检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Seedat, Nabeel Tozzi, Caterina Ardiaca, Andrea Hita van der Schaar, Mihaela Weatherall, James Taylor, Adam Department of Applied Mathematics and Theoretical Physics University of Cambridge Cambridge United Kingdom Data Science & Artificial Intelligence BioPharmaceuticals R&D AstraZeneca Barcelona Spain Data Science & Artificial Intelligence BioPharmaceuticals R&D AstraZeneca Cambridge United Kingdom

Background: The reuse of historical clinical trial data has significant potential to accelerate medical research and drug development. However, interoperability challenges, particularly with missing medical codes, hinder effective data integration across studies. While Large Language Models (LLMs) offer a promising solution for automated coding without labeled data, current approaches face challenges on complex coding tasks. Methods: We introduce ALIGN, a novel compositional LLM-based system (i.e. compound AI system) for automated, zero-shot medical coding. ALIGN follows a three-step process: (1) diverse candidate code generation;(2) self-evaluation of codes and (3) confidence scoring and uncertainty estimation enabling human deferral to ensure reliability. We evaluate ALIGN on harmonizing medication terms into Anatomical Therapeutic Chemical (ATC) and medical history terms into Medical dictionary for regulatory Activities (MeddrA) codes extracted from 22 immunology trials (10 rheumatoid arthritis, 12 systemic lupus erythematosus) and compare to LLM baselines, including prompting and retrieval Augmented Generation (rAG). results: ALIGN outperformed the LLM baselines, while also providing capabilities for trustworthy deployment. For MeddrA coding, ALIGN achieved high accuracy across all levels, matching rAG and excelling at the most specific levels (87-90% for HLGT). For ATC coding, ALIGN demonstrated superior performance, particularly at lower hierarchy levels (ATC Level 4), with 72-73% overall accuracy and 86-89% accuracy for common medications, outperforming baselines by 7-22%. ALIGN's uncertainty-based deferral improved accuracy by 17% to ±90% accuracy with 30% deferral, notably enhancing performance on uncommon medications. ALIGN achieves this cost-efficiently at $0.0007 and $0.02 per code for GPT-4omini and GPT-4o, reducing barriers to clinical adoption. Conclusion: ALIGN advances automated medical coding for clinical trial data, contributing to enhanced data i

关键词： Clinical research

来源：评论

学校读者我要写书评

暂无评论

design of a Multispectral Imaging System for Unmanned Aerial Vehicles 8

Design of a Multispectral Imaging System for Unmanned Aerial...

引用

Multispectral, Hyperspectral, and Ultraspectral remote Sensing Technology, Techniques, and Applications VIII 2024

作者： Huang, Ting-Ming Lin, Yu-Chuan Tsai, Yu-An Chao, Cheng-Tang Chen, Ming-Fu Taiwan Instrument Research Institute National Applied Research Laboratories 20 R&D Road VI Hsinchu Science-Based Industrial Park Hsinchu300 Taiwan Department of Mechanical Engineering National Yunlin University of Science and Technology 123 University Road Section 3 Yunlin Douliou64002 Taiwan

ISBN: (数字)9781510682757

ISBN: (纸本)9781510682740

remote sensing has been applied to land, water, ocean, and atmosphere monitoring in earth science for several decades. UAV-based remote sensing also gradually becomes an important research or tool for better understanding our living earth and environment considering less cost, flexibility of operation, and controllability of image acquisition. A mutlispetcral imager with four spectral bands is designed for ground and vegetation monitoring that installed on a hybrid vertical takeoff and landing (VTOL) UAV. A rGB camera with an Ir-cut filter and a monochrome camera with an Ir range or red-edge range filter are included. Passive altitude controlled is adopted to reduce the power requirement. © 2024 SPIE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Efficient Auto Scaling of Pods in Kubernetes: Accelerating Continuous delivery with KEPTN 5

Efficient Auto Scaling of Pods in Kubernetes: Accelerating C...

