检索结果-内蒙古大学图书馆

CNN-based cancer prediction scheme using 5G-assisted federated learning for healthcare Industry 5.0

Alexandria Engineering Journal 2025年 126卷 131-142页

作者： Kumari, Aparna Patadia, Divya Tanwar, Sudeep Pau, Giovanni Alqahtani, Fayez Tolba, Amr Department of Computer Science and Engineering Institute of Technology Nirma University Ahmedabad382481 India Faculty of Engineering and Architecture Kore University of Enna Enna94100 Italy Software Engineering Department College of Computer and Information Sciences King Saud University Riyadh12372 Saudi Arabia Computer Science Department Community College King Saud University Riyadh11437 Saudi Arabia

Healthcare Industry 5.0 has witnessed a transformative change by incorporating Artificial Intelligence (AI), Internet-of-things (IoT), and genomics to provide individualized and patient-centered healthcare. It prioritizes comprehensive health, proactive strategies for chronic diseases like tumors, cancer, etc., and effective cooperation among participants. Much work has been done for cancer prediction using machine learning and deep learning approaches. However, it has yet to be fully explored to protect data privacy and security by limiting data sharing. So, this paper proposes a Convolutional Neural Networks (CNN)-based Cancer Prediction scheme, i.e., CNN-CPS within the context of Healthcare Industry 5.0. The proposed scheme harnesses the capabilities of 5G-assisted Federated Learning (FL), a revolutionary method for predicting cancer occurrences with data privacy, security, and limiting data sharing. Then, it also leverages model data from dispersed systems to boost efficiency. By capitalizing on the speed and efficiency of 5G networks and the collaborative nature of FL, precise cancer predictions can be attained, all while upholding the confidentiality of sensitive data. This integration of technologies has the potential to significantly reshape cancer diagnosis and therapeutic approaches in the Industry 5.0 landscape. Here, 5G can enable real-time data interchange across remote data centers with rapid transmission of data capabilities and low-latency connectivity, enabling more effective and precise model training. Hence, this study examines the FL to predict breast cancer and combines the optimizer weights from several clients to continually enhance the performance of the overall model. The experimental results show the efficacy of the CNN-CPS compared to the existing approaches based on several parameters like low latency (40.77% improvement), accuracy (75%), and loss (0.54). © 2025 The Authors

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Efficient clustering for NOMA with THz mMIMO D2D inspired 6G system model

引用

Telecommunication Systems 2025年第2期88卷 1-16页

作者： Jain, Preksha Gupta, Akhil Rakesh, Nitin Tanwar, Sudeep Pau, Giovanni Alqahtani, Fayez Tolba, Amr Indian Institute of Technology Maharashtra Bombay India Nagpur Campus Maharashtra Pune India Department of Computer Science and Engineering Institute of Technology Nirma University Gujrat Ahmedabad India Faculty of Engineering and Architecture Kore University of Enna Enna94100 Italy Software Engineering Department College of Computer and Information Sciences King Saud University Riyadh12372 Saudi Arabia Computer Science Department Community College King Saud University Riyadh11437 Saudi Arabia

Terahertz (THz) communication, offering unprecedented bandwidth, is a key enabler for the high data rates envisioned in 6G wireless networks. To further enhance capacity and spectral efficiency, this paper proposes a novel 6G hybrid system model integrating THz communication with massive multiple-input multiple-output (mMIMO), cooperative non-orthogonal multiple access (NOMA), and device-to-device (D2D) communication within a heterogeneous network architecture comprising macrocells and small cells. This integrated approach aims to address the escalating demand for connectivity. A crucial aspect of our proposed system is the development of an Antenna Angle Bound (AAB) clustering technique. This innovative method leverages antenna parameters, specifically beam angle, and width, to intelligently group users. By forming clusters based on these spatial characteristics, the AAB technique minimizes inter-user interference, a critical challenge in mMIMO systems. This interference reduction directly contributes to significantly improving the overall system sum rate. Furthermore, we formulate an energy efficiency maximization problem to optimize power allocation coefficients across the various technologies employed. This optimization ensures a balance between achieving high data rates and minimizing energy consumption, a critical consideration for sustainable 6G deployments. The complex optimization problem is tackled using the alternating direction method of multipliers algorithm, which efficiently decomposes the problem into manageable sub-problems. The combination of THz communication, mMIMO, cooperative NOMA, D2D, the AAB clustering technique, and the optimized power allocation promises to deliver a substantial leap in performance for future 6G wireless communication systems, addressing the growing need for higher data rates and improved energy efficiency. The simulation shows that the proposed 6G hybrid system schemes perform better than the traditional models by attaini

