检索结果-内蒙古大学图书馆

Multilayer perceptron ensembles in a truly sparse training context

Neural Computing and Applications 2025年

作者： van der Wal, Peter R. D. Strisciuglio, Nicola Azzopardi, George Mocanu, Decebal Constatin Information Systems Group Bernoulli Institute for Mathematics Computer Science and Artificial Intelligence University of Groningen Nijenborgh 9 Groningen9747 AG Netherlands Data Management and Biometrics Group Faculty of Electrical Engineering Mathematics and Computer Science University of Twente Hallenweg 19 Enschede7522 NH Netherlands Department of Computer Science Faculty of Science Technology and Medicine University of Luxembourg Maison du Nombre 6 avenue de la Fonte Esch4364 Luxembourg

Ensemble learning for artificial neural networks (ANNs) is an effective method to enhance predictive performance. However, ANNs are computationally and memory intensive, and naively training multiple networks can lead to excessive training times and costs. An effective tool for improving ensemble efficiency is introducing topological sparsity. Even though several implementations of efficient ensembles have been proposed, none of them can provide actual benefits in terms of computational overhead as the sparsity is simulated using binary masks. In this paper, we address this issue by introducing a Truly Sparse Ensemble without binary masks and directly incorporate native sparsity. We also propose two algorithms for initializing new subnetworks within the ensemble, leveraging this native topological sparsity to enhance subnetwork diversity. We demonstrate the performance of the resulting models at high levels of sparsity on several datasets in terms of classification accuracy, floating point operations (FLOPs), and actual running time. The proposed methods outperform all baseline dense and truly sparse models on tabular data, successfully diversify the training trajectory of the subnetworks, and increase the topological distance between subnetworks after re-initialization. © The Author(s) 2025.

关键词： Digital arithmetic

来源：评论

学校读者我要写书评

暂无评论

Multi-strategy Based Quantum Cost Reduction of Quantum Boolean Circuits

arXiv

引用

arXiv 2024年

作者： Ahmed, Taghreed Younes, Ahmed Elkabani, Islam Department of Mathematics and Computer Science Faculty of Science Alexandria University Alexandria Egypt Alexandria Quantum Computing Group Alexandria University Alexandria Egypt Faculty of Computer Science and Engineering Alamein International University El-Alamein Egypt

The construction of quantum computers is based on the synthesis of low-cost quantum circuits. The quantum circuit of any Boolean function expressed in a Positive Polarity Reed-Muller PPRM expansion can be synthesized using Multiple-Control Toffoli (MCT) gates. This paper proposes two algorithms to construct a quantum circuit for any Boolean function expressed in a Positive Polarity Reed-Muller PPRM expansion. The Boolean function can be expressed with various algebraic forms, so there are different quantum circuits can be synthesized for the Boolean function based on its algebraic form. The proposed algorithms aim to map the MCT gates into the NCV gates for any quantum circuit by generating a simple algebraic form for the Boolean function. The first algorithm generates a special algebraic form for any Boolean function by rearrangement of terms of the Boolean function according to a predefined degree of term dterm, then synthesizes the corresponding quantum circuit. The second algorithm applies the decomposition methods to decompose MCT circuit into its elementary gates followed by applying a set of simplification rules to simplify and optimize the synthesized quantum circuit. The proposed algorithms achieve a reduction in the quantum cost of synthesized quantum circuits when compared with relevant work in the literature. The proposed algorithms synthesize quantum circuits that can applied on IBM quantum computer. Copyright © 2024, The Authors. All rights reserved.

关键词： Boolean functions

来源：评论

学校读者我要写书评

暂无评论

IOT based Health Monitoring System with AI-Powered Disease Prediction 13

IOT based Health Monitoring System with AI-Powered Disease P...

