检索结果-内蒙古大学图书馆

IEEE International Conference on Consumer Electronics (ICCE)

作者： Xiang-Rui Huang Huai-Jhan Ke Szu-Yu Kuo Liang-Bi Chen Department of Electrical Engineering Master Program in Electrical Engineering and Computer Science National Penghu University of Science and Technology Penghu Taiwan Department of Computer Science and Information Engineering National Penghu University of Science and Technology Penghu Taiwan Department of Shipping and Transportation Management National Kaohsiung University of Science and Technology Kaohsiung Taiwan

ISBN: (数字)9798331521165

ISBN: (纸本)9798331521172

Lilies are popular in the global flower market, but consumers often lack information about specific varieties. To address this issue, this paper proposes a computer recognition platform based on the Vision Transformer (ViT) architecture. The proposed platform uses an improved vision transformer (ViT) architecture to classify different types of lilies, allowing consumers to access information and names of various Lilium species. The experimental results show that the proposed lily classification model achieved a 96.4% accuracy rate in classifying six lily species.

关键词： computer vision Electric potential Accuracy Computational modeling computer architecture computer applications Flowering plants Network architecture Transformers Consumer electronics

来源：评论

学校读者我要写书评

暂无评论

Meta-optic accelerators for object classification

Meta-optic accelerators for object classification

引用

2023 Flat Optics: Components to Systems, FLatOptics 2023 in Optica Imaging Congress - Part of Imaging and Applied Optics Congress 2023

作者： Zheng, Hanyu Liu, Quan Zhou, You Kravchenko, Ivan I. Huo, Yuankai Valentine, Jason Department of Electrical and Computer Engineering Vanderbilt University NashvilleTN37212 United States Department of Computer Science Vanderbilt University NashvilleTN37212 United States Department of Mechanical Engineering Vanderbilt University NashvilleTN37212 United States Interdisciplinary Materials Science Program Vanderbilt University NashvilleTN37212 United States Center for Nanophase Materials Sciences Oak Ridge National Laboratory Oak RidgeTN37830 United States

A meta-optic platform for accelerating object classification is demonstrated. End-to-end design is used to co-optimize the optical and digital systems resulting in high-speed classifiers that are demonstrated for hand... 详细信息

ISBN: (纸本)9781957171289

关键词： Imaging systems Machine vision Neural networks Optical components Optical neural systems Optical systems

来源：评论

学校读者我要写书评

暂无评论

Dynamic Surrogate Optimization of Vertically Stacked Nanosheet FET Based on Gaussian Process Regression

引用

IEEE Access 2025年 13卷 95730-95738页

作者： Christofer N. Yalung Doldet Tantraviwat Doctor of Philosophy Program in Nanoscience and Nanotechnology (International Program/Interdisciplinary) Materials Science Research Center Faculty of Science Chiang Mai University Chiang Mai Thailand Department of Electrical Engineering Faculty of Engineering Chiang Mai University Chiang Mai Thailand Center of Excellence in Materials Science and Technology Faculty of Science Chiang Mai University Chiang Mai Thailand

