检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Wang, Sifan Li, Bowen Perdikaris, Paris Chen, Yuhan Graduate Group in Applied Mathematics and Computational Science University of Pennsylvania PhiladelphiaPA19104 United States Department of Mathematics Duke University DurhamNC27708 United States Department of Mechanical Engineering and Applied Mechanics University of Pennsylvania PhiladelphiaPA19104 United States Department of Electrical and Computer Engineering North Carolina State University RaleighNC27695 United States

While physics-informed neural networks (PINNs) have become a popular deep learning framework for tackling forward and inverse problems governed by partial differential equations (PDEs), their performance is known to degrade when larger and deeper neural network architectures are employed. Our study identifies that the root of this counter-intuitive behavior lies in the use of multi-layer perceptron (MLP) architectures with non-suitable initialization schemes, which result in poor trainablity for the network derivatives, and ultimately lead to an unstable minimization of the PDE residual loss. To address this, we introduce Physics-Informed Residual Adaptive Networks (PirateNets), a novel architecture that is designed to facilitate stable and efficient training of deep PINN models. PirateNets leverage a novel adaptive residual connection, which allows the networks to be initialized as shallow networks that progressively deepen during training. We also show that the proposed initialization scheme allows us to encode appropriate inductive biases corresponding to a given PDE system into the network architecture. We provide comprehensive empirical evidence showing that PirateNets are easier to optimize and can gain accuracy from considerably increased depth, ultimately achieving state-of-the-art results across various benchmarks. All code and data accompanying this manuscript will be made publicly available at https://***/PredictiveIntelligenceLab/jaxpi. © 2024, CC BY-NC-ND.

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

Comparative analysis of deep learning models for detecting face mask

引用

Procedia computer science 2023年 216卷 48-56页

作者： M Vickya Ramadhan Kahlil Muchtar Yudha Nurdin Maulisa Oktiana Maya Fitria Novi Maulina Gregorius Natanael Elwirehardja Bens Pardamean Department of Electrical and Computer Engineering Universitas Syiah Kuala Banda Aceh 23111 Indonesia. Telematics Research Center (TRC) Universitas Syiah Kuala Banda Aceh 23111 Indonesia. Microbiology Department School of Medicine Universitas Syiah Kuala Banda Aceh 23111 Indonesia. Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta 11480 Indonesia. Computer Science Department BINUS Graduate Program - Master of Computer Science Program Bina Nusantara University Jakarta 11480 Indonesia.

The spread of Corona Virus Disease 19 (COVID-19) in Indonesia is still relatively high and has not shown a significant decrease. One of the main reasons is due to the lack of supervision on the implementation of health protocols such as wearing masks in daily activities. Recently, state-of-the-art algorithms were introduced to automate face mask detection. To be more specific, the researchers developed various kinds of architectures for the detection of masks based on computer vision methods. This paper aims to evaluate well-known architectures, namely the ResNet50, VGG11, InceptionV3, EfficientNetB4, and YOLO (You Only Look Once) to recommend the best approach in this specific field. By using the MaskedFace-Net dataset, the experimental results showed that the EfficientNetB4 architecture has better accuracy at 95.77% compared to the YOLOv4 architecture of 93.40%, InceptionV3 of 87.30%, YOLOv3 of 86.35%, ResNet50 of 84.41%, VGG11 of 84.38%, and YOLOv2 of 78.75%, respectively. It should be noted that particularly for YOLO, the model was trained using a collection of MaskedFace-Net images that had been pre-processed and labelled for the task. The model was initially able to train faster with pre-trained weights from the COCO dataset thanks to transfer learning, resulting in a robust set of features expected for face mask detection and classification.

关键词： Binary Classification Deep Learning Face mask detection

来源：评论

学校读者我要写书评

暂无评论

Gallium Oxide as Photonic Integrated Platforms in the UV–Visible Spectra

Gallium Oxide as Photonic Integrated Platforms in the UV–Vi...

引用

Conference on Lasers and Electro-Optics (CLEO)

作者： Jingan Zhou Xuan Zhao Rui Xu Xiang Zhang Kai Fu Tao Li Mingfei Xu Shisong Luo Ziyi He Jacob T. Robinson Hanyu Zhu Pulickel M. Ajayan Xiaodong Zhang Yuji Zhao Department of Electrical and Computer Engineering Rice University Houston TX USA Applied Physics Graduate Program Smalley-Curl Institute Rice University Houston TX USA Department of Materials Science and NanoEngineering Rice University Houston TX USA School of Electrical Computer and Energy Engineering Arizona State University Tempe Arizona USA Nanofabrication Facility Suzhou Institute of Nano-Tech and Nano-Bionics Chinese Academy of Sciences Suzhou China

We report the Ga 2 O 3 as photonic integrated platforms and its nonlinear optical effects in the UV–visible spectra. A low propagation loss of 3.7 dB/cm and second-order susceptibility of χ (2) =4.89×10 -3 pm... 详细信息

ISBN: (纸本)9781957171258

关键词： Material properties Nonlinear effects Nonlinear susceptibility Optical components Thin films Visible light communications

