检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Burner, Levi Fermüller, Cornelia Aloimonos, Yiannis Department of Electrical and Computer Engineering University of Maryland College Park United States Institute for Advanced Computer Studies University of Maryland College Park United States Department of Computer Science University of Maryland College Park United States

Suppose you are at your desk looking at some objects on it. You don't know the precise distance from your eye to any particular object in meters. However, you can immediately reach out and touch any of them. Instead of the meter, your knowledge of distance is encoded in unknown but embodied units of action. In contrast, standard approaches in robotics assume calibration to the meter, so that separated vision and control processes can be interfaced. Consequently, robots are precisely manufactured and calibrated, resulting in expensive systems available in only a few configurations. In response, we propose Embodied Visuomotor Representation, a framework that allows distance to be measured by a robot's own actions and thus minimizes dependence on calibrated 3D sensors and physical models. Using it, we demonstrate that a robot without knowledge of its size, environmental scale, or its own strength can become capable of touching and clearing obstacles after several seconds of operation. Similarly, we demonstrate in simulation that an agent, without knowledge of its mass or strength, can jump a gap of unknown size after performing a few test oscillations. These experiments parallel bee and gerbil behavior, respectively. Copyright © 2024, The Authors. All rights reserved.

关键词： Robots

来源：评论

学校读者我要写书评

暂无评论

Development of Intelligent Power Quality Management in Renewable Energy System in Smart Grid using Deep Learning 7

Development of Intelligent Power Quality Management in Renew...

引用

7th International Conference on Inventive Computation Technologies, ICICT 2024

作者： Rajendran, P. Ranga, Jarabala Prasad, P. Venkata Mallala, Balasubbareddy Senthilkumar, G. Natrayan, L. Chinmaya Vishwa Vidyapeeth Deemed To Be University Department of Management Studies Kerala Ernakulam India Ramachandra College of Engineering Department of Electrical And Electronics Engineering Andhra Pradesh Eluru India Chaitanya Bharathi Institute of Technology Department of Electrical And Electronics Engineering Telangana Hyderabad India Panimalar Engineering College Department of Computer Science And Engineering Tamil Nadu Chennai India SIMATS Saveetha School of Engineering Department of Mechanical Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350359299

The present research addresses the crucial issues in intelligent power quality management inside smart grids by merging machine learning models with an Internet of Things (IoT) infrastructure. The research focuses on renewable energy sources, notably solar and wind, employing multiple sensors such as temperature, wind speed, and windmill rotation speed to obtain complete environmental data. A microcontroller records the sensor readings and related power production, generating a dataset of 20,223 entries over a month. Four machine learning models - the Recurrent Neural Network (RNN), Decision Tree (DT), Support Vector Machine (SVM), and Artificial Neural Network (ANN) - are evaluated on 20% of the dataset after being trained on 80% of it. Thesse trained ML model predicts the electricity that can be produced in future based on the information collected from the sensor. Also if the climatic condition is known then the electricity produced in future can be predicted in future. From the experimental result it is seen that the ANN emerges as the top-performing model with an accuracy of 93.5%, displaying its ability to predict electricity. SVM closely follows with 92.3%, while DT exhibits a balanced performance at 89.7%. The RNN, specialized in handling sequential data, achieves an accuracy of 86.22%. The findings underline the usefulness of the integrated system for forecasting electricity production based on real-time environmental conditions, supporting informed decision-making for smart grid stability. This work advances the field of intelligent power quality management and offers a roadmap for maximising the integration of renewable energy sources through the use of machine learning and Internet of Things technology. As the study seek for sustainable energy solutions, this research moves the sector ahead by giving practical insights for robust and efficient smart grid operations. © 2024 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Aerosol jet printing of piezoelectric surface acousticwave thermometer

引用

Microsystems & Nanoengineering 2023年第3期9卷 31-42页

作者： Nicholas McKibben Blake Ryel Jacob Manzi Florent Muramutsa Joshua Daw Harish Subbaraman David Estrada Zhangxian Deng Micron School of Materials Science and Engineering Boise State University1910 W University DriveBoiseID 83725USA Department of Mechanical and Biomedical Engineering Boise State UniversityBoiseID 83725USA School of Electrical Engineering and Computer Science Oregon State University2500 NW Monroe AvenueCorvallisOR 97331USA Idaho National Laboratory Idaho FallsID 83415USA Center for Advanced Energy Studies Idaho FallsID 83401USA

