检索结果-内蒙古大学图书馆

Unlocking the Secrets Behind Advanced Artificial Intelligence Language Models in Deidentifying Chinese-English Mixed Clinical Text: Development and Validation Study

引用

Journal of Medical Internet Research 2024年第1期26卷 e48443页

作者： Lee, You-Qian Chen, Ching-Tai Chen, Chien-Chang Lee, Chung-Hong Chen, Peitsz Wu, Chi-Shin Dai, Hong-Jie Dialogue System Technical Department Asustek Computer Inc Taipei Taiwan Intelligent System Laboratory Department of Electrical Engineering College of Electrical Engineering and Computer Science National Kaohsiung University of Science and Technology Kaohsiung Taiwan Department of Bioinformatics and Medical Engineering Asia University Taichung Taiwan Center for Precision Health Research Asia University Taichung Taiwan Electromagnetic Sensing Control and AI Computing System Laboratory Department of Electrical Engineering College of Electrical Engineering and Computer Science National Kaohsiung University of Science and Technology Kaohsiung Taiwan Knowledge Discovery and Data Mining Lab Department of Electrical Engineering College of Electrical Engineering and Computer Science National Kaohsiung University of Science and Technology Kaohsiung Taiwan Department of Chemical Engineering Feng Chia University Taichung Taiwan National Center for Geriatrics and Welfare Research National Health Research Institutes Zhunan Taiwan National Institute of Cancer Research National Health Research Institutes Tainan Taiwan School of Post-Baccalaureate Medicine College of Medicine Kaohsiung Medical University Kaohsiung Taiwan Center for Big Data Research Kaohsiung Medical University Kaohsiung Taiwan

Background: The widespread use of electronic health records in the clinical and biomedical fields makes the removal of protected health information (PHI) essential to maintain privacy. However, a significant portion of information is recorded in unstructured textual forms, posing a challenge for deidentification. In multilingual countries, medical records could be written in a mixture of more than one language, referred to as code mixing. Most current clinical natural language processing techniques are designed for monolingual text, and there is a need to address the deidentification of code-mixed text. Objective: The aim of this study was to investigate the effectiveness and underlying mechanism of fine-tuned pretrained language models (PLMs) in identifying PHI in the code-mixed context. Additionally, we aimed to evaluate the potential of prompting large language models (LLMs) for recognizing PHI in a zero-shot manner. Methods: We compiled the first clinical code-mixed deidentification data set consisting of text written in Chinese and English. We explored the effectiveness of fine-tuned PLMs for recognizing PHI in code-mixed content, with a focus on whether PLMs exploit naming regularity and mention coverage to achieve superior performance, by probing the developed models’ outputs to examine their decision-making process. Furthermore, we investigated the potential of prompt-based in-context learning of LLMs for recognizing PHI in code-mixed text. Results: The developed methods were evaluated on a code-mixed deidentification corpus of 1700 discharge summaries. We observed that different PHI types had preferences in their occurrences within the different types of language-mixed sentences, and PLMs could effectively recognize PHI by exploiting the learned name regularity. However, the models may exhibit suboptimal results when regularity is weak or mentions contain unknown words that the representations cannot generate well. We also found that the availability of cod

关键词： ChatGPT code mixing deidentification electronic health record large language model pretrained language model

来源：评论

学校读者我要写书评

暂无评论

Optimal Linear Deception Attacks on Remote State Estimation with Constrained Alarm Rates: A Low-Dimensional Case

Optimal Linear Deception Attacks on Remote State Estimation ...

引用

IEEE Conference on Decision and control

作者： Jun Shang Hanwen Zhang Jing Zhou Tongwen Chen Department of Control Science and Engineering Shanghai Research Institute for Intelligent Autonomous Systems National Key Laboratory of Autonomous Intelligent Unmanned Systems and Frontiers Science Center for Intelligent Autonomous Systems Tongji University Shanghai China Key Laboratory of Knowledge Automation for Industrial Processes of Ministry of Education School of Automation and Electrical Engineering University of Science and Technology Beijing Beijing China Department of Electrical and Computer Engineering University of Alberta Edmonton AB Canada

ISBN: (数字)9798350316339

ISBN: (纸本)9798350316346

This study addresses linear attacks on remote state estimation within the context of a constrained alarm rate. Smart sensors, which are equipped with local Kalman filters, transmit innovations instead of raw measurements through a wireless communication network. This transmission is vulnerable to malicious data interception and manipulation by attackers. The aim of this research is to identify the optimal attack strategy that degrades the system performance while adhering to stealthiness constraints. A notable innovation of this paper is the direct association of the attack’s stealthiness with the alarm rate, diverging from traditional approaches that rely on the covariance of the innovation or the Kullback–Leibler divergence, which are conventional metrics that have been extensively explored in previous studies. Our findings reveal that the optimal attack strategy exhibits some structural characteristics in systems of low dimensions. The performance of the proposed attack strategy is demonstrated through numerical examples.

