检索结果-内蒙古大学图书馆

26th International Conference on Research in Computational Molecular Biology, RECOMB 2022

作者： Rachtman, Eleonora Sarmashghi, Shahab Bafna, Vineet Mirarab, Siavash Bioinformatics and Systems Biology Graduate Program UC San Diego La JollaCA United States Department of Electrical and Computer Engineering UC San Diego La JollaCA United States Department of Computer Science and Engineering UC San Diego La JollaCA United States

Computing the distance between two genomes, often without using alignments or even access to assembled sequences, is fundamental to many downstream analyses. © 2022, The Author(s), under exclusive license to Spri... 详细信息

ISBN: (纸本)9783031047480

关键词： Uncertainty analysis

来源：评论

学校读者我要写书评

暂无评论

SURVEY AND EVALUATION OF CONVERGING ARCHITECTURE IN LLMS BASED ON FOOTSTEPS OF OPERATIONS

arXiv

引用

arXiv 2024年

作者： Kim, Seongho Moon, Jihyun Oh, Juntaek Choi, Insu Yang, Joon-Sung Department of Electrical and Electronic Engineering Yonsei University Seoul Korea Republic of Department of Systems Semiconductor Engineering Yonsei University Seoul Korea Republic of BK21 Graduate Program in Intelligent Semiconductor Technology Yonsei University Seoul Korea Republic of

Large Language Models (LLMs), emerging from advancements in Natural Language Processing (NLP) tasks, allow chatbots to provide more sophisticated and human-like text generation by leveraging their vast model sizes, often exceeding billions of parameters, to provide deep knowledge across various domains. Hence, they are becoming more integrated into our daily lives, serving as personal assistants or even as experts across various domains. Initial language models relied on rule-based systems and early neural networks like Recurrent Neural Networks (RNNs). However, it remained an issue to handle long-term dependency and to understand context over extended conversation. The advent of the Attention mechanism and Transformer architecture enables contextually natural text generation and compresses the burden of processing entire source information into singular vectors. Based on these two main ideas, model sizes gradually increases to accommodate more precise and comprehensive information, leading to the current state-of-the-art LLMs being very large, with parameters around 70 billion. As the model sizes are growing, the demand for substantial storage and computational capacity increases. This leads to the development of high-bandwidth memory and accelerators, as well as a variety of model architectures designed to meet these requirements. We note that LLM architectures have increasingly converged. This paper analyzes how these converged architectures perform in terms of layer configurations, operational mechanisms, and model sizes, considering various hyperparameter settings. In this paper, we conduct a concise survey of the history of LLMs by tracing the evolution of their operational improvements. Furthermore, we summarize the performance trends of LLMs under various hyperparameter settings using the RTX 6000, which features the state-of-the-art Ada Lovelace architecture. We conclude that even the same model can exhibit different behaviors depending on the hyperparamete

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Expert-level sleep staging using an electrocardiography-only feed-forward neural network

引用

Computers in Biology and Medicine 2024年 176卷 108545-108545页

作者： Jones, Adam M. Itti, Laurent Sheth, Bhavin R. Neuroscience Graduate Program University of Southern California Los AngelesCA United States Department of Electrical & Computer Engineering University of Houston HoustonTX United States Center for NeuroEngineering and Cognitive Systems University of Houston HoustonTX United States

Reliable classification of sleep stages is crucial in sleep medicine and neuroscience research for providing valuable insights, diagnoses, and understanding of brain states. The current gold standard method for sleep stage classification is polysomnography (PSG). Unfortunately, PSG is an expensive and cumbersome process involving numerous electrodes, often conducted in an unfamiliar clinic and annotated by a professional. Although commercial devices like smartwatches track sleep, their performance is well below PSG. To address these disadvantages, we present a feed-forward neural network that achieves gold-standard levels of agreement using only a single lead of electrocardiography (ECG) data. Specifically, the median five-stage Cohen's kappa is 0.725 on a large, diverse dataset of 5 to 90-year-old subjects. Comparisons with a comprehensive meta-analysis of between-human inter-rater agreement confirm the non-inferior performance of our model. Finally, we developed a novel loss function to align the training objective with Cohen's kappa. Our method offers an inexpensive, automated, and convenient alternative for sleep stage classification—further enhanced by a real-time scoring option. Cardiosomnography, or a sleep study conducted with ECG only, could take expert-level sleep studies outside the confines of clinics and laboratories and into realistic settings. This advancement democratizes access to high-quality sleep studies, considerably enhancing the field of sleep medicine and neuroscience. It makes less-expensive, higher-quality studies accessible to a broader community, enabling improved sleep research and more personalized, accessible sleep-related healthcare interventions. © 2024 Elsevier Ltd

关键词： Electrocardiography

来源：评论

学校读者我要写书评

暂无评论

Virtual Wearable Sensor Data Generation with Generative Adversarial Networks

Virtual Wearable Sensor Data Generation with Generative Adve...

