检索结果-内蒙古大学图书馆

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Jiang, Ruohui Li, Changtai Ban, Xiaojuan Yin, Shihua Yao, Chao Guo, Yu Obaidat, Mohammad S. University of Science and Technology Beijing Beijing Advanced Innovation Center for Materials Genome Engineering Beijing China University of Science and Technology Beijing School of Intelligence Science and Technology Beijing China Liaoning Academy of Materials Institute of Materials Intelligent Technology Shenyang China Second Affiliated Hospital Guangxi Medical University Nanning China University of Science and Technology Beijing School of Computer and Communication Engineering Beijing China University of Jordan King Abdullah Ii School of Information Technology Amman Jordan Amity University UP Noida India

ISBN: (纸本)9798350386226

Precise lesion segmentation is essential in computer-aided diagnosis and treatment. Prevalent deep-learning-based approaches need high-quality annotations to achieve satisfying performance. However, blurring effects and infiltration hamper the accurate delineation of lesions. A common solution is to divide the annotation process into initial annotation by non-specialized personnel and subsequent modification by expert physicians, where the latent correction patterns and non-expert labels are seldom utilized effectively. To explore their helpfulness, we propose ReReNet, a recurrent refined network for lesion segmentation that learns from non-expert to expert. It achieves progressively refined segmentation results through multiple iterations with tailored discrepancy-aware supervision. During training, as the iterative process perceives discrepancies between refining and expert labels, the model gradually grasps the knowledge of turning the barely correct into the clinically accurate. We validate ReReNet's capability on three medical image segmentation (MIS) datasets, including magnetic resonance (MR) and computed tomography (CT) modalities. Comparison results indicate that the proposed approach achieves superior performance by introducing the designed recurrent mechanism and outperforms mainstream methods, demonstrating the effectiveness of mining hidden correction patterns by utilizing non-expert information. © 2024 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

An Active Visible-Light Integrated Photonics Platform on 200-mm Si

An Active Visible-Light Integrated Photonics Platform on 200...

引用

2023 Optical Fiber Communications Conference and Exhibition, OFC 2023

作者： Sacher, Wesley D. Lin, Yiding Chen, Hong Azadeh, Saeed S. Yong, Zheng Luo, Xianshu Chua, Hongyao Mak, Jason C. C. Govdeli, Alperen Sharma, Ankita Mikkelsen, Jared C. Mu, Xin Stalmashonak, Andrei Lo, Guo-Qiang Poon, Joyce K. S. Max Planck Institute of Microstructure Physics Weinberg 2 Halle06120 Germany Department of Electrical and Computer Engineering University of Toronto 10 King's College Road TorontoONM5S 3G4 Canada Advanced Micro Foundry Pte. Ltd 11 Science Park Road Science Park II Singapore117685 Singapore

We present a foundry-fabricated monolithically integrated photonics platform for the visible spectrum (λ=445-640nm) with two layers of silicon nitride waveguides, silicon photodiodes, efficient undercut thermo-optic ... 详细信息

ISBN: (纸本)9781957171180

关键词： Silicon nitride

来源：评论

学校读者我要写书评

暂无评论

Nanophotonic neural probe enabled light-sheet light-field fluorescence imaging microendoscope

Nanophotonic neural probe enabled light-sheet light-field fl...

引用

2023 Conference on Lasers and Electro-Optics, CLEO 2023

作者： Ding, Peisheng Wahn, Hannes Chen, Fu-Der Luo, Xianshu Lo, Guo-Qiang Poon, Joyce K.S. Sacher, Wesley D. Max Planck Institute of Microstructure Physics Weinberg 2 Halle06120 Germany Department of Electrical and Computer Engineering University of Toronto 10 King's College Road TorontoONM5S 3G4 Canada Advanced Micro Foundry Pte Ltd 11 Science Park Road Singapore Science Park II 117685 Singapore

We demonstrate a lensless volumetric imaging microendoscope for deep-brain fluorescence microscopy. It consists of a nanophotonic neural probe for light-sheet illumination and an image fiber bundle for light-field flu... 详细信息

ISBN: (纸本)9781957171258

关键词： Nanophotonics

来源：评论

学校读者我要写书评

暂无评论

Innovative Approaches to the Use of Multifunctional Materials in Building Envelopes 7th

Innovative Approaches to the Use of Multifunctional Material...

