检索结果-内蒙古大学图书馆

Novel Feature Extractor Framework in Conjunction with Supervised Three Class-XGBoost Algorithm for Osteosarcoma Detection from Whole Slide Medical Histopathology Images

引用

computers, Materials & Continua 2025年第2期82卷 3337-3353页

作者： Tanzila Saba Muhammad Mujahid Shaha Al-Otaibi Noor Ayesha Amjad Rehman Khan Artificial Intelligence&Data Analytics Lab College of Computer&Information SciencesPrince Sultan UniversityRiyadh11586Saudi Arabia Department of Information Systems College of Computer and Information SciencesPrincess Nourah Bint Abdulrahman UniversityRiyadh11671Saudi Arabia Center of Excellence in Cyber Security(CYBEX) Prince Sultan UniversityRiyadh11586Saudi Arabia

Osteosarcomas are malignant neoplasms derived from undifferentiated osteogenic mesenchymal cells. It causes severe and permanent damage to human tissue and has a high mortality rate. The condition has the capacity to occur in any bone;however, it often impacts long bones like the arms and legs. Prompt identification and prompt intervention are essential for augmenting patient longevity. However, the intricate composition and erratic placement of osteosarcoma provide difficulties for clinicians in accurately determining the scope of the afflicted area. There is a pressing requirement for developing an algorithm that can automatically detect bone tumors with tremendous accuracy. Therefore, in this study, we proposed a novel feature extractor framework associated with a supervised three-class XGBoost algorithm for the detection of osteosarcoma in whole slide histopathology images. This method allows for quicker and more effective data analysis. The first step involves preprocessing the imbalanced histopathology dataset, followed by augmentation and balancing utilizing two techniques: SMOTE and ADASYN. Next, a unique feature extraction framework is used to extract features, which are then inputted into the supervised three-class XGBoost algorithm for classification into three categories: non-tumor, viable tumor, and non-viable tumor. The experimental findings indicate that the proposed model exhibits superior efficiency, accuracy, and a more lightweight design in comparison to other current models for osteosarcoma detection.

关键词： Medical image processing deep learning healthcare image classification histopathology

来源：评论

学校读者我要写书评

暂无评论

Velocity control of a Stephenson III six-bar linkage-based gait rehabilitation robot using deep reinforcement learning

引用

Neural Computing and Applications 2025年第7期37卷 5671-5682页

作者： Kapsalyamov, Akim Brown, Nicholas A. T. Goecke, Roland Jamwal, Prashant K. Hussain, Shahid School of Information Technology and Systems University of Canberra CanberraACT2617 Australia School of Clinical Sciences Queensland University of Technology BrisbaneQLD Australia School of Systems and Computing UNSW CanberraACT Australia Department of Electrical and Computer Engineering Nazarbayev University Nur-Sultan City Kazakhstan

Lower limb rehabilitation robots can help to improve the locomotor capabilities of patients experiencing gait impairments and help medical workers by reducing strain on them. However, since commercially available exoskeletons are expensive and there is a lack of number of physiotherapists many patients are still not able to get proper rehabilitation training. The closed-loop linkage mechanisms have recently drawn much attention in the realization of gait rehabilitation robots. Such mechanisms are affordable and capable of providing suitable trajectories for gait training therapy. In this work, we have proposed a fully operational one degree-of-freedom mechanism which can generate complex naturalistic lower limb trajectories. Although in theory, it is assumed that the constant speed applied at the input crank is sufficient to control the system, in reality, the external forces exerted by human legs and the inertia of the links can greatly alter the rotational velocity at the crank, which may negatively affect the training process. Therefore, we have explored the performance of a deep reinforcement learning-based control algorithm designed to regulate the speed of the input crank to reach satisfactory performance needed for gait rehabilitation training. Experimental evaluations with healthy human subjects were conducted to demonstrate that the mechanism is capable of directing lower limbs on naturalistic gait trajectories with a required walking speed. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Exoskeleton (Robotics)

来源：评论

学校读者我要写书评

暂无评论

LLM-Driven Cross-Platform Code Generation for Polyhedral Optimized NPDP Codes 15th

LLM-Driven Cross-Platform Code Generation for Polyhedral Op...

