检索结果-内蒙古大学图书馆

6th International Conference on electrical engineering and Information and Communication Technology, ICEEICT 2024

作者： Muntasir, Fahim Datta, Ayon Mahmud, Shakib Brac University Department of Computer Science and Engineering Dhaka Bangladesh Ahsanullah University of Science and Technology Department of Electrical and Electronic Engineering Dhaka Bangladesh Bangladesh University of Engineering and Technology Department of Biomedical Engineering Dhaka Bangladesh

ISBN: (纸本)9798350385779

Lung cancer is one of the most prevalent and deadly cancer kinds. CT scan imaging has made it easier to observe in-depth at different lung cancer conditions. Convolutional Neural Networks have already been utilized for detecting objects in images. This research implements a lightweight CNN architecture in classifying two types of cancerous images and distinguishing them from healthy ones. AlexNet, ResNet101 V2, DenseNet201, MobileNet V2, and other sizable deep learning and transfer learning models were tested against this unique architecture with global max pooling. The proposed CNN model overlaps in performance with much bigger models whilst using about eight times fewer parameters, thus being efficient. Apart from making the architecture smaller, Grad-CAM was used to explain the convolutional flow over different convolution layers. This integration of the Grad-CAM technique into the analysis adds a crucial layer of transparency to the deep-learning models. By vi-sualizing the regions within lung cancer images that significantly influence predictions, we aim to enhance the interpretability of our model, fostering trust and better understanding among healthcare professionals. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Hybrid In-Vehicle Background Noise Reduction for Robust Speech Recognition:The Possibilities of Next Generation 5G Data Networks

引用

computers, Materials & Continua 2022年第6期71卷 4659-4676页

作者： Radek Martinek Jan Baros Rene Jaros Lukas Danys Jan Nedoma VSB-Technical University of Ostrava Faculty of Electrical Engineering and Computer ScienceDepartment of Cybernetics and Biomedical Engineering70800Ostrava-PorubaCzechia VSB Technical University of Ostrava Faculty of Electrical Engineering and Computer ScienceDepartment of Telecommunications70800Ostrava-PorubaCzechia

This pilot study focuses on employment of hybrid LMS-ICA system for in-vehicle background noise *** vehicles are nowadays increasingly supporting voice commands,which are one of the pillars of autonomous and SMART *** speaker recognition for context-aware in-vehicle applications is limited to a certain extent by in-vehicle back-ground *** article presents the new concept of a hybrid system which is implemented as a virtual *** highly modular concept of the virtual car used in combination with real recordings of various driving scenarios enables effective testing of the investigated methods of in-vehicle background noise *** study also presents a unique concept of an adaptive system using intelligent clusters of distributed next generation 5G data networks,which allows the exchange of interference information and/or optimal hybrid algorithm settings between individual *** average,the unfiltered voice commands were successfully recognized in 29.34%of all scenarios,while the LMS reached up to 71.81%,and LMS-ICA hybrid improved the performance further to 73.03%.

关键词： 5G noise reduction hybrid algorithms speech recognition 5G data networks in-vehicle background noise

来源：评论

学校读者我要写书评

暂无评论

Far-field super-resolution chemical microscopy

引用

Light(Science & Applications) 2023年第7期12卷 1246-1267页

作者： Mingwei Tang Yubing Han Danchen Jia Qing Yang Ji-Xin Cheng State Key Laboratory of Modern Optical Instrumentation College of Optical Science and EngineeringZhejiang UniversityHangzhou 310027China Intelligent Perception Research Institute Zhejiang LabHangzhou 311100China Department of Biomedical Engineering Department of Electrical and Computer EngineeringPhotonics CenterBoston UniversityBostonMA 02459USA

Far-feld chemical microscopy providing molecular electronic or vibrational fingerprint information opens a new window for the study of three-dimensional biological,material,and chemical *** microscopy provides a nondestructive way of chemical identification without exterior ***,the diffraction limit of optics hindered it from discovering more details under the resolution *** development of super-resolution techniques gives enlightenment to open this door behind far-field chemical ***,we review recent advances that have pushed the boundary of far-field chemical microscopy in terms of spatial *** further highlight applications in biomedical research,material characterization,environmental study,cultural heritage conservation,and integrated chip inspection.

关键词： chemical details optics

来源：评论

学校读者我要写书评

暂无评论

Wireless agents for brain recording and stimulation modalities

引用

Bioelectronic Medicine 2023年第1期9卷 1-12页

作者： Bok, Ilhan Vareberg, Adam Gokhale, Yash Bhatt, Suyash Masterson, Emily Phillips, Jack Zhu, Tianxiang Ren, Xiaoxuan Hai, Aviad Department of Biomedical Engineering University of WI – Madison 1550 Engineering Dr MadisonWIRm 2112 United States Department of Electrical and Computer Engineering University of WI – Madison MadisonWI United States MadisonWI United States

