检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Darestani, Mohammad Zalbagi Chaudhari, Akshay S. Heckel, Reinhard Dept. of Electrical and Computer Engineering Rice University Dept. of Radiology Dept. of Biomedical Data Science Stanford University Dept. of Electrical and Computer Engineering Technical University of Munich

Deep neural networks give state-of-the-art accuracy for reconstructing images from few and noisy measurements, a problem arising for example in accelerated magnetic resonance imaging (MRI). However, recent works have raised concerns that deep-learning-based image reconstruction methods are sensitive to perturbations and are less robust than traditional methods: Neural networks (i) may be sensitive to small, yet adversarially-selected perturbations, (ii) may perform poorly under distribution shifts, and (iii) may fail to recover small but important features in an image. In order to understand the sensitivity to such perturbations, in this work, we measure the robustness of different approaches for image reconstruction including trained and un-trained neural networks as well as traditional sparsity-based methods. We find, contrary to prior works, that both trained and un-trained methods are vulnerable to adversarial perturbations. Moreover, both trained and un-trained methods tuned for a particular dataset suffer very similarly from distribution shifts. Finally, we demonstrate that an image reconstruction method that achieves higher reconstruction quality, also performs better in terms of accurately recovering fine details. Our results indicate that the state-of-the-art deep-learning-based image reconstruction methods provide improved performance than traditional methods without compromising robustness. Copyright © 2021, The Authors. All rights reserved.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

A Real-Time Translation of Arabic Video Contents to Arabic Sign Language

A Real-Time Translation of Arabic Video Contents to Arabic S...

引用

International Conference on Computational science and Computational Intelligence (CSCI)

作者： Ashwag Maghraby Safaa Qutub Afraa Alandijani Huda Alandijani Linah Bakhsh Nuha Alharbi Dept. of Computer Science and Informatics Umm Al-Qura University Mecca Saudi Arabia

ISBN: (纸本)9781665458429

The shift to online education due to the COVID-19 pandemic has brought various challenges to different individuals. Among these affected individuals are deaf and hearing-impaired. They face difficulties in understanding online videos because they do not provide real-time translation into Sign languages. The main idea of this project is derived from this point. It proposes a PC-based application called "Al-Banan" that supports deaf and hearing-impaired in the Arabic region to understand media in general including learning video and live virtual classes by translating Basic Arabic Speech into Arabic Sign language using a three-dimensional avatar. The application was built done using Python and C# languages. The application was tested on many deaf through social media and proved to be effective if the word exists in the dictionary a three-dimensional cartoon avatar showing the corresponding Saudi Arabia Sign Language. Otherwise, the word is represented by finger spelling. The results proved the understanding and acceptance of the idea by the deaf.

关键词： Social networking (online) Scientific computing Pandemics Avatars Fingers Gesture recognition Assistive technologies

来源：评论

学校读者我要写书评

暂无评论

Acoustic measurement framework for audio systems based on structured periodic test signals

Acoustic measurement framework for audio systems based on st...

引用

IEEE Global Conference on Consumer Electronics (GCCE)

作者： Hideki Kawahara Kohei Yatabe Ken-Ichi Sakakibara Mitsunori Mizumachi Tatsuya Kitamura Cntr. Innovative Research and Liaison Wakayama University Wakayama Japan Dept. Electrical Engineering and Computer Science Tokyo University of Agriculture and Technology Tokyo Japan Dept. Speech-Language-Hearing Therapy Health Sciences University of Hokkaido Hokkaido Japan Dept. Electrical and Electronic Eng. Kyushu Institute of Technology Kita-Kyushu Japan Dept. Intelligence and Informatics Konan University Kita-Kyushu Japan

We introduce a framework for acoustic measurement that allows everyday sounds into acoustic measurement test signals and standard test signals such as swept-sine and MLS (Maximum Length Sequence). The framework extends our extended Time-Stretched-Pulse generation method and safeguarding method for any signals to make them appropriate for acoustic measurement. The extension uses the periodic nature of discrete Fourier transform combined with orthogonalization based on the Walsh-Hadamerd matrix. This framework enables simultaneous measurement of acoustic attributes such as linear time-invariant response, signal-dependent non-linear and time-invariant components, and random time-varying components. We also discuss and demonstrate practical scenarios in classes and laboratory lessons using tools developed based on the proposed framework.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Large Language Models: A Concise Review of Types and Considerations

Large Language Models: A Concise Review of Types and Conside...

