检索结果-内蒙古大学图书馆

International Workshop on Coordination, Organizations, Institutions, and Norms for Governance of Multi-Agent Systems, COIN 2017, co-located with AAMAS 2017 and the International Workshop on Coordination, Organizations, Institutions, Norms and Ethics for Governance of Multi-Agent Systems, COINE 2020, co-located with AAMAS 2020

作者： Siebert, Luciano Cavalcante Mercuur, Rijk Dignum, Virginia van den Hoven, Jeroen Jonker, Catholijn Faculty of Electrical Engineering Mathematics and Computer Science Delft University of Technology Delft Netherlands AiTech Delft University of Technology Delft Netherlands Faculty of Technology Policy and Management Delft University of Technology Delft Netherlands Department of Computing Sciences Umeå University Umeå Sweden Leiden Institute of Advance Computer Science Leiden University Leiden Netherlands

ISBN: (纸本)9783030723750

Autonomous agents (AA) will increasingly be interacting with us in our daily lives. While we want the benefits attached to AAs, it is essential that their behavior is aligned with our values and norms. Hence, an AA will need to estimate the values and norms of the humans it interacts with, which is not a straightforward task when solely observing an agent’s behavior. This paper analyses to what extent an AA is able to estimate the values and norms of a simulated human agent (SHA) based on its actions in the ultimatum game. We present two methods to reduce ambiguity in profiling the SHAs: one based on search space exploration and another based on counterfactual analysis. We found that both methods are able to increase the confidence in estimating human values and norms, but differ in their applicability, the latter being more efficient when the number of interactions with the agent is to be minimized. These insights are useful to improve the alignment of AAs with human values and norms. © 2021, Springer Nature Switzerland AG.

关键词： Autonomous agents

来源：评论

学校读者我要写书评

暂无评论

A Joint Modeling Approach for Clustering Mixed-Type Multivariate Longitudinal Data: Application to the CHILD Cohort Study

arXiv

引用

arXiv 2022年

作者： Tan, Zhiwen Shen, Chang Subbarao, Padmaja Lou, Wendy Lu, Zihang Department of Public Health Sciences Queen's University KingstonON Canada Department of Electrical and Computer Engineering Queen's University KingstonON Canada Division of Respiratory Medicine Department of Pediatrics Hospital for Sick Children University of Toronto TorontoON Canada Dalla Lana School of Public Health University of Toronto TorontoON Canada

In epidemiological and clinical studies, identifying patients' phenotypes based on longitudinal profiles is critical to understanding the disease's developmental patterns. The current study was motivated by data from a Canadian birth cohort study, the CHILD Cohort Study. Our goal was to use multiple longitudinal respiratory traits to cluster the participants into subgroups with similar longitudinal respiratory profiles in order to identify clinically relevant disease phenotypes. To appropriately account for distinct structures and types of these longitudinal markers, we proposed a novel joint model for clustering mixed-type (continuous, discrete and categorical) multivariate longitudinal data. We also developed a Markov Chain Monte Carlo algorithm to estimate the posterior distribution of model parameters. Analysis of the CHILD Cohort data and simulated data were presented and discussed. Our study demonstrated that the proposed model serves as a useful analytical tool for clustering multivariate mixed-type longitudinal data. We developed an R package BCClong to implement the proposed model efficiently. © 2022, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Decentralised, Collaborative, and Privacy-preserving Machine Learning for Multi-Hospital Data

arXiv

引用

arXiv 2024年

作者： Fang, Congyu Dziedzic, Adam Zhang, Lin Oliva, Laura Verma, Amol Razak, Fahad Papernot, Nicolas Wang, Bo Department of Computer Science University of Toronto Canada Peter Munk Cardiac Centre University Health Network Canada Vector Institute Toronto Canada CISPA Helmholtz Center for Information Security Germany Department of Electrical and Computer Engineering University of Toronto Canada Simon Fraser University Canada St. Michael’s Hospital Unity Health Toronto Canada Department of Medicine University of Toronto Canada Institute of Health Policy Management and Evaluation University of Toronto Canada Department of Laboratory Medicine and Pathobiology Temerty Faculty of Medicine University of Toronto Canada

