检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Wang, Xiang Yang, Yimin Guo, Zhichang Zhou, Zhili Liu, Yu Pang, Qixiang Du, Shan The Dept. of Computer Science Lakehead University Thunder BayON Canada The Dept. of electrical and computer engineering Western University LondonON Canada The School of Mathematics Harbin Institute of Technology Hei Long Jiang China The School of Computer and Software Nanjing University of Information Science and Technology Jiangsu China The School of Microelectronics Tianjin University Tianjin China The Okanagan College KelownaBC Canada The Dept. of Comp. Sci. Math Physics & Statistics The University of British Columbia OkanaganBC Canada

Deep Convolutional Neural Networks (DCNNs) have exhibited impressive performance on image super-resolution tasks. However, these deep learning-based super-resolution methods perform poorly in real-world super-resolution tasks, where the paired high-resolution and low-resolution images are unavailable and the low-resolution images are degraded by complicated and unknown kernels. To break these limitations, we propose the Unsupervised Bi-directional Cycle Domain Transfer Learning-based Generative Adversarial Network (UBCDTL-GAN), which consists of an Unsupervised Bi-directional Cycle Domain Transfer Network (UBCDTN) and the Semantic Encoder guided Super Resolution Network (SESRN). First, the UBCDTN is able to produce an approximated real-like LR image through transferring the LR image from an artificially degraded domain to the real-world LR image domain. Second, the SESRN has the ability to super-resolve the approximated real-like LR image to a photo-realistic HR image. Extensive experiments on unpaired real-world image benchmark datasets demonstrate that the proposed method achieves superior performance compared to state-of-the-art methods. © 2022, CC BY.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

SOLAS: Superpositioning an Optical Lens in Automotive Simulation

arXiv

引用

arXiv 2025年

作者： Jakab, Daniel Barthel, Julian Braun, Alexander Mohandas, Reenu Deegan, Brian Michael Kumbham, Mahendar Molloy, Dara Collins, Fiachra Scanlan, Anthony Eising, Ciarán Dept. of Electronic and Computer Engineering University of Limerick Castletroy Co. Limerick V94 T9PX Ireland Faculty of Electrical Engineering & Information Technology University of Applied Sciences Düsseldorf40476 Germany Dept. of Electrical and Electronic Engineering University of Galway GalwayH91 TK33 Ireland Valeo Vision Systems Tuam GalwayDY1 22DJ Ireland Lero the Science Foundation Ireland Research Centre for Software University of Limerick LimerickV94 T9PX Ireland

Automotive Simulation is a potentially cost-effective strategy to identify and test corner case scenarios in automotive perception. Recent work has shown a significant shift in creating realistic synthetic data for road traffic scenarios using a video graphics engine. However, a gap exists in modeling realistic optical aberrations associated with cameras in automotive simulation. This paper builds on the concept from existing literature to model optical degradations in simulated environments using the Python-based ray-tracing library KrakenOS. As a novel pipeline, we degrade automotive fisheye simulation using an optical doublet with +/-2◦ Field of View(FOV), introducing realistic optical artifacts into two simulation images from SynWoodscape and Parallel Domain Woodscape. We evaluate KrakenOS by calculating the Root Mean Square Error (RMSE), which averaged around 0.023 across the RGB light spectrum compared to Ansys Zemax OpticStudio, an industrial benchmark for optical design and simulation. Lastly, we measure the image sharpness of the degraded simulation using the ISO12233:2023 Slanted Edge Method and show how both qualitative and measured results indicate the extent of the spatial variation in image sharpness from the periphery to the center of the degradations. © 2025, CC BY.

关键词： Ray tracing

来源：评论

学校读者我要写书评

暂无评论

Classification of Awareness in Disorders of Consciousness Using Common Spatial Pattern

Classification of Awareness in Disorders of Consciousness Us...

引用

International Winter Workshop on Brain-computer Interface (BCI)

作者： Chaewon Lee Sunho Lee Jitka Annen Ji-Hoon Jeong Marcello Massimini Silvia Casarotto Melanie Boly Olivier Bodart Aurore Thibaut Mario Rosanova Steven Laureys Olivia Gosseries Minji Lee Dept. Data Science The Catholic University of Korea Bucheon Republic of Korea Dept. Biomedical Software Engineering The Catholic University of Korea Bucheon Republic of Korea Dept. GIGA-Research & Neurology University and University Hospital of Liege Liege Belgium Dept. Data Analysis University of Ghent Ghent Belgium Dept. Computer Science Chungbuk National University Cheongju Republic of Korea Dept. Biomedical and Clinical Sciences “L. Sacco” University of Milan Milan Italy Dept. Psychiatry Wisconsin Institute for Sleep and Consciousness University of Wisconsin Madison USA Coma Science Group GIGA-Consciousness GIGA Research Center University of Liège Liège Belgium Centre du Cerveau Neurology department University Hospital of Liège Liège Belgium