关键词： Wireless communication Measurement Technological innovation System performance Kalman filters State estimation Intelligent sensors

来源：评论

学校读者我要写书评

暂无评论

Non-Euclidean Monotone Operator Theory with Applications to Recurrent Neural Networks

arXiv

引用

arXiv 2022年

作者： Davydov, Alexander Jafarpour, Saber Proskurnikov, Anton V. Bullo, Francesco The Center for Control Dynamical Systems and Computation University of California Santa Barbara93106-5070 United States The School of Electrical and Computer Engineering Georgia Institute of Technology United States The Department of Electronics and Telecommunications Politecnico di Torino Turin Italy

We provide a novel transcription of monotone operator theory to the non-Euclidean finite-dimensional spaces l1 and l∞. We first establish properties of mappings which are monotone with respect to the non-Euclidean norms l1 or l∞. In analogy with their Euclidean counterparts, mappings which are monotone with respect to a non-Euclidean norm are amenable to numerous algorithms for computing their zeros. We demonstrate that several classic iterative methods for computing zeros of monotone operators are directly applicable in the non-Euclidean framework. We present a case-study in the equilibrium computation of recurrent neural networks and demonstrate that casting the computation as a suitable operator splitting problem improves convergence rates. Copyright © 2022, The Authors. All rights reserved.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Measurement-device-independent quantum key distribution with passive time-dependent source side channels

引用

Physical Review A 2022年第6期106卷 062618-062618页

作者： J. Eli Bourassa Amita Gnanapandithan Li Qian Hoi-Kwong Lo Department of Physics University of Toronto Toronto Canada Department of Electrical and Computer Engineering University of Toronto Toronto Canada Center for Quantum Information and Quantum Control University of Toronto Toronto Canada Department of Physics University of Hong Kong Hong Kong

While measurement-device-independent (MDI) quantum key distribution (QKD) allows two trusted parties to establish a shared secret key from a distance without needing to trust a central detection node, their quantum sources must be well characterized, with side channels at the source posing the greatest loophole to the protocol's security. In this paper, we identify a time-dependent side channel in a common polarization-based QKD source that employs a Faraday mirror for phase stabilization. We apply a recently developed numerical proof technique [Phys. Rev. A 99, 062332 (2019)] to quantify the sensitivity of the secret key rate to the quantum optical model for the side channel, and to develop strategies to mitigate the information leakage. In particular, we find that the MDI three-state and BB84 protocols, while yielding the same key rate under ideal conditions, have diverging results in the presence of a side channel, with BB84 proving more advantageous. While we consider only a representative case example, we expect the strategies developed and key rate analysis method to be broadly applicable to other leaky sources.

关键词： Optical quantum information processing Quantum communication Quantum cryptography

来源：评论

学校读者我要写书评

暂无评论

Robust Frequency Regulation for Dual-Area Interconnected Grids Using Hybrid controller: A Comparative Study

Robust Frequency Regulation for Dual-Area Interconnected Gri...

引用

Smart Technologies for Power, Energy and control (STPEC), IEEE International Conference on

作者： Awadh Ba Wazir Abdullah A. Alhussainy Abdulraheem H. Alobaidi Aatif Altaf Anil Kumar Mahendra Kumar Sultan Alghamdi Department of Electrical and Computer Engineering Faculty of Engineering King Abdulaziz University Jeddah Saudi Arabia Center of Research Excellence in Renewable Energy and Power Systems King Abdulaziz University Jeddah Saudi Arabia Instrumentation and Control Engineering Department Dr. B R Ambedkar National Institute of Technology Jalandhar Jalandhar Punjab India

This paper introduces a robust controller designed for load frequency control in a dual-area integrated power grid. Here, the suggested controller is a blend of a fuzzy logic controller with an integral controller. The parameters of the integral controller and frequency bias settings are optimized to enhance the dynamic response of the proposed controller. To attain this, three distinct optimization algorithms are employed, i.e., genetic algorithm, simulated annealing, and pattern search. A new objective function using settling time, settling-max, and settling-min with a suitable weight factor is used to improve the parameters estimation process. A comparative analysis is performed using the proposed approach and classical-I controller under two cases considering several load disturbance scenarios. Furthermore, the suggested hybrid controller is evaluated and compared with similar models in the literature. As expected, the proposed controller exhibits superior performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enabling Smart Agriculture in Nigeria: Application of Digital-Twin Technology 1

Enabling Smart Agriculture in Nigeria: Application of Digita...