Background: Machine Learning (ML) has demonstrated its great potential on medical data analysis. Large datasets collected from diverse sources and settings are essential for ML models in healthcare to achieve better accuracy and generalizability. Sharing data across different healthcare institutions or jurisdictions is challenging because of complex and varying privacy and regulatory requirements. Hence, it is hard but crucial to allow multiple parties to collaboratively train an ML model leveraging the private datasets available at each party without the need for direct sharing of those datasets or compromising the privacy of the datasets through collaboration. Methods: In this paper, we address this challenge by proposing Decentralized, Collaborative, and Privacy-preserving ML for Multi-Hospital Data (DeCaPH). This framework offers the following key benefits: (1) it allows different parties to collaboratively train an ML model without transferring their private datasets (i.e., no data centralization);(2) it safeguards patients’ privacy by limiting the potential privacy leakage arising from any contents shared across the parties during the training process;and (3) it facilitates the ML model training without relying on a centralized party/server. Findings: We demonstrate the generalizability and power of DeCaPH on three distinct tasks using real-world distributed medical datasets: patient mortality prediction using electronic health records, cell-type classification using single-cell human genomes, and pathology identification using chest radiology images. The ML models trained with DeCaPH framework have less than 3.2% drop in model performance comparing to those trained by the non-privacy-preserving collaborative framework. Meanwhile, the average vulnerability to privacy attacks of the models trained with DeCaPH decreased by up to 16%. In addition, models trained with our DeCaPH framework achieve better performance than those models trained solely with the private

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

False Data Injection Attacks against Low Voltage Distribution Systems

False Data Injection Attacks against Low Voltage Distributio...

引用

GLOBECOM 2022 - 2022 IEEE Global Communications Conference

作者： Panagiotis Radoglou-Grammatikis Christos Dalamagkas Thomas Lagkas Magda Zafeiropoulou Maria Atanasova Pencho Zlatev Alexandros-Apostolos A. Boulogeorgos Vasileios Argyriou Evangelos K. Markakis Ioannis Moscholios Panagiotis Sarigiannidis Department of Electrical and Computer Engineering University of Western Macedonia Kozani Greece Innovation Hub of Public Power Corporation S.A. Kantza Attica Greece Department of Computer Science International Hellenic University Kavala Campus Greece Innovative Energy and Information Technologies LTD (IEIT) BIC-IZOT Sofia Bulgaria Department of Networks and Digital Media Kingston University London Kingston upon Thames Surrey UK Department of Electrical and Computer Engineering Hellenic Mediterranean University Crete Greece Department of Informatics & Telecommunications University of Peloponnese Tripolis Greece

ISBN: (纸本)9781665435413

The transformation of the conventional electrical grid into a digital ecosystem brings significant benefits, such as two-way communication between energy consumers and utilities, self-monitoring and pervasive controls. However, the advent of the smart electrical grid raises severe cybersecurity and privacy concerns, given the presence of legacy systems and communications protocols. This paper focuses on False Data Injection (FDI) cyberattacks against a low-voltage distribution system, taking full advantage of Man In The Middle (MITM) actions. The first cyberattack targets the communication between a smart meter and an Active Distribution Management System (ADMS), while the second FDI cyberattack targets the communication between a smart inverter and ADMS. In both cases, the cyberattacks affect the operation of the distribution transformer, thus resulting in devastating consequences. Moreover, this paper provides an Artificial Intelligence (AI)-based Intrusion Detection System (IDS), detecting and mitigating the above cyberattacks in a timely manner. The evaluation results demonstrate the efficiency of the proposed IDS.

关键词： Low voltage Privacy Protocols Ecosystems Intrusion detection Transformers Smart meters

来源：评论

学校读者我要写书评

暂无评论

Retrieve, reason, and refine: generating accurate and faithful patient instructions 22

Retrieve, reason, and refine: generating accurate and faithf...

