检索结果-内蒙古大学图书馆

61st ACM/IEEE Design Automation Conference, DAC 2024

作者： Shin, Dongjin Choi, Insu Yang, Joon-Sung Department of Electrical and Electronic Engineering Yonsei University Seoul Korea Republic of Department of Systems Semiconductor Engineering Yonsei University Seoul Korea Republic of BK21 Graduate Program in Intelligent Semiconductor Technology Yonsei University Seoul Korea Republic of

ISBN: (纸本)9798400706011

Vision Transformers have demonstrated remarkable performance in various vision tasks. However, general-purpose processors, such as CPUs and GPUs, face challenges in efficiently handling the inference of Vision Transformers. To address the issue, prior works have focused on accelerating only attention due to its high computational cost in NLP Transformers. In contrast, Vision Transformers demonstrate a higher computational cost due to linear modules such as linear transformation, linear projection and Feed-Forward Network (FFN), compared to attention. In this paper, we present ViT-slice, an algorithm-architecture co-design that enhances end-to-end performance and energy efficiency by optimizing not only attention but also linear modules. At the algorithm level, we propose bit-slice compression that avoids storing the redundant most significant bits (MSBs). Additionally, we present bit-slice dot product with early skip to efficiently compute the dot product using bit-sliced data. To enable early skip during the dot product computation, we leverage a trainable threshold. On the hardware level, we introduce a specialized bit-slice dot product unit (BSDPU) to efficiently process the bit-slice dot product with early skip algorithm. Additionally, we present a bit-slice encoder and decoder for on-chip bit-slice compression. ViT-slice achieves 244×, 35.3×, 16.8×, 10.4×, 5.0× end-to-end speedup over Xeon CPU, EdgeGPU, TITAN Xp GPU, Sanger accelerator and ViTCoD accelerator, respectively. © 2024 Copyright held by the owner/author(s).

关键词： Linear transformations

来源：评论

学校读者我要写书评

暂无评论

Actively Controllable Beam Steering Optical Wireless Communication (OWC) Using Integrated Optical Phased Array (OPA)

引用

Journal of Lightwave Technology 2023年第4期41卷 1122-1128页

作者： Chow, Chi-Wai Chang, You-Chia Kuo, Sheng-I Kuo, Pin-Cheng Wang, Ju-Wei Jian, Yin-He Ahmad, Zohauddin Fu, Po-Han Shi, Jin-Wei Huang, Ding-Wei Hung, Tun-Yao Lin, Yuan-Zeng Yeh, Chien-Hung Liu, Yang National Yang Ming Chiao Tung University Department of Photonics and Graduate Institute of Electro-Optical Engineering College of Electrical and Computer Engineering Hsinchu30010 Taiwan National Chiao Tung University Hsinchu30010 Taiwan National Central University Department of Electrical Engineering Taoyuan320 Taiwan National Taiwan University Department of Electrical Engineering Taipei10617 Taiwan Feng Chia University Department of Photonics Seatwen Taichung40724 Taiwan Philips Electronics Ltd. Shatin Hong Kong

We put forward and present a demonstration of an actively controlled optical beam steering optical wireless communication (OWC) system based on an integrated actively steerable optical phased array (OPA). We theoretically and experimentally analyze the emitted optical beam full-width-half-maximum (FWHM) divergence angle and field-of-view (FOV) of the proposed integrated actively steerable OPA. Experimental results show that the beam steering can be achieved over a range of 17° with a minimum optical beam FWHM divergence angle of 1.49°. Besides, the integrated OPA chip design, beam forming optimization, packaging, as well as temperature stabilization are also discussed. Genetic Algorithm (GA) is utilized to optimize the applied voltages for the 30 phase shifters to produce low-divergence optical beams in different directions. A proof-of-concept bit-error-rate (BER) measurement using 10 Gbit/s on-off-keying (OOK) signal is also carried out, and the beam steered optical signal satisfying the pre-forward error correction BER limit (pre-FEC BER = 3.8 × 10-3) is achieved. © 1983-2012 IEEE.

关键词： Bit error rate

来源：评论

学校读者我要写书评

暂无评论

Influence of Outer Oxide Charges on the Electrostatics of Metal-Insulator-Semiconductor Tunnel Diode

Influence of Outer Oxide Charges on the Electrostatics of Me...