ISBN: (数字)9798331521929

ISBN: (纸本)9798331521936

Advances in intensive care have improved the survival rate of patients with severe acute brain injury, but diagnostic errors for patients with disorders of consciousness are still high. Accurate diagnosis of these patients is very important because effective treatment can vary depending on the diagnosis. In this study, we propose a framework for classifying unresponsive wakefulness syndrome and minimally conscious state, focusing on awareness. In particular, power spectral density and common spatial patterns were used together, considering that spatial information is a key feature in consciousness. The 16 patients with unresponsive wakefulness syndrome and 14 with minimally conscious state underwent resting-state electroencephalography measurements. In addition, we compared the performance by utilizing each frequency (delta, theta, alpha, beta, gamma bands) related to consciousness. As a result, the highest accuracy of 95.06% was achieved by the EEGNet classifier, especially in the beta frequency band. We demonstrated that spatial information is very important in consciousness, as we observed that classification performance improved when common spatial patterns were used. These results provide insight into various frameworks for diagnosing patients with disorders of consciousness and may help patients survive by increasing the diagnosis rate in the future.

关键词： Deep learning Accuracy Biological system modeling Pattern classification Focusing Signal processing Brain modeling Particle measurements Electroencephalography Robustness

来源：评论

学校读者我要写书评

暂无评论

Transportation Path Planning Model for Multi-Constraint Unmanned Aerial Vehicle in Healthcare

Transportation Path Planning Model for Multi-Constraint Unma...

引用

Innovations in High Speed Communication and Signal Processing (IHCSP), International Conference on

作者： Haewon Byeon Pramod Kumar Kottala Sri Yogi Leeladhar Gudala Mukesh Soni Samarth Motagi Department of AI and Software Inje University Gimhae Republic of Korea Ganga Institute of Technology and Management Jhajjar Haryana India Dept of Operations A Constituent College of Symbiosis International University Pune India Department of Computer Science and Engineering Valparaiso University West Godavari India D. Y. Patil Vidyapeeth Pune Dr. D. Y. Patil School of Science & Technology Pune Department of Aircraft Seating Collins Aerospace Winston-Salem North Carolina

ISBN: (数字)9798350368949

ISBN: (纸本)9798350368956

In response to the path planning problem of using Unmanned Aerial Vehicle (UAV) for blood transportation, with the objective of minimizing the total distance travelled by the UAV, a multi-constraint drone blood transportation path planning model is established. Taking into account the limited number of drone take-off and landing platforms and the safety time intervals for continuous drone take-off and landing, a drone take-off scheduling strategy is designed to reduce the total time spent by UAV completing transportation tasks. Additionally, an Imperial Competition Algorithm based on Imperialist Competitive Algorithm is proposed to solve this problem. This algorithm introduces a sine disturbance strategy and adds Imperial Reform stages to improve the search accuracy of the algorithm. It utilizes acceptance criteria related to solution quality to maintain the diversity of the population. Validation is conducted using benchmark examples and instances of drone blood transportation. The results indicate that the proposed algorithm can provide transportation solutions for drone blood transportation tasks that meet various constraints without any conflicts in drone take-off and landing. The drone take-off scheduling strategy effectively reduces the total time spent by UAV in completing tasks.

关键词： Technological innovation Accuracy Transportation Signal processing algorithms Medical services Autonomous aerial vehicles Path planning Mathematical models Blood Drones

来源：评论

学校读者我要写书评

暂无评论

State of Security Awareness in the Additive Manufacturing Industry: 2020 Survey 6

State of Security Awareness in the Additive Manufacturing In...

引用

6th International Conference on Additive Manufacturing, ICAM 2021

作者： Yampolskiy, Mark Bates, Paul Seifi, Mohsen Shamsaei, Nima Dept. of Computer Science and Software Engineering Auburn Cyber Research Center 3127B Shelby Center 345 W. Magnolia Ave. AuburnAL36849 United States ASTM International 1850 M St. NW Suite 1030 WashingtonDC20036 United States Dept. of Mechanical Engineering Auburn University 1418 Wiggins Hall 354 War Eagle Way AuburnAL36849 United States National Center for Additive Manufacturing Excellence Auburn University 311 W. Magnolia Ave. AuburnAL36849 United States

