检索结果-内蒙古大学图书馆

ATFS: A deep learning framework for angle transformation and face swapping of face de-identification

Multimedia Tools and Applications 2024年第12期83卷 36797-36822页

作者： Tsai, Chwei-Shyong Wu, Hsien-Chu Chen, Wei-Ting Ying, Josh Jia-Ching Department of Management Information Systems National Chung Hsing University Taichung402 Taiwan Language Center National Chin-Yi University of Technology Taichung411 Taiwan Department of Computer Science and Information Engineering National Taichung University of Science and Technology Taichung404 Taiwan

This paper proposes an effective framework for improving angle transformation and face replacement. This ATFS framework aims to solve the image distortion caused by angled face swapping in face de-identification. In the ATFS framework, TransNet and SWGAN were proposed based on generative adversarial networks. When TransNet uses neural networks to reconstruct images, it combines the predicted facial points. As a result, Transnet can locate the target’s facial features and generate multi-angle transformed images to achieve angle transformation. The SWGAN applies a complicated neural network that combines residual operations and self-attention modules to extract the input image features and replace the face region of the input image with the target image to achieve face de-identification. Both TransNet and SWGAN adopt discriminators and various loss functions to train the neural network and accurately accelerate the training process. The experimental results show that the proposed method can maintain high-quality images and avoid image distortion during face swapping for image angle transformation compared to previously proposed methods. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2023.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

A Method Based on Entity Interaction Graph for Detecting Social Events Using GDELT 11

A Method Based on Entity Interaction Graph for Detecting Soc...

引用

11th International Conference on Intelligent Computing and Wireless Optical Communications, ICWOC 2023

作者： Zhao, Dongxu Zhang, Xin Wang, Yinsen Qiao, Fengcai Pan, Yan National University of Defense Technology College of Information Systems and Management Science and Technology on Information Systems Engineering Laboratory Changsha China National University of Defense Technology College of Advanced Interdisciplinary Studies The First Interdisciplinary Center Changsha China

ISBN: (纸本)9798350321791

Social events are group activities gathered at a certain time and location. Timely detecting social events is of great significance to grasp the dynamics of social development. Most of the existing researches on social event detection are oriented to unstructured data, and these methods are difficult to applied for structured data. Considering that structured data focuses on the event level and has strong authority, it is necessary to put efforts into related research on structured data. However, the existing researches on structured data rely heavily on rule-based feature construction, which cannot fully mine the hidden layer features representing events. Fortunately, deep learning methods can solve this problem. In this paper, we design a social event detection method based on entity interaction graph mining to achieve this task. Firstly, we build a feature mining module based on multi-relational graph convolutional network, and update the feature information by the powerful feature mining ability of graph convolutional network. Then, a feature selection module is designed based on the graph pooling mechanism to select important nodes and edges. Finally, the feature concatenation module is constructed, the feature mining layer and feature selection layer are reasonably laid out, the embeddings of nodes and edges of corresponding layers are obtained by max pool and average pool, and the embeddings of corresponding layers are concatenated before classification. Finally, a classifier is constructed to obtain the final output. In order to demonstrate effectiveness and performance of our model, we construct datasets and design evaluation experiments on this basis. Experimental results show that our model outperforms the baselines with better generalization. © 2023 IEEE.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

What needs making information systems integration successful in the case of mergers and acquisition

What needs making information systems integration successful...

引用

2022 International Conference on ENTERprise information systems, centerIS 2022 - International Conference on Project MANagement, ProjMAN 2022 and International Conference on Health and Social Care information systems and Technologies, HCist 2022

作者： Johansson, Björn Waldau, Fredrik Ahlström, Oskar Department of Management and Engineering Division of Information Systems and Digitalisation LinköpingSE-581 83 Sweden Gapgemini Stockholm Sweden SEB Stockholm Sweden

information system integration during merger and acquisition (M&A) is a critical process when organizations are joining. The integration process consisting of several crucial activities for making organizations being able to work together. Organizations need to evaluate internal and external factors in order to make the process work. In this paper we evaluated critical success factors, challenges and information systems (IS integration methods from interviews with employees in a case study to identify the most critical activities for a successful IS integration. The investigated process stretches from the introduction of the M&A to the actual integration of two organizations IT-stacks. The identified crucial activities found were top management support, organizational culture, importance of competence, internal communication, maintaining information system security, communication with end-users and managing legacy system. Evaluating these topics and creating a short and a long-Term plan on how to integrate and work with these are essential to succeed with the IS integration in any M&A. © 2023 Elsevier B.V.. All rights reserved.

