检索结果-内蒙古大学图书馆

International Symposium on Soft Computing and Intelligent systems (SCIS)

作者： Nobuyuki Umezu Satoshi Iijima Dept. of Computer and Information Sciences Ibaraki University Hitachi Japan Dept. of Mechanical Systems Engineering Ibaraki University Hitachi Japan

ISBN: (数字)9798350373332

ISBN: (纸本)9798350373349

We propose a new display method for visualizing flower models using a pseudo-holographic technique known as the Pepper's ghost illusion. This classic optical illusion technique creates the appearance of floating objects by reflecting them off a transparent panel, thereby producing a convincing visual effect that simulates three-dimensionality. In our approach, we utilized this illusion to display six distinct flower models obtained from a comprehensive photogrammetry archive of various plant species. These models were rendered to overlay onto a transparent glass vase, enhancing the realism of quality. To facilitate user interaction with the displayed models, we incorporated a dept. sensor (Intel D415) to track the user's hand position. A user study revealed that participants were notably attracted to the display, indicating successful capture of their attention. Feedback, however, suggested that the system requires enhancements in usability and dept. perception to improve the overall user experience. Our future work includes addressing these limitations by developing a larger display setup that could accommodate more complex interactions and by integrating motion-parallax techniques to enhance the three-dimensional view. This could be implemented using head-tracking technology, further advancing the effectiveness of the pseudo-holographic display.

关键词： Three-dimensional displays Optical feedback Glass Flowering plants Visual effects User experience Optical sensors Optical reflection Usability Photogrammetry

来源：评论

学校读者我要写书评

暂无评论

Human Detection Combining RGB and Thermal Modalities

Human Detection Combining RGB and Thermal Modalities

引用

Intelligent Reality (ICIR), IEEE International Conference on

作者： Chaymaa Fakrane Kennedy O. S. Mota Cristiano Premebida Rui P. Rocha Dept. of Electrical and Computer Engineering (DEEC) Institute of Systems and Robotics (ISR) University of Coimbra Portugal

ISBN: (数字)9798331534424

ISBN: (纸本)9798331534431

This paper addresses a late-fusion approach that combines RGB and thermal (long-wave IR) modalities to enhance human detection in indoor environments for robotic perception domains. The study explores multimodal human detection using YOLO series (v5s-6s and v8s-11s models), demonstrating significant improvements in detection accuracy under challenging lighting conditions on a dataset collected by a mobile robot. The use of a Weighted-Mean (WM) as a late-fusion approach demonstrates favorable results over more complex methods such as neural networks or SVM. The WM approach is simple to implement and has a low computational cost. Additionally, it is more interpretable and modular and allows straightforward adjustments to the weights of the YOLO models and thresholds, facilitating adaptation to the target system's specific needs. The experimental results indicate that the implemented late-fusion approach improves the baseline performance in terms of mean average precision.

关键词： YOLO Support vector machines Adaptation models Accuracy Computational modeling Neural networks Lighting Indoor environment Computational efficiency Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Passing Practice Support for Soccer Players Using First-Person Videos

Passing Practice Support for Soccer Players Using First-Pers...

引用

International Symposium on Soft Computing and Intelligent systems (SCIS)

作者： Nobuyuki Umezu Yuya Imada Dept. of Computer and Information Sciences Ibaraki University Hitachi Japan Dept. of Mechanical Systems Engineering Ibaraki University Hitachi Japan

ISBN: (数字)9798350373332

ISBN: (纸本)9798350373349

We propose a novel visualization system to enhance soccer passing practice by providing potential pass courses and their scores. The proposed system is based on a first-person video footage captured during soccer play and extracts frames for pass-course suggestions using the rate of ground-surface pixels in the frame and dept. estimation. Possible pass courses were scored according to their direction and distance to the closest player. To validate the proposed method's effectiveness, we conducted a series of experiments involving 17 participants, comprising 12 museum visitors and five university students. The estimated score of visualized pass courses using the proposed method was generally successful, whereas some pass courses received lower scores from participants owing to limitations in the system's ability to accurately detect the color of players' uniforms, which affected the overall evaluation of certain passing options.

