检索结果-内蒙古大学图书馆

Text Extraction with Optimal Bi-LSTM

computers, Materials & Continua 2023年第9期76卷 3549-3567页

作者： Bahera H.Nayef Siti Norul Huda Sheikh Abdullah Rossilawati Sulaiman Ashwaq Mukred Saeed Computer Techniques Engineering Department Ibn Khaldun University CollegeBaghdad10011Iraq Faculty of Information Science and Technology Universiti Kebangsaan MalaysiaBangiSelangor43600Malaysia School of Electrical Engineering and Artificial Intelligence Xiamen University MalaysiaSepang43900Malaysia

Text extraction from images using the traditional techniques of image collecting,and pattern recognition using machine learning consume time due to the amount of extracted features from the *** Neural Networks introduce effective solutions to extract text features from images using a few techniques and the ability to train large datasets of images with significant *** study proposes using Dual Maxpooling and concatenating convolution Neural Networks(CNN)layers with the activation functions Relu and the Optimized Leaky Relu(OLRelu).The proposed method works by dividing the word image into slices that contain *** pass them to deep learning layers to extract feature maps and reform the predicted *** Short Memory(BiLSTM)layers extractmore compelling features and link the time sequence fromforward and backward directions during the training *** Connectionist Temporal Classification(CTC)function calcifies the training and validation loss *** addition to decoding the extracted feature to reform characters again and linking them according to their time *** proposed model performance is evaluated using training and validation loss errors on the Mjsynth and Integrated Argument Mining Tasks(IAM)*** result of IAM was 2.09%for the average loss errors with the proposed dualMaxpooling and *** the Mjsynth dataset,the best validation loss rate shrunk to 2.2%by applying concatenating CNN layers,and Relu.

关键词： Deep neural network text features dual max-pooling concatenating convolution neural networks bidirectional long short memory text connector characteristics

来源：评论

学校读者我要写书评

暂无评论

ProTEA: Programmable Transformer Encoder Acceleration on FPGA

ProTEA: Programmable Transformer Encoder Acceleration on FPG...

引用

High Performance Computing, Networking, Storage and Analysis, SC-W: Workshops of the International Conference for

作者： Ehsan Kabir Jason D. Bakos David Andrews Miaoqing Huang Department of Electrical Engineering and Computer Science University of Arkansas Fayetteville USA Department of Computer Science and Engineering University of South Carolina USA

ISBN: (数字)9798350355543

ISBN: (纸本)9798350355550

Transformer neural networks (TNN) have been widely utilized on a diverse range of applications, including natural language processing (NLP), machine translation, and computer vision (CV). Their widespread adoption has been primarily driven by the exceptional performance of their multi-head self-attention block used to extract key features from sequential data. The multi-head self-attention block is followed by feedforward neural networks, which play a crucial role in introducing non-linearity to assist the model in learning complex patterns. Despite the popularity of TNNs, there has been limited numbers of hardware accelerators targeting these two critical blocks. Most prior works have concentrated on sparse architectures that are not flexible for popular TNN variants. This paper introduces ProTEA, a runtime programmable accelerator tailored for the dense computations of most of state-of-the-art transformer encoders. ProTEA is designed to reduce latency by maximizing parallelism. We introduce an efficient tiling of large matrices that can distribute memory and computing resources across different hardware components within the FPGA. We provide run time evaluations of ProTEA on a Xilinx Alveo U55C high-performance data center accelerator card. Experimental results demonstrate that ProTEA can host a wide range of popular transformer networks and achieve near optimal performance with a tile size of 64 in the multi-head self-attention block and 6 in the feedforward networks block when configured with 8 parallel attention heads, 12 layers, and an embedding dimension of 768 on the U55C. Comparative results are provided showing ProTEA is 2.5× faster than an NVIDIA Titan XP GPU. Results also show that it achieves 1.3 – 2.8× speed up compared with current state-of-the-art custom designed FPGA accelerators.

