检索结果-内蒙古大学图书馆

2024 IEEE International Conference on E-Health Networking, Application and Services, HealthCom 2024

作者： Liu, Xinkai Peng, Boyuan Zhu, Xin Iwasaki, Tsuyoshi Sato, Atsuya Kazama, Junichiro James Huang, Jie Graduate Department of Computer Science and Engineering The University of Aizu Fukushima Aizu-Wakamatsu Japan Department of AI Technology Development M&D Data Science Center Institute of Science Tokyo Tokyo Japan Department of Nephrology and Hypertension Fukushima Medical University Fukushima Japan Graduate Department of Computer Science and Engineering Division of Information Systems The University of Aizu Fukushima Aizu-Wakamatsu Japan

ISBN: (纸本)9798350350548

The advent of the Segment Anything Model (SAM) marks a significant milestone in deep learning semantic segmentation tasks. In this study, an incremental learning model based on pseudo labels is proposed. The model generates bounding box prompts for SAM, enhancing the accuracy of glomeruli segmentation in renal pathology images. The model uses DenseNet-121 along with contrastive learning to enable self-supervised pre-training using mouse glomeruli images. Transfer learning is then conducted using labeled human renal pathology images to develop a binary classification model for glomeruli. Unlabeled images of human renal pathology are subsequently introduced for incremental learning. Class activation maps (CAMs) generated by the incremental learning model are post-processed to extract bounding rectangles for connected regions. These rectangles are then used as prompts for SAM segmentation. The proposed approach resulted in an average Dice similarity coefficient (DSC) of 0.825 in the glomeruli segmentation task. This result demonstrates the effectiveness of the incremental learning model and post-processing algorithms in improving SAM’s segmentation accuracy for renal pathology. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Improving Prediction Quality of Face Image Preference Using Combinatorial Fusion Algorithm 16th

Improving Prediction Quality of Face Image Preference Using...

引用

16th International Conference on Brain Informatics, BI 2023

作者： Zhang, Zihan Schweikert, Christina Shimojo, Shinsuke Hsu, D. Frank Laboratory of Informatics and Data Mining Department of Computer and Information Science Fordham University YorkNY10023 United States Division of Computer Science Mathematics and Science St. John’s University QueensNY11439 United States Division of Biology and Biological Engineering/Computation and Neural Systems California Institute of Technology PasadenaCA91125 United States

ISBN: (纸本)9783031430749

When two face images are shown to a subject, the subject’s preference choice is influenced by many factors. Although it is a challenging task, one way to detect a subject’s preference is to analyze the eye movement gaze cascade in the recorded video sequence together with a set of extracted attributes (features). Combinatorial fusion algorithm (CFA) is a new information fusion and machine learning paradigm for combining multiple scoring systems using rank-score characteristic (RSC) function and cognitive diversity (CD). In this paper, we apply CFA in the analysis of the eye movement gaze cascade sequence. In particular, we characterize each of the attributes and measure the diversity between two attributes using RSC function and CD respectively. The novelty of the combinatorial fusion approach is the new paradigm of incorporating both score function and rank function as well as using both score combination and rank combination. In addition, our results demonstrate that weighted rank combination has some advantage over weighted score combination when the weight is measured using diversity strength. Since diversity strength depends only on cognitive diversity between two attributes but not on any specific sequence in the eye movement gaze cascade, our result facilitates learning and modeling in an unsupervised manner. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： information fusion

来源：评论

学校读者我要写书评

暂无评论

Decentralized Optimal Merging Control for Mixed Traffic with Vehicle Inference

Decentralized Optimal Merging Control for Mixed Traffic with...

引用

American Control Conference (ACC)

作者： Wei Xiao Christos G. Cassandras Computer Science & Artificial Intelligence Lab Massachusetts Institute of Technology Cambridge MA USA Division of Systems Engineering and Center for Information and Systems Engineering Boston University Brookline MA USA

ISBN: (数字)9798350382655

ISBN: (纸本)9798350382662

This paper addresses the optimal control of vehicles arriving from two curved roads at a merging point where the objective is to jointly minimize the travel time, energy consumption, and passenger discomfort. Unlike prior work where traffic consists entirely of Connected and Automated Vehicles (CAVs), we consider optimal controls for CAVs in mixed traffic including Human-Driven Vehicles (HDVs) behaving according to some car-following model that includes random actions. The control applied to CAVs is based on partial information about the presence and states of HDVs which is inferred from local observations available to the CAVs. The passing order of HDVs at the merging point is determined and assisted by CAVs using a proposed Minimum-Effort Merging Contract (MEMC) that uses Control Barrier Functions (CBFs) to guarantee safety. A coordinator is used to manage both the CAV information and inferred HDV information such that the problem can still be solved in a decentralized way. Our approach first determines an analytically tractable unconstrained optimal solution. We then use the joint Optimal Control and Barrier Function (OCBF) method to obtain a controller which optimally tracks such a solution while also guaranteeing all safety and control constraints, including a safe merging contract between CAVs and HDVs. Simulation examples are included to compare the performance under different CAV penetration rates.

