检索结果-内蒙古大学图书馆

European Control Conference (ECC)

作者： Mustafa Abdallah Qin Hu Department of Computer and Information Technology Indiana University-Purdue University Indianapolis Department of Computer and Information Science Indiana University-Purdue University Indianapolis

We consider a security game in a setting consisting of an attacker and multiple defenders. Both defenders and attacker have limited budgets such that they can select subsets of the nodes to defend and attack, respectively. Each node has a certain gain and loss to the attacker and the defender, respectively. Each node has also a probability of being successfully compromised, which is a function of the investments in that node by the defenders. For such games, we investigate the impacts of behavioral probability weighting on the strategies of the players; such probability weighting, where humans overweight low probabilities and underweight high probabilities, has been identified by behavioral economists to be a common feature of human decision-making. We explore the multi-round game under regret-matching and prove the convergence to correlated equilibrium in our game. We then show the effect of the behavioral bias on the convergence of the regret-matching learning. Finally, we show via numerical experiments that the regret-matching algorithm is effective for both behavioral and rational defenders (i.e., it helps both classes of defenders to converge to better investments over time)

关键词：

来源：评论

学校读者我要写书评

暂无评论

AARA-PR: Asset-Aware PageRank-Based Security Resource Allocation Method for Attack Graphs

AARA-PR: Asset-Aware PageRank-Based Security Resource Alloca...

引用

Electrics and computer (INTCEC), Interdisciplinary Conference on

作者： Mohammad Ryiad Al-Eiadeh Mustafa Abdallah Electrical and Computer Engineering Department Purdue School of Engineering and Technology Indiana University-Purdue University Indianapolis (IUPUI) Indianapolis IN USA Computer and Information Technology Department Purdue School of Engineering and Technology Indiana University-Purdue University Indianapolis (IUPUI) Indianapolis IN USA

ISBN: (数字)9798350349450

ISBN: (纸本)9798350349467

Interdependent systems face rising cybersecurity risks. This paper introduces a security decision-making framework for interdependent systems managed by a human defender. We use attack graphs to model vulnerabilities. We then propose a resource allocation method, prioritizing edges using in-Degree Defense. In our resource allocation method, we adapted the PageRank algorithm to prioritize critical assets based on both their connectivity and the assets' losses. Our approach demonstrates resilience to concurrent attacks and outperforms existing algorithms in resource allocation across four real-world interdependent systems, supported by statistical tests. We release the source codes of our implementation for the research community for further exploration on our method.

关键词： Adaptation models Sensitivity Source coding Decision making Resource management computer security Faces

来源：评论

学校读者我要写书评

暂无评论

Multi-Agent LLM Actor-Critic Framework for Social Robot Navigation

arXiv

引用

arXiv 2025年

作者： Wang, Weizheng Obi, Ike Min, Byung-Cheol SMART Laboratory Department of Computer and Information Technology Purdue University West LafayetteIN United States

Recent advances in robotics and large language models (LLMs) have sparked growing interest in human-robot collaboration and embodied intelligence. To enable the broader deployment of robots in human-populated environments, socially-aware robot navigation (SAN) has become a key research area. While deep reinforcement learning approaches that integrate human-robot interaction (HRI) with path planning have demonstrated strong benchmark performance, they often struggle to adapt to new scenarios and environments. LLMs offer a promising avenue for zero-shot navigation through commonsense inference. However, most existing LLM-based frameworks rely on centralized decision-making, lack robust verification mechanisms, and face inconsistencies in translating macro-actions into precise low-level control signals. To address these challenges, we propose SAMALM, a decentralized multi-agent LLM actor-critic framework for multirobot social navigation. In this framework, a set of parallel LLM actors, each reflecting distinct robot personalities or configurations, directly generate control signals. These actions undergo a two-tier verification process via a global critic that evaluates group-level behaviors and individual critics that assess each robot’s context. An entropy-based score fusion mechanism further enhances self-verification and re-query, improving both robustness and coordination. Experimental results confirm that SAMALM effectively balances local autonomy with global oversight, yielding socially compliant behaviors and strong adaptability across diverse multi-robot scenarios. More details and videos about this work are available at: https://sites. ***/view/SAMALM. Copyright © 2025, The Authors. All rights reserved.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Impact of Instructional Activities on Students' Positivity, Participation, and Perceived Value in a Systems Analysis and Design Course 53

Impact of Instructional Activities on Students' Positivity, ...