引用

Simulation Winter Conference

作者： Yining Huang Hong Wan Xi Chen Operations Research Graduate Program North Carolina State University Raleigh NC USA Department of Industrial and Systems Engineering North Carolina State University Raleigh NC USA Grado Department of Industrial and Systems Engineering Virginia Tech Blacksburg VA USA

This study delves into the utilization of Generative Adversarial Networks (GANs) for generating subject-specific time series sensor data, offeringaninnovativealternativetotraditionalmetamodel-basedsimulations. We undertake an in-depth analysis of DoppelGANger, a prominent GAN variant for time series data and metadata generation, evaluating its efficiency and efficacy. The sensor data for this investigation was sourced from the National Health and Nutrition Examination Survey, which served as the foundational training set. We scrutinized the synthesized sensor data corresponding to various physical attributes, focusing on the temporal and multi-dimensional statistical properties. Our empirical findings underscore the potential of GANs to adeptly capture the time-dependent correlations and the intricate statistical characteristics inherent in multi-dimensional data. This insight into GANs’ capabilities is a crucial step towards more sophisticated synthetic data generation, with significant implications for future applications in wearable technology and personalized health monitoring systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Preprocessing Algorithm for Seismic Signals Monitored by Fiber Optic Distributed Sensors

Preprocessing Algorithm for Seismic Signals Monitored by Fib...

引用

SBMO/IEEE MTT-S International Conference on Microwave and Optoelectronics (IMOC)

作者： Erik Tarlles Silveira Beatriz Brusamarello Uilian J. Dreyer Guilherme H. Weber Danilo F. Gomes Sidnei H. C. Teixeira Gilson A. Brunetto Luis F. P. Melegari Cicero Martelli Jean Carlos Cardozo da Silva Graduate Program in Electrical and Computer Engineering (CPGEI-UTFPR) Curitiba Parana Brazil Graduate Program in Energy Systems (PPGSE-UTFPR) Curitiba Parana Brazil Civil Engineering Studies Center (CESEC-UFPR) Curitiba Parana Brazil CPFL Energia Brasil Universidade Tecnológica Federal do Paraná Curitiba Paraná Brazil

Fiber optic-based sensors have experimented with significant technological advances in the last two decades. Distributed acoustic sensors represent their most recent iteration. This sensing technology become all the cable length into a sensor, a favorable condition for seismic studies. Data preprocessing is a crucial step in this study, in which the seismic signals captured by optical interrogators must be converted to the apparent velocity of particles that sensitized the fiber. Amongst the main conversion algorithms, the ones based on Fourier Transforms are more adopted at large-scale surveys. This paper presents an algorithm implementation for this conversion, based on the 2D Fourier Transform, in a small-scale laboratory investigation. The results are favorable and show that it is a possible use. It brings more definition to individualizing first break time arrivals, equalizing signal amplitude, and aligning oscillation peaks, essential parameters for applying reflections and refraction methods in seismic studies.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Blockchain: A Review from the Perspective of Operations Researchers 22

Blockchain: A Review from the Perspective of Operations Rese...

引用

Proceedings of the Winter Simulation Conference

作者： Hong Wan Kejun Li Yining Huang Department of Industrial and Systems Engineering North Carolina State University Raleigh NC USA Operations Research Graduate Program North Carolina State University Raleigh NC USA

Blockchain is a distributed append-only digital ledger. The technology has caught much attention since the emergence of cryptocurrency, and there is an increasing number of blockchain applications in various businesses. The concept, however, is still novel to many members of the simulation and operations research community. In this tutorial, we introduce the blockchain technology and review its frontier related research. There are exciting opportunities for researchers in simulation, system analysis, and data science.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Incentive Mechanisms for Federated Learning in Vehicular Networks

引用

IEEE Transactions on Vehicular Technology 2025年

作者： Fathi, Faeze Montazeri, Mina N.araabi, Babak Du, Hongyang Niyato, Dusit Kebriaei, Hamed University of Tehran School of Ece College of Engineering Tehran Iran Urban Energy Systems Laboratory Dübendorf8600 Switzerland Nanyang Technological University School of Computer Science and Engineering The Energy Research Institute @ Ntu Interdisciplinary Graduate Program Singapore Nanyang Technological University School of Computer Science and Engineering Singapore School of Computer Science Tehran Iran

