检索结果-内蒙古大学图书馆

A Wideband 24-29 GHz Differential All-Pass Filter in 65-nm CMOS

学校读者我要写书评

暂无评论

A Wideband 24-29 GHz Differential All-Pass Filter in 65-nm C...

IEEE International Symposium on Circuits and systems

作者： M. B. Elamien B. J. Maundy L. Belostotski A. S. Elwakil Department of Electrical and Computer Engineering University of Calgary Canada Department of Electrical and Computer Engineering University of Sharjah UAE Nanoelectronics Integrated Systems Center (NISC) Nile University Egypt

A CMOS wideband voltage-mode fully differential all-pass filter (APF) is discussed. The APF circuit consists of three transistors, two inductors, two capacitors, and four resistors. The proposed APF employs the generic two-transistor common-source amplifier structure. Design procedures along with parasitic analysis are presented for wideband applications. The proposed APF is designed and fabricated in a 65-nm CMOS process. The operation of the proposed APF is validated by experimental and post-layout simulation results. The filter experimentally demonstrates a group delay (GD) of 59 ps at 26 GHz and it has less than 10% delay variation across a wide bandwidth of 24-29 GHz. The implemented design occupies an area of 0.09 mm 2 and consumes 5.1 mA from 1 V supply voltage. The noise and linearity performances of the proposed APF are validated by post-layout simulation results. The filter has a noise figure of 8.6-8.9 dB across 24-29 GHz and it achieves an input-referred IP3 of -1.14 dBm.

关键词： Semiconductor device modeling Simulation CMOS process Delays Transistors Integrated circuit modeling Wideband

Prediction of neonatal respiratory distress in term babies at birth from digital stethoscope recorded chest sounds

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Grooby, Ethan Sitaula, Chiranjibi Tan, Kenneth Zhou, Lindsay King, Arrabella Ramanathan, Ashwin Malhotra, Atul Dumont, Guy A. Marzbanrad, Faezeh Department of Electrical & Computer Systems Engineering Monash University MelbourneVIC Australia Department of Electrical & Computer Engineering University British Columbia VancouverBC Canada Monash Newborn Monash Children's Hospital Department of Paediatrics Monash University Melbourne Australia BC Children's Hospital Research Institute VancouverBC Canada

Neonatal respiratory distress is a common condition that if left untreated, can lead to short- and long-term complications. This paper investigates the usage of digital stethoscope recorded chest sounds taken within 1 min post-delivery, to enable early detection and prediction of neonatal respiratory distress. Fifty-one term newborns were included in this study, 9 of whom developed respiratory distress. For each newborn, 1 min anterior and posterior recordings were taken. These recordings were pre-processed to remove noisy segments and obtain high-quality heart and lung sounds. The random undersampling boosting (RUSBoost) classifier was then trained on a variety of features, such as power and vital sign features extracted from the heart and lung sounds. The RUSBoost algorithm produced specificity, sensitivity, and accuracy results of 85.0%, 66.7% and 81.8%, respectively. Copyright © 2022, The Authors. All rights reserved.

关键词： Biological organs

Online Deep Equilibrium Learning for Regularization by Denoising

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Liu, Jiaming Xu, Xiaojian Gan, Weijie Shoushtari, Shirin Kamilov, Ulugbek S. Department of Electrical and Systems Engineering Washington University St. LouisMO63130 United States Department of Computer Science and Engineering Washington University St. LouisMO63130 United States

Plug-and-Play Priors (PnP) and Regularization by Denoising (RED) are widely-used frameworks for solving imaging inverse problems by computing fixed-points of operators combining physical measurement models and learned image priors. While traditional PnP/RED formulations have focused on priors specified using image denoisers, there is a growing interest in learning PnP/RED priors that are end-to-end optimal. The recent Deep Equilibrium Models (DEQ) framework has enabled memory-efficient end-to-end learning of PnP/RED priors by implicitly differentiating through the fixed-point equations without storing intermediate activation values. However, the dependence of the computational/memory complexity of the measurement models in PnP/RED on the total number of measurements leaves DEQ impractical for many imaging applications. We propose ODER as a new strategy for improving the efficiency of DEQ through stochastic approximations of the measurement models. We theoretically analyze ODER giving insights into its convergence and ability to approximate the traditional DEQ approach. Our numerical results suggest the potential improvements in training/testing complexity due to ODER on three distinct imaging applications. © 2022, CC BY.