关键词： Visualization Color Museums Sports

来源：评论

学校读者我要写书评

暂无评论

Email Armour: A Multi-Layered Email Defense Solution

Email Armour: A Multi-Layered Email Defense Solution

引用

International Conference on Information Technology Research (ICITR)

作者： K.T.A.U Lakmal L.M.C Perera S.P.K Padmika S.P.A De Silva Dinithi Pandithage Deemantha Siriwardana Dept. computer systems engineering Sri Lanka institute of information technology Malabe Sri Lanka

ISBN: (数字)9798331511425

ISBN: (纸本)9798331511432

Phishing and spam emails are evolving threats in today's digital landscape, posing significant risks to small and medium-sized businesses (SMBs). Despite the growing demand for email security solutions, SMBs often face barriers such as high costs and complexity. To address this gap, this study introduces a cost-effective, multi-layered email security solution leveraging machine learning. The proposed system comprises four core components: (1) spam detection using natural language processing (NLP) to analyze email content, (2) phishing URL and QR code detection by identifying malicious patterns and attributes, (3) attachment security analysis to detect malware and harmful scripts, and (4) suspicious URL detection focusing on JavaScript obfuscation. The model was trained and validated on publicly available datasets, achieving an overall accuracy of 85% and demonstrating effectiveness in identifying diverse email threats. Designed as an email client, this tool empowers SMBs to secure communication with an accessible and robust defense against email-based attacks

关键词： Uniform resource locators Unsolicited e-mail Phishing Focusing Machine learning QR codes Natural language processing Malware Security Information technology

来源：评论

学校读者我要写书评

暂无评论

Dantalion: Digital Twinning the Computing Continuum

Dantalion: Digital Twinning the Computing Continuum

引用

2023 IEEE Globecom Workshops, GC Wkshps 2023

作者： Laso, Sergio Martín, Luis Herrera, Juan Luis Galán-Jiménez, Jaime Berrocal, Javier Murillo, Juan M. Cáceres Spain University of Extremadura Dept. of Computer Systems and Telematics Engineering Spain University of Bologna Dipartamento di Informatica Scienza e Ingegneria Italy Cáceres Spain

ISBN: (纸本)9798350370218

Thanks to the Internet of Things (IoT) paradigm, it is now possible to develop computer applications that automate real, intensive processes, by processing sensor information using techniques such as artificial intelligence or computer vision. Nonetheless, due to the criticality of the processes they automate, intensive IoT applications have very strict Quality of Service (QoS) requirements to function properly, motivating their deployment throughout the Computing Continuum to optimize the obtained QoS. Evaluating and guaranteeing the QoS of this application can be a challenging endeavor, as current QoS evaluation tools are unable to predict future changes to the real world, evaluate multiple adaption alternatives, or act accordingly. To fulfill these needs, in this paper, we present the evolution of a Computing Continuum emulator towards Dantalion, a complete Digital Twin for the Computing Continuum. © 2023 IEEE.

关键词： Computing Continuum Digital Twin In-ternet of Things Quality of Service

来源：评论

学校读者我要写书评

暂无评论

Self-Optimizing Memory Controllers: Proposing Request-level Scheduling 2

Self-Optimizing Memory Controllers: Proposing Request-level ...

引用

2nd International Conference on computer Science, engineering and Applications, ICCSEA 2022

作者： Shawky, Alaa Watheq El-Kharashi, M. Safar, Mona Dessouky, Mohamed Ain Shams University Faculty of Engineering Electronics and Communications Dept. Cairo Egypt Siemens Digital Industries Software Cairo Egypt Ain Shams University Faculty of Engineering Computer and Systems Engineering Dept. Cairo Egypt

ISBN: (数字)9781665458344

ISBN: (纸本)9781665458344

Self-Optimizing Memory Controllers present a great potential in the future of memory controllers. As they alleviate the burden of designing an optimal memory scheduling policy, while providing adaptability to different workloads and systems. Previous state-of-art controllers scheduled memory accesses on the command level. This causes the agent to lose sight of the relation between commands and can lead to the issuing of unuseful sequences of precharge/activate of rows or closing banks that should have been left open, and vice versa. In this work we propose a bank-aware self-optimizing memory controller that schedules memory references on the request-level, presenting to the agent the actual problem it needs to tackle. This simplifies the evaluation of system attributes and eliminates the need for correction mechanisms that was needed in previous controllers. With the proposed algorithm a maximum of 18% increase in the data bus utilization is achieved compared to the commonly used FR-FCFS algorithm. © 2022 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Purple-teaming LLMs with Adversarial Defender Training

arXiv

引用

arXiv 2024年

作者： Zhou, Jingyan Li, Kun Li, Junan Kang, Jiawen Hu, Minda Wu, Xixin Meng, Helen Dept. of Systems Engineering & Engineering Management The Chinese University of Hong Kong Hong Kong Dept. of Computer Science & Engineering The Chinese University of Hong Kong Hong Kong