引用

53rd IEEE ASEE Frontiers in Education International Conference, FIE 2023

作者： Ali, Syeda Fizza Bang, Daniel Magana, Alejandra J. Anwar, Saira Texas A&m University Department of Multidisciplinary Engineering College StationTX United States Purdue University Computer and Information Technology and Engineering Education West LafayetteIN United States

ISBN: (纸本)9798350336429

The ICAP framework classifies learning into four levels based on students' cognitive engagement with the course materials. These levels are Interactive, Constructive, Active, and Passive. The built-in hypothesis within the framework suggests that Interactive activities may generate better learning and engagement than Constructive activities, which may generate better outcomes than Active activities, which in turn may generate better results than Passive activities. Prior literature has focused on the impact of ICAP learning modes on student engagement, motivation, and learning outcomes. Most of these studies were conducted in either lab settings or for testing a section of the hypothesis. Although ICAP provides a baseline to determine the nature of class activities, literature is scarce on studies that use the framework. Considering this gap, for this study, we specifically selected a class where the instructor conducted lectures using active learning-based instructional activities. Considering that the instructor's perspective may differ from students' perspective, we use the validated survey instrument Student Response to Instructional Practices (StRIP) to examine how students perceive the instructional activities in class. Also, this study focuses on the impact of the Interactive, Constructive, Active, and Passive components of ICAP on students' positivity, participation, and the value they derive from course materials. More specifically, the study answers two research questions: 1) How did students perceive the frequency of the different instructional activities (interactive, constructive, active, or passive) in class? and 2) How did the instructional activities relate to students' positivity, participation, and perceived value of the activities? We collected the data from a systems analysis and design course at a large Midwestern university. Eighty-eight students voluntarily participated in the end-of-semester survey. Data were collected for students' responses

关键词： Class participation ICAP framework Instructional activities Perceived value Positivity StRIP

来源：评论

学校读者我要写书评

暂无评论

Learning from Demonstration Framework for Multi-Robot Systems Using Interaction Keypoints and Soft Actor-Critic Methods

Learning from Demonstration Framework for Multi-Robot System...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Vishnunandan L. N. Venkatesh Byung-Cheol Min Department of Computer and Information Technology SMART Lab Purdue University West Lafayette IN USA

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

Learning from Demonstration (LfD) is a promising approach to enable Multi-Robot Systems (MRS) to acquire complex skills and behaviors. However, the intricate interactions and coordination challenges in MRS pose significant hurdles for effective LfD. In this paper, we present a novel LfD framework specifically designed for MRS, which leverages visual demonstrations to capture and learn from robot-robot and robot-object interactions. Our framework introduces the concept of Interaction Keypoints (IKs) to transform the visual demonstrations into a representation that facilitates the inference of various skills necessary for the task. The robots then execute the task using sensorimotor actions and reinforcement learning (RL) policies when required. A key feature of our approach is the ability to handle unseen contact-based skills that emerge during the demonstration. In such cases, RL is employed to learn the skill using a classifier-based reward function, eliminating the need for manual reward engineering and ensuring adaptability to environmental changes. We evaluate our framework across a range of mobile robot tasks, covering both behavior-based and contact-based domains. The results demonstrate the effectiveness of our approach in enabling robots to learn complex multi-robot tasks and behaviors from visual demonstrations.

