检索结果-内蒙古大学图书馆

A swin transformer and CNN fusion framework for accurate Parkinson disease classification in MRI

Scientific Reports 2025年第1期15卷 1-14页

作者： Hussain, Sayyed Shahid Shah, Pir Masoom Dawood, Hussain Degang, Xu Alshamayleh, Ahmad Khan, Muhammad Adnan Ghazal, Taher M. School of Automation Central South University Changsha 410083 China School of Computer Science and Engineering Central South University Changsha 410010 China Department of Computer Science Bacha Khan University Charsadda Pakistan School of Computing Skyline University College Sharjah United Arab Emirates Department of Data Science and Artificial Intelligence Hourani Center for Applied Scientific Research Al-Ahliyya Amman University Amman Jordan Department of Software Faculty of Artificial Intelligence and Software Gachon University Seongnam-si 13120 South Korea Riphah School of Computing and Innovation Riphah International University Lahore Campus Lahore 54000 Pakistan Chitkara University Institute of Engineering and Technology Chitkara University Punjab Rajpura 140401 India Networks and Cybersecurity Department Hourani Center for Applied Scientific Research Al-Ahliyya Amman University Amman Jordan

Parkinson’s disease ranks as the second most prevalent neurological disorder after Alzheimer’s disease. Convolutional neural networks (CNNs) have been extensively employed in Parkinson’s disease (PD) detection using MR images. However, CNN models generally focus on local features while prone to capture global representations. On the other hand, the vision transformer (ViT) excels at capturing global features through its self-attention mechanism, but it compromises local feature representations. Additionally, the varying magnitude of MR data poses a challenge for ViT, potentially leading to the gradient vanishing problem. To address these limitations, this paper proposed a novel framework that combines the Swin-Transformer and CNN to capture both local and global features effectively. To mitigate the gradient vanishing issue in ViT, we used skipped connections and cosine attention mechanism in VIT that preserves the output distribution regardless of input magnitude variations. The proposed model comprises three primary blocks: Transformer-block, convolutional block, and dense-block. The input image is processed concurrently by the cosine transformer and convolutional block. Subsequently, the extracted features from both blocks are concatenated and fed to the dense block for decision-making. The proposed model achieved promesing results of 96%, 97%, 95%, and 95% in terms of accuracy, sensitivity, specificity, and area under the curve, respectively. © The Author(s) 2025.

关键词： CNN Cosine similarity MRI Parkinson’s disease Swin-transformer

来源：评论

学校读者我要写书评

暂无评论

AI-enhanced intrusion detection in smart renewable energy grids: A novel industry 4.0 cyber threat management approach

引用

International Journal of Critical Infrastructure Protection 2025年 50卷

作者： Umar Islam Hanif Ullah Naveed Khan Kashif Saleem Iftikhar Ahmad Department of Computer Science IQRA National University Swat Campus KPK Pakistan School of Computing Ulster University Belfast UK Department of Computer Science & Engineering College of Applied Studies & Community Service King Saud University Riyadh 11362 Saudi Arabia Department of Information Technology Faculty of Computing and Information Technology King Abdulaziz University Jeddah 21589 Saudi Arabia

The rapid adoption of Industry 4.0 technologies in renewable energy grids has significantly improved efficiency and scalability. However, this integration has also amplified cybersecurity risks, making conventional Intrusion Detection Systems (IDS) insufficient against evolving cyber threats. This study proposes a novel AI-enhanced Intrusion Detection System (IDS) tailored for smart renewable energy grids, leveraging a multi-stage detection framework that integrates both supervised and unsupervised learning techniques. The proposed IDS combines Random Forest for signature-based detection and Autoencoders for anomaly-based threat identification, enabling real-time detection of both known and zero-day cyber threats. A comprehensive evaluation using real-world cyberattack datasets demonstrates that the system achieves a detection accuracy of 97.8 %, significantly reducing false positives compared to traditional IDS solutions. This work not only enhances the security and resilience of smart grids but also offers a scalable and adaptable cybersecurity framework for Industry 4.0 applications. The findings contribute to the advancement of AI-driven security mechanisms, ensuring the reliability of critical energy infrastructure in the face of sophisticated cyber threats.

关键词： AI-enhanced intrusion detection Smart grids Renewable energy Industry 4.0 Cybersecurity Machine learning Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Hilbert-Peano and Zigzag: Two Approaches Mapping Pattern of Digital Watermarking for Text Images Authentication 7

Hilbert-Peano and Zigzag: Two Approaches Mapping Pattern of ...

