检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Chen, Shu Xu, Zitao Pan, Weike Yang, Qiang Ming, Zhong College of Computer Science and Software Engineering Shenzhen University China WeBank AI Lab WeBank China The Hong Kong University of Science and Technology China College of Big Data and Internet Shenzhen Technology University China

Cross-domain sequential recommendation (CDSR) shifts the modeling of user preferences from flat to stereoscopic by integrating and learning interaction information from multiple domains at different granularities (ranging from inter-sequence to intra-sequence and from single-domain to cross-domain). In this survey, we first define the CDSR problem using a four-dimensional tensor and then analyze its multi-type input representations under multidirectional dimensionality reductions. Following that, we provide a systematic overview from both macro and micro views. From a macro view, we abstract the multi-level fusion structures of various models across domains and discuss their bridges for fusion. From a micro view, focusing on the existing models, we first discuss the basic technologies and then explain the auxiliary learning technologies. Finally, we exhibit the available public datasets and the representative experimental results as well as provide some insights into future directions for research in CDSR. Copyright © 2024, The Authors. All rights reserved.

关键词： Stereo image processing

来源：评论

学校读者我要写书评

暂无评论

An n-MOSFET Layout with Multi-Finger Z Gate for Radiation Tolerance 5

An n-MOSFET Layout with Multi-Finger Z Gate for Radiation To...

引用

5th IEEE International Conference on Knowledge Innovation and Invention, ICKII 2022

作者： Shan, Chan Liu, Ying Chen, Huan Huo, Dong-Yang Xu, Tian-Rong Jimei University College of Ocean Information Engineering Xiamen China Xiamen Institute of Software Technology Department of Software Technology Xiamen China Minjiang University School of Journalism and Communication Fuzhou China Universiti Malaya Faculty of Computer Science and Information Technology Department of Information Systems Kuala Lumpur Malaysia Universiti Malaya Planning Faculty of Built Environment Department of Urban and Regional Kuala Lumpur Malaysia

ISBN: (数字)9781665479295

ISBN: (纸本)9781665479295

In this paper, a new n-MOSFET layout with multi-finger Z gate is proposed to reduce the total ionizing dose (TID) effect. In addition to the proposed layout, multi-finger single gate layout is also simulated using Sentaurus TCAD in 3D. Firstly, drain current - gate voltage curves of both layouts are compared in order to verify the radiation hardening ability of the proposed layout. Secondly, we compare TID responses by extracting threshold voltages and leakage currents from both layouts. Thirdly, the finger number is investigated for both layouts because it is an important factor for multi-finger layout. The results have indicated that the finger number significantly affects the multi-finger single gate layout, whereas the proposed multi-finger Z gate layout is relatively little affected by the finger number in radiation environment. © 2022 IEEE.

关键词： Drain current

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Optimal ECG-Lead Subsets for Arrhythmia/ECG Pattern Classification: Deep Learning Versus Conventional Methods

SSRN

引用

SSRN 2024年

作者： Reznichenko, Serhii Whitaker, John Ni, Zixuan Zhou, Shijie The Department of Computer Science and Software Engineering Miami University Oxford45056 OH United States Division of Biomedical Engineering and Imaging Sciences College of Computer Science and Technology Zhejiang University Hangzhou China The Department of Chemical Paper and Biomedical Engineering Miami University Oxford45056 OH United States

