检索结果-内蒙古大学图书馆

Preliminary Design for Reference tracking feedback for Medical Cyber-Physical Pharmacokinetic Systems

学校读者我要写书评

暂无评论

Preliminary Design for Reference tracking feedback for Medic...

IEEE International Conference on Automatica (ICA-ACCA)

作者： Pedro M. Oliveira Daniel Bustos Rodolfo Lobo Márcio J. Lacerda Jonathan M. Palma Graduate Program in Electrical Engineering Federal University of Minas Gerais Belo Horizonte Brazil Dept. of Translational Medicine Universidad Católica del Maule Talca Chile Ingenieria en Telecomunicaciones e Informática Universidad Diego Portales Santiago Chile Centre for Communications Technology School of Computing and Digital Media London Metropolitan University London UK Faculty of Engineering Universidad de Talca Curicó Chile

ISBN: (数字)9798350378115

ISBN: (纸本)9798350378122

This paper addresses the reference tracking control problem for Medical Cyber-Physical Systems (MCPS). The control theory is employed to guarantee the suitable concentration of drugs in the body of patients to guarantee a safe treatment. The MCPS is modeled as a switched system, and the modes consider the different scenarios for the problem. A discrete-time model is utilized for the pharmacokinetic process, and the zero input control strategy is employed to design state-feedback controllers with a guaranteed exponential convergence rate. A numerical experiment is presented to illustrate the validity and effectiveness of our method.

关键词： Drugs Switched systems Design methodology Process control Medical services Cyber-physical systems Numerical models Control theory Pharmacokinetics Convergence

Augmented Reality Based Brain Tumor 3D Visualization

学校读者我要写书评

暂无评论

Procedia Computer Science 2017年 113卷 400-407页

作者： Qian Shan Thomas E. Doyle Reza Samavi Mona Al-Rei Department of Computing and Software McMaster University 1280 Main St. W Hamilton ON L8S 4L8 Canada Department of Electrical and Computer Engineering School of Biomedical Engineering McMaster University 1280 Main St. W Hamilton ON L8S 4L8 Canada eHealth Graduate Program McMaster University 1280 Main St. W Hamilton ON L8S 4L8 Canada

In this paper we present an augmented reality system for mobile devices that facilitates 3D brain tumor visualization in real time. The system uses facial features to track the subject in the scene. The system performs camera calibration based on the face size of the subject, instead of the common approach of using a number of chessboard images to calibrate the camera every time the application is installed on a new device. Camera 3D pose estimation is performed by finding its position and orientation based on a set of 3D points and their corresponding 2D projections. According to the estimated camera pose, a reconstructed brain tumor model is displayed at the same location as the subject’s real anatomy. The results of our experiment show the system was successful in performing the brain tumor augmentation in real time with a reprojection accuracy of 97%.

关键词： Augmented reality 3D visualization Tumor visualization Markerless tracking Mobile device

AVTENet: Audio-Visual Transformer-based Ensemble Network Exploiting Multiple Experts for Video Deepfake Detection

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Hashmi, Ammarah Shahzad, Sahibzada Adil Lin, Chia-Wen Tsao, Yu Wang, Hsin-Min The Social Networks and Human-Centered Computing Program Taiwan International Graduate Program Academia Sinica Taipei11529 Taiwan The Institute of Information Systems and Applications National Tsing Hua University Hsinchu30013 Taiwan The Department of Computer Science National Chengchi University Taipei11605 Taiwan The Department of Electrical Engineering The Institute of Communications Engineering National Tsing Hua University Hsinchu300044 Taiwan The Research Center for Information Technology Innovation Academia Sinica Taipei11529 Taiwan The Institute of Information Science Academia Sinica Taipei11529 Taiwan

