检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Wang, Xinyi Enoch, Simon Yusuf Kim, Dan Dongseong School of Info. Tech and Elec. Engr. University of Queensland Brisbane Australia Department of Computer Science Federal University Kashere Gombe Nigeria

Widely used deep learning models are found to have poor robustness. Little noises can fool state-of-the-art models into making incorrect predictions. While there is a great deal of high-performance attack generation methods, most of them directly add perturbations to original data and measure them using L_p norms;this can break the major structure of data, thus, creating invalid attacks. In this paper, we propose a black-box attack, which, instead of modifying original data, modifies latent features of data extracted by an autoencoder;then, we measure noises in semantic space to protect the semantics of data. We trained autoencoders on MNIST and CIFAR-10 datasets and found optimal adversarial perturbations using a genetic algorithm. Our approach achieved a 100% attack success rate on the first 100 data of MNIST and CIFAR-10 datasets with less perturbation than FGSM. © 2022, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Sub-Picosecond-Level Laser-Based Underwater Transfer of Radio Frequency with Optical Phase Compensation 20

Sub-Picosecond-Level Laser-Based Underwater Transfer of Radi...

引用

20th IEEE International Conference on Communication Technology, ICCT 2020

作者： Pan, Bisong Li, Haopengyu Hou, Dong Zhao, Jianye Univ. of Electronic Science and Technology of China School of Automation Engineering Chengdu China Peking University College of Elec. Engineering and Computer Science Beijing China

ISBN: (纸本)9781728181417

We demonstrated a sub-picosecond laser-based underwater frequency transfer with an optical phase compensation. With this transfer technique, a highly-stable 500 MHz radio-frequency (RF) signal was disseminated over a 5-m underwater link for 5000 s, and the characteristic of the timing fluctuation and instability for the transfer was analyzed and measured. The experimental results show the total root-mean-square (RMS) timing fluctuation of the transferred RF signal with compensation is about 162 fs with a fractional frequency instability on the order of 2.8 × 10-13 at 1 s and 2.7 × 10-16 at 1000 s. The laser-based underwater frequency transfer proposed in this paper has a potential application of transferring atomic clock in water environment as its instability is less than the currently-used commercial Cs or H-master clocks. © 2020 IEEE.

关键词： Stability

来源：评论

学校读者我要写书评

暂无评论

Geometric-Aware Facial Landmark Emotion Recognition

Geometric-Aware Facial Landmark Emotion Recognition

引用

Software engineering and computer science (CSECS), International Conference on

作者： Qixuan Zhang Zhifeng Wang Yang Liu Zhenyue Qin Kaihao Zhang Tom Gedeon College of Engineering and Computer Science Australian National University Canberra Australia School of Elec Eng Comp and Math Sci Curtin University Perth Australia

Emotion recognition is crucial for enhancing human-computer interaction. While traditional approaches largely depend on RGB images, our proposed Geometric-Aware Facial Landmark Emotion Recognition framework harnesses the geometric and spectral attributes of facial landmarks for emotion recognition. This work unfolds three key contributions: utilizing Graph Convolutional Networks to grasp the natural spatial relationships among facial landmarks, introducing distance-aware graph operations to accentuate the relational geometry, and employing spectral encodings to comprehend the frequency-based attributes of landmark positions. Through rigorous experiments on recognized datasets RAF-DB and KDEF, Our method surpasses baseline methods, demonstrating its effectiveness especially in high-resolution scenarios where detailed facial landmarks are apparent. The datasets curated for Facial Landmark Emotion Recognition will also be shared publicly as part of this work, offering a significant resource for the community. The encouraging results highlight the potential of geometric-aware analysis in propelling emotion recognition systems forward, opening avenues for further research in this evolving domain.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Information Transfer in Spintronics Networks under Worst Case Uncertain Parameter Errors

Information Transfer in Spintronics Networks under Worst Cas...