引用

7th International Conference on Construction, Real Estate, Infrastructure, and Project Management, ICCRIP 2023

作者： Kumari, Soni Suresh Kumar, R. Abhishek, Kumar Pathak, B.N. Nijhawan, Ginni Khayoon, Ali Talib Rajalakshmi, B. Kalra, Ravi Department of Mechanical Engineering GLA University UP Mathura India Department of Civil Engineering Institute of Aeronautical Engineering Hyderabad500043 India Gujarat Ahmedabad380026 India Department of Mechanical Engineering IMS Engineering College Ghaziabad India Lovely Professional University Panjab Phagwara India College of Engineering Technology National University of Science and Technology Dhi Qar Iraq Department of Computer Science New Horizon College of Engineering Bangalore India Lloyd Institute of Engineering and Technology Knowledge Park II Uttar Pradesh Greater Noida201306 India

ISBN: (纸本)9789819649013

Multifunctional materials have become a hot topic in building envelope design due to their ability to simultaneously perform several functions such as structural support, insulation, energy harvesting, and storage. This paper reviews recent developments in the use of multifunctional materials in building envelopes, including their composition, properties, and potential applications. The paper also examines innovative approaches to integrating these materials into building envelopes to enhance their performance and sustainability. The potential benefits and challenges of using multifunctional materials in building envelopes are discussed, along with future directions for research in this field. However, there are also challenges associated with the use of these materials, including their high cost, complexity of integration, and potential durability issues, which require further research and development. Overall, this review provides insights into the current state and potential of multifunctional materials in building envelopes, highlighting opportunities for future research and application. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Thermal comfort

来源：评论

学校读者我要写书评

暂无评论

Deploying Unsupervised Learning for Daily Activity Windows Analysis in Cancer Patients 2

Deploying Unsupervised Learning for Daily Activity Windows A...

引用

2nd Edition IEEE International Conference on Metrology for eXtended Reality, Artificial Intelligence and Neural Engineering, MetroXRAINE 2023

作者： Tramontano, Adriano Feoli, Chiara Tamburis, Oscar Conson, Manuel Salzano, Francesco Magliulo, Mario Institute of Biostructures and Bioimaging National Research Council of Italy Naples Italy University of Naples 'Federico II' Department of Advanced Biomedical Sciences Naples Italy University of Cagliari Department of Mathematics and Computer Science Cagliari Italy University of Molise Stake Lab Campobasso Italy Hassisto S.r.l. Naples Italy

ISBN: (纸本)9798350300802

Radiotherapy (RT) could have significant impact on quality of life (QoL) in cancer patient. The aim of the study is to evaluate Radiation Treatment impact on daily activities in cancer patient using wearable devices technologies to monitor patients in their daily activities. Objective data were collected over RT time and a dedicated in-house algorithm was designed to recognize and analyze several repeated activity windows (RAWs) during days based on the intensity of the subject's activity (steps walked) and the duration of such activity (minutes). Subjective patient reported outcomes (PROs) were collected in the form of an answer scoring to a dedicated questionnaire. Unsupervised machine learning approach (K-means) was used to cluster RAWs over RT time for each patient. 9-18 RAWs were counted in a day per patient, by the conducted analysis. Four RAWs clusters were found characterized by a variation in their parameters. The analysis of the clusters' parameters showed that subjects' activity level could be corelated with the variation in the subjective PRO providing indicators of the RT treatment impact on the patients' QoL. QoL variation evaluation could be improved by blending the objective data collected via a continuous patient monitoring with the powerful information coming from the PRO. © 2023 IEEE.

关键词： Health Related Quality of Life Internet of Things Radiotherapy Treatment Unsupervised Leaning Wearable devices

来源：评论

学校读者我要写书评

暂无评论

The PredictMed-PoMAS Architecture for Intelligent Patient Monitoring within a Complex Healthcare Ecosystem 2

The PredictMed-PoMAS Architecture for Intelligent Patient Mo...

