检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Yi, Ziruo Xiao, Ting Ijeoma, Kaz-Onyeakazi Cheran, Ratnam Baweja, Yuvraj Nelson, Phillip Department of Computer Science & Engineering University of North Texas DentonTX76207 United States Department of Information Science University of North Texas DentonTX76207 United States Texas Academy of Math and Science DentonTX76201 United States

Building predictive models for companies often relies on inference using historical data of companies in the same industry sector. However, companies are similar across a variety of dimensions that should be leveraged in relevant prediction problems. This is particularly true for large, complex organizations which may not be well defined by a single industry and have no clear peers. To enable prediction using company information across a variety of dimensions, we create an embedding of company stocks, Stock2Vec, which can be easily added to any prediction model that applies to companies with associated stock prices. We describe the process of creating this rich vector representation from stock price fluctuations, and characterize what the dimensions represent. We then conduct comprehensive experiments to evaluate this embedding in applied machine learning problems in various business contexts. Our experiment results demonstrate that the four features in the Stock2Vec embedding can readily augment existing cross-company models and enhance cross-company predictions. Copyright © 2022, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

MetaUE: Model-based Meta-learning for Underwater Image Enhancement

arXiv

引用

arXiv 2023年

作者： Zhang, Zhenwei Yan, Haorui Tang, Ke Duan, Yuping Center for Applied Mathematics Tianjin University Tianjin300072 China The Guangdong Key Laboratory of Brain-Inspired Intelligent Computation Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China The Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Shenzhen518055 China

The challenges in recovering underwater images are the presence of diverse degradation factors and the lack of ground truth images. Although synthetic underwater image pairs can be used to overcome the problem of inadequately observing data, it may result in over-fitting and enhancement degradation. This paper proposes a model-based deep learning method for restoring clean images under various underwater scenarios, which exhibits good interpretability and generalization ability. More specifically, we build up a multi-variable convolutional neural network model to estimate the clean image, background light and transmission map, respectively. An efficient loss function is also designed to closely integrate the variables based on the underwater image model. The meta-learning strategy is used to obtain a pre-trained model on the synthetic underwater dataset, which contains different types of degradation to cover the various underwater environments. The pre-trained model is then fine-tuned on real underwater datasets to obtain a reliable underwater image enhancement model, called MetaUE. Numerical experiments demonstrate that the pre-trained model has good generalization ability, allowing it to remove the color degradation for various underwater attenuation images such as blue, green and yellow, etc. The fine-tuning makes the model able to adapt to different underwater datasets, the enhancement results of which outperform the state-of-the-art underwater image restoration methods. All our codes and data are available at https://***/Duanlab123/MetaUE. Copyright © 2023, The Authors. All rights reserved.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

A 100x100 CMOS SPAD Array with In-Pixel Correlation Techniques for Fast Quantum Ghost Imaging Applications

A 100x100 CMOS SPAD Array with In-Pixel Correlation Techniqu...

引用

European Conference on Solid-State Circuits (ESSCIRC)

作者： Massimo Gandola Enrico Manuzzato Matteo Perenzoni Filippo Dal Farra Valerio Flavio Gili Dupish Dupish Andres Vega Thomas Pertsch Frank Setzpfandt Leonardo Gasparini Fondazione Bruno Kessler Povo (TN) Italy Department of Information Engineering and Computer Science University of Trento Trento Italy now at Sony Semiconductor Solutions Europe Povo (TN) Italy Department of Physics University of Trento Trento Italy Abbe Center of Photonics Friedrich-Schiller-Universität Jena Institute of Applied Physics Jena Germany Fraunhofer Institute for Applied Optics and Precision Engineering Jena Germany

In this paper, a 100x100 CMOS Single Photon Avalanche Diode (SPAD) array designed for quantum imaging applications requiring synchronization with an external unpredictable and aperiodic trigger is presented. The targeted application takes advantage of non-classical quantum states of light to achieve quantum ghost imaging in the middle-infrared (MIR) up to 7 $\mu \mathrm{m}$ wavelength by detecting the corresponding entangled photons in the visible spectrum with the SPAD imager. For this purpose, a SPAD array with in-pixel backward-looking temporal correlation capabilities has been implemented to spatially resolve the entangled photons in a ghost imaging setup. The correlation is performed through a pixel-wise asynchronous delayed time window, whose width can be tuned to maximize the correlation efficiency. Two pixel variants, without and with resource sharing, have been designed: the resulting imager has been implemented in a 110 nm CIS FSI technology, achieving a correlation window width between 2 ns and 27 ns and a delay range between 5 ns and 40 ns, with 17 $\mu \mathrm{m}$ pixel pitch and fill-factor of 19.3% and 31.3%. A smart readout architecture has been implemented to improve the acquisition duty cycle, given the expected sparsity of the detected events.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Demonstration of Scully-Drühl-type quantum erasers on quantum computers