Existing efforts in safeguarding LLMs are limited in actively exposing the vulnerabilities of the target LLM and readily adapting to newly emerging safety risks. To address this, we present Purple-teaming LLMs with Adversarial Defender training (PAD), a pipeline designed to safeguard LLMs by novelly incorporating the red-teaming (attack) and blue-teaming (safety training) techniques. In PAD, we automatically collect conversational data that cover the vulnerabilities of an LLM around specific safety risks in a self-play manner, where the attacker aims to elicit unsafe responses and the defender generates safe responses to these attacks. We then update both modules in a generative adversarial network style by training the attacker to elicit more unsafe responses and updating the defender to identify them and explain the unsafe reason. Experimental results demonstrate that PAD significantly outperforms existing baselines in both finding effective attacks and establishing a robust safe guardrail. Furthermore, our findings indicate that PAD excels in striking a balance between safety and overall model quality. We also reveal key challenges in safeguarding LLMs, including defending multi-turn attacks and the need for more delicate strategies to identify specific risks. © 2024, CC BY-NC-ND.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

A Social Referencing Disambiguation Framework for Domestic Service Robots

A Social Referencing Disambiguation Framework for Domestic S...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Kevin Fan Melanie Jouaiti Ali Noormohammadi-As Chrystopher L. Nehaniv Kerstin Dautenhahn Dept. of Electrical & Computer Engineering University of Waterloo ON Canada Dept. of Systems Design Engineering University of Waterloo ON Canada

The successful integration of domestic service robots into home environments can bring significant services and convenience to the general population and possibly mitigate important societal issues, such as care provision for older adults. However, home environments are complex, dynamic and object-rich. It is, thus, very probable that service robots will encounter ambiguity while interacting with household items. To enable service robots to be more adaptive, we proposed a learning so-cial referencing computational framework and experimentally evaluated the framework on a mobile manipulator robot, Fetch, in object selection scenarios. The framework allows the robot to (1) detect and analyze the ambiguity level based on the robot's view and user's command, (2) assess the human's attention level and attract their attention, (3) disambiguate references to objects using human feedback and (4) learn novel objects after clarification from the user. System evaluation results are presented. The framework is modular and can be applied to different robotic platforms.

关键词：

来源：评论

学校读者我要写书评

暂无评论

On Detecting Low-pass Graph Signals under Partial Observations

arXiv

引用

arXiv 2024年

作者： Nguyen, Hoang-Son Wai, Hoi-To Dept. of Computer Science & Engineering The Chinese University of Hong Kong Hong Kong Dept. of Systems Engineering & Engineering Management The Chinese University of Hong Kong Hong Kong

The application of graph signal processing (GSP) on partially observed graph signals with missing nodes has gained attention recently. This is because processing data from large graphs are difficult, if not impossible due to the lack of availability of full observations. Many prior works have been developed using the assumption that the generated graph signals are smooth or low pass filtered. This paper treats a blind graph filter detection problem under this context. We propose a detector that certifies whether the partially observed graph signals are low pass filtered, without requiring the graph topology knowledge. As an example application, our detector leads to a pre-screening method to filter out non low pass signals and thus robustify the prior GSP algorithms. We also bound the sample complexity of our detector in terms of the class of filters, number of observed nodes, etc. Numerical experiments verify the efficacy of our method. © 2024, CC BY.

关键词： Data handling

来源：评论

学校读者我要写书评

暂无评论

Applying LSTM for River's Water Level Forecasting as Potential Flood Indication: A Case Study in Greece

Applying LSTM for River's Water Level Forecasting as Potenti...

引用

International Conference on Information, Intelligence, systems and Applications (IISA)

作者： Theodoros Tziolas Elpiniki Papageorgiou Konstantinos Papageorgiou Georgios Zardas Alexios Lekidis Papazoglou Panagiotis Dept. of Energy Systems University of Thessaly Gaiopolis Campus Larisa Greece Dept. of Electrical and Computer Engineering University of Thessaly Volos Greece Dept. of Architecture and Computer and Communication Simulation Systems National and Kapodistrian University of Athens Chalkida Greece

ISBN: (数字)9798350368833

ISBN: (纸本)9798350368840

Floods can have significant life-threatening and economic impacts on human societies. Flood forecasting with data-driven methods is a crucial aspect of disaster risk management, providing valuable insights into potential flood events and allowing for timely mitigation measures. This work illustrates the application of a Long Short-Term Memory (LSTM) neural network for short-term forecasting of a river's water level. The water treatment data used for training the LSTM models were gathered from Sperchios river, located in central Greece. Historical time-series data in a half-hour interval of the river's water level, water velocity, and area precipitation were utilized for the development of the proposed scheme. The developed model is deployed in the backend of a web application for half-hour ahead predictions of the river's water level that are visualized in the frontend. The post-analysis of the deployed forecasting model indicates that it consistently delivers forecasts with minimal error and demonstrates high accuracy in recent flood events.

关键词： Training Precipitation Biological system modeling Prevention and mitigation Neural networks Predictive models Rivers Floods Forecasting Long short term memory

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：