引用

2nd AIxIA Workshop on Artificial Intelligence for Healthcare, HC@AIxIA 2023

作者： Costantini, Stefania Bertoncelli, Carlo Bertoncelli, Domenico De Meo, Pasquale Falcone, Rino Persia, Fabio Rossi, Silvia Department of Information Engineering Computer Science and Mathematics -DISIM Università di L’Aquila Italy Côte-d’Azur University of Nice and Etablissement pour Enfants ou Adolescents Polyhandicapés H. Germain Fondation Lenval Nice France Department of Computer Science University of West Florida United States Department of Ancient and Modern Civilizations University of Messina Italy Institute of Cognitive Sciences and Technologies National Research Council Rome Italy Department of Electrical Engineering and Information Technologies DIETI University of Naples "Federico II" Italy

In this paper, we leverage our past work to outline and describe, also using examples, a comprehensive architecture that goes from PMAs, i.e., Patient Monitoring Agents, to a novel notion of Hybrid Society (HS) instantiated in this paper to the healthcare domain, different from previous existing proposals. The HS is meant to encompass PMAs and offices of medical specialists, healthcare companies such as medical centres, and institutions such as hospitals. Our approach is based on approaches to agents and Multi-Agent-Systems (MAS) rooted in computational logic, whose nice formal foundation allows properties of agents and MAS to be proved/enforced through theorem proving, model-checking, run-time verification and other techniques. © 2023 CEUR-WS. All rights reserved.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

PW-MAD: Pixel-wise supervision for generalized face morphing attack detection

arXiv

引用

arXiv 2021年

作者： Damer, Naser Spiller, Noémie Fang, Meiling Boutros, Fadi Kirchbuchner, Florian Kuijper, Arjan Fraunhofer Institute for Computer Graphics Research IGD Germany Department of Computer Science TU Darmstadt Germany

A face morphing attack image can be verified to multiple identities, making this attack a major vulnerability to processes based on identity verification, such as border checks. Various methods have been proposed to detect face morphing attacks, however, with low generalizability to unexpected post-morphing processes. A major post-morphing process is the print and scan operation performed in many countries when issuing a passport or identity document. In this work, we address this generalization problem by adapting a pixel-wise supervision approach where we train a network to classify each pixel of the image into an attack or not, rather than only having one label for the whole image. Our pixel-wise morphing attack detection (PW-MAD) solution proved to perform more accurately than a set of established baselines. More importantly, PW-MAD shows high generalizability in comparison to related works, when evaluated on unknown re-digitized attacks. Additionally to our PW-MAD approach, we create a new face morphing attack dataset with digital and re-digitized samples, namely the LMA-DRD dataset that is publicly available for research purposes upon request. Copyright © 2021, The Authors. All rights reserved.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Next-Generation Computational Models for Enhanced Interpretation of Biospeckle Images Leveraging Deep Learning and Fourier Transform Techniques in Biomedical Applications 7

Next-Generation Computational Models for Enhanced Interpreta...

引用

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

作者： Gowtham Raj, R. Sreekanth, S. Nijhawan, Ginni Gupta, Shubhi Sharma, Saurabh Mounika, T. New Horizon College of Engineering Deparment of Mechanical Engineering Bangalore India Institute of Aeronautical Engineering Dundigal Hyderabad500043 India Lloyd Law College Plot No. 11 Knowledge Park II Greater Uttar Pradesh Noida201314 India Lovely Professional University Phagwara India Amity University Amity School of Engineering & Technology Greater Noida India Mlr Institute of Technology Department of Computer Science and Engineering Telangana Hyderabad India

ISBN: (纸本)9798350350067

This study looks at advanced computational techniques that enhance the understanding of biospeckle images in biological contexts. Our models use Fourier transform and deep learning techniques to achieve improved specificity, recall, accuracy, and precision. The Fourier transform may provide a more accurate description of frequency domain data as biological processes evolve over time. Deep learning algorithms recognise patterns in biospeckle images, facilitating analysis, memory, and response. The analysis research delineates the several components that influence the outcome and provides evidence of their respective roles. This research shows how helpful the models are and offers suggestions on how to make them better. Non-invasive biomedical testing uses these computer models to illustrate the temporal evolution of biological cells. Our techniques improve the interpretation of biospeckle images, potentially revolutionising non-invasive biomedical imaging. Future researchers may evaluate these models using different datasets and testing conditions. This guarantees their adaptability and power in biological contexts. © 2024 IEEE.

