检索结果-内蒙古大学图书馆

computer System, Information Technology, and electrical engineering (COSITE), International Conference on

作者： Muhajir Muhajir Maulisa Oktiana Kahlil Muchtar Maya Fitria Akhyar Akhyar Muhammad Dandy Pratama Chih-Yang Lin Department of Electrical and Computer Engineering Universitas Syiah Kuala Banda Aceh Indonesia Department of Electrical Electronic and Systems Engineering Faculty of Engineering and Built Environment Universiti Kebangsaan Malaysia Selangor Malaysia Department of Mechanical Engineering National Central University Taoyuan City Taiwan

Emotions play an essential role in the learning process and have an impact on how the learning process is eventually carried out. Facial expressions can be used to visually identify a person’s emotions. Along with the advancement of computer vision and deep learning techniques, the study of human-computer interaction is increasingly focusing on the recognition of facial expressions. One of the main issues is the availability of sufficient datasets, especially for students. This study examined the deep learning architecture for face emotion classification. In addition, this research also introduces a new emotional dataset acquired from the junior high school student at SMP Negeri 1 Darul Imarah, Aceh Besar Regency, Indonesia. This dataset contains five classes that include the emotions of happiness, sadness, anger, surprise, and boredom. The dataset was then tested using the Mobile-Net architecture, the highest accuracy was achieved with a learning rate of 0.0001% of 88.492%. The dataset can be explored via the link https://***/USK-FEMO-DATASET/

关键词：

来源：评论

学校读者我要写书评

暂无评论

Chemical kinetics study with a GHz mid-infrared dual-comb spectrometer

Chemical kinetics study with a GHz mid-infrared dual-comb sp...

引用

CLEO: Science and Innovations in CLEO 2024, CLEO: S and I 2024 - Part of Conference on Lasers and Electro-Optics

作者： Hoghooghi, Nazanin Chang, Peter Egbert, Scott Burch, Matt Shaik, Rizwan Lynch, Patrick Diddams, Scott Rieker, Gregory B. Time and Frequency Division National Institute of Standards and Technology BoulderCO United States Precision Laser Diagnostics Laboratory University of Colorado Boulder BoulderCO United States Department of Physics University of Colorado Boulder BoulderCO United States Department of Mechanical and Industrial Engineering University of Illinois Chicago ChicagoIL United States Electrical Computer and Energy Engineering Department University of Colorado Boulder BoulderCO United States

We study abundance and temperature of species in reactant to product breakdown of 1,3,5-trioxane inside a shock-tube using a 1 GHz repetition rate mid-infrared dual-comb spectrometer with optical bandwidth > 30 THz... 详细信息

关键词： Infrared spectrometers

来源：评论

学校读者我要写书评

暂无评论

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration

arXiv

引用

arXiv 2024年

作者： Chen, Yuzong AbouElhamayed, Ahmed F. Dai, Xilai Wang, Yang Andronic, Marta Constantinides, George A. Abdelfattah, Mohamed S. Computer Systems Lab Cornell University United States Systems and Networking Research Group Microsoft Research United States Department of Electrical and Electronic Engineering Imperial College London United Kingdom

Large language models (LLMs) have demonstrated remarkable performance across various machine learning tasks. Yet the substantial memory footprint of LLMs significantly hinders their deployment. In this paper, we improve the accessibility of LLMs through BitMoD1, an algorithm-hardware co-design solution that enables efficient LLM acceleration at low weight precision. On the algorithm side, BitMoD introduces fine-grained data type adaptation that uses a different numerical data type to quantize a group of (e.g., 128) weights. Through the careful design of these new data types, BitMoD is able to quantize LLM weights to very low precision (e.g., 4 bits and 3 bits) while maintaining high accuracy. On the hardware side, BitMoD employs a bit-serial processing element to easily support multiple numerical precisions and data types;our hardware design includes two key innovations: First, it employs a unified representation to process different weight data types, thus reducing the hardware cost. Second, it adopts a bit-serial dequantization unit to rescale the per-group partial sum with minimal hardware overhead. Our evaluation on six representative LLMs demonstrates that BitMoD significantly outperforms state-of-the-art LLM quantization and acceleration methods. For discriminative tasks, BitMoD can quantize LLM weights to 4-bit with © 2024, CC BY-NC-ND.

关键词： Intellectual property core

来源：评论

学校读者我要写书评

暂无评论

Noncontact Clearance Measurement Research Based on Machine Vision 11th

Noncontact Clearance Measurement Research Based on Machine V...

引用

11th International Workshop of Advanced Manufacturing and Automation, IWAMA 2021

作者： Che, Kai Lu, Dongli Guo, Jun Chen, Yufeng Peng, Guosheng Xu, Lianbing School of Electrical and Information Engineering Hubei University of Automotive Technology Hubei Shiyan442002 China Zhejiang Hong Cheng Computer Systems Co. Ltd. Hangzhou311100 China

ISBN: (纸本)9789811905711

Parts assembly clearance measurement is facing a trend towards high-precision and noncontact. This work aims to measure clearance by image processing based on machine vision. The machine vision system is to highlight the assembly clearance region. Hence, clearance regions are segmenting, and rotating to vertical, then get the geometric center of the region and the inclination relative to the horizontal direction, the two points intersecting the boundary of the region can be obtained through the linear relationship, the clearance width is the pixel distance between two points mapped to the actual width in the world coordinate system. Results of the measurement results show that the system works effectively and meets the requirements, which makes it suitable for industrial applications. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Enhancing Power Quality Event Classification with AI Transformer Models

Enhancing Power Quality Event Classification with AI Transfo...