关键词： Runtime High performance computing Memory management Parallel processing Transformers Feature extraction Magnetic heads Sparse matrices Machine translation Field programmable gate arrays

来源：评论

学校读者我要写书评

暂无评论

Digital Twin-Assisted Space-Air-Ground Integrated Networks for Vehicular Edge Computing

引用

IEEE Journal on Selected Topics in Signal Processing 2024年第1期18卷 66-82页

作者： Paul, Anal Singh, Keshav Nguyen, Minh-Hien T. Pan, Cunhua Li, Chih-Peng National Sun Yat-sen University Institute of Communications Engineering Kaohsiung80424 Taiwan Queen's University Belfast School of Electronics Electrical Engineering and Computer Science BelfastBT71NN United Kingdom Southeast University National Mobile Communications Research Laboratory Nanjing211111 China

In this paper, we present a framework that integrates digital twin (DT) technology into space-air-ground integrated networks (SAGINs) to enhance vehicular edge computing (VEC). Our objective is to efficiently offload tasks in ultra-reliable low-latency communications (URLLC)-enabled vehicular networks, focusing on minimizing overall latency for requested tasks by reducing transmission time for task offloading and edge processing requirements. The proposed framework leverages DT-assisted SAGINs to minimize task offloading latency, expand network coverage, and reduce energy consumption. Key components of our framework include partial task offloading, distributed edge computing, latency modeling, energy consumption analysis, mobility, and channel modeling. We formulate a non-convex optimization problem considering various network constraints to achieve the system objective. To solve this optimization problem, we develop a novel multi-agent deep reinforcement learning (DRL) algorithm, enabling intelligent decision-making by individual agents. Through extensive simulations, we validate the effectiveness of our proposed system in advancing VEC by integrating DT technology into SAGINs. © 2007-2012 IEEE.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Expanding chiral metamaterials for retrieving fingerprints via vibrational circular dichroism

引用

Light(science & Applications) 2023年第7期12卷 1401-1414页

作者： Cheng Xu Zhihao Ren Hong Zhou Jingkai Zhou Chong Pei Ho Nan Wang Chengkuo Lee Department of Electrical and Computer Engineering National University of SingaporeSingapore 117583Singapore Center for Inteligent Sensors and MEMS(CISM) National University of SingaporeSingapore 117608Singapore institute of Microelectronics(IME) Agency for ScienceTechnology and Research(A*STAR)Singapore 138634Singapore NUS Graduate School for Integrative Science and Engineering Program(ISEP) National University of SingaporeSingapore 117456Singapore

Circular dichroism(CD)spectroscopy has been widely demonstrated for detecting chiral ***,the determination of chiral mixtures with various concentrations and enantiomeric ratios can be a challenging *** solve this problem,we report an enhanced vibrational circular dichroism(VCD)sensing platform based on plasmonic chiral metamaterials,which presents a 6-magnitude signal enhancement with a selectivity of chiral *** by coupled-mode theory,we leverage both in-plane and out-of-plane symmetry-breaking structures for chiral metamaterial design enabled by a two-step lithography process,which increases the near-field coupling strengths and varies the ratio between absorption and radiation loss,resulting in improved chiral light-matter interaction and enhanced molecular VCD ***,we demonstrate the thin-film sensing process of BSA andβ-lactoglobulin proteins,which contain secondary structures a-helix andβ-sheet and achieve a limit of detection down to zeptomole ***,we also,for the first time,explore the potential of enhanced VCD spectroscopy by demonstrating a selective sensing process of chiral mixtures,where the mixing ratio can be successfully differentiated with our proposed chiral *** findings improve the sensing signal of molecules and expand the extractable information,paving the way toward label-free,compact,small-volume chiral molecule detection for stereochemical and clinical diagnosisapplications.

关键词： chiral vibrational circular

来源：评论

学校读者我要写书评

暂无评论

Improved SINR m-Coverage Probability in 6G Networks: Unveiling the Sample Point Saturation Phenomenon in Urban and Suburban Environments

Improved SINR m-Coverage Probability in 6G Networks: Unveili...

引用

2024 International Conference on science, engineering and Business for Driving Sustainable Development Goals, SEB4SDG 2024

作者： Ajaegbu, Chigozirim Adebiyi, Abayomi A. Kanu, R.U. Babcock University Department of Computer Science Ogun State Ilishan-Remo Nigeria Durban University of Technology Department of Electrical Power Engineering Durban South Africa Babcock University Department of Basic Science Ogun State Ilishan-Remo Nigeria

ISBN: (纸本)9798350358155

This study looks at the influence of sample points on SINR-based m-coverage probability in Urban and Suburban environments within the context of 6G networks. SINR is a crucial factor impacting network coverage and reliability. While it is commonly assumed that increasing sample points enhances SINR coverage probability, the relationship between sample points and coverage probability remains intricate and not well-understood. The main objective of this study was to determine the saturation point at which additional sample points only marginally improve network performance. To achieve this, advanced simulations were conducted using the Poisson point process to spatially distribute nodes in single-tier and multi-tier networking scenarios. Existing mathematical models of path-loss, interference, and coverage probability were extended, taking into account other wireless phenomena present in urban and suburban environments. The analysis indicates a positive correlation between coverage probability and increasing sample points, as expected for improved network performance. However, intriguingly, both Urban and Suburban environments exhibit a saturation point, challenging the conventional belief of continuous improvements with more sample points. The optimization of sample point numbers becomes crucial to strike the right balance between accuracy and computational efficiency in designing 6G networks. These findings offer valuable insights for network planning, ultimately enhancing the overall performance and reliability of 6G networks in dynamic environments. © 2024 IEEE.