Centralized machine learning algorithms in vehicular networks face privacy and resource constraints. Federated Learning (FL) addresses these by enabling collaborative model training without sharing raw data. To incentivize vehicle participation despite resource constraints, we propose a contract between Roadside Units (RSUs) and vehicles, specifying required computation resources and rewards based on local data quality. The contract is designed to maximize the utility of the RSU, subject to constraints that ensure the participation of the vehicles in the task and truthful reporting of their data quality parameter. However, designing an optimal contract with classical methods is limited to specific utility functions. To extend the design methodology of optimal contracts to a broader range of utility functions, our study proposes a deep learning-based solution. Specifically, we present a novel application of Deep Neural Networks (DNNs), marking the first instance of applying DNNs in contract theory-based incentive mechanisms to achieve nearoptimal contracts. We design the DNN's structure to inherently satisfy specific constraints of the optimization problem, enhancing its efficiency and accuracy in determining the optimal contract. We utilize an augmented Lagrangian method to approximate the optimal contract in federated learning tasks. A case study on traffic sign recognition demonstrates the applicability and effectiveness of our method. Comparing our approach with the well-known generative diffusion model shows that in the FL scenarios, the DNN results are closer to the optimal contract compared to those of the generative diffusion model. © 1967-2012 IEEE.

关键词： Traffic signs

来源：评论

学校读者我要写书评

暂无评论

Implementation and Evaluation of 0.6 µm CMOS Complex RCPF for Accurate Frequency Response Measurement

IEEJ Transactions on Electronics, Information and Systems

引用

IEEJ Transactions on Electronics, Information and systems 2025年第1期145卷 25-37页

作者： Sato, Lina Fukagawa, Kanta Shouno, Kazuhiro Tanimoto, Hiroshi Muto, Cosy Moriyama, Seijiro Takahashi, Chikau Yoshino, Michitaka Graduate School of Science and Technology Degree Programs in Systems and Information Engineering Master’s Program in Computer Science University of Tsukuba Japan Division of Information Engineering University of Tsukuba 1-1-1 Tennoudai Ibaraki Tsukuba305-8573 Japan Kitami Institute of Technology 165 Koen-cho Hokkaido Kitami090-8507 Japan Faculty of Education Nagasaki University 1-14 Bunkyo-machi Nagasaki852-8521 Japan Anagix Corporation 3-22-27 Numama Kanagawa Zushi249-0004 Japan Takamori Corporation Japan Research Center for Micro-Nano Technology Hosei University 3-11-15 Midori-cho Koganei Tokyo184-0003 Japan

This paper describes the implementation and evaluation of an RC polyphase filter (RCPF) and circuitry for measuring its frequency characteristics. The integrated circuit is fabricated on a 0.6 µm CMOS process and its supply voltage is 5 V. The integrated circuit includes a filter under test (FUT), a four-phase square wave generator, several analog switches and differential amplifiers to amplify the high-impedance signals of the RCPF. This FUT is a third-order complex RCPF whose passband is 8 − 40 MHz. This paper describes the design of these circuits in detail. This integrated circuit can select two measurement methods by means of external control signals. The first method uses a four-phase square wave. The frequency characteristics are measured by using an on-chip four-phase square wave generator driven by an external clock generator and by a spectrum analyzer tuned to the fundamental frequency. The second method uses an external network analyzer. Furthermore, this integrated circuit is equipped with a calibration circuit to measure the frequency characteristics of the circuitry except FUT by passing through the input / output signals of the FUT. As a result, the frequency characteristics of the FUT itself can be accurately measured. The effectiveness is confirmed through evaluation of the fabricated integrated circuit. © 2025 The Institute of Electrical Engineers of Japan.

关键词： Differential amplifiers

来源：评论

学校读者我要写书评

暂无评论

Relationship Between Mechanical Deformation and Contact Force Applied by Catheter Tip on Cardiac Muscle: Experimentation and Computer Modeling

Relationship Between Mechanical Deformation and Contact Forc...

