检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Bao, Peng Wang, Gong Yang, Ruijie Dong, Bin The Center for Data Science Peking University the Department of Radiation Oncology Peking University Third Hospital Beijing China The Department of Radiation Oncology Peking University Third Hospital Beijing China Beijing International Center for Mathematical Research Center for Machine Learning Research National Biomedical Imaging Center Peking University Beijing China

Objective: Intensity-modulated radiation therapy (IMRT) beam angle optimization (BAO) is a challenging combinatorial optimization problem that is NP-hard. In this study, we aim to develop a personalized BAO algorithm for IMRT that improves the quality of the final treatment. Methods: To improve the quality of IMRT treatment planning, we propose a deep reinforcement learning (DRL)based approach for IMRT BAO. We consider the task as a sequential decision-making problem and formulate it as a Markov Decision Process. To facilitate the training process, a 3D-Unet is designed to predict the dose distribution for the different number of beam angles, ranging from 1 to 9, to simulate the IMRT environment. By leveraging the simulation model, double deep-Q network (DDQN) and proximal policy optimization (PPO) are used to train agents to select the personalized beam angle sequentially within a few seconds. Results: The treatment plans with beam angles selected by DRL outperform those with clinically used evenly distributed beam angles. For DDQN, the overall average improvement of the CIs is 0.027, 0.032, and 0.03 for 5, 7, and 9 beam angles respectively. For PPO, the overall average improvement of CIs is 0.045, 0.051, and 0.025 for 5, 7, and 9 beam angles respectively. Conclusion: The proposed DRL-based beam angle selection strategy can generate personalized beam angles within a few seconds, and the resulting treatment plan is superior to that obtained using evenly distributed angles. Significance: A fast and automated personalized beam angle selection approach is been proposed for IMRT BAO. © 2023, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Mixing Histopathology Prototypes into Robust Slide-Level Representations for Cancer Subtyping

arXiv

引用

arXiv 2023年

作者： Butke, Joshua Hashimoto, Noriaki Takeuchi, Ichiro Miyoshi, Hiroaki Ohshima, Koichi Sakuma, Jun Machine Learning and Data Mining Lab University of Tsukuba Japan RIKEN Center for Advanced Intelligence Project Japan Department of Mechanical Systems Engineering Nagoya University Japan Department of Pathology Kurume University Japan Department of Computer Science Tokyo Institute of Technology Japan

Whole-slide image analysis via the means of computational pathology often relies on processing tessellated gigapixel images with only slide-level labels available. Applying multiple instance learning-based methods or transformer models is computationally expensive as, for each image, all instances have to be processed simultaneously. The MLP-Mixer is an under-explored alternative model to common vision transformers, especially for large-scale datasets. Due to the lack of a self-attention mechanism, they have linear computational complexity to the number of input patches but achieve comparable performance on natural image datasets. We propose a combination of feature embedding and clustering to preprocess the full whole-slide image into a reduced prototype representation which can then serve as input to a suitable MLP-Mixer architecture. Our experiments on two public benchmarks and one inhouse malignant lymphoma dataset show comparable performance to current state-of-the-art methods, while achieving lower training costs in terms of computational time and memory load. Code is publicly available at https://***/butkej/ProtoMixer. Copyright © 2023, The Authors. All rights reserved.

关键词： Mixers (machinery)

来源：评论

学校读者我要写书评

暂无评论

learning effective nonlinear operator for high speed optical compensation system

引用

Optics Express 2025年第12期33卷 24448-24480页

作者： Xinyu Xiao Zhennan Zhou Hang Yang Dingjiong Ma Jie Sun Bin Dong School of Mathematical Science Peking University China xiao-xin-yu@*** Institute for Theoretical Sciences Westlake University Hangzhou 310030 China zhouzhennan@*** Theory Lab Central Research Institute 2012 Labs Huawei Technology Co. Ltd. Shanghai China Theory Lab Central Research Institute 2012 Labs Huawei Technology Co. Ltd. Hong Kong SAR China ma.dingjiong1@*** j.sun@*** Beijing International Center for Mathematical Research and the New Cornerstone Science Laboratory Peking University China Center for Machine Learning Research Peking University China National Biomedical Imaging Center Peking University China dongbin@math.***