关键词： Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Current Injection Based Quasi-Static Time Series Load Flow Algorithm for Distribution System with Multiple Distributed Energy Resources

Current Injection Based Quasi-Static Time Series Load Flow A...

引用

2023 IEEE International Conference on Energy Technologies for Future Grids, ETFG 2023

作者： Suresh, Arun Murari, Krishna Kamalasadan, Sukumar University of North Carolina at Charlotte Department of Electrical Engineering CharlotteNC28223 United States The University of Toledo Electrical Engineering and Computer Science Department ToledoOH43606 United States

ISBN: (纸本)9781665471640

In this paper, a current injection-based QSTS load flow approach has been developed to simulate and analyze the interactions between Distributed Energy Resources (DERs) and voltage-regulating devices over a given time. The novelty is that the paper proposes a comprehensive modeling approach that takes into account the intricacies of both voltage-regulating devices and DERs. By integrating these models into the QSTS simulation, the researchers can perform detailed analyses and simulations to evaluate the effects of DERs on control devices and assess the overall impact on the grid's stability and operation. The process involves modeling the voltage-regulating devices, such as the load tap changers and voltage regulators, in a way that accurately represents their physical characteristics and control strategies. This enables the simulation to mimic the real-world behavior of these devices under various conditions. The time series analysis has been successfully validated using a state-of-the-art QSTS solver, demonstrating that the developed approach is both efficient and accurate. © 2023 IEEE.

关键词： Distributed Energy Resources Grid Modernization Injected Current Sensitivity (ICS) Load Tap Changer (LTC) Multi-Phase Load Flow Unbalanced Distribution System Voltage Regulator

来源：评论

学校读者我要写书评

暂无评论

Graphene oxide-coated microbottle resonators for relative humidity sensing

引用

Optoelectronics Letters 2024年第7期20卷 400-405页

作者： Huda Adnan Zain Malathy Batumalay Md Ashadi Md Johari Hazli Rafis Abdul Rahim Sulaiman Wadi Harun Department of Electrical Engineering Faculty of EngineeringUniversity of MalayaKuala Lumpur 50603Malaysia Faculty of Data Science and Information Technology INTI International UniversityNilai 71800Malaysia1 Faculty of Electrical and Electronic Engineering Technology Universiti Teknikal Malaysia MelakaMelaka 76100Malaysia Faculty of Electronic and Computer Engineering Universiti Teknikal Malaysia MelakaMelaka 76100Malaysia

Graphene oxide(GO)is a 2D coating material used to improve fiber optics sensors’response to relative *** resonators(MBRs)have garnered more attention as sensing media *** MBR with a 190μm diameter was coated with ***,tapered fiber light coupling was used to investigate the relative humidity sensing performance in the range of 35—70%RH at 25℃.The MBR showed a higher Q factor before and after GO *** sensitivity of 0.115 dB/%RH was recorded with the 190μm GO-coated MBR sample compared to a sensitivity of 0.022 dB/%RH for the uncoated MBR *** results show that the MBR can be used in fiber optic sensing applications for environmental sensing.

关键词： humidity oxide bottle

来源：评论

学校读者我要写书评

暂无评论

Finite-time robust performance improvement for non-linear systems in the presence of input non-linearity and external disturbance

引用

IET Control Theory and Applications 2023年第6期17卷 672-682页

作者： Wang, Haoping Ghaffari, Valiollah Mobayen, Saleh Bartoszewicz, Andrzej Fekih, Afef Assawinchaichote, Wudhichai School of Automation Nanjing University of Science and Technology Nanjing China Department of Electrical Engineering Persian Gulf University Bushehr Iran Graduate School of Intelligent Data Science National Yunlin University of Science and Technology Yunlin Douliou Taiwan Institute of Automatic Control Lodz University of Technology Lodz Poland Department of Electrical and Computer Engineering University of Louisiana at Lafayette LafayetteLA United States Department of Electronic and Telecommunication Engineering Faculty of Engineering King Mongkut's University of Technology Thonburi Bangkok Thailand

