检索结果-内蒙古大学图书馆

Fully Convolutional Change Detection Framework with Generative Adversarial network for Unsupervised, Weakly Supervised and Regional Supervised Change Detection

arXiv

引用

arXiv 2022年

作者： Wu, Chen Du, Bo Zhang, Liangpei The State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing Wuhan University Wuhan430072 China National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence School of Computer Science Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University Wuhan China

Deep learning for change detection is one of the current hot topics in the field of remote sensing. However, most end-to-end networks are proposed for supervised change detection, and unsupervised change detection models depend on traditional pre-detection methods. Therefore, we proposed a fully convolutional change detection framework with generative adversarial network, to conclude unsupervised, weakly supervised, regional supervised, and fully supervised change detection tasks into one framework. A basic Unet segmentor is used to obtain change detection map, an image-to-image generator is implemented to model the spectral and spatial variation between multi-temporal images, and a discriminator for changed and unchanged is proposed for modeling the semantic changes in weakly and regional supervised change detection task. The iterative optimization of segmentor and generator can build an end-to-end network for unsupervised change detection, the adversarial process between segmentor and discriminator can provide the solutions for weakly and regional supervised change detection, the segmentor itself can be trained for fully supervised task. The experiments indicate the effectiveness of the propsed framework in unsupervised, weakly supervised and regional supervised change detection. This paper provides theorical definitions for unsupervised, weakly supervised and regional supervised change detection tasks, and shows great potentials in exploring end-to-end network for remote sensing change detection. © 2022, CC BY-NC-ND.

关键词： Remote sensing

来源：评论

学校读者我要写书评

暂无评论

An improved machine learning model for data analysis in Big-data environment

An improved machine learning model for data analysis in Big-...

引用

International Conference on Computing and networking Technology (ICCNT)

作者： Sheetal Temara Sagar Varma Samanthapudi Piyush Rohella Ketan Gupta T. Kiruthiga Dept of Computer & Information Sciences University of the Cumberlands Williamsburg KY USA Applied Data Science The Polis Center at Indiana University Purdue University Indianapolis Indianapolis Indiana USA Payments &Commerce GoDaddy Edmonds Washington USA Dept. of Information Technology University of The Cumberlands Williamsburg KY USA Department of ECE Vetri Vinayaha College of Engineering and Technology Trichy Tamil Nadu INDIA

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

This technical abstract offers an outline of the ability of artificial Intelligence (AI) and device studying (ML) answers for managing leverage threats in banking. Leverage is a key element in banking danger management, as it could expose the organization to disproportionate liabilities if left unchecked. AI and ML may be used to automate the tracking system of leverage hazards, allowing extra correct and welltimed identification and management of exposures. The abstract examines how AI/ML-driven solutions can leverage to be had facts to detect subtle modifications in leverage through the years, combining techniques from supervised and unsupervised ML to generate actionable insights. It then opinions viable implementation fashions and capacity challenges and gives first-rate practices for a hit implementation. The summary concludes that AI/ML-driven hazard management structures offer a promising new approach to leverage threat management inside the banking sector. In addition, research is warranted on this location.

关键词： Analytical models Data analysis Banking Organizations Machine learning Hazards Data models Pattern recognition Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Op2Vec: An Opcode Embedding Technique and Dataset Design for End-to-End Detection of Android Malware

arXiv

引用

arXiv 2021年

作者： Khan, Kaleem Nawaz Ullah, Najeeb Ali, Sikandar Khan, Muhammad Salman Nauman, Mohammad Ghani, Anwar Department of Computer Science University of Engineering and Technology Mardan Pakistan Department of Computer Science and Technology University of Swat Pakistan AI in Healthcare Intelligent Information Processing Lab National Center of Artificial Intelligence UET Peshawar Pakistan University of Engineering and Technology Peshawar Pakistan Department of Computer Science National University of Computer and Emerging Sciences Peshawar Pakistan Department of Computer Science and Software Engineering International Islamic University Islamabad Pakistan

