检索结果-内蒙古大学图书馆

Deep-Learning–Based Screening and Ancillary Testing for Thyroid Cytopathology

American Journal of Pathology 2023年第9期193卷 1185-1194页

作者： Dov, David Elliott Range, Danielle Cohen, Jonathan Bell, Jonathan Rocke, Daniel J. Kahmke, Russel R. Weiss-Meilik, Ahuva Lee, Walter T. Henao, Ricardo Carin, Lawrence Kovalsky, Shahar Z. I-Medata AI Center Tel Aviv Sourasky Medical Center Tel Aviv-Yafo Israel Department of Pathology Duke University Medical Center Durham NC United States Department of Head and Neck Surgery & Communication Sciences Duke University Medical Center Durham NC United States Department of Head and Neck Surgery Kaplan Medical Center Rehovot Israel Biological Environmental Sciences and Engineering Division King Abdullah University of Science and Technology Thuwal Saudi Arabia Department of Biostatistics and Bioinformatics Duke University Durham NC United States Computer Science Program Computer Electrical and Mathematical Sciences and Engineering (CEMSE) Division King Abdullah University of Science and Technology Thuwal Saudi Arabia Department of Mathematics University of North Carolina at Chapel Hill Chapel Hill NC United States

Thyroid cancer is the most common malignant endocrine tumor. The key test to assess preoperative risk of malignancy is cytologic evaluation of fine-needle aspiration biopsies (FNABs). The evaluation findings can often be indeterminate, leading to unnecessary surgery for benign post-surgical diagnoses. We have developed a deep-learning algorithm to analyze thyroid FNAB whole-slide images (WSIs). We show, on the largest reported data set of thyroid FNAB WSIs, clinical-grade performance in the screening of determinate cases and indications for its use as an ancillary test to disambiguate indeterminate cases. The algorithm screened and definitively classified 45.1% (130/288) of the WSIs as either benign or malignant with risk of malignancy rates of 2.7% and 94.7%, respectively. It reduced the number of indeterminate cases (N = 108) by reclassifying 21.3% (N = 23) as benign with a resultant risk of malignancy rate of 1.8%. Similar results were reproduced using a data set of consecutive FNABs collected during an entire calendar year, achieving clinically acceptable margins of error for thyroid FNAB classification. © 2023 American Society for Investigative Pathology

关键词：

来源：评论

学校读者我要写书评

暂无评论

Meaningful human control: actionable properties for AI system development

引用

AI and Ethics 2022年第1期3卷 241-255页

作者： Cavalcante Siebert, Luciano Lupetti, Maria Luce Aizenberg, Evgeni Beckers, Niek Zgonnikov, Arkady Veluwenkamp, Herman Abbink, David Giaccardi, Elisa Houben, Geert-Jan Jonker, Catholijn M. van den Hoven, Jeroen Forster, Deborah Lagendijk, Reginald L. AiTech Interdisciplinary Research Program on Meaningful Human Control Delft University of Technology Delft The Netherlands Faculty of Electrical Engineering Mathematics and Computer Science Delft University of Technology Delft The Netherlands Faculty of Industrial Design Engineering Delft University of Technology Delft The Netherlands Faculty of Mechanical Maritime and Materials Engineering Delft University of Technology Delft The Netherlands Faculty of Technology Policy and Management Delft University of Technology Delft The Netherlands

How can humans remain in control of artificial intelligence (AI)-based systems designed to perform tasks autonomously? Such systems are increasingly ubiquitous, creating benefits - but also undesirable situations where moral responsibility for their actions cannot be properly attributed to any particular person or group. The concept of meaningful human control has been proposed to address responsibility gaps and mitigate them by establishing conditions that enable a proper attribution of responsibility for humans; however, clear requirements for researchers, designers, and engineers are yet inexistent, making the development of AI-based systems that remain under meaningful human control challenging. In this paper, we address the gap between philosophical theory and engineering practice by identifying, through an iterative process of abductive thinking, four actionable properties for AI-based systems under meaningful human control, which we discuss making use of two applications scenarios: automated vehicles and AI-based hiring. First, a system in which humans and AI algorithms interact should have an explicitly defined domain of morally loaded situations within which the system ought to operate. Second, humans and AI agents within the system should have appropriate and mutually compatible representations. Third, responsibility attributed to a human should be commensurate with that human’s ability and authority to control the system. Fourth, there should be explicit links between the actions of the AI agents and actions of humans who are aware of their moral responsibility. We argue that these four properties will support practically minded professionals to take concrete steps toward designing and engineering for AI systems that facilitate meaningful human control.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Role of deep learning in cognitive healthcare: Wearable signal analysis, algorithms, benefits, and challenges

