检索结果-内蒙古大学图书馆

68th International Annual Meeting of the Human Factors and Ergonomics Society, HFES 2024

作者： Mallam, Steven C. Attarzadeh, Amin Samanta, Akash Bhattacharjee, Ankan Nordby, Kjetil Fisheries and Marine Institute Memorial University of Newfoundland St. John’sNLA1C 5R3 Canada Electrical and Computer Engineering Faculty of Engineering and Applied Science Memorial University of Newfoundland St. John’s Canada Institute of Design The Oslo School of Architecture and Design Akershus Norway

This paper presents the developments across a multi-year collaborative industry-academia R&D project designing and testing novel Augmented Reality (AR) solutions for differing maritime operations and work tasks. We describe the step-wise approach taken in our Human Factors testing program exploring the effects of AR on maritime operators. This paper focuses specifically on our empirical simulator laboratory experiments using differing data collection designs, tools and operational scenarios to investigate operator Situation Awareness, cognitive workload, performance and usability. Moving from comparatively rudimentary measures using static scenarios, desktop data collections and post hoc video analysis to implementing eye-tracking and automated object identification in dynamic scenarios and full-mission simulated environments, we present an overview of how our testing program has evolved and lessons learned. Further, we discuss ongoing research and future plans to better understand the effects of AR on maritime end-users to implement human-centred solutions more effectively in maritime settings. © 2024 Human Factors and Ergonomics Society.

关键词： Head-up displays

来源：评论

学校读者我要写书评

暂无评论

Pixel-Level Reasoning Segmentation via Multi-turn Conversations

arXiv

引用

arXiv 2025年

作者： Cai, Dexian Yang, Xiaocui Liu, Yongkang Wang, Daling Feng, Shi Zhang, Yifei Poria, Soujanya School of Computer Science and Engineering Northeastern University Shenyang China Singapore University of Technology and Design Singapore

Existing visual perception systems focus on region-level segmentation in single-turn dialogues, relying on complex and explicit query instructions. Such systems cannot reason at the pixel level and comprehend dynamic user intent that changes over interaction. Our work tackles this issue by introducing a novel task, Pixel-level Reasoning Segmentation (Pixel-level RS) based on multi-turn conversations, tracking evolving user intent via multi-turn interactions for fine-grained segmentation. To establish a benchmark for this novel task, we build a Pixel-level ReasonIng Segmentation Dataset Based on Multi-Turn Conversations (PRIST), comprising 24k utterances from 8.3k multi-turn conversational scenarios with segmentation targets. Building on PRIST, we further propose MIRAS, a Multi-turn Interactive ReAsoning Segmentation framework, integrates pixel-level segmentation with robust multi-turn conversation understanding, generating pixel-grounded explanations aligned with user intent. The PRIST dataset and MIRSA framework fill the gap in pixel-level reasoning segmentation. Experimental results on the PRIST dataset demonstrate that our method outperforms current segmentation-specific baselines in terms of segmentation and LLM-based reasoning metrics. The code and data are available at: https://***/ccccai239/PixelRIST. Copyright © 2025, The Authors. All rights reserved.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Exploiting human-AI dependence for learning to defer 24

Exploiting human-AI dependence for learning to defer

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Zixi Wei Yuzhou Cao Lei Feng College of Computer Science Chongqing University China School of Computer Science and Engineering Nanyang Technological University Singapore Information Systems Technology Design Pillar Singapore University of Technology and Design Singapore

The learning to defer (L2D) framework allows models to defer their decisions to human experts. For L2D, the Bayes optimality is the basic requirement of theoretical guarantees for the design of consistent surrogate loss functions, which requires the minimizer (i.e., learned classifier) by the surrogate loss to be the Bayes optimality. However, we find that the original form of Bayes optimality fails to consider the dependence between the model and the expert, and such a dependence could be further exploited to design a better consistent loss for L2D. In this paper, we provide a new formulation for the Bayes optimality called dependent Bayes optimality, which reveals the dependence pattern in determining whether to defer. Based on the dependent Bayes optimality, we further present a deferral principle for L2D. Following the guidance of the deferral principle, we propose a novel consistent surrogate loss. Comprehensive experimental results on both synthetic and real-world datasets demonstrate the superiority of our proposed method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhanced GAN-Assisted Intrusion Detection Model for Addressing Data Imbalance Issues

Enhanced GAN-Assisted Intrusion Detection Model for Addressi...