Optical communication systems, which form the backbone of modern communication networks, are often hindered by impairments arising from both linear and nonlinear Kerr effects during signal transmission. While Chromatic Dispersion Compensation (CDC) mitigates linear distortions, existing digital signal processing (DSP) algorithms focus on addressing nonlinear Kerr effects. Current compensation architectures, including post-processing compensation (PPC) and digital back-propagation (DBP), each have limitations: PPC’s separate handling of linear and nonlinear effects reduces compensation accuracy, while DBP’s iterative nature incurs high computational complexity. Neither PPC nor DBP achieves efficient nonlinear compensation. This motivates the need for a method that unifies the strengths of both algorithms and optimizes the trade-off between performance and computational cost. In this paper, we present SNSE, the simplified nonlinear symbol equation, as our theoretical contribution, which provides a unified framework for the design of nonlinear compensation operators. Based on SNSE, we introduce what we believe to be a compensation framework, SNSE-DBP. SNSE-DBP leverages a regular cross-shaped truncation method for nonlinear effects, enabling efficient convolutional modeling for the nonlinear compensation operator. Furthermore, we translate SNSE-DBP into a deep neural network to optimize performance via data-driven training. Numerical simulations demonstrate that SNSE-DBP outperforms both the PPC scheme and DBP scheme in efficiency. This work presents a promising pathway toward effective and computationally feasible nonlinear compensation in optical communication systems.

关键词： Kerr effect Nonlinear effects Nonlinear impairments Optical systems Signal processing Signal transmission

来源：评论

学校读者我要写书评

暂无评论

Weakly supervised image segmentation for defect-based grading of fresh produce

arXiv

引用

arXiv 2024年

作者： Knott, Manuel Odion, Divinefavour Sontakke, Sameer Karwa, Anup Defraeye, Thijs Empa Swiss Federal Laboratories for Materials Science and Technology Laboratory for Biomimetic Membranes and Textiles St. Gallen Switzerland Swiss Data Science Center ETH Zurich EPFL Zurich Switzerland Institute for Machine Learning Department of Computer Science ETH Zurich Switzerland Constructor University Bremen Campus Ring 1 Bremen28759 Germany Innoterra BioScience Private Limited Mumbai India

Implementing image-based machine learning in agriculture is often limited by scarce data and annotations, making it hard to achieve high-quality model predictions. This study tackles the issue of postharvest quality assessment of bananas in decentralized supply chains. We propose a method to detect and segment surface defects in banana images using panoptic segmentation to quantify defect size and number. Instead of time-consuming pixel-level annotations, we use weak supervision with coarse labels. A dataset of 476 smartphone images of bananas was collected under real-world field conditions and annotated for bruises and scars. Using the Segment Anything Model (SAM), a recently published foundation model for image segmentation, we generated dense annotations from coarse bounding boxes to train a segmentation model, significantly reducing manual effort while achieving a panoptic quality score of 77.6%. This demonstrates SAM's potential for low-effort, accurate segmentation in agricultural settings with limited data. © 2024, CC BY.

关键词： Fruits

来源：评论

学校读者我要写书评

暂无评论

A Review on machine learning Assisted Drying Behaviour Prediction of Agricultural Seeds and Fruits

A Review on Machine Learning Assisted Drying Behaviour Predi...

引用

Artificial Intelligence in Education and Industry 4.0 (IDICAIEI), DMIHER International Conference on

作者： Sandip Jawre Prateek Verma Chandrakant B. Kothare Department of Artificial Intelligence and Data Science Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research Wardha Maharashtra India Department of Artificial Intelligence and Machine Learning Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research Wardha Maharashtra India Department of Mechanical Engineering Shri Shankarprasad Agnihotri College of Engineering Wardha Maharashtra India

ISBN: (数字)9798331528713

ISBN: (纸本)9798331528720

machine learning approaches have been more popular in recent years across many scientific and engineering fields, with the potential to improve drying behavior and thermal property predictions in terms of accuracy and efficiency. Agricultural seeds and fruits must be handled carefully after harvest because drying has a considerable impact on their quality, shelf life, and overall worth. To optimize drying processes and guarantee product quality, drying kinetics and thermal characteristics must be accurately predicted. This review article outlines the basic principles of drying, emphasizes their significance in determining the ideal drying conditions, and provides a thorough overview of the application of machine learning methods for predicting the drying kinetics and thermal properties of agricultural seeds and fruits. Then, in the context of their applications to drying prediction, a summary of several machine learning approaches, including artificial neural networks, support vector machines, and decision trees have been discussed.