关键词： Energy consumption Rollover Roads Merging Optimal control Safety Contracts

来源：评论

学校读者我要写书评

暂无评论

Femoropopliteal Artery Stent Detection in Fluoroscopy Using Otsu's Preprocessing and CNN Segmentation 4

Femoropopliteal Artery Stent Detection in Fluoroscopy Using ...

引用

4th International Conference on Technological Advancements in Computational sciences, ICTACS 2024

作者： Rajinikanth, Venkatesan Damaševičius, Robertas Taniar, David Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Division of Research and Innovation Department of Computer Science and Engineering TN Chennai602105 India Kaunas University of Technology Centre of Real Time Computer Systems Kaunas44249 Lithuania Monash University Faculty of Information Technolog MelbourneVIC3800 Australia

ISBN: (纸本)9798350387490

Computer algorithm supported medical image analysis is a prevalent method in clinics, which effectively alleviates the diagnostic burden associated with traditional image assessment methods. This study aims to create a method that utilizes a Convolutional-Neural-Network (CNN) to accurately segment the Femoropopliteal Artery Stent (FAS) in Digital Fluoroscopy Images (DFI). In order to improve the accuracy of segmentation, this study used the combination of Otsu's tri-level thresholding and the Lévy-Flight Distribution Algorithm (LFDA). The suggested technique consists of many stages: collecting and resizing images and masks, boosting the DFI using Otsu and LFDA, using CNN-segmentation to extract the stent region, comparing segmented stent with mask, and calculating the required performance metrics. The efficacy of the suggested system is validated by analyzing the raw and thresholded DFI. The investigational results of this work affirm that this method achieves a higher level of accuracy (>96%) in segmenting images when the Otsu's preprocessed image is utilized. The experimental study employs the UNet-variants, and in the future, alternative CNN-segmentation methodologies can be utilized to validate the effectiveness of the presented scheme. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Brownian-Distribution Algorithm Optimized Efficientnet Features for Normal/Glaucoma Retinal Fundus Image Classification 4

Brownian-Distribution Algorithm Optimized Efficientnet Featu...

引用

4th International Conference on Technological Advancements in Computational sciences, ICTACS 2024

ISBN: (纸本)9798350387490

The eye is a critical sensory organ in human physiology, and any abnormality in the eye will result in vision problems ranging from mild to severe. Image-guided methods are frequently employed to conduct clinical-level eye health assessments, and retinal fundus imaging (RFI) is among the most frequently employed modalities for eye analysis. This research aims to implement a Deep-Learning (DL)-based technique for classifying the Normal/Glaucoma RFI database. This scheme consist following phases, image collection and labelling, feature extraction with EfficientNet, feature optimization using a novel Brownian-Distribution Algorithm (BDA), and binary classification with 3-fold cross validation. Initially, the proposed approach performs the classification with EfficientNet-model features and documents the results. Subsequently, the BDA is employed to optimize the features in order to identify the most significant ones. Serial features-fusion is then implemented to generate a new features vector. The results of this study confirm that this approach is capable of achieving a 100 % accuracy rate when the BDA optimized feature vector is utilized for the classification task. In the future, this application may be utilized to analyze the RFI collected from hospital. © 2024 IEEE.

关键词： Ophthalmology

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence based Healthcare Knowledge Structure for Automatic Medical Report Generation 7

Artificial Intelligence based Healthcare Knowledge Structure...