Forged content shared widely on social media platforms is a major social problem that requires increased regulation and poses new challenges to the research community. The recent proliferation of hyper-realistic deepfake videos has drawn attention to the threat of audio and visual forgeries. Most previous work on detecting AI-generated fake videos only utilizes visual modality or audio modality. While there are some methods in the literature that exploit audio and visual modalities to detect forged videos, they have not been comprehensively evaluated on multi-modal datasets of deepfake videos involving acoustic and visual manipulations. Moreover, these existing methods are mostly based on CNN and suffer from low detection accuracy. Inspired by the recent success of Transformer in various fields, to address the challenges posed by deepfake technology, in this paper, we propose an Audio-Visual Transformer-based Ensemble Network (AVTENet) framework that considers both acoustic manipulation and visual manipulation to achieve effective video forgery detection. Specifically, the proposed model integrates several purely transformer-based variants that capture video, audio, and audio-visual salient cues to reach a consensus in prediction. For evaluation, we use the recently released benchmark multi-modal audio-video FakeAVCeleb dataset. For a detailed analysis, we evaluate AVTENet, its variants, and several existing methods on multiple test sets of the FakeAVCeleb dataset. Experimental results show that our best model outperforms all existing methods and achieves state-of-the-art performance on Testset-I and Testset-II of the FakeAVCeleb dataset. © 2023, CC BY.

关键词： Statistical tests

Application of Deep Artificial Neural Network to Model Characteristic Fluctuation of Multi-Channel Gate-All-Around Silicon Nanosheet and Nanofin MOSFETs Induced by Random Nanosized Metal Grains

学校读者我要写书评

暂无评论

Application of Deep Artificial Neural Network to Model Chara...

IEEE Electron Devices Technology and Manufacturing Conference (EDTM)

作者： Sagarika Dash Yiming Li Wen-Li Sung Parallel and Scientific Computing Laboratory National Yang-Ming Chiao Tung University Hsinchu Taiwan Electrical Engineering and Computer Science International Graduate Program National Yang-Ming Chiao Tung University Hsinchu Taiwan Institute of Communications Engineering National Yang-Ming Chiao Tung University Hsinchu Taiwan Department of Electronics and Electrical Engineering National Yang-Ming Chiao Tung University Hsinchu Taiwan Institute of Biomedical Engineering National Yang-Ming Chiao Tung University Hsinchu Taiwan Center for mm Wave Smart Radar System and Technologies National Yang-Ming Chiao Tung University Hsinchu Taiwan

In this work, we propose a deep artificial neural network (D-ANN) to estimate the work function fluctuation (WKF) on 4-channel stacked gate-all-around (GAA) silicon (Si) nanosheet (NS) and nanofin (NF) MOSFET devices for the first time. The 2-layered simple deep model can well predict the transfer characteristics for both NS/NF FET with a large number of (128) input features, utilizing considerably lesser (1100 samples) data uniformly. The resultant model is evaluated by the $\mathrm{R}^{2}$ score and RMSE to witness its competency and the average error is $< 4\%$ . We do also discuss the circuit simulation possibility by applying the ANN approach.

关键词： Semiconductor device modeling MOSFET Gallium arsenide Artificial neural networks Predictive models Logic gates Silicon

Understanding Audiovisual Deepfake Detection: Techniques, Challenges, Human Factors and Perceptual Insights

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Hashmi, Ammarah Shahzad, Sahibzada Adil Lin, Chia-Wen Tsao, Yu Wang, Hsin-Min The Social Networks and Human-Centered Computing Program Taiwan International Graduate Program Institute of Information Science Academia Sinica Taipei11529 Taiwan The Institute of Information Systems and Applications National Tsing Hua University Hsinchu300044 Taiwan The Department of Computer Science National Chengchi University Taipei11529 Taiwan The Department of Electrical Engineering The Institute of Communications Engineering National Tsing Hua University Hsinchu300044 Taiwan The Research Center for Information Technology Innovation Academia Sinica Taipei11529 Taiwan The Institute of Information Science Academia Sinica Taipei11529 Taiwan

Deep Learning has been successfully applied in diverse fields, and its impact on deepfake detection is no exception. Deepfakes are fake yet realistic synthetic content that can be used deceitfully for political impersonation, phishing, slandering, or spreading misinformation. Despite extensive research on unimodal deepfake detection, identifying complex deepfakes through joint analysis of audio and visual streams remains relatively unexplored. To fill this gap, this survey first provides an overview of audiovisual deepfake generation techniques, applications, and their consequences, and then provides a comprehensive review of state-of-the-art methods that combine audio and visual modalities to enhance detection accuracy, summarizing and critically analyzing their strengths and limitations. Furthermore, we discuss existing open source datasets for a deeper understanding, which can contribute to the research community and provide necessary information to beginners who want to analyze deep learning-based audiovisual methods for video forensics. By bridging the gap between unimodal and multimodal approaches, this paper aims to improve the effectiveness of deepfake detection strategies and guide future research in cybersecurity and media integrity. © 2024, CC BY.

