检索结果-内蒙古大学图书馆

Proceedings of the 55th Annual IEEE/ACM International Symposium on Microarchitecture

作者： Xueliang Li Zhuobin Shi Junyang Chen Yepang Liu National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China College of Computer Science and Software Engineering Shenzhen University China Research Institute of Trustworthy Autonomous Systems Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation and Department of Computer Science and Engineering Southern University of Science and Technology China

ISBN: (纸本)9781665462723

In the age of AI, mobile architectures such as smartphones are still "cold machines"; machines do not feel. If the architecture is able to feel users' feelings and runtime user experience (UX), it will accordingly adapt performance/energy to find the optimal system-operating state that consumes the least energy to satisfy users. In this paper, we will utilize users' facial expressions (FEs) to learn their runtime UX. We know that FEs are the natural and direct way for humans to convey their emotions and feelings. Our study reveals that FEs also reflect UX. Our research for the first time quantifies the link between FEs and UX. Leveraging this link, the architecture will be able to use the front camera to see FEs and feel users' UX. Based on UX, the architecture can appropriately provision computing resources. We propose Vi-energy system to realize the above idea. Our evaluation shows that Vi-energy reduces energy consumption by 52.9% at maximum and secures UX.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Cooperative Co-Evolution Algorithm with Variable-Importance Grouping for Large-Scale Optimization

A Cooperative Co-Evolution Algorithm with Variable-Importanc...

引用

Congress on Evolutionary Computation

作者： Yongfeng Li Yuze Zhang Lijia Ma Junkai Ji Dugang Liu Victor C. M. Leung Jianqiang Li College of Computer Science and Software Engineering Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Guangdong Laboratory of Artificial Intelligence and Digital Economy Shenzhen China Artificial Intelligence Research Institute Shenzhen MSU-BIT University Shenzhen China Department of Electrical and Computer Engineering The University of British Columbia Vancouver Canada

ISBN: (数字)9798350308365

ISBN: (纸本)9798350308372

Cooperative co-evolution (CC) is a promising direction in solving large-scale multiobjective optimization problems (LMOPs). However, most existing methods of grouping decision variables face some difficulties when searching in the huge search space. Specifically, the methods of grouping decision variables can be classified into two types, i.e., high-consumption grouping methods and non-consumption grouping methods. On the one hand, the former ones divide the decision variables into different groups based on the correlation analysis between variables, which consume much evaluation. This way may lead to premature convergence within limited computational resources. On the other hand, the later ones allocate the decision variables into sub-groups based on some metrics, e.g., order and size, which consume no evaluation while may cause the search fall into local optima. To alleviate the above issues, this paper proposes a CC-based algorithm with a variable-importance grouping (VIG) method, called VICCA. Firstly, the decision variables are classified into several subgroups according to their importance quantified by a meta-gene construction method. Secondly, a CC strategy is designed to simultaneously optimize all subgroups of decision variables formed by VIG using the differential evolution operator, which aims to accelerate the convergence speed. Thirdly, a global evolutionary strategy is proposed to optimize original decision variable space by the competitive swarm optimizer, aiming to maintain the diversity. Finally, the experiments demonstrate that our proposed VICCA has the significant advantage in solving LMOPs when compared with state-of-the-art evolutionary algorithms.

关键词： Measurement Correlation Sociology Evolutionary computation Reinforcement learning Germanium Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Hyperbolic Neural Network Based Preselection for Expensive Multi-Objective Optimization

引用

IEEE Transactions on Evolutionary Computation 2024年 1-1页

作者： Li, Bingdong Yang, Yanting Hong, Wenjing Yang, Peng Zhou, Aimin Shanghai Institute of AI for Education the School of Computer Science and Technology and the Shanghai Frontiers Science Center of Molecule Intelligent Syntheses East China Normal University Shanghai China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Department of Computer Science and Engineering Guangdong Key Laboratory of Brain-Inspired Intelligent Computation Southern University of Science and Technology Shenzhen China

