检索结果-内蒙古大学图书馆

3rd International Conference on computer Vision and Data Mining, ICCVDM 2022

作者： Zhang, Yuze Zhang, Yaqi Zhang, Honghao School of Computer Science and Engineering Tianjin University of Technology Tianjin300384 China School of Information and Electronics Beijing Institute of Technology Beijing100081 China

ISBN: (纸本)9781510661363

Biometric methods have been widely used for privacy protection. Biometric recognition has unique and random characteristics, which can better protect people's privacy and security. In this paper, a biometric system based on plethysmography (PPG) signals using fuzzy min-max neural network are developed. The PPG signals have the ability of liveness detection compared with fingerprint recognition and face recognition. The system consists of three processes: signal preprocessing, feature extraction and model classification. The experimental results were obtained an accuracy of 97.62% in the Capnobase database. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Electrically programmable solid-state metasurfaces via flash localised heating

引用

Light(science & Applications) 2023年第3期12卷 391-397页

作者： Khosro Zangeneh Kamali Lei Xu Nikita Gagrani Hark Hoe Tan Chennupati Jagadish Andrey Miroshnichenko Dragomir Neshev Mohsen Rahmani ARC Centre of Excellence for Transformative Meta-Optical Systems(TMOS) Research School of PhysicsThe Australian National UniversityCanberraACT 2601Australia Advanced Optics and Photonics Laboratory Department of EngineeringSchool of Science and TechnologyNottingham Trent UniversityNottinghamNG118NSUK School of Engineering and Information Technology University of New South WalesCanberraACT 2600Australia

In the last decades,metasurfaces have attracted much attention because of their extraordinary light-scattering ***,their inherently static geometry is an obstacle to many applications where dynamic tunability in their optical behaviour is ***,there is a quest to enable dynamic tuning of metasurface properties,particularly with fast tuning rate,large modulation by small electrical signals,solid state and programmable across multiple ***,we demonstrate electrically tunable metasurfaces driven by thermo-optic effect and flash-heating in *** show a 9-fold change in transmission by<5 V biasing voltage and the modulation rise-time of<625µ*** device consists of a silicon hole array metasurface encapsulated by transparent conducting oxide as a localised *** allows for video frame rate optical switching over multiple pixels that can be electrically *** of the advantages of the proposed tuning method compared with other methods are the possibility to apply it for modulation in the visible and near-infrared region,large modulation depth,working at transmission regime,exhibiting low optical loss,low input voltage requirement,and operating with higher than video-rate switching *** device is furthermore compatible with modern electronic display technologies and could be ideal for personal electronic devices such as flat displays,virtual reality holography and light detection and ranging,where fast,solid-state and transparent optical switches are required.

关键词： tuning flash state

来源：评论

学校读者我要写书评

暂无评论

Software Defect Prediction Using Ensemble Technique

Software Defect Prediction Using Ensemble Technique

引用

International Conference on information Management and Technology (ICIMTech)

作者： Pandu Wicaksono Panji Arisaputra Rezky Yunanda Willy Kristian Almuzhidul Mujhid Software Engineering Department School of Computer Science Bina Nusantara University Jakarta Indonesia Information Systems Department School of Information Systems Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798350390025

ISBN: (纸本)9798350390032

Software defect prediction is the methodical process of identifying code segments that are likely to have problems. This is done by analyzing software metrics and using categorization algorithms. This work introduces an alternate approach that utilizes ensemble learning techniques to improve the effectiveness of fault detection models. The models utilized in this study are CodeGPT and CodeBERT, both of which are transformer-based deep learning models that can extract code features from source code. The models are trained using the PROMISE dataset, which consists of Java projects that have been labeled with defects. The test results show that using ensemble learning methods can improve the accuracy, precision, recall, and F1 score of a single model by around 1-3%. This study contributes to the progress of software dependability and quality by utilizing advanced software fault prediction algorithms.

关键词： Codes Source coding Software algorithms Predictive models Prediction algorithms Feature extraction Transformers Software Ensemble learning Software measurement

来源：评论

学校读者我要写书评

暂无评论

F-GAN: A fusion algorithm for surface defect detection based on generative adversarial network 8

F-GAN: A fusion algorithm for surface defect detection based...