引用

International Conference on Parallel Distributed and Grid Computing (PDGC)

作者： Apeksha Aggarwal Naveen Kumar Gupta Ajay Agarwal Pawan Kumar Dept. of CSE and IT Jaypee Institute of Information Technology Noida India Dept. of Information Technology Center of Energy and Environment Dr B R Ambedkar National Institute of Technology Jalandhar Jalandhar India Department of Computer Science and Engineering R. D. Engineering College Ghaziabad India Biomedical Engineering Indian Institute of Technology Bombay Mumbai India

ISBN: (数字)9798331521349

ISBN: (纸本)9798331521356

This research paper explores nuances of large language models along with a detailed analysis of various model types, and their associated advantages and drawbacks. The primary objective of this paper is to provide a brief knowledge about prevailing popular LLMs. This study further offers a thorough summary of the most recent survey articles that have been published on Large Language Models (LLMs) till date. Furthermore, a comparative study of the latest LLMs launched by popular organizations is also done, along with their evolution over a period of time. Challenges of LLMs are also outlined in this work.

关键词： Surveys Analytical models Reviews Large language models Organizations Transformers Grid computing Natural language processing

来源：评论

学校读者我要写书评

暂无评论

Enhance Undergraduate Research by Incorporating an Entrepreneurial Mindset

Enhance Undergraduate Research by Incorporating an Entrepren...

引用

Frontiers in Education (FIE) Conference

作者： Maysam Nezafati Irene Reizman Mary Lauren Benton John Peponis Michelle Marincel Payne Blake E. Johnson Kenneth Van Treuren Liping Liu Dept. of Biomedical Eng. Georgia Tech / Emory Uni. Atlanta GA USA Dept. of Chemical Eng. Rose-Hulman Inst. of Technology Terre Haute IN USA Dept. of Computer Science Baylor University Waco TX USA Dept. of Biomedical Eng. Lawrence Technological University Southfield MI USA Dept. of Civil & Env. Eng. Rose-Hulman Inst. of Technology Terre Haute IN USA Dept. of Mechanical Eng. Uni. of Illinois Urbana-Champaign Urbana IL USA Dept. of Mechanical Eng. Baylor University Waco TX USA

Undergraduate (UG) Undergraduate (UG) research is a high-impact practice that has been shown to benefit students' development and has the potential to contribute to faculty research output. However, UG research does not attain the impact that it could have on student development or faculty research productivity. Faculty doing UG research face two main challenges: continuity and efficiency. Continuity is important for faculty to achieve research goals. However, onboarding, training, and mentoring UG researchers can be an inefficient, time-consuming process due to a lack of formal mentorship processes. From a student perspective, UG research has two main challenges: lack of autonomy and understanding of relevance relative to other co-curricular activities. In some research groups, UG students may not feel that they have ownership of their work, which results in the decay of intrinsic motivation. We are developing an Entrepreneurial Mindset (EM)-focused framework to enhance the research experience both for faculty and students. This framework provides faculty with access to resources and collaborators to support their efforts in engaging students in UG research and developing continuity in their laboratories. Students, on the other hand, will benefit from training opportunities designed to spark their curiosity, help them establish connections between their learnings, and enhance the value they create through their work. EM principles can transform UG research experiences by improving students' understanding of the relevance of their research and how it creates value for society. Our goal is to infuse EM into students' understanding of the UG research process, with the objective of broadening their participation, addressing institutional challenges, and enhancing research productivity to benefit society. We seek to understand what benefits students perceive they will gain through the UG research experience so that we can understand how entrepreneurially-minded learning

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enabling Scalable Analytics of Physiological Sensor and Derived Feature Multi-Modal Time-Series with Big Data Management

Enabling Scalable Analytics of Physiological Sensor and Deri...