引用

7th International Conference on Software Engineering and Computer Systems and 4th International Conference on Computational Science and Information Management, ICSECS-ICOCSIM 2021

作者： Ghani, Aqilah Abd. Izhar Hisham, Syifak Arshad, Nurul Wahidah Faculty of Computing College of Computing and Applied Sciences Universiti Malaysia Pahang Pekan26600 Malaysia Faculty of Electrical and Electronic Engineering Technology College of Engineering Technology Universiti Malaysia Pahang Pekan26600 Malaysia

ISBN: (纸本)9781665414074

The wide increment of information and communication technology nowadays in line with the usage of digital documents, the user from different organizations such as education, military, medical, business, and others tend to transfer any official file through various digital platforms. Thus, to secure this confidential data, a digital watermarking technique was chosen. This paper proposed an improved mapping pattern method of a fragile watermarking authentication algorithm for text images. There are various methods for watermark embedding, which mapping pattern is one of them. The aim is to validate and compare the SCAN pattern for digital watermarking in order to produce a fast and efficient authentication algorithm. We proposed a Zigzag SCAN pattern algorithm and compared it with the proposed Hilbert-Peano scheme. The result from this paper shows that Zigzag SCAN algorithm contributed to a superior performance in regard to processing time, while PSNR and MSE are similar. © 2021 IEEE.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Semantic parsing of speech using grammars learned with weak supervision

Semantic parsing of speech using grammars learned with weak ...

引用

Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2015

作者： Gaspers, Judith Cimiano, Philipp Wrede, Britta Semantic Computing Group CITEC Bielefeld University Germany Applied Informatics Faculty of Technology Bielefeld University Germany

ISBN: (纸本)9781941643495

Semantic grammars can be applied both as a language model for a speech recognizer and for semantic parsing, e.g. in order to map the output of a speech recognizer into formal meaning representations. Semantic speech recognition grammars are, however, typically created manually or learned in a supervised fashion, requiring extensive manual effort in both cases. Aiming to reduce this effort, in this paper we investigate the induction of semantic speech recognition grammars under weak supervision. We present empirical results, indicating that the induced grammars support semantic parsing of speech with a rather low loss in performance when compared to parsing of input without recognition errors. Further, we show improved parsing performance compared to applying n-gram models as language models and demonstrate how our semantic speech recognition grammars can be enhanced by weights based on occurrence frequencies, yielding an improvement in parsing performance over applying unweighted grammars. © 2015 Association for Computational Linguistics.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Components for COVID19 Outbreak Control Model: A System Dynamics Perspective 7

Components for COVID19 Outbreak Control Model: A System Dyna...

引用

7th International Conference on Software Engineering and Computer Systems and 4th International Conference on Computational Science and Information Management, ICSECS-ICOCSIM 2021

作者： Ibrahim, Aisyah Abdul Kadir, Tuty Asmawaty Daniyal, Hamdan Kamaludin, Adzhar Faculty of Computing College of Computing Applied Sciences Universiti Malaysia Pahang Pahang Pekan Malaysia Faculty of Electrical and Electronic Engineering Technology Universiti Malaysia Pahang Pahang Pekan Malaysia

ISBN: (纸本)9781665414074

The world is facing a massive challenge as the COVID-19 outbreak strikes across the globe. Many efforts have been made to detect, control and contain the coronavirus proactively and aggressively before a further catastrophe occurs. Indeed, ending the global COVID-19 pandemic is not a simple task. It requires adequate planning and implementation of sustainable strategies and interventions to control COVID-19 from keep spreading globally. One way to address this issue is using System Dynamics (SD). With this aim in mind, this paper presents an initial COVID-19 modelling work in the formulation stage of SD methodology. A literature review was carried out on published and unpublished papers to understand the essential outbreak model design structure. Within this process, a total of 15 COVID-19 models in SD were gathered and analysed. As the outcome, this paper highlights the components of the conceptual representation model for the COVID-19 outbreak, which later can serve as the core basis for modelling complex COVID19 outbreak dynamics and interventions for future development. As an implication, a comprehensive model can be developed to support decision making. © 2021 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Effect of copper nanoparticle volume fraction on flow in a 3D lid-driven cavity with phase change materials using molecular dynamics simulation

Case Studies in Chemical and Environmental Engineering

引用

Case Studies in Chemical and Environmental Engineering 2025年 11卷

作者： Sawaran Singh, Narinderjit Singh Hassan, Waqed H. Thiab, Rifqa F. Al-zahy, Younis Mohamed Atiah Salahshour, Soheil Hekmatifar, M. Faculty of Data Science and Information Technology INTI International University Persiaran Perdana BBN Putra Nilai Nilai 71800 Malaysia University of Warith Al-Anbiyaa Kerbala 56001 Iraq Department of Civil Engineering College of Engineering University of Kerbala Kerbala 56001 Iraq College of Health and Medical Techniques Al-Zahraa University for Women Karbala 56100 Iraq Department of Physics College of Education Misan University Maysan Iraq Faculty of Engineering and Natural Sciences Istanbul Okan University Istanbul Turkey Faculty of Engineering and Natural Sciences Bahcesehir University Istanbul Turkey Research Center of Applied Mathematics Khazar University Baku Azerbaijan Fast Computing Center Shabihsazan Ati Pars Tehran Iran