关键词： Visualization Robot kinematics Scalability Transforms Reinforcement learning Manuals Robot sensing systems Robot learning Multi-robot systems Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Drowsy Driving Prevention IoT System: Waking Up the Driver Through Responsiveness Check 13

Drowsy Driving Prevention IoT System: Waking Up the Driver T...

引用

13th International Conference on information and Communication technology Convergence, ICTC 2022

作者： Jung, Gyeyoung Bok, Sinyoung Lee, Yesung Kwak, Mirae Kim, Heejung Kim, Jaejeung Park, William Choi, Alex Lee, Minji Smith, Tony Chungnam National University Division of Computer Convergence Daejeon Korea Republic of Purdue University Department of Computer and Information Technology West Lafayette United States

ISBN: (数字)9781665499392

ISBN: (纸本)9781665499392

Conditions such as physical fatigue and sleep deprivation decrease the driver's responsiveness and are a major factor of drowsy driving. Maintaining the driver's alertness to drowsy driving through a simple secondary task, such as vocal response, has been proven to be effective in preventing accidents. The prototype of an IoT system that prevents drowsy driving by maintaining alertness and awakening from drowsiness has been developed in this paper. The wrist wearable device is developed to monitor the driver's heart rate and oxygen saturation variability through a sensor to detect drowsiness. The threshold value for the detection of heart rate and oxygen saturation is personalized to the driver. When drowsiness is detected, the Responsiveness Check System(RCS) checks the driver's vocal responsiveness to the tactile vibration stimulus, that is applied from the wrist wearable device to the driver. The stimulation continues until the RCS determines the driver is recovered from the fatigue condition. The proposed system is able to understand driver's drowsy condition and expected to decrease drowsy driving in practical environments. © 2022 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

WGAN-Based Synthetic Data Generation for Modeling Cyberattacks in Power Transmission Systems

WGAN-Based Synthetic Data Generation for Modeling Cyberattac...

引用

Innovative Approaches in Smart Technologies (ISAS), International Symposium on

作者： Spoorthy Reddy Gondhi Urmisha Reddy Janak Ashok Raja Arash Asrari Electrical and Computer Engineering Department Purdue University Northwest Hammond IN USA Computer Information Technology and Graphics Department Purdue University Northwest Hammond IN USA

ISBN: (数字)9798331540104

ISBN: (纸本)9798331540111

The integration of diverse infrastructures in modern-day power systems facilitates unauthorized access and data manipulation by adversaries, as these systems heavily rely on information and Communication technology (ICT) for monitoring and control. A significant challenge within these power networks is the risk of operational disruptions, such as congestion and voltage instability, resulting from stealthy false data injection (FDI) cyberattacks. Different from the existing work, this paper proposes a solution by introducing a defense framework that utilizes a Wasserstein Generative Adversarial Network (WGAN) to generate synthetic data. This synthetic data closely resembles the output from actual Phasor Measurement Units (PMU) and is developed by training the WGAN with extensive real PMU datasets. Additionally, mixing synthetic and real data when sending it to the Supervisory Control and Data Acquisition (SCADA) system adds layers of complexity and obscures the data landscape for attackers, thereby hindering their ability to detect vulnerabilities and anomalies.

关键词： SCADA systems Power system stability Generative adversarial networks Phasor measurement units Data models Power system reliability information and communication technology Reliability computer crime Synthetic data

来源：评论

学校读者我要写书评

暂无评论

Semantic Layering in Room Segmentation via LLMs

Semantic Layering in Room Segmentation via LLMs

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Taehyeon Kim Byung-Cheol Min Department of Computer and Information Technology SMART Lab Purdue University West Lafayette IN USA

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

In this paper, we introduce Semantic Layering in Room Segmentation via LLMs (SeLRoS), an advanced method for semantic room segmentation by integrating Large Language Models (LLMs) with traditional 2D map-based segmentation. Unlike previous approaches that solely focus on the geometric segmentation of indoor environments, our work enriches segmented maps with semantic data, including object identification and spatial relationships, to enhance robotic navigation. By leveraging LLMs, we provide a novel framework that interprets and organizes complex information about each segmented area, thereby improving the accuracy and contextual relevance of room segmentation. Furthermore, SeLRoS overcomes the limitations of existing algorithms by using a semantic evaluation method to accurately distinguish true room divisions from those erroneously generated by furniture and segmentation inaccuracies. The effectiveness of SeLRoS is verified through its application across 30 different 3D environments. Source code and experiment videos for this work are available at: https://***/view/selros.

