检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Pei, Zhiyuan Yan, Jianqi Yan, Jin Yang, Bailing Li, Ziyuan Zhang, Lin Liu, Xin Zhang, Yang School of Computer Science and Engineering Faculty of Innovation Engineering Macau University of Science and Technology 999078 China Macau Institute of Systems Engineering Faculty of Innovation Engineering Macau University of Science and Technology 999078 China Emerging Technology Innovation and Ventures HSBC Shenzhen518052 China School of Accounting and Finance Beijing Institute of Technology Zhuhai519088 China Department of Mathematics University of Manitoba WinnipegR3T 2N2 Canada

Recently, deep learning in stock prediction has become an important branch. Image-based methods show potential by capturing complex visual patterns and spatial correlations, offering advantages in interpretability over time series models. However, image-based approaches are more prone to overfitting, hindering robust predictive performance. To improve accuracy, this paper proposes a novel method, named Sequence-based Multi-scale Fusion Regression Convolutional Neural Network (SMSFR-CNN), for predicting stock price movements in the China A-share market. Firstly, the historical opening, highest, lowest, closing price, and turnover rate (OHLCT) of stocks are converted into images, separated by weekends, with time information to help the CNN learn the impact of different trading periods. To reduce overfitting, long sequences of stock features are decomposed into multiple time periods, and OHLCT images at different time scales are utilized as inputs, significantly reducing overfitting. Thirdly, in order to overcome the problem that classification labels lose information about the magnitude of stock price changes, we introduce regression labels to help the model capture more latent features of stock price fluctuations. By utilizing CNN to learn sequential features and combining them with image features, we improve the accuracy of stock trend prediction on the A-share market stock dataset. This approach reduces the search space for image features, stabilizes and accelerates the training process. Extensive comparative experiments on 4,454 A-share stocks show that the model achieves 61.15% positive predictive value and 63.37% negative predictive value for the next 5 days, resulting in a total profit of 165.09%. Copyright © 2024, The Authors. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

LWiHS: A Lightweight WiFi-enabled Human Sensing Using Feature Fusion Strategy

引用

IEEE Transactions on Instrumentation and Measurement 2025年 74卷

作者： Liu, Chuan Hao, Yanling Liu, Yue Zhang, Xingqi Wang, Xianchao Liu, Yuanwei Macao Polytechnic University Faculty of Applied Sciences 999078 China Chaohu University School of Computer and Artificial Intelligence HeFei238024 China University College Dublin School of Electrical and Electronic Engineering DublinD04 V1W8 Ireland Queen Mary University of London School of Electronic Engineering and Computer Science LondonE1 4NS United Kingdom University of Alberta Department of Electrical and Computer Engineering EdmontonABT6G 2H5 Canada The University of Hong Kong Department of Electrical and Electronic Engineering 999077 Hong Kong

Human sensing based on Wi-Fi Channel State Information (CSI) has attracted attention due to its non-intrusiveness and wide applications. However, due to its susceptibility to external environmental noise and interference, high-complexity deep learning (DL) algorithms are usually adopted to improve the sensing accuracy, which can hardly be deployed in edge devices with limited computational abilities. Building a high-precision, low-complexity human sensing system remains challenging. To improve the accuracy of CSI time series (TS) classification, we proposed a TS to image conversion method based on feature fusion, which is developed to increase the spatial structure information of the original data and expand the feature vector space. To build an efficient and lightweight feature extraction network, we designed a framework LWiHS, which is a lightweight universal feature extraction network used to extract the perceptual information containing both deep and shallow features in the images. To reduce the number of model parameters, we adopted channel pruning based on layer adaptive amplitude pruning (LAMP) scoring. LWiHS is lightweight while maintaining good feature extraction capabilities. Our proposed LWiHS outperforms other advanced algorithms in both complexity and sensing performance on four open-source datasets. © 1963-2012 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Control of an Environmental Spin Defect beyond the Coherence Limit of a Central Spin

