Accuracy Recurrent neural networks Mental disorders Transformers Brain modeling Object recognition Knowledge transfer

来源：评论

学校读者我要写书评

暂无评论

AI-Assisted Decision-Making for Clinical Assessment of Auto-Segmented Contour Quality

arXiv

引用

arXiv 2025年

作者： Wang, Biling Maniscalco, Austen Bai, Ti Wang, Siqiu Dohopolski, Michael Lin, Mu-Han Shen, Chenyang Nguyen, Dan Huang, Junzhou Jiang, Steve Wang, Xinlei Medical Artificial Intelligence and Automation Laboratory University of Texas Southwestern Medical Center DallasTX United States Department of Statistics and Data Science Southern Methodist University DallasTX United States Department of Radiation Oncology University of Texas Southwestern Medical Center DallasTX United States Department of Computer Science and Engineering University of Texas at Arlington ArlingtonTX United States Department of Mathematics University of Texas at Arlington ArlingtonTX United States Division of Data Science College of Science University of Texas at Arlington ArlingtonTX United States

Purpose: This study introduces a novel Deep Learning (DL)-based quality assessment (QA) approach specifically designed for evaluating auto-generated contours (auto-contours) in auto-segmentation for radiotherapy, with a focus on Online Adaptive Radiotherapy (OART). The proposed method leverages Bayesian Ordinal Classification (BOC), combined with calibrated thresholds derived from uncertainty quantification, to deliver confident QA predictions. This approach addresses key challenges in clinical auto-segmentation QA workflows such as the absence of ground truth contours, limited availability of manually labeled data, and inherent uncertainty in AI model predictions. Methods: We developed a BOC model to classify the quality of auto-contours and quantify uncertainty. To enhance predictive reliability, we implemented a calibration step to determine optimal uncertainty thresholds that meet specific clinical accuracy requirements. The method was validated under three distinct data availability scenarios: absence of manual labels, limited manual labeling, and extensive manual labeling. We specifically tested our method for auto-segmented rectum contours in prostate cancer radiotherapy. Geometric surrogate labels were employed in the absence of manual labels, transfer learning was applied when manual labels were limited, and direct use of manual labels was performed when extensive labeling was available. Results: The BOC model demonstrated robust performance across all data availability scenarios for confident predictions, with significant accuracy gains when pre-trained with surrogate labels and fine-tuned with limited manually labeled data. Specifically, fine-tuning the pretrained model with just 30 manually labeled cases and calibrating with 34 subjects achieved over an accuracy of over 90% against manual labels in the test dataset. Furthermore, with the calibrated uncertainty threshold, over 93% of the auto-contours’ qualities were accurately predicted in over 98% of ca

关键词： Damage detection

来源：评论

学校读者我要写书评

暂无评论

Optimal Energy Storage Operation under Demand Uncertainty: A Prospect Theory Analysis

Optimal Energy Storage Operation under Demand Uncertainty: A...

引用

IEEE International Conference on Smart Grid Communications (SmartGridComm)

作者： Qisheng Huang Jin Xu Peng Sun Bo Liu Costas Courcoubetis School of Mechanical Engineering and Automation Harbin Institute of Technology Shenzhen Shenzhen China School of Management Huazhong University of Science and Technology Wuhan China College of Computer Science and Electronic Engineering Hunan University Changsha China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China School of Data Science The Chinese University of Hong Kong Shenzhen Shenzhen China

In this paper, we study the consumer’s optimal energy storage operation problem under demand uncertainty. Each consumer can purchase energy storage service from an independent energy storage aggregator to shift demand from peak periods to off-peak periods under time-of-use (ToU) pricing. Previous studies on energy storage operation and investment mainly focused on the expected cost-minimization problem of a risk-neutral consumer based on the expected utility theory (EUT). We propose a prospect theory (PT) model from behavioral economics to understand the consumer’s realistic energy storage operation behaviors considering their risk preferences. Although it is challenging to solve the PT-based non-convex optimization problem, we are able to characterize the optimal solution by exploiting the unimodal structure of the objective function. Theoretical and numerical results show that the consumer’s risk preferences have a significant impact on his decisions: 1) a PT-consumer with a low reference point is more willing to use energy storage to reduce risk compared with the EUT benchmark; and 2) a PT consumer is more willing to use the energy storage when the probability of high demand is small, due to the probability distortion.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Solving Expensive Optimization Problems in Dynamic Environments with Meta-learning

arXiv

引用

arXiv 2023年

作者： Zhang, Huan Ding, Jinliang Feng, Liang Tan, Kay Chen Li, Ke State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang110819 China College of Computer Science Chongqing University Chongqing400044 China Department of Data Science and Artificial Intelligence Hong Kong Polytechnic University Hong Kong Department of Computer Science University of Exeter ExeterEX4 4QF United Kingdom