关键词： Frequency domain analysis

来源：评论

学校读者我要写书评

暂无评论

Advancing Wire Arc Additive Manufacturing: A New Era of Precision and Efficiency in Large Metal Component Production

Advancing Wire Arc Additive Manufacturing: A New Era of Prec...

引用

2024 OPJU International Technology Conference on Smart Computing for Innovation and Advancement in Industry 4.0, OTCON 2024

作者： Khan, Irfan Anjimoon, Shaik Asha, V. Singla, Atul Akhil, P. Alsultany, Nahed Mahmood Ahmed Lloyd Institute of Engineering & Technology Knowledge Park II Uttar Pradesh Greater Noida201306 India Institute of Aeronautical Engineering Hyderabad Dundigal India New Horizon College of Engineering Department of Computer Applications Bangalore India Lovely Professional University Phagwara India St. Martin's Engineering College Dept. of Cse Telangana Secunderabad India National University of Science and Technology Collage of Dentist Dhi Qar64001 Iraq

ISBN: (纸本)9798350373783

A comprehensive Wire Arc Additive Manufacturing (WAAM) approach that employs five algorithms to improve massive metal components is described in this research. The adaptive layer thickness control algorithm adjusts layer thickness based on real-time complexity. This ensures additive manufacturing accuracy throughout. Also, the Material Versatility Optimization Algorithm simplifies working with multiple materials, making casting more efficient. The Intelligent Path Planning Algorithm allocates the robotic arm's movement to traverse the shortest distance and uniformly distribute heat during deposition. The MultiMaterial-Materialon Strategy Algorithm improves material amounts, making WAAM more usable for additional materials. The Real-Time Excellent Assurance Algorithm constantly examines and adjusts parameters to ensure excellent production. A complete analysis of research reveals how algorithms are related and how vital they are for accuracy, speed, and flexibility. Testing shows that the recommended technique controls layer thickness, material variety, deposition velocity, accuracy, energy efficiency, and real-time tracking better than typical WAAM methods. Figures 6, 7, and 8 indicate that the proposed method delivers superior results across several criteria. The recommended WAAM approach can create more massive metal components by fundamentally changing how things are done. This research provides a comprehensive additive manufacturing approach to solve numerous large-scale metal production issues. © 2024 IEEE.

关键词： Quality control

来源：评论

学校读者我要写书评

暂无评论

Sophisticated Neural Network Architectures for the Holistic Simulation and Performance Enhancement of Convective Boiling Processes in Industrial Applications

Sophisticated Neural Network Architectures for the Holistic ...

引用

2024 OPJU International Technology Conference on Smart Computing for Innovation and Advancement in Industry 4.0, OTCON 2024

作者： Asha, V. Anjimoon, Shaik Singla, Atul Khan, Irfan Alsharifi, Haider Asaad Farhoud Maranan, Ramya New Horizon College of Engineering Department of Computer Applications Bangalore India Institute of Aeronautical Engineering Hyderabad Dundigal India Lovely Professional University Phagwara India Lloyd Institute of Engineering & Technology Knowledge Park II Uttar Pradesh Greater Noida201306 India National University of Science and Technology Collage of Dentist Dhi Qar64001 Iraq Simats Saveetha School of Engineering Department of Research and Innovation Tamil Nadu Chennai602105 India

ISBN: (纸本)9798350373783

In this research, neural network approaches for industrial convective boiling simulation are fully examined. Five strategies address feature extraction, temporal dynamics, memory retention, data enrichment, and knowledge sharing issues. Recurrent neural networks (RNNs) discover temporal changes, whereas CNNs find spatial patterns. Long ShortTerm Memory (LSTM) Networks assist in recalling things;Generative Adversarial Networks (GANs) add data;and Transfer Learning conveys information using taught models. These methods accurately simulate convective boiling 96.0% of the time. Compared to tried-and-true approaches, it's faster, more extensible, and more resilient. Visualizations indicate how superior the technique is at accuracy, stability distribution, and multi-metric scores. Here's a detailed design for modeling convective boiling, including how space and time change, how to protect memories, add data, and exchange information. Industrial usage is possible since the recommended technique mimics convective cooking processes more complexly and cost-effectively. © 2024 IEEE.

关键词： Generative adversarial networks

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：