Android is one of the leading operating systems for smart phones in terms of market share and usage. Unfortunately, it is also an appealing target for attackers to compromise its security through malicious applications. To tackle this issue, domain experts and researchers are trying different techniques to stop such attacks. All the attempts of securing Android platform are somewhat successful. However, existing detection techniques have severe shortcomings, including the cumbersome process of feature engineering. Designing representative features require expert domain knowledge. There is a need for minimizing human experts' intervention by circumventing handcrafted feature engineering. Deep learning could be exploited by extracting deep features automatically. Previous work has shown that operational codes (opcodes) of executables provide key information to be used with deep learning models for detection process of malicious applications. The only challenge is to feed opcodes information to deep learning models. Existing techniques use one-hot encoding to tackle the challenge. However, the one-hot encoding scheme has severe limitations. In this paper, we introduce;(1) a novel technique for opcodes embedding, which we name Op2Vec, (2) based on the learned Op2Vec we have developed a dataset for end-to-end detection of android malware. Introducing the end-to-end Android malware detection technique avoids expert-intensive handcrafted features extraction, and ensures automation. Some of the recent deep learning-based techniques showed significantly improved results when tested with the proposed approach and achieved an average detection accuracy of 97.47%, precision of 0.976 and F1 score of 0.979. Copyright © 2021, The Authors. All rights reserved.

关键词： Android (operating system)

来源：评论

学校读者我要写书评

暂无评论

SynFacePAD 2023: Competition on Face Presentation Attack Detection Based on Privacy-aware Synthetic Training Data

arXiv

引用

arXiv 2023年

作者： Fang, Meiling Huber, Marco Fierrez, Julian Ramachandra, Raghavendra Damer, Naser Alkhaddour, Alhasan Kasantcev, Maksim Pryadchenko, Vasiliy Yang, Ziyuan Huangfu, Huijie Chen, Yingyu Zhang, Yi Pan, Yuchen Jiang, Junjun Liu, Xianming Sun, Xianyun Wang, Caiyong Liu, Xingyu Chang, Zhaohua Zhao, Guangzhe Tapia, Juan Gonzalez-Soler, Lazaro Aravena, Carlos Schulz, Daniel Fraunhofer Institute for Computer Graphics Research IGD Darmstadt Germany Department of Computer Science TU Darmstadt Darmstadt Germany Biometrics and Data Pattern Analytics Lab Universidad Autonoma de Madrid Spain Norway ID R&D Inc. New York United States School of Cyber Science and Engineering Sichuan University Chengdu China School of Computer Science and Technology Harbin Institute of Technology Harbin China School of Electrical and Information Engineering Beijing University of Civil Engineering and Architecture China Biometrics and Security Research Group Hochschule Darmstadt Darmstadt Germany I+D Vision Center Santiago Chile

This paper presents a summary of the Competition on Face Presentation Attack Detection Based on Privacy-aware Synthetic Training Data (SynFacePAD 2023) held at the 2023 International Joint Conference on Biometrics (IJCB 2023). The competition attracted a total of 8 participating teams with valid submissions from academia and industry. The competition aimed to motivate and attract solutions that target detecting face presentation attacks while considering synthetic-based training data motivated by privacy, legal and ethical concerns associated with personal data. To achieve that, the training data used by the participants was limited to synthetic data provided by the organizers. The submitted solutions presented innovations and novel approaches that led to outperforming the considered baseline in the investigated benchmarks. © 2023, CC BY-NC-SA.

关键词： Competition

来源：评论

学校读者我要写书评

暂无评论

Ultra-Low-Loss Silicon Nitride Photonics Based on Deposited Films Compatible with Foundries

arXiv

引用

arXiv 2023年

作者： Ji, Xingchen Okawachi, Yoshitomo Gil-Molina, Andres Corato-Zanarella, Mateus Roberts, Samantha Gaeta, Alexander L. Lipson, Michal Department of Electrical Engineering Columbia University New YorkNY10027 United States Department of Applied Physics and Applied Mathematics Columbia University New YorkNY10027 United States Currently at John Hopcroft Center for Computer Science School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai200240 China

The fabrication processes of silicon nitride (Si3N4) photonic devices used in foundries require low temperature deposition, which typically leads to high propagation losses. Here, we show that propagation loss as low as 0.42 dB/cm can be achieved using foundry compatible processes by solely reducing waveguide surface roughness. By post-processing the fabricated devices using rapid thermal anneal (RTA) and furnace anneal, we achieve propagation losses down to 0.28 dB/cm and 0.06 dB/cm, respectively. These low losses are comparable to the conventional devices using high temperature, high-stress LPCVD films. We also tune the dispersion of the devices, and proved that these devices can be used for linear and nonlinear applications. Low threshold parametric oscillation, broadband frequency combs and narrow-linewidth laser are demonstrated. Our work demonstrates the feasibility of scalable photonic systems based on foundries. Copyright © 2023, The Authors. All rights reserved.

关键词： Silicon nitride

来源：评论

学校读者我要写书评

暂无评论

Intelligent decoding method for Ground-penetrating radar based on improved YOLOv5

Intelligent decoding method for Ground-penetrating radar bas...