引用

1st International Conference on Multidisciplinary engineering and Applied Science, ICMEAS 2021

作者： Elijah, Olakunle Rahim, Sharul Kamal A. Emmanuel, Abioye Abiodun Salihu, Yahaya Otuoze Usman, Zubair Gatugel Jimoh, Adinoyi Momoh Wireless Communication Center School of Electrical Engineering University of Technology Malaysia Johor Bahru Malaysia School of Electrical Engineering University of Technology Malaysia Control and Mechatronics Engr. Dept. Johor Bahru Malaysia Kaduna Polytechnic Computer Engineering Department Kaduna Nigeria Saudi Telecommunication Company Riyadh Saudi Arabia

ISBN: (纸本)9781665434935

The digital twin (DT) is an emerging technology and one of the industry 4.0 technologies. The research in the application of DT in agriculture is currently attracting research interest. In this paper, we provide an overview of DT and discuss possible areas in which it can enable smart agriculture in Nigeria. The benefits and challenges of deploying the DT are also presented. Finally, methods that can be adopted in the application of DT towards solving the problems facing Nigeria's agriculture sector are proposed. © 2021 IEEE.

关键词： Agriculture

来源：评论

学校读者我要写书评

暂无评论

Joint Multi-stage Planning of Renewable Generation, HESS, and AESS for Deeply Decarbonizing Power Systems with High-penetration Renewables

引用

IEEE Transactions on Sustainable Energy 2024年

作者： Yu, Zhipeng Chi, Yingtian Lin, Jin Liu, Feng Li, Jiarong Song, Yonghua Ren, Zhengwei Lu, Chengcheng Ji, Mengbo Tsinghua University State Key Laboratory of Control and Simulation of Power Systems and Generation Equipment Department of Electrical Engineering Beijing100087 China Tsinghua University Sichuan Energy Internet Research Institute Chengdu610213 China Harvard University Harvard John A. Paulson School of Engineering and Applied Sciences Cambridge United States University of Macau Department of Electrical and Computer Engineering Macau999078 China Tsinghua University Department of Electrical Engineering Beijing100087 China China Electric Power Planning & Engineering Institute National Electric Power Planning and Research Center Beijing100087 China Co. Ltd. Beijing100087 China Ordos City Hanxia Renewable Energy Co. Ltd. Ordos014300 China

The further decarbonization of power systems with high renewable energy penetration faces the problem of inter-day intermittence of renewable energy sources (RES) and the seasonal imbalance between RES and load demand, due to the limited regulation ability of conventional units such as thermal generation. Regular solutions based on battery energy storage system (BESS) are too costly to be practical. To address issues above, hydrogen energy storage system (HESS) and ammonia energy storage system (AESS) are introduced to gradually replace thermal generation. Specifically, first, HESS and AESS are incorporated into the multi-stage capacity expansion planning (MSCEP) model with carbon emission reduction constraints. Yearly data with hourly time resolution are utilized for each stage to accurately describe the intermittence of RES. Then, an improved column generation (CG) with Dantzig-Wolfe decomposition (DWD) embedded solution approach is used to efficiently solve the large-scale MSCEP model. Finally, a real-life system in China is studied. The results indicate that the proposed method can guarantee high power supply reliability (PSR) under different renewable energy penetration levels, avoiding the low PSR problem that may be caused by the existing typical scenario-based method (TSM) under high penetration (≥30%). Moreover, HESS and AESS are essential to reduce the cost of decarbonization. Especially under the goal of carbon neutrality, the contribution of HESS and AESS in reducing levelized cost of energy (LCOE) reaches 12.28% and 14.59%, respectively, leading to a levelized cost of carbon reduction (LCOCr) of 998 RMB/t. © 2010-2012 IEEE.

关键词： Hydrogen storage

来源：评论

学校读者我要写书评

暂无评论

Optical Properties and Behavior of Whispering Gallery Mode Resonators in Complex Microsphere Configurations: Insights for Sensing and Information Processing Applications

arXiv

引用

arXiv 2023年

作者： Banad, Yaser M. Hasan, Syed Mohammad Abid Sharif, Sarah S. Veronis, Georgios Gartia, Manas Ranjan The School of Electrical and Computer Engineering University of Oklahoma NormanOK73019 United States The Department of Mechanical and Industrial Engineering Louisiana State University Baton RougeLA70803 United States The Center for Quantum Research and Technology University of Oklahoma NormanOK73019 United States The School of Electrical Engineering and Computer Science Louisiana State University Baton RougeLA70803 United States Center for Computation and Technology Louisiana State University Baton RougeLA70803 United States

Whispering gallery mode (WGM) resonators are garnering significant attention due to their unique characteristics and remarkable properties. When integrated with optical sensing and processing technology, WGM resonators offer numerous advantages, including compact size, high sensitivity, rapid response, and tunability. This paper comprehensively investigates the optical properties and behavior of WGMs in complex microsphere resonator configurations. The findings underscore the potential of WGMs in sensing applications and their role in advancing future optical information processing. The study explores the impact of configuration, size, excitation, polarization, and coupling effects on the WGMs’ properties. The paper provides crucial insights and valuable guidance for designing and optimizing microsphere resonator systems, enabling their realization for practical applications. © 2023, CC BY.