引用

243rd ECS Meeting

作者： Chen, Kung-Chu Lin, Kuan-Wun Hwu, Jenn-Gwo Graduate Institute of Electronics Engineering National Taiwan University Taipei10617 Taiwan Department of Electrical Engineering National Taiwan University Taipei10617 Taiwan

ISBN: (纸本)9781607685395

In this work, the impact of outer oxide charges on the electrostatics of metal-insulator-semiconductor tunnel diodes (MISTD) is discussed. The existence of outer oxide charges will significantly affect the critical voltage V c of MISTD in the strong inversion region. At the bias voltage of V V c, the MISTD goes to deep depletion. V c is an important boundary for the electrostatics behavior of MISTD. We propose a model, considering the existing outer oxide charges, to calculate V c and compare the calculated results with V c extracted from our devices. V c of our devices is extracted by measuring high-frequency capacitance-voltage (HFCV) at 300 kHz. It is found that the model is able to fit well with the experimental results when the amount of outer oxide charges is in the magnitude of 2.5×1011 cm-2 for our devices. The model is fundamental but helpful for analyzing and designing a MISTD. © 2023 ECS-The Electrochemical Society.

关键词： Metal insulator boundaries

来源：评论

学校读者我要写书评

暂无评论

Low Polarization Loss of Long Endurance on Scavenged Ru-Based Electrode Ferroelectric Hf0.5Zr0.5O2by Optimizing TiNxInterfacial Capping Layer and Its Fatigue Mechanism

IEEE Electron Device Letters

引用

IEEE Electron Device Letters 2024年第4期45卷 673-676页

作者： Senapati, Asim Lou, Zhao-Feng Lee, Jia-Yang Chen, Yi-Pin Huang, Shih-Yin Maikap, Siddheswar Lee, Min-Hung Liu, Chee-Wee Department of Electronic Engineering Guishan33302 Taiwan National Taiwan University Program for Semiconductor Devices Materials and Hetero-Integration Graduate School of Advanced Technology Taipei106319 Taiwan School of Traditional Chinese Medicine College of Medicine Taoyuan33302 Taiwan Department of Obstetrics and Gynecology Anle 204 Taiwan Chang Gung University College of Medicine Taoyuan33302 Taiwan The Graduate School of Advanced Technology Department of Electrical Engineering Taipei10617 Taiwan

Double remnant polarization (2Pr values are increased significantly from 17.1μC/cm2 to 39.9μC/cm2 by reducing the TiNx interfacial capping layer (ICL) thickness from 3 nm to 1 nm in the Ru/TiNx/Hf0.5 Zr0.5O2(HZO)/TiN structure owing to lower monoclinic (m) phase with respect to orthorhombic (o) plus rhombohedral (r) phases. These phases are observed by geometrical phase analysis (GPA) of high-resolution transmission electron microscope (HRTEM) images. An optimized 2 nm TiNx ICL ferroelectric memory shows lowest fatigue and mechanism is higher m-phase starting to grow from the HZO/TiN BE interface, which is evidenced in the HRTEM image after long endurance of 1011 cycles under high ±4 MV/cm, 0.5μs (remaining higher 2Pr value of 20μC/cm2). © 1980-2012 IEEE.

关键词： Electrodes

来源：评论

学校读者我要写书评

暂无评论

A pathology-based machine learning method to assist in epithelial dysplasia diagnosis

引用

Research on Biomedical engineering 2022年第3期38卷 989-1002页

作者： da Rocha, Karoline Bermudez, José C. M. Rivero, Elena R. C. Costa, Márcio H. Graduate Program in Electrical Engineering Federal University of Santa Catarina Florianópolis Brazil Department of Pathology Federal University of Santa Catarina Florianópolis Brazil

Epithelial dysplasia (ED) is one of the most important factors in detecting the progression of an oral tissue alteration towards carcinoma. Its early detection is instrumental in avoiding the progression of the tumor. A major difficulty for detecting ED is the recognized variability of pathologist assessments. This study proposes a new method that leverages the pathologist expertise to design a simple and efficient classification system to support the detection of dysplastic epithelia. We employ a multilayer artificial neural network (MLP-ANN) and defining the regions of the epithelium to be assessed based on the knowledge of the pathologist. The performance of the proposed solution was statistically evaluated. The implemented MLP-ANN presented an average accuracy of 87 % , with a variability much inferior to that obtained from three trained evaluators. Moreover, the proposed solution led to results which are very close to those obtained using a convolutional neural network (CNN) implemented by transfer learning, with 100 times less computational complexity. In conclusion, our results show that a simple neural network structure combined with the pathologist expertise can lead to a performance equivalent to that of much more complex structures, which are routinely used in the literature. © 2022, The Author(s), under exclusive licence to The Brazilian Society of Biomedical engineering.