引用

Digital Communications and Networks 2025年第3期11卷 642-670页

作者： Alam, Md. Sakib Bin Lameesa, Aiman Sharmin, Senzuti Afrin, Shaila Ahmed, Shams Forruque Nikoo, Mohammad Reza Gandomi, Amir H. Department of Information Technology University of Information Technology and Sciences (UITS) Dhaka 1212 Bangladesh Department of Computer Science American International University - Bangladesh (AIUB) Dhaka 1229 Bangladesh Science and Math Program Asian University for Women Chattogram 4000 Bangladesh School of Mathematical Sciences Sunway University Bandar Sunway Petaling Jaya Selangor Darul Ehsan 47500 Malaysia Department of Mathematics and Physics North South University Dhaka 1229 Bangladesh Department of Civil and Architectural Engineering Sultan Qaboos University Muscat Oman Faculty of Engineering and Information Technology University of Technology Sydney Sydney 2007 NSW Australia University Research Innovation Center (EKIK) Óbuda University Budapest 1034 Hungary Department of Computer Science Khazar University Mahsati 41 Baku Azerbaijan

Deep Learning (DL) offers promising solutions for analyzing wearable signals and gaining valuable insights into cognitive disorders. While previous review studies have explored various aspects of DL in cognitive healthcare, there remains a lack of comprehensive analysis that integrates wearable signals, data processing techniques, and the broader applications, benefits, and challenges of DL methods. Addressing this limitation, our study provides an extensive review of DL's role in cognitive healthcare, with a particular emphasis on wearables, data processing, and the inherent challenges in this field. This review also highlights the considerable promise of DL approaches in addressing a broad spectrum of cognitive issues. By enhancing the understanding and analysis of wearable signal modalities, DL models can achieve remarkable accuracy in cognitive healthcare. Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), and Long Short-term Memory (LSTM) networks have demonstrated improved performance and effectiveness in the early diagnosis and progression monitoring of neurological disorders. Beyond cognitive impairment detection, DL has been applied to emotion recognition, sleep analysis, stress monitoring, and neurofeedback. These applications lead to advanced diagnosis, personalized treatment, early intervention, assistive technologies, remote monitoring, and reduced healthcare costs. Nevertheless, the integration of DL and wearable technologies presents several challenges, such as data quality, privacy, interpretability, model generalizability, ethical concerns, and clinical adoption. These challenges emphasize the importance of conducting future research in areas such as multimodal signal analysis and explainable AI. The findings of this review aim to benefit clinicians, healthcare professionals, and society by facilitating better patient outcomes in cognitive healthcare. © 2025 Chongqing University of Posts and Telecommunications

关键词： Cognitive healthcare Convolutional neural network Deep learning Recurrent neural network Wearable sensor

来源：评论

学校读者我要写书评

暂无评论

Next-Gen Smart Vehicle Number Plate Recognition with Dynamic Character Encoding for Lightning-Fast and Accurate Detection

Next-Gen Smart Vehicle Number Plate Recognition with Dynamic...

引用

Ubiquitous Computing and Intelligent Information Systems (ICUIS), International Conference on

作者： Gandhi Prakash Panem M. Amina Begum Ramya Maranan Ankita Gaur Ajay Singh Yadav Alok Dubey Lakireddy Bali Reddy College of Engineering (Autonomous) Department of ECE Sri Venkateswaraa College of Technology Chennai India Department of Research and Innovation Saveetha School of Engineering SIMATS Chennai Tamil Nadu India Department of Sciences Program Mathematics Manav Rachna University Faridabad Haryana Department of Mathematics SRM Institute of Science and Technology Delhi-NCR Campus Ghaziabad U.P Department of Preventive Dental Sciences College of Dentistry Jazan University Jazan Saudi Arabia

ISBN: (数字)9798331529635

ISBN: (纸本)9798331529642

This research explores the application of deep learning techniques, specifically Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs with LSTM), for robust Automatic Number Plate Recognition (ANPR) in real-world scenarios. The system effectively detects and recognizes license plates from images captured in real-world environments. By treating the character string recognition as a sequence labeling problem, the system achieves a high success rate of 97%. This research demonstrates the significant potential of deep learning in enhancing the accuracy and reliability of ANPR systems, enabling applications in intelligent transportation systems, traffic management, and law enforcement.