引用

13th IEEE International Conference on Communication Systems and Network Technologies, CSNT 2024

作者： Mahendran, S. Radha Hari Priya, M.P. Mohsen, Karrar Shareef Khan, Mohammad Shahbaz Obaid, Ahmed J. Shareef, Ashraf Mohammed Department of Bioinformatics Pallavaram Chennai117 India Department of Computer Science Karnataka Bangalore560077 India Scientific Research Center Al-Ayen University Information and Communication Technology Research Group Thi-Qar Iraq Children's National Hospital Operations and Regulatory Affairs WashingtonDC United States University of Kufa Faculty of Computer Science and Mathematics Najaf Iraq National University of Science and Technology Dhi Qar Iraq

ISBN: (纸本)9798350305463

Healthcare monitoring systems have advanced significantly in emergency rooms and many other health settings. Today, many nations are deeply concerned about the rise of small healthcare monitoring systems. In-person advising and telemedicine are two different ways that the Internet of Things (IoT) is further developing healthcare. The Internet of Things makes things and individuals reliably available, and its relationship with the cloud improves our personal satisfaction. Proactive clinical exploration can help change a responsive healthcare approach into a proactive one, as man-made reasoning (AI) and high-level human insight become increasingly more coordinated into the healthcare area. Within the field of machine learning, deep learning holds significant potential in precisely and swiftly analysing vast quantities of data, producing perceptive experiences, and resolving intricate issues. Preventive treatment and early intervention for persons who are at risk depend on accurate and useful illness prediction. The constant inflow of electronic medical information necessitates the need for more accurate prediction models in recurrent neural network versions of deep learning that handle successive time-series data. Devices connected to the Internet of Things provide data to the proposed system, and future analysis will be conducted on cloud-stored electronic clinical records pertaining to patient histories. © 2024 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

ELECTRONIC CIRCUITRY FOR A NON-CONTACTING PARTIAL DISCHARGE GMR SENSOR 23

ELECTRONIC CIRCUITRY FOR A NON-CONTACTING PARTIAL DISCHARGE ...

引用

23rd International Symposium on High Voltage Engineering, ISH 2023

作者： Chen, Yun Heredia, Luis C.C. Niasar, Mohamad G. Ross, Robert Smit, Johan J. Hao, Yanpeng Li, Licheng High Voltage Technologies Group Faculty of Electrical Engineering Mathematics & Computer Science Delft University of Technology Delft Netherlands IWO Institute for Science and Development Ede Netherlands School of Electric Power Engineering South China University of Technology Guangzhou China

ISBN: (纸本)9781839539954

Partial discharge (PD) detection is an important tool for evaluating the insulation condition of high-voltage power equipment. This paper investigates a diagnostic system consisting of a magnetic sensor with dedicated electronic circuitry. The investigated sensor is based on the giant magnetoresistance (GMR) effect, which enables the possibility of contactless detection of magnetic fields caused by PD currents. However, the bandwidth of the circuitry can be a limiting factor. In order to exploit the bandwidth of an extra high-sensitivity adapted giant magneto-resistive (xMR) sensor, this paper describes dedicated designs for compensation and signal conditioning of the xMR signals. Typical performance has been evaluated, including frequency response and time-domain response to fast calibrator pulses by the xMR sensor with the implemented circuit. The results show that the xMR sensor with the implemented circuit covers a relatively broad bandwidth and can detect PD pulses with a minimum amount of 10 pC, preliminarily verifying its possibility to detect PDs. Using this xMR system, magnetic signals from an experimental model producing surface discharges have been detected and compared with simultaneously measured signals from a high-frequency current transformer (HFCT). The results show that the xMR system can measure the magnetic fields produced by the PD currents. © The Institution of Engineering & Technology 2023.

关键词： Partial discharges

来源：评论

学校读者我要写书评

暂无评论

EXTREMAL AND CONTINUA SOLUTIONS FOR STOCHASTIC FRACTIONAL DIFFERENTIAL EQUATIONS

引用

Journal of Mathematical sciences (United States) 2025年 1-15页

作者： Benhamida, Ouafaa Dahmani, Zoubir Ibrahim, Rabha W. Laboratory of Pure and Applied Maths Faculty of Sciences UMAB Mostaganem Algeria Near East University Mathematics Research Center Department of Mathematics Near East Boulevard Nicosia /Mersin 10 99138 Türkiye Department of Computer Science and Mathematics Lebanese American University Beirut 13-5053 Lebanon Information and Communication Technology Research Group Scientific Research Center Al-Ayen University Thi-Qar Iraq Laboratory of LAMDA-RO Faculty of Sciences University of Blida 1 Blida 09000 Algeria

The aim of this work is to study two classes of stochastic fractional differential equations via the application of the method of upper and lower solutions combined with the Arzela-Ascoli theorem. We begin by proving an auxiliary result for the integral representation of an Airy-type stochastic problem. The specific symmetry features of an Airy-type stochastic problem depend on the form of the stochastic differential equations (SDE) and the relevant coefficients, it is vital to note. To comprehend each issue’s unique symmetries and their effects, a thorough investigation is necessary. Then, we prove an existence result for extremal solutions for the same problem. Another class of stochastic equations of higher-order type is also studied. We also present some examples to show the validity of the obtained results. At the end, a conclusion follows. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2025.

