检索结果-内蒙古大学图书馆

7th International Conference on computer science and Computational Intelligence, CSCI 2022

作者： Ramadhan, M. Vickya Muchtar, Kahlil Nurdin, Yudha Oktiana, Maulisa Fitria, Maya Maulina, Novi Elwirehardja, Gregorius Natanael Pardamean, Bens Department of Electrical and Computer Engineering Universitas Syiah Kuala Banda Aceh23111 Indonesia Universitas Syiah Kuala Banda Aceh23111 Indonesia Microbiology Department School of Medicine Universitas Syiah Kuala Banda Aceh23111 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. © 2022 Elsevier B.V.. All rights reserved.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Circular eight-room maze for assessing spatial learning and memory functions in rats: An example using a traumatic brain injury model

引用

computers in Biology and Medicine 2024年 182卷 109086-109086页

作者： Chen, Chi-Chun Hung, Yu-Rui Department of Electronic Engineering National Chin-Yi University of Technology Taichung Taiwan Graduate Institute Prospective Technology of Electrical Engineering and Computer Science National Chin-Yi University of Technology Taichung Taiwan

Background and objectives: This study introduced an animal cognitive function assessment system using a novel circular eight-room maze (CERM). The CERM, designed for tracking path trajectories in animal models of cognitive impairment pathologies such as traumatic brain injury (TBI), comprised a 120-cm diameter disk with eight rooms (30 cm × 25 cm × 30 cm). Methods: These rooms have magnetic interfaces for modular assembly and disassembly. Notably, one room remained dark and contained food, while the remaining seven rooms automatically lit up when a rat entry, facilitating the assessment of the rat's learning and spatial memory. An infrared night vision camera captured the animal's search trajectory, and binary image processing techniques were employed to eliminate noise and extract the rat's position coordinates to record the rat's path trajectories. The system automatically calculated various cognitive assessment parameters, such as latency, distance traveled, time spent in each quadrant, inner and outer area exploration times, short-term and long-term memory errors, and the number of entries to all the rooms by chance/by memory. Results: The analysis of overall path trajectories revealed increasingly erratic movement and a growing reliance on chance to enter rooms in rats with TBI over time, likely due to declining memory and the consequent inability to locate the food room. Moreover, increased trajectories in the first quadrant and inner area characterized the behavior of rats with TBI, with statistically significant differences from the sham group observed on day 7. By day 28, all cognitive parameters except short-term memory error significantly differed between the two groups. Conclusion: Experimental data indicated a substantial increase in irregular search behavior in the TBI group over time, suggesting deterioration in cognitive function and an inability to accurately recall the food room. Conversely, the sham group exhibited consistent search trajectories,

关键词： Rats

来源：评论

学校读者我要写书评

暂无评论

Impact of In flux on self-assembled InGaN/GaN superlattice grown on GaN template by plasma-assisted molecular beam epitaxy

Impact of In flux on self-assembled InGaN/GaN superlattice g...

引用

2022 Compound Semiconductor Week, CSW 2022

作者： Khan, Kamruzzaman Sun, Kai Wurm, Christian Ahmadi, Elaheh University of Michigan Department of Materials Science and Engineering Ann ArborMI United States University of California Department of Electrical and Computer Engineering Santa BarbaraCA United States University of Michigan Department of Electrical Engineering and Computer Science Ann ArborMI United States University of Michigan Applied Physics Program Ann ArborMI United States

ISBN: (数字)9781665453400

ISBN: (纸本)9781665453400

We have previously reported spontanous formation of InGaN/GaN superlattice structure on nominal InGaN films grown by plasma-assisted molecular beam epitaxy (PAMBE). In this work, we report on the impact of In flux on the formation and periodicity of self-assembled InxGa1-xN/InyGa1-yN superlattice structure (SASL). We show that the thickness and In composition in the InGaN layer varies by changing the In flux. These films were stucturally characterized by X-ray diffraction and simulated by globalfit software to get the thickness and In composition. The superlattice structures were confimred by scanning transmission electron microscopy and the thickness of InGaN layer and In composition were determined by energy dispersive X-ray spectroscopy. This work can provide a method for using the SASL with better control for their optoelectronics application. © 2022 IEEE.

关键词： III-V semiconductors

来源：评论

学校读者我要写书评

暂无评论

Demonstration of a polarization-agnostic geometric phase in nonlocal metasurfaces

Demonstration of a polarization-agnostic geometric phase in ...

引用

2023 Conference on Lasers and Electro-Optics, CLEO 2023

作者： Overvig, Adam C. Kasahara, Y. Alu, Andrea Photonics Initiative Advanced Science Research Center City University of New York New YorkNY10031 United States Department of Electrical and Computer Engineering The University of Texas at Austin AustinTX78712 United States Physics Program Graduate Center of the City University of New York New YorkNY10016 United States

We theoretically propose and experimentally demonstrate nonlocal metasurfaces rationally designed using symmetry-breaking principles to manipulate the optical wavefront with a geometric phase selective to custom ellip...