关键词： Deep learning Accuracy Recurrent neural networks Law enforcement Ubiquitous computing Character recognition Reliability Vehicle dynamics License plate recognition Long short term memory

来源：评论

学校读者我要写书评

暂无评论

A Portable Multiscopic Camera for Novel View and Time Synthesis in Dynamic Scenes

arXiv

引用

arXiv 2022年

作者： Zhang, Tianjia Lau, Yuen-Fui Chen, Qifeng The Hong Kong University of Science and Technology Hong Kong The Individualized Interdisciplinary Program The Robotics Institute Hong Kong The Department of Mathematics Hong Kong The Department of Computer Science and Engineering The Department of Electronic and Computer Engineering Hong Kong

We present a portable multiscopic camera system with a dedicated model for novel view and time synthesis in dynamic scenes. Our goal is to render high-quality images for a dynamic scene from any viewpoint at any time using our portable multiscopic camera. To achieve such novel view and time synthesis, we develop a physical multiscopic camera equipped with five cameras to train a neural radiance field (NeRF) in both time and spatial domains for dynamic scenes. Our model maps a 6D coordinate (3D spatial position, 1D temporal coordinate, and 2D viewing direction) to view-dependent and time-varying emitted radiance and volume density. Volume rendering is applied to render a photo-realistic image at a specified camera pose and time. To improve the robustness of our physical camera, we propose a camera parameter optimization module and a temporal frame interpolation module to promote information propagation across time. We conduct experiments on both real-world and synthetic datasets to evaluate our system, and the results show that our approach outperforms alternative solutions qualitatively and quantitatively. Our code and dataset are available at https://***/. Copyright © 2022, The Authors. All rights reserved.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Adsorption evaluation of linear alkylbenzene sulfonate on magadiite-magnetite and carbon-magnetite from rice husk ash

Case Studies in Chemical and Environmental Engineering

引用

Case Studies in Chemical and Environmental engineering 2025年 11卷

作者： Yuliana, Yuliana Permana, Muhamad Diki Solihudin Eddy, Diana Rakhmawaty Saito, Norio Takei, Takahiro Department of Chemistry Faculty Mathematics and Natural Sciences Universitas Padjadjaran Sumedang 45363 Indonesia Special Educational Program for Green Energy Conversion Science and Technology Integrated Graduate School of Medicine Engineering and Agricultural Sciences University of Yamanashi Kofu 400-8511 Japan Center for Crystal Science and Technology University of Yamanashi Kofu 400-8511 Japan

The presence of surfactant waste in the aquatic environment contributes to environmental problems. In this study, the adsorption that uses magadiite and carbon from rice husk ash via the microwave irradiation method and is composited with magnetite was proposed. The composite magadiite-magnetite (MM) and carbon-magnetite (CM) were obtained by co-precipitation methods by intercalation and impregnation. MM and CM were evaluated as adsorbents for the removal of the anionic surfactant linear alkylbenzene sulfonate (LABS). The obtained material was characterized by X-ray diffraction (XRD), Fourier-transform infrared (FTIR), scanning electron microscope-energy dispersive X-ray spectroscopy (SEM-EDX), thermal gravimetric analysis (TGA), N₂ adsorption by Brunauer-Emmet-Teller (BET) method, and vibrating sample magnetometer (VSM). The influence of contact time, initial concentration, temperature, pH, and adsorbent dose on the adsorption process was investigated. The adsorption kinetics of LABS onto MM and CM followed the pseudo-second-order model and the equilibrium data fitted well to the monolayer Langmuir model as confirmed by the calculated values of R². The adsorption capacity for LABS on MM and CM is 129.00 and 91.77 mg g⁻¹, respectively. The thermodynamic study exhibited that those adsorptions occurred spontaneously with a predominance of chemisorption. MM and CM could be utilized as effective adsorbents with retrieval ability for removing anionic surfactant pollutants in aquatic environments. © 2025 The Authors

关键词： Adsorption Carbon Linear alkylbenzene sulfonate Magadiite Magnetite

来源：评论

学校读者我要写书评

暂无评论

Bayesian Parameter Inference for Partially Observed Diffusions using Multilevel Stochastic Runge-Kutta Methods

arXiv

引用

arXiv 2023年

作者： Moral, Pierre Del Hu, Shulan Jasra, Ajay Ruzayqat, Hamza Wang, Xinyu Institut de Mathematiques de Bordeaux FR Bordeaux33405 France School of Mathematics and Statistics Wenlan School of Business China Applied Mathematics and Computational Science Program Computer Electrical and Mathematical Sciences and Engineering Division King Abdullah University of Science and Technology Thuwal23955-6900 Saudi Arabia Zhongnan University of Economics and Law CN China