While speed improvements are pivotal for advancing modern transistor technologies and ensuring faster computational performance, the tradeoffs with other critical electrical properties, such as threshold voltage ( $V_{T}$ ) and off-current ( $I_{OFF}$ ), are often overlooked. These tradeoffs can significantly impact the overall device performance. The design of vertically stacked n-type and p-type nanosheet FETs (NSFETs) was applied using a dynamic surrogate optimization-gaussian process regression (DSO-GPR) with batch assessment and halting conditions. A vertically stacked silicon-based system is created and refined. Source extension ( $S_{ext}$ ), drain extension ( $D_{ex\mathrm {t}}$ ), gate length ( $L_{g}$ ), nanosheet height (NSh), nanosheet width (NSw), and number of fin (nfin) make up the input variables. In addition to applying normalization to make the weight assignment to the goal functions easier, a penalty component was incorporated to manage the $V_{T}$ . This study demonstrates the effectiveness of the DSO-GPR framework in optimizing NSFET-based inverter designs by balancing speed, $I_{OFF}$ and $V_{T}$ . Among the three evaluated cases, case 1 achieved the fastest propagation delay (1.05 ps) due to higher $I_{ON}$ and lower $V_{T}$ , albeit with increased $I_{OFF}$ and $V_{T}$ mismatch. Case 2 provided a balanced trade-off, significantly reducing $I_{OFF}$ while maintaining a competitive delay of 1.25 ps and achieving $V_{T}$ matching at 0.11 V for both n-type and p-type NSFETs. The optimum parameters for n-type are ${L} _{g}$ = 5 nm, $N_{Sh} = 9$ nm, $N_{Sw} = 42$ nm, $S_{ext} = 3$ nm and $D_{ext} = 4$ nm, nfin = 5; for p-type, $L_{g} = 7$ nm, $N_{Sh} = 10$ nm, $N_{Sw} = 42$ nm, $S_{ext} = 3$ nm and $D_{ext} = 3$ nm, nfin = 5. Case 3 minimized leakage at the cost of delay, highlighting the trade-off between power and performance. These results validate the framework’s adaptability and automation, with performance-based stopping criteria that balance

关键词： Optimization Logic gates Ions Silicon Performance evaluation Linear programming Gaussian processes Field effect transistors Accuracy Machine learning

来源：评论

学校读者我要写书评

暂无评论

Towards Efficient In-memory Computing Hardware for Quantized Neural Networks: State-of-the-art, Open Challenges and Perspectives

arXiv

引用

arXiv 2023年

作者： Krestinskaya, Olga Zhang, Li Salama, Khaled Nabil Electrical and Computer Engineering Program the Division of Computer Electrical and Mathematical Sciences and Engineering King Abdullah University of Science and Technology Thuwal23955 Saudi Arabia

The amount of data processed in the cloud, the development of Internet-of-Things (IoT) applications, and growing data privacy concerns force the transition from cloud-based to edge-based processing. Limited energy and computational resources on edge push the transition from traditional von Neumann architectures to In-memory Computing (IMC), especially for machine learning and neural network applications. Network compression techniques are applied to implement a neural network on limited hardware resources. Quantization is one of the most efficient network compression techniques allowing to reduce the memory footprint, latency, and energy consumption. This paper provides a comprehensive review of IMC-based Quantized Neural Networks (QNN) and links software-based quantization approaches to IMC hardware implementation. Moreover, open challenges, QNN design requirements, recommendations, and perspectives along with an IMC-based QNN hardware roadmap are provided. © 2023, CC BY.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Sample-efficient Adversarial Imitation Learning

arXiv

引用

arXiv 2023年

作者： Jung, Dahuin Lee, Hyungyu Yoon, Sungroh Electrical and Computer Engineering Seoul National University Seoul08826 Korea Republic of Electrical and Computer Engineering Interdisciplinary Program in Artificial Intelligence Seoul National University Seoul08826 Korea Republic of

Imitation learning, in which learning is performed by demonstration, has been studied and advanced for sequential decision-making tasks in which a reward function is not predefined. However, imitation learning methods still require numerous expert demonstration samples to successfully imitate an expert’s behavior. To improve sample efficiency, we utilize self-supervised representation learning, which can generate vast training signals from the given data. In this study, we propose a self-supervised representation-based adversarial imitation learning method to learn state and action representations that are robust to diverse distortions and temporally predictive, on non-image control tasks. In particular, in comparison with existing self-supervised learning methods for tabular data, we propose a different corruption method for state and action representations that is robust to diverse distortions. We theoretically and empirically observe that making an informative feature manifold with less sample complexity significantly improves the performance of imitation learning. The proposed method shows a 39% relative improvement over existing adversarial imitation learning methods on MuJoCo in a setting limited to 100 expert state-action pairs. Moreover, we conduct comprehensive ablations and additional experiments using demonstrations with varying optimality to provide insights into a range of factors. Copyright © 2023, The Authors. All rights reserved.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Downstream Task Performance of Pre-Trained Model For Outdoor Audio Event Classification 9

Downstream Task Performance of Pre-Trained Model For Outdoor...