引用

IEEE International Conference on Big Data

作者： Jamal Saied-Walker Pallavi Gupta Ruhan Yi Noah Marchal Marjorie Skubic Grant J. Scott Dept. of EE & Computer Science University of Missouri Columbia Missouri University of Missouri Institute for Data Science & Informatics Columbia Missouri Center to Stream Healthcare in Place University of Missouri Columbia Missouri

ISBN: (纸本)9781665480468

With the increasing interconnection of smart sensors in long-term care facilities, the amount of data available for multi-modal Big Data analytics is advantageous. Using raw smart sensor data, researchers can derive and extract physiological features useful for health monitoring. Nonetheless, with the immense amount of smart sensor data, the ability to utilize these data for multi-modal analytics as the data grows presents a great challenge for researchers and long-term care facilities. This paper proposes a database design system for multi-modal derived time-series featured data (respiration and restlessness) by using techniques such as hierarchical time-indexed databases and dense numerical array storage. We present evaluations and findings for our proposed database system design for multi-modal time-series feature data to assess the various performance characteristics in data access time, storage, and usability; demonstrating an extremely scalable design and simple integration with existing analytic tools via SQL interfaces. Furthermore, we introduce a data-processing pipeline enabling Big Data analytics for multi-modal time-series feature data.

关键词： Pipelines Big Data Feature extraction Database systems Data mining Arrays biomedical monitoring

来源：评论

学校读者我要写书评

暂无评论

Design of Efficient Single-Etch Grating Couplers for Silicon Nitride Photonics at 1550 NM

Design of Efficient Single-Etch Grating Couplers for Silicon...

引用

Photonics North

作者： William Fraser Daniel Benedikovic Radovan Korcek Maziyar Milanizadeh Thalía Domínguez Bucio Valerio Vitali Frederic Y. Gardes Jens H. Schmid Pavel Cheben Winnie N. Ye Dept. Electronics Carleton University Ottawa Canada Dept. Multimedia and Information-Communication Technologies University of Zilina Zilina Slovakia University Science Park University of Zilina Zilina Slovakia National Research Council Ottawa Canada Optoelectronics Research Centre Highfield Campus University of Southampton Southampton UK Electrical Computer and Biomedical Engineering Department University of Pavia Pavia Italy

ISBN: (数字)9798350366365

ISBN: (纸本)9798350366372

We present the design of single-etch grating couplers implemented on native and a hybrid silicon nitride (SiN) photonic platform with amorphous silicon (α-Si) overlays, operating in the telecom waveband. The SiN-only grating coupler has a coupling loss of -3.6 dB and a 1-dB bandwidth of 37 nm. A hybrid α-Si-on-SiN platform yields improved coupling loss of -1.4 dB and -1 dB for uniform and subwavelength grating apodized designs, respectively.

关键词： Couplings Optical losses Couplers Bandwidth Silicon nitride Optical coupling Telecommunications

来源：评论

学校读者我要写书评

暂无评论

Iterative Feedback Tuning Algorithm for Tower Crane Systems

引用

Procedia computer science 2022年 199卷 157-165页

作者： Raul-Cristian Roman Radu-Emil Precup Elena-Lorena Hedrea Stefan Preitl Iuliu Alexandru Zamfirache Claudia-Adina Bojan-Dragos Emil M Petriu Politehnica University of Timişoara Dept. Automation and Applied Informatics Bd. V. Parvan 2 300223 Timişoara Romania University of Ottawa School of Electrical Engineering and Computer Science Ottawa Canada

This paper proposes validates an Iterative Feedback Tuning (IFT) algorithm, which is a classical and also popular data-driven algorithm, on tower crane systems. The IFT algorithm is applied to improve the performances of three proportional-integral (PI) controllers by solving an optimization problem. The IFT algorithm is validated using experiments to control the cart position, the arm angular position and the payload position. The experiments are conducted on a tower crane system in authors’ laboratory, and the experimental setup is laboratory equipment that has strong nonlinearities. Ten iterations are performed to highlight the control system performance using IFT controllers.

关键词： Iterative Feedback Tuning control algorithms tower crane systems

来源：评论

学校读者我要写书评

暂无评论

Comfortable long term ECG monitoring system by the filtering electrodes

Comfortable long term ECG monitoring system by the filtering...