引用

5th International Conference on Electronics and Sustainable Communication Systems, ICESC 2024

作者： Sivaraman, Perumal Prabaharan, G. rajasekar, Vani Sarveshwaran, Velliangiri University of Technology and Applied Sciences Dept of Information Technology Al Musanna Oman Vel Tech Rangarajan Dr. Saguthala R&d Institute of Science and Technology Department of Cs Engineering Chennai Avadi India Kongu Engineering College Department of Information Technology Erode Perundurai India Srm Institute of Science and Technology Department of Computational Intelligence Kattankulathu Campus Chennai India

ISBN: (纸本)9798350379945

Model deployment in machine learning has become recognised as an emerging field of research in recent years. It can be viewed as a method similar to conventional software development. Organisations can move more quickly and smoothly when development and operations (devOps) practises like Continuous Integration and Continuous delivery (CI/Cd) are used. Various software development approaches are available for enterprise applications. Micro-services architecture has become very popular among these accessible software development approaches. Enterprise applications, which are frequently sophisticated and require out-of-the-box scalability and low latency, integrate well with the micro-service design. For enterprise applications, microservices in a containerized cloud environment are particularly helpful. It is also extremely important from a software development standpoint in the software business to find and fix errors early on in the development process rather than once they have reached the level of the production environment. Kubernetes is a creative and well-integrated platform solution for running and controlling containerized applications gracefully and effectively. developers can easily build and maintain clusters with the managed Kubernetes service known as AKS. It makes containerized application deployment and management possible. AKS offers serverless Kubernetes, a continuous integration and delivery experience that is integrated, as well as enterprise-level security and governance. Users of Microsoft Azure will find that AKS offers several appealing features that make it simple to set up, administer, scale, and monitor an AKS cluster. © 2024 IEEE.

关键词： Software design

来源：评论

学校读者我要写书评

暂无评论

Utilizing Artificial Intelligence for Plant Phenotyping in Soilless Farming: An Innovative deep Learning Approach on a Unique dataset 1

Utilizing Artificial Intelligence for Plant Phenotyping in S...

引用

1st IEEE International Conference on Smart Power Control and renewable Energy, ICSPCrE 2024

作者： reddy, d. Jaya Narayana Krishna Priya, r. Kumar, J. Arun Prasad, P. dharani Nawaz, Mustafa Venu, Nookala G Pullaiah College of Engineering and Technology India University of Technology and Applied Sciences Research and Consultancy Department Governorate of Musandam Oman Vel Tech Rangarajan Sagunthala R&d Institute of Science and Technology Department of Ece India Dept of Pharmacology Tirupati India Sri Sairam Institute of Technology Department of Computer Science and Engineering India Centre for IoT Madhya Pradesh Gwalior474005 India

ISBN: (纸本)9798350377002

In the dynamic landscape of agriculture, the convergence of technological advancements and sustainable practices has become imperative. The emergence of soilless farming, driven by hydroponics and aeroponics, presents a promising solution to address food security challenges while mitigating environmental concerns. Central to the success of soilless farming is efficient plant phenotyping, which traditionally relies on labour-intensive methodologies. However, this paradigm is shifting with the integration of Artificial Intelligence (AI) and deep Learning techniques. This research endeavours to pioneer an innovative approach to plant phenotyping in soilless farming by harnessing the power of AI. Leveraging a unique dataset meticulously curated from controlled hydroponic and aeroponic environments, our study aims to redefine the boundaries of agricultural research and practice. By employing state-of-the-art Convolutional Neural Networks (CNNs) and recurrent Neural Networks (rNNs), we dissect complex phenotypic traits encompassing leaf morphology, biomass accumulation, and physiological responses. Through iterative model refinement and validation, we strive to develop a robust framework capable of real-time phenotypic assessment across diverse plant species and growth stages. By synthesizing diverse environmental conditions and perturbations, we augment the original dataset, enhancing model generalization and adaptability. Moreover, through transfer learning techniques, Furthermore, the scalability and accessibility of AI technologies pave the way for democratizing agricultural innovation, fostering inclusive growth and resilience in the face of global challenges. © 2024 IEEE.