ISBN: (纸本)9781957171258

关键词：

来源：评论

学校读者我要写书评

暂无评论

Overcoming Data Inequality across Domains with Semi-Supervised Domain Generalization

arXiv

引用

arXiv 2024年

作者： Park, Jinha Cho, Wonguk Kim, Taesup Department of Electrical and Computer Engineering Seoul National University Korea Republic of Graduate School of Data Science Seoul National University Korea Republic of

While there have been considerable advancements in machine learning driven by extensive datasets, a significant disparity still persists in the availability of data across various sources and populations. This inequality across domains poses challenges in modeling for those with limited data, which can lead to profound practical and ethical concerns. In this paper, we address a representative case of data inequality problem across domains termed Semi-Supervised Domain Generalization (SSDG), in which only one domain is labeled while the rest are unlabeled. We propose a novel algorithm, ProUD, which can effectively learn domain-invariant features via domain-aware prototypes along with progressive generalization via uncertainty-adaptive mixing of labeled and unlabeled domains. Our experiments on three different benchmark datasets demonstrate the effectiveness of ProUD, outperforming all baseline models including single domain generalization and semi-supervised learning. Source code will be released upon acceptance of the paper. Copyright © 2024, The Authors. All rights reserved.

关键词： Population statistics

来源：评论

学校读者我要写书评

暂无评论

Extrinsic LiDAR-Robot And LiDAR-Camera Calibration For Multi-sensor Fusion*

Extrinsic LiDAR-Robot And LiDAR-Camera Calibration For Multi...

引用

IEEE Latin American Robotics Symposium, LARS

作者： Gilmar Pereira Da Cruz Hector Azpúrua Fernando Lizarralde Gustavo Medeiros Freitas Graduate Program in Electrical Engineering Universidade Federal de Minas Gerais - Av. Antônio Carlos 6627 Belo Horizonte MG Brazil Department of Computer Science Universidade Federal de Minas Gerais MG Brasil Electrical Engineering Program - COPPE Universidade Federal do Rio de Janeiro RJ Brasil

ISBN: (数字)9798331508807

ISBN: (纸本)9798331508814

In mobile robotics, an essential requirement for the fusion of different sensors is that measurements are expressed with respect to the same reference. In this sense, the transformation between sensors and robot is necessary to ensure better sensor fusion. Therefore, this article proposes an extrinsic sensor calibration based on markers and associated to three orthogonal planes. This technique is applied to two calibration approaches, LiDAR-Robot and LiDAR-Camera. The first one calculates the transformation between a 3D LiDAR sensor and a robot, and the second system calculates the transformation between a 3D LiDAR and an embedded RGB camera. To demonstrate the efficiency of our method, we performed simulations on the CoppeliaSim simulator and experiments in the laboratory. Then, the results show that it is possible to calibrate the sensors with the methodologies.

关键词： Visualization Laser radar Three-dimensional displays Robot vision systems Sensor fusion Cameras Sensor systems Sensors Calibration Registers

来源：评论

学校读者我要写书评

暂无评论

Energy Efficiency Optimization for NOMA-based Multi-cell VLC System with Optical IRS

Energy Efficiency Optimization for NOMA-based Multi-cell VLC...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Liu, Zehao Yang, Fang Sun, Shiyuan Song, Jian Han, Zhu Tsinghua University Beijing National Research Center for Information Science and Technology Department of Electronic Engineering Beijing100084 China Research Institute of Tsinghua University Shenzhen518057 China Tsinghua University Shenzhen International Graduate School Shenzhen518055 China University of Houston Department of Electrical and Computer Engineering HoustonTX77004 United States

ISBN: (纸本)9798350351255

Considering that optical intelligent reflecting surface (OIRS) can change the optical channel, the enhancement performance of OIRS on the energy efficiency (EE) of the non-orthogonal multiple access (NOMA)-based visible light communication (VLC) system is investigated. Specifically, a multi-cell VLC system is modelled with both line-of-sight (LoS) and OIRS-reflected paths, and then the problem is formulated to optimize the OIRS configuration and power allocation for the maximization of the overall EE while adhering to various constraints. Moreover, the original task is decomposed into two sub-problems, and is solved iteratively by the proposed algorithm. In addition, the convergence of the proposed algorithm and enhancement in EE achieved by OIRS are illustrated by simulation results, which offer beneficial insights on resource allocation for the NOMAbased VLC systems with OIRS. © 2024 IEEE.

关键词： Optical communication

来源：评论

学校读者我要写书评

暂无评论

Artificial compound eye camera for wide field of view and high-resolution imaging

Artificial compound eye camera for wide field of view and hi...