引用

15th International Conference on Parallel Processing and Applied Mathematics, PPAM 2024

作者： Palkowski, Marek Faculty of Computer Science and Information Systems West Pomeranian University of Technology in Szczecin Zolnierska 49 Szczecin71210 Poland

ISBN: (纸本)9783031856990

This paper explores using large language models (LLM) for automatic and source-to-source programming across various cross-platform languages and libraries, including generating CUDA code for high performance computing (HPC). Our proposed solution aims to demonstrate the capabilities of ChatGPT in generating valid CUDA code based on existing OpenMP code obtained from a polyhedral compilers Traco and Dapt. Specifically, we intend to showcase the model’s proficiency in producing equivalent and valid GPU code. Furthermore, we extend the application of our solution by prompting the AI model to generate similar code for another input benchmark, emphasizing its adaptability and versatility across different scenarios. This approach seeks to highlight the model’s capacity to provide automated and efficient solutions for diverse programming challenges. We chose non-trivial kernels from the non-serial polyadic dynamic programming (NPDP) benchmark with non-uniform loops. The focus is on ensuring code validity and understanding limitations in obtaining valid CUDA code. Additionally, we assess the efficiency and scalability of NVIDIA A100 GPU codes generated by artificial intelligence (AI) models, comparing them with optimized Intel Xeon Gold CPU codes from polyhedral optimizers. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Dynamic programming

来源：评论

学校读者我要写书评

暂无评论

Utilizing TOGAF 10 to Design an Enterprise Architecture for BPRBCo SME Digital Transformation

Utilizing TOGAF 10 to Design an Enterprise Architecture for ...

引用

2025 International Conference on Advancement in Data Science, E-learning and information System, ICADEIS 2025

作者： Mumtaza, Farisa Fikri Mulyana, Rahmat Mukti, Iqbal Yulizar Telkom University Information Systems Department Bandung Indonesia Stockholm University Department of Computer and System Sciences Stockholm Sweden

ISBN: (纸本)9798331513320

Digital Transformation (DT) has become a strategic imperative for Small and Medium Enterprise (SME) banks, including for Bank Perekonomian Rakyat (BPRBCo) in Indonesia, which often face constraints in infrastructure, technology adoption, and regulatory compliance. While prior research has underscored the importance of DT strategy and architecture for success in large banking institutions, how these insights apply to smaller-scale banks remains underexplored. This paper develops an Enterprise Architecture (EA) blueprint for BPRBCo, an SME-scale bank, following a Design Science Research approach that encompasses problem explication, requirement specification, design and development, demonstration, and evaluation. Data was collected through semistructured interviews and triangulated with internal documents. By employing the latest best practice TOGAF Standard 10th Edition from preliminary planning to migration, the study proposes an integrated architecture featuring core banking enhancements and loan management automation. The resulting blueprint, incorporated into BPRBCo's DT Strategy, provides a replicable roadmap for aligning technology investments with business objectives. This research contributes both theoretically by extending EA discourse to smaller-scale banking contexts - and practically by offering actionable guidance for BPR-scale organizations seeking to achieve successful DT despite limited resources. © 2025 IEEE.

关键词： Investments

来源：评论

学校读者我要写书评

暂无评论

Enhancing Performance of Machine Learning Models in Healthcare: An Analytical Framework for Assessing and Improving Data Quality 5th

Enhancing Performance of Machine Learning Models in Healthca...

引用

5th International Conference on Advances in information Communication Technology and Computing, AICTC 2024

作者： Al-Hgaish, Areen Atan, Rodziah Yaakob, Razali Osman, Mohd Hafeez Department of Software Engineering and Information Systems Faculty of Computer Science and Information Technology Universiti Putra Malaysia Serdang44330 Malaysia Department of Computer Science Faculty of Computer Science and Information Technology Universiti Putra Malaysia Serdang44330 Malaysia