引用

8th International Conference on Intelligent Computing and Signal Processing, ICSP 2023

作者： Dai, Yang Zhang, Lin Wu, YaJuan China West Normal University School of Electronic Information Engineering Nanchong China China West Normal University School of Computer Science Nanchong China

ISBN: (纸本)9798350302455

With the continuous development of manufacturing intelligence, the focus of industrial research has gradually shifted from quantity to quality. There have been technical difficulties in the detection of surface defects of products. Therefore, the detection accuracy of product quality has become a research hotspot. In this paper, we propose a fusion algorithm F-GAN for unsupervised surface defect detection based on generative adversarial network. The method builds a network model based on encoder-decoder-encoder and incorporates an attention feature fusion module in the decoder, which can complete defect detection under defect-free sample conditions. In addition, we use structural similarity in the loss function to measure the reconstruction effect of the network from multiple perspectives. Finally, to visualize the defect segmentation effect of the network, we designed the residual binarization module to binarize the residual images to obtain the final defect detection results. We conducted experiments on the MVTec public dataset. The results show that our proposed method has a high level of AUC with an average improvement of 2.1%. In addition, to illustrate the effectiveness of the F-GAN, we conducted ablation experiments for different modules. © 2023 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

A DC Microgrid Attack Detection Strategy based on Complete Ensemble Empirical Mode Decomposition with Adaptive Noise

A DC Microgrid Attack Detection Strategy based on Complete E...

引用

2023 International Conference on Smart Electrical Grid and Renewable Energy, SEGRE 2023

作者： Wen, Mengfei Wen, Yian Zhang, Yu Zhang, Zhongke Zhu, Ren Changsha Preschool Education College School of Information Technology Changsha China Changsha University of Science and Technology School of Electrical and Information Engineering Changsha China Central South University School of Computer Science and Engineering Changsha China Changsha Preschool Education College School of Preeducation Changsha China

ISBN: (纸本)9798350323269

With the continuous development of renewable energy technologies and intelligent control systems, DC microgrids have become a popular direction for the development of future energy systems with the advantages of high efficiency and flexibility. However, because DC microgrids are closely connected to the Internet, their complex network structures and communication protocols make them easy targets for cyber attacks. Therefore, this paper proposes an attack detection strategy based on the complete ensemble empirical mode decomposition with adaptive noise for detecting abnormal output data in DC microgrids. First, the voltage signal with a fast response rate is analyzed based on the effect of data injection on the output of DC microgrids. Secondly, sufficient feature extraction is performed on the output voltage using complete set empirical mode decomposition. Then, calculate the energy of the decomposed feature mode function, and set an anomaly threshold detection scheme based on the energy interval during normal operation of the DC microgrid to complete the detection of the abnormal output of the DC microgrid. Finally, the simulation verifies the reliability and effectiveness of the proposed detection strategy. © 2023 IEEE.

关键词： Renewable energy resources

来源：评论

学校读者我要写书评

暂无评论

Cyber-Immunity at the Core: Securing Biomedical Devices through Hardware-Level Machine Learning Defense

Cyber-Immunity at the Core: Securing Biomedical Devices thro...

引用

2023 IEEE Biomedical Circuits and systems Conference, BioCAS 2023

作者： Sayadi, Hossein He, Zhangying Fernandes, Chelsea William Miari, Tahereh California State University Department of Computer Engineering and Computer Science Long BeachCA United States Claremont Graduate University Center for Information Systems and Technology CA United States