引用

computer, Big Data and Artificial Intelligence (ICCBD+AI), International Conference on

作者： ZeYu Chen YongKang Wang HongLiang Liu Chuan Wang XinBo Jiang Ning Zhang Zhen Huang Lei Jiang Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) JiNan China Technological Innovation Department Shandong Hi-Speed Group Co Ltd JiNan China School of Qilu Transportation Shandong University JiNan China No.1 Engineering Development Co. Ltd. of China Railway 14Th Bureau Group RiZhao China

ISBN: (数字)9798331533991

ISBN: (纸本)9798331534004

Ground-penetrating radar (GPR) is a non-invasive detection technique that effectively gathers information about subsurface materials. In tunneling projects, GPR can provide a fast and accurate forecast of the geological conditions in front of tunnel boring, which provides an important reference basis for tunnel construction. Currently, the interpretation of GPR images relies heavily on manual expertise, resulting in low efficiency and minimal automation. This creates an urgent need for effective and accurate identification of poor geological conditions depicted in radar images. In this study, we present the GPR-YOLOv5 model, which is designed to detect unfavorable geologic features ahead of the tunnel face from GPR images. We enhance this model with the CA attention mechanism, GSConv module, ghostC3 module, and the VariFocal loss function to improve decoding accuracy while minimizing computational load. Additionally, we integrate this algorithm with established modern object detection techniques, and our experimental results demonstrate its effectiveness.

关键词： YOLO Accuracy Ground penetrating radar Attention mechanisms Geology Computational modeling Radar imaging Tunneling Decoding Load modeling

来源：评论

学校读者我要写书评

暂无评论

Dynamic graph transformer network via dual-view connectivity for autism spectrum disorder identification

引用

computers in Biology and Medicine 2024年 174卷 108415-108415页

作者： Guan, Zihao Yu, Jiaming Shi, Zhenshan Liu, Xiumei Yu, Renping Lai, Taotao Yang, Changcai Dong, Heng Chen, Riqing Wei, Lifang College of Computer and Information Science Fujian Agriculture and Forestry University Fuzhou350002 China Digital Fujian Research Institute of Big Data for Agriculture and Forestry Fujian Agriculture and Forestry University Fuzhou350002 China Department of Radiology The First Affiliated Hospital of Fujian Medical University Fuzhou350002 China Developmental and Behavior Pediatrics Department Fujian Children's Hospital - Fujian Branch of Shanghai Children's Medical Center Fuzhou350002 China College of Clinical Medicine for Obstetrics Gynecology and Pediatrics Fujian Medical University Fuzhou350012 China School of Electrical and Information Engineering Zhengzhou University Zhengzhou450001 China College of Computer and Control Engineering Minjiang University Fuzhou350108 China

Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder that requires objective and accurate identification methods for effective early intervention. Previous population-based methods via functional connectivity (FC) analysis ignore the differences between positive and negative FCs, which provide the potential information complementarity. And they also require additional information to construct a pre-defined graph. Meanwhile, two challenging demand attentions are the imbalance of performance caused by the class distribution and the inherent heterogeneity of multi-site data. In this paper, we propose a novel dynamic graph Transformer network based on dual-view connectivity for ASD Identification. It is based on the Autoencoders, which regard the input feature as individual feature and without any inductive bias. First, a dual-view feature extractor is designed to extract individual and complementary information from positive and negative connectivity. Then Graph Transformer network is innovated with a hot plugging K-Nearest Neighbor (KNN) algorithm module which constructs a dynamic population graph without any additional information. Additionally, we introduce the PolyLoss function and the Vrex method to address the class imbalance and improve the model's generalizability. The evaluation experiment on 1102 subjects from the ABIDE I dataset demonstrates our method can achieve superior performance over several state-of-the-art methods and satisfying generalizability for ASD identification. © 2024 Elsevier Ltd

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Anomaly Detection Mechanism for Solar Generation using Semi-supervision Learning Model 2

Anomaly Detection Mechanism for Solar Generation using Semi-...

