检索结果-内蒙古大学图书馆

A roulette wheel-based pruning method to simplify cumbersome deep neural networks

Neural computing and Applications 2024年第22期36卷 13915-13933页

作者： Chan, Kit Yan Yiu, Ka Fai Cedric Guo, Shan Jiang, Huimin School of Electrical Engineering Computing and Mathematics Sciences Curtin University Bentley Australia Department of Applied Maths The Hong Kong Polytechnic University Hong Kong School of Business Macau University of Science and Technology China

Deep neural networks (DNNs) have been applied in many pattern recognition or object detection applications. DNNs generally consist of millions or even billions of parameters. These demanding computational storage and requirements impede deployments of DNNs in resource-limited devices, such as mobile devices, micro-controllers. Simplification techniques such as pruning have commonly been used to slim DNN sizes. Pruning approaches generally quantify the importance of each component such as network weight. Weight values or weight gradients in training are commonly used as the importance metric. Small weights are pruned and large weights are kept. However, small weights are possible to be connected with significant weights which have impact to DNN outputs. DNN accuracy can be degraded significantly after the pruning process. This paper proposes a roulette wheel-like pruning algorithm, in order to simplify a trained DNN while keeping the DNN accuracy. The proposed algorithm generates a branch of pruned DNNs which are generated by a roulette wheel operator. Similar to the roulette wheel selection in genetic algorithms, small weights are more likely to be pruned but they can be kept;large weights are more likely to be kept but they can be pruned. The slimmest DNN with the best accuracy is selected from the branch. The performance of the proposed pruning algorithm is evaluated by two deterministic datasets and four non-deterministic datasets. Experimental results show that the proposed pruning algorithm generates simpler DNNs while DNN accuracy can be kept, compared to several existing pruning approaches. © The Author(s) 2024.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Natural Language Processing Revolution From Humble Beginnings to Deep Learning and Beyond 4

Natural Language Processing Revolution From Humble Beginning...

引用

4th IEEE International Conference on ICT in Business Industry and Government, ICTBIG 2024

作者： Smarts, Nyalalani Selvaraj, Rajalakshmi Kuthadi, Venumadhav Botswana International University of Science and Technology School of Pure and Applied Sciences Department of Computing and Informatics Palapye Botswana

ISBN: (纸本)9798331518981

This paper explores the intricate development of Natural Language Processing (NLP), a domain which is centered at the core of computational intelligence and human communication. This research is inspired by the need to understand the foundations of NLP and how it has influenced the development of human-computer interactions, language comprehension systems and information retrieval techniques. It explores the transformational effect of deep learning and attention-based models such as the third-generation Generative Pre-trained Transformer (GPT-3), Text-to-Text Transfer Transformer (T5) and Bidirectional Encoder Representations from Transformers (BERT). The models mentioned above have greatly improved the capability to comprehend and generate human-like language using computers. The originality of the work is also reflected on its comprehensive overview of key NLP concepts, tracing chronological advancements, exploring deep learning innovations, and discussing effective pruning techniques to optimize model performance. By reviewing the history of NLP, this research not merely brings the past into focus but suggests future developments for scholars to investigate and find solutions for current challenges in NLP. Its results not only act as a guide for practitioners today but also suggest new directions for research and development that will help meet the challenges of tomorrow in this dynamic discipline of NLP. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

q-Difference Recurrence Relations of Aleph Function with Generalization to nth Derivative

引用

International Journal of applied and Computational Mathematics 2024年第2期10卷 1-14页

作者： Bhat, Mohammad Younus Maqbool, Humaira Bhat, Altaf A. Department of Mathematical Sciences Islamic University of Science and Technology Kashmir Awantipora India Mathematics and Computing Skills Preparatory Studies Centre University of Technology and Applied Sciences Salalah Oman

Sharma and Jain studied the basic analogue of Meijer’s G-function by using the methods of q-calculus and constructed the q-difference operators and their lie algebra. In this article, we employ the same technique for basic anlogue of the Aleph function defined by Dutta et al. and thus on account of general nature of q-analogue of Aleph function,the q-difference recurrence relations of the Aleph function are obtained and an enumerous number of new and known results are special cases of our main results. Also the recurrence relation of I-function and Fox-H function are deduced as special cases by suitable substitutions. Furthermore the generalisation to nth partial derivatives and the required relations are also discussed which are quite general in nature and capable of producing a number of new and known results. © The Author(s), under exclusive licence to Springer Nature India Private Limited 2024.