关键词： Legacy systems

来源：评论

学校读者我要写书评

暂无评论

Non-invasive glucose sensing via the fingernail bed using THz radiation

引用

Current Directions in Biomedical engineering 2023年第1期9卷 507-510页

作者： Jalali, Mandana Prokscha, Andreas Kaiser, Thomas Yan, Yijun Taro Svejda, Jan Erni, Daniel Kubiczek, Tobias Balzer, Jan Preu, Sascha General and Theoretical Electrical Engineering (ATE) Faculty of Engineering University of Duisburg-Essen Essen Duisburg Germany CENIDE-Center for Nanointegration Duisburg-Essen Duisburg D-47048 Germany Institute of Digital Signal Processing Faculty of Engineering University of Duisburg-Essen Duisburg D-47048 Germany Chair of Communication Systems Faculty of Engineering University of Duisburg-Essen Duisburg D-47048 Germany Terahertz Devices and Systems Institute of Microwave Engineering and Photonics Department of Electrical Engineering and Information Technology Technical University of Darmstadt Darmstadt D-64283 Germany

The possibility of establishing a novel technique for reliably accessing glycemic information in a non-invasive, easy to implement method at THz frequencies via the fingernail bed is investigated. The nail bed's major content is blood at its various glucose levels and is also partially protected from environmental conditions by the nail plate, making it a desirable platform for non-invasive glucose sensing. The study is based on a 2D computational electromagnetics (EM) model of the layered fingernail in COMSOL Multiphysics, where the required dielectric function (i.e. permittivity and conductivity) of the fingernail plate is measured using THz-Time-Domain-Spectroscopy (THz-TDS), and the glucose-dependend dielectric functions of the fingernail bed are taken from available experimental data in the literature. From this data a material model using a multipole Cole-Cole model is established for both, the nail plate and the nail bed, where the glucose content in the latter is varied from 3.0-19.0 mmol/l. A numerical analysis of the THz reflectometry at the fingernail in the frequency range of 0.1-2.0 THz revealed that the reflectance spectra are sensitive to the glucose content in the nail bed proving that accurate glucose sensing via the fingernail bed may become feasible around 0.2-0.4 THz. © 2023 the author(s), published by Walter de Gruyter Berlin/Boston.

关键词： Glucose

来源：评论

学校读者我要写书评

暂无评论

Urban Air Mobility Traffic Analysis Tool for Testing Various ATM Methods

Urban Air Mobility Traffic Analysis Tool for Testing Various...

引用

AIAA Science and Technology Forum and Exposition, AIAA SciTech Forum 2025

作者： Kopyt, Antoni Kaczmarek, Kacper Sochacki, Mateusz Stephens, Chad Division of Automation and Aeronautical Systems Faculty of Power and Aeronautical Engineering Warsaw University of Technology Warsaw00-661 Poland Crew Systems and Aviation Operations Branch National Aeronautics and Space Administration Langley Research Center HamptonVA23666 United States

ISBN: (数字)9781624107238

ISBN: (纸本)9781624107238

The increasing complexity and wide use of an Advanced Unmanned systems (UAS) generates new risks and security challenges, that have to be solve in Urban Air Mobility environment. Integrating all various aircraft systems in one environment maintaining high fidelity and safety using the methods and solutions originally designed for manned aircraft, might be insufficient. Existing infrastructure and approach are not designed to handle the expected volume of UAS traffic. In urban environments, where traffic, pedestrians, and existing aircraft are densely concentrated, the risks of collisions and accidents increase, potentially causing serious damage and harm. As UAS applications expand, from deliveries to surveillance, there is a pressing need for effective risk management strategies. Identifying and understanding risks is essential to developing appropriate mitigation measures for safe UAS operations in urban areas. This paper explores the challenges of UAS integration into urban environments having ability to perform set of different simulations with collision analysis. Presented software called Urban Air Mobility Traffic Analysis Tool, allows to perform simulations of urban air traffic based on various factors such as population density, airspace restrictions, and various aircraft performance including their different level of autonomy. In the following paper case study is presented to show the importance of creating proper ATM in UAM environment especially to find a safe airspace saturation. The delivered tool shows the possibility to calculate the capacity of the area having a strong safety factor. © 2025, American Institute of Aeronautics and Astronautics Inc, AIAA. All rights reserved.

