检索结果-内蒙古大学图书馆

A topology-based bounded rationality day-to-day traffic assignment model

Communications in Transportation Research 2022年第1期2卷 298-313页

作者： Enrico Siri Silvia Siri Simona Sacone Department of Informatics BioengineeringRobotics and Systems EngineeringUniversity of GenovaGenova16145Italy

This paper analyzes the day-to-day adjustment process of users’behaviors in a transport network which is affected by relevant alterations such as disruptions due to critical events which cause the impossibility to use one or more *** representing the progressive adjustment of the flows on the network to reach a new equilibrium,a dayto-day discrete-time model is proposed,based on the idea that people are bounded rational in their choices,*** often do not behave according to the optimal solution but they accept solutions they consider ***,in their choice process,are influenced by the topological similarity between the route they are currently using and *** means that they tend to prefer the solutions that are more similar to the one they are already *** parallel,users exhibit a myopic behavior,i.e.,they tend to overestimate the goodness of a route if,when using it,they suddenly experience a significant reduction in travel time compared to what they are used *** the paper it is shown that such route choice behaviour implies that the steady state of the system corresponds to a Bounded Rational User Equilibrium,i.e.,a state that does not diverge from the user equilibrium more than a certain value which increases when the relative importance given to the topological similarity *** model also assumes that these biases vanish,at least with respect to those routes that are most frequently used by users,after a sufficient amount of *** certain conditions,it is then shown that the steady state can eventually collapse into a User *** effectiveness of the proposed model is assessed via simulation results in which two test networks are analyzed in detail to show the evolution of the users’behaviour in a transport network after a disruption.

关键词： Traffic Assignment Day-to-day traffic assignment Bounded rationality

来源：评论

学校读者我要写书评

暂无评论

Towards a Coalition Refinement Approach in the Strategic Verification of Multi-Agent systems 11

Towards a Coalition Refinement Approach in the Strategic Ver...

引用

11th Italian Workshop on Planning and Scheduling, 30th RCRA Workshop on Experimental Evaluation of Algorithms for Solving Problems with Combinatorial Explosion, and 2023 SPIRIT Workshop on Strategies, Prediction, Interaction, and Reasoning in Italy, IPS-RCRA-SPIRIT 2023 Workshops

作者： Ferrando, Angelo Department of Informatics Bioengineering Robotics and Systems Engineering University of Genoa Italy

In the context of formal verification of Multi-Agent systems, it is common to check whether a subset of agents (also called a coalition) can achieve specific goals of interest, usually expressed as temporal properties. However, each coalition is hand-picked, and there is no guarantee that the agents within it will actually cooperate during system execution. This creates a gap between what the agents are assumed to achieve statically and what they can achieve in practice dynamically. In this paper, we explore and lay the foundation for an engineering approach to guide a coalition refinement technique. Multi-Agent systems are first statically verified with respect to certain coalitions and then revised based on the actual dynamic behaviour of the agents during runtime. © 2023 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

On Theoretical Questions of Machine Learning, Multi-Agent systems, and Quantum Computing with Their Reciprocal Applications 20th

On Theoretical Questions of Machine Learning, Multi-Agent S...

引用

Proceedings of the 20th European Conference on Multi-Agent systems, EUMAS 2023

作者： Sadeghi Garjan, Mahyar Department of Informatics Bioengineering Robotics and Systems Engineering University of Genoa Genoa Italy

ISBN: (纸本)9783031432637

Recent advances in Multi-Agent systems (MAS) have shown the importance of this field in computer science. Applications can vary in many different research areas in which the problems can be tackled with distributional AI, like economics, sociology, and psychology. However, there are still challenges and open questions to be answered. Cooperation among agents, implies the existence of a complex connection. Connections can be analysed using GNNs. On the other hand, an agent, per se, should be flexible and adapted to the environment which can be done using RL. In this proposal we are mentioning some challenges and open questions that can be raised by combining these methods in MAS. Additionally, quantum computing is introduced that can fasten the computational effort of ML and MAS programs. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

AGAMAS: A New Agent-Oriented Traffic Simulation Framework for SUMO 20th

AGAMAS: A New Agent-Oriented Traffic Simulation Framework fo...