关键词： Computer aided diagnosis

来源：评论

学校读者我要写书评

暂无评论

Impact of Renewable Energy on the Philippine Electricity Spot Prices: An Ex-Post Analysis Using Multiple Linear Regression

Impact of Renewable Energy on the Philippine Electricity Spo...

引用

2023 IEEE International Conference on electrical, Computer and Energy Technologies, ICECET 2023

作者： Marzo Barcenas, Mark Reden Ang, Gerard Ladignon, Christopher Musni School of Graduate Studies Mapúa University Manila Philippines School of Electrical Electronics and Computer Engineering Mapúa University Manila Philippines Nueva Ecija University of Science and Technology Electrical Engineering Department Cabanatuan City Philippines

ISBN: (纸本)9798350327816

The increasing integration of renewable energy (RE) sources impacts the spot price in the electricity market. Decentralized markets observe electricity spot price elasticity in response to the additional supply from the RE sources. This study focused on the empirical investigation of the impact of solar PV, wind, and biomass power generation in the Philippine Wholesale Electricity Spot Market (WESM) prices using multiple linear regression. STATA software was the main driver for statistical modeling and testing. To ensure the result's accuracy and avoid spurious analysis, the hourly market data was initially subjected to data cleaning and evaluation. The heteroskedasticity and serial correlation detected in the initial regression model were addressed using the Newey-West error estimation - the recommended robust technique for the mentioned concerns. The energy dispatch of different power plant types significantly explains the 2019 Philippine electricity spot price variations, hence the model's reliability for the analysis. The proposed methodology may be adopted and found helpful in assessing the impacts of the rising RE grid integration in the electricity spot price. © 2023 IEEE.

关键词： decentralized market electricity spot price multiple linear regression analysis renewable energy sources

来源：评论

学校读者我要写书评

暂无评论

Auxiliary Classifier based Residual RNN for Image Captioning 30

Auxiliary Classifier based Residual RNN for Image Captioning

引用

30th European Signal Processing Conference, EUSIPCO 2022

作者： Çayli, Özkan Kiliç, Volkan Onan, Aytug Wang, Wenwu Electrical and Electronics Engineering Graduate Program Izmir Katip Çelebi University Turkey Department of Computer Engineering Izmir Katip Çelebi University Turkey University of Surrey United Kingdom

ISBN: (纸本)9789082797091

Image captioning aims to generate a description of visual contents with natural language automatically. This is useful in several potential applications, such as image understanding and virtual assistants. With recent advances in deep neural networks, natural and semantic text generation has been improved in image captioning. However, maintaining the gradient flow between neurons in consecutive layers becomes challenging as the network gets deeper. In this paper, we propose to integrate an auxiliary classifier in the residual recurrent neural network, which enables the gradient flow to reach the bottom layers for enhanced caption generation. Experiments on the MSCOCO and VizWiz datasets demonstrate the advantage of our proposed approach over the state-of-the-art approaches in several performance metrics. © 2022 European Signal Processing Conference, EUSIPCO. All rights reserved.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Automated Image Captioning with Multi-layer Gated Recurrent Unit 30

Automated Image Captioning with Multi-layer Gated Recurrent ...

引用

30th European Signal Processing Conference, EUSIPCO 2022

作者： Moral, Özge Taylan Kiliç, Volkan Onan, Aytug Wang, Wenwu Electrical and Electronics Engineering Graduate Program Izmir Katip Celebi University Turkey Department of Computer Engineering Izmir Katip Celebi University Turkey University of Surrey United Kingdom