引用

IEEE International Conference on Flexible and Printable Sensors and Systems (FLEPS)

作者： Sehui Chang Young Min Song Gwangju Institute of Science and Technology (GIST): School of Electrical Engineering and Computer Science Gwangju Korea GIST: AI Graduate School Gwangju Korea GIST: Department of Semiconductor Engineering Gwangju Korea

ISBN: (数字)9798350383263

ISBN: (纸本)9798350383270

Insect compound eyes have been garnered a great attention in the fields of optical design, owing to their remarkably economical, but sophisticated visual structures and process. However, a rigid and planar imaging sensor hardly supporting curved micro-optics hinders full implementation of insect vision system. Here, we present a bioinspired artificial compound eye camera for wide field of view and high-resolution imaging based on the hemispherical microlens array and tapered imaging fiber bundles. The hemispherical microlens array focuses a wide field of view image on the curved facet of tapered fiber bundle, which relays the image to another facet contacted on commercial image sensor providing high resolution. The integrated compound eye module suggests a facile way to fill the technical gap for practical applications of artificial insect vision systems.

关键词： Optical fiber sensors Visualization Machine vision Insects High-resolution imaging Cameras Compounds

来源：评论

学校读者我要写书评

暂无评论

Hybrid Full-Bridge Phase-Shift and Half-Bridge LLC Resonant Converter Based on Dual Transformers 10

Hybrid Full-Bridge Phase-Shift and Half-Bridge LLC Resonant ...

引用

10th International Conference on Applied System Innovation, ICASI 2024

作者： Hua, Chih-Chiang Chuang, Ching-Chun Hong, Min-Rui Wang, Jian-Min National Yunlin University of Science and Technology Department of Electrical Engineering 123 University Road Section 3 Yunlin Douliou64002 Taiwan National Kaohaiung University of Science and Technology Department of Electrical Engineering No. 415 Jiangong Rd. Sanmin Dist Kaohsiung City807618 Taiwan National Formosa University Computer Science and Information Engineering No.64 Wunhua Rd. Huwei Township Yunlin County632 Taiwan Graduate Institute of Vehicle Engineering National Formosa University No.64 Wunhua Rd. Huwei Township Yunlin County632 Taiwan

ISBN: (纸本)9798350394924

This paper proposes a hybrid full-bridge phase-shift and half-bridge LLC resonant converter based on dual transformers with different output voltages. In the proposed LLC resonant circuit, the power switches can achieve zero-voltage switching, which reduces power losses caused by traditional hard switching. Additionally, the converter continuously operates at the resonant frequency, enabling zero-current switching for the rectifier diodes and enhancing overall converter efficiency. The prototype circuit operates at an input voltage of 400V and fixed frequency with a constant duty ratio. By adjusting the phase shift between PWM square waves to change the output power, the proposed converter achieves a wide range of output voltages from 250V to 450V and a rated capacity of 1kW. The experimental results show that the proposed converter achieves a maximum conversion efficiency of 92.01% at an output voltage of 250V and a maximum conversion efficiency of 93.78% at an output voltage of 450V. © 2024 IEEE.

关键词： Zero voltage switching

来源：评论

学校读者我要写书评

暂无评论

Optical Neuromorphic modulators based on Tamm Plasmon Resonators with PEDOT:PSS

Optical Neuromorphic modulators based on Tamm Plasmon Resona...

引用

IEEE International Conference on Flexible and Printable Sensors and Systems (FLEPS)

作者： Young Min Song Joo Hwan Ko Dong Hyun Seo Gwangju Institute of Science and Technology (GIST) School of Electrical Engineering and Computer Science Gwangju Korea GIST: AI Graduate School Gwangju Korea GIST: Department of Semiconductor Engineering Gwangju Korea

ISBN: (数字)9798350383263

ISBN: (纸本)9798350383270

Reconfigurable optical devices are increasingly recognized for their potential in enhancing high-density optical interconnects, photonic switching, and memory systems. While various optical modulators utilizing active materials have been successfully developed, achieving high modulation depth with low operating voltage in the near-infrared (NIR) spectrum remains a significant challenge. This spectrum is particularly important for free-space communication and imaging technologies. In this context, an electrically switchable device employing Tamm plasmon coupled with poly(3,4-ethylenedioxythiophene): polystyrene sulfonate (PEDOT:PSS) has been introduced. This innovative approach enables substantial modulation depth throughout the NIR spectrum, effectively absorbing incident light even under epsilon near zero conditions. The device boasts an impressive optical modulation efficiency of over 88% at a CMOS-compatible voltage of ±1 V, achieved through meticulous electrical manipulation of charge carrier density via an electrochemical doping/dedoping process. Moreover, this device opens new avenues for creating non-volatile optical memory storage solutions, exhibiting rewritable multi-memory states and demonstrating long-term potentiation/depression capabilities, akin to neuromorphic behavior.

关键词： Neuromorphics Optical switches Optical resonators Voltage Plasmons Optical imaging Sensor systems

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：