关键词： 133D05 20C20 42C40 Aleph function q-Analogue q-Calculus q-Gamma function Recurrence relations

来源：评论

学校读者我要写书评

暂无评论

Automated Radiology Report Generation from Chest X-ray Scans Using Deep Learning 6th

Automated Radiology Report Generation from Chest X-ray Scans...

引用

6th International Conference on Recent Innovations in computing, ICRIC 2023

作者： Veer, V. Druva Priya, S. Baghavathi Tamilselvi, M. Department of Computer Science and Engineering Amrita School of Computing AmritaVishwaVidyapeetham Chennai India Information Technology Department University of Technology and Applied Sciences Nizwa Oman

ISBN: (纸本)9789819778614

A chest X-ray is a common diagnostic tool for many thoracic illnesses. Interpreting these images and coming up with accurate diagnostic results is a difficult and time-consuming task for radiologists. Recent results using deep learning approaches to automate the analysis of chest X-rays are promising. This paper provides a comprehensive description of deep learning techniques used to chest X-ray processing for the diagnosis of several diseases, including TB, pneumonia, and COVID-19. This paper provide a summary of the primary deep learning architectures, such as convolutional neural networks (CNNs), recurrent neural networks (RNNs), and attention models, that are used for disease classification, localization, segmentation, and report generation from chest X-rays. This paper also discuss explainability techniques that are used to offer transparency and increase trust in model predictions. Along with existing issues, future directions are taken into consideration, such as multimodal learning, few-shot learning, and model evaluation. This paper explains the model which takes less time and give the optimal results. In order to facilitate future research into developing AI systems that are more accurate, understandable, and advantageous from a medical standpoint, this article provides an overview of the most current developments in deep learning techniques for automated chest X-ray diagnosis. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Digital Maturity Assessment Model (DMAM): assimilation of Design Science Research (DSR) and Capability Maturity Model Integration (CMMI)

Digital Transformation and Society

引用

Digital Transformation and Society 2025年第2期4卷 128-152页

作者： Omol, Edwin Juma Mburu, Lucy Waruguru Abuonji, Paul Anyango Department of Software Development and Information Systems (SDIS) School of Technology KCA University Nairobi Kenya Chair of Department - Networks and Applied Computing (NAC) School of Technology KCA University Nairobi Kenya KCA University Nairobi Kenya

Purpose: This study introduces the Digital Maturity Assessment Model (DMAM), a model tailored to assess the digital maturity of SMEs, tracing its development from addressing business challenges to establishing a comparative analysis framework grounded in Resource Dependence Theory (RDT). Design/methodology/approach: DMAM is based on positivist philosophy and objectivist epistemology, supported by Design Science Research (DSR) and Capability Maturity Model Integration (CMMI). The methodology involves iterative development, from problem identification to creating a practical solution for assessing SMEs' digital maturity and guiding digitalization efforts. Findings: DMAM offers a clear and specific methodology, distinguishing itself by addressing the unique needs of SMEs, particularly resource-dependent ones. The model’s development fills critical gaps in existing literature and provides a practical artifact for SMEs' digitalization. Originality/value: DMAM is original in its focus on the specific needs of resource-dependent SMEs, offering actionable recommendations and addressing shortcomings in existing models. It serves as a foundational framework for SMEs' digital transformation, making a significant contribution to the digital maturity assessment literature. © 2024, Edwin Juma Omol, Lucy Waruguru Mburu and Paul Anyango Abuonji.

关键词： Capability Maturity Model Integration (CMMI) Design Science Research (DSR) Digital Maturity Assessment Model (DMAM) Goal Question Metric (GQM) Proof-of-Concept (POC) & Minimum Viable Product (MVP) Resource Dependence Theory (RDT)

来源：评论

学校读者我要写书评

暂无评论

Work in Progress: The Effectiveness of Knowledge Management System on Companies Performance 3

Work in Progress: The Effectiveness of Knowledge Management ...