关键词： Hydroponics

来源：评论

学校读者我要写书评

暂无评论

FraMark: A Blockchain Marketplace for a 5G Network Management using Fractional NFTs 7

FraMark: A Blockchain Marketplace for a 5G Network Managemen...

引用

7th World Symposium on Communication Engineering, WSCE 2024

作者： Michoulis, George Tsourdinis, Kyros Niotis, George Kyranou, Konstantinos Fountoukidis, Eleutherios Lagkas, Thomas Argyriou, Vasileios Sarigiannidis, Panagiotis Psannis, Konstantinos E. Goudos, Sotirios K. Sidroco Holdings Ltd R&D Dpt. Thessaloniki Greece Sidroco Holdings Ltd R&D Dpt. Nicosia Cyprus Democritus University of Thrace Dpt. of Computer Science Kavala Greece University of Western Macedonia Dpt. of Electrical & Computer Engineering Kozani Greece Kingston University London Kingston Upon Thames Dpt. of Networks and Digital Media Surrey United Kingdom University of Macedonia Department of Applied Informatics Thessaloniki Greece ELEDIA@AUTH School of Physics Aristotle University of Thessaloniki Thessaloniki Greece

ISBN: (纸本)9798331542825

This paper presents FraMark, a blockchain-based framework for 5G network management that utilizes Hyperledger Fabric and fractional Non-Fungible Tokens (NFTs) to optimize resource allocation. We introduce a comprehensive system that fractionalizes digital assets to represent 5G network resources, enhancing efficiency and allocation flexibility. Our framework addresses the challenges of 5G network management by ensuring low latency, high transaction throughput, and secure resource trading. We conduct experiments to evaluate the performance of our approach, including CPU and memory utilization, latency analysis, and block size assessment. The results demonstrate the effectiveness of FraMark in improving network resource utilization and transaction efficiency, validating our framework's claims. By leveraging blockchain technology and innovative resource slicing techniques, FraMark paves the way for dynamic and efficient 5G network management. © 2024 IEEE.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

Biometric Application on Facial Image recognition Techniques 5

Biometric Application on Facial Image Recognition Techniques

引用

5th IEEE International Conference on Computing, Power, and Communication Technologies, IC2PCT 2024

作者： Ambikapathy, A. Beeta, Thiyam deepa Kanna, r. Kishore danquah-Amoah, Archibald ramya, V. Subha Mutheeswaran, U. Galgotias College of Engineering and Technology Department of Electrical and Electronics Engineering UP Greater Noida India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Biomedical Engineering Chennai India Department of Biomedical Engineering Chennai India Accra Technical Universit Faculty of Applied Science Department of Biomedical Equipment Technology Department of Medical Laboratory Ghana Vels Institute of Science Technology and Adbvanced Studies Department of Biomedical Engineering Chennai India

ISBN: (纸本)9798350383522

Currently, the utilisation of biometric traits for the authentication of individuals has become widespread. Various biometric features such as fingerprints, iris patterns, and facial characteristics are employed for the purpose of person authentication. Facial recognition technology is widely recognised as a popular method for person authentication. There exists a variety of algorithms, each with its own set of advantages and disadvantages. dimensionality reduction is a crucial step in facial recognition algorithms due to the presence of multiple facial features within a facial image. The primary objective of this paper is to employ principle component analysis techniques in the face recognition process. Principal Component Analysis (PCA) has been found to yield highly favourable outcomes in the context of dimensionality reduction. Principal Component Analysis (PCA) is a statistical technique that generates eigenvectors. The eigenvectors are combined to form images, which are subsequently used to visualise the eigenfaces. © 2024 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Intelligent Solar Energy Harvesting and Management in IoT Nodes Using deep Self-Organizing Maps 2

Intelligent Solar Energy Harvesting and Management in IoT No...