引用

Indo - Taiwan 2nd International Conference on Computing, Analytics and networks, Indo-Taiwan ICAN 2020

作者： Tsai, Chia-Wei Yang, Chun-Wei Hsu, Feng-Ling Tang, Hsih-Min Fan, Nien-Chin Lin, Cheng-Yang National Taitung University Department of Computer Science and Information Engineering Taitung Taiwan Center for General Education China Medical University Taichung Taiwan

ISBN: (纸本)9781728149998

Solar is an important energy resource at present, and thus how to generate power efficiently by using solar is the crucial research topics in next generation power system. Among these research topics, managing and maintaining the solar panels for avoiding the situation which cannot generate power due to damage is also an interesting issue. Because the cost of developing the solar plant is expensive and needing the extra-cost to maintain solar, how to maintain the solar panels effectively is another important issue. In this study, an anomaly detection mechanism with using the semi-supervision learning model is proposed to pre-identify whether the solar panel will occur the abnormal events or not. In the anomaly detection mechanism, this study uses the clustering algorithm to filter the normal events, and then adopts the neuron network model, Autoencoder, to develop the classificator. This study takes the data collected from a 500kW solar power plant to train models and verify the feasibility of the proposed anomaly detection mechanism. © 2020 IEEE.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Lightweight Vertebrae Segmentation network based on Convolutional Multilayer Perceptron and Structural Re-parameterization 23

Lightweight Vertebrae Segmentation Network based on Convolut...

引用

Proceedings of the 2023 4th International Symposium on Artificial Intelligence for Medicine science

作者： Songsen Cheng Jie Dong Meiyun Wang Yusong Lin School of Computer and Artificial Intelligence Zhengzhou University China School of Information Engineering North China University of Water Resources and Electric Power China Department of Radiology People's Hospital of Zhengzhou University China School of Cyber Science and Engineering Zhengzhou University China Collaborative Innovation Center for Internet Healthcare Zhengzhou University China and Hanwei IoT Institute Zhengzhou University China

ISBN: (纸本)9798400708138

Localization, segmentation, and identification of vertebrae in CT images are crucial for many clinical applications, such as spinal surgery planning and disease diagnosis. Although deep learning approaches have made significant progress in this field in recent years, most multi-stage vertebrae segmentation methods often face challenges of high computational complexity and slow inference speed, which is a big problem in clinical environments with limited computational resources. To address this issue, we propose a lightweight vertebrae segmentation network called 3D Re-parameterization UNeXt (3DRepUNeXt), based on convolutional multilayer perceptron (MLP) and structural re-parameterization. The network consists of a re-parameterization convolution stage and a tokenized MLP stage. The structural re-parameterization can remove residual structures during inference time to reduce network parameters, while the tokenized MLP performs better global modeling and maintains a smaller parameter count. The design of each module reduces the number of parameters to improve computational efficiency while maintaining segmentation performance. We applied this network within an anatomical consistency cycle method and evaluated it on the Verse’20 dataset. The results show that our method has achieved significant advantages in segmentation speed. Compared to the original method, it has reduced the median inference time by 81.29% and 80.73% on the Verse’20 public and hidden test sets, respectively. Additionally, our method has also achieved better segmentation performance.

关键词： CT Lightweight network MLP Re-parameterization Vertebrae Segmentation

来源：评论

学校读者我要写书评

暂无评论

Active RISs: Signal Modeling, Asymptotic Analysis, and Beamforming Design

Active RISs: Signal Modeling, Asymptotic Analysis, and Beamf...

引用

GLOBECOM 2022 - 2022 IEEE Global Communications Conference

作者： Zijian Zhang Linglong Dai Xibi Chen Changhao Liu Fan Yang Robert Schober H. Vincent Poor Department of Electronic Engineering Beijing National Research Center for Information Science and Technology (BNRist) Tsinghua University China Institute for Digital Communications Friedrich-Alexander University Erlangen-Nürnberg Germany Department of Electrical and Computer Engineering Princeton University USA

ISBN: (纸本)9781665435413

Reconfigurable intelligent surfaces (RISs) have emerged as a candidate technology for future 6G networks. However, due to the “multiplicative fading” effect, the existing passive RISs only achieve a negligible capacity gain in environments with strong direct links. In this paper, the concept of active RISs is studied to overcome this fundamental limitation. Unlike the existing passive RISs that reflect signals without amplification, active RISs can amplify the reflected signals via amplifiers integrated into their elements. To characterize the signal amplification and incorporate the noise introduced by the active components, we verify the signal model of active RISs through the experimental measurements on a fabricated active RIS element. Based on the verified signal model, we formulate the sum-rate maximization problem for an active RIS aided multi-user multiple-input single-output (MU-MISO) system and a joint transmit precoding and reflect beamforming algorithm is proposed to solve this problem. Simulation results show that, in a typical wireless system, the existing passive RISs can realize only a negligible sum-rate gain of 3%, while the active RISs can achieve a significant sum-rate gain of 62%, thus over coming the “multiplicative fading” effect. Finally, we develop a 64-element active RIS aided wireless communication prototype, and the significant gain of active RISs is validated by field test.

关键词： Fading channels Wireless communication Array signal processing Simulation Precoding Prototypes Reconfigurable intelligent surfaces

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：