引用

IEEE Conference on Decision and Control

作者： A. A. Rompokos F. C. Langbein E. Jonckheere Dept. of Elec. Eng. Univ. of Southern California Los Angeles CA School of Computer Science and Informatics Cardiff University UK

ISBN: (数字)9781665467612

ISBN: (纸本)9781665467629

A novel quantum landscape optimization with respect to bias field control inputs is developed with the goal of achieving optimal transfer fidelity subject to robustness against bias field, spin couplings and other uncertainties. This objective is achieved by minimization of a convex combination of fidelity error and worst-case perturbation of fidelity error under directional perturbation of uncertain parameters. The novelty is that the end-point perturbations of the parameters are points of a random uniform sampling of the sphere centered at the nominal values of the parameters. This reveals that the previously developed perfect state transfer with zero sensitivity solution keeps high fidelity and robustness under large rather than differential perturbations.

关键词： Robust control Couplings Sensitivity Uncertainty Perturbation methods Minimization Robustness

来源：评论

学校读者我要写书评

暂无评论

Implementation of an Efficient IoT Enabled Automated Paralysis Healthcare System 8

Implementation of an Efficient IoT Enabled Automated Paralys...

引用

8th IEEE International Conference on engineering Technologies and Applied sciences, ICETAS 2023

作者： Annepu, Visalakshi Jameel Al-Tamimi, Adnan Naji Aljibori, H.S.S. Challa, Naga Raju Bagadi, Kalapraveen Mohammed, M.N. Abdullah, Oday I. Alfiras, M. Abbas Helmi, Rabab Alayham School of Comp. Science & Eng. VIT-AP University Amaravati India College of Technical Engineering AI-Farahidi University Baghdad Iraq College of Engineering University of Warith Al-Anbiyaa Karbala Iraq Bapatla Engineering College Dept. of Elec. and Comm. Eng. Baptla India College of Engineering Gulf University Mechanical Engineering Department Sanad26489 Bahrain University of Baghdad Dept of Energy Engineering Iraq College of Engineering Gulf University Mechanical Engineering Dept Sanad26489 Bahrain Hamburg University of Technology Institute of Laser and Systems Technologies Hamburg Germany College of Engineering Gulf University Electrical and Electronic Engineering Department Sanad26489 Bahrain School of Graduate Studies Management and Science University Shah Alam Selangor Malaysia

ISBN: (纸本)9798350327090

This system aims to provide comprehensive care to individuals with paralysis, including symptom monitoring, medical treatment, and rehabilitation. The IoT-based system comprises interconnected devices, such as sensors, wearables, and mobile apps that communicate with one another and with healthcare providers. The system can track patients' vital signs, activity levels, and medication adherence, and provide immediate feedback to healthcare providers. Additionally, the system can aid with rehabilitation exercises, send reminders, and gather data on progress to enhance treatment outcomes. The system's intelligent analytics can also assist healthcare providers in detecting patterns in patient behavior and tailoring treatment plans more effectively. Overall, an IoT-based paralysis healthcare system has the potential to transform healthcare delivery by offering personalized, real-time care and monitoring to individuals with paralysis. © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Cognitive-inspired Post-processing of optical character recognition for Swedish addresses 21

Cognitive-inspired Post-processing of optical character reco...

引用

21st IEEE International Conference on Cognitive Informatics and Cognitive Computing, ICCI*CC 2022

作者： Andersson, Moa Kanwal, Summrina Khan, Faiza School of Electrical Engineering and Computer Science Kth Royal Institute of Technology in Stockholm Sweden Sch. of Elec. Eng. and Comp. Sci. Kth Roy. Inst. of Technol. in Stockholm Ctr. for Appl. Intelligent Syst. Res. Halmstad Univ. Sweden Riphah International University Faculty of Computing Islamabad Pakistan