引用

IEEE General Meeting Power& Energy Society

作者： Ahmad M. Saber Amr Youssef Davor Svetinovic Hatem Zeineldin Deepa Kundur Ehab El-Saadany EECS Department Advanced Power and Energy Center Khalifa University Abu Dhabi UAE Department of Electrical and Computer Engineering University of Toronto Toronto Canada Concordia Institute for Information Systems Engineering Montreal Canada

ISBN: (数字)9798350381832

ISBN: (纸本)9798350381849

Recently, there has been a growing interest in utilizing machine learning for accurate classification of power quality events (PQEs). However, most of these studies are performed assuming an ideal situation, while in reality, we can have measurement noise, DC offset, and variations in the voltage signal’s amplitude and frequency. Building on the prior PQE classification works using deep learning, this paper proposes a deep-learning framework that leverages attention-enabled Transformers as a tool to accurately classify PQEs under the aforementioned considerations. The proposed framework can operate directly on the voltage signals with no need for a separate feature extraction or calculation phase. Our results show that the proposed framework outperforms recently proposed learning-based techniques. It can accurately classify PQEs under the aforementioned conditions with an accuracy varying between 99.81%–91.43% depending on the signal-to-noise ratio, DC offsets, and variations in the signal amplitude and frequency.

关键词： Voltage measurement Noise Power quality Transformers Harmonic analysis Frequency measurement Numerical models Noise measurement Transient analysis Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Intelligent Duty Cycling Management and Wake-up for Energy Harvesting IoT Networks with Correlated Activity 58

Intelligent Duty Cycling Management and Wake-up for Energy H...

引用

58th Asilomar Conference on Signals, systems and computers, ACSSC 2024

作者： Ruíz-Guirola, David E. López, Onel L. A. Montejo-Sánchez, Samuel Leyva Mayorga, Israel Han, Zhu Popovski, Petar University of Oulu Centre for Wireless Communications Oulu Finland Instituto Universitario de Investigación y Desarrollo Tecnológico Universidad Tecnológica Metropolitana Santiago Chile Aalborg University Department of Electronic Systems Aalborg Denmark University of Houston Department of Electrical and Computer Engineering HoustonTX United States

ISBN: (纸本)9798350354058

This paper presents an approach for energy-neutral Internet of Things (IoT) scenarios where the IoT devices (IoTDs) operate solely on harvested energy. We use a Markov chain to represent the operation and transmission states of the IoTDs, a modulated Poisson process to model their energy harvesting process, and a discrete-time Markov chain to model their battery state. The aim is to efficiently manage the duty cycling of the IoTDs, so as to prolong their battery life and reduce instances of low-energy availability. We propose a duty-cycling management based on K-nearest neighbors, aiming to strike a trade-off between energy efficiency and detection accuracy. This is done by incorporating spatial and temporal correlations among IoTDs ' activity, as well as their energy harvesting capabilities. We also allow the base station to wake up specific IoTDs if more information about an event is needed upon initial detection. Our proposed scheme shows significant improvements in energy savings and performance, with up to 11 times lower misdetection probability and 50% lower energy consumption compared to a random duty cycling benchmark. © 2024 IEEE.

关键词： Markov chains

来源：评论

学校读者我要写书评

暂无评论

Planning for Grid Decarbonization in New Mexico: An Energy Storage Perspective

Planning for Grid Decarbonization in New Mexico: An Energy S...

引用

IEEE electrical Energy Storage Application and Technologies Conference (EESAT)

作者： Cody J. Newlun Walker Olis Atri Bera Andrew Benson Raymond H. Byrne Tu Nguyen Joydeep Mitra Electric Power Systems Research Sandia National Laboratories Energy Storage Technology & Systems Albuquerque NM USA Electrical & Computer Engineering Michigan State University East Lansing MI USA

Several states and territories have passed legislation to transition power systems from conventional thermal generation to renewable generation coupled with energy storage in an effort to combat climate change. As a result, grid planners are faced with the monumental task of determining the optimal resource mix and grid topology to meet the future economic and electric demand needs and comply with decarbonization policies. This paper investigates the future pathways for achieving the decarbonization goals in New Mexico, mandated by the New Mexico Energy Transition Act (NMETA). A long-term capacity expansion planning (CEP) model is developed and deployed for achieving this. CEP models are forward-looking optimization frameworks designed to evaluate future planning scenarios and analyze the possible pathways required to achieve the desired de-carbonization targets. Several planning scenarios with uncertain-ties encompassing technology maturation, economic assumptions, and generation retirement schedules are investigated. Multiple future planning scenarios incorporating several ES technologies that differ in cost, duration, and efficiencies are also evaluated. The CEP model is deployed using system data representing the Public Service Company of New Mexico and policies reflecting the NMETA, which enforces statewide carbon-free generation by 2045. This paper estimates the quantity and location of different resources, including energy storage, required to meet the NMETA targets,