Surface acoustic wave(SAW)devices are a subclass of micro-electromechanical systems(MEMS)that generate an acoustic emission when electrically *** transducers also work as detectors,converting surface strain into readable electrical *** properties of the generated SAW are material dependent and influenced by external factors like *** monitoring temperature-dependent scattering parameters a SAW device can function as a thermometer to elucidate substrate *** fabrication of SAW sensors requires labor-and cost-intensive subtractive processes that produce large volumes of hazardous *** study utilizes an innovative aerosol jet printer to directly write consistent,high-resolution,silver comb electrodes onto a Y-cut LiNbO3 *** printed,two-port,20 MHz SAW sensor exhibited excellent linearity and repeatability while being verified as a thermometer from 25 to 200℃.Sensitivities of the printed SAW thermometer are−96.9×10^(−6)℃^(−1)and−92.0×10^(-6)℃^(−1) when operating in pulse-echo mode and pulse-receiver mode,*** results highlight a repeatable path to the additive fabrication of compact high-frequency SAW thermometers.

关键词： scattering wave surface

来源：评论

学校读者我要写书评

暂无评论

Intelligent Kidney Abnormality Detection in CT Images Using GLCM and Neural Networks 4

Intelligent Kidney Abnormality Detection in CT Images Using ...

引用

4th IEEE International Conference on Mobile Networks and Wireless Communications, ICMNWC 2024

作者： Bajpai, Chhavi Anitha, S. Gaur, Manish Raghini, M. Kaliappan, S. Khan, Imran Centre for Advanced Studies Aktu Department of Computer Science and Engineering Lucknow India Acs College of Engineering Department of CSE-Cyber Security Bangalore India Institute of Engineering and Technology Aktu Department of Computer Science & Engineering Lucknow India Velammal College of Engineering and Technology Department of Artificial Intell igence and Data Science Madurai India Lovely Professional University Department of Research and Development Jalandhar India Sharda School of Nursing Science and Research Sharda University Department of Medical Surgical Nursing Greater Noida India

ISBN: (纸本)9798350352931

Kidney stone illness, one of the most common medical problems worldwide, relieves pain and drives people to the ER. Diagnoses often use imaging, but educated doctors must interpret them. computer-aided diagnostics (CAD) systems help doctors discover kidney stones more accurately. The suggested technique includes preprocessing, feature extraction, and model training. Ultrasound (US) image preprocessing includes restoration, smoothness, sharpness, and contrast enhancement. The Grey Level Co-occurrence Matrices (GLCM) analyze image texture to extract characteristics. Model training uses KELM. The KELM-based model outperforms Extreme Learning Machine (ELM) and K-Nearest Neighbours (KNN) with an average accuracy of 92.54%. This accuracy demonstrates the method can detect kidney stones in ultrasound images. This proposed shows that computer-aided kidney stone detection can be fast and accurate. The combination of GLCM's texture analysis and KELM's classification skills can help medical professionals diagnose kidney stones using imaging. © 2024 IEEE.

关键词： computerized tomography

来源：评论

学校读者我要写书评

暂无评论

Benchmarking Large Language Models for Persian: A Preliminary Study Focusing on ChatGPT

arXiv

引用

arXiv 2024年

作者： Abbasi, Nesa Sani, Samin Mahdizadeh Abaskoh, Amirhossein Sadeghi, Pouya Babalou, Mohammad Hadi Barun, Sara Masoudi, Mostafa Kamahi, Sepehr Namazifard, Danial Edalat, Ali Yaghoobzadeh, Yadollah Naghavian, Nikoo Computer Science Department University of British Columbia Vancouver Canada School of Electrical and Computer Engineering College of Engineering University of Tehran Tehran Iran Tehran Institute for Advanced Studies Khatam University Tehran Iran