引用

7th International Conference on Contemporary Computing and Informatics, IC3I 2024

作者： Kumar, Pramod Alghayadh, Faisal Yousef Tamta, Vinay Prasad Anand, Monika Soni, Mukesh Chaudhary, Jitendra Kumar Ganga Institute of Technology and Management Bhadana- Bahadurgarh Road Kablana Haryana Jhajjar India AlMaarefa University Computer Science and Information Systems Department College of Applied Sciences Riyadh Saudi Arabia Department of Information Technology Uttarakhand Srinagar India Chandigarh University Department Cse Punjab Mohali India Lovely Professional University Division of Research and Development Punjab Phagwara India Graphic Era Hill University School of Computing Bhimtal Campus Uttarakhand India

ISBN: (纸本)9798350350067

Automatic medical report production is a key text summarization application. Traditional text summarizing systems cannot completely interpret and use medical texts' complicated vocabulary due to the disparities between medical consultation data and general domain data. The crucial knowledge in medical consultations has not been successfully harnessed. Traditional text summary algorithms cannot automatically identify, and filter key information based on medical reports' structure and generate structured text. An AI-based knowledge-assisted structured medical report creation solution addresses these difficulties. This method uses entity-guided previous domain knowledge and structure-guided task decoupling to fully utilize medical consultation data and medical report structure. The suggested strategy improves ROUGE scores by 2% to 3% compared to similar methods, resulting in more accurate medical reports, according to IMCS21 dataset experiments. © 2024 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Advanced UAV photogrammetry for precision 3D modeling in GPS denied inaccessible tunnels

引用

Safety in Extreme Environments 2024年第4期6卷 269-287页

作者： Ikeda, Hajime Bibish, Baterdene Fissha, Yewuhalashet Sinaice, Brian Bino Toriya, Hisatoshi Adachi, Tsuyoshi Kawamura, Youhei Department of Systems Control and Information Engineering National Institute of Technology Asahikawa College 2-2-1-6 Syunkodai Hokkaido Asahikawa-city 0718142 Japan Graduate School of International Resources Akita University 1-1 Tegatagakuen Machi Akita Akita-City 0108502 Japan Faculty of Engineering Division of Sustainable Resources Hokkaido University 13jyounishi8 Kita-ku Hokkaido Sapporo-City 0608628 Japan North China Institute of Science and Technology Hebei Langfang 065201 China

Unmanned Aerial Vehicles (UAVs) have evolved into potent tools for both researchers and professionals. Their use has expanded significantly in recent years across diverse fields of research and engineering, primarily owing to their image-capturing capabilities. These capabilities offer benefits such as time efficiency, cost-effectiveness, minimal fieldwork, and high precision. This study focuses on harnessing UAVs’ photogrammetric technology to create a reliable and accurate 3D modeling process. By doing so, we assess the feasibility of modeling and mapping hard-to-access tunnels using imagery acquired from UAVs combined with photogrammetry. This approach consistently provided a faithful representation of the environment under study. Three distinct experiments underpin this research. The first aims to construct a 3D model using a singular directional light source, evaluating its precision in a concrete tunnel setting. The second experiment involves crafting a 3D model of an underground sewer tunnel using both unidirectional and omnidirectional light sources. The final experiment leverages the insights from the preceding tests to create a 3D model via a specially-designed UAV system, gauging the accuracy of this 3D photogrammetric model within what is termed in this study as a "pedestrian tunnel." However, there are inherent challenges to this approach. For instance, augmenting a drone with additional equipment changes its weight distribution, potentially compromising its stability. An improperly balanced payload could result in uneven flight patterns, rendering the UAV harder to manage. © The Author(s) 2024.

关键词： Inaccessible tunnel mapping Payload balance challenges Photogrammetric analysis Subterranean 3D modeling Unmanned Aerial Vehicles (UAVs)

来源：评论

学校读者我要写书评

暂无评论

Analyzing the behaviors of pedestrians and cyclists in interactions with autonomous systems using controlled experiments: A literature review

引用

Transportation Research Part F: Traffic Psychology and Behaviour 2025年 114卷 270-307页

作者： Danya Li Wencan Mao Francisco C. Pereira Yu Xiao Xiang Su Rico Krueger Department of Technology Management and Economics Technical University of Denmark (DTU) Denmark Information Systems Architecture Science Research Division National Institute of Informatics (NII) Japan Department of Information and Communications Engineering Aalto University Finland Department of Computer Science and Department of Agricultural Sciences University of Helsinki Finland