ISBN: (纸本)9781665490849

Optical character recognition (OCR) has many ap-plications, such as digitizing historical documents, automating processes, and helping visually impaired people read. However, extracting text from images into a digital format is not an easy problem to solve, and the outputs from the OCR frameworks often include errors. The complexity comes from the many variations in (digital) fonts, handwriting, lighting, etc. To tackle this problem, this thesis investigates two different methods for correcting the errors in OCR output. The used dataset consists of Swedish addresses. The methods are therefore applied to postal automation to investigate the usage of these methods for further automating postal work by automatically reading addresses on parcels using OCR. The first method, the lexical implementation, uses a dataset of Swedish addresses so that any valid address should be in this dataset (hence there is a known and limited vocabulary), and misspelled addresses are corrected to the address in the lexicon with the smallest Levenshtein distance. The second approach uses the same dataset, but with artificial errors, or artificial noise, added. The addresses with this artificial noise are then used together with their correct spelling to train a machine learning model based on Neural machine translation (NMT) to automatically correct errors in OCR read addresses. The results from this study could contribute by defining in what direction future work connected to OCR and postal addresses should go. The results were that the lexical implementation outperformed the NMT model. However, more experiments including real data would be required to draw definitive conclusions as to how the methods would work in real-life applications. © 2022 IEEE.

关键词： Optical character recognition

来源：评论

学校读者我要写书评

暂无评论

Cardiovascular Disease Prediction Using Machine Learning Algorithms 8

Cardiovascular Disease Prediction Using Machine Learning Alg...

引用

8th IEEE International Conference on engineering Technologies and Applied sciences, ICETAS 2023

作者： Bagadi, Kalapraveen Annepu, Visalakshi Jameel Al-Tamimi, Adnan Naji Challa, Naga Raju Aljibori, H.S.S. Mohammed, M.N. Abdullah, Oday I. Abbas Helmi, Rabab Alayham Alfiras, M. School of Electronics Enineering VIT-AP University Amaravati India School of Comp. Science & Eng. VIT-AP University Amaravati India College of Technical Engineering Al-Farahidi University Baghdad Iraq Bapatla Engineering College Dept. of Elec. and Comm. Eng. Baptla India College of Engineering University of Warith Al-Anbiyaa Karbala Iraq College of Engineering Gulf University Mechanical Engineering Department Sanad26489 Bahrain University of Baghdad Dept of Energy Engineering Iraq College of Engineering Gulf University Mechanical Engineering Dept Sanad26489 Bahrain Hamburg University of Technology Institute of Laser and Systems Technologies Hamburg Germany School of Graduate Studies Management and Science University Selangor Shah Alam Malaysia College of Engineering Gulf University Electrical and Electronic Engineering Department Sanad26489 Bahrain

ISBN: (纸本)9798350327090

The fact that cardiovascular disease (CVD) is a major cause of death worldwide highlights the significance of accurate prediction for successful preventative and treatment measures. Machine learning algorithms, which use the analysis of vast patient data to reveal hidden patterns and risk variables, have recently come to light as potential techniques for CVD prediction. This study intends to analyse how machine learning (ML) techniques are used in CVD prediction and evaluate how well they perform in comparison to conventional approaches. The study makes use of a sizable patient cohort's medical history, demographic data, and clinical factors in a complete dataset. Predictive models are built using a variety of machine learning algorithms, including support vector machine (SVM), gradient boosting, K-nearest neighbours, naive Bayes classifier, and logistic regression. To find the most important factors influencing CVD risk, feature selec.ion techniques are used. Metrics like accuracy, sensitivity, specificity, and the area under the receiver operating characteristic curve are used to assess how well the machine learning models work. The outcomes are contrasted with well-known risk prediction models and clinical guidelines in order to assess the added value of machine learning methods. This work intends to improve CVD prediction capabilities and offer useful insights for better risk assessment and management strategies by utilizing the power of machine learning. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Experimental Investigation of Reduced Complexity MIMO Equalization in a 55-Mode Fiber SDM Transmission System

Experimental Investigation of Reduced Complexity MIMO Equali...