引用

3rd International Conference on computing and Information technology, ICCIT 2023

作者： Al Akhzami, Fatma Hamed Al Hasani, Malak Hamed Al Rahbi, Muna Saif University of Technology and Applied Science College of Computing and Information Sciences Information Technology Department Muscat Oman

ISBN: (纸本)9798350321487

In the current challenging environment with the highly speed development that the companies' world faced, finding and keeping up with the auxiliary tools and systems has become a requirement and a necessity to deal with the complexity and uncertainty changes. One of the efficient ways to reach the previous goal is to implement knowledge management system (KMS). KMS is a systematic way that stores and retrieves knowledge to improve the process of understanding and collaboration [1]. The major purpose of this research is to examine the effectiveness of the knowledge management system on performance and a case study of Petroleum Development Oman (PDO) company is selected. This research will adopt mixed methodology consisting of quantitative and qualitative approaches through conducting questionnaire and interviews primarily. In addition to evaluate literature review as additional source. After that, the collected data will be analyzed with the appropriate data analysis technique. © 2023 IEEE.

关键词： Knowledge based systems

来源：评论

学校读者我要写书评

暂无评论

Intelligent cache and buffer optimization for mobile VR adaptive transmission in 5G edge computing networks

引用

Digital Communications and Networks 2024年第5期10卷 1234-1244页

作者： Junchao Yang Ali Kashif Bashir Zhiwei Guo Keping Yu Mohsen Guizani Chongqing Key Laboratory of Intelligent Perception and BlockChain Technology School of Artificial IntelligenceChongqing Technology and Business UniversityChongqing400067China Department of Computing and Mathematics Manchester Metropolitan UniversityUK Woxsen School of Business Woxsen UniversityHyderabad 502345India Department of Computer Science and Mathematics Lebanese American UniversityBeirutLebanon Graduate School of Science and Engineering Hosei UniversityTokyo184-8584Japan Machine Learning Department Mohamed Bin Zayed University of Artificial Intelligence(MBZUAI)United Arab Emirates

Virtual Reality(VR)is a key industry for the development of the digital economy in the *** VR has advantages in terms of mobility,lightweight and cost-effectiveness,which has gradually become the mainstream implementation of *** this paper,a mobile VR video adaptive transmission mechanism based on intelligent caching and hierarchical buffering strategy in Mobile Edge computing(MEC)-equipped 5G networks is proposed,aiming at the low latency requirements of mobile VR services and flexible buffer management for VR video adaptive *** support VR content proactive caching and intelligent buffer management,users’behavioral similarity and head movement trajectory are jointly used for viewpoint *** tile-based content is proactively cached in the MEC nodes based on the popularity of the VR ***,a hierarchical buffer-based adaptive update algorithm is presented,which jointly considers bandwidth,buffer,and predicted viewpoint status to update the tile chunk in client ***,according to the decomposition of the problem,the buffer update problem is modeled as an optimization problem,and the corresponding solution algorithms are ***,the simulation results show that the adaptive caching algorithm based on 5G intelligent edge and hierarchical buffer strategy can improve the user experience in the case of bandwidth fluctuations,and the proposed viewpoint prediction method can significantly improve the accuracy of viewpoint prediction by 15%.

关键词： Virtual reality Adaptive transmission Edge cache Buffer management 5G Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

On Some Novel Results About the Behavior of Some Numerical Solutions of a Neutrosophic Generalized Half – Linear Second Order Differential Equation

引用

Neutrosophic Sets and Systems 2025年 76卷 551-569页

作者： Alrayes, Norah Mousa Abualhomos, Mayada Abbas Ali, Mutaz Mohamed Shatarah, Amani Mahmoud Alhejoj, Mai Mousa Al-Husban, Abdallah Department of Mathematics College of Science Taibah University Al-Madinah Saudi Arabia Applied Science Private University Amman11931 Jordan Zayed Military College Department of General Science United Arab Emirates Department of Basic Sciences and Informatics Al-Balqa Applied University Jordan Department of Mathematics Faculty of Science and Technology Irbid National University P.O. Box: 2600 Irbid Jordan Jadara Research Center Jadara University Irbid21110 Jordan