引用

9th International Conference on Signal Processing and Intelligent Systems, ICSPIS 2023

作者： Rochadiani, Theresia Herlina Heryadi, Yaya Sonata, Ilvico Lukas Suparta, Wawan Bina Nusantara University Binus Graduate Program- Computer Science Jakarta Indonesia Universitas Katolik Indonesia Atma Jaya Cognitive Engineering Research Group Jakarta Indonesia Institut Teknologi Nasional Yogyakarta Department of Electrical Engineering Yogyakarta Indonesia

ISBN: (纸本)9798350369922

Our surroundings' auditory landscapes are a wealth of knowledge, providing insights into a range of outdoor pursuits. The automatic classification of these actions using audio event detection and classification (AEDC) systems has a great deal of potential applications in environmental monitoring, security, surveillance, and driverless cars. Even though AEDC has advanced significantly in indoor settings, difficulties still exist outside because of the variable and changing acoustic conditions brought on by elements like the weather, different sound sources, and ambient noise from traffic and industry. This study suggests an outdoor audio event categorization model based on convolutional neural networks (CNNs). The suggested model shows passable accuracy by utilizing adaptation to the downstream task using the ESC-50 dataset and transfer learning from a pre-trained model. The effectiveness of multi-class audio classification models in downstream tasks is analyzed in this paper, with an emphasis on the effect of an increasing number of output classes on accuracy. Three models - three, four, and five classes - with different output class configurations are used in the study, and their training and validation accuracies are assessed. Although the accuracy scores above 80% are commendable, the data show a discernible reduction in performance as the number of classes rises. Notably, the three-class model attains a validation accuracy exceeding 90%, whereas the four-class and five-class models exhibit reduced accuracies, falling below 90% and 85%, respectively. © 2023 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Optically Controlled Charge Trapping Memory Based on Spin Coated Hafnium Diselenide Flakes

Optically Controlled Charge Trapping Memory Based on Spin Co...

引用

IEEE Conference on Nanotechnology

作者： Bashayr Alqahtani Nazek El Atab King Abdullah University of Science and Technology Program of Electrical and Computer Engineering Computer Electrical Mathematical Sciences and Engineering King Abdullah University of Science and Technology Thuwal Saudi Arabia

This paper demonstrates the seamless fabrication of optoelectronic memory by integrating HfSe 2 as a charge-trapping layer in a MOS memory structure. Through a spin coating technique, solution-processable HfSe 2 flakes with average thicknesses of 2 nm were deposited between the tunneling and blocking oxide layers. The charge-trapping material distribution and thickness were explored by Atomic Force Microscopy and X-ray Diffraction Spectroscopy. The electrical characterization of MOS memory revealed a memory window of 5.5 Volts under ±16 Volts biasing. Furthermore, the memory endurance exceeds 10 4 electrical programming and erasing cycles. The retention test performed at room temperature showed that the memory device is expected to lose only 10% of the stored charges after 10 years. Under light stimuli (405nm wavelength and output power ~ 20 mW) with electrical readout voltage, the MOS memory showed an increase in the memory window from 5.5 Volts to 6.5 Volts.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Brain Tumor Detection and Segmentation Using Deep Learning Models 6

Brain Tumor Detection and Segmentation Using Deep Learning M...