arXiv

引用

arXiv 2024年

作者： Chen, Bo-Hung Chiou, Dah-Wei Hsu, Hsiu-Chuan Department of Physics National Taiwan University Taipei10617 Taiwan Graduate Institute of Electronics Engineering National Taiwan University Taipei10617 Taiwan Center for Quantum Science and Engineering National Taiwan University Taipei10617 Taiwan Physics Division National Center for Theoretical Sciences Taipei10617 Taiwan Graduate Institute of Applied Physics National Chengchi University Taipei11605 Taiwan Department of Computer Science National Chengchi University Taipei11605 Taiwan

We present a novel quantum circuit that genuinely implements the Scully-Drühl-type delayed-choice quantum eraser, where the two recorders of the which-way information directly interact with the signal qubit and remain spatially separated. Experiments conducted on IBM Quantum and IonQ processors demonstrate that the recovery of interference patterns, to varying degrees, aligns closely with theoretical predictions, despite the presence of systematic errors. This quantum circuit-based approach, more manageable and versatile than traditional optical experiments, facilitates arbitrary adjustment of the erasure and enables a true random choice in a genuine delayed-choice manner. On the IBM Quantum platform, delay gates can be employed to further defer the random choice, thereby amplifying the retrocausal effect. Since gate operations are executed sequentially in time, the system does not have any involvement of random choice until after the signal qubit has been measured, therefore eliminating any potential philosophical loopholes regarding retrocausality that might exist in other experimental setups. Remarkably, quantum erasure is achieved with delay times up to ∼ 1 µs without noticeable decoherence, a feat challenging to replicate in optical setups. © 2024, CC BY.

关键词： Systematic errors

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning Approach for Nerve Injury Classification in Brachial Plexopathies Using Magnetic Resonance Neurography with Modified Hiking Optimization Algorithm

引用

Academic Radiology 2025年

作者： Dahou, Abdelghani Elaziz, Mohamed Abd Khattap, Mohamed G. Hassan, Hend Galal Eldeen Mohamed Ali School of Computer Science and Technology Zhejiang Normal University Jinhua 321004 China Mathematics and Computer Science department University of Ahmed DRAIA Adrar 01000 Algeria Department of Mathematics Faculty of Science Zagazig University Zagazig 44519 Egypt Faculty of Computer Science and Engineering Galala University Suez 435611 Egypt Artificial Intelligence Research Center (AIRC) Ajman University Ajman 346 United Arab Emirates Department of Diagnostic Interventional Radiology and Molecular Imaging Faculty of Medicine Ain Shams University Cairo 11591 Egypt Technology of Radiology and Medical Imaging Program Faculty of Applied Health Sciences Technology Galala University Suez 435611 Egypt

Rationale and Objectives: Brachial plexopathies (BPs) encompass a complex spectrum of nerve injuries affecting motor and sensory function in the upper extremities. Diagnosis is challenging due to the intricate anatomy and symptom overlap with other neuropathies. Magnetic Resonance Neurography (MRN) provides advanced imaging but requires specialized interpretation. This study proposes an AI-based framework that combines deep learning (DL) with the modified Hiking Optimization Algorithm (MHOA) enhanced by a Comprehensive Learning (CL) technique to improve the classification of nerve injuries (neuropraxia, axonotmesis, neurotmesis) using MRN data. Materials and Methods: The framework utilizes MobileNetV4 for feature extraction and MHOA for optimized feature selection across different MRI sequences (STIR, T2, T1, and DWI). A dataset of 39 patients diagnosed with BP was used. The framework classifies injuries based on Seddon's criteria, distinguishing between normal and abnormal conditions as well as injury severity. Results: The model achieved excellent performance, with 1.0000 accuracy in distinguishing normal from abnormal conditions using STIR and T2 sequences. For injury severity classification, accuracy was 0.9820 in STIR, outperforming the original HOA and other metaheuristic algorithms. Additionally, high classification accuracy (0.9667) was observed in DWI. The proposed framework outperformed traditional methods and demonstrated high sensitivity and specificity. Conclusion: The proposed AI-based framework significantly improves the diagnosis of BP by accurately classifying nerve injury types. By integrating DL and optimization techniques, it reduces diagnostic variability, making it a valuable tool for clinical settings with limited specialized neuroimaging expertise. This framework has the potential to enhance clinical decision-making and optimize patient outcomes through precise and timely diagnoses. © 2025 The Association of University Radiologists