引用

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Fenglin Liu Bang Yang Chenyu You Xian Wu Shen Ge Zhangdaihong Liu Xu Sun Yang Yang David A. Clifton Department of Engineering Science University of Oxford School of ECE Peking University Department of Electrical Engineering Yale University Tencent JARVIS Lab China Department of Engineering Science University of Oxford and Oxford-Suzhou Centre for Advanced Research China MOE Key Lab of Computational Linguistics School of Computer Science Peking University School of Public Health Shanghai Jiao Tong University School of Medicine China

ISBN: (纸本)9781713871088

The "Patient Instruction" (PI), which contains critical instructional information provided both to carers and to the patient at the time of discharge, is essential for the patient to manage their condition outside hospital. An accurate and easy-to-follow PI can improve the self-management of patients which can in turn reduce hospital readmission rates. However, writing an appropriate PI can be extremely time-consuming for physicians, and is subject to being incomplete or error-prone for (potentially overworked) physicians. Therefore, we propose a new task that can provide an objective means of avoiding incompleteness, while reducing clinical workload: the automatic generation of the PI, which is imagined as being a document that the clinician can review, modify, and approve as necessary (rather than taking the human "out of the loop"). We build a benchmark clinical dataset and propose the Re3Writer, which imitates the working patterns of physicians to first retrieve related working experience from historical PIs written by physicians, then reason related medical knowledge. Finally, it refines the retrieved working experience and reasoned medical knowledge to extract useful information, which is used to generate the PI for previously-unseen patient according to their health records during hospitalization. Our experiments show that, using our method, the performance of five different models can be substantially boosted across all metrics, with up to 20%, 11% and 19% relative improvements in BLEU-4, ROUGE-L and METEOR, respectively. Meanwhile, we show results from human evaluations to measure the effectiveness in terms of its usefulness for clinical practice.

关键词：

来源：评论

学校读者我要写书评

暂无评论

BanditPAM: Almost linear time k-medoids clustering via multi-armed bandits 34

BanditPAM: Almost linear time k-medoids clustering via multi...

引用

34th Conference on Neural Information Processing Systems, NeurIPS 2020

作者： Tiwari, Mo Zhang, Martin Jinye Mayclin, James Thrun, Sebastian Piech, Chris Shomorony, Ilan Department of Computer Science Stanford University United States Department of Epidemiology Harvard T.H. Chan School of Public Health Electrical and Computer Engineering University of Illinois Urbana-Champaign United States

Clustering is a ubiquitous task in data science. Compared to the commonly used k-means clustering, k-medoids clustering requires the cluster centers to be actual data points and supports arbitrary distance metrics, which permits greater interpretability and the clustering of structured objects. Current state-of-the-art k-medoids clustering algorithms, such as Partitioning Around Medoids (PAM), are iterative and are quadratic in the dataset size n for each iteration, being prohibitively expensive for large datasets. We propose BanditPAM, a randomized algorithm inspired by techniques from multi-armed bandits, that reduces the complexity of each PAM iteration from O(n2) to O(n log n) and returns the same results with high probability, under assumptions on the data that often hold in practice. As such, BanditPAM matches state-of-the-art clustering loss while reaching solutions much faster. We empirically validate our results on several large real-world datasets, including a coding exercise submissions dataset from ***, the 10x Genomics 68k PBMC single-cell RNA sequencing dataset, and the MNIST handwritten digits dataset. In these experiments, we observe that BanditPAM returns the same results as state-of-the-art PAM-like algorithms up to 4x faster while performing up to 200x fewer distance computations. The improvements demonstrated by BanditPAM enable k-medoids clustering on a wide range of applications, including identifying cell types in large-scale single-cell data and providing scalable feedback for students learning computer science online. We also release highly optimized Python and C++ implementations of our algorithm1 © 2020 Neural information processing systems foundation. All rights reserved.

关键词： Genome

来源：评论

学校读者我要写书评

暂无评论

A Framework for Smart City Implementation using IoT-Cloud Based System Architecture

A Framework for Smart City Implementation using IoT-Cloud Ba...