New sensors and modulators that interact wirelessly with medical modalities unlock uncharted avenues for in situ brain recording and stimulation. Ongoing miniaturization, material refinement, and sensitization to specific neurophysiological and neurochemical processes are spurring new capabilities that begin to transcend the constraints of traditional bulky and invasive wired probes. Here we survey current state-of-the-art agents across diverse realms of operation and evaluate possibilities depending on size, delivery, specificity and spatiotemporal resolution. We begin by describing implantable and injectable micro- and nano-scale electronic devices operating at or below the radio frequency (RF) regime with simple near field transmission, and continue with more sophisticated devices, nanoparticles and biochemical molecular conjugates acting as dynamic contrast agents in magnetic resonance imaging (MRI), ultrasound (US) transduction and other functional tomographic modalities. We assess the ability of some of these technologies to deliver stimulation and neuromodulation with emerging probes and materials that provide minimally invasive magnetic, electrical, thermal and optogenetic stimulation. These methodologies are transforming the repertoire of readily available technologies paired with compatible imaging systems and hold promise toward broadening the expanse of neurological and neuroscientific diagnostics and therapeutics. © 2023, The Author(s).

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Deep learning augmented microscopy: a faster, wider view, higher resolution autofluorescenceharmonic microscopy

引用

Light(Science & Applications) 2022年第5期11卷 746-747页

作者： Lei Tian Department of Electrical and Computer Engineering Boston UniversityBostonMA 02215USA Department of Biomedical Engineering Boston UniversityBostonMA 02215USA

Deep learning enables bypassing the tradeoffs between imaging speed,field of view,and spatial resolution in autofluorescence-harmonic microscopy.

关键词： harmonic Deep faster

来源：评论

学校读者我要写书评

暂无评论

A Stretchable Leaky Integrate-and-Fire Neuron Enables Uncertainty Handling in Spiking Neural Networks

IEEE Electron Device Letters

引用

IEEE Electron Device Letters 2025年第6期46卷 999-1002页

作者： Mao, Linna Ke, Yizhen Su, Hengjie Zhang, Xinyang Sun, Biao Ma, Kaixue Li, Ting Institute of Biomedical Engineering Chinese Academy of Medical Sciences Peking Union Medical College Tianjin300192 China University of Houston Department of Electrical and Computer Engineering HoustonTX77005 United States Tianjin University School of Electrical and Information Engineering Tianjin300072 China Tianjin University School of Microelectronics Tianjin300072 China

Flexible neuromorphic computing systems have emerged as a promising candidate for next-generation edge computing systems, especially for the development of lightweight, low-power spiking neural network (SNN) systems. However, the mechanical coupling noise caused by flexible components poses challenges in uncertainty handling during the inference process in SNNs. Herein, we developed a stretchable leaky integrate-and-fire neuron device with enhanced uncertainty handling capabilities for stochastic SNN hardware implementation. These neuron devices utilize strain-induced uncertainty to model neuronal function as a conditional random variable. In addition, the SNN was incorporated in a Bayesian approximation model when the firing patterns exhibit mean stationarity over time steps. Simulations on classification and regression tasks on various datasets performed improved confidence and high generalization capability. The results demonstrate that the stretchable LIF neurons have significant potential for constructing robust and accurate SNNs for flexible neuromorphic computing. © 1980-2012 IEEE.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

Analysis of Social Media Data Using Deep Learning and NLP Method for potential use as Natural Disaster Management in Indonesia 2

Analysis of Social Media Data Using Deep Learning and NLP Me...

引用

2nd International Conference on computer System, Information Technology, and electrical engineering, COSITE 2023

作者： Nurdin, Nadhila Kluza, Krzysztof Fitria, Maya Saddami, Khairun Utami, Rika Sri Department of Electrical and Computer Engineering Universitas Syiah Kuala Banda Aceh Indonesia Faculty of Electrical Engineering Automatics Computer Science and Biomedical Engineering AGH University of Krakow Krakow Poland

ISBN: (纸本)9798350343069

During the last decade, the use of social media has exploded. One of the internet’s most popular and accessible social media sites is Twitter in which people can have micro-blog to post their views on any subject, called a tweet. Indonesia becomes one of country which has the most active user of social media. On the other side, Indonesia has experienced a great deal of natural disasters because it is located in a pacific ring of fire. It is needed effective disaster management used in Indonesia, especially with the help of social media data. Big data analysis obtained during turbulent and unorganized emergency situations is the perfect fit for effective management. During a disaster, it is vital to manage the proper decision to help people affected with their needs. This research investigated some methods used in social media analysis and then apply deep learning model for supervised tasks which classify the related and unrelated disasters on tweet datasets and Latent Dirichlet Allocation (LDA) for unsupervised learning which extracts the details category on the disaster Twitter data. The LSTM model architecture obtained a higher score accuracy than CNN. Moreover, the LDA topic modeling obtained potential results on the details topic from the datasets which could describe useful information to help disaster management. © 2023 IEEE.

关键词： Disasters

来源：评论

学校读者我要写书评

暂无评论

Tracking Blood Glucose Concentration of Type 1 Diabetic Patients Using Reinforcement Learning 9

Tracking Blood Glucose Concentration of Type 1 Diabetic Pati...