This paper explores the efficacy of large language models (LLMs) for Persian. While ChatGPT and consequent LLMs have shown remarkable performance in English, their efficiency for more low-resource languages remains an open question. We present the first comprehensive benchmarking study of LLMs across diverse Persian language tasks. Our primary focus is on GPT-3.5-turbo, but we also include GPT-4 and OpenChat-3.5 to provide a more holistic evaluation. Our assessment encompasses a diverse set of tasks categorized into classic, reasoning, and knowledge-based domains. To enable a thorough comparison, we evaluate LLMs against existing task-specific fine-tuned models. Given the limited availability of Persian datasets for reasoning tasks, we introduce two new benchmarks: one based on elementary school math questions and another derived from the entrance exams for 7th and 10th grades. Our findings reveal that while LLMs, especially GPT-4, excel in tasks requiring reasoning abilities and a broad understanding of general knowledge, they often lag behind smaller pre-trained models fine-tuned specifically for particular tasks. Additionally, we observe improved performance when test sets are translated to English before inputting them into GPT-3.5. These results highlight the significant potential for enhancing LLM performance in the Persian language. This is particularly noteworthy due to the unique attributes of Persian, including its distinct alphabet and writing styles. We have made our codes, prompts, and data available here: https://***/Ipouyall/Benchmarking_ChatGPT_for_Persian. © 2024, CC BY.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Monolithically Integrated 940 nm Half VCSELs on Bulk Ge Substrates

引用

IEEE Photonics Technology Letters 2024年第3期36卷 203-206页

作者： Zhao, Yunlong Wan, Zeyu Guo, Jia Yang, Yun-Cheng Cheng, Hao-Tien Chrostowski, Lukas Lackner, David Wu, Chao-Hsin Xia, Guangrui Department of Materials Engineering VancouverV6T 1Z4 Canada Graduate Institute of Electronics Engineering National Taiwan University Taipei10617 Taiwan Department of Electrical and Computer Engineering VancouverV6T 1Z4 Canada Freiburg im Breisgau79110 Germany Graduate Institute of Photonics and Optoelectronics Graduate School of Advanced Technology National Taiwan University Taipei10617 Taiwan

High-quality n-type AlGaAs distributed Bragg reflectors (DBRs) and lnGaAs multiple quantum wells (MQWs) were successfully monolithically grown on 4-inch off-cut Ge (100) wafers. Even without any design and process optimization for the Ge substrates, the Ge-based half VCSELs have photoluminescence and reflectance spectra comparable to those grown on conventional GaAs wafers. Flat and sub-nm RMS surface roughness and uniform DBR and MQW growth across the wafer were achieved. These results strongly support full VCSEL growth and fabrication on larger-area Ge wafers for the mass production of AlGaAs-based VCSELs. © 1989-2012 IEEE.

关键词： Surface emitting lasers

来源：评论

学校读者我要写书评

暂无评论

Analysis of Self-Supervised Speech Models on Children’s Speech and Infant Vocalizations

Analysis of Self-Supervised Speech Models on Children’s Spe...

引用

Acoustics, Speech, and Signal Processing Workshops (ICASSPW), IEEE International Conference on

作者： Jialu Li Mark Hasegawa-Johnson Nancy L. McElwain Department of Electrical and Computer Engineering University of Illinois Beckman Institute for Advanced Science and Technology University of Illinois Department of Human Development and Family Studies University of Illinois

ISBN: (数字)9798350374513

ISBN: (纸本)9798350374520

To understand why self-supervised learning (SSL) models have empirically achieved strong performances on several speech-processing downstream tasks, numerous studies have focused on analyzing the encoded information of the SSL layer representations in adult speech. Limited work has investigated how pre-training and fine-tuning affect SSL models encoding children's speech and vocalizations. In this study, we aim to bridge this gap by probing SSL models on two relevant downstream tasks: (1) phoneme recognition (PR) on the speech of adults, older children (8-10 years old), and younger children (1-4 years old), and (2) vocalization classification (VC) distinguishing cry, fuss, and babble for infants under 14 months old. For younger children's PR, the superiority of fine-tuned SSL models is largely due to their ability to learn features that represent older children's speech and then adapt those features to the speech of younger children. For infant VC, SSL models pre-trained on large-scale home recordings learn to leverage phonetic representations at middle layers, and thereby enhance the performance of this task.

关键词： Adaptation models Analytical models Speech recognition Self-supervised learning Speech enhancement Phonetics Encoding

来源：评论

学校读者我要写书评

暂无评论

An Efficient Hardware Design of CoAP Protocol for The Internet of Things

An Efficient Hardware Design of CoAP Protocol for The Intern...