Background:Deep Learning methods have been constantly growing in popularity. Prior to Deep Learning methods, Conventional Machine Learning has been effectively used for the classification of heart arrhythmias/ECG patterns. However, there has limited research into the potential benefits of Deep Learning methods over conventional Machine Learning. Given that Deep Learning often demands larger datasets to achieve robust classification results, using conventional techniques could yield superior accuracy. Additionally, the classification of heart arrhythmias/ECG patterns is often dependent on specific ECG leads for acccurate classification. It is unknown how Deep Learning and conventional Machine Learning methods perform on reduced subsets of ECG ***:The goal of the study is to compare the performance of a Deep Learning method to a conventional Machine Learning method to classify 8 different arrhythmias/ECG patterns using subsets of a full 12-lead ECG .Methods:We used a public dataset from the PhysioNet Cardiology Challenge 2020. The research involved the utilization of both Deep Learning and Conventional Machine Learning methods. For the Deep Learning method, we trained a CNN classifier and extracted 32 features for each ECG lead, which were then used in a feedforward neural network. For the conventional Machine Learning method, we employed a Random Forest classifier that operated on manually extracted features from the ECG signals. The optimal subsets of ECG leads were identified using recursive feature elimination for both of the methods. This process involves training a classifier, evaluating its performance, identifying the least important lead, eliminating it, and then iteratively repeating the procedure. We determined lead importance using Random Forest feature importance scores for the conventional Machine Learning method and used SHAP values for Deep Learning. Finally, the subset of ECG leads that was statistically significant (p-value Results:We id

关键词： Electrocardiograms

来源：评论

学校读者我要写书评

暂无评论

The capability of multi resolution analysis: A case study of COVID-19 diagnosis 4

The capability of multi resolution analysis: A case study of...

引用

4th International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2021

作者： Monday, Happy Nkanta Li, Jian Ping Nneji, Grace Ugochi James, Edidiong Christopher Chikwendu, Ijeoma Amuche Ejiyi, Chukwuebuka Joseph Oluwasanmi, Ariyo Mgbejime, Goodness Temofe University of Electronic Science and Technology of China School of Computer Science and Engineering Sichuan Chengdu China University of Electronic Science and Technology of China School of Information and Software Engineering Sichuan Chengdu China

ISBN: (纸本)9781665413220

The outbreak of COVID-19 in more than 150 nations across the globe is severely impacting the health of people worldwide. A more reliable way to curb the spread of COVID-19 is early detection of infected patients for temporary isolation and care. Image base detection of COVID-19 presents the quickest way to diagnose patients. Few literatures have shown that chest radiograms of infected COVID-19 patients contain irregular characteristics. From related studies, we investigated the application of wavelet transform multi resolution analysis to detect COVID-19 patients using chest radiography. In this study, we proposed a wavelet based convolutional neural network to handle data scarcity in this era of COVID-19 fast emergence. We only considered four levels of wavelet transform decompositions. We utilized an open source dataset from National Institute Health containing several X-rays of pneumonia related diseases whereas the COVID-19 dataset is collected from Radiology Society North America. From the experimental results, our model achieved sensitivity greater than 90% while the specificity is above 90%. We also show the receiver operating characteristic and precision-recall curves of each decomposition level. Our results show that the performance of our proposed model is encouraging and outperformed previous state-of-the-art models. © 2021 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

An Energy-Efficient Mobile Agent-Based Data Aggregation Scheme for Wireless Body Area Networks

引用

computers, Materials & Continua 2022年第3期70卷 5929-5948页

作者： Gulzar Mehmood Muhammad Zahid Khan Muhammad Fayaz Mohammad Faisal Haseeb Ur Rahman Jeonghwan Gwak Department of Computer Science&Information Technology University of MalakandChakdara Dir Lower23021Pakistan Department of Computer Science University of Central AsiaNarynKyrgyzstan Department of Software Korea National University of TransportationChungju27469Korea Department of Biomedical Engineering Korea National University of TransportationChungju27469Korea Department of AI Robotics Engineering Korea National University of TransportationChungju27469Korea Department of IT and Energy Convergence(BK21 FOUR) Korea National University of TransportationChungju27469Korea