关键词： Bandwidth

来源：评论

学校读者我要写书评

暂无评论

A semi-automatic multiple-strategy approach to mapping tree-structured symbolic processing programs

引用

JOURNAL OF SYMBOLIC COMPUTATION 1996年第4-6期21卷 615-634页

作者： Sodan, A GMD Institute for Computer Architecture and Software Technology Germany

Symbolic applications such as expert systems, theorem provers, and computer algebra exhibit dynamic, tree-structured behavior with respect to control and data structures. This is why it is difficult to parallelize a program and get it running efficiently on a parallel computer, especially one with distributed memory. This paper introduces a semi-automatic mapping environment providing a set of support tools, intended for application to large, real-life programs. Mapping can perform adaptive granularity control, dynamic load balancing, and scheduling on parallel programs with dynamic data and control behavior, providing a set of strategies for all components. A set of mapping rules are extracted, describing when which strategy is appropriate. The approach systematically selects and configures its strategies to suit the characteristics of the application and is thus superior to a universal heuristic. (C) 1996 Academic Press Limited

关键词：

来源：评论

学校读者我要写书评

暂无评论

Sensor fusion and motion analysis for medical rehabilitation - The fraunhofer FIRST Motion technology Validation Lab

引用

Systems Science 2010年第1期36卷 41-53页

作者： Kock, Gerd John, Michael Klose, Stefan Ernst, Thilo Popescu, Florin Fraunhofer Institute for Computer Architecture and Software Technology Kekuléstr. 7 D 12489 Berlin Germany

It is a well-known factor that our activities of daily life play an important role for staying healthy. In order to validate different motion analysis techniques for clinical and therapeutic purposes fraunhofer FIRST set up a sensor-controlled testbed. The technologies investigated include time-of-flight cameras, bio-inspired optical stereo-sensors, laminar pressure and proximity sensors as well as body-worn devices including inertial sensors. This paper presents these technologies and sketches the process of sensor fusion and motion analysis being under implementation in the fraunhofer Motion technology Validation Lab.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Modeling for automated test generation - A comparison

Modeling for automated test generation - A comparison

引用

Dagstuhl-Workshop MBEES: Modellbasierte Entwicklung eingebetteter Systeme VIII - 8th Workshop on Model-Based Development of Embedded Systems, MBEES 2012

作者： Lackner, Hartmut Schlingloff, Bernd-Holger Fraunhofer Institute for Computer Architecture and Software Technology FIRST Berlin Germany

In this contribution, we compare and analyze different methodologies of modeling for test generation. As an example, we use an industrial requirement specification given in natural language, which describes a safety function in a hybrid car. We model these requirements with three different paradigms and languages: as the specification imposes several timing constraints, we choose abstract State Machines, Timed Automata and UML2 State Machines to formalize the given requirements. From these models, we employ different tools for generating test cases, and compare the resulting test suites with respect to coverage and fault detection capabilities. We discuss the process of designing the models and the implications for professional software testing.

关键词： software testing

来源：评论

学校读者我要写书评

暂无评论

Web Service Faceplates: Building Web Services Clients with XML and XSLT

引用

2002年

作者： Stephen F Mohr Erik Fuller Michael John Michael Corning Donald Kackman

From the Publisher: Every book out there so far describes how to build Web Services, with some explanation on the creation of the clients. The Web Service design should mean that the client developer need never know t...

ISBN: (纸本)9781861007025

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-core technology for fault tolerant high-performance spacecraft computer systems

Multi-core technology for fault tolerant high-performance sp...

引用

DAta Systems In Aerospace, DASIA 2012

作者： Behr, Peter M. Haulsen, Ivo Van Kampenhout, J. Reinier Pletner, Samuel Fraunhofer Institute for Computer Architecture and Software Technology Fraunhofer FIRST Kékulestr 7 12489 Berlin Germany

ISBN: (纸本)9789290922650

The current architectural trends in the field of multi-core processors can provide an enormous increase in processing power by exploiting the parallelism available in many applications. In particular because of their high energy efficiency, it is obvious that multi-core processor-based systems will also be used in future space missions. In this paper we present the system architecture of a powerful optical sensor system based on the eight core multi-core processor P4080 from Freescale. The fault tolerant structure and the highly effective FDIR concepts implemented on different hardware and software levels of the system are described in detail. The space application scenario and thus the main requirements for the sensor system have been defined by a complex tracking sensor application for autonomous landing or docking manoeuvres.