We consider the problem of Bayesian estimation of static parameters associated to a partially and discretely observed diffusion process. We assume that the exact transition dynamics of the diffusion process are unavailable, even up-to an unbiased estimator and that one must time-discretize the diffusion process. In such scenarios it has been shown how one can introduce the multilevel Monte Carlo method to reduce the cost to compute posterior expected values of the parameters for a pre-specified mean square error (MSE);see [12]. These afore-mentioned methods rely on upon the Euler-Maruyama discretization scheme which is well-known in numerical analysis to have slow convergence properties. We adapt stochastic Runge-Kutta (SRK) methods for Bayesian parameter estimation of static parameters for diffusions. This can be implemented in high-dimensions of the diffusion and seemingly under-appreciated in the uncertainty quantification and statistics fields. For a class of diffusions and SRK methods, we consider the estimation of the posterior expectation of the parameters. We prove that to achieve a MSE of O(ϵ2), for ϵ > 0 given, the associated work is O(ϵ−2). Whilst the latter is achievable for the Milstein scheme, this method is often not applicable for diffusions in dimension larger than two. We also illustrate our methodology in several numerical examples. Copyright © 2023, The Authors. All rights reserved.

关键词： Diffusion

来源：评论

学校读者我要写书评

暂无评论

Modifying BiVO4 as a photocatalyst for water oxidation using constant-duration alkaline-etched post treatments

引用

New Journal of Chemistry 2023年第2期48卷 569-577页

作者： Hsu, Chuan-Chih Chuang, Kai-Jie Huang, Hsiao-Wen Pan, Bo-Jin Chen, Hung-Ming Husain, Sadang Yougbaré, Sibidou Hsiao, Yu-Cheng Wu, Yung-Fu Lin, Lu-Yin Division of Cardiovascular Surgery Department of Surgery School of Medicine College of Medicine Taipei Medical University Taiwan Division of Cardiovascular Surgery Department of Surgery Taipei Medical University Hospital Taiwan Department of Chemical Engineering and Biotechnology National Taipei University of Technology Taipei Taiwan Department of Chemical Engineering Ming Chi University of Technology New Taipei City24301 Taiwan Gingen Technology Co. Ltd. Rm. 7 10F. No. 189 Sec. 2 Keelung Rd. Xinyi Dist. Taipei11054 Taiwan Department of Physics Faculty of Mathematics and Natural Science Lambung Mangkurat University Banjarmasin70124 Indonesia /Nanoro Ouagadougou03 Burkina Faso International PhD Program in Biomedical Engineering College of Biomedical Engineering Taipei Medical University Taipei11031 Taiwan Stanford Byers Center for Biodesign Stanford University CA94305-5428 United States Graduate Institute of Biomedical Optomechatronics College of Biomedical Engineering Taipei Medical University Taipei11031 Taiwan Cell Physiology and Molecular Image Research Center Wan Fang Hospital Taipei Medical University Taipei11696 Taiwan

BiVO4 with suitable band edges and a small band gap is considered an efficient photocatalyst for the oxygen evolution reaction (OER), but short charge-transfer lengths limit its photocatalytic ability. Increasing active sites can essentially enhance oxidation reactions and photocatalytic ability. The alkaline etching technique can refine the surface properties of BiVO4 by introducing oxygen vacancies and possibly establishing a heterojunction, but suitable alkaline etching methods are rarely discussed. In this study, three alkaline etching methods, including hydrothermal, soaking, and electrodeposition processes, are first applied for a constant duration to tailor the surface properties of BiVO4 as a photocatalyst for the OER. Alkaline-etched BiVO4 prepared using hydrothermal and soaking processes shows better photocatalytic abilities due to the generation of additional oxygen vacancies, while poor photocatalytic ability is found for that fabricated using electrodeposition due to the formation of less photocatalytic VO2. The highest photocurrent density of 2.38 mA cm−2 is obtained at 1.23 V versus a reversible hydrogen electrode in an electrolyte without a hole scavenger for the BiVO4 etched in the hydrothermal process, while the untreated BiVO4 presents a photocurrent density of 0.58 mA cm−2. A photocurrent retention of 92.3% is achieved after 5000 seconds of continuous illumination. The study supplies blueprints for establishing effective alkaline etching methods for enhancing the photocatalytic ability of BiVO4, with the exception of time costs. © 2024 The Royal Society of Chemistry.