Due to the advancement in wireless technology and miniaturization,Wireless Body Area Networks(WBANs)have gained enormous popularity,having various applications,especially in the healthcare *** are intrinsically resource-constrained;therefore,they have specific design and development *** such highly desirable requirement is an energy-efficient and reliable Data Aggregation(DA)mechanism for *** efficient and reliableDAmay ultimately push the network to operate without much human intervention and further extend the network *** conventional client-serverDAparadigm becomes unsuitable and inefficient for WBANs when a large amount of data is generated in the ***,in most of the healthcare applications(patient’s critical conditions),it is highly important and required to send data as soon as possible;therefore,reliable data aggregation in WBANs is of great *** tackle the shortcomings of the client-serverDAparadigm,theMobile Agent-Basedmechanismproved to be a more workable *** aMobile Agent-Based mechanism,a taskspecific mobile agent(code)traverses to the intended sources to gather *** agents travel on a predefined path called itinerary;however,planning a suitable and reliable itinerary for a mobile agent is also a challenging issue *** paper presents a new Mobile Agent-Based DA scheme for WBANs,which is energy-efficient and ***,in the proposed scheme,the network is divided into clusters,and cluster-heads are ***,a mobile agent is generated from the base station to collect the required data from cluster *** the case,if any fault occurs in the existing itinerary,an alternate itinerary is planned in real-time without compromising the network *** our simulation-based validation,we have found that the proposed system delivers significantly improved fault-tolerance and reliability with energy-efficiency and extended network lifetime in WBANs.

关键词： WBANs mobile-agent data aggregation reliability

来源：评论

学校读者我要写书评

暂无评论

A Composite Schema Matching Method Based on Contrastive Learning in Data Integration

A Composite Schema Matching Method Based on Contrastive Lear...

引用

International Conference on computer Supported Cooperative Work in Design

作者： Liying Shao Xinyu Hao Jian-tao Zhou Ministry of Education Inner Mongolia Engineering Laboratory for Cloud Computing and Service Software Inner Mongolia Engineering Laboratory for Big Data Analysis Technology College of Computer Science Inner Mongolia University Engineering Research Center of Ecological Big Data Hohhot China

ISBN: (数字)9798331513054

ISBN: (纸本)9798331513061

Schema matching is a crucial step in data integration for in-depth information mining, aimed at capturing seman-tic correspondences between elements of multi-source datasets. The existing schema matching methods still face problems such as insufficient representations of schema information diversity, poor cross-domain expression ability, and inadequate adaptability to complex data environments. We propose a composite schema matching method based on contrastive learning. Our method de-signs multi-domain word lists for data augmentation, the schema-based matching part fine-tunes pre-trained models through con-trastive learning and finally designs multi-model voting strategies to complete the composite matches. It also designs a format validation strategy to enhance the performance of the schema matching model. The experimental results show that our method has improved the F1 comprehensive performance indicators on three benchmark datasets by an average compared to existing benchmark methods.

关键词： Adaptation models Federated learning Face recognition Semantics Data integration Contrastive learning Benchmark testing Data augmentation Data models Data mining

来源：评论

学校读者我要写书评

暂无评论

Uniqueness Proof of Optimal Power Management Strategies for Energy Storage Dynamic Models

SSRN

引用

SSRN 2024年

作者： Goldstein-Tweg, Tom Ginzburg-Ganz, Elinor Belikov, Juri Levron, Yoash The Andrew and Erna Viterbi Faculty of Electrical and Computer Engineering Technion—Israel Institute of Technology Haifa3200003 Israel Department of Software Science Tallinn University of Technology Akadeemia tee 15a Tallinn12618 Estonia

The current paper belongs to a class of research works that aim to find analytic and semi-analytic solutions to optimal power flow problems that involve storage systems. The main contribution of this work is a rigorous proof for the uniqueness of the ``shortest-path" optimal solution, which is a cornerstone in this class of algorithms, and relies upon a graphical design procedure presented in an earlier work. The proof builds upon five consequential lemmas, each provides a different characteristic of the optimal solution. These characteristics are then merged to prove the uniqueness of the optimal solution, which is given by the shortest path of the generated energy within bounds. The presented proof provides not only a sound theoretical foundation for this class of algorithms, but may also help develop additional analytic solutions for more complex optimal control problems involving storage systems. © 2024, The Authors. All rights reserved.

关键词： Power management

来源：评论

学校读者我要写书评

暂无评论

Dynamic knowledge graph completion through time-aware relational message passing

Dynamic knowledge graph completion through time-aware relati...