关键词： Support vector machines Accuracy Thermal engineering machine learning Predictive models Agricultural products Kinetic theory Decision trees Forecasting Systematic literature review

来源：评论

学校读者我要写书评

暂无评论

AI-DRIVEN AUTOMATED TOOL FOR ABDOMINAL CT BODY COMPOSITION ANALYSIS IN GASTROINTESTINAL CANCER MANAGEMENT

arXiv

引用

arXiv 2025年

作者： Nan, Xinyu He, Meng Chen, Zifan Dong, Bin Tang, Lei Zhang, Li Center for Data Science Peking University China Department of Radiology Key Laboratory of Carcinogenesis and Translational Research Ministry of Education Peking University Cancer Hospital and Institute Beijing China Peking University Beijing China Center for Machine Learning Research Peking University Beijing China National Biomedical Imaging Center Peking University Beijing China

The incidence of gastrointestinal cancers remains significantly high, particularly in China, emphasizing the importance of accurate prognostic assessments and effective treatment strategies. Research shows a strong correlation between abdominal muscle and fat tissue composition and patient outcomes. However, existing manual methods for analyzing abdominal tissue composition are time-consuming and costly, limiting clinical research scalability. To address these challenges, we developed an AI-driven tool for automated analysis of abdominal CT scans to effectively identify and segment muscle, subcutaneous fat, and visceral fat. Our tool integrates a multi-view localization model and a high-precision 2D nnUNet-based segmentation model, demonstrating a localization accuracy of 90% and a Dice Score Coefficient of 0.967 for segmentation. Furthermore, it features an interactive interface that allows clinicians to refine the segmentation results, ensuring high-quality outcomes effectively. Our tool offers a standardized method for effectively extracting critical abdominal tissues, potentially enhancing the management and treatment for gastrointestinal cancers. The code is available at https://***/NanXinyu/***. Copyright © 2025, The Authors. All rights reserved.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

A Review on Advancing Prosthetics with Artificial Intelligence: Enhancing Control, Sensory Feedback, and Adaptability

A Review on Advancing Prosthetics with Artificial Intelligen...

引用

International Conference on Trends in Electronics and Informatics (ICEI)

作者： Shivam Bhoyar Renuka Motghare Subodh Daronde Department of Artificial Intillengence and Data Science Datta Meghe Institute of Higher Education and Research(Demeed to be University) Wardha Maharashtra India Department of Artificial Intillengence and Machine Learning Datta Meghe Institute of Higher Education and Research (Demeed to be University) Wardha Maharashtra India Department of Biomedical Engineering Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research. (Demeed to be University) Wardha Maharashtra India

ISBN: (数字)9798331544607

ISBN: (纸本)9798331544614

Recent advancements in prosthetic technology have dramatically improved quality of life for amputees, with AI-powered devices now offering capabilities far beyond traditional prosthetics. This paper traces the evolution of prosthetic limbs from basic mechanical designs to today's intelligent systems featuring myoelectric control and neural interfaces. Modern AI integration enables three key benefits: (1) more natural movement through real-time pattern recognition, (2) enhanced sensory feedback that restores touch perception, and (3) adaptive functionality that reduces user fatigue. Breakthroughs in osseointegration and smart materials further improve comfort and usability. These innovations extend beyond limb prosthetics to include cardiac implants and spinal support systems. Looking ahead, we anticipate a new generation of affordable, autonomous prosthetics that will blur the line between human and machine capabilities.

关键词： Limbs Technological innovation Prosthetic limbs Reviews Tactile sensors Surgery Real-time systems Usability Smart materials Prosthetics

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Modelling Approach to Employee Burnout in the Context of the Big Five Personality Traits

SSRN

引用

SSRN 2022年

作者： Bashkirova, Anna Compagner, Annelies Henningsen, Diana M. Treur, Jan King's College London Institute of Psychiatry Psychology and Neuroscience United Kingdom Vrije Universiteit Amsterdam Department of Computer Science Social AI Group Netherlands University of Copenhagen Department of Computer Science Machine Learning and Data Science Denmark