关键词： Charge transfer

来源：评论

学校读者我要写书评

暂无评论

Potential of fungal thermostable alpha amylase enzyme isolated from Hot springs of Central Anatolia(Turkey)in wheat bread quality

引用

Food Bioscience 2022年第1期45卷 214-222页

作者： Arzu Unal Asiye Seis Subasi Semra Malkoc Ijlal Ocak SElif Korcan Elif Yetilmezer Seyhun Yurdugül Hülya Yaman Turgay Sanal Alaettin Keceli Igdır University Faculty of AgricultureDepartment of Agricultural BiotechnologyI˘gdırTurkey Ministry of Agriculture and Forestry Field Crops Central Research Institute Department of Quality and TechnologyAnkaraTurkey Eskisehir Technical University Faculty of EngineeringDepartment of Environmental EngineeringEskisehirTurkey Afyon Kocatepe University Faculty of EducationDepartment of Mathematics and Science EducationDivision of Science EducationAfyonTurkey Usak University Vocational School of Health ServicesMedical Laboratory Techniques ProgramUsakTurkey Ministry of Agriculture and Forestry Field Crops Central Research Institute Department of BiotechnologyAnkaraTurkey Bolu Abant Izzet Baysal University Faculty of Arts and ScienceDepartment of BiologyBoluTurkey Bolu Abant Izzet Baysal University Vocational School of the Technical Sciences of BoluFood Technology ProgramBoluTurkey Pamukkale University School of Applied SciencesDepartment of Organic Farming Business ManagementDenizliTurkey

Many industrial processes may quickly proceed with biotechnological and enzymatic *** and production facilitator properties of enzymes have provided variable advantages for ***,enzyme utilization has become inevitable for industry and supplied financial advantages in case of the high energy requirement *** the study,the amylase enzymes were isolated from thermal spring sources,and the effect on bread quality was ***,fungal amylases were isolated from thermal spring sources(29-98◦C)in various places around *** determining the functional properties of amylase enzymes,the most active enzyme was used in bread production to examine their effect on bread *** maximum alpha-amylase activity(38.6 U/mg)has been detected in Aspergillus niger G 2-1 *** compared with the commercially available one,native alpha-amylase increased the bread volume.A significant difference(p<0.01)was found in the color properties and size of the bread between microbial produced in this study and commercially produced *** ppm alpha-amylase addition showed the optimum bread properties for dough processing.

关键词： Alpha-amylase Thermal spring Quality of bread Commercial enzymes

来源：评论

学校读者我要写书评

暂无评论

Relativistic Quantum Simulation of Hydrogen Sulfide for Hydrogen Energy via Hybrid Quantum-Classical Algorithms

arXiv

引用

arXiv 2025年

作者： Hwang, Chi-Chuan Su, Cheng-Fang Yang, Jung-Fan Department of Engineering Science National Cheng Kung University Tainan City701 Taiwan Department of Applied Mathematics National Yang Ming Chiao Tung University Hsinchu City30010 Taiwan Undergraduate Degree Program of Systems Engineering and Technology National Yang Ming Chiao Tung University Hsinchu City30010 Taiwan Chung Cheng Institute of Technology National Defense University Taoyuan City33551 Taiwan

We present a hybrid quantum-classical computational framework for simulating relativistic quantum chemical systems using the variational quantum eigensolver (VQE). Our approach integrates relativistic electron integrals derived from the Dirac–Coulomb Hamiltonian with quantum circuit models constructed via Jordan–Wigner transformation. By employing both heuristic and chemistry-inspired ansätze, we compute ground-state energies and potential energy surfaces (PES) for benchmark molecules including H2, H2O, and H2S. Active-space reduction and Hartree–Fock embedding techniques are used to minimize the number of qubits and Pauli terms, enabling efficient simulation on near-term quantum devices. Our results demonstrate that VQE can reproduce classical full-configuration-interaction energies with millihartree-level accuracy, even under relativistic Hamiltonians. We observe consistent relativistic energy shifts and orbital contraction effects, particularly for the sulfur-containing H2S molecule. The constructed PES allow for equilibrium geometry prediction and activation energy analysis. This work highlights the feasibility and scalability of applying quantum algorithms to relativistic electronic structure problems, paving the way for future simulations of heavier-element systems in quantum chemistry. Copyright © 2025, The Authors. All rights reserved.

关键词： Molecular orbitals

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：