引用

Proceedings of the 20th European Conference on Multi-Agent systems, EUMAS 2023

作者： Sadeghi Garjan, Mahyar Chaanine, Tommy Pasquale, Cecilia Paolo Pastore, Vito Ferrando, Angelo Department of Informatics Bioengineering Robotics and Systems Engineering University of Genoa Genoa Italy

ISBN: (纸本)9783031432637

Simulating everyday traffic scenarios is not an easy task. Many aspects have to be taken into consideration and properly modelled, from static components, like traffic lights, to dynamic components, like vehicles. Due to their intrinsic autonomy and distribution, such components have already been designed as software agents, and integrated into existing traffic simulators, such as SUMO. The needing for agent-based modelling is even more evident when autonomous vehicles are present in the simulation. In this paper, we present an Agent-Based Traffic Simulation framework, where the simulation components can be defined as JADE agents. We present the engineering of our framework, and we show how it represents a new alternative for creating Agent-Based simulations in the largely used SUMO traffic simulator. We also demonstrate its applicability by employing the framework in one case study involving autonomous vehicles. © 2023, The Author(s), under exclusive license to 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

AI-Based Predictive Ramp-Metering Control for Freeway Traffic systems 27

AI-Based Predictive Ramp-Metering Control for Freeway Traffi...

引用

27th IEEE International Conference on Intelligent Transportation systems, ITSC 2024

作者： Binjaku, K. Mece, E.K. Pasquale, C. Siri, S. Sacone, S. University of Genova Department of Informatics Bioengineering Robotics and Systems Engineering Italy Polytechnic University of Tirana Department of Computer Engineering Albania

ISBN: (纸本)9798331505929

Traffic congestion in freeways poses significant challenges, impacting travel times and environmental sustainability. This paper proposes a novel approach to enhance ramp metering control using predictive traffic insights derived from physics-informed LSTM (Long Short-Term Memory) models. By integrating predictive capabilities with established control strategies like ALINEA, the method dynamically adjusts on-ramp flow rates based on anticipated traffic conditions. Real-world traffic data are used to evaluate the effectiveness of the approach, demonstrating improved performance compared to the adoption of conventional controllers. © 2024 IEEE.

关键词： Travel time

来源：评论

学校读者我要写书评

暂无评论

AI vs. AI: The Detection Game 8

AI vs. AI: The Detection Game

引用

8th IEEE International Forum on Research and Technologies for Society and Industry Innovation, RTSI 2024

作者： Coccoli, Mauro Patanè, Gabriella University of Genoa Dibris - Department of Informatics Bioengineering Robotics and Systems Science Genoa Italy Genoa Italy

ISBN: (纸本)9798350362138

In this paper, we present the results achieved by performing a test addressed to evaluate the capabilities of the so-called AI content Detectors or AI Detection systems. Such systems promise to find out whether a given text was written by a human or created by an artificial intelligence (AI). The ability to identify the 'synthetic' nature of a text is paramount in many workplaces as well as in the educational field, where we focused our research. More specifically, we considered the academic environment and the frequent request by faculty to students to write term papers on a wide variety of topics. Then, it is essential for teachers to be able to evaluate content quality as well as their authenticity. Until now, anti-plagiarism tools have been widely used to verify that homework assignments were not copied, but the recent advent of generative artificial intelligence-based tools changed the game, moving the focus to automatic generation. In both cases, we are facing a violation of the educational pact by a student, versus a teacher, if not outright an offence. Conversely, an unfounded accusation of fraud by a teacher toward a student would be equally serious. Therefore, to use automatic detection tools one must have a guarantee on the reliability of their output. © 2024 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Cybersecurity and AI: The PRALab Research Experience

Cybersecurity and AI: The PRALab Research Experience

引用

2023 Italia Intelligenza Artificiale - Thematic Workshops, Ital-IA 2023

作者： Pintor, Maura Orrú, Giulia Maiorca, Davide Demontis, Ambra Demetrio, Luca Marcialis, Gian Luca Biggio, Battista Roli, Fabio Department of Electrical and Electronic Engineering University of Cagliari Italy Department of Informatics Bioengineering Robotics and Systems Engineering University of Genova Italy