引用

IEEE International Conference on Consumer Electronics (ICCE)

作者： Chang-Ming Yang Shu-Cing Wu Ji-Jer Huang Chi-Chun Chen Ming Young Biomedical Corp. Miaoli Taiwan Prospective Technology of Electrical Engineering and Computer Science National Chin-Yi University of Technology Taichung Taiwan Department of Electrical Engineering Southern Taiwan University of Science and Technology Tainan Taiwan Dept. of Electronic Engineering National Chin-Yi University of Technology Taichung Taiwan

This paper introduces a novel standard 3lead ECG monitoring system, designed for enhanced comfort in daily wear. The system utilizes innovative dry electrodes, seamlessly integrated into both underwear and shirts. These electrodes, made of non-filtering silver material, are specifically engineered to maximize wearer comfort while reliably capturing standard 3-lead ECG signals. This design allows for accurate ECG signal acquisition in both stationary and ambulatory states. The system uniquely records life behavior patterns by analyzing the noise components within the 3-lead ECG signals. For physical activities, the system switches to a filtering silver electrode, ensuring the capture of high-fidelity ECG signals without compromising comfort. The primary goal of this research is to develop a versatile standard 3-lead ECG monitoring system suitable for various daily activities, including exercise, Holter monitoring, and sleep tracking.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multiband highly sensitive metamaterial-based THz absorber for edible oil adulteration sensing

引用

Optik 2024年 307卷

作者： Anowarul Haque, S.M. Sohayeb Hossain, Md Alqahtani, Abdulrahman Islam, Mohammad Tariqul Moniruzzaman, Md. Samsuzzaman, Md. Dept. of Electrical Electronic and Systems Engineering Faculty of Engineering and Built Environment Universiti Kebangsaan Malaysia Selangor Bangi43600 Malaysia Dept. of Electrical and Electronic Engineering Mymensingh Engineering College Bangladesh Department of Biomedical Technology College of Applied Medical Sciences in Al-Kharj Prince Sattam Bin Ab-dulaziz University Al-Kharj11942 Saudi Arabia Department of Medical Equipment Technology College of Applied Medical Science Majmaah University Majmaah City11952 Saudi Arabia Dept. of Electrical and Electronic Engineering College of Engineering and Technology International University of Business Agriculture and Technology Dhaka Uttara1230 Bangladesh Dept. of Computer and Communication Engineering Faculty of Computer Science and Engineering Patuakhali Science and Technology University Bangladesh Faculty of Graduate Studies Daffodil International University Daffodil Smart City Birulia Dhaka Savar1216 Bangladesh

A terahertz (THz) wave technology is very appealing for applications in detection in biomedicine, biological spectroscopy, material characterization, detection, imaging, sensing, and other convenient applications. Metamaterials (MMs) are artificial structures that have structures in a regular periodic arrangement and don't exist in nature. By utilizing a proposed terahertz metamaterial absorber, a broad spectrum of adulterated lubricants can be detected. It is an efficient detection process that enables the development of a THz detection approach by making use of the metamaterial as a sensor. The proposed terahertz absorber is analyzed and optimized using the CST Microwave Studio 2019 software. The article proposed a multiband THz metamaterial absorber with a unit size of 70 µm. According to the demonstrated results, we can achieve five narrow absorption peaks with perfect absorption within the frequency range between (0.2–4.2) Terahertz. Also, the result shows that, the average absorbance of 99.07% at the resonance frequencies of 0.56, 1.42, 2.676, 3.14, and 3.89 THz. The E (electric) and H (magnetic)-field distributions on the resonator at different resonance frequencies were also analyzed as well as. The recommended metamaterial absorber has a good sensing capability at different resonant frequencies, with refractive index sensitivities of 80 GHz/RIU, 240 GHz/RIU, 480 GHz/RIU, 480 GHz/RIU, and 520 GHz/RIU obtained by modifying the refractive index of the sample holder or the analytic layer, respectively. As a result, the proposed detector has a high refractive index sensitivity, high Q-factor, and high FOM, making it suitable for detecting oil adulteration. © 2024 Elsevier GmbH

关键词： Metamaterials

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：