关键词： Optical data processing

来源：评论

学校读者我要写书评

暂无评论

A Coalitional Game for Demand-Side Management in a Low-Voltage Resistive Micro-Grid with Multiple Electricity Retailers

arXiv

引用

arXiv 2024年

作者： Mendoza, Fernando Genis Baldivieso-Monasterios, Pablo R. Bauso, Dario Konstantopoulos, George The Department of Automatic Control and Systems Engineering The University of Sheffield Mappin Street SheffieldS1 3JD United Kingdom The Department of Electrical and Computer Engineering University of Patras Rion26500 Greece The Jan C. Willems Center for Systems and Control ENTEG Fac. Science and Engineering University of Groningen Nijenborgh 4 Groningen9747 AG Netherlands The Netherlands and Dipartimento di Ingegneria Università di Palermo viale delle Scienze Palermo Italy

An existing challenge in power systems is the implementation of optimal demand management through dynamic pricing. This paper encompasses the design, analysis and implementation of a novel on-line pricing scheme based on coalitional game theory. The setting consists of a network with multiple energy retailers competing to attract consumers by announcing a price in a hierarchical leader-follower structure. The process of coalition formation under such a pricing scheme can be viewed as a game for which we show that a Stackelberg equilibrium exists, i.e., given a price, consumers will respond by conforming to a reciprocal power consumption quantity. We propose a coalition formation algorithm and perform a game-theoretic stability analysis on the resulting coalitions. We integrate the pricing setting with a resistive micro-grid dynamic model. In this context we analyse the behaviour of the integrated system, bridging the gap between market and physical layers of the problem. Simulations provide a comparison of profits generated by the proposed scheme against a more traditional single retailer scheme, while simultaneously showing convergence towards a steady-state equilibrium. Additionally, we shed light into the system's physical response when subject to our proposed pricing scheme. © 2024, CC BY.

关键词： Costs

来源：评论

学校读者我要写书评

暂无评论

Kartalol: A New Deep Neural Network Framework Based on Transfer Learning for Iris Segmentation and Localization Task: New Dataset for Iris Segmentation

SSRN

引用

SSRN 2022年

作者： Khiarak, Jalil Nourmohammadi Oskouei, Amin Golzari Nasab, Samaneh Salehi Jaryani, Farhang Moafinejad, Seyed Naeim Pourmohamad, Rana Amini, Yasin Noshad, Morteza Institute of Control and Computation Engineering Warsaw University of Technology Warsaw Poland Department of Computer Engineering Faculty of Electrical and Computer Engineering University of Tabriz Iran School of Engineering Lorestan University Aleshtar Campus Aleshtar Iran Malek-Ashtar University of Technology Department of Physics Shahid Beheshti University Tehran Iran School of Computing Informatics and Decision Systems Engineering Arizona State University AZ United States Faculty of Electrical and Computer Engineering University of Kharazmi Iran Stanford University United States

Iris segmentation and localization in unconstrained environments is challenging due to long distances, illumination variations, limited user cooperation, and moving subjects. Some existing methods in the literature, each of which has somehow mitigated some of the mentioned issues. In this paper, motivated by these weaknesses, we propose a framework that employs a deep neural network-based approach to iris segmentation and localization. The proposed framework is based on a U-Net architecture that has been initialized with a pre-trained MobileNetV2 model. In addition, we have collected 1000 images to study the detectors in iris recognition scenarios better. The provided dataset (KartalOl) is available free for the research community. In the proposed framework, to better generalizability, we fine-tune the MobileNetV2 model on the provided data for NIR-ISL 2021 from the CASIA-Iris-Asia, CASIA-Iris-M1, and CASIA-Iris-Africa and our dataset. Also, data augmentation technics are applied on images. We chose the binarization threshold for the binary masks by iterating over the images in the provided dataset. The proposed framework is trained and tested in CASIA-Iris-Asia, CASIA-Iris-M1, CASIA-Iris-Africa, along the KartalOl dataset. The experimental results highlight that our method surpasses state-of-the-art methods on mobile-based benchmarks. The codes and evaluation results are publicly available at https://***/Jalilnkh/KartalOl-NIR-ISL2021031301. © 2022, The Authors. All rights reserved.

关键词： Deep neural 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：