We present here the main research topics and activities on the design, security, safety, and robustness of machine learning models developed at the Pattern Recognition and Applications Laboratory (PRALab) of the University of Cagliari. Our findings have significantly contributed to identifying and characterizing the vulnerability of such models to adversarial attacks in the context of real-world applications and proposing robust techniques to make these models more reliable in security-critical scenarios. © 2022 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

AI Security and Safety: The PRALab Research Experience

AI Security and Safety: The PRALab Research Experience

引用

2023 Italia Intelligenza Artificiale - Thematic Workshops, Ital-IA 2023

作者： Demontis, Ambra Pintor, Maura Demetrio, Luca Sotgiu, Angelo Angioni, Daniele Piras, Giorgio Gupta, Srishti Biggio, Battista Roli, Fabio Department of Electrical and Electronic Engineering University of Cagliari Italy Department of Informatics Bioengineering Robotics and Systems Engineering University of Genova Italy Italy

We present here the main research topics and activities on security, safety, and robustness of machine learning models developed at the Pattern Recognition and Applications (PRA) Laboratory of the University of Cagliari. We have provided pioneering contributions to this research area, being the first to demonstrate gradient-based attacks to craft adversarial examples and training data poisoning attacks. The findings of our research have significantly contributed not only to identifying and characterizing vulnerabilities of such models in the context of real-world applications but also to the development of more trustworthy artificial intelligence and machine learning models. We are part of the ELSA network of excellence for the development of safe and secure AI-based technologies, funded by the European Union. © 2023 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Optimization of Electric Bus Charging: Integrating Discrete Event Modeling in Public Transportation systems

引用

IFAC-PapersOnLine 2024年第2期58卷 162-167页

作者： Virginia Casella Riccardo Minciardi Luca Parodi Department of Informatics Bioengineering Robotics and Systems Engineering (DIBRIS) University of Genoa Genoa Italy

The transition to electric transportation is gaining more and more importance in the last years leading to new challenges to be addressed. A key role in this framework is represented by public transportation systems. This paper introduces a Discrete Event (DE) optimization model to optimize the charging scheduling of electric buses (EBs). By accounting for time tabling constraints, energy demand satisfaction, and the capability for simultaneous multi-socket charging, our model addresses the complexities inherent in managing EB fleets. Utilizing a periodic model to capture cyclical system behavior, we incorporate a detailed battery model reflecting nonlinear charging profiles to enhance accuracy in power requirement prediction and charging duration estimation. Validation of our model is performed using real-world data, demonstrating its practical applicability.

关键词： Electric Buses Electric Vehicles Optimization Smart Charging Discrete Events Modeling

来源：评论

学校读者我要写书评

暂无评论

Examining Cognitive Biases in ChatGPT 3.5 and 4 through Human Evaluation and Linguistic Comparison 16

Examining Cognitive Biases in ChatGPT 3.5 and 4 through Huma...

引用

16th Conference of the Association for Machine Translation in the Americas, AMTA 2024

作者： Pantana, Giada Castello, Marta Torre, Ilaria Department of Modern Languages and Cultures University of Genoa Genoa Italy Creative Words Genoa Italy Department of Informatics Bioengineering Robotics and Systems Engineering University of Genoa Genoa Italy

This paper aims to investigate the presence of cognitive biases, more specifically of Availability heuristics, Representativeness heuristics and Framing, in OpenAI's ChatGPT 3.5 and ChatGPT 4, as well as the linguistic dependency of their occurrences in the Large Language Models' (LLMs) outputs. The innovative aspect of this research is conveyed by rephrasing three tasks proposed in Kahneman and Tversky's works and determining whether the LLMs' answers to the tasks are correct or incorrect and human-like or non-human-like. The latter classification is made possible by interviewing a total of 56 native speakers of Italian, English and Spanish, thus introducing a new linguistic comparison of results and forming a "human standard". Our study indicates that GPTs 3.5 and 4 are very frequently subject to the cognitive biases under discussion and their answers are mostly non-human-like. There is minimal but significant discrepancy in the performance of GPT 3.5 and 4, slightly favouring ChatGPT 4 in avoiding biased responses, specifically for Availability heuristics. We also reveal that, while the results for ChatGPT 4 are not significantly language dependent, meaning that the performances in avoiding biases are not affected by the prompting language, their difference with ChatGPT 3.5 is statistically significant. © AMTA *** rights reserved.

关键词： Linguistics

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：