A series of surrogate-assisted evolutionary algorithms (SAEAs) have been proposed for expensive multi-objective optimization problems (EMOPs), building cheap surrogate models to replace the expensive real function evaluations. However, the search efficiency of these SAEAs is not yet satisfactory. More efforts are needed to further exploit useful information from the real function evaluations in order to better guide the search process. Facing this challenge, this paper proposes a Hyperbolic Neural Network (HNN) based preselection operator to accelerate the optimization process based on limited evaluated solutions. First, the preselection task is modeled as a multi-label classification problem where solutions are classified into different layers (ordinal categories) through -relaxed objective aggregation. Second, in order to resemble the hierarchical structure of candidate solutions, a hyperbolic neural network is applied to tackle the multi-label classification problem. The reason for using HNN is that hyperbolic spaces more closely resemble hierarchical structures than Euclidean spaces. Moreover, to alleviate the data deficiency issue, a data augmentation strategy is employed for training the HNN. In order to evaluate its performance, the proposed HNN-based preselection operator is embedded into two surrogate-assisted evolutionary algorithms. Experimental results on two benchmark test suites and three real-world problems with up to 11 objectives and 150 decision variables involving seven state-of-the-art algorithms demonstrate the effectiveness of the proposed method. IEEE

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Smart Class on Android: A Handy Classroom Scheduling Solution

Smart Class on Android: A Handy Classroom Scheduling Solutio...

引用

Next Generation Communication & Information Processing (INCIP), International Conference on

作者： Vishnuraja Palanisamy M. Thiyagarajan R. Bhavani Arun Anthonisamy K. Manivannan S. Vaishnavi Department of Artificial Intelligence and Data Science Builders Engineering College Kangeyam Tamil Nadu India Department of Computer Science and Engineering School of Computing Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Avadi Chennai Tamil Nadu India Department of Electronics and Communication Engineering K. Ramakrishnan College of Technology Trichy Tamil Nadu India Department of Computer Science and Business System Panimalar Engineering College Chennai Tamil Nadu India Department of Information Science and Engineering School of Computer Science & Engineering JAIN (Deemed-to-be) University Bengaluru Karnataka India Department of Information Technology Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education (MAHE) Manipal India

ISBN: (数字)9798331528140

ISBN: (纸本)9798331528157

Classroom scheduling is vital but difficult for educational institutions, especially those with large student populations and diverse needs. Traditional methods using outdated software or manual processes often cause inefficiencies, disagreements, and administrative workload. In low-resource regions without access to cutting-edge technology and infrastructure, these issues are severe. This paper introduces Android-based SmartClass Mobile to transform classroom scheduling. The program's SOA-based functionality offers flexibility, adaptability, and integration with institution-specific procedures. The Heuristic algorithm and Solution Space Navigation (SSN) tackle scheduling problems such as room availability, multimedia needs, and seating capacities. SSN dynamically resolves conflicts by exploring alternate configurations, while the Heuristic Algorithm assigns time slots and classrooms depending on availability and priority. SmartClass Mobile analysis indicates benefits. The solution reduces conflicts, increases user satisfaction, and decreases scheduling time by 50% compared to manual methods with 85% test user approval. Due to its mobile-first approach, the initiative is open to urban and rural institutions. Dependence on internet access for some functions is a downside, especially in resource-constrained contexts. The findings suggest that SmartClass Mobile provides a scalable, effective, and simple classroom scheduling solution. Mobile technology, advanced algorithms, and SOA concepts make it valuable for school administrators. Additions like AI and machine learning will boost its potential.

关键词： Navigation Heuristic algorithms Software algorithms Manuals Transforms Scheduling Software Real-time systems Mobile applications Reliability

来源：评论

学校读者我要写书评

暂无评论

Mining Whole-liver Information with Deep Learning for Preoperatively Predicting HCC Recurrence-free Survival *

Mining Whole-liver Information with Deep Learning for Preope...