ISBN: (纸本)9789819761050

The utilization of Data-Driven Machine Learning (DDML) models in the healthcare sector poses unique challenges due to the crucial nature of clinical decision-making and its impact on patient outcomes. A primary concern in this domain is the data quality that forms the basis for these models, which is essential for their effectiveness. While numerous studies are dedicated to leveraging Machine Learning (ML) to enhance patient care, a substantial gap exists in understanding and evaluating the quality of training data before training ML models. This issue is exacerbated by the lack of well-defined standards to ensure that data characteristics align with the specific goals of ML in healthcare. To address this, our study introduces a conceptual three-dimensional framework focusing on data accuracy, completeness, and consistency aimed at assessing and improving the quality of training data. This framework is designed to enhance the performance, predictability, and interpretability of healthcare-specific ML models and reduce biases, thus bridging current research gaps and laying the groundwork for future developments in ML-driven healthcare systems. This paper presents the initial step for our proposed Data Quality Framework (DQF), which addresses the three dimensions mentioned above. It discusses its potential implications and applications in healthcare data, and its main goal is to provide a comprehensive overview of the proposed DQF, illustrating its significance in advancing healthcare data quality and ultimately improving patient outcomes. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Data accuracy

来源：评论

学校读者我要写书评

暂无评论

History of Artificial Lighting, From Fire to LED [History]

引用

IEEE INDUSTRY APPLICATIONS MAGAZINE 2025年第2期31卷 10-25页

作者： Canale, Laurent Hamady, Mohamad S & C Electric Company Chicago Illinois USA Research Engineer CNRS LAPLACE Laboratory UMR 5213 Paul Sabatier University Toulouse Cedex 9 France Computer Systems Department Faculty of Computer and Information Sciences Ain Shams University Cairo Cairo Egypt

Having become so present and accessible, artificial light has been forgotten in the same way as the air we breathe. It is obvious and is only noticed by its often-exceptional absence. Its omnipresence is such that it goes to excess, resulting in light pollution;environmental impacts;impacts on fauna and flora;and, even more serious, impacts on human health. But it has also been an essential driving force in the evolution of humanity. From the first traces of the mastery of fire as a light source up to the "electronic" light of LEDs, we will travel through more than 500,000 years of history of lighting technologies and more particularly focus on the last 150 years, which have ended with the LED revolution.

关键词： Force Flora Fauna Light emitting diodes Artificial light History Light sources

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Based Side-Channel Attack Detection for Mobile Devices Security in 5G Networks

引用

清华大学学报自然科学版（英文版） 2025年第3期30卷 1012-1026页

作者： Amjed A.Ahmed Mohammad Kamrul Hasan Ali Alqahtani Shayla Islam Bishwajeet Pandey Leila Rzayeva Huda Saleh Abbas Azana Hafizah Mohd Aman Nayef Alqahtani Center for Cyber Security Faculty of Information Science and TechnologyUniversiti Kebangsaan MalaysiaBangi 43600Malaysia Imam Alkadhim University College Department of Computer Techniques EngineeringBaghdad 10066Iraq Center for Cyber Security Faculty of Information Science and TechnologyUniversiti Kebangsaan MalaysiaBangi 43600Malaysia Department of Networks and Communications Engineering College of Computer Science and Information SystemsNajran UniversityNajran 61441Saudi Arabia Institute of Computer Science and Digital Innovation UCSI UniversityKuala Lumpur 56000Malaysia Department of Intelligent Systems and Cyber Security Astana IT UniversityAstana 20000Kazakstan Department of Computer Science College of Computer Science and EngineeringTaibah UniversityMadinah 42353Saudi Arabia Department of Electrical Engineering College of EngineeringKing Faisal UniversityAl-Hofuf 31982Saudi Arabia

Mobile devices within Fifth Generation(5G)networks,typically equipped with Android systems,serve as a bridge to connect digital gadgets such as global positioning system,mobile devices,and wireless routers,which are vital in facilitating end-user communication ***,the security of Android systems has been challenged by the sensitive data involved,leading to vulnerabilities in mobile devices used in 5G *** vulnerabilities expose mobile devices to cyber-attacks,primarily resulting from security ***-permission apps in Android can exploit these channels to access sensitive information,including user identities,login credentials,and geolocation *** such attack leverages"zero-permission"sensors like accelerometers and gyroscopes,enabling attackers to gather information about the smartphone's *** underscores the importance of fortifying mobile devices against potential future *** research focuses on a new recurrent neural network prediction model,which has proved highly effective for detecting side-channel attacks in mobile devices in 5G *** conducted state-of-the-art comparative studies to validate our experimental *** results demonstrate that even a small amount of training data can accurately recognize 37.5％of previously unseen user-typed ***,our tap detection mechanism achieves a 92％accuracy rate,a crucial factor for text *** findings have significant practical implications,as they reinforce mobile device security in 5G networks,enhancing user privacy,and data protection.