关键词： Brachial Plexopathy (BP) Comprehensive Learning (CL) Deep Learning (DL) Feature Selection (FS) Hiking Optimization Algorithm (HOA) Magnetic Resonance Neurography (MRN) MobileNetV4

来源：评论

学校读者我要写书评

暂无评论

An Auditable Confidentiality Protocol for Blockchain Transactions

SSRN

引用

SSRN 2023年

作者： Li, Aoxuan D’Angelo, Gabriele Tang, Su-Kit Fang, Frank Gong, Baron Faculty of Applied Sciences Macao Polytechnic University Rua de Luís Gonzaga Gomes China Department of Computer Science and Engineering University of Bologna Mura Anteo Zamboni 7 BolognaI-40127 Italy Mystiko.Network

Blockchain exposes all users’ transaction data to the public, including account balances, asset holdings, trading history, etc. Such data exposure leads to potential security and personal privacy risks that restrict blockchain from broader adoption. Although some existing projects focus on single-chain confidential payment, no existing cross-chain system supports private transactions yet, which is incompatible with privacy regulations such as GDPR. Also, current confidential payment systems require users to pay high extra fees. However, a private and anonymous protocol encrypting all transaction data raises concerns about malicious and illegal activities since the protocol is difficult to audit. We need to balance privacy and auditability in *** propose an auditable and affordable protocol for cross-chain and single-chain transactions. This protocol leverages zero-knowledge proofs to encrypt transactions and perform validation without disclosing sensitive users' data. To meet regulations, each auditor from an auditing committee will have an encrypted secret share of the transaction data. Auditors may view the private transaction data only if a majority of the committee agrees to decrypt the data. We employ a ZK-rollup scheme by processing multiple transactions in batches, which reduces private transaction costs of 90\% compared with solutions that do not employ the ZK-rollup. The proposed scheme has been implemented using Zokrates and Solidity and evaluated running on the Ethereum test network. The results show that the total one-to-one private transactions latency is about 5 seconds. Moreover, the security of the protocol is analyzed by mean of the standard real/ideal world paradigm. © 2023, The Authors. All rights reserved.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

Exploring the Roles of Agents and Multi-Agent in Improving Mobile Ad Hoc Networks 4

Exploring the Roles of Agents and Multi-Agent in Improving M...

引用

4th International Symposium on Agents, Multi-Agents Systems and Robotics, ISAMSR 2021

作者： Jubair, Mohammed Ahmed Alabdullah, Abdullah I. M. Mostafa, Salama A. Mustapha, Aida Hassan, Mustafa Hamid Gunasekaran, Saraswathy Shamini College of Information Technology Imam ja'Afar Al-Sadiq University Department of Computer Technical Engineering Al-Muthanna Iraq University of Mosul College of Science Department of Physics Mosul Iraq Faculty of Computer Science and Information Technology Universiti Tun Hussein Onn Malaysia Johor Malaysia Faculty of Applied Sciences and Technology Universiti Tun Hussein Onn Malaysia Johor Malaysia College of Computer Science and Informatics Universiti Tenaga Nasional Kajang43000 Malaysia

ISBN: (纸本)9781728166544

We are experiencing a rapid evolution and advancement of technologies that are capable of supporting the formulation and implementation of robust and adaptive network architectures designed for mobile and dynamic environments. An example of such technologies is the Mobile Ad-Hoc Network (MANET), which supports self-organizing multi-hop heterogeneous network routing services and organization. The importance of such technologies for the future of DoD networking is evident, particularly in the front edge of the battlespace where there is a need for robust and self-organizing network. Another area of such technological advancement is the Multi-Agent Systems (MAS), which are capable of supporting both team-based and independent problem solving in many different environments. These two technologies have been extensively explored, but their combination is largely unexplored. Consequently, this paper aims to investigate the joint operation of agents and multi-agent in the MANET environment. The paper also discusses the research efforts that have been made to optimally improve the technologies. © 2021 IEEE.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Hyperspectral Brain Tissue Classification using a Fast and Compact 3D CNN Approach

Hyperspectral Brain Tissue Classification using a Fast and C...