ISBN: (纸本)9798350300260

Healthcare cybersecurity is crucial for protecting hospitals' networks and computing systems from malicious cyber-attacks. With the increasing motivation and capability of cyber attackers, it is necessary to secure the software and hardware infrastructure of biomedical computing systems used in healthcare. Due to the increasingly digitized nature of modern biomedical devices used in healthcare systems, effective cybersecurity solutions have become more essential. Traditional security protocols focused on software-level protection, with the underlying hardware assumed to be secure. However, recent studies have revealed vulnerabilities in hardware that attackers can exploit to compromise computing systems. To address this, in this paper a bottom-up approach is proposed, delegating security to the underlying hardware to enhance the security and cost-efficiency with less visibility to the attacker. This paper aims to develop effective intelligent countermeasures for hardware-assisted cyber-security at run-time in biomedical devices. It leverages processors' performance events via Hardware Performance Counters (HPCs) combined with Machine Learning (ML) techniques to fortify biomedical devices at the hardware level. To achieve this objective, we introduce a tailored and cost-effective hardware monitoring framework, complemented by a machine learning-enabled methodology. This approach enhances the accuracy and efficiency of malware detection and identification using real-time data from biomedical processors' hardware events. The experimental results demonstrate that the XGBoost model, using 4 hardware events, excels in malware detection, boasting 95% detection rate (F-measure and Accuracy), efficient resource utilization, and low inference latency. Additionally, the ExtraTree classifier achieves 87% F-measure and exhibits swift performance in classifying malware types in real-time. © 2023 IEEE.

关键词： Biomedical Cybersecurity Hardware Security Machine Learning Malware Detection and Identification

来源：评论

学校读者我要写书评

暂无评论

PPA: Preference Profiling Attack Against Federated Learning 30

PPA: Preference Profiling Attack Against Federated Learning

引用

30th Annual Network and Distributed System Security Symposium, NDSS 2023

作者： Zhou, Chunyi Gao, Yansong Fu, Anmin Chen, Kai Dai, Zhiyang Zhang, Zhi Xue, Minhui Zhang, Yuqing School of Computer Science and Engineering Nanjing University of Science and Technology China State Key Laboratory of Information Security Institute of Information Engineering Chinese Academy of Science China Data61 CSIRO Syndey Australia National Computer Network Intrusion Protection Center University of Chinese Academy of Science China

ISBN: (纸本)1891562835

—Federated learning (FL) trains a global model across a number of decentralized users, each with a local dataset. Compared to traditional centralized learning, FL does not require direct access to local datasets and thus aims to mitigate data privacy concerns. However, data privacy leakage in FL still exists due to inference attacks, including membership inference, property inference, and data inversion. In this work, we propose a new type of privacy inference attack, coined Preference Profiling A ttack (PPA), t hat accurately profiles t he p rivate p references o f a l ocal u ser, e .g., m ost liked (disliked) items from the client’s online shopping and most common expressions from the user’s selfies. I n g eneral, P PA can profile t op-k (i.e., k = 1, 2, 3 a nd k = 1 i n p articular) preferences contingent on the local client (user)’s characteristics. Our key insight is that the gradient variation of a local user’s model has a distinguishable sensitivity to the sample proportion of a given class, especially the majority (minority) class. By observing a user model’s gradient sensitivity to a class, PPA can profile the sample proportion of the class in the user’s local dataset, and thus the user’s preference of the class is exposed. The inherent statistical heterogeneity of FL further facilitates PPA. We have extensively evaluated the PPA’s effectiveness using four datasets (MNIST, CIFAR10, RAF-DB and Products-10K). Our results show that PPA achieves 90% and 98% top-1 attack accuracy to the MNIST and CIFAR10, respectively. More importantly, in real-world commercial scenarios of shopping (i.e., Products-10K) and social network (i.e., RAF-DB), PPA gains a top-1 attack accuracy of 78% in the former case to infer the most ordered items (i.e., as a commercial competitor), and 88% in the latter case to infer a victim user’s most often facial expressions, e.g., disgusted. The top-3 attack accuracy and top-2 accuracy is up to 88% and 100% for the Products-10K and RAF-DB, re

关键词：

来源：评论

学校读者我要写书评

暂无评论

A New Signal Packing Algorithm for CAN-FD with Security Consideration 2nd

A New Signal Packing Algorithm for CAN-FD with Security Cons...