Background: Phase Change Materials are substances characterized by specific properties, including defined melting points and substantial latent heat of fusion. Effective heat transfer management is vital in modern industries, as it supports essential processes across various sectors. Methods: This study investigates the effect of copper nanoparticle volume fraction on flow behavior and thermal dynamics in a 3D lid-driven cavity. This enclosure was a controlled environment filled with phase change materials, designed to optimize thermal energy management. The system configuration comprised a wavy bottom wall and an adaptable upper wall, allowing for dynamic adjustments during the simulation. The results show that as the volume ratio of copper nanoparticles increased from 1 % to 3 %, the steady heat transfer process in the simulated nanoparticles also increased. Increasing the volume ratio from 1 % to 3 % resulted in a decrease in the maximum density of nanoparticles, which decreased from 0.0152 to 0.0146 atom/Å³. Additionally, this increase led to a rise in thermal conductivity from 1.26 to 1.45 W/m·K and in heat flux from 8.26 to 9.95 W/m². Significant Findings: The study demonstrates that optimizing the volume fraction of Cu-NPs in PCMs can significantly enhance thermal conductivity and heat flux, offering potential improvements in thermal energy storage systems. © 2025 The Authors

关键词： Density Heat flux Molecular dynamics simulation Phase change material Thermal conductivity

来源：评论

学校读者我要写书评

暂无评论

Learnability factors of AR usage performance: Validating through survey 7

Learnability factors of AR usage performance: Validating thr...

引用

7th International Conference on Software Engineering and Computer Systems and 4th International Conference on Computational Science and Information Management, ICSECS-ICOCSIM 2021

作者： Hafsa, Sayera Majid, Mazlina Abdul Tawafak, Ragad M Universiti Malaysia Pahang Faculty of Computing College of Computing and Applied Sciences Pahang Malaysia AlBuraimi University College Department of Information Technology Buaimi Oman

ISBN: (纸本)9781665414074

Augmented Reality has become an important learning medium in both educational and learning domain. AR has been in use within the game technology since long. Moreover, greater prospects of AR have been seen during learning and training, specifically in the developed countries. AR has contributed in enhancing the learnability of the users. In order to understand the impact of AR usage, this work starts by preparing the list of factors that influence the learnability with the AR usage. The list of seven (7) factors were identified through Literature Review (LR) using Kolb's Experiential Learning Theory (ELT) 1984. Survey method was used to validate the factor's questions, Next, the validated questions were given to student and academicians for answering through another survey for factor validation. Results showed the identified factors (Motivation, Better lab experience, Enhanced Focus, Satisfaction, Enable Visualization of Invisible Concepts, Better Learning and Performance and Confidence) within the Proposed Learnability Enhancement Model (LEM). Additionally, all the questions were validated with acceptance by experts and 32 academicians through the survey 1. Also, all the factors were accepted with 94% and above acceptance rate in survey 2. The significance of identifying these AR acceptance factors for enhancement of learnability will impact better learnability and performance with AR usage, the study will continue with testing the LEM efficiency through the simulation of AR usage on the real environment in the next phase of this work. © 2021 IEEE.

关键词： Surveys

来源：评论

学校读者我要写书评

暂无评论

Gene Regulatory Network Construction of Ovarian Cancer Based on Passing Attributes between Network for Data Assimilation 8

Gene Regulatory Network Construction of Ovarian Cancer Based...

引用

8th International Conference on Information technology and Multimedia, ICIMU 2020

作者： Ern Isaac, Yeo Zhu Moorthy, Kohbalan MacHap, Logenthiran Mohamad, Mohd Saberi Sallim, Jamaludin College of Computing and Applied Sciences Faculty of Computing Universiti Malaysia Pahang Pahang26300 Malaysia School of Computing Faculty of Engineering Universiti Teknologi Malaysia Skudai81310 Malaysia Faculty of Bioengineering and Technology Universiti Malaysia Kelantan Kelantan17600 Malaysia