引用

PRX Quantum 2024年第1期5卷 010321-010321页

作者： Alexander Ungar Paola Cappellaro Alexandre Cooper Won Kyu Calvin Sun Research Laboratory of Electronics Massachusetts Institute of Technology Cambridge Massachusetts 02139 USA Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology Cambridge Massachusetts 02139 USA Department of Nuclear Science and Engineering Massachusetts Institute of Technology Cambridge Massachusetts 02139 USA Department of Physics Massachusetts Institute of Technology Cambridge Massachusetts 02139 USA Institute for Quantum Computing University of Waterloo Waterloo Ontario N2L 3G1 Canada Department of Physics University of Illinois at Urbana-Champaign Illinois 61801 USA

Electronic spin defects in the environment of an optically active spin can be used to increase the size and hence the performance of solid-state quantum registers, especially for applications in quantum metrology and quantum communication. Previous works on multiqubit electronic spin registers in the environment of a nitrogen-vacancy (NV) center in diamond have only included spins directly coupled to the NV. As this direct coupling is limited by the central spin coherence time, it significantly restricts the maximum attainable size of the register. To address this problem, we present a scalable approach to increase the size of electronic spin registers. Our approach exploits a weakly coupled probe spin together with double-resonance control sequences to mediate the transfer of spin polarization between the central NV spin and an environmental spin that is not directly coupled to it. We experimentally realize this approach to demonstrate the detection and coherent control of an unknown electronic spin outside the coherence limit of a central NV. Our work paves the way for engineering larger quantum spin registers with the potential to advance nanoscale sensing, enable correlated noise spectroscopy for error correction, and facilitate the realization of spin-chain quantum wires for quantum communication.

关键词： Coherent control Crystal defects Hybrid quantum systems Quantum sensing Nitrogen vacancy centers in diamond Electron spin resonance Optically detected magnetic resonance

来源：评论

学校读者我要写书评

暂无评论

A Novel Method for Exploring the Store Sales Forecasting using Fuzzy Pruning LS-SVM Approach

A Novel Method for Exploring the Store Sales Forecasting usi...

引用

International Conference on Edge Computing and Applications (ICECAA)

作者： Mohd. Asif Gandhi Vusal Karimli Maharram G. Raja S.P. Sellapaandi Ketan Rathor Kamlesh Singh Department of Mechanical Engineering Anjuman-I-Islam's Kalsekar Technical Campus Panvel Maharashtra India Western Caspian University Azerbaijan/ 2Azerbaijan State University of Economics Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram Andhra Pradesh India Department of ECE PSNA College of Engineering and Technology Dindigul Tamilnadu India PMO Gyan Sys Inc Maharashtra India Department of Computer Science and Engineering Graphic Era Hill University Dehradun Campus Dehradun India

Intelligent robots, intelligent mobiles, intelligent stores, and so on are just a few of the areas where computer-aided ergonomics is being put to use. Convenience stores (CVS) are adapting to a new era of competition by offering a wider variety of products and services than ever before, such as daily fresh meals, a cafe, ticketing, and a grocery. Therefore, it is becoming increasingly difficult to estimate daily sales of’ fresh commodities due to the impact of both internal and external factors. In the long run, a trustworthy sales-forecasting system is going to be critical for enhancing corporate plans and gaining an edge over the competition. In today's internet age, data production has reached unprecedented levels, well beyond what any single human being can comprehend. This has led to the development of a plethora of machine learning methods. In this proposed approach various machine learning methods are explored for predicting store's sales and evaluate them to find the one that works best for the specific scenario. Training times are reduced and data quality is enhanced with the help of Normalization in the proposed approach. K-Means is a popular feature selection clustering algorithm. Fuzzy Pruning LS-SVM is used in the suggested method for training the model. The proposed model has superior performance on SVM and CNN.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Gold-Price Forecasting Method Using Long Short-Term Memory and the Association Rule

引用

Journal of Mobile Multimedia 2023年第1期19卷 165-186页

作者： Boongasame, Laor Viriyaphol, Piboonlit Tassanavipas, Kriangkrai Temdee, Punnarumol Department of Mathematics Faculty of Science King Mongkut’s Institute of Technology Ladkrabang Bangkok 10520 Thailand Business Innovation and Investment Laboratory: B2I-Lab Faculty of Science King Mongkut’s Institute of Technology Ladkrabang Bangkok 10520 Thailand Gold Research Center Gold Traders Association Bangkok Thailand Faculty of Engineering and Technology Panyapiwat Institute of Management Nonthaburi 11120 Thailand Computer and Communication Engineering for Capacity Building Research Center School of Information Technology Mae Fah Luang University Chiang Rai 57100 Thailand