引用

2023 Optical Fiber Communications Conference and Exhibition, OFC 2023

作者： Ospina, Ruby S. B. Rademacher, Georg Luis, Ruben S. Puttnam, Benjamin J. Fontaine, Nicolas K. Mazur, Mikael Chen, Haoshuo Ryf, Roland Neilson, David T. Dahl, Daniel Carpenter, Joel Sillard, Pierre Achten, Frank Bigot, Marianne Mello, Darli A. A. Furukawa, Hideaki Nict 4-2-1 Nukui-Kitamachi Tokyo Koganei184-8795 Japan School of Electrical and Computer Engineering University of Campinas Campinas13083-852 Brazil Nokia Bell Labs 600 Mountain Ave Murray HillNJ07974 United States School of Inf. Technol. and Elec. Eng The University of Queensland BrisbaneQLD4072 Australia Prysmian Group Parc des Industries Artois Flandres Haisnes62092 France Prysmian Group Eindhoven5651 CA Netherlands

We investigate the MIMO equalizer complexity reduction by selec.ive filter deactivation in a 25.9 km 55-mode SDM transmission system. We demonstrate a 21.5% equalizer complexity reduction at the cost of a 4.9% decreas... 详细信息

ISBN: (纸本)9781957171180

关键词： Equalizers

来源：评论

学校读者我要写书评

暂无评论

A Lightening Fine-grained Access Control Scheme Supporting Full Policy Hiding in Cloud Storage

A Lightening Fine-grained Access Control Scheme Supporting F...

引用

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Jiaoli Shi Chao Hu Shimao Yao Zhuolin Mei Bin Wu Hui Li School of Computer and Big Data Jiujiang Univ. Jiujiang China School of Software IoT Engineering Jiangxi Univ. of Finance and Economics Nanchang China Jiujiang Key Lab. of Network and Information Security Jiujiang China School of Computer and Big Data Jiujiang University Jiujiang China School of Elec. and Comp. Engineering Peking University Shenzhen China

Efficiency, security, and flexibility are difficult to balance in a full policy hiding CP-ABE scheme. This paper creatively converts the privacy matching problem of access policy and a user’s private key to the privacy three-party set computation problem. Then the new privacy set computation problem is resolved by a message driven key generation method. Additionally, the ROBDD (Reduced Ordered Binary Decision Diagrams) is utilized to rich access structure expression and convert access policies into feasible path sets. Each feasible path is composed of attributes and these attributes are bound to the ciphertext using CP-ABE. Based on the innovative ideas mentioned above, we present a Lighten Fine-grained Access Control scheme supporting Full Policy Hidden (LFAC-FPH) that integrates data confidentiality protection, access policy rich expression but complete hiding, fine-grained access control, and lightweight terminal computing. Our scheme has three advantages: 1) High Efficiency. The proposed scheme can achieve fast privacy matching of access policies during user decryption. 2) Full Policy Hiding. The access policy bound by an owner on the ciphertext does not leak any information. Moreover, a user cannot know attributes they do not own. 3) High Flexibility. The decryption process does not require online from owners or KGC, and system attributes can be added at any time.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Lightweight and Efficient Scheme for e-Health Care System using Blockchain Technology

A Lightweight and Efficient Scheme for e-Health Care System ...

引用

International Conference on Information Systems and computer Networks (ISCON)

作者： Sandeep Saxena Namita Arya Sunil Kumar Bharti Vimal Dwivedi Dept. of CSE GNIOT Greater Noida India Dept. of CSE Galgotias University Greater Noida India Dept. of IT GCET Greater Noida India Institute of Computer Science University of Taru Estonia School of Elec. Elect. Engg. and Computer Science Queens University Belfast Northern Ireland

We are witnessed to the huge amount of health care information is processed via Internet and uploaded to the servers. Hence, the network content suffers from various challenges in handling this wide range of information such as privacy-preservation, message requests, and sharing of information with the entities. Protection of health care information with less communication overhead and avoid signaling congestion among entities is the biggest concern. We suggest a simple and effective blockchain-based system for e-health care in order to address these problems. We attempt to show the collective trust between receiver/ users and key generation center (KGC). Due to the characteristics such as tamper-resistant of transactions and responsiveness, the blockchain technology maintains the data access policy and privacy of each receiver/ users. In addition, we provide the public transactions apparently with the help of miners. Also, the performance analysis shows that the protocol is free from all the security attacks and avoid the signaling congestion with less overhead.

关键词： Privacy Protocols Information security Medical services Information processing Blockchains Performance 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：