关键词： Airy equation Extremal solutions Fractional calculus Fractional differential operator Stochastic fractional differential equation Upper and lower method

来源：评论

学校读者我要写书评

暂无评论

Taming Detection Transformers for Medical Object Detection

Taming Detection Transformers for Medical Object Detection

引用

Bildverarbeitung für die Medizin Workshop, BVM 2023

作者： Ickler, Marc K. Baumgartner, Michael Roy, Saikat Wald, Tassilo Maier-Hein, Klaus H. Division of Medical Image Computing German Cancer Research Center Heidelberg Germany Pattern Analysis and Learning Group Heidelberg University Hospital Germany Faculty of Mathematics and Computer Science Heidelberg University Germany Helmholtz Imaging Germany

ISBN: (纸本)9783658416560

The accurate detection of suspicious regions in medical images is an error-prone and time-consuming process required by many routinely performed diagnostic procedures. To support clinicians during this difficult task, several automated solutions were proposed relying on complex methods with many hyperparameters. In this study, we investigate the feasibility of detection transformer (DETR) models for volumetric medical object detection. In contrast to previous works, these models directly predict a set of objects without relying on the design of anchors or manual heuristics such as non-maximum-suppression to detect objects. We show by conducting extensive experiments with three models, namely DETR, Conditional DETR, and DINO DETR on four data sets (CADA, RibFrac, KiTS19, and LIDC) that these set prediction models can perform on par with or even better than currently existing methods. DINO DETR, the best-performing model in our experiments demonstrates this by outperforming a strong anchor-based one-stage detector, Retina U-Net, on three out of four data sets. © 2023 Der/die Autor(en), exklusiv lizenziert an Springer Fachmedien Wiesbaden GmbH, ein Teil von Springer Nature.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Towards Automated BIM and BEM Model Generation using a B-Rep-based Method with Topological Map

Towards Automated BIM and BEM Model Generation using a B-Rep...

引用

2024 Mid-term Symposium on Spatial Information to Empower the Metaverse

作者： Roman, Oscar Mazzacca, Gabriele Farella, Elisa Mariarosaria Remondino, Fabio Bassier, Maarten Agugiaro, Giorgio Trento Italy University of Trento Trento Italy Department of Mathematics Computer Science and Physics University of Udine Italy Department of Civil Engineering TC Construction - Geomatics KU Leuven Faculty of Engineering Technology Ghent Belgium School of Architecture and Built Environment Delft University of Technology Netherlands

In many countries, recent boosts in the construction and renovation sectors and energy efficiency directives are driving a growing interest in the built environment among designers and maintainers. In this context, customized software solutions tailored for Building Information Modelling (BIM) and Building Energy Modelling (BEM) are proving to be indispensable for optimizing operational efficiency within the architecture, Engineering, Construction, Owner, and Operator (AECOO) sector and for facilitating the generation of buildings' Digital Twins (DTs). These DTs rely on accurate geometry and ancillary information (semantics, sensors, etc.) to define properties of single elements, enabling crucial simulations in structural conditions or energy needs. However, BIM and BEM model creation and their enrichment with semantic information are highly time-consuming and prone to manual errors. Hence, there is an increasing demand for automatic methods featuring a high level of geometric accuracy to reconstruct building elements, such as walls, floors, and openings captured via 3D reality-based surveying. This paper introduces an automated method for creating Boundary Representation (B-Rep) models from 3D surveying data for the generation of digital building replicas. The method is based on the detection and computation of topological elements from 3D reality-based point clouds. It proves valuable for architectural or design workflows and for conducting energy or quality system simulations. © Author(s) 2024.