关键词：

来源：评论

学校读者我要写书评

暂无评论

Differentially Private Set-Based Estimation Using Zonotopes

Differentially Private Set-Based Estimation Using Zonotopes

引用

European Control Conference (ECC)

作者： Mohammed M. Dawoud Changxin Liu Amr Alanwar Karl H. Johansson School of Computer Science and Engineering Constructor University Bremen Germany Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology and Digital Futures Stockholm Sweden

For large-scale cyber-physical systems, the collaboration of spatially distributed sensors is often needed to perform the state estimation process. Privacy concerns naturally arise from disclosing sensitive measurement signals to a cloud estimator that predicts the system state. To solve this issue, we propose a differentially private set-based estimation protocol that preserves the privacy of the measurement signals. Compared to existing research, our approach achieves less privacy loss and utility loss using a numerically optimized truncated noise distribution. The proposed estimator is perturbed by weaker noise than the analytical approaches in the literature to guarantee the same level of privacy, therefore improving the estimation utility. Numerical and comparison experiments with truncated Laplace noise are presented to support our approach. Zonotopes, a less conservative form of set representation, are used to represent estimation sets, giving set operations a computational advantage. The privacy-preserving noise anonymizes the centers of these estimated zonotopes, concealing the precise positions of the estimated zonotopes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optical Propulsion and Levitation of Metajets

arXiv

引用

arXiv 2025年

作者： Kudtarkar, Kaushik Chen, Yixin Cai, Ziqiang Cunha, Preston Wang, Xinyi Lin, Sam Wong, Zi Jing Liu, Yongmin Lan, Shoufeng Department of Mechanical Engineering Texas A&M University College StationTX United States Department of Material Science and Engineering Texas A&M University College StationTX United States Department of Electrical & Computer Engineering Northeastern University BostonMA United States Department of Aerospace Engineering Texas A&M University College StationTX United States Department of Mechanical Engineering & Industrial Engineering Northeastern University BostonMA United States Department of Electrical & Computer Engineering Texas A&M University College StationTX United States

The quintessential hallmark distinguishing metasurfaces from traditional optical components is the engineering of subwavelength meta-atoms to manipulate light at will. Enabling this freedom, in a reverse manner, to control objects constituted by metasurfaces could expand our capability of optical manipulation to go beyond the predominant microscopic and sub-microscopic scales. Here, we introduce a driving metaphotonic force fully controllable by meta-atoms to manipulate structured objects named metajets. Upon Newton’s law of motion that can apply to classical and relativistic mechanics, we develop a first-principles theory to analyze optical forces generated by refraction and reflection at an interface. We find that three-dimensional motions of metajets would be possible if one could introduce an extra wavevector component. We achieve that by creating a spatially distributed phase gradient with deliberately arranged silicon nanopillars. Our experiments and simulations reveal an in-plane propulsion and, very importantly, out-of-plane levitation of the metajets, aligning well with the theory. We also find that the metaphotonic force augments with increased light power but is not limited by the size of metajets, which could unleash new opportunities for metaphotonic control in large settings, such as interstellar light sails. © 2025, CC BY.

关键词： Aircraft propulsion

来源：评论

学校读者我要写书评

暂无评论

Long thorax disease classification using convolutional long short term memory

Long thorax disease classification using convolutional long ...

引用

2021 IEEE International Conference on electrical, computer, Communications and Mechatronics engineering, ICECCME 2021

作者： Olulana, Kolawole Owolawi, Pius Tu, Chunling Abe, Bolanle Tshwane University of Technology Department of Computer Systems Engineering Soshanguve South Africa Tshwane University of Technology Department of Electrical Engineering Pretoria South Africa

ISBN: (纸本)9781665412629

According to the National Heart, Lung, and Blood Institute (NHLBI), lung thorax diseases like lung nodule, enema, mass, fibrosis among others are one of the most common causes of death globally, the British Thoracic Society (BTS) reported that for each year respiratory diseases are responsible for one in five deaths, of the reported 580, 000 deaths, lung cancer was responsible for 35, 000 deaths, pneumonia for 34, 000, and deaths from COPD was 27, 000, the same organisation reported that over 845, 000 cases were reported each year. Developing better diagnosis processes for treatment using deep learning methods like Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) have proven to work quite well together in a hybridized architectural model for computer-aided diagnosis systems in the medical field. In this paper, we develop a model that makes use of hybridisation of conventional neural networks and long short term memory network in the multi-class labelling of lung thorax diseases. We explore the architecture of convolutional long short-term memory (ConvLSTM) in classification of thorax diseases using a Xray dataset from the National Institute of Health (NIH) as the data source containing 112, 120 images with fourteen(14) diseases label of thorax diseases to help develop an improved hybridized model to help in the diagnosis of multiple lung thorax diseases. © 2021 IEEE.

关键词： Long short-term memory

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：