来源：评论

学校读者我要写书评

暂无评论

Full-Duplex Beamforming in the Sub-Terahertz Regime

Full-Duplex Beamforming in the Sub-Terahertz Regime

引用

International Conference on Infrared and Millimeter Waves

作者： Subhajit Karmakar Atsutse Kludze Jacques Doumani Andrey Baydin Junichiro Kono Yasaman Ghasempour Department of Electrical and Computer Engineering Princeton University Princeton NJ USA Department of Electrical and Computer Engineering Rice University Houston TX USA Applied Physics Graduate Program Smalley-Curl Institute Rice University Houston TX USA Smalley-Curl Institute Rice University Houston TX USA Department of Physics and Astronomy Rice University Houston TX USA Department of Material Science and NanoEngineering Rice University Houston TX USA

We propose a novel architecture that realizes full-duplex directional beamforming in the sub-terahertz regime. Our architecture leverages the frequency-controlled beam steering of leaky-wave antenna together with the polarization-dependent response of aligned single-wall carbon nanotubes. We evaluate the performance of this architecture via preliminary experiments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Trends, Opportunities, and Challenges in Detecting Depressive Disorders Through Mobile Devices: A Review

Trends, Opportunities, and Challenges in Detecting Depressiv...

引用

computer System, Information Technology, and electrical engineering (COSITE), International Conference on

作者： Gregorius Natanael Elwirehardja Mahmud Isnan Anzaludin Samsinga Perbangsa Kahlil Muchtar Bens Pardamean Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta Indonesia Information System Department School of Information Systems Bina Nusantara University Jakarta Indonesia Department of Electrical and Computer Engineering Universitas Syiah Kuala Banda Aceh Indonesia Computer Science Department BINUS Graduate Program -Master of Computer Science Bina Nusantara University Jakarta Indonesia

Depressive Disorders (DD) is one of the most prevalent mental disorders in the world that may lead to suicide cases. To prevent the latter, ubiquitous early detection systems may be effective. Recent studies have since researched the development of such systems by exploiting several forms of data, including video, audio, Ecological Momentary Assessments (EMA), and passive sensing data using sensors embedded in mobile devices. To summarize the trends, opportunities, and existing challenges in this field, this study reviewed 15 papers to answer four research questions. EMA was the most popular data to be used in this task, but other approaches, such as using video, audio, and typing behaviors, may be considered due to the subjectivity of EMA. These data were typically recorded using smartphones and analyzed using Machine Learning (ML). However, most of the developed systems had yet to be implemented. Overall, it was concluded that further studies may need to explore usages of more objective data in multimodal approaches as well as consider using Mobile Cloud Computing (MCC) to deploy these systems to provide more effective and efficient diagnoses. Future studies must also take into account the existing challenges of the data and infrastructures, such as the weaknesses of several data types, limitations of mobile devices, as well as the challenges of diagnosis approaches.

关键词：

来源：评论

学校读者我要写书评

暂无评论

IoT–based tire pressure monitoring system for air and temperature pressure using MPX5500D and LM35 sensor

IoT–based tire pressure monitoring system for air and tempe...

引用

International Conference on Computing, engineering, and Design (ICCED)

作者： Agung Pangestu Iing Sodikin Muhammad Yusro Rum Sapundani Rosyid Ridlo Al Hakim Sinka Wilyanti Electrical Engineering Department Faculty of Engineering and Computer Science Jakarta Global University Depok Indonesia Department of Electronic Engineering Faculty of Engineering State University of Jakarta Jakarta Indonesia Electromedical Engineering Technology Faculty of Health Science University of Muhammadiyah Purwokerto Purwokerto Indonesia Graduate Program in Electrical Engineering Faculty of Engineering and Computer Science Jakarta Global University Depok Indonesia

ISBN: (纸本)9781665453905

Research has been carried out to monitor vehicle tires before they are used and can reduce damage, including overcoming vehicle fuel waste because air pressure is continuously monitored. This research aims to utilize the MPX5500DP sensor as an air pressure device, the LM35 sensor as a temperature reader, and a buzzer based on IoT to build a tire pressure monitoring system (TPMS). The MPX5500DP and LM35 sensor inputs to the Arduino Uno microcontroller are distributed by the NodeMCU, fitted with a Wi-Fi module. The Blynk application sends and displays the data on a smartphone using the IoT-based. Based on this research, data on the percentage of errors in monitoring air pressure and tire temperature on vehicles were obtained by comparing the data to the pressure gauge and thermometer: 1—the results of the average reading of the sensor error value. MPX5500DP air pressure against pressure gauge is 5.3%. 2—the average reading of the LM35 sensor error value on the temperature thermometer is 6.8%. With this research, the air pressure and temperature in the tires can be monitored in real-time via a smartphone using the IoT-based.

