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

Capability Assessment of software Product Line Processes in Defense Industry 6

Capability Assessment of Software Product Line Processes in ...

引用

6th International Conference on computer Science and engineering, UBMK 2021

作者： Savaç, Danila Gökalp, Ebru Tarhan, Ayça Kolukisa Software Engineering Research Group Computer Engineering Hacettepe Unv. Ankara Turkey

ISBN: (纸本)9781665429085

The software Product Line (SPL) approach is used to enhance reuse, increase quality, and reduce cost and the project completion time of the developed products. To gain these benefits, companies want to assess their current S P L capability/maturity level and to achieve guidance for improvement. The software Product Line Capability Maturity Model (S P L - C M M) aims to provide a generic assessment methodology that different companies can use. This research aims to apply S P L - C M M in a defense company that has already been studying the S P L transformation. The S P L - C M M has two dimensions: process and capability. The process dimension includes 16 SPL-speciflc processes. The case study includes assessing these 16 SPL-speciflc processes performed in the Company, determining their current process capability levels, and derivation of a road-map for improving to the next capability level. The results support that S P L - C M M is applicable and usable in the defense industry. © 2021 IEEE

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

Tangible landscape: Simulation of changing of hydrology condition due to mining activity at karst area

Tangible landscape: Simulation of changing of hydrology cond...

引用

2017 International Symposium on Geoinformatics, ISyG 2017

作者： Rahman, Cendi Tito Febriandhika, Adhi Isti Ramdani, Fatwa Saputra, Mochamad Chandra Geoinformatics Research Group Faculty of Computer Science Malang Indonesia Software Engineering Research Group Faculty of Computer Science Malang Indonesia

ISBN: (纸本)9781538616833

Indonesia is a country that has the largest karst area in Southeast Asia. With the existence of this large karst area provides advantages due to the composition of rocks from this karst area can be mined for a source of raw materials of cement. And Indonesia is the second largest miner of karst area after Vietnam. Karst area is very important area as a source of water storage, karst area can be found and identified in Indonesia using geological map from Badan Geologi dan Pusat Survey Geologi. Southern Malang is one of the karst areas in Indonesia located in East Java and is a potential area for mining activity for cement industries. This cement mining activity can change the landscape of karst area that can cause many potential disasters such as flooding, erosion, and water and air pollution. In Indonesia the technology that can be used to analyze the impact of mining from karst areas is very limited, the impact that we want to know is the surface hydrological change of the karst area landscape change. This research uses tangible landscape method in GIS to visualize the simulation of surface hydrological changes that can occur in karst area in South Malang, Indonesia. © 2017 IEEE.

关键词： Cements

来源：评论

学校读者我要写书评

暂无评论

Faster and more complete extended static checking for the java modeling language

Faster and more complete extended static checking for the ja...

引用

作者： James, Perry R. Chalin, Patrice Dependable Software Research Group Department of Computer Science and Software Engineering Concordia University Montreal Canada

Extended Static Checking (ESC) is a fully automated formal verification technique. Verification in ESC is achieved by translating programs and their specifications into verification conditions (VCs). Proof of a VC establishes the correctness of the program. The implementations of many seemingly simple algorithms are beyond the ability of traditional Extended Static Checking (ESC) tools to verify. Not being able to verify toy examples is often enough to turn users off of the idea of using formal methods. ESC4, the ESC component of the JML4 project, is able to verify many more kinds of methods in part because of its use of novel techniques which apply multiple theorem provers. In particular, we present Offline User-Assisted ESC (OUA-ESC), a new form of verification that lies between ESC and Full Static Program Verification (FSPV). ESC is generally quite efficient, as far as verification tools go, but it is still orders of magnitude slower than simple compilation. As can be imagined, proving VCs is computationally expensive: While small classes can be verified in seconds, verifying larger programs of 50 KLOC can take hours. To help address the added cost of using multiple provers and this lack of scalability, we present the multi-threaded version of ESC4 and its distributed prover back-end. © 2009 Springer Science+Business Media B.V.