ISBN: (纸本)9780803177352

The security of additive manufacturing (AM) gets increased attention due to the growing proliferation and adoption of AM in a variety of applications and business models. However, there is a significant disconnect between the AM community focused on manufacturing and the AM security community focused on securing this highly computerized manufacturing technology. To bridge this gap, we surveyed the America Makes AM community, asking in total 11 AM security-related questions aiming to discover the existing concerns, posture, and expectations. The first set of questions aimed to discover how many of these organizations use AM, outsource AM, or provide AM as a service. Then we asked about biggest security concerns as well as about assessment of who the potential adversaries might be and their motivation for attack. We then proceeded with questions on any experienced security incidents, if any security risk assessment was conducted, and if the participants' organizations were partnering with external experts to secure AM. Last, we asked whether security measures are implemented at all and, if so, whether they fall under the general cybersecurity category. Out of 69 participants affiliated with commercial industry, agencies, and academia, 53 have completed the entire survey. This paper presents the results of this survey, as well as our assessment of the AM security posture. The answers are a mixture of what we could label as expected, shocking but not surprising, and completely unexpected. Assuming that the provided answers are somewhat representative of the current state of the AM industry, we conclude that the industry is not ready to prevent or detect AM-specific attacks that have been demonstrated in the research literature. Copyright © 2022 by ASTM International.

关键词： 3D printing

来源：评论

学校读者我要写书评

暂无评论

The concordia NLG surface realizer at SR'19 2

The concordia NLG surface realizer at SR'19

引用

2nd Workshop on Multilingual Surface Realisation, MSR@EMNLP-IJCNLP 2019

作者： Farahnak, Farhood Rafiee, Laya Kosseim, Leila Fevens, Thomas Dept. of Computer Science and Software Engineering Concordia University Montreal Canada

ISBN: (纸本)9781950737765

This paper presents the model we developed for the shallow track of the 2019 NLG Surface Realization Shared Task. The model reconstructs sentences whose word order and word inflections were removed. We divided the problem into two sub-problems: reordering and inflecting. For the purpose of reordering, we used a pointer network integrated with a transformer model as its encoder-decoder modules. In order to generate the inflected forms of tokens, a Feed Forward Neural Network was employed. © 2019 Association for Computational Linguistics.

关键词： Feedforward neural networks

来源：评论

学校读者我要写书评

暂无评论

Explaining RADAR features for detecting spoofing attacks in Connected Autonomous Vehicles

arXiv

引用

arXiv 2022年

作者： Rastogi, Nidhi Rampazzi, Sara Clifford, Michael Heller, Miriam Bishop, Matthew Levitt, Karl Dept. of Software Engineering Rochester Institute of Technology RochesterNY United States University of Florida GainesvilleFL United States Toyota InfoTech Labs Mountain ViewCA United States Department of Computer Science University of California DavisCA United States

Connected autonomous vehicles (CAVs) are anticipated to have built-in AI systems for defending against cyberattacks. Machine learning (ML) models form the basis of many such AI systems. These models are notorious for acting like black boxes, transforming inputs into solutions with great accuracy, but no explanations support their decisions. Explanations are needed to communicate model performance, make decisions transparent, and establish trust in the models with stakeholders. Explanations can also indicate when humans must take control, for instance, when the ML model makes low confidence decisions or offers multiple or ambiguous alternatives. Explanations also provide evidence for post-incident forensic analysis. Research on explainable ML to security problems is limited, and more so concerning CAVs. This paper surfaces a critical yet under-researched sensor data uncertainty problem for training ML attack detection models, especially in highly mobile and risk-averse platforms such as autonomous vehicles. We present a model that explains certainty and uncertainty in sensor input- a missing characteristic in data collection. We hypothesize that model explanation is inaccurate for a given system without explainable input data quality. We estimate uncertainty and mass functions for features in radar sensor data and incorporate them into the training model through experimental evaluation. The mass function allows the classifier to categorize all spoofed inputs accurately with an incorrect class *** Codes 68M25, 60B11, 68T05 © 2022, CC BY-NC-ND.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Adaptive Security Policy Management in Cloud Environments Using Reinforcement Learning

arXiv

引用

arXiv 2025年

作者： Saqib, Muhammad Mehta, Dipkumar Yashu, Fnu Malhotra, Shubham Dept. of Computer Science Texas Tech University LubbockTX United States C.K.Pithawalla College of Engineering and Technology Gujrat India Dept. of Computer Science Stony Brook University Stony BrookNY United States Dept. of Software Engineering Rochester Institute of Technology RochesterNY United States