关键词： Fifth Generation(5G)networks smartphone information leakage Side-Channel Attack(SCA) deep learning

来源：评论

学校读者我要写书评

暂无评论

A Framework for Identifying Influential Spreaders of Drug Use in Online Social Networks

A Framework for Identifying Influential Spreaders of Drug Us...

引用

2025 International Conference on Intelligent Control, Computing and Communications, IC3 2025

作者： Al-Ghannam, Reem Ykhlef, Mourad Al-Dossari, Hmood College of Computer and Information Sciences King Saud University Information Systems Department Riyadh Saudi Arabia

ISBN: (纸本)9798331527495

Online social networks have become key platforms for spreading drug-related content, which presents a risk to the public, especially for people who are more susceptible to drug use and addiction. Generating vast amounts of data, such networks offer valuable insights for computational analysis. In this paper, we introduce a new framework to identify influential spreaders who use social networks to promote drug-related content. It does so by means of influence maximization (1M) algorithms;in particular, it uses an approach called 'label neighbor-based selection of seed nodes (LNSSN)'. It also proposes new metrics for the percentages of types of users affected, comprehensively assessing each algorithm's effectiveness across different network types and combinations of scenarios. This framework is designed to assist governments, technology companies, and law enforcement agencies in prioritizing and addressing sources of drug-related content on social networks. © 2025 IEEE.

关键词： Tweets

来源：评论

学校读者我要写书评

暂无评论

A Neutrosophic Approach to Robust Web Security: Mitigating XSS Attacks

引用

Neutrosophic Sets and systems 2025年 79卷 1-22页

作者： Salama, A.A. Aboelfotoh, El-Said F. El-Bakry, Hazem M. Khalid, Huda E. Essa, Ahmed K. Sabbagh, Ramiz El-Morshedy, Doaa S. Department of Mathematics and Computer Science Faculty of Science Port Said University Egypt Department of Information Systems Faculty of Computers and Information Mansoura University Mansoura Egypt Telafer University Telafer Iraq Department of the Scientific Affairs Telafer University Mosul Iraq

Cross-Site Scripting (XSS) is one of the most grievous vulnerabilities-a pitfall through which web applications are affected. These types of attacks are complex, and the available threat landscape is always changing, making it hard for conventional security tools to effectively detect or prevent these types of attacks. We present here an approach that detects and prevents XSS attacks on Web pages. Since Neutrosophism works with different kinds of data, it aims at the validity degree of the attack. This way the system understands the different types of attacks and allows the system to act more effectively. Our system combines (1) static analysis-to look into the code behind the website-with (2) dynamic analysis-to watch the website in action. Moreover, a proactive defense watches your user behavior and scrubs every input/output. © 2025, University of New Mexico. All rights reserved.

关键词： Websites

来源：评论

学校读者我要写书评

暂无评论

Exploring The Role of Interpretability in Adversarial Defense Mechanisms based Malware Classification 6

Exploring The Role of Interpretability in Adversarial Defens...

引用

6th International Conference on Mobile Computing and Sustainable Informatics, ICMCSI 2025

作者： Alhawari, Assem Ebadinezhad, Sahar Department of Computer Information Systems Near East University Nicosia99138 Cyprus Near East University Nicosia99138 Cyprus

ISBN: (纸本)9798331522667

This systematic literature review (SLR) presents a comprehensive overview of the current state of interpretability techniques in malware classification based on adversarial defense mechanisms, challenges, and future directions. Several ML and DL approaches have been integrated into the malware detection and classification defense systems, where adversarial attacks represent a crucial security threat against these defense systems. The interpretability techniques have been found very important to be applied to enhance the performance of these security systems and develop more explainable models and decisions for users and security experts. The SLR was conducted by combining and reviewing scientific literature on adversarial defense mechanisms-based interpretability techniques in the field of malware classification published between 2013 and 2024. This SLR presents a new insight into the categorization of interpretability techniques' implications in adversarial defense systems. We evaluate the importance and effectiveness of interpretability techniques by investigating ML models, adversarial attacks, evaluation methods, datasets, user trust, and malware features. Furthermore, the study provides challenges and future research directions for further existing issues. © 2025 IEEE.

关键词： Adversarial machine learning

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：