关键词： Visualization Accuracy Three-dimensional displays Statistical analysis Source coding Robot kinematics Semantics Indoor environment Object recognition Videos

来源：评论

学校读者我要写书评

暂无评论

SMART-LLM: Smart Multi-Agent Robot Task Planning using Large Language Models

SMART-LLM: Smart Multi-Agent Robot Task Planning using Large...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Shyam Sundar Kannan Vishnunandan L. N. Venkatesh Byung-Cheol Min Department of Computer and Information Technology SMART Lab Purdue University West Lafayette IN USA

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

In this work, we introduce SMART-LLM, an innovative framework designed for embodied multi-robot task planning. SMART-LLM: Smart Multi-Agent Robot Task Planning using Large Language Models (LLMs), harnesses the power of LLMs to convert high-level task instructions provided as input into a multi-robot task plan. It accomplishes this by executing a series of stages, including task decomposition, coalition formation, and task allocation, all guided by programmatic LLM prompts within the few-shot prompting paradigm. We create a benchmark dataset designed for validating the multi-robot task planning problem, encompassing four distinct categories of high-level instructions that vary in task complexity. Our evaluation experiments span both simulation and real-world scenarios, demonstrating that the proposed model can achieve promising results for generating multi-robot task plans. The experimental videos, code, and datasets from the work can be found at https://***/view/smart-llm/.

关键词： Codes Large language models Benchmark testing Planning Complexity theory Resource management Intelligent robots Videos

来源：评论

学校读者我要写书评

暂无评论

LightLT: A Lightweight Representation Quantization Framework for Long-Tail Data 40

LightLT: A Lightweight Representation Quantization Framework...

引用

40th IEEE International Conference on Data Engineering, ICDE 2024

作者： Wang, Haoyu Li, Ruirui Wang, Zhengyang Tang, Xianfeng Zhang, Danqing Cheng, Monica Yin, Bing Droppo, Jasha Wang, Suhang Gao, Jing School of Electrical and Computer Engineering Purdue University West Lafayette United States Amazon Palo Alto United States Amazon Sunnyvale United States College of Information Sciences and Technology Pennsylvania State University University Park United States

ISBN: (纸本)9798350317152

Search tasks require finding items similar to a given query, making it a crucial aspect of various applications. However, storing and computing similarity for millions or billions of item representations can be computationally expensive. To address this, quantization-based hash methods present memory and inference-efficient solutions by converting continuous representations into non-negative integer codes. Despite their advantages, these methods often encounter difficulties in handling long-tail datasets due to imbalanced class distributions. To address this, we propose LightLT, a lightweight representation quantization framework tailored for long-tail datasets. LightLT produces compact codebooks and discrete IDs, enabling efficient inference by computing distances between query and codewords. Our framework includes innovative designs: 1) Quantization Step: We select the most similar codeword for continuous inputs using the differentiable argmax operation. 2) Double Skip Quantization Connection Module: This module promotes codebook diversity and stability during training. 3) Training Loss: Our comprehensive loss includes class-weighted cross-entropy, center loss, and ranking loss. 4) Model Ensemble: We incorporate a model ensemble step to improve generalization. Theoretical analysis confirms LightLT's low space and inference complexity. Experimental results demonstrate superior performance compared to state-of-the-art baselines in terms of search accuracy, efficiency, and memory usage. © 2024 IEEE.

关键词： computer vision

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：