Urban transportation is set to undergo a profound transformation with the advent of autonomous systems such as autonomous vehicles, automated buses, and sidewalk delivery robots. To promote safe, sustainable, and inclusive urban mobility, understanding and predicting the behaviors of pedestrians and cyclists, including their intentions, decisions, and movements, when they interact with autonomous systems becomes crucial. Gaining a thorough understanding of these complex interactions can not only improve the safety, efficiency, and acceptance of autonomous systems but also enhance the design and implementation of these technologies. Through a comprehensive review of the literature spanning the years 2014 to 2023, we identify 99 articles that empirically investigate the interactions of humans and autonomous systems. Based on our overview of progress and challenges within this field, we further identify five research gaps that future research should address to enhance human-autonomous system interactions, including: (1) scaling up experimental scenarios to multi-user and multi-modal setups to better represent real-world challenges, (2) emphasizing safety-critical scenarios that are difficult to achieve in real-world environments by applying virtual reality, (3) incorporating diverse behavioral data from the human perspective to deepen the understanding of vulnerable road user behavior and decisions, (4) embracing continuous and real-time interaction to better predict dynamic future environments, and (5) enhancing the generalization ability to ensure realism and broad applicability. This review article offers valuable insights for the growing human-autonomous system research community, specifically those interested in leveraging controlled experiments to enhance the understanding and prediction of pedestrians' and cyclists' behaviors in future urban environments.

关键词： Human-autonomous system interaction Human behavioral modeling Autonomous vehicles Virtual reality Controlled experiment

来源：评论

学校读者我要写书评

暂无评论

Self-Supervised Learning of Grasping Arbitrary Objects On-the-Move

Self-Supervised Learning of Grasping Arbitrary Objects On-th...

引用

IEEE/SICE International Symposium on System Integration

作者： Takuya Kiyokawa Eiki Nagata Yoshihisa Tsurumine Yuhwan Kwon Takamitsu Matsubara Division of Information Science Robot Learning Laboratory Nara Institute of Science and Technology (NAIST) Ikoma Nara Japan Department of Systems Innovation Graduate School of Engineering Science Osaka University Toyonaka Osaka Japan

ISBN: (数字)9798331531614

ISBN: (纸本)9798331531621

Mobile grasping enhances manipulation efficiency by utilizing robots’ mobility. This study aims to enable a commercial off-the-shelf robot for mobile grasping, requiring precise timing and pose adjustments. Self-supervised learning can develop a generalizable policy to adjust the robot’s velocity and determine grasp position and orientation based on the target object’s shape and pose. Due to mobile grasping’s complexity, action primitivization and step-by-step learning are crucial to avoid data sparsity in learning from trial and error. This study simplifies mobile grasping into two grasp action primitives and a moving action primitive, which can be operated with limited degrees of freedom for the manipulator. This study introduces three fully convolutional neural network (FCN) models to predict static grasp primitive, dynamic grasp primitive, and residual moving velocity error from visual inputs. A two-stage grasp learning approach facilitates seamless FCN model learning. The ablation study demonstrated that the proposed method achieved the highest grasping accuracy and pick-and-place efficiency. Furthermore, randomizing object shapes and environments in the simulation effectively achieved generalizable mobile grasping.

关键词： Visualization Accuracy Shape Grasping Self-supervised learning Timing Complexity theory Trajectory Convolutional neural networks Manipulator dynamics

来源：评论

学校读者我要写书评

暂无评论

Basic Approach to Estimation of Blood Oxygen Saturation Using an RGB Color Camera without Infrared Light 4

Basic Approach to Estimation of Blood Oxygen Saturation Usin...

引用

4th IEEE Global Conference on Life sciences and Technologies, LifeTech 2022

作者： Yoshizawa, Makoto Sugita, Norihiro Tanaka, Akira Togashi, Atsushi Kaji, Isao Yambe, Tomoyuki Tohoku University Center for Promotion of Innovation Strategy Sendai Japan Tohoku University Graduate School of Engineering Sendai Japan Fukushima University Faculty of Symbiotic Systems Science Fukushima Japan Shizuoka Institute of Science and Technology Faculty of Informatics Fukuroi Japan Sendai Foundation for Applied Information Sciences Sendai Japan

ISBN: (纸本)9781665419048

A method for estimating SPO2 using only an ordinary RGB color camera without using infrared light required by general pulse oximeters has been developed. In the method, first, three video pulse waves based on RGB video signals obtained by photographing the palm with a white LED light source were acquired as accurately as possible, and then their AC and DC components were obtained. SPO2 was estimated from the interrelationship among the three types of ratios. In the experiment, healthy 91 participants were made to hold their breath for 20s to create changes in SPO2. True values of SPO2 obtained from the fingertip photoelectric pulse wave meter was compared with estimated values from the palm video image. The results performed from five trials of cross-validation demonstrated that the multiple regression model was superior to the optimization method for absorption coefficients. © 2022 IEEE.

关键词： Oxygen

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：