The generalized neutrosophic differential equation is a differential equation with neutrosophic real variable x 4- yl instead of classical real variable x. This research is devoted to studying the oscillation of generalized neutrosophic half linear second order differential equation with the negative and delayed neutral term as follows: (r(k + ml)z (k 4- ml)) 4- c(k 4- ml)f [x(f)(k 4- ml)),r(k 4- ml)z (k 4- ml)) = 0. Also, the generalized neutrosophic half-linear differential equation of the second order with max term featured by the following from: [r(k 4- ml)z (fc 4- ml)] 4- c(k 4- ml) MAXse[gQk+mlXk+mI] f (x(s),r(k 4- ml)z (k 4- ml)) = 0, with z(k + ml) = x(k + ml) — a(k + ml)x(d(k + ml)), Where we illustrate a numerical approach for the oscillation with indeterminacy element that represents the neutrosophic approach. © 2025, university of New Mexico. All rights reserved.

关键词： Riccati equations

来源：评论

学校读者我要写书评

暂无评论

Dynamic generative R-CNN

引用

Neural computing and Applications 2025年第10期37卷 7107-7120页

作者： Saffarini, Rasha Khamayseh, Faisal Awwad, Yousef Sabha, Muath Eleyan, Derar IT Engineering Arab American University Jenin Palestine Department of Computer Science Palestine Polytechnic University Hebron Palestine Department of Computer System Engineering Palestine Technical University Tulkarm Palestine Department of Multimedia Technology Arab American University Jenin Palestine Department of Applied Computing Palestine Technical University Tulkarm Palestine

Different techniques have been developed for object detection and recognition. These techniques can be divided into single-shot and two-shot methods. Single-shot methods focus on real-time applications, while two-shot methods are used in applications requiring higher accuracy. However, different versions of the two-shot techniques produce limited results in terms of accuracy and speed, or both. Therefore, this study proposes a novel model called dynamic generative R-CNN (DGR-CNN) that reduces the number of proposed regions using a dynamic programming model that applies the graph similarity method over graph-based image segmentation. Additionally, the proposed model employs DCGAN technique to improve detection performance. DGR-CNN reduces the overall detection and classification time and enhances the detection accuracy. The PASCAL VOC2007 and MS COCO datasets were utilized to evaluate the model. The results showed that DGR-CNN significantly reduces the number of candidate regions compared to the selective search algorithm employed in R-CNN and fast R-CNN. Although fast R-CNN utilizes 2000 regions and faster R-CNN utilizes 300 regions, DGR-CNN reduces the number of regions to approximately 130. The mean average precision of the proposed method was 75.1% on the PASCAL VOC2007, while fast and faster R-CNN scored 66.9% and 69.9%, respectively. Moreover, the DGR-CNN model significantly improved the classification accuracy when tested on the MS COCO dataset, achieving an MAP of 68.76%, compared with 32.64% and 42.3% for fast and faster R-CNN. This increase in accuracy was achieved without significantly compromising the speed compared with faster R-CNN. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Strategic Defense Post Allocation Using the Corona Cover Set for Enhanced Military Zone Security 1

Strategic Defense Post Allocation Using the Corona Cover Set...

引用

1st International Conference for Women in computing, InCoWoCo 2024

作者： Niveditha, P. Mahadevan, G. Sivagnanam, C. Department of Mathematics Tamilnadu Gandhigram India University of Technology and Applied Sciences-Sur Mathematics and Computing Skills Unit Oman

ISBN: (纸本)9798331518943

Defense forces are vital for national safety, peace-keeping, disaster response, and economic support. They require strong support systems, medical access, rapid deployment, and effective command centers to operate efficiently. Proper placement and a well-structured defense strategy focusing on sustainability and readiness are essential for ensuring safety and stability for both military and civilians. Recently G. Mahadevan *** established the concept of Corona covering number of a graph and obtained many results. A vertex cover set $S\subseteq V(G)$ is a corona cover set if every vertex $v\in S$ such that $d_{\langle S\rangle}(v)=1$ or there exist a vertex $u\in S$ with $d_{\langle S\rangle}(u)=1$ and $uv\in E$. The least cardinality of a corona cover set is the corona covering number of a graph and it is expressed as $\tau_{C}(G)$. In this article, the investigation of corona covering number in the strategic placement of defense posts within military zones, aiming to enhance operational efficiency and effectively deter unauthorized incursions has been attained. © 2024 IEEE.

关键词： Disasters

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：