关键词： Architectural design

来源：评论

学校读者我要写书评

暂无评论

Global Bike Go: SAP-Based Mini Business Simulation Games 17

Global Bike Go: SAP-Based Mini Business Simulation Games

引用

17th International Conference on computer Supported Education, CSEDU 2025

作者： Häusler, Robert Rathjens, Malte Werner, Erik Gulyak, Boris Turowski, Klaus Magdeburg Research and Competence Cluster Very Large Business Applications Faculty of Computer Science Otto-von-Guericke University Magdeburg Magdeburg Germany Research Group Non-linear Partial Differential Equations and Geometric Analysis Faculty of Mathematics Otto-von-Guericke University Magdeburg Magdeburg Germany

ISBN: (纸本)9789897587467

Education Service Providers try to support lecturers by offering standardized teaching and learning environments (TLEs). With the help of Bloom's taxonomy, learning environments can be described and modified by creating, adding, or adjusting learning objectives and activities. The paper shows one possible way to adjust SAP S/4HANA TLEs for the individual learning setup. The suggestion is to use mini business simulation games (BSGs) to enhance learners' motivation. These games can tap into the general play instinct, impart knowledge in a playful and practice-oriented approach, give the possibility to try things risk-free and use the positive aspects of game elements for learning success. Exemplary, the idea and implementation of Global Bike Go: Explore Sales as one BSG is presented. Besides the game procedure, the systemic game architecture is elaborated to emphasize flexibility and reusability on the implementation side. Even though game aspects in learning arrangements could enhance the learning itself, gamification is not the Holy Grail for good learning setups. There is a need e.g. to keep the initial motivation up and to impart the knowledge, not just seeking rewards or simply playing the game without taking any learning success out of it. Copyright © 2025 by SCITEPRESS - science and Technology Publications, Lda.

关键词： Enterprise resource planning

来源：评论

学校读者我要写书评

暂无评论

Simulation Secure MQTT Protocol Based on TLS in IoT-Fog Computing Environment 4th

Simulation Secure MQTT Protocol Based on TLS in IoT-Fog Comp...

引用

4th Doctoral Symposium on Computational Intelligence, DoSCI 2023

作者： Kadhim, Ola Najah Ketab, Ahmed Saud Obaid, Ahmed J. Albermany, Salah Abdulhadi Raheem, Ahmed R. Hussien, Naseer Ali Faculty of Computer Science and Mathematics University of Kufa Najaf Iraq College of Engineering Technology National University of Science and Technology Dhi Qar Iraq Information and Communication Technology Research Group Scientific Research Center Al-Ayen University Thi-Qar Iraq

ISBN: (纸本)9789819937158

Fog computing is a way to run a computer that sends data from IoT devices to a group of nodes that get it in real time. These nodes do real-time processing of the data that they get, with the least amount of response time. The nodes send summaries of their analysis to the server regularly. A server-based application then looks at the data that has been sent from the different nodes and tries to come up with actionable information. Fog architecture needs more than just computer power. It needs to be able to communicate quickly between IoT devices and servers. In this paper, a secure Message Queuing Telemetry Transport Protocol (MQTT) broker in fog computing is described as an entity that acts as an intermediate to facilitate communication between MQTT clients, to receive messages that have been published by clients, to filter the messages based on topic, and to disseminate them to subscribers. The MQTT protocol publish/subscribe data transmission is encrypted using Transport Layer Security (TLS) in the proposed method. This has the additional advantages of maintaining network performance, improving channel utilization, lowering the number of loose packets in comparison with the case study that was carried out without TLS, and increasing network latency. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2023.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Skeletonisation Scale-Spaces 10th

Skeletonisation Scale-Spaces

引用

10th International Conference on Scale Space and Variational Methods in computer Vision, SSVM 2025

作者： Gierke, Julia Peter, Pascal Mathematical Image Analysis Group Faculty of Mathematics and Computer Science Campus E1.7 Saarland University Saarbrücken66041 Germany

ISBN: (纸本)9783031923685

The medial axis transform is a well-known tool for shape recognition. Instead of the object contour, it equivalently describes a binary object in terms of a skeleton containing all centres of maximal inscribed discs. While this shape descriptor is useful for many applications, it is also sensitive to noise: Small boundary perturbations can result in large unwanted expansions of the skeleton. Pruning offers a remedy by removing unwanted skeleton parts. In our contribution, we generalise this principle to skeleton sparsification: We show that subsequently removing parts of the skeleton simplifies the associated shape in a hierarchical manner that obeys scale-space properties. To this end, we provide both a continuous and discrete theory that incorporates architectural and simplification statements as well as equivariances. We illustrate how our skeletonisation scale-spaces can be employed for practical applications with two proof-of-concept implementations for pruning and compression. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Musculoskeletal system

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：