关键词： Inverse problems

Analysis of the Effect of Time Delay for Unmanned Aerial Vehicles with Applications to Vision Based Navigation

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Humais, Muhammad Ahmed Chehadeh, Mohamad Boiko, Igor Zweiri, Yahya The Center for Autonomous Robotic Systems Khalifa University Abu Dhabi United Arab Emirates The Department of Electrical Engineering and Computer Science The Department of Aerospace Engineering Khalifa University Abu Dhabi United Arab Emirates

In this paper, we analyze the effect of time delay dynamics on controller design for Unmanned Aerial Vehicles (UAVs) with vision based navigation. Time delay is an inevitable phenomenon in cyber-physical systems, and has important implications on controller design and trajectory generation for UAVs. The impact of time delay on UAV dynamics increases with the use of the slower vision based navigation stack. We show that the existing models in the literature, which exclude time delay, are unsuitable for controller tuning since a trivial solution for minimizing an error cost functional always exists. The trivial solution that we identify suggests use of infinite controller gains to achieve optimal performance, which contradicts practical findings. We avoid such shortcomings by introducing a novel nonlinear time delay model for UAVs, and then obtain a set of linear decoupled models corresponding to each of the UAV control loops. The cost functional of the linearized time delay model of angular and altitude dynamics is analyzed, and in contrast to the delay-free models, we show the existence of finite optimal controller parameters. Due to the use of time delay models, we experimentally show that the proposed model accurately represents system stability limits. Due to time delay consideration, we achieved a tracking results of RMSE 5.01 cm when tracking a lemniscate trajectory with a peak velocity of 2.09 m/s using visual odometry (VO) based UAV navigation, which is on par with the state-of-the-art. Copyright © 2022, The Authors. All rights reserved.

关键词： Time delay

An Application of Quadrature-Inspired Generalized Choquet Integral to Anomaly Detection and Multi-Class Problems

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Karczmarek, Pawel Dolecki, Michal Powroznik, Pawel Lagodowski, Zbigniew A. Gregosiewicz, Adam Galka, Lukasz Pedrycz, Witold Czerwinski, Dariusz Department of Computer Science Lublin University of Technology ul. Nadbystrzycka 36B Lublin20-618 Poland Department of Mathematics Lublin University of Technology ul. Nadbystrzycka 36B Lublin20-618 Poland Department of Electrical & Computer Engineering University of Alberta EdmontonT6R 2V4 AB Canada Department of Electrical and Computer Engineering King Abdulaziz University Jeddah21589 Saudi Arabia Systems Research Institute Polish Academy of Sciences Warsaw Poland

In this study, we thoroughly analyze and evaluate a novel approach to derive an aggregate classification score. The aggregation process applied to various classifiers is realized on a basis of Choquet integral enhancements. These new expressions are inspired by Newton-Cotes quadratures and other formulae well-known from numerical analysis. Unlike previous approaches where to find the Choquet integral generalization one has to use two or three adjacent values associated to the membership of a given element to individual classes, here, one can use more efficient enhancement. Namely, a t-norm appearing under the symbol of integral can be effectively replaced by mathematical expressions used in carrying out numerical integration formulae. It yields more precise results and fully reflects the concept of numerical integration. Moreover, in a series of experiments, we thoroughly analyze the performance of the proposed approach in terms of accuracy in the classification tasks. We analyze the pros and cons of the new approach and establish the experimental settings which can be used in similar tasks. © 2023, The Authors. All rights reserved.

关键词： Anomaly detection

Multi-Camera Multi-Object Tracking: A Review of Current Trends and Future Advances

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Amosa, Temitope Ibrahim Sebastian, Patrick Izhar, Lila Iznita Ibrahim, Oladimeji Bala, Abubakar Ayinla, Lukman Shehu Samaila, Yau Alhaji Department of Electrical and Electronics Engineering Universiti Teknologi PETRONAS Bandar Seri Iskandar Perak Tronoh32610 Malaysia Institute of Autonomous Systems Universiti Teknologi PETRONAS Malaysia Institute of Health and Analytics Universiti Teknologi PETRONAS Malaysia Department of Computer Engineering University of Ilorin Ilorin240103 Nigeria

The nascent applicability of multi-camera tracking (MCT) in numerous real-world applications makes it a significant computer vision problem. The primary goal of visual tracking is to continuously estimate the trajectory of targets in a video sequence while preserving their identities. This task has attracted huge research attention over the years, especially for video obtained from single camera setting (SCT). However, accurate, robust and fast tracking of multiple targets, especially as they transit across multiple cameras remains an open research problem. The ill-posed nature of tracking under multiple camera settings makes the task more complicated. Furthermore, effectively linking data from multiple cameras and across time frames is more critical for tracking in MCT systems as compared to tracking under single camera settings. Meanwhile several research efforts have been expended over the years to effectively address various challenges in tracking under such arrangement. However, studies that critically review and report the recent trend of research in multi-camera multi-target tracking are still limited. The current study presents a comprehensive and up-to-date review of visual tracking problems in multi-camera settings. This paper analyzes and categorizes existing works based on six crucial facets: problem formulation, adopted problem solving approach, data association requirements, mutual exclusion constraints, benchmark datasets, and performance metrics. Also, the study summarizes the outcomes of 30 MCT algorithms on common datasets to allow quantitative comparison and analysis of experimental results. Finally, we examine recent advances in MCT and suggest some promising future research directions. © 2023, The Authors. All rights reserved.