引用

International CSI computer Conference, CSICC

作者： Amirhossein Baqinejadqazvini Saedeh Tahery Saeed Farzi Department of Software Engineering Faculty of Computer Engineering K. N. Toosi University of Technology Tehran Iran Department of Artificial Intelligence Faculty of Computer Engineering K. N. Toosi University of Technology Tehran Iran School of Computer Science Institute for Research in Fundamental Sciences (IPM) Tehran Iran

As the structure of knowledge graphs may vary over time, static knowledge graph completion methods do not deal with time-varying knowledge graphs. However, examining the paths between entities and entities' context information can lead to more accurate completion methods. This paper attempts to complete dynamic (time-varying) knowledge graphs by combining time-aware relational paths and relational context. The proposed model can improve dynamic knowledge graph completion methods by leveraging neural networks. Experimental results conducted on two standard datasets, ICEWS14 and ICEWS05-15, indicate our model's superiority in terms of Mean Reciprocal Rank (MRR) and Hit@k over its well-known counterparts, such as DE-TransE and DE-DistMult.

关键词： Computational modeling Message passing Neural networks Knowledge graphs Time factors Standards Context modeling

来源：评论

学校读者我要写书评

暂无评论

Research on the Numerical Representation of Stock Linkage Prediction 2nd

Research on the Numerical Representation of Stock Linkage Pr...

引用

2nd International Symposium on Simulation and Process Modelling, ISSPM 2020

作者： Ma, Chi Wang, Shaofan Lu, Shengliang Han, Guojing School of Computer Science and Engineering Huizhou University Huizhou516007 China School of Computer Science and Software Engineering University of Science and Technology Liaoning Anshan114051 China Meteorological Administration Anshan China

ISBN: (纸本)9789813345744

In this paper, time series of numerical correlations and morphological similarities are analyzed. It is proposed to combine the correlation coefficient with a time-weighted dynamic time warping (DTW) distance to emphasize timeliness as a stock linkage numerical formula. Therefore, the problem of finding the connection relationship between stocks can be converted into a numerical representation problem of stock linkage, and a stock linkage prediction optimized model based on long short-term memory (LSTM) can be established. At the same time, in order to improve the prediction performance of the LSTM model for the time series of stock interconnection values, wavelet transform and denoising autoencoder are used to denoise and reconstruct the input samples, thereby achieving more accurate prediction and analysis of stock linkage. © 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Multi-Hierarchy Metamorphic Testing for Hyphenated Words in Machine Translation 31

Multi-Hierarchy Metamorphic Testing for Hyphenated Words in ...

引用

31st Asia-Pacific software engineering Conference, APSEC 2024

作者： Zhu, Rui Tao, Chuanqi Gao, Jerry College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China Nanjing University of Aeronautics and Astronautics Ministry Key Laboratory for Safety-Critical Software Development and Verification Nanjing China Nanjing University State Key Laboratory for Novel Software Technology Nanjing China San Jose State University Computer Engineering Department San Jose United States

ISBN: (纸本)9798331534011

With the advancement of deep neural networks, machine translation has seen rapid progress in recent years. Individuals often rely on machine translation software to facil-itate various tasks. However, the intricacies of neural networks can lead to translation errors, resulting in misunderstandings or conflicts. The most common method for testing machine translation is metamorphic testing. However, metamorphic testing at the phrase or sentence hierarchy may result in some test cases being incorrectly identified as failures. To mitigate this issue, we added the word hierarchy. We proposed a multi-hierarchy metamorphic testing method, MHT, to test machine translation. Hyphenated words as a specific format prone to translation errors, which are chosen as our research object. Based on the common notion that translations of words within the same sentence should be similar, we extract contents from different hierarchies within sentences containing hyphenated words and compare the similarity of their corresponding translations for these specific words. We conducted the experiments on 881 sentences leveraging Google Translate, Microsoft Bing Translator, and Baidu Translate, which detected 111, 91, and 111 suspicious errors with high precision (78.4 %, 82.4 %, and 81.1 %). Translation errors mainly include mis-translation, under-translation, over-translation, and non-translation. © 2024 IEEE.

关键词： Neural machine translation

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：