关键词： Java programming language

来源：评论

学校读者我要写书评

暂无评论

Parkinson's disease detection using FMRI images leveraging transfer learning on convolutional neural network 19

Parkinson's disease detection using FMRI images leveraging t...

引用

19th International Conference on Machine Learning and Cybernetics, ICMLC 2020

作者： Sajeeb, Asaduzzaman Nazmus Sakib, A.F.M. Ali Shushmita, Sanjida Ashraf Kabir, S.M. Reza, M.D. Tanzim Parvez, Mohammad Zavid Brac University Software Engineering and HCI Research Group Department of Computer Science and Engineering Bangladesh

ISBN: (纸本)9780738124261

Parkinson's disease(PD) is a neurological condition that is dynamic and steadily influences the movement of the human body. PD influences the central apprehensive system which happens because of the hardship of dopaminergic neurons brought about in a neuro-degenerative incubation. The patients who have PD usually suffer from tremor, unyielding nature, postural shifts, and lessen in unconstrained advancements. There is no particular diagnosis process for PD. PD varies from one person to another person depending on the situation and the family *** Resonance Imaging (MRI), Computed Tomography (CT), ultrasound of the brain, Positron Emission Tomography (PET) scans are common imaging tests to figure out this disease but these tests are not particularly effective. In this research, several tests are run on two types of data group - control and PD affected people. The dataset is collected from the Parkinson's Progression Markers Initiative (PPMI) repository. Then MRI slices are processed from the selected data group into the CNN models. Three different Convolutional Neural Network (CNN) architectures are used in this work to extract features from the data group. The CNN models are InceptionV3, VGG16 and VGG19. These models are used in this research to compare and to get better accuracy. Among these models, VGG19 worked best in the dataset because the accuracy for VGG19 is 91.5% where VGG16 gives 88.5% and inceptionV3 gives 89.5% accuracy on detecting PD. © 2020 IEEE.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Prediction of Epileptic Seizures using Support Vector Machine and Regularization

Prediction of Epileptic Seizures using Support Vector Machin...

引用

2020 IEEE Region 10 Symposium, TENSYMP 2020

作者： Rafid Ahmad, Shaikh Rezwan Sayeed, Samee Mohammad Ahmed, Zaziba Siddique, Nusayer Masud Parvez, Mohammad Zavid Brac University Software Engineering and Hci Research Group Department of Computer Science and Engineering Bangladesh

ISBN: (纸本)9781728173665

Epilepsy is a neurological disorder that causes abnormal behavior and recurrent seizures due to unusual brain activity. This study has attempted to predict seizures in epileptic patients through the process of feature extraction from EEG signals during preictal/ictal and interictal periods, classification and regularization. EEG signals from various parts of the brain from 10 epileptic patients are considered. Fast Fourier Transform (FFT) is used to determine the three features-the phase angle, the amplitude and the power spectral density of the signals. To classify the signals, these features are then used along with Support Vector Machine (SVM) as the classifier. Furthermore, regularization is used to make better predictions i.e. increase prediction accuracy and decrease the rate of false alarm. Finally, the proposed approach is tested on CHB-MIT Scalp EEG data set and it is able to predict epileptic seizures 25 minutes on average before the onset of the seizure with 100% accuracy and a low false-alarm rate of 0.46 per hour. This study intends to contribute to the development of better and advanced seizure predicting devices in the medical field. © 2020 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Solving the families to persons case using EVL+Strace 10

Solving the families to persons case using EVL+Strace

引用

10th Transformation Tool Contest, TTC 2017

作者： Samimi-Dehkordi, Leila Zamani, Bahman Kolahdouz-Rahimi, Shekoufeh MDSE Research Group Department of Software Engineering Faculty of Computer Engineering University of Isfahan Iran

Benchmarx is the subject of bidirectional transformation case study for the Transformation Tool Contest 2017. The example is a wellknown model-to-model transformation from the ATL transformation Zoo named " Families to Persons ". This paper presents a solution to provide the inter-model consistency using the Epsilon Validation Language (EVL) and domain-specific traceability techniques. We call this approach EVL+Strace. Copyright © by the paper's authors. Copying permitted for private and academic purposes.