关键词： Aircraft accidents

来源：评论

学校读者我要写书评

暂无评论

Control of Linear Servo Carts with Integral-Based Disturbance Rejection

引用

Computers, Materials & Continua 2022年第10期73卷 453-463页

作者： Ibrahim M.Mehedi Abdulah Jeza Aljohani Ubaid M.Al-Saggaf Ahmed I.Iskanderani Thangam Palaniswamy Mohamed Mahmoud Mohammed J.Abdulaal Muhammad Bilal Waleed Alasmary Department of Electrical and Computer Engineering(ECE) King Abdulaziz University5521589Saudi Arabia Center of Excellence in Intelligent Engineering Systems(CEIES) King Abdulaziz University6521589Saudi Arabia Electrical and Computer Engineering TN38505United States Computer and Information Systems Umm Al-Qura UniversityMakkahSaudi Arabia

This paper describes a system designed for linear servo cart systems that employs an integral-based Linear Active Disturbance Rejection Control(ILADRC)scheme to detect and respond to *** upgrade in this control technique provides extensive immunity to uncertainties,attenuation,internal disturbances,and external sources of *** fundamental technology base of LADRC is Extended State Observer(ESO).LADRC,when combined with Integral action,becomes a hybrid control technique,namely *** tracking is based on Bode’s Ideal Transfer Function(BITF)in this proposed ILADRC *** proves to be a very robust and appropriate pole placement *** proposed LSC system has experimented with the hybrid ILADRC technique plotted the *** the results,it is evident that the proposed ILADRC scheme enhances the robustness of the LSC system with remarkable disturbance ***,the results of a linear quadratic regulator(LQR)and ILADRC schemes are comparatively *** analysis deduced the improved performance of ILADRC over the LQR control scheme.

关键词： Pole placement ADRC Active disturbance rejection robust control linear servo cart system

来源：评论

学校读者我要写书评

暂无评论

Longitudinal Vehicle Motion Prediction in Traffic Junctions Using a Data-Driven Multi-Object Intelligent Driver Model 27

Longitudinal Vehicle Motion Prediction in Traffic Junctions ...

引用

27th IEEE International Conference on Intelligent Transportation systems, ITSC 2024

作者： Buyer, Johannes Wetzel, Konstantin Zollner, Raoul Zollner, J. Marius Heilbronn University of Applied Sciences Faculty Engineering Heilbronn74081 Germany Fzi Research Center for Information Technology Department of Technical Cognitive Assistance Systems Karlsruhe76131 Germany

ISBN: (纸本)9798331505929

The paper presents an approach for longitudinal interaction-aware vehicle motion prediction using an Intelligent Driver Model (IDM) with a data-driven extension, which is able to consider several traffic participants. The basic prediction concept for that approach was originally designed for multi-lane traffic scenarios in the authors' previous work [1], [2]. The approach is based on model knowledge, probabilistic estimation as well as machine learning components. The innovation of the paper at hand is the transfer of the concept for its usage in traffic junctions. Thereby, a decision tree is developed that processes different interaction features in order to select the relevant traffic participants. To estimate the model parameter values, a Sequential Importance Resampling (SIR) particle filter is used. Time-varying parameters which weight the selected objects considered in the multi-object IDM are adapted over the prediction horizon using a trained support vector machine (SVM) regression model. For validation, roundabout motion trajectories of the INTERACTION dataset [3] are used. Since the proposed prediction approach is able to consider vehicles' turn signal status, an augmentation of the dataset with turn signal attributes is realized. The accuracy of the prediction approach is compared to baseline methods by calculating the mean absolute error (MAE) of predicted vehicle speeds. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Robotic Near-Field Measurements Using Reduced Angular Sparse Grids 46

Robotic Near-Field Measurements Using Reduced Angular Sparse...

