检索结果-内蒙古大学图书馆

FusionMamba: dynamic feature enhancement for multimodal image fusion with Mamba

Visual Intelligence 2024年第1期2卷 1-18页

作者： Xie, Xinyu Cui, Yawen Tan, Tao Zheng, Xubin Yu, Zitong School of Computing and Information Technology Great Bay University Guangdong Dongguan 523000 China Faculty of Applied Sciences Macao Polytechnic University Macao Department of Electrical and Electronic Engineering The Hong Kong Polytechnic University Hong Kong

Multimodal image fusion aims to integrate information from different imaging techniques to produce a comprehensive, detail-rich single image for downstream vision tasks. Existing methods based on local convolutional neural networks (CNNs) struggle to capture global features efficiently, while Transformer-based models are computationally expensive, although they excel at global modeling. Mamba addresses these limitations by leveraging selective structured state space models (S4) to effectively handle long-range dependencies while maintaining linear complexity. In this paper, we propose FusionMamba, a novel dynamic feature enhancement framework that aims to overcome the challenges faced by CNNs and Vision Transformers (ViTs) in computer vision tasks. The framework improves the visual state-space model Mamba by integrating dynamic convolution and channel attention mechanisms, which not only retains its powerful global feature modeling capability, but also greatly reduces redundancy and enhances the expressiveness of local features. In addition, we have developed a new module called the dynamic feature fusion module (DFFM). It combines the dynamic feature enhancement module (DFEM) for texture enhancement and disparity perception with the cross-modal fusion Mamba module (CMFM), which focuses on enhancing the inter-modal correlation while suppressing redundant information. Experiments show that FusionMamba achieves state-of-the-art performance in a variety of multimodal image fusion tasks as well as downstream experiments, demonstrating its broad applicability and superiority. © The Author(s) 2024.

关键词： Feature enhancement Image fusion Mamba Multimodal

来源：评论

学校读者我要写书评

暂无评论

An Integrated Image Classification Approach to Detect the Flood Prone Areas using Sentinel-1 Images 10

An Integrated Image Classification Approach to Detect the Fl...

引用

17th INDIACom;2023 10th International Conference on computing for Sustainable Global Development, INDIACom 2023

作者： Siddique, Mohammed Ahmed, Tasneem Husain, Mohd Shahid Integral University Advanced Computing Research Lab Department of Computer Application Lucknow India Majan University College Faculty of Information Technology Muscat Oman CAS-Ibri University of Technology and Applied Sciences Department of Information Technology Muscat Oman

ISBN: (纸本)9789380544472

The untimely monsoon floods and the rise in the level of rivers in the north Indian state of Uttar Pradesh (UP) is a major challenge for coordinating relief and rescue operations. To address this challenge, the experts that are deploying a variety of techniques to evaluate the damages might get useful information from synthetic aperture radar (SAR) images which offer images in close to real-time. The Sentinel-1A satellite images from the European Space Agency provide C-band SAR images that have helped researchers achieve enhanced processes of flood detection and flood mapping in flood-prone areas. In regular cases, the Random Forest (RF) and K-Nearest Neighbor (KNN) supervised classification techniques provide higher accuracies than the unsupervised K-Means classification techniques. The integrated approach with the resultant accuracy provides long-reliable elucidation towards flood damages and assessment control. Thenceforth, the RF and KNN supervised classifications based outcomes were integrated with the outcomes of K-Means iterative clustering unsupervised classification producing an enhanced overall accuracy. The overall accuracy from the integrated approach for the city of Basti and Ayodhya is 97% and 93.8% which is higher than the accuracies derived from the supervised and unsupervised classifications. Further, these processed results when refined by time-series analysis over a number of years along with implementing change detection techniques would help in monitoring the flood situation and undertaking precautionary measures. © 2023 Bharati Vidyapeeth, New Delhi.

关键词： Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

Classification Framework for Autoimmune Liver Disease using Machine Learning and Deep Learning Techniques

Classification Framework for Autoimmune Liver Disease using ...

引用

technology Innovation Management and Engineering Science International Conference (TIMES-iCON)

作者： E. Ben George G. Jeba Rosline Abraham Varghese Rajesh D. Gnana Department of Information Technology College of Computing and Information Sciences University of Technology and Applied Sciences Muscat Sultanate of Oman Department of Information Technology College of Computing and Information Sciences University of Technology and Applied Sciences Al Mussanah Sultanate of Oman

ISBN: (数字)9798350362602

ISBN: (纸本)9798350362619

Autoimmune diseases affect people of all ages, genders, and ethnic backgrounds, making it one of the most widespread health issues we face today. These disorders occur when the immune system mistakenly targets healthy cells within the body and causing a wide range of potentially life-threatening diseases. There are over 80 recognized autoimmune disorders, including type-1 diabetes, rheumatoid arthritis, Graves’ disease, alopecia, celiac disease, and autoimmune liver disease(AiLD). Autoimmune liver disease is one such chronic disorder characterized by liver inflammation and damage. If not detected on time and untreated within the given time, it might lead to liver cirrhosis or liver cancer. Identifying and treating autoimmune liver disease is a complex and time consuming process which involves symptom analysis, laboratory tests, and clinical assessments. Detecting the disease can be more challenging because many symptoms of autoimmune liver diseases overlap with those of other autoimmune conditions. As a result, there is a need for an optimized, accurate, efficient, and cost-effective methodology to identify the disease without extensive and invasive procedures such as organ transplants. This paper introduces an innovative approach that employs the power of supervised machine learning and deep learning techniques to predict the onset of autoimmune liver diseases in advance. The machine learning model is constructed using a comprehensive dataset comprising the complete medical history of patients, physical examination records, histopathology and genetic data. Along with the machine learning model, the deep learning model is also developed for liver MRI images of various patients to make accurate prediction. This system provides a second opinion for medical professionals that may avoid the need for extensive and invasive medical procedures, including biopsies, and ultimately improve patient care and outcomes.