关键词： computer circuits

来源：评论

学校读者我要写书评

暂无评论

Solving the quality-based software-selection and hardware-mapping problem with ACO 11

Solving the quality-based software-selection and hardware-ma...

引用

11th Transformation Tool Contest, TTC 2018

作者： HoseinDoost, Samaneh Karimi, Meysam Kolahdouz-Rahimi, Shekoufeh Zamani, Bahman MDSE research group Department of Software Engineering Faculty of Computer Engineering University of Isfahan Iran

This paper presents a solution for the Quality-based software-Selection and Hardware-Mapping problem using the ACO algorithm. ACO is one of the most successful swarm intelligence algorithms for solving discrete optimization problems. The evaluation results show that the proposed approach generates correct results for all evaluated test cases. Also, better results in terms of performance and scalability are given in comparison with the ILP and EMFeR approaches. Copyright © by the paper’s authors.

关键词： computer software selection and evaluation

来源：评论

学校读者我要写书评

暂无评论

MoMi: Model-based diagnosis middleware for sensor networks

MoMi: Model-based diagnosis middleware for sensor networks

引用

MidSens'09 - 4th International Workshop on Middleware Tools, Services and Run-Time Support for Sensor networks, Co-located with the 10th ACM/IFIP/USENIX International Middleware Conference

作者： De Jong, Adriaan Woehrle, Matthias Langendoen, Koen Embedded Software Group Delft University of Technology Netherlands Computer Engineering and Networks Lab. ETH Zurich Switzerland

ISBN: (纸本)9781605588513

Numerous deployments of Wireless Sensor networks (WSNs) have shown that intricate problems are introduced by deploying sensor nodes in an unknown and dynamic environment. Consequently, a vital part of a WSN deployment is the supervision of the sensor nodes and detection of abnormalities in their operation. Previous approaches have devised hand-crafted solutions to detect application-specific problems. This work proposes a generic middleware component, named MoMi, to detect such problems in a systematic way. Given a description of normal system behavior MoMi uses a Model-Based Diagnosis (MBD) framework to present the likely causes of system abnormalities to an administrator. This paper demonstrates a proof of concept implementation of MBD on sensor nodes and presents examples of its applicability for typical WSN applications. Copyright 2009 ACM.

关键词： Sensor nodes

来源：评论

学校读者我要写书评

暂无评论

On the potential of software rejuvenation for long-running sensor network deployments

On the potential of software rejuvenation for long-running s...

引用

2010 ICSE Workshop on software engineering for Sensor Network Applications, SESENA 2010, in Conjunction with the 32nd ACM/IEEE International Conference on software engineering, ICSE 2010

作者： Woehrle, Matthias Meier, Andreas Langendoen, Koen Computer Engineering and Networks Lab. ETH Zurich Switzerland Embedded Software Group Delft University of Technology Netherlands

ISBN: (纸本)9781605589695

Many sensor network systems encounter considerable problems after deployment despite extensive simulation and testing during the development. A fundamental issue is unforeseen problems that rarely occur, which makes them hard to reproduce. This work focuses on a class of problems that occur due to so-called software aging: The classical software engineering approach to handle software aging effects is software rejuvenation, i. e., the proactive reset of software components. In this positioning paper we discuss whether software rejuvenation can be applied to resource scarce sensor nodes, which are tightly coupled distributed system. We detail why and how software rejuvenation techniques are applicable to sensor networks and presents the basic building blocks required. © 2010 ACM.

关键词： software testing

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：