Since gold prices influence international economic and monetary systems, numerous studies have been conducted to forecast gold prices. Nonetheless, studies employing the linear relationship method usually fail to explain the change in the pattern of the gold price. This study introduces a new paradigm that incorporates association rules and long short-term memory (LSTM) as a nonlinear-based method. For simulation, the proposed method was analyzed with data from Yahoo Finance from January 2010 to December 2020. The association rule was used to choose features relevant to the gold spot (GS) in the US Dollar Index (DXY). The LSTM forecast the gold price with a range of hyperparameter settings. The simulation results showed that the proposed method—the LSTM with GS and DXY, or LSTM-GS-DXY—resulted in low mean absolute percentage error (MAPE) metrics. In addition, the proposed LSTM-GS-DXY system outperformed the simple moving average (SMA), weight moving average (WMA), exponential moving average (EMA), and auto-regressive integrated moving average (ARIMA). © 2022 River Publishers.

关键词： artificial neural network association rule gold forecasting LSTM

来源：评论

学校读者我要写书评

暂无评论

Direct measurement of DNA bending by quantum magnetic imaging of a nanomechanical torque balance

引用

Physical Review Applied 2024年第6期22卷 064044-064044页

作者： Zeeshawn Kazi Isaac M. Shelby Ruhee Nirodi Joseph Turnbull Hideyuki Watanabe Kohei M. Itoh Paul A. Wiggins Kai-Mei C. Fu Department of Physics University of Washington Seattle Washington 98105 USA Present address: Department of Electrical and Computer Engineering Princeton University Princeton New Jersey 08540 USA. National Institute of Advanced Industrial Science and Technology Tsukuba Central 2 1-1-1 Umezono Tsukuba Ibaraki 305-8568 Japan School of Fundamental Science and Technology Keio University 3-14-1 Hiyoshi Kohoku-ku Yokohama 223-8522 Japan Department of Bioengineering University of Washington Seattle Washington 98105 USA Department of Electrical and Computer Engineering University of Washington Seattle Washington 98105 USA Physical Sciences Division Pacific Northwest National Laboratory Richland Washington 99354 USA

DNA flexibility is a key determinant of biological function, from nucleosome positioning to transcriptional regulation, motivating a direct measurement of the bend-torque response of individual DNA molecules. In this work, DNA bending is detected with the use of a nanomechanical torque balance formed by the tethering of a ferromagnetic nanoparticle probe by an individual DNA molecule to a diamond magnetic field imager. The torque exerted by the DNA in response to bending caused by an applied magnetic torque is measured by wide-field imaging of quantum defects near the surface of the diamond. Qualitative measurements of differences in DNA biomechanical binding configuration are demonstrated, and as a proof of principle, a quantitative measurement of the bend response is made for individual DNA molecules. This quantum-enabled measurement approach could be applied to characterize the bend response of biophysically relevant short DNA molecules as well as the sequence dependence of DNA bending energy.

关键词： Molecules

来源：评论

学校读者我要写书评

暂无评论

Network Slicing with MEC and Deep Reinforcement Learning for the Internet of Vehicles

arXiv

引用

arXiv 2022年

作者： Mlika, Zoubeir Cherkaoui, Soumaya Faculty of Engineering Department of Electrical and Computer Science Engineering University of Sherbrooke SherbrookeQCJ1K 2R1 Canada

The interconnection of vehicles in the future fifth generation (5G) wireless ecosystem forms the so-called Internet of vehicles (IoV). IoV offers new kinds of applications requiring delay-sensitive, compute-intensive and bandwidth-hungry services. Mobile edge computing (MEC) and network slicing (NS) are two of the key enabler technologies in 5G networks that can be used to optimize the allocation of the network resources and guarantee the diverse requirements of IoV applications. As traditional model-based optimization techniques generally end up with NP-hard and strongly non-convex and non-linear mathematical programming formulations, in this paper, we introduce a model-free approach based on deep reinforcement learning (DRL) to solve the resource allocation problem in MEC-enabled IoV network based on network slicing. Furthermore, the solution uses non-orthogonal multiple access (NOMA) to enable a better exploitation of the scarce channel resources. The considered problem addresses jointly the channel and power allocation, the slice selection and the vehicles selection (vehicles grouping). We model the problem as a single-agent Markov decision process. Then, we solve it using DRL using the well-known DQL algorithm. We show that our approach is robust and effective under different network conditions compared to benchmark solutions. Copyright © 2022, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Bright-dark pulses in coupled ring lasers