引用

Annual International Conference of the IEEE engineering in Medicine and Biology Society (EMBC)

作者： Chao Huang Peijun Hu Yu Tian Yiwei Gao Yangyang Wang Qi Zhang Tingbo Liang Jingsong Li Research Center for Healthcare Data Science Zhejiang Laboratory Hangzhou China Engineering Research Center of EMR and Intelligent Expert System Ministry of Education College of Biomedical Engineering and Instrument Science Zhejiang University Hangzhou China Department of Hepatobiliary and Pancreatic Surgery the First Affiliated Hospital Zhejiang University School of Medicine Hangzhou China Research Center for Healthcare Data Science of Zhejiang Laboratory Hangzhou China

Hepatocellular carcinoma (HCC) is globally a leading cause of cancer death. Non-invasive pre-operative prediction of HCC recurrence-free survival (RFS) after resection is essential but remains challenging. Previous models based on medical imaging focus only on tumor area while neglecting the whole liver condition. In fact, HCC patients usually suffer from chronic liver diseases which also hamper the patient survival. This work aims to develop a novel convolutional neural network (CNN) to mine whole-liver information from contrast-enhanced computed tomography (CECT) to predict RFS after hepatic resection in HCC. Our proposed RFSNet takes liver regions from CECT as input, and outputs a risk score for each patient. Cox proportional-hazards loss was applied for model training. A total of 215 patients with primary HCC and treated with hepatic resection were included for analysis. Patients were randomly split into developing subcohort and testing subcohort by 4:1. The developing subcohort was further split into the training subcohort and validation subcohort for model training. Baseline models were built with tumor region, radiomics features and/or clinical features the same as previous tumor-based approaches. Results showed that RFSNet achieved the best performance with concordance-indinces (CIs) of 0.88 and 0.65 for the developing and testing subcohorts, respectively. Adding clinical features did not improve RFSNet. Our findings suggest that the proposed RFSNet based on whole liver is able to extract more valuable information concerning RFS prognosis compared to features from only tumor and the clinical indicators.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Big data service capability of enterprise-scale data middle platform

Big data service capability of enterprise-scale data middle ...

引用

Tsinghua University-IET Electrical engineering Academic Forum: Constructing Green and Sustainable Energy system 2021

作者： Chen, Lianfu Wang, Xuan Peng, Fang Liu, Shi State Key Laboratory of Control and Simulation of Power System and Generation Equipments Tsinghua University Beijing China Department of Electrical Engineering Tsinghua University Beijing China Big Data Center of State Grid Corporation of China Beijing China

ISBN: (纸本)9781839536199

With the rapid development of technologies such as big data, cloud computing, Internet of things and artificial intelligence, electric power enterprises are faced with the strategic deployment of digital transformation. By upgrading IT architecture, power grid companies build the data middle platform, and separate the data operation and product technology from its front platform. Through service reusing and data sharing, the business capability can be shared, which providing technical support for power enterprises to serve a variety of complex business scenarios. This paper focuses on the architecture design of data middle platform in power grid companies, and analyzes its service capability. In addition, this paper sorts out the capability output framework of big data middle platform, and analyzes the data service requirements and application modellings for data middle platform in different business scenarios. © 2021 Institution of engineering and Technology. All rights reserved.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

AN EFFICIENT AZIMUTH SAMPLING DESIGN NETWORK FOR SPARSE SAR IMAGING

AN EFFICIENT AZIMUTH SAMPLING DESIGN NETWORK FOR SPARSE SAR ...

引用

IET International Radar Conference 2023, IRC 2023

作者： Wu, Yuwei Zhang, Zhe Qiu, Xiaolan Zhao, Yao Yu, Weidong Song, Ruizhen Department of Space Microwave Remote Sensing System Beijing100090 China Aerospace Information Research Institute Chinese Academy of Sciences Beijing100094 China Key Laboratory of Intelligent Aerospace Big Data Application Technology Suzhou215123 China Suzhou Aerospace Information Research Institute Suzhou215123 China School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing100049 China Guangdong University of Technology Guangdong Guangzhou China

ISBN: (纸本)9781839539954

Conventional synthetic aperture radar (SAR) imaging methods based on the Nyquist sampling theorem encounters the dilemma of balancing imaging quality and resource consumption. In order to solve the problem, we propose a novel network to optimize the azimuth sampling pattern for sparse SAR imaging. We harness the impressive information extraction capabilities inherent in deep neural networks to efficiently segregate valuable information from clutter. This empowers us to extract more pertinent data while minimizing pulse utilization. Additionally, we have integrated the nonuniform fast Fourier transform (NUFFT) MF operator into the network-based SAR imaging framework, ensuring both efficiency and viability of the proposed approach. Experiments on real SAR scene data have been conducted, and both visual comparisons and numerical analysis demonstrate the efficiency and superiority of our method in the field of sparse SAR imaging. © The Institution of engineering & Technology 2023.