引用

2nd IEEE International Conference on Emerging research in Computational Science, ICErCS 2024

作者： Shinkar, Anita rajkumar Joshi, drumil Praveen, r.V.S. rajesh, Yelisela Boopalan, K. Singh, dharmendra Dr. D.Y. Patil College of Engineering Department of Computer Engineering Maharashtra Varale India Southern Power Birmingham Alabama Monitoring & Diagnostics Department India Digital Engineering and Assurance Telangana Hyderabad India KLEF Department of Computer Science & Engineering Andhra Pradesh India Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology School of Computing Tamilnadu India School of Management Sciences Department of Applied Sciences & Humanities Lucknow India

ISBN: (纸本)9798331534950

Smart city energy generation must be efficient and dependable. As a result of studies conducted in this field, reliable control schemes for microgrid management have been developed, which seamlessly integrate with smart building management systems. In order for a building microgrid's solar energy system to recover from problems, this article suggests reliable controllers and the hardware to install them. Training models and Internet of Things (IoT) sensors provide the backbone of this proposed approach. When it comes to organizational and industrial contexts, sensors have evolved significantly with the introduction of the IoT. Pressure, optical, temperature, chemical sensors, and proximity are just a few examples of the many types of data that IoT devices may collect and send through sensor networks, allowing for greater efficiency. The model achieves a 91.37% accuracy rate in solar energy harvesting prediction after being trained using the Extended dSOM. © 2024 IEEE.

关键词： Conformal mapping

来源：评论

学校读者我要写书评

暂无评论

Preliminary study on degradation mechanisms of plasma-treated dr1 by atomistic simulations

引用

Plasma Science and Technology 2025年第3期27卷 94-103页

作者： Namunakhon NABIYEVA Tohir AKrAMOV davronjon ABdUVOKHIdOV Yuantao ZHANG Maksudbek YUSUPOV Jamoliddin rAZZOKOV Institute of Fundamental and Applied Research National Research University TIIAMETashkent 100000Uzbekistan Laboratory of Experimental Biophysics Centre for Advanced TechnologiesTashkent 100174Uzbekistan Department of Theoretical Physics National University of Uzbekistan named after Mirzo UlugbekTashkent 100174Uzbekistan Institute of Nuclear Physics Academy of Sciences of UzbekistanTashkent 100214Uzbekistan R&D Center New Uzbekistan UniversityTashkent 100007Uzbekistan School of Electrical Engineering Shandong UniversityJinan 250061People’s Republic of China Department of Information Technologies Tashkent International University of EducationTashkent 100207Uzbekistan Kokand University Andijan Branch Andijan 170619Uzbekistan Department of Biotechnology Tashkent State Technical UniversityTashkent 100095Uzbekistan

Cold atmospheric plasma(CAP)has emerged as a promising technology for the degradation of organic dyes,but the underlying mechanisms at the molecular level remain poorly *** density-functional tight-binding(dFTB)-based quantum chemical molecular dynamics at 300 K,we have performed numerical simulations to investigate the degradation mechanism of disperse red 1(dr)interacting with CAP-generated oxygen *** hundred directdynamics trajectories were calculated for up to 100 ps simulation time,after which hydrogenabstraction,benzene ring-opening/expanding,formaldehyde formation and modification in the chromophoric azo group which can lead to color-losing were *** latter was obtained with yields of around 6%at the given *** findings not only enhance our understanding of CAP treatment processes but also have implications for the development of optimized purification systems for sustainable wastewater *** study underscores the utility of dFTB simulations in unraveling complex chemical processes and guiding the design of advanced treatment strategies in the context of CAP technology.