引用

6th World Symposium on Artificial Intelligence, WSAI 2024

作者： Abiodun, Moses Kazeem Adeniyi, Abidemi Emmanuel Awotunde, Joseph Bamidele Aworinde, Halleluyah Tinuoye, George Imoize, Agbotiname Lucky Li, Chun-Ta Lee, Cheng-Chi Landmark University Department of Computer Science Kwara State Omu-Aran Nigeria Bowen University Department of Computer Science Osun State Iwo Nigeria University of Ilorin Department of Computer Science Kwara State Ilorin Nigeria University of Lagos Faculty of Engineering Department of Electrical and Electronics Engineering Akoka Nigeria Fu Jen Catholic University Bachelor's Program of Artificial Intelligence and Information Security New Taipei City Taiwan Fu Jen Catholic University Department of Library and Information Science New Taipei City Taiwan

ISBN: (纸本)9798350374162

This study focuses on brain tumor detection and segmentation using Convolutional Neural Networks (CNN) with architectures of Fully Convolutional Net-work (FCN) and VGG16. The dataset imported for this study consists of brain MRI images, which were preprocessed to improve the overall image resolution. Data augmentation techniques were applied to heighten the variability and volume of the training data. For feature extraction, CNN models were utilized, specifically the VGG16 architectures. This model was trained on a preprocessed dataset to learn the important features associated with the presence of brain tumor. Image segmentation was performed to precisely outline and identify the tumor region within the brain images. FCN architecture was employed for this task, which allowed pixel-level classification of tumor regions. Finally, image classification was carried out to group brain images based on the absence or presence of a tumor. The trained models were evaluated using accuracy, precision, recall and F1score as the performance metrics. The results of the study demonstrated promising outcomes, achieving an accuracy score of 93% and a precision, recall and f1score ranging from 75% to 100% based on the specific type of tumor enlisted. This indicates that the developed CNN models, with the FCN and VGG16 architectures, effectively detect and segment brain tumors from MRI images. The findings of this study contribute to the field of medical image analysis and gives a foundation for further research and development in brain tumor diagnosis and treatment. The study recommends the use of more deep learning algorithms for the process of detecting brain tumors. © 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

On-chip meta-lens based Adaptive Integrated Photonic Imager

On-chip meta-lens based Adaptive Integrated Photonic Imager

引用

Conference on Lasers and Electro-Optics (CLEO)

作者： Jong Ryul Kim Heijun Jeong Tingyi Gu Quantum Science and Engineering program University of Delaware Newark DE USA Electrical and Computer Engineering University of Delaware Newark DE USA

We demonstrate single-drive adaptive on-chip meta-lens imager with optimized profile for doped silicon heater and metal heaters.

ISBN: (纸本)9798350369311

We demonstrate single-drive adaptive on-chip meta-lens imager with optimized profile for doped silicon heater and metal heaters.

关键词： Heating systems Metals Doping profiles Silicon System-on-chip Electro-optical waveguides Photonics

来源：评论

学校读者我要写书评

暂无评论

Textual Training for the Hassle-Free Removal of Unwanted Visual Data: Case Studies on OOD and Hateful Image Detection

arXiv

引用

arXiv 2024年

作者： Lee, Saehyung Mok, Jisoo Park, Sangha Shin, Yongho Jung, Dahuin Yoon, Sungroh Department of Electrical and Computer Engineering Seoul National University Korea Republic of Qualcomm Korea YH Seoul Korea Republic of School of Computer Science and Engineering Soongsil University Korea Republic of Interdisciplinary Program in Artificial Intelligence Seoul National University Korea Republic of

In our study, we explore methods for detecting unwanted content lurking in visual datasets. We provide a theoretical analysis demonstrating that a model capable of successfully partitioning visual data can be obtained using only textual data. Based on the analysis, we propose Hassle-Free Textual Training (HFTT), a streamlined method capable of acquiring detectors for unwanted visual content, using only synthetic textual data in conjunction with pre-trained vision-language models. HFTT features an innovative objective function that significantly reduces the necessity for human involvement in data annotation. Furthermore, HFTT employs a clever textual data synthesis method, effectively emulating the integration of unknown visual data distribution into the training process at no extra cost. The unique characteristics of HFTT extend its utility beyond traditional out-of-distribution detection, making it applicable to tasks that address more abstract concepts. We complement our analyses with experiments in out-of-distribution detection and hateful image detection. Our codes are available at https://***/Saehyung-Lee/HFTT © 2024, CC BY.

关键词： Data assimilation

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：