ISBN: (纸本)9789082797091

Describing the semantic content of an image via natural language, known as image captioning, has recently attracted substantial interest in computer vision and language processing communities. Current image captioning approaches are mainly based on an encoder-decoder framework in which visual information is extracted by an image encoder and captions are generated by a text decoder, using convolution neural networks (CNN) and recurrent neural networks (RNN), respectively. Although this framework is promising for image captioning, it has limitations in utilizing the encoded visual information for generating grammatically and semantically correct captions in the RNN decoder. More specifically, the RNN decoder is ineffective in using the contextual information from the encoded data due to its limited ability in capturing long-term complex dependencies. Inspired by the advantage of gated recurrent unit (GRU), in this paper, we propose an extension of conventional RNN by introducing a multi-layer GRU that modulates the most relevant information inside the unit to enhance the semantic coherence of captions. Experimental results on the MSCOCO dataset show the superiority of our proposed approach over the state-of-the-art approaches in several performance metrics. © 2022 European Signal Processing Conference, EUSIPCO. All rights reserved.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

On Reliability Assessment of a Battery Energy Storage Systems Supporting PV Plants 8

On Reliability Assessment of a Battery Energy Storage System...

引用

8th Southern Power electronics Conference and the 17th Brazilian Power electronics Conference, SPEC / COBEP 2023

作者： Amorim, William Caires Silva Cupertino, Allan Fagner Mendes, Victor Flores De Sousa, Renata Oliveira De Barros, Rodrigo Cássio Pereira, Heverton Augusto Federal University of Minas Gerais Graduate Program in Electrical Engineering Belo Horizonte Brazil Federal University of Juz de Fora Department of Electrical Energy Juiz de Fora Brazil Federal University of Minas Gerais Department of Electrical Engineering Belo Horizonte Brazil Federal University of Tech. - Paraná Department of Electronics Curitiba Brazil Federal University of Recôncavo da Bahia Department of Electrical Engineering Cruz das Almas Brazil Federal University of Viçosa Department of Electrical Engineering Viçosa Brazil

ISBN: (纸本)9798350321128

Battery energy storage system (BESS) has been highlighted for its possibilities of performing ancillary services to the power system, such as voltage and frequency regulation, power quality, power smoothing, and peak shaving, among others. The BESS is very promising especially associated with renewable energies, such as photovoltaic (PV) and wind. Among some of these ancillary services, this work evaluates the battery lifetime and reliability. The proposed methodology includes the combined analysis of rainflow counting algorithm, Monte Carlo simulation, and nonlinear damage accumulation rule for battery reliability assessment. Monte Carlo simulation is used to approximate the battery reliability estimation of practical applications, by considering stochastic variations in the battery lifetime model. The case study is based on a 100 kW PV system, assessed using a one-year mission profile of solar irradiance and ambient temperature from Goiânla-Brazll associated with a mission profile of 100 kW industrial load. The PV plant is connected to a 440 V grid associated with a BESS that mitigates oscillations of 10% of PV nominal power per minute. The peak shaving service presented a decrease in the battery lifetime by approximately 11 % in relation to the deterministic battery lifetime analysis. On the other hand, the peak shaving presented a decrease in the battery lifetime by approximately 17.4 %. In addition, the pack-level analysis revealed a maximum reduction in the battery lifetime by approximately 30%, when compared to the conventional deterministic battery reliability estimation procedure. © 2023 IEEE.

关键词： Battery energy storage system mission profile Monte Carlo peak shaving power smoothing reliability

来源：评论

学校读者我要写书评

暂无评论

SliQSim: A Quantum Circuit Simulator and Solver for Probability and Statistics Queries 31th

SliQSim: A Quantum Circuit Simulator and Solver for Probabil...

引用

31st International Conference on Tools and Algorithms for the Construction and Analysis of Systems, TACAS 2025, which was held as part of the International Joint Conferences on Theory and Practice of Software, ETAPS 2025

作者： Chen, Tian-Fu Jiang, Jie-Hong R. Graduate School of Advanced Technology National Taiwan University Taipei Taiwan Graduate Institute of Electronics Engineering National Taiwan University Taipei Taiwan Department of Electrical Engineering National Taiwan University Taipei Taiwan Center for Quantum Science and Engineering National Taiwan University Taipei Taiwan Physics Division National Center for Theoretical Sciences Taipei Taiwan

ISBN: (纸本)9783031906596

SliQSim, originally developed as the first exact quantum circuit simulator, is extended in this paper to provide capabilities for the analysis and verification of quantum states. It provides an interface for users to specify interested quantum states for querying the exact probability or expectation value of a user-defined property. Case studies on three quantum algorithms show the unique capability of SliQSim benefiting exact quantum circuit analysis and verification, beyond the support by other tools. © The Author(s) 2025.

关键词： Quantum electronics

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：