The main focus of this research is on improving the performance of dynamic systems with actuator non-linearities and time-varying disturbances. To this end, using the concept of finite-time stability, a novel observer is presented to estimate the disturbances in systems with input non-linearities. Then, introducing an innovative sliding manifold, a robust observer-based technique is derived to guarantee the finite-time stability of the sliding surface. Hence, the closed-loop system would be stable in the presence of hard non-linearities and time-varying disturbances. The performance of the proposed approach was assessed in using a simulation study of two numerical examples. The obtained results and comparison with a conventional method confirmed the benefits of the suggested approach. © 2022 The Authors. IET Control Theory & Applications published by John Wiley & Sons Ltd on behalf of The Institution of engineering and Technology.

关键词： Closed loop systems

来源：评论

学校读者我要写书评

暂无评论

LSTM Based Neural Network Model for Anomaly Event Detection in Care-Independent Smart Homes

引用

computer Modeling in engineering & sciences 2024年第9期140卷 2689-2706页

作者： Brij B.Gupta Akshat Gaurav Razaz Waheeb Attar Varsha Arya Ahmed Alhomoud Kwok Tai Chui Department of Computer Science and Information Engineering Asia UniversityTaichung413TaiwanChina Symbiosis Centre for Information Technology(SCIT) Symbiosis International UniversityPune411057India Center for Interdisciplinary Research University of Petroleum and Energy Studies(UPES)Dehradun248007India Computer Engineering Ronin InstituteMontclairNJ 07043USA Management Department College of Business AdministrationPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Business Administration Asia UniversityTaichung413TaiwanChina Department of Electrical and Computer Engineering Lebanese American UniversityBeirut1102Lebanon Department of Computer Sciences Faculty of Computing and Information TechnologyNorthern Border UniversityRafha91911Saudi Arabia School of Science and Technology Hong Kong Metropolitan University(HKMU)Hong KongChina

This study introduces a long-short-term memory(LSTM)-based neural network model developed for detecting anomaly events in care-independent smart homes,focusing on the critical application of elderly fall *** balances the dataset using the Synthetic Minority Over-sampling Technique(SMOTE),effectively neutralizing bias to address the challenge of unbalanced datasets prevalent in time-series classification *** proposed LSTM model is trained on the enriched dataset,capturing the temporal dependencies essential for anomaly *** model demonstrated a significant improvement in anomaly detection,with an accuracy of 84%.The results,detailed in the comprehensive classification and confusion matrices,showed the model’s proficiency in distinguishing between normal activities and *** study contributes to the advancement of smart home safety,presenting a robust framework for real-time anomaly monitoring.

关键词： LSTM neural networks anomaly detection smart home health-care elderly fall prevention

来源：评论

学校读者我要写书评

暂无评论

Strumming in the Metaverse: A Deep-Learning-Enabled Virtual Air Guitar System in VR with Enhanced Chord Recognition and Simulated Pedal Effects

引用

IEEE Transactions on Multimedia 2025年

作者： Hsieh, Yi-Zeng Lin, Ji-Jie Su, Mu-Chun Lin, Wei-Jen National Taiwan University of Science and Technology Department of Electrical Engineering Taiwan National Central University Department of Computer Science and Information Engineering Taiwan

Virtual reality (VR) is increasingly capable and inexpensive, and VR devices have become indispensable in many domains, such as gaming, videoconferencing, education, and healthcare. VR has also been applied to music performance and learning. Virtual instruments, such as virtual pianos and drums, free users from the need to own physical forms of these (often bulky and expensive) instruments. VR devices enable users to enjoy music anytime and anywhere without constraints. Virtual concerts, including spatial audio simulations and reconstructions of historical performances, are becoming increasingly common. Previous studies have primarily examined virtual guitars in nonVR environments and air guitar chord recognition. However, systematic research on virtual air guitar systems in VR remains scarce. Virtual guitar games that are available on the market cannot recognize hand gestures accurately and thus cannot accurately identify the strumming patterns and chords played by the player. To overcome this problem, we propose a VRbased virtual air guitar system that can recognize 30 chords and various strumming techniques through deep learning and visual feedback. Employing a black-box approach, we combine WaveNet and FiLM to simulate electric guitar pedal effects with a knob difference loss mechanism, which simulates the turning of knobs on a guitar effects pedal, for enhanced accuracy. © 1999-2012 IEEE.

关键词： Knobs

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：