引用

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

作者： Raghu Dhumpati Nirmala Reddy Sankati Ramakrishna Posimsetti Naveen Kumar Sheo Kumar Homera Durani Department of Computer Science and Engineering Bahrain Polytechnic Bahrain Department of Computer Science and Engineering IES College of Technology Bhopal India Department of Computer Science and Engineering-Data Science KKR & KSR Institute of Technology and Sciences Guntur India VLSI System Design Department of Computer Science and Engineering CMR Engineering College Hyderabad India Department of CSE School of Engineering RK University Rajkot India

ISBN: (数字)9798331533663

ISBN: (纸本)9798331533670

With the introduction of IIoT systems, industry breakthroughs and linked smart objects revolutionize the world. The enemies are finding a lot of room to launch a number of devastating cyber assaults thanks to all this connection and dependability. However, implementing IDS systems may be tough due to the absence of dataset for training as well as testing. This makes it difficult to detect likely cyberattacks with the required accuracy. The method of detection might not be able to learn perfectly and detect cyberattacks significantly higher precision if there aren't enough records related to every threat category in the dataset. In addition, the detection of breaches procedure is becoming more complicated due to unbalanced datasets. In this light, our research suggests a more effective GAN-based IDS model for creating simulated data samples that can fool and evade security systems before directing the real-life network assault. To be more specific, it creates fictitious datasets and trains IDS on these in conjunction with the actual data in order to boost the system's efficiency. The specifics of the Improved Generative Adversarial Network-based Intrusion Detection System (IGAN-IDS) model that is suggested in this study are described in this section. With an accuracy of 99.6 percent, the suggested IGAN-IDS model surpasses all of its competitors, including BSA-IDS, GAN, MLP-GAN, Synthetic Minority Over-sampling Technique (SMOTE), and ADASYN. This proves that it outperforms all other approaches when it comes to classification.

关键词： Training Accuracy Intrusion detection Generative adversarial networks Rendering (computer graphics) Data models Security computer crime Industrial Internet of Things Testing

来源：评论

学校读者我要写书评

暂无评论

Sybil Assault Detection in VANET with Efficient Network Analysis

Sybil Assault Detection in VANET with Efficient Network Anal...

引用

MIT Art, design and Technology School of Computing International Conference (MITADTSoCiCon)

作者： Shubhra Mukherjee Mathur Nagesh Jadhav Ravindra Gupta Department of Computer Science and Engineering School of Computing MIT Art Design and Technology University Pune Sarvepalli Radakrishnan University Bhopal Department of Computer Science and Engineering School of Computing MIT Art Design and Technology University Pune Department of Computer Science and Engineering School of Computing Sarvepalli Radakrishnan University Bhopal

ISBN: (数字)9798350362879

ISBN: (纸本)9798350362886

A developing technology that can be highly helpful for both intelligent transportation services and safety and security is the Automobile ad hoc network, or VANET. Nevertheless because of the great mobility and wireless connection of cars, there are numerous security risks that jeopardize people's safety and security when driving. The Sybil assault, in which the perpetrator makes up a false identity to obtain significant influence within the network and delay certain services and manipulate others by fictitious voting, is one of the main security issues. People can avoid being duped by an attacker or falling into traps when attacks are detected early.. This study describes two methods for detecting Sybil attacks: the first uses the Poisson Distribution Method in order to forecast traffic on the street, whereas the latter examines network efficiency for packet delivery ratio (PDR) in both benign additionally malicious environments. According to the simulation's findings, PDR lowers the number of fictitious cars in the network. Our method is straightforward and efficient because it doesn't involve a lot of computational overhead and doesn't breach users' privacy concerns.