引用

46th Annual Meeting and Symposium of the Antenna Measurement Techniques Association, AMTA 2024

作者： Varela, Fernando Rodriguez Arboleya, Ana Martinez-De-Rioja, Eduardo Romero, Celia Fonta Castaner, Manuel Sierra Group of Microwave Engineering and Radiocommunication Systems Universidad Rey Juan Carlos Madrid Spain Universidad Politécnica de Madrid Information Processing and Telecommunications Center Madrid Spain

ISBN: (纸本)9781736235164

This work presents a fast Planar Near-Field (PNF) technique for characterizing electrically large antennas from sparse acquisitions over localized angular domains employing a robotic arm in non-anechoic environments. The proposed technique has been designed for the effective characterization of complex antenna systems with multiple beams, such as Reflective Intelligent Surfaces (RIS) or Massive MIMO panels for millimeter wave (mmW) 5G communications although it is particularly suitable for any electrically large antenna with narrow and tilted beams. The near-field to far-field transformation is restricted to a reduced angular domain, and the non-redundant acquisition grid is computed by means of Singular Value Decomposition (SVD) techniques so that the number of unknowns of the inverse problem is highly reduced, significantly decreasing acquisition time. The proposed technique has been validated by means of a numerical example in the X-band and a measurement example in the Ka-bands yielding excellent results. © 2024 Antenna Measurement Techniques Association (AMTA).

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

Personalized music recommendation based on knowledge graphs and social circles 43

Personalized music recommendation based on knowledge graphs ...

引用

43rd Chinese Control Conference, CCC 2024

作者： Li, Lin Liu, Jianchang Zhang, Wei Tan, Shubin Liu, Yuanchao The College of Information Science and Engineering Northeastern University Shenyang110819 China Northeastern University The National Frontiers Science Center for Industrial Intelligence and Systems Optimization Shenyang110819 China

ISBN: (纸本)9789887581581

With the rapid development of digital music ser vices, personalized music recommendation systems have become crucial for enhancing user experience. Addressing the limitations of traditional recommendation algorithms in understanding user needs and recommendation accuracy, this study proposes a knowledge-based social circle personalized music recommendation model (KSPMR). This model aims to provide more comprehensive and accurate music recommendations by deeply analyzing individual user preferences. Initially, we developed a data preprocessing method to optimize embedding computation and graph construction efficiency. Subsequently, we explored the impact of social circles on user music preferences, integrating social network factors into the recommendation logic. Finally through a series of comparative experiments, the superiority of our model in improving recommendation effectiveness was demonstrated. Experimental results show that, compared to baseline models, our model significantly improves across various performance metrics, especially in accuracy and effectiveness of recommendations after incorporating information from the user and artist social circles. © 2024 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Physical insights into trapping effects on vertical GaN-on-Si trench MOSFETs from TCAD

引用

Journal of Semiconductors 2024年第3期45卷 45-52页

作者： NicolòZagni Manuel Fregolent Andrea Del Fiol Davide Favero Francesco Bergamin Giovanni Verzellesi Carlo De Santi Gaudenzio Meneghesso Enrico Zanoni Christian Huber Matteo Meneghini Paolo Pavan Department of Engineering“Enzo Ferrari” University of Modena and Reggio EmiliaModena 41125Italy Department of Information Engineering University of PadovaPadova 35131Italy Department of Sciences and Methods for Engineering(DISMI) University of Modena and Reggio EmiliaReggio Emilia 42122Italy EN&TECH Center University of Modena and Reggio EmiliaReggio Emilia 42122Italy Advanced Technologies and Micro Systems Department Robert Bosch GmbHRenningen 71272Germany

Vertical GaN power MOSFET is a novel technology that offers great potential for power switching *** still in an early development phase,vertical GaN devices are yet to be fully optimized and require careful studies to foster their *** this work,we report on the physical insights into device performance improvements obtained during the development of vertical GaN-on-Si trench MOSFETs(TMOS’s)provided by TCAD simulations,enhancing the dependability of the adopted process optimization ***,two different TMOS devices are compared in terms of transfer-curve hysteresis(H)and subthreshold slope(SS),showing a≈75%H reduction along with a≈30%SS *** allow attributing the achieved improvements to a decrease in the border and interface traps,respectively.A sensitivity analysis is also carried out,allowing to quantify the additional trap density reduction required to minimize both figures of merit.

关键词： vertical GaN trench MOSFET SiO_(2) interface traps border traps hysteresis BTI

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：