引用

Distributed Computing and electrical Circuits and Electronics (ICDCECE), IEEE International Conference on

作者： V Dankan Gowda KDV Prasad Tanmoy De Ved Srinivas N Anil Kumar Tejashree Tejpal Moharekar Department of Electronics and Communication Engineering BMS Institute of Technology and Management Bangalore India Symbiosis Institute of Business Management (SIBM) Symbiosis International (Deemed University) (SIU) Hyderabad India Symbiosis Institute of Business Management Hyderabad Symbiosis International (Deemed University) Pune India Public Policy Thiagarajar School of Management Madurai India Department of Electronics and Communication Engneering School of Engineering and Technology Mohan Babu University (Erst While Sree Vidyanikethan Engineering College) Tirupati India Computer Department Yashwantrao Chavan School of Rural Development Shivaji University Kolhapur Maharashtra India

The Internet, a key participant (world wide web) in worldwide information exchange and media sharing, has experienced cumulative upgrades, developments, and given up consequent product IOT, making technology affordable and practical for all uses. Research development includes smart sensors, a communication channel and protocols for exchanging data, and peripherals like an Arduino, a Texas Instruments MSP430G2553, a Weather-proof Tx. Rx. Kit (for exchanging data), a Data Receptor and Decoder Shield for Lab View Kit (for exchanging data), an addressing and de-addressing data module, a communication shield, etc. It is now possible to communicate from a desktop computer or an Android smartphone to a portable device that has an embedded device, such as a microcontroller, a microprocessor, or a sensor. In other words, IOT combines always-on networking, always-on computation, and always-on intelligence. The Internet of Things facilitates communication between the central hub (fitted with a Lab-View interface) and the distributed modules (found in places like parks, subways, and highways) that control the lights. The Internet of Things is also useful for keeping the overall cost of setup and maintenance within reasonable economic bounds. The planned development takes into account IoT on two main scales: city-wide automation (also known as smart city) and home-level automation (also known as covering up).

关键词：

来源：评论

学校读者我要写书评

暂无评论

Federated Detection of Open Charge Point Protocol 1.6 Cyberattacks

arXiv

引用

arXiv 2025年

作者： Dalamagkas, Christos Radoglou-Grammatikis, Panagiotis Bouzinis, Pavlos Papadopoulos, Ioannis Lagkas, Thomas Argyriou, Vasileios Goudos, Sotirios Margounakis, Dimitrios Fountoukidis, Eleftherios Sarigiannidis, Panagiotis Department of Computer Science Democritus University of Thrace Kavala65404 Greece Innovation Hub Public Power Corporation S.A. Kantza-Pallini 15351 Greece Department of Electrical and Computer Engineering University of Western Macedonia Kozani50100 Greece Metamind Innovations IKE Kozani50100 Greece Department of Networks and Digital Media Kingston University London SurreyKT1 2EE United Kingdom School of Physics Aristotle University of Thessaloniki Thessaloniki54124 Greece SIDROCO Holdings Ltd Nicosia1082 Cyprus

The ongoing electrification of the transportation sector requires the deployment of multiple Electric Vehicle (EV) charging stations across multiple locations. However, the EV charging stations introduce significant cyber-physical and privacy risks, given the presence of vulnerable communication protocols, like the Open Charge Point Protocol (OCPP). Meanwhile, the Federated Learning (FL) paradigm showcases a novel approach for improved intrusion detection results that utilize multiple sources of Internet of Things data, while respecting the confidentiality of private information. This paper proposes the adoption of the FL architecture for the monitoring of the EV charging infrastructure and the detection of cyberattacks against the OCPP 1.6 protocol. The evaluation results showcase high detection performance of the proposed FL-based solution. © 2025, CC BY.

关键词： Charging stations

来源：评论

学校读者我要写书评

暂无评论

False Data Injection Attack on Atmospheric Electric Field in Thunderstorm Warning

False Data Injection Attack on Atmospheric Electric Field in...