关键词： Wireless communication Privacy Vehicle detection Vehicular ad hoc networks Transportation Network analyzers Safety

来源：评论

学校读者我要写书评

暂无评论

Integrating Image Recognition and Board Games into Financial Education 16

Integrating Image Recognition and Board Games into Financial...

引用

16th Asia-Pacific Workshop on Mixed and Augmented Reality, APMAR 2024

作者： Hung, Yu-Han Chao, Hao-Bin Liou, Jie-Sin Han, Ping-Hsuan Hsieh, Yi-Zeng Fan, Ping-Lin Chou, Chien-Hsing Department of Mathematics and Information Education National Taipei University of Education Taiwan Department of Interaction Design National Taipei University of Technology Taiwan Department of Electrical and Computer Engineering National Taiwan University of Science and Technology Taiwan Department of Digital Technology Design National Taipei University of Education Taiwan

As financial products diversify and market structures become more complex, promoting financial education has become increasingly important. Given that the foundation of financial literacy should be established from childhood, how to cultivate students' correct financial management concepts from a young age has become a significant issue in modern society. Considering the substantial advantages of game-based learning in providing high interactivity and real-world scenario simulations, this paper aims to develop an innovative financial education board game that incorporates elements of risk assessment and insurance planning, and digitalizes it. With the assistance of an app and the application of image recognition technology, we could enhance the convenience and fun of the gameplay. Research results show that integrating digital apps into board games as a game-based learning strategy significantly improves the learning outcomes and motivation of upper elementary school students in the areas of risk and insurance knowledge, compared to traditional lecture methods. It also enhances their understanding and application abilities. Students hold a positive attitude toward this teaching approach, demonstrating its potential and advantages in financial education. © 2024 Copyright for this paper by its authors.

关键词： Decentralized finance

来源：评论

学校读者我要写书评

暂无评论

Development of A Cloud Storage Based Data Logging System

Development of A Cloud Storage Based Data Logging System

引用

IEEE Calcutta Conference (CALCON)

作者： Shaheen Wasif Saif Wasim Parthasarathi Satvaya School of Illumination Science Engineering and Design Jadavpur University Kolkata India Department of Computer Science Engineering JLD Engineering and Management College Kolkata India

ISBN: (数字)9798331516666

ISBN: (纸本)9798331516673

In the present world, as Internet of Things (IoT) based sensor monitoring and conditional controlling technology has been embedded in our day-to-day lives, there is a need for logging and storing sensor data for big data analysis. Due to free and easy to use features, Google spreadsheet has been chosen as the Cloud-based spreadsheet platform for sensor data logging and storing. This paper has provided a procedure to monitor sensor data, located at different geographical locations onto their corresponding specified worksheet in a well-defined structured manner in a single Google spreadsheet. The sensor readings uploaded in the Google spreadsheet can be accessed online by smartphone or a personal computer. For stable and accurate readings of sensors which work best on 5 V, the hardware communication protocol, Universal Asynchronous Receiver/Transmitter (UART) has been used during the development of the present work and this paper shows a simplistic way for uploading sensor values on the web, where memory constraint for storing sensor data is absent. In this developmental work, Arduino has been used for sensor data monitoring and ESP32 has been used for Internet connection

关键词： Cloud computing Protocols Accuracy Memory management Organizations Microcomputers Hardware Internet of Things Monitoring Periodic structures

来源：评论

学校读者我要写书评

暂无评论

The Use of Privacy-Preserving Techniques in Edge-Cloud Computing: A Study of Alternative Approaches to Face Recognition 3

The Use of Privacy-Preserving Techniques in Edge-Cloud Compu...