关键词： Fast Fourier transforms

来源：评论

学校读者我要写书评

暂无评论

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

Rationet Based End-to-End Ml Calibration of Ultrasonic Doppler Flowmeters in Sewage Monitoring

SSRN

引用

SSRN 2024年

作者： Zhang, Zhenyu Liang, Ying Guan, Xiaolin Gong, Xiangyu Qiu, Chunming Zhou, Chichun Zhao, Enming Guo, Xiao Jiang, Wei School of Engineering Dali University Yunnan Dali671003 China Air-Space-Ground Integrated Intelligence and Big Data Application Engineering Research Center of Yunnan Provincial Department of Education Yunnan 671003 China Institute Of Unmanned System Beihang University Beijing00191 China Yunnan Dowater Technology Development Co. Ltd Yunnan Kunming650051 China

Monitoring sewage networks is vital for environmental protection, with accurate flow measurement being essential. Ultrasonic Doppler flow meters are favored for their non-invasive setup but face challenges, experiencing errors up to ~90% under extreme conditions due to fluctuating sewage levels and turbidity. Traditional calibration methods are costly and complex, making the quest for effective calibration critical. This study introduces a straightforward solution using neural networks, specifically addressing the scarcity of calibration data and the need for efficient modeling in sewage monitoring. We present an end-to-end dataset for ultrasonic Doppler flow meters and unveil RatioNet, a neural network model based on rational fraction polynomials, adept at correcting the nonlinear discrepancies between meter readings and actual flow rates. RatioNet significantly improves accuracy, reducing error from ~90% to ~2%, enhancing the utility of ultrasonic Doppler meters in sewage flow monitoring. This advancement promises substantial economic and societal benefits by improving sewage network management. © 2024, The Authors. All rights reserved.

关键词： Calibration

来源：评论

学校读者我要写书评

暂无评论

BLE-based Real-time Location system Integration with Hospital Information system to Reduce Patient Waiting Time 3

BLE-based Real-time Location System Integration with Hospita...

引用

3rd International Conference on Electrical, Communication and Computer engineering, ICECCE 2021

作者： Osman, Mohd Shafarudin Azizan, Azizul Hassan, Khairul Nizam Ghani, Hadhrami Ab. Hassan, Noor Hafizah Yakub, Fitri Daud, Salwani Mohd Latiff, Liza Abdul Universiti Teknologi Malaysia Razak Faculty of Technology and Informatics Advanced Informatic Department Kuala Lumpur Malaysia Hospital Putrajaya Emergency and Trauma Department Putrajaya Malaysia Universiti Malaysia Kelantan Institute for Artificial Intelligence Big Data Department of Data Science Kelantan Malaysia Universiti Teknologi Malaysia Malaysia-Japan International Institute of Technology Electronic System Engineering Department Kuala Lumpur Malaysia Universiti Teknologi Malaysia Razak Faculty of Technology and Informatics Engineering Department Kuala Lumpur Malaysia

ISBN: (纸本)9781665438971

Emergency and Trauma department (ETD) in Malaysia's public hospitals receives millions of patients than other clinics due to cheap charges and reliable services, however most of them are Green Zone non-critical patients. Long waiting time for patient treatment results into congestion and affects the quality of service provided in the ETD. To date only 20 public hospitals in Malaysia implements Hospital Information system (HIS) and patient waiting time is captured from the system manually, thus lacking the functionality to track patient in realtime. Despite studies conducted worldwide, studies on design, development and implementation of RTLS in public hospital in Malaysia have not been conducted yet. This paper examines a Bluetooth Low Energy (BLE) based Real-time Location system (RTLS) implementation in ETD with HIS integration to reduce patient waiting time. We develop a Bluetooth Low Energy (BLE) based RTLS prototype that is integrated with existing HIS at ETD, Hospital Putrajaya and augment data visualization interventions to reduce patient waiting time in ETD. Preliminary results show substantial benefits of patient waiting time reduction leading to improvement of service quality. Our preliminary findings show when RTLS is introduced in the ETD workflow, the mean ATC time was significantly reduced to 10.47% in comparison to HIS without RTLS. © 2021 IEEE.

关键词： Bluetooth

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：