引用

International Image Processing, Applications and Systems Conference (IPAS)

作者： Hamail Ayaz David Tormey Ian McLoughlin Muhammad Ahmad Saritha Unnikrishnan Faculty of Engineering and Design and Mathematical Modelling and Intelligent Systems for Health and Environment Atlantic Technological University Sligo Ireland Faculty of Engineering and Design Centre for Precision Engineering Materials and Manufacturing Research (PEM) Atlantic Technological University Sligo Ireland Department of Computer Science and Applied Physics Atlantic Technological University Galway Ireland Department of Computer Science National University of Computer and Emerging Sciences Chiniot Pakistan

ISBN: (纸本)9781665462204

Glioblastoma (GB) is a malignant brain tumor and requires surgical resection. Although complete resection of GB improves prognosis, supratotal resection may cause neurological abnormalities. Therefore, intraoperative tissue classification techniques are needed to delineate infected tumor regions to remove reoccurrences. To delineate the affected regions, surgeons mostly rely on traditional magnetic resonance imaging (MRI) which often lacks accuracy and precision due to the brain-shift phenomenon. Hyperspectral Imaging (HSI) is a noninvasive advanced optical technique and has the potential to classify tissue cells accurately. However, HSI tumor classification is challenging due to overlapping regions, high interclass similarity, and homogeneous information. Additionally, HSI models using 2D Convolutional Neural Network (CNN) models works with spectral information eliminating spatial features and 3D followed by 2D hybrid model lacks abstract level spatial information. Therefore, in this study, we have used a minimal layer 3D CNN model to classify the GB tumor region from normal tissues using an intraoperative VivoHSI dataset. The HSI data have normal tissue (NT), tumor tissue (TT), hypervascularized tissue or blood vessels (BV), and background (BG) tissue cells. The proposed 3D CNN model consists of only two 3D layers using limited training samples (20%), which are further divided into 50% for training and 50% for validation and blind tested (80%) on the rest of the data. This study outperformed then state-of-the-art hybrid architecture by achieving an overall accuracy of 99.99%.

关键词： Training Solid modeling Three-dimensional displays Magnetic resonance imaging Surgery Brain modeling Data models

来源：评论

学校读者我要写书评

暂无评论

Simulation of Conducted Emissions From Power Converters Using Leading Switching Technologies

Simulation of Conducted Emissions From Power Converters Usin...

引用

IEEE Global Electromagnetic Compatibility Conference (GEMCCON)

作者： Amr Madi Francinei Vieira Piotr Lezynski Sebastian Koj Robert Smolenski Electrical Engineering Mathematics & Computer Science (EEMCS) University of Twente Enschede Netherlands Institute of Electrical Engineering and Measurement Technology Leibniz University Hannover Hannover Germany Institute of Automatic Control Electronics and Electrical Engineering University of Zielona Gora Zielona Gora Poland Department of Engineering Sciences Jade University of Applied Sciences Wilhelmshaven Germany

This paper presents a comparative study between the commonly used switches (IGBT, MOSFET, SiC and GaN) for power inverters of electric vehicles. A 400 V, three-phase inverter system simulation test is implemented using LTspice and the conducted emissions are compared to variant CISPR standards and switching frequencies in order to show the possible interferences with the other car equipment.

关键词： MOSFET Silicon carbide Switching frequency Interference Predictive models SPICE Inverters

来源：评论

学校读者我要写书评

暂无评论

Generating datasets for software requirements prioritization research

Generating datasets for software requirements prioritization...

引用

2020 IEEE International Conference on Computing, Power and Communication Technologies, GUCON 2020

作者： Nazim, Mohd. Mohammad, Chaudhary Wali Sadiq, Mohd. Faculty of Engineering and Technology Department of Applied Sciences and Humanities New Delhi110025 India Indian Institute of Science Department of Computer Science and Automation Bangalore560012 India

ISBN: (纸本)9781728150703

Software requirements are the need of the stakeholders which are identified during requirements elicitation process. There are different types of the software requirements like functional requirements, non-functional requirements, testing requirements, etc. After requirements elicitation process, a system may have hundreds or thousands of requirements;and during the development process it is not possible to implement all the software requirements because of the several limitations of an organization as well as the stakeholders. To develop the successful software product, the elicited software requirements must be prioritized before the development of software so that high ranked software requirements can be identified. Computation of the ranking values of the software requirements is a difficult task because it involves lot of computational steps like evaluation of software requirements, computation of group preferences from the individual preferences, computation of the ranking values after normalizing the preference matrices, etc. Among these steps, in this paper, we mainly focus on the evaluation of the software requirements using linguistic variables because in real life applications people use linguistic variables to specify their preferences on software requirements. The objective of this paper is to generate a dataset of 32 functional requirements after evaluating it on the basis of 3 non-functional requirements so that the generated dataset can be used as an input into the software requirements prioritization methods. The institute examination system is used as case study to explain the steps for the generation of the dataset. © 2020 IEEE.

关键词： Requirements engineering

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：