引用

3rd International Conference on Intelligent Computing, Instrumentation and Control Technologies, ICICICT 2022

作者： Nambiar, Rajashree Jaiganesh, M. Rao, M.V. Panduranga Jain University Electronics and Communication Bengaluru India Karpagam College of Engineering Department of Computer Science and Design Coimbatore India Jain University Information Science and Engineering Bengaluru India

ISBN: (数字)9781665410052

ISBN: (纸本)9781665410052

Face verification is by far the most popular biometrics technology used for authentication since it is noninvasive and does not require the assistance of the user. In contrast, fingerprint and iris identification technologies require the help of a user during the identification process. Now the technology behind facial recognition has been around for years but recently as its grown more sophisticated is applications have expanded greatly. These days a third-party service provider is often hired to perform facial recognition. The sensitivity of face data raises important privacy concerns about outsourcing servers. In order to protect the privacy of users, this paper discusses privacy-preserving face recognition frameworks applied to different networks. In this survey, we focused primarily on the accuracy of face recognition, computation time, and algorithmic approaches to face recognition on edge and cloud-based networks. © 2022 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Inscribing or Circumscribing a Histogon to a Convex Polygon 42

Inscribing or Circumscribing a Histogon to a Convex Polygon

引用

42nd IARCS Annual Conference on Foundations of Software Technology and Theoretical computer science, FSTTCS 2022

作者： Chung, Jaehoon Bae, Sang Won Shin, Chan-Su Yoon, Sang Duk Ahn, Hee-Kap Department of Computer Science and Engineering Pohang University of Science and Technology Korea Republic of Division of Computer Science and Engineering Kyonggi University Suwon Korea Republic of Division of Computer Engineering Hankuk University of Foreign Studies Seoul Korea Republic of Department of Service and Design Engineering SungShin Women's University Seoul Korea Republic of Graduate School of Artificial Intelligence Department of Computer Science and Engineering Pohang University of Science and Technology Korea Republic of

ISBN: (纸本)9783959772617

We consider two optimization problems of approximating a convex polygon, one by a largest inscribed histogon and the other by a smallest circumscribed histogon. An axis-aligned histogon is an axis-aligned rectilinear polygon such that every horizontal edge has an integer length. A histogon of orientation θ is a copy of an axis-aligned histogon rotated by θ in counterclockwise direction. The goal is to find a largest inscribed histogon and a smallest circumscribed histogon over all orientations in [0, π). Depending on whether the horizontal width of a histogon is predetermined or not, we consider several different versions of the problem and present exact algorithms. These optimization problems belong to shape analysis, classification, and simplification, and they have applications in various cost-optimization problems. © Jaehoon Chung, Sang Won Bae, Chan-Su Shin, Sang Duk Yoon, and Hee-Kap Ahn;licensed under Creative Commons License CC-BY 4.0.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Strategies for Data Security and Privacy Protection in Cloud Infrastructure

Strategies for Data Security and Privacy Protection in Cloud...

引用

Blockchain and Distributed Systems Security (ICBDS), IEEE International Conference on

作者： Namrata Naikwade Shafi Pathan Dept. of Computer Science & Engineering MIT Art Design and Technology University Pune India

ISBN: (数字)9798350354348

ISBN: (纸本)9798350354355

In today's rapidly growing digital era, cloud computing has emerged as an important technology, providing the ability to scale resources efficiently, accessibility, and cost-effectiveness for storing and processing huge amounts of data. However, alongside its numerous benefits, the adoption of cloud computing has also introduced deep concerns regarding data protection and privacy. The current scenario of cloud computing is characterized by increase in usage of cloud services and an exponential growth of data. While organizations leverage the cloud to enhance agility and innovation, the data sharing ability of cloud and the outsourcing of data management raise significant challenges for ensuring the privacy, integrity, and availability of sensitive data. Moreover, the rising cyber threats, regulatory compliance requirements, and the possibility for unauthorized access bring out the critical importance of robust data protection mechanisms in the cloud *** paper presents a comprehensive survey of strategies for data protection and identity protection in the context of cloud based systems. It examines encryption techniques, access control mechanisms, identity management solutions, among other approaches, highlighting their strengths, limitations, and applicability in different cloud deployment models and use cases. Furthermore, the paper discusses emerging trends such as homomorphic encryption, Attributes Based Encryption (ABE) Schemes and Identity Based Encryption (IBE), which hold promise for enhancing data protection in the developing landscape of cloud technology.

关键词： Surveys Access control Cloud computing Technological innovation Data security Data protection Encryption Protection Usability Secure storage

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：