ISBN: (纸本)9781728173108

In the field of cancer informatics, there are computational methods or approach exists to share the same goal, which is to unravel the interactions between genes through the effort of gene regulatory network (GRN) inference and construction. Even now, such a complex task has always been challenging and at the same time, this challenge becomes a motivation for new methods to be invented. Hence, the development of PYPANDA, which is a new method for applying the assimilation of several different datasets input for the construction of the gene regulatory network. Moreover, this integration model is capable of redeeming information that was lost when using other methods that only utilize a single dataset, thus having an innate capacity of predicting a more accurate interaction between genes. The proposed improvement of PYPANDA in this article has been able to filter and determine the most informative or significant genes for the construction of the GRN. With this, the differences between the prior network and the improved PYPANDA network can be specified. As such, two new relationships between the highly informative genes that have not been identified before were successfully identified. © 2020 IEEE.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

Tube-based Model Reference Adaptive Control for Vibration Suppression of Active Suspension Systems

引用

IEEE/CAA Journal of Automatica Sinica 2022年第4期9卷 728-731页

作者： Yashar Mousavi Alireza Alfi Ibrahim Beklan Kucukdemiral Afef Fekih IEEE the Department of Applied Science School of ComputingEngineering and Built EnvironmentGlasgow Caledonian University the Faculty of Electrical Engineering Shahrood University of Technology the Electrical and Computer Engineering Department University of Louisiana at Lafayette

Dear editor,With the developments of industrial automation in recent years,vehicle suspension systems have received a great deal of attention in industry and academia due to their critical role in the chassis performance of vehicles[1].The suspension system is expected to guarantee the vehicle’s maneuverability and provide satisfactory ride comfort by absorbing the vibrations arising from the road surface excitations and ensuring road-holding capability and suspension *** by the desirable performance of the model reference adaptive control(MRAC)approach,various literature studies have investigated its performance in diverse linear and nonlinear practical systems[2].

关键词： editor Active guarantee

来源：评论

学校读者我要写书评

暂无评论

Thermal and mechanical attributes and swelling percentage of hydrogels by changing in magnetic field frequency using computer simulation

引用

International Communications in Heat and Mass Transfer 2025年 165卷

作者： Wang, Haoyu Basem, Ali Alhamdi, Sabah F.H. Singh, Narinderjit Singh Sawaran Al-Bahrani, Mohammed Abdullaeva, Barno Salahshour, Soheil Esmaeili, Sh. Medical College Xijing University Shaanxi Xi'an710123 China Faculty of Engineering Warith Al-Anbiyaa University Karbala56001 Iraq Department of Mechanical Engineering University of Misan Misan Amarah62001 Iraq Faculty of Data Science and Information Technology INTI International University Persiaran Perdana BBN Putra Nilai Nilai71800 Malaysia Chemical Engineering and Petroleum Industries Department Al-Mustaqbal University Babylon51001 Iraq Department of Mathematics and Information Technologies Vice-Rector for Scientific Affairs Tashkent State Pedagogical University Tashkent Uzbekistan Faculty of Engineering and Natural Sciences Istanbul Okan University Istanbul Turkey Faculty of Engineering and Natural Sciences Bahcesehir University Istanbul Turkey Research Center of Applied Mathematics Khazar University Baku Turkey Fast Computing Center Shabihsazan Ati Pars Tehran Iran

The thermodynamic, mechanical, and expansion properties of synthetic hydrogels derived from polyacrylamide (PAM) are investigated in this study to the impact of magnetic field frequency (MFF) as an external stimulus. The impact of various MFFs on essential parameters, such as swelling percentage (SP), ultimate strength (US), Young's modulus (YM), heat flux (HF), and thermal conductivity (TC), is assessed using Molecular Dynamics (MD) simulation with LAMMPS software, ranging from 0.01 to 0.05 1/fs. It is important to note that our results indicate that the structural volume decreased from 356,985 to 349,982 Å at 0.05 1/fs as the MFF increased. The alignment of polymer chains in the hydrogel was improved by increasing the MFF, resulting in a more compact structure. Through this compaction, the total structural volume diminished as the chains were drawn closer together, thereby reducing the spaces among them. US experienced a decrease from 0.0325 to 0.0331 MPa, while YM converged to 0.0008 MPa. The alignment and packaging of polymer chains improved, resulting in an increase in the US of hydrogels as the MFF increased. This enhanced alignment resulted in a material that can withstand a larger amount of stress before failing, as a result of the stronger intermolecular interactions. Additionally, the temperature coefficient (TC) increased to 0.56 W/m·K as the MFFs increased. An increase in molecular alignment and a decrease in free volume within the hydrogel can be attributed to the higher MFF. This enhanced alignment enabled the molecules to transfer heat more efficiently, resulting in improved TC and increased HF. These findings illustrate the substantial influence of MFF on hydrogel properties, offering valuable insights for the development of drug delivery systems and responsive materials. © 2025 Elsevier Ltd

关键词： Positive temperature coefficient

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：