引用

2nd International Conference on Ubiquitous Security, UbiSec 2022

作者： Zheng, Bo Xie, Yong Department of Computer and Information Engineering Xiamen University of Technology Xiamen361024 China School of Computer Science Nanjing University of Posts and Telecommunications Xianlin210023 China

ISBN: (纸本)9789819902712

The Controller Area Network with flexible data-rate (CAN-FD) is thought to be a good replacement for the CAN. The CAN-FD has a faster transmission rate and more data capacity than the CAN. Network security is critical for car safety, but CAN-FD has inherent network security flaws, making vehicles equipped with the protocol extremely vulnerable to malicious attacks. As a result, in order to protect against those attacks, CAN-FD requires a robust and efficient security model. In addition, as a distributed real-time network, the end-to-end timing requirement of CAN-FD should be satisfied. Otherwise, the vehicle cannot run consistently and safely. Therefore, we proposed a network security model suitable for CAN-FD. Based on the model, we further proposed an end-to-end delay optimization algorithm. Experimental results show that our proposed algorithm can effectively reduce end-to-end delay compared with the baseline algorithm. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

FastDrag: Manipulate Anything in One Step 38

FastDrag: Manipulate Anything in One Step

引用

38th Conference on Neural information Processing systems, NeurIPS 2024

作者： Zhao, Xuanjia Guan, Jian Fan, Congyi Xu, Dongli Lin, Youtian Pan, Haiwei Feng, Pengming College of Computer Science and Technology Harbin Engineering University China School of Intelligence Science and Technology Nanjing University China State Key Laboratory of Space-Ground Integrated Information Technology China

Drag-based image editing using generative models provides precise control over image contents, enabling users to manipulate anything in an image with a few clicks. However, prevailing methods typically adopt n-step iterations for latent semantic optimization to achieve drag-based image editing, which is time-consuming and limits practical applications. In this paper, we introduce a novel one-step drag-based image editing method, i.e., FastDrag, to accelerate the editing process. Central to our approach is a latent warpage function (LWF), which simulates the behavior of a stretched material to adjust the location of individual pixels within the latent space. This innovation achieves one-step latent semantic optimization and hence significantly promotes editing speeds. Meanwhile, null regions emerging after applying LWF are addressed by our proposed bilateral nearest neighbor interpolation (BNNI) strategy. This strategy interpolates these regions using similar features from neighboring areas, thus enhancing semantic integrity. Additionally, a consistency-preserving strategy is introduced to maintain the consistency between the edited and original images by adopting semantic information from the original image, saved as key and value pairs in self-attention module during diffusion inversion, to guide the diffusion sampling. Our FastDrag is validated on the DragBench dataset, demonstrating substantial improvements in processing time over existing methods, while achieving enhanced editing performance. Project page: https://***/. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Solving Injection Molding Production Cost Problem Based on Combined Group Role Assignment with Costs 24th

Solving Injection Molding Production Cost Problem Based on ...

引用

24th International Conference on Web information systems engineering, WISE 2023

作者： Teng, Shaohua Chen, Yanhang Teng, Luyao Zheng, Zefeng Zhang, Wei School of Computer Science and Technology Guangdong University of Technology Guangzhou510006 China School of Information Engineering Guangzhou Panyu Polytechic Guangzhou511483 China

ISBN: (纸本)9789819972531

Currently, scheduling plastic production is a big challenge. That is due to the emergence of complex features of small batches and more varieties. At present, two issues arise when it comes to production scheduling. The initial issue is that dissimilarities between previous and subsequent orders may result in extra expenses for order switching. For instance, a significant variation in the material or color of the product could increase scheduling time and production costs. The second issue is attaining greater profits within a limited time and resources. Unscientific scheduling techniques could decrease the production efficiency of plastic products and result in higher expenditures for companies. We suggest Combined Group Role Assignment with Costs (CGRAC) to address the mentioned issues. This technique is based on the theory of Role Based Collaboration (RBC). To solve the problem of high order switching costs, combine multiple roles and create a set of combined roles. Calculate the switching costs within each combination to minimize differences when scheduling orders. Calculate the total cost matrix and assignment matrix of the combined roles to minimize the overall cost and solve the problem of unscientific scheduling. Ultimately, a production schedule that fulfills all constraints is achieved. Evidence of the cost-reducing efficiency of CGRAC was demonstrated through experiments. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Injection molding

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：