关键词： Temperature measurement Temperature distribution Thermometers Microcontrollers Tire pressure Real-time systems Pressure gauges

来源：评论

学校读者我要写书评

暂无评论

Nernst-Ettingshausen effect in thin Pt and W films at low temperatures

arXiv

引用

arXiv 2023年

作者： Luo, Renjie Legvold, Tanner J. Chen, Liyang Natelson, Douglas Department of Physics and Astronomy Rice University HoustonTX77005 United States Applied Physics Graduate Program Smalley-Curl Institute Rice University HoustonTX77005 United States Department of Electrical and Computer Engineering Department of Materials Science and NanoEngineering Rice University HoustonTX77005 United States

As spin caloritronic measurements become increasingly common techniques for characterizing material properties, it is important to quantify potentially confounding effects. We report measurements of the Nernst-Ettingshausen response from room temperature to 5 K in thin film wires of Pt and W, metals commonly used as inverse spin Hall detectors in spin Seebeck characterization. Johnson-Nyquist noise thermometry is used to assess the temperature change of the metals with heater power at low temperatures, and the thermal path is analyzed via finite-element modeling. The Nernst-Ettingshausen response of W is found to be approximately temperature-independent, while the response of Pt increases at low temperatures. These results are discussed in the context of theoretical expectations and the possible role of magnetic impurities in Pt. Copyright © 2023, The Authors. All rights reserved.

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

Terahertz Time-Domain Imaging for Radiotherapy Treatment Monitoring in Pancreatic Ductal Adenocarcinoma

Terahertz Time-Domain Imaging for Radiotherapy Treatment Mon...

引用

Conference on Lasers and Electro-Optics (CLEO)

作者： Debamitra Chakraborty Bradley N. Mills Jing Cheng Ivan Komissarov Scott Gerber Roman Sobolewski Materials Science Graduate Program University of Rochester Rochester New York Laboratory for Laser Energetics University of Rochester Rochester New York Department of Surgery University of Rochester Medical Center Rochester New York Department of Electrical and Computer Engineering University of Rochester Rochester New York

ISBN: (纸本)9798350369311

Terahertz time-domain imaging was performed of stereotactic body radiotherapy-treated murine pancreatic ductal adenocarcinoma (PDAC) with a high spatial resolution. To generate 2D maps of the tissue samples, the refractive index and absorption coefficient were used as imaging markers extracted with the maximum a-posteriori probability (MAP) estimation algorithm. The results were then compared with the terahertz maps of untreated murine PDAC tissue samples and demonstrated that terahertz imaging can probe physical changes with high sensitivity in the tissue post treatment.

关键词： Maximum a posteriori estimation Terahertz wave imaging Laser theory Sensitivity Refractive index Radiation therapy Time-domain analysis Spatial resolution Probes Monitoring

来源：评论

学校读者我要写书评

暂无评论

AVTENet: A Human-Cognition-Inspired Audio-Visual Transformer-Based Ensemble Network for Video Deepfake Detection

引用

IEEE Transactions on Cognitive and Developmental Systems 2025年

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

The recent proliferation of hyper-realistic deepfake videos has drawn attention to the threat of audio and visual forgeries. Most previous studies on detecting artificial intelligence-generated fake videos only utilize visual modality or audio modality. While some methods exploit audio and visual modalities to detect forged videos, they have not been comprehensively evaluated on multimodal datasets of deepfake videos involving acoustic and visual manipulations, and are mostly based on convolutional neural networks with low detection accuracy. Considering that human cognition instinctively integrates multisensory information including audio and visual cues to perceive and interpret content and the success of transformer in various fields, this study introduces the audio-visual transformer-based ensemble network (AVTENet). This innovative framework tackles the complexities of deepfake technology by integrating both acoustic and visual manipulations to enhance the accuracy of 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 multimodal 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 the proposed model outperforms all existing methods and achieves state-of-the-art performance on Testset-I and Testset-II of the FakeAVCeleb dataset. We also compare AVTENet against humans in detecting video forgery. The results show that AVTENet significantly outperforms humans. © 2016 IEEE.

关键词： audio-visual AVTENet Deepfake detection

来源：评论

学校读者我要写书评

暂无评论

Modeling multi-legged robot locomotion with slipping and its experimental validation

arXiv

引用

arXiv 2023年

作者： Wu, Ziyou Zhao, Dan Revzen, Shai Robotics University of Michigan United States Mechanical Engineering University of Michigan United States Electrical Engineering and Computer Science University of Michigan United States Ecology and Evolutionary Biology University of Michigan United States Applied Physics Program University of Michigan United States

Multi-legged robots with six or more legs are not in common use, despite designs with superior stability, maneuverability, and a low number of actuators being available for over 20 years. This may be in part due to the difficulty in modeling multi-legged motion with slipping and producing reliable predictions of body velocity. Here we present a detailed measurement of the foot contact forces in a hexapedal robot with multiple sliding contacts, and provide an algorithm for predicting these contact forces and the body velocity. The algorithm relies on the recently published observation that even while slipping, multi-legged robots are principally kinematic, and employ a friction law ansatz that allows us to compute the shape-change to body-velocity connection and the foot contact forces. This results in the ability to simulate motion plans for a large number of contacts, each potentially with slipping. Furthermore, in homogeneous environments, this kind of simulation can run in (parallel) logarithmic time of the planning horizon. © 2023, CC BY.

关键词： Friction

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：