引用

IEEE Eurasia Conference on Biomedical engineering, Healthcare and Sustainability (ECBIOS)

作者： Yukako Ijima Kriengsak Masnok Juan J. Perez Ana González-Suárez Enrique Berjano Nobuo Watanabe Master's Program Global Course of Engineering and Science Graduate School of Engineering and Science Shibaura Institute of Technology Saitama Japan Biofluid Science and Engineering Laboratory Functional Control Systems Graduate School of Engineering and Science Shibaura Institute of Technology Saitama Japan Department of Electronic Engineering BioMIT Universitat Politecnica de Valencia Valencia Spain Translational Medical Device Lab School of Engineering University of Galway Galway Ireland Department of Bio-Science and Engineering Biofluid Science and Engineering Laboratory Functional Control Systems Graduate School of Engineering and Science College of Systems Engineering and Science Shibaura Institute of Technology Saitama Japan

The cardiac muscle is elastic and deformable. Pushing a catheter in contact with the cardiac muscle surface to conduct focal energy-based ablative therapies, such as RF ablation, requires an adequate electrode-tissue contact surface to transfer the energy to the target site. In this regard, the relationship between the contact force (CF) and the resulting mechanical response is still unclear, in particular, the insertion depth (ID) and the diameter of the surface deformation. The objective of this study was to quantify these relationships using an ex vivo model and a computational model. A rigid bar with a 2.3 mm diameter blunt tip (mimicking a 7Fr standard ablation catheter) was placed at a perpendicular orientation on a fragment of the porcine heart. CF values ranged from 10 to 80g. We used ANSYS to build a Mooney-Rivlig model of 3 parameters based on hyperelastic material and to simulate the same conditions as in the experiments. The experimental results showed a strong linear correlation between CF and insertion depth ID ( $\mathrm{R}^{2}=0.97, \mathrm{P} < 0.001$ ), from $0.7 \pm 0.3$ mm at 10 gto $6.9 \pm 0.1$ mm at 80 g. We also found a strong linear correlation between CF and minor and major diameters of the surface deformation assessed, from $4.0 \pm 0.4$ mm at 20 g to $10.3 \pm 0.0$ mm at 80 g ( $\mathrm{R}^{2}=0.96$ ), and from $6.4 \pm 0.7$ mm at 20 g to $16.7 \pm 0.1$ mm at 80 g ( $\mathrm{R}^{2}=0.95$ ), respectively. A descent gradient algorithm was used to minimize the mean square error (MSE) between the experimental and computational results of ID for the 10 values of CF. After trying different combinations for the3 parameters of the Mooney-Rivlig model, an optimal fit was achieved after 5 iterations, with an error of less than 0.55 mm for ID. This same mode was then used to predict the diameter of the surface deformation, obtaining an error of less than 0.65 mm. The results confirm that a Mooney-Rivlig model of three parameters based on

关键词：

来源：评论

学校读者我要写书评

暂无评论

Mechanical Wave Detection Through Polyurethane Foam Using Optical Fiber Sensors

Mechanical Wave Detection Through Polyurethane Foam Using Op...

引用

SBMO/IEEE MTT-S International Conference on Microwave and Optoelectronics (IMOC)

作者： Beatriz Brusamarello Uilian J. Dreyer Erik T. Silveira Carlos A. Bavastri Gilson A. Brunetto Luis F. P. Melegari Guilherme H. Weber Danilo F. Gomes Cicero Martelli Jean Carlos Cardozo da Silva Graduate Program in Electrical and Computer Engineering (CPGEI-UTFPR) Universidade Tecnologica Federal do Parana Curitiba Parana Brazil Graduate Program in Energy Systems (PPGSE-UTFPR) Universidade Tecnologica Federal do Parana Curitiba Parana Brazil Graduate Program in Mechanical Engineering (PGMEC-UFPR) Universidade Tecnologica Federal do Parana Curitiba Parana Brazil CPFL Energia Brasil Universidade Tecnologica Federal do Parana Curitiba Parana Brazil

In recent years, distributed acoustic sensing has garnered significant interest in seismic monitoring due to its sensitivity to low frequencies, continuity of measurement in both time and space and the capacity to provide vast amounts of data regarding the conditions of large structures. This study aims to develop a metrological characterization system to evaluate the performance of the distributed acoustic sensing systems to reconstruct the mechanical wavefront and measure its propagation speed in polyurethane foams. The wave propagation speed measured using distributed acoustic sensing is compared with optical fiber Bragg grating sensors and piezoelectric accelerometer, and the difference is less than 1.5%. The results demonstrate that it is possible to reconstruct the mechanical wavefront using both instrumented sensors, thus validating the application of a distributed acoustic sensing system for mechanical wave measurement in polyurethane foams.

关键词：

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：