Burnout has been on the rise in the past decade, especially amongst the younger working generation. While work environmental aspects play an important role in predicting burnout, variations in personality traits are integral for understanding the syndrome's risk factors, processes, and outcomes. This paper studies the complex interaction of personality factors on the one hand and work environment aspects on the other through the relatively novel adaptive causal network modelling paradigm. Due to the adaptive nature of the model, it can investigate the effects of changes in particular job demands and resources on the symptoms of burnout and their dependence on different personality traits. The model can also demonstrate how an individual’s personality traits, environmental perception, and burnout symptoms can adaptively be altered by individual therapy, in this case, mindfulness-based cognitive therapy. Using the dedicated software environment to simulate the designed adaptive causal network model, two main scenarios were explored, focusing on the neuroticism personality *** demonstrate that neuroticism increases due to interpersonal conflict, indicating that neuroticism can be treated as an adaptive trait. Furthermore, when mindfulness-based cognitive therapy was introduced into the simulation, the likelihood of developing burnout decreased because the perception of the work environment was positively changed due to the therapy. This model contributes to the field of burnout modelling by representing personality traits as adaptive factors that can be changed through individual interventions. More detailed research is needed to understand how organisational-level interventions can also impact burnout development through changes in environmental perception and personality. © 2022, The Authors. All rights reserved.

关键词： Employment

来源：评论

学校读者我要写书评

暂无评论

Sensor Allocation and Online-learning-based Path Planning for Maritime Situational Awareness Enhancement: A Multi-Agent Approach

arXiv

引用

arXiv 2023年

作者： Nguyen, Bach Long Doan, Anh-Dzung Chin, Tat-Jun Guettier, Christophe Gupta, Surabhi Parra, Estelle Reid, Ian Wagner, Markus The Department of Data Science and AI Monash Univeristy ClaytonVIC3800 Australia Australian Institute for Machine Learning The University of Adelaide AdelaideSA5000 Australia Safran Electronics and Defense Massy91300 France Safran Electronics and Defense Australasia BotanyNSW2019 Australia

Countries with access to large bodies of water often aim to protect their maritime transport by employing maritime surveillance systems. However, the number of available sensors (e.g., cameras) is typically small compared to the to-be-monitored targets, and their Field of View (FOV) and range are often limited. This makes improving the situational awareness of maritime transports challenging. To this end, we propose a method that not only distributes multiple sensors but also plans paths for them to observe multiple targets, while minimizing the time needed to achieve situational awareness. In particular, we provide a formulation of this sensor allocation and path planning problem which considers the partial awareness of the targets’ state, as well as the unawareness of the targets’ trajectories. To solve the problem we present two algorithms: 1) a greedy algorithm for assigning sensors to targets, and 2) a distributed multi-agent path planning algorithm based on regret-matching learning. Because a quick convergence is a requirement for algorithms developed for high mobility environments, we employ a forgetting factor to quickly converge to correlated equilibrium solutions. Experimental results show that our combined approach achieves situational awareness more quickly than related work. Copyright © 2023, The Authors. All rights reserved.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

All labels are not created equal: Enhancing semi-supervision via label grouping and co-training

arXiv

引用

arXiv 2021年

作者： Nassar, Islam Herath, Samitha Abbasnejad, Ehsan Buntine, Wray Haffari, Gholamreza Dept of Data Science and AI Faculty of IT Monash University Australia Australian Institute for Machine Learning University of Adelaide Australia

Pseudo-labeling is a key component in semi-supervised learning (SSL). It relies on iteratively using the model to generate artificial labels for the unlabeled data to train against. A common property among its various methods is that they only rely on the model's prediction to make labeling decisions without considering any prior knowledge about the visual similarity among the classes. In this paper, we demonstrate that this degrades the quality of pseudo-labeling as it poorly represents visually similar classes in the pool of pseudo-labeled data. We propose SemCo, a method which leverages label semantics and co-training to address this problem. We train two classifiers with two different views of the class labels: one classifier uses the onehot view of the labels and disregards any potential similarity among the classes, while the other uses a distributed view of the labels and groups potentially similar classes together. We then co-train the two classifiers to learn based on their disagreements. We show that our method achieves state-of-the-art performance across various SSL tasks including 5.6% accuracy improvement on Mini-ImageNet dataset with 1000 labeled examples. We also show that our method requires smaller batch size and fewer training iterations to reach its best performance. We make our code available at https://***/islam-nassar/semco. Copyright © 2021, The Authors. All rights reserved.

关键词： Semantics

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：