Dynamic environments pose great challenges for expensive optimization problems, as the objective functions of these problems change over time and thus require remarkable computational resources to track the optimal solutions. Although data-driven evolutionary optimization and Bayesian optimization (BO) approaches have shown promise in solving expensive optimization problems in static environments, the attempts to develop such approaches in dynamic environments remain rarely explored. In this paper, we propose a simple yet effective meta-learning-based optimization framework for solving expensive dynamic optimization problems. This framework is flexible, allowing any off-the-shelf continuously differentiable surrogate model to be used in a plug-in manner, either in data-driven evolutionary optimization or BO approaches. In particular, the framework consists of two unique components: 1) the meta-learning component, in which a gradient-based meta-learning approach is adopted to learn experience (effective model parameters) across different dynamics along the optimization process. 2) the adaptation component, where the learned experience (model parameters) is used as the initial parameters for fast adaptation in the dynamic environment based on few shot samples. By doing so, the optimization process is able to quickly initiate the search in a new environment within a strictly restricted computational budget. Experiments demonstrate the effectiveness of the proposed algorithm framework compared to several state-of-the-art algorithms on common benchmark test problems under different dynamic characteristics. Copyright © 2023, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Disentangling clusters from non-Euclidean data via graph frequency reorganization

引用

Information sciences 2024年 662卷

作者： Geng, Yangli-ao Chi, Chong-Yung Sun, Wenju Zhang, Jing Li, Qingyong Key Laboratory of Big Data & Artificial Intelligence in Transportation Ministry of Education Beijing Jiaotong University Beijing100044 China Frontiers Science Center for Smart High-speed Railway System Beijing Jiaotong University Beijing100044 China Institute of Communications Engineering National Tsing Hua University Hsinchu30013 Taiwan Power Automation Department China Electric Power Research Institute Beijing100192 China

In light of the growing need for non-Euclidean data analysis, graphs have been recognized as an effective tool for characterizing the distribution and correlation of such data, thus inspiring many graph-based developments for various applications such as clustering, of non-Euclidean data. However, under unsupervised scenarios, the construction of graphs from unlabeled data often involves numerous noisy links, consequently leading to serious performance degradation in concerned applications. To resolve this issue, we propose a novel method, referred to as Graph Frequency Reorganization (GFR), to enhance the discriminability of potential clusters and the associated graph quality. GFR shows capability far beyond the suboptimality in unsupervised graph construction. Furthermore, a fast version of GFR is proposed to reduce its computation overhead for large-scale datasets. Consequently, the obtained unsupervised clustering results can be significantly upgraded using the GFR data (i.e., the data after the GFR processing). To evaluate the effectiveness of the GFR, some experimental results on ten real-world datasets are provided to demonstrate that the overall clustering performance of a simple k-means using the GFR data is superior to several state-of-the-art graph-based clustering methods1. © 2024 Elsevier Inc.

关键词： K-means clustering

来源：评论

学校读者我要写书评

暂无评论

Federated Learning for Medical Image Classification: Advances, Challenges and Opportunities

SSRN

引用

SSRN 2023年

作者： Zhang, Xiaobo Zhao, Xiaole Wu, Yunyang Zheng, Hailong Li, Yang School of Computing and Artificial Intelligence Southwest Jiaotong University Chengdu611756 China Artificial Intelligence Research Institute Southwest Jiaotong University Chengdu611756 China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University Chengdu611756 China Engineering Research Center of Sustainable Urban Intelligent Transportation Ministry of Education China School of Automation Science and Electrical Engineering Beihang University Beijing100191 China

Medical images are private integrations comprising private patient information owned by various hospitals and relevant research institutes, and the generated image data can be utilized to infer physical health conditions. In recent years, more and more AI researchers have used medical images as datasets for their analysis purposes, which will cause relevant personnel to worry about their privacy. As a distributed machine learning framework, federated learning can effectively solve the problem of data privacy. It participates in and completes model training without sharing personal data, with strong universality and good results. In this work, Computed Tomography (CT), Magnetic Resonance Imaging (MRI), Wilhelm Conrad Röntgen (X-Ray) as well as other typical medical imaging modes are used as research objects to summarize, analyze and look forward to the previous work related to federal learning in the field of medical image analysis. On the one hand, this survey classifies and compares the existing federal learning framework and algorithm for different medical image datasets;on the other hand, it discusses the relevant federal studies that are widely used in medical images, analyses the problems that need to be solved in the field of medical images, and looks forward to future studies. © 2023, The Authors. All rights reserved.

关键词： Medical imaging

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：