引用

2022 International Conference on Computing, Communication, Perception and Quantum Technology, CCPQT 2022

作者： Li, Xiang Hayawi, Kadhim Chen, Yi Chang, Shih Yu Wen, Hong Ho, Pin-Han Yang, Ling Yin, Qiyuan College of Electronic Engineering Chengdu University of Information Technology Chengdu610225 China College of Technological Innovation Zayed University Abu Dhabi144534 United Arab Emirates School of Aeronautics and Astronautics University of Electronic Science and Technology of China Chengdu611731 China Cma Key Laboratory of Atmospheric Sounding Chengdu610225 China San Jose State University Department of Applied Data Science San JoseCA95192 United States University of Waterloo Department of Electrical and Computer Engineering Waterloo Canada Guangdong Meteorological Public Safety Technical Support Center Guangzhou510640 China

ISBN: (数字)9781665470209

ISBN: (纸本)9781665470209

Thunderstorm warning plays an important role in lightning prevention and disaster mitigation. In practical applications, thunderstorm warning system is also vulnerable to attacks, such as False Data Injection Attack (FDIA). However, there is a lack of research on False Data Injection Attack for thunderstorm warning. Therefore, this paper put forwards a FDIA method based on principal component analysis (PCA) for atmospheric electric field (AEF), which is usually used for thunderstorm warning. In the FDIA scenario, the AEF-based thunderstorm warning algorithm is also introduced with electric field differential index (EFDI). Finally, experiments are conducted based on AEF data collected by an atmospheric electric field meter (AEFM) about the real thunderstorm. The experimental results show that FDIA seriously interferes with the results of the AEF-based thunderstorm warning. © 2022 IEEE.

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Using Arduino Iot Modules As A Low Cost Environmental Research Monitoring System

Using Arduino Iot Modules As A Low Cost Environmental Resear...

引用

computer Science and Emerging Technologies (CSET), International Conference on

作者： Murad Magableh Ziyad Marie Rajina R. Mohamed Mohd Hafizuddin Bin Ibrahim Julaily Aida Jusoh Rohit Kumar MIS BI and Data Analysis Department Faculty of Business and Financial Science Irbid National University Irbid Jordan Public administration Department Faculty of Administrative sciences and Informatics Al-Istiqlal University Palestine College of Computing dan Informatics Universiti Tenaga Nasional Malaysia Department of Electrical Engineering Politeknik Kuala Terenngganu Kuala Terengganu Malaysia Faculty of Informatics and Computing UniSZA Malaysia School of Computer Science and Engineering Jain Deemed To Be University Bangalore India

Environmental monitoring plays a crucial role in understanding the impact of human activities on our ecosystems. However, the cost and complexity of traditional monitoring systems often hinder widespread deployment, especially in resource-constrained regions. This research paper explores the feasibility and effectiveness of employing Arduino Internet of Things (IoT) modules as a low-cost alternative for environmental research monitoring. The study focuses on designing and implementing an Arduino-based environmental monitoring system capable of gathering real-time data on key environmental parameters, such as temperature, humidity, air quality, and soil moisture. The hardware setup comprises Arduino microcontrollers interfaced with a range of environmental sensors and connectivity modules for data transmission. To assess the system's reliability and accuracy, a series of field experiments were conducted in diverse environmental settings, including urban areas, agricultural zones, and natural habitats. The collected data was compared against measurements from conventional monitoring equipment to validate the Arduino-based system's performance. The research demonstrates that the Arduino IoT modules can effectively monitor and transmit environmental data with a reasonable level of accuracy and stability, making them suitable for various environmental research applications. The low-cost nature of Arduino components and the open-source ecosystem facilitate customization and scalability, enabling researchers and organizations to develop tailored monitoring solutions for specific environmental contexts. Additionally, the paper discusses the challenges and limitations encountered during the deployment of Arduino-based monitoring systems, including power constraints, sensor calibration, and data processing techniques. Furthermore, it explores potential avenues for improvement and optimization to enhance the system's capabilities and data accuracy. In conclusion, this research

关键词：

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：