关键词： wastewater treatment disperse red 1 cold atmospheric plasma reactive oxygen species reactive molecular dynamics degradation mechanisms

来源：评论

学校读者我要写书评

暂无评论

Innovative Techniques in the Construction of Very Large Scale Integration Circuits for Low-Power and High-Performance Circuits 2

Innovative Techniques in the Construction of Very Large Scal...

引用

2nd IEEE Global Conference on Communications and Information Technologies, GCCIT 2024

作者： Saravanan, V. Sasikala, G. Gomathi, P. Kirubakaran, d. rajalingam, A. Pagunuran, Jubert r. Saveetha University Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Nano Electronics Materials and Sensors Tamilnadu Chennai India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Ece Avadi Chennai India V.S.B. Engineering College Department of Ece India R.M.K Engineering College Department of Computer Science and Engineering India University of Technology and Applied Sciences College of Engineering and Technology Engineering Department Shinas Oman

ISBN: (纸本)9798350388916

Portable electronic gadgets and high-performance computing systems have increased demand for low-power, high-performance integrated circuits (ICs). VLSI technology, which creates integrated circuits with dozens to millions of transistors on a chip, is leading these efforts. This research investigates low-power, high-performance VLSI circuit construction methods. We start with VLSI design fundamentals and power management and performance optimization concerns. The constraints of traditional VLSI design methods in satisfying current electronics' strict requirements are examined. VLSI design methodology development and evaluation are the focus of this research. Advanced power optimization methods include MTCMOS, adaptive body biasing, and power gating. We also study clock tree improvement, signal integrity enhancement, and new materials and device topologies for high performance. In addition, we study how machine learning techniques automate and optimize circuit placement, routing, and timing in VLSI design. AI handles the complexity of current VLSI designs and finds optimal design parameters for minimal power and high performance. Scaling VLSI circuits to newer technology nodes raises process variance, leakage current, and thermal management difficulties, which the research tackles. These issues can be overcome with new ways to keep VLSI circuits scaling while preserving performance and power efficiency. Finally, case studies and experimental findings show that the offered methods work in real-world applications. These findings demonstrate significant power usage and performance benefits over typical VLSI design. In conclusion, our research advances VLSI technology by developing low-power, high-performance integrated circuits. The proposed VLSI design methods and solutions could lead to more efficient and powerful electronic systems. © 2024 IEEE.

关键词： VLSI circuits

来源：评论

学校读者我要写书评

暂无评论

Ensemble Approach for Optimizing Variable rigidity Joints in robotic Manipulators Using MOALO-MOdA 6th

Ensemble Approach for Optimizing Variable Rigidity Joints in...

引用

6th International Conference on Intelligent Computing and Optimization, ICO 2023

作者： Shanmugasundar, G. Pal, Subham Chohan, Jasgurpeet Singh Kalita, Kanak Department of Mechanical Engineering Sri Sairam Institute of Technology Chennai India Department of Aerospace Engineering and Applied Mechanics Indian Institute of Engineering Science and Technology Shibpur India Department of Mechanical Engineering and University Centre for Research and Development Chandigarh University Mohali India Department of Mechanical Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Avadi India

ISBN: (纸本)9783031503290

A novel ensemble-based optimization technique is proposed for designing a robot manipulator variable stiffness joint. A multi-objective optimization is performed by considering the maximization of generated torque and the minimization of the weight of the joints. This investigation considers three design parameters (i.e., inner stator width, outer stator width, and magnet height) to maximize torque and reduce weight. Multi-objective ant lion optimization (MOALO) and multi-objective dragonfly algorithm (MOdA) optimization techniques are employed to generate Pareto fronts. These multiple Pareto fronts from the same algorithm are collated and condensed using non-dominated sorting (NdS) to reject the most dominant solutions. These new and improved Pareto fronts are called MOALO and MOdA ensembles. Next, the MOALO and MOdA ensemble Pareto front solutions are collated together, and NdS is performed again. The resulting Pareto front containing solutions of both MOALO and MOdA is referred to as the MOALO-MOdA ensemble. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Multiobjective optimization

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：