Bright-dark pulses in coupled ring lasers

引用

CLEO: Fundamental science, CLEO:FS 2024 - Part of Conference on Lasers and Electro-Optics, CLEO 2024

作者： Letsou, Theodore P. Kazakov, Dmitry Ratra, Pawan Columbo, Lorenzo L. Cin, Sandro Dal Opacak, Nikola Piccardo, Marco Schwarz, Benedikt Capasso, Federico Harvard John A. Paulson School of Engineering and Applied Sciences Harvard University CambridgeMA02138 United States Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology CambridgeMA02139 United States Department of Electrical and Electronic Engineering Imperial College London Exhibition Rd South Kensington LondonSW7 2BX United Kingdom Dipartimento di Elettronica e Telecomunicazioni Politecnico di Torino Torino10129 Italy Institute of Solid State Electronics TU Wien Vienna1040 Austria Department of Physics Instituto Superior Técnico Universidade de Lisboa Lisbon1049-001 Portugal

Coupling semiconductor laser together unlocks new optical states unstable in uncoupled lasers. Here, we present one such state which manifests itself as a pair of bright and dark optical pulses. © 2024 The Author... 详细信息

ISBN: (纸本)9781957171395

关键词： Ring lasers

来源：评论

学校读者我要写书评

暂无评论

Total Variation Constrained Non-Negative Matrix Factorization for Medical Image Registration

引用

IEEE/CAA Journal of Automatica Sinica 2021年第5期8卷 1025-1037页

作者： Chengcai Leng Hai Zhang Guorong Cai Zhen Chen Anup Basu the School of Mathematics Northwest UniversityXi’an 710127 the Institute of Automation Chinese Academy of SciencesBeijing 100190China the Department of Computing Science University of AlbertaEdmontonAB T6G 2E8Canada the College of Computer Engineering Jimei UniversityXiamen 361021China the School of Measuring and Optical Engineering Nanchang Hangkong UniversityNanchang 330063China

This paper presents a novel medical image registration algorithm named total variation constrained graphregularization for non-negative matrix factorization(TV-GNMF).The method utilizes non-negative matrix factorization by total variation constraint and graph *** main contributions of our work are the ***,total variation is incorporated into NMF to control the diffusion *** purpose is to denoise in smooth regions and preserve features or details of the data in edge regions by using a diffusion coefficient based on gradient ***,we add graph regularization into NMF to reveal intrinsic geometry and structure information of features to enhance the discrimination ***,the multiplicative update rules and proof of convergence of the TV-GNMF algorithm are *** conducted on datasets show that the proposed TV-GNMF method outperforms other state-of-the-art algorithms.

关键词： Data clustering dimension reduction image registration non-negative matrix factorization(NMF) total variation(TV)

来源：评论

学校读者我要写书评

暂无评论

Bright-dark pulses in coupled ring lasers

Bright-dark pulses in coupled ring lasers

引用

2024 Conference on Lasers and Electro-Optics, CLEO 2024

作者： Letsou, Theodore P. Kazakov, Dmitry Ratra, Pawan Columbo, Lorenzo L. Dal Cin, Sandro Opačak, Nikola Piccardo, Marco Schwarz, Benedikt Capasso, Federico Harvard John A. Paulson School of Engineering and Applied Sciences Harvard University CambridgeMA02138 United States Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology CambridgeMA02139 United States Department of Electrical and Electronic Engineering Imperial College London Exhibition Rd South Kensington LondonSW7 2BX United Kingdom Dipartimento di Elettronica e Telecomunicazioni Politecnico di Torino Torino10129 Italy Institute of Solid State Electronics TU Wien Vienna1040 Austria Department of Physics Instituto Superior Técnico Universidade de Lisboa Lisbon1049-001 Portugal

ISBN: (纸本)9781957171395

关键词： Ring lasers

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：