The security of cloud environments, such as Amazon Web Services (AWS), is complex and dynamic. Static security policies have become inadequate as threats evolve and cloud resources exhibit elasticity [1]. This paper addresses the limitations of static policies by proposing a security policy management framework that uses reinforcement learning (RL) to adapt dynamically. Specifically, we employ deep reinforcement learning algorithms, including deep Q Networks and proximal policy optimization, enabling the learning and continuous adjustment of controls such as firewall rules and Identity and Access Management (IAM) policies. The proposed RL based solution leverages cloud telemetry data (AWS Cloud Trail logs, network traffic data, threat intelligence feeds) to continuously refine security policies, maximizing threat mitigation, and compliance while minimizing resource impact. Experimental results demonstrate that our adaptive RL based framework significantly outperforms static policies, achieving higher intrusion detection rates (92% compared to 82% for static policies) and substantially reducing incident detection and response times by 58%. In addition, it maintains high conformity with security requirements and efficient resource usage. These findings validate the effectiveness of adaptive reinforcement learning approaches in improving cloud security policy management. Copyright © 2025, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Proposed Framework for Smart Geo-Fencing For Religious Places

A Proposed Framework for Smart Geo-Fencing For Religious Pla...

引用

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

作者： Ankit Vishnoi Tanupriya Choudhury Jagdish Chandra Patni Ayan Sar Hussain Falih Mahdi CSE Dept. Symbiosis Institute of Technology Symbiosis International (Deemed University) Pune Maharashtra India. CSE Dept. Lavale Campus Symbiosis Institute of Technology Symbiosis International (Deemed University) Pune Maharashtra India. Symbiosis Institute of Technology Nagpur Campus Symbiosis International (Deemed University) Pune India. School of Computer Science University of Petroleum and Energy Studies (UPES) Dehradun Uttarakhand India. Dept. of Computer and Software Engineering University of Diyala Baquba Iraq.

The innovative system known as “Smart Geo-fencing for Religious Places” integrates Blockchain and Zero Power Device technology to enhance the reverence of sacred sites. By amalgamating the robustness of blockchain with geofencing capabilities and electronic apparatuses, this solution delineates invisible perimeters encircling religious structures like mosques, churches, and temples. As worshippers enter these digitally marked zones with their smartphones, the setup is capable of monitoring select operations such as making calls, sending texts, or receiving app alerts to foster a serene atmosphere. Furthermore, leveraging blockchain’s prowess guarantees that all recorded data remains secure and unalterable. The incorporation of devices that consume minimal energy is crucial for ensuring sustainability. This sophisticated fusion promotes tranquility within religious communities by adeptly marrying contemporary technological advancements with age-old spiritual practices.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cyberattack Analysis on Smart Home Iot Devices in the Smart Grid Environment Using Gridattackanalyzer

SSRN

引用

SSRN 2023年

作者： Darteh, Oscar Famous Liu, Qi Bah, Ibrahima Amoah, Lord Acakpovi, Amevi Liu, Xiaodong School of Electronic and Information Engineering Nanjing University of Information Science and Technology No.219 Ningliu Road Jiangsu 210044 China Wuxi University No.333 Xishan Road Jiangsu 214106 China School of Mathematics and Computer Science Zhejiang Normal University Jinhua China School of Computer and Software Nanjing University of Information Science & Technology Nanjing210044 China Dept. of Electrical and Electronic Engineering Accra Technical University P.O.Box GP561 Barnes Road Accra Ghana School of Computing Edinburgh Napier University 10 Colinton Road EdinburghEH10 5DT United Kingdom

As the deployment of smart home IoT devices and smart grid infrastructure grows, the threat of cyberattacks has become a pressing concern. The common vulnerability exposure (CVE) of smart grid infrastructure presents a prime opportunity for attackers to launch cyberattacks, often exploiting the vulnerabilities of medium and vulnerable smart home IoT devices. This paper presents a comprehensive analysis of cyberattacks launched on the smart grid through vulnerable IoT devices, using key security metrics to evaluate the attacks' success probability and path analysis. Our main contribution is decreasing the attack success probability, risk, and cost to attackers while increasing the unlikelihood and rarity of attack paths. To achieve this, we created four case study models using the GridAttackAnalyzer on the Feeder R4-12.47-2 of the Pacific Northwest National Laboratory (PNNL). Additionally, we developed a fifth model that deploys patching of CVEs for the previous case studies. Our analysis revealed that our models are the first of their kind created using the GridAttackAnalyzer, and the patch model has successfully achieved the aim of reducing the attack success probability and risk to the smart grid system. The findings of this study can inform the development of effective cyber defense strategies for smart home IoT devices and smart grid infrastructure. © 2023, The Authors. All rights reserved.

关键词： Regression analysis

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：