关键词： computer vision

ProxNF: Neural Field Proximal Training for High-Resolution 4D Dynamic Image Reconstruction

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Lozenski, Luke Cam, Refik Mert Pagel, Mark D. Anastasio, Mark A. Villa, Umberto Department of Electrical and Systems Engineering Washington University in St. Louis St. LouisMO63130 United States Department of Electrical and Computer Engineering University of Illinois Urbana-Champaign UrbanaIL61801 United States Department of Medical Physics The University of Wisconsin–Madison MadisonWI53705 United States Department of Bioengineering University of Illinois Urbana-Champaign UrbanaIL61801 United States Oden Institute for Computational Engineering and Sciences University of Texas at Austin AustinTX78712 United States

Accurate spatiotemporal image reconstruction methods are needed for a wide range of biomedical research areas but face challenges due to data incompleteness and computational burden. Data incompleteness arises from the undersampling often required to increase frame rates, while computational burden emerges due to the memory footprint of high-resolution images with three spatial dimensions and extended time horizons. Neural fields (NFs), an emerging class of neural networks that act as continuous representations of spatiotemporal objects, have previously been introduced to solve these dynamic imaging problems by reframing image reconstruction as a problem of estimating network parameters. Neural fields can address the twin challenges of data incompleteness and computational burden by exploiting underlying redundancies in these spatiotemporal objects. This work proposes ProxNF, a novel neural field training approach for spatiotemporal image reconstruction leveraging proximal splitting methods to separate computations involving the imaging operator from updates of the network parameters. Specifically, ProxNF evaluates the (subsampled) gradient of the data-fidelity term in the image domain and uses a fully supervised learning approach to update the neural field parameters. This method is demonstrated in two numerical phantom studies and an in-vivo application to tumor perfusion imaging in small animal models using dynamic contrast-enhanced photoacoustic computed tomography (DCE PACT). © 2024, CC BY-NC-ND.

关键词： Digital elevation model

Speech Separation for Low-Resource Languages

学校读者我要写书评

暂无评论

Speech Separation for Low-Resource Languages

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Marvin Borsdorf Zexu Pan Pascal Himmelmann Haizhou Li Tanja Schultz Machine Listening Lab University of Bremen Bremen Germany Alibaba Group Singapore Department of Mathematics and Computer Science FernUniversität in Hagen Hagen Germany School of Data Science Shenzhen Research Institute of Big Data The Chinese University of Hong Kong Shenzhen China Department of Electrical and Computer Engineering National University of Singapore Singapore Cognitive Systems Lab University of Bremen Bremen Germany

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Speech separation aims to equip machines with the human ability of selective listening, i.e. to focus attention on specific information in spoken communication. Studies have shown that the language spoken in a cocktail party scenario matters. While the development of speech separation models can leverage extensive databases, for the majority of languages only very limited data is available. This work presents the very first study on speech separation for low-resource languages. We choose blind source separation as the task to be studied and analyze three strategies to overcome the data scarcity of two low-resource languages from the GlobalPhoneMS2 database. We show that data from other languages can be used to develop models that work for low-resource languages. Finetuning additionally boosts the performance, and training on multiple languages increases both performance and robustness. We show that dynamic mixing in the development helps to find a trade-off between performance and development time.

关键词： Training Measurement Databases Signal processing Data models Blind source separation Robustness Acoustics Speech processing

Classification vs regression in overparameterized regimes: does the loss function matter?

学校读者我要写书评

暂无评论

The Journal of Machine Learning Research

The Journal of Machine Learning Research 2021年第1期22卷 10104-10172页

作者： Vidya Muthukumar Adhyyan Narang Vignesh Subramanian Mikhail Belkin Daniel Hsu Anant Sahai Electrical and Computer Engineering and Industrial and Systems Engineering Georgia Institute of Technology Atlanta GA Department of Electrical and Computer Engineering University of Washington Seattle WA Department of Electrical Engineering and Computer Sciences University of California Berkeley Berkeley CA Halicioğlu Data Science Institute UC San Diego La Jolla CA Department of Computer Science and Data Science Institute Columbia University New York NY

We compare classification and regression tasks in an overparameterized linear model with Gaussian features. On the one hand, we show that with sufficient overparameterization all training points are support vectors: solutions obtained by least-squares minimum-norm interpolation, typically used for regression, are identical to those produced by the hard-margin support vector machine (SVM) that minimizes the hinge loss, typically used for training classifiers. On the other hand, we show that there exist regimes where these interpolating solutions generalize well when evaluated by the 0-1 test loss function, but do not generalize if evaluated by the square loss function, i.e. they approach the null risk. Our results demonstrate the very different roles and properties of loss functions used at the training phase (optimization) and the testing phase (generalization).

关键词： classification regression overparameterized support vector machines survival contamination