引用

9th International Conference on Control, Instrumentation and Automation, ICCIA 2023

作者： Sabzevar, Peyman Vafadoost Sadrian, Hamid Hajipour, Ahmad Hakim Sabzevari University Electrical and Computer Faculty Biomedical Engineering Department Sabzevar Iran

ISBN: (纸本)9798350366013

Blood glucose control in diabetic patients has become one of the main concerns of researchers due to its widespread growth in society in recent years. Additionally, during the COVID-19 pandemic, research indicates that individuals who have diabetes have a higher susceptibility to contracting COVID-19 and experiencing more severe complications. This is attributed to a compromised immune system, resulting in a greater number of fatalities compared to individuals without diabetes. Therefore, the desired controller for blood glucose regulation should be very stable against hypoglycemia and perturbations such as meals, noise, and uncertainty, such as the pancreas of a healthy person. The metabolic disorders that cause diabetes in people are covered first in this article. Then Reinforcement Learning will be introduced as one of the machine learning methods to control the blood glucose concentration, and its robustness in the presence of disturbance will be investigated. © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Photoacoustic microscopy using four-wave mixing in a large mode-area fiber

Photoacoustic microscopy using four-wave mixing in a large m...

引用

2023 IEEE International Ultrasonics Symposium, IUS 2023

作者： Buma, Takashi Union College Department of Electrical Computer and Biomedical Engineering SchenectadyNY United States

ISBN: (纸本)9798350346459

Many applications in photoacoustic microscopy (PAM) require laser pulses at multiple wavelengths. High repetition rate multi-wavelength lasers have been demonstrated using nonlinear fiber optics, which produce a wide wavelength range but tend to suffer from low pulse energy (e.g. 100 nJ). This paper presents our preliminary investigation into multimode fibers as a path to achieve higher output laser pulse energy for multi-spectral PAM. Laser pulses from a 532 nm pulsed Nd:YAG laser are coupled into a large mode area (LMA) fiber that supports six spatial modes at 532 nm. Phase-matched four-wave mixing (FWM) between fiber modes produces a broad continuum extending past 800 nm. The pulse energy at 550, 650, and 750 nm spectral bands is 0.84 uJ, 1.31 uJ, and 0.73 uJ, respectively. Multi-spectral imaging experiments successfully differentiate vessel phantoms containing Allura Red, methylene blue, and IR-820 dyes. These results show the potential of using intermodal FWM in a few-mode multimode fiber to achieve uJ-level pulse energies for multi-spectral PAM applications. © 2023 IEEE.

关键词： Four wave mixing

来源：评论

学校读者我要写书评

暂无评论

Customizable Graphite-On-Paper-Based Keypads: Toward Disposable and Recyclable Wireless Human-Machine Interfaces

IEEE Journal on Flexible Electronics

引用

IEEE Journal on Flexible Electronics 2023年第1期2卷 25-33页

作者： Zulfiqar, Muhammad Hamza Hassan, Mahmood Ul Maqbool, Khawaja Qasim Zubair, Muhammad Mehmood, Muhammad Qasim Riaz, Kashif Massoud, Yehia MicroNano Laboratory Department of Electrical Engineering Lahore54600 Pakistan University of Engineering and Technology Lahore Department of Biomedical Engineering Lahore54890 Pakistan Bahria University Department of Computer Science Lahore Campus Islamabad44000 Pakistan Thuwal23955 Saudi Arabia

There is a rapid increase in the use of affordable electronic devices and human-machine interfaces (HMIs) with short serviceable life in almost every aspect of our lives. It is estimated that the waste electrical and electronic equipment (WEEE) and electronic waste (e-waste) generated in year 2021 was 57.5 million metric tons (Mt) and it is expected that the production of e-waste will increase to 110 Mt by the end of 2050. To mitigate these wastes, green HMIs are required which can be customized for multiple applications and can be recycled or disposed of with minimal environmental impact. This work presents customizable graphite-on-paper (GOP)-based keypad consists of interdigitated capacitive (IDC) touch sensors is demonstrated as HMIs to interact with different electronic and media applications wirelessly. The GOP keypads are fabricated through facile and green fabrication process by direct writing of graphite on flexible paper substrate. The GOP keypads can be fabricated in a home setting as the required materials are readily available, i.e., paper, pencils, and Arduino. The GOP keypads can be easily disposed of or recycled at the end of its life or requirement due to the employment of biodegradable materials like paper and graphite. The IDC touch sensors are optimized by analyzing the number of electrode fingers, finger's width, finger's overlap length, and spacing between the electrode fingers. The same GOP keypad is customized to interact with different electronic and media applications wirelessly, i.e., laptop cursor navigation, calculator app on mobile, numeric keypad, etc. The customizable GOP keypads have potential to be used as green wireless HMIs to enforce a circular economy by mitigating electronic and plastic waste, which leads to the vision of a sustainable and green world. © 2022 IEEE.

关键词： Substrates

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：