关键词： Audiovisual

Unmasking Illusions: Understanding Human Perception of Audiovisual Deepfakes

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Hashmi, Ammarah Shahzad, Sahibzada Adil Lin, Chia-Wen Tsao, Yu Wang, Hsin-Min Social Networks and Human-Centered Computing Program Taiwan International Graduate Program Institute of Information Science Academia Sinica Taipei11529 Taiwan Institute of Information Systems and Applications National Tsing Hua University Hsinchu300044 Taiwan Department of Computer Science National Chengchi University Taipei11529 Taiwan Department of Electrical Engineering Institute of Communications Engineering National Tsing Hua University Hsinchu300044 Taiwan Research Center for Information Technology Innovation Academia Sinica Taipei11529 Taiwan Institute of Information Science Academia Sinica Taipei11529 Taiwan

The emergence of contemporary deepfakes has attracted significant attention in machine learning research, as artificial intelligence (AI) generated synthetic media increases the incidence of misinterpretation and is difficult to distinguish from genuine content. Currently, machine learning techniques have been extensively studied for automatically detecting deepfakes. However, human perception has been less explored. Malicious deepfakes could ultimately cause public and social problems. Can we humans correctly perceive the authenticity of the content of the videos we watch? The answer is obviously uncertain;therefore, this paper aims to evaluate the human ability to discern deepfake videos through a subjective study. We present our findings by comparing human observers to five state-of-the-art deepfake detection models. To this end, we used gamification concepts to provide 110 participants (55 native English speakers and 55 non-native English speakers) with a web-based platform where they could access a series of 40 videos (20 real and 20 fake) to determine their authenticity. Each participant performed the experiment twice with the same 40 videos in different random orders. The videos are manually selected from the FakeAVCeleb dataset. We found that all AI models performed significantly better than humans when evaluated on the same 40 videos. The study also reveals that while deception is not impossible, humans tend to overestimate their detection capabilities. Our experimental results may help benchmark human versus machine performance, advance forensics analysis, and enable adaptive countermeasures. © 2024, CC BY.

关键词： Audiovisual

programming Variational Quantum Circuits with Quantum-Train Agent

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Liu, Chen-Yu Chen, Samuel Yen-Chi Chen, Kuan-Cheng Huang, Wei-Jia Chang, Yen-Jui Graduate Institute of Applied Physics National Taiwan University Taipei Taiwan Research Institute Taipei Taiwan Wells Fargo New YorkNY United States Department of Electrical and Electronic Engineering Imperial College London London United Kingdom Imperial College London London United Kingdom Quantum Information Center Chung Yuan Christian University Taoyuan City Taiwan Master Program in Intelligent Computing and Big Data Chung Yuan Christian University Taoyuan City Taiwan

In this study, the Quantum-Train Quantum Fast Weight programmer (QT-QFWP) framework is proposed, which facilitates the efficient and scalable programming of variational quantum circuits (VQCs) by leveraging quantum-driven parameter updates for the classical slow programmer that controls the fast programmer VQC model. This approach offers a significant advantage over conventional hybrid quantum-classical models by optimizing both quantum and classical parameter management. The framework has been benchmarked across several time-series prediction tasks, including Damped Simple Harmonic Motion (SHM), NARMA5, and Simulated Gravitational Waves (GW), demonstrating its ability to reduce parameters by roughly 70-90% compared to Quantum Long Short-term Memory (QLSTM) and Quantum Fast Weight programmer (QFWP) without compromising accuracy. The results show that QT-QFWP outperforms related models in both efficiency and predictive accuracy, providing a pathway toward more practical and cost-effective quantum machine learning applications. This innovation is particularly promising for near-term quantum systems, where limited qubit resources and gate fidelities pose significant constraints on model complexity. QT-QFWP enhances the feasibility of deploying VQCs in time-sensitive applications and broadens the scope of quantum computing in machine learning domains. Copyright © 2024, The Authors. All rights reserved.

关键词： Long short-term memory

Is Attention All You Need for EEG to Predict Neurological Outcomes in Cardiac Arrest?

学校读者我要写书评

暂无评论

Is Attention All You Need for EEG to Predict Neurological Ou...