关键词： Fault tolerance

来源：评论

学校读者我要写书评

暂无评论

THE SUPRENUM SUPERcomputer - GOALS, ACHIEVEMENTS, AND LESSONS LEARNED

引用

PARALLEL COMPUTING 1994年第10-11期20卷 1407-1425页

作者： GILOI, WK GMD Institute for Computer Architecture and Software Technology Rudower Chausses 5 D-12489 Berlin Germany

SUPRENUM is a highly parallel supercomputer for numerical applications. The 5-GFLOPS peak performance of the 256-node system made it the most powerful MIMD architecture of the 'first generation.' Each node is a complete, single-board vector machine with 20 Mflops peak performance (IEEE double precision). SUPRENUM is a distributed memory architecture, resulting in a highly scalable system that can be made fault-tolerant. Message passing is accelerated by dedicated communication hardware in each node. Array access is performed by an 'intelligent' DMA address generator. The SUPRENUM architecture was the first to be based on two-level interconnection structure, consisting of a number of clusters with each cluster consisting of a number of nodes. At the cluster level the nodes are interconnected by two very fast parallel buses. At the system level the clusters are interconnected by a torus structure consisting of serial ring buses. The nodes run under the proprietary, distributed PEACE operating system. Significant efforts were undertaken to make the system programmable, by providing a host of software tools, libraries, and application software packages. The paper discusses the rationale for the SUPRENUM architecture, the goals achieved, and the lessons learned.

关键词： DISTRIBUTED MEMORY architecture VECTOR NODES HIERARCHICAL INTERCONNECTION STRUCTURE DISTRIBUTED OPERATING SYSTEM PROGRAMMING PARADIGMS AND TOOLS

来源：评论

学校读者我要写书评

暂无评论

Criminal emotion detection framework using convolutional neural network for public safety

引用

Scientific Reports 2025年第1期15卷 1-18页

作者： Raval, Jay Jadav, Nilesh Kumar Tanwar, Sudeep Pau, Giovanni Alqahtani, Fayez Tolba, Amr Department of Computer Science and Engineering Institute of Technology Nirma University Gujarat Ahmedabad 382481 India Department of Computer Engineering - AI ML & DS Marwadi University Rajkot 360003 India Faculty of Engineering and Architecture Kore University of Enna Enna 94100 Italy Software Engineering Department College of Computer and Information Sciences King Saud University Riyadh 12372 Saudi Arabia Computer Science Department Community College King Saud University Riyadh 11437 Saudi Arabia

In the era of rapid societal modernization, the issue of crime stands as an intrinsic facet, demanding our attention and consideration. As our communities evolve and adopt technological advancements, the dynamic landscape of criminal activities becomes an essential aspect that requires careful examination and proactive approaches for public safety application. In this paper, we proposed a collaborative approach to detect crime patterns and criminal emotions with the aim of enhancing judiciary decision-making. For the same, we utilized two standard datasets - a crime dataset comprised of different features of crime. Further, the emotion dataset has 135 classes of emotion that help the AI model to efficiently find criminal emotions. We adopted a convolutional neural network (CNN) to get first trained on crime datasets to bifurcate crime and non-crime images. Once the crime is detected, criminal faces are extracted using the region of interest and stored in a directory. Different CNN architectures, such as LeNet-5, VGGNet, RestNet-50, and basic CNN, are used to detect different emotions of the face. The trained CNN models are used to detect criminal emotion and enhance judiciary decision-making. The proposed framework is evaluated with different evaluation metrics, such as training accuracy, loss, optimizer performance, precision-recall curve, model complexity, training time, and inference time. In crime detection, the CNN model achieves a remarkable accuracy of 92.45% and in criminal emotion detection, LeNet-5 outperforms other CNN architectures by offering an accuracy of 98.6%. © The Author(s) 2025.

关键词： Artificial intelligence Convolutional neural networks Deep learning Face emotion detection Public safety

来源：评论

学校读者我要写书评

暂无评论

Declarative Programming for Knowledge Management: 16th International Conference on Applications of Declarative Programming and Knowledge Management, Inap 2005 Fukuoka, Japan, October 22-24, 2005: Revised Selected Papers 1

引用

2007年

作者： Masanobu Umeda Armin Wolf Oskar Bartenstein Ulrich Geske Dietmar Seipel Osamu Takata

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：