引用

Proceedings of the IEEE Dallas Circuits and Systems Workshop (DCAS)

作者： Kasem Khalil Tamador Mohaidat Mahmoud Darwich Ashok Kumar Magdy Bayoumi Department of Electrical and Computer Engineering University of Mississippi Mississippi USA Department of Mathematics and Computer Science University of Mount Union Alliance OH USA The Center for Advanced Computer Studies University of Louisiana at Lafayette LA USA Department of Electrical and Computer Engineering University of Louisiana at Lafayette LA USA

ISBN: (数字)9798350349535

ISBN: (纸本)9798350349542

CoAP (Constrained Application Protocol) plays a crucial role in IoT by providing a lightweight and efficient communication protocol tailored for resource-constrained devices, facilitating seamless and reliable data exchange. This paper proposes a novel hardware accelerator for CoAP to address critical performance challenges in the context of the Internet of Things (IoT). The proposed method focuses on optimizing two key parameters, namely latency and execution time, through a carefully designed hardware setup. Implemented using VHDL on Xilinx Virtex-7 FPGA, the study demonstrates through extensive evaluations that the proposed method outperforms traditional software-based CoAP implementations. It achieves reduced execution times and lower latency across varying payloads and sampling rates, with a power consumption of 4.63 mW. These results signify a notable improvement in CoAP functionality, positioning the proposed hardware acceleration approach as a promising candidate for enhancing communication protocols in IoT environments.

关键词： Performance evaluation Energy consumption Protocols VHDL Power demand Internet of Things Reliability

来源：评论

学校读者我要写书评

暂无评论

Efficient Deep Learning Approach for Breast Cancer Detection

Efficient Deep Learning Approach for Breast Cancer Detection

引用

Omni-layer Intelligent Systems (COINS), International Conference on

ISBN: (数字)9798350349597

ISBN: (纸本)9798350349603

Breast cancer detection saves lives by enabling early diagnosis, timely intervention, and treatment. Early detection and treatment reduce patients' mortality rates and reduce the overall burden of the disease on affected individuals and healthcare systems. A scientific research challenge for breast cancer detection is achieving as high accuracy as possible. Machine learning is providing greater hope for achieving high accuracy. This paper proposes a high-accuracy breast cancer detection method utilizing feature correlation and a reconfigurable neural network (RNN). The proposed method has been comprehensively tested using breast cancer detection datasets and is compared against Support Vector Machine (SVM) and K-Nearest Neighbors (KNN) methods. The results demonstrate the superior performance of the proposed method, achieving an accuracy of 97.2% and sensitivity of 97.8 %, surpassing known traditional methods. The proposed method is implemented using VHDL on Xilinx Virtex-7 FPGA and incurs a lower power consumption of 0.984 W with acceptable resource utilization.

关键词： Support vector machines Accuracy VHDL Power demand Nearest neighbor methods Feature extraction Breast cancer

来源：评论

学校读者我要写书评

暂无评论

Sound Tagging in Infant-centric Home Soundscapes

arXiv

引用

arXiv 2024年

作者： Khan, Mohammad Nur Hossain Li, Jialu McElwain, Nancy L. Hasegawa-Johnson, Mark Islam, Bashima Department of Electrical and Computer Engineering Worcester Polytechnic Institute United States Department of Electrical and Computer Engineering University of Illinois United States Department of Human Development and Family Studies University of Illinois United States Beckman Institute for Advanced Science and Technology University of Illinois United States

Certain environmental noises have been associated with negative developmental outcomes for infants and young children. Though classifying or tagging sound events in a domestic environment is an active research area, previous studies focused on data collected from a non-stationary microphone placed in the environment or from the perspective of adults. Further, many of these works ignore infants or young children in the environment or have data collected from only a single family where noise from the fixed sound source can be moderate at the infant’s position or vice versa. Thus, despite the recent success of large pretrained models for noise event detection, the performance of these models on infant-centric noise soundscapes in the home is yet to be explored. To bridge this gap, we have collected and labeled noises in home soundscapes from 22 families in an unobtrusive manner, where the data are collected through an infant-worn recording device. In this paper, we explore the performance of a large pre-trained model (Audio Spectrogram Transformer [AST]) on our noise-conditioned infant-centric environmental data as well as publicly available home environmental datasets. Utilizing different training strategies such as resampling, utilizing public datasets, mixing public and infant-centric training sets, and data augmentation using noise and masking, we evaluate the performance of a large pre-trained model on sparse and imbalanced infant-centric data. Our results show that fine-tuning the large pre-trained model by combining our collected dataset with public datasets increases the F1-score from 0.11 (public datasets) and 0.76 (collected datasets) to 0.84 (combined datasets) and Cohen’s Kappa from 0.013 (public datasets) and 0.77 (collected datasets) to 0.83 (combined datasets) compared to only training with public or collected datasets, respectively. © 2024, CC BY.

关键词： Large datasets

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：