IEEE EMBS International Conference on Information Technology Applications in Biomedicine (ITAB)

作者： Jefferson Dionisio Muhammad Rizwan Hidetaka Suzuki Kazi Mahmudul Hassan Ingon Chanpornpakdi Lian-Yu Lin Toshihisa Tanaka Che Lin Department of Smart Medicine and Health Informatics National Taiwan University Taipei Taiwan Artificial Intelligence of Things Taiwan International Graduate Program Academia Sinica Taipei Taiwan Tokyo University of Agriculture and Technology Tokyo Japan Department of Emergency and Critical Care Japanese Red Cross Musashino Hospital Tokyo Japan Department of Internal Medicine Division of Cardiology National Taiwan University College of Medicine and Hospital Taipei Taiwan Department of Electrical Engineering National Taiwan University Taipei Taiwan Graduate Institute of Communication Engineering National Taiwan University Taipei Taiwan Center for Advanced Computing and Imaging in Biomedicine National Taiwan University Taipei Taiwan

ISBN: (数字)9798350351552

ISBN: (纸本)9798350351569

Sudden cardiac arrest (SCA) poses a significant health challenge, necessitating accurate predictions of neurological outcomes in comatose patients, where good outcomes are defined as the recovery of most cognitive functions. Electroencephalogram (EEG) serves as a valuable biomarker for monitoring neurological states due to its rich, time-dependent information. This study aims to predict neurological outcomes using early EEG data by employing the Transformer model, which leverages multi-headed attention to identify patterns in lengthy sequences such as hour-long EEG recordings. Unlike traditional methods that use subsampled EEG epochs, we utilize the entire EEG sequences, subdivided into time steps, allowing our model to capture detailed temporal patterns via the attention mechanism. Moreover, we trained our proposed model using each EEG recording as an individual data sample but evaluated our model through aggregated patient-wise predictions. This approach allows us to boost the data sample size. Our results demonstrate promising predictive performance, achieving an AUROC of 0.82 and AUPRC of 0.90 on the holdout test set and an AUROC of 0.73 and AUPRC of 0.93 on an external test set with patient-wise predictions. This study highlights the potential of utilizing attention mechanisms to capture important time series progressions across EEG sequences for improving SCA prognosis.

关键词： Attention mechanisms Biological system modeling Time series analysis Cardiac arrest Predictive models Brain modeling Transformers Electroencephalography Data models Recording

Loss tangent fluctuations due to two-level systems in superconducting microwave resonators

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Vallières, A. Russell, M.E. You, X. Garcia-Wetten, D.A. Goronzy, D.P. Walker, M.J. Bedzyk, M.J. Hersam, M.C. Romanenko, A. Lu, Y. Grassellino, A. Koch, J. McRae, C.R.H. Graduate Program in Applied Physics Northwestern University EvanstonIL60208 United States Fermi National Accelerator Laboratory BataviaIL60510 United States Department of Physics and Astronomy Northwestern University EvanstonIL60208 United States Department of Materials Science and Engineering Northwestern University EvanstonIL60208 United States Department of Chemistry Northwestern University EvanstonIL60208 United States Department of Electrical and Computer Engineering Northwestern University EvanstonIL60208 United States Center for Applied Physics and Superconducting Technologies Northwestern University EvanstonIL60208 United States Electrical Computing and Energy Engineering Department University of Colorado BoulderCO80309 United States Department of Physics University of Colorado BoulderCO80309 United States National Institute of Standards and Technology BoulderCO80305 United States

Superconducting microwave resonators are critical to quantum computing and sensing technologies. Additionally, they are common proxies for superconducting qubits when determining the effects of performance-limiting loss mechanisms such as from two-level systems (TLS). The extraction of these loss mechanisms is often performed by measuring the internal quality factor Qi as a function of power or temperature. In this work, we investigate large temporal fluctuations of Qi at low powers over periods of 12 to 16 hours (relative standard deviation σQi/Qi = 13%). These fluctuations are ubiquitous across multiple resonators, chips and cooldowns. We are able to attribute these fluctuations to variations in the TLS loss tangent due to two main indicators. First, measured fluctuations decrease as power and temperature increase. Second, for interleaved measurements, we observe correlations between low- and medium-power Qi fluctuations and an absence of correlations with high-power fluctuations. Agreement with the TLS loss tangent mean is obtained by performing measurements over a time span of a few hours. We hypothesize that, in addition to decoherence due to coupling to individual near-resonant TLS, superconducting qubits are affected by these observed TLS loss tangent fluctuations. © 2024, CC BY.

关键词： Qubits