关键词： Deep learning Accuracy Liver diseases Biological system modeling Predictive models Autoimmune diseases Task analysis

来源：评论

学校读者我要写书评

暂无评论

NLP-Based Sentiment Analysis using Deep Learning Methods 1

NLP-Based Sentiment Analysis using Deep Learning Methods

引用

1st IEEE International Conference on Advances in computing, Communication and Networking, ICAC2N 2024

作者： Kumar, Dheeraj Bhatia, Sandeep Singh Dhillon, Hardeep Goel, Amit Kumar Galgotias University School of Computing Science and Engineering Greater Noida India Department of Applied Sciences Panjab Mohali140307 India Apeejay Stya University Sohna Gurugram School of Engineering and Technology India

ISBN: (纸本)9798350356816

Opinion mining systems rely heavily on sentiment analysis because to the vast amount of data and opinions that are generated, exchanged, and sent on a regular basis through the internet and other media. This study presents a deep learning network-based sentiment analysis categorization that was created and compares the results across multiple deep learning networks. Using the Multilayer Perceptron, a benchmark for other networks' performance was established (MLP). Built and implemented on the 50K movie review file IMDB dataset were a hybrid model of long short-term memory (LSTM) and convolutional neural network (CNN), as well as an LSTM recurrent neural network. Reviews for the dataset were 50% positive and 50% negative. After Word2Vec performed its initial pre-processing on the data, word embedding was applied. The hybrid CNN_LSTM model outperformed the MLP and the separate CNN and LSTM networks, as seen by the findings. While CNN reported an accuracy of 88.9%, MLP and LSTM reported accuracy of 87.78% and 87.68, respectively. 89.4% accuracy was reported by CNN_LSTM. Results further show that the proposed deep learning models have performed better than SVM, Naïve Bayes, and RNTN models based on English datasets presented in previous works. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Optical dromions for complex Ginzburg Landau model with nonlinear media

引用

applied Mathematics(A Journal of Chinese Universities) 2023年第1期38卷 111-125页

作者： Syed T.R.Rizvi Aly R.Seadawy Muhammad Younis S.O.Abbas Abdul Khaliq Department of Mathematics COMSATS University IslamabadLahore CampusPakistan Mathematics Department Faculty of ScienceTaibah UniversityAl-Madinah Al-Munawarah 41411Kingdom of Saudi Arabia Punjab University College of Information Technology University of the PunjabLahore Pakistan Mathematics Department Riphah Institute of Computing and Applied SciencesRiphah International UniversityLahorePakistan

This manuscript studies the optical dromions with beta derivative(BD)applied to the Complex Ginzburg Landau equation(CGLE)with Kerr law,parabolic law,cubic quintic septic law and quadratic cubic *** obtain bright dromians by using the sine-cosine method(SCM).We will also obtain domain walls with the assistance of Bernoulli equation approach(BEA).Constraint conditions are also listed.

关键词： CGLE optical dromians non-Kerr laws

来源：评论

学校读者我要写书评

暂无评论

Reduced Order Modeling for First Order Hyperbolic Systems with Application to Multiparameter Acoustic Waveform Inversion

引用

SIAM Journal on Imaging Sciences 2025年第2期18卷 851-880页

作者： Borcea, Liliana Garnier, Josselin Mamonov, Alexander V. Zimmerling, Jorn Applied Physics and Applied Mathematics Columbia University New YorkNY10027 United States CMAP CNRS Ecole Polytechnique Institut Polytechnique de Paris Palaiseau91120 France Department of Mathematics University of Houston HoustonTX77204-3008 United States Department of Information Technology Division of Scientific Computing Uppsala Universitet Uppsala75105 Sweden

Waveform inversion seeks to estimate an inaccessible heterogeneous medium from data gathered by sensors that emit probing signals and measure the generated waves. It is an inverse problem for a second order wave equation or a first order hyperbolic system, with the sensor excitation modeled as a forcing term and the heterogeneous medium described by unknown, spatially variable coefficients. The traditional ``full waveform inversion"" (FWI) formulation estimates the unknown coefficients via minimization of the nonlinear, least squares data fitting objective function. For typical band-limited and high frequency data, this objective function has spurious local minima near and far from the true coefficients. Thus, FWI implemented with gradient based optimization algorithms may fail, even for good initial guesses. Recently, it was shown that it is possible to obtain a better behaved objective function for wave speed estimation, using data driven reduced order models (ROMs) that capture the propagation of pressure waves, governed by the classic second order wave equation. Here we introduce ROMs for vectorial waves, satisfying a general first order hyperbolic system. They are defined via Galerkin projection on the space spanned by the wave snapshots, evaluated on a uniform time grid with appropriately chosen time step. Our ROMs are data driven: They are computed in an efficient and noniterative manner, from the sensor measurements, without knowledge of the medium and the snapshots. The ROM computation applies to any linear waves in lossless and nondispersive media. For the inverse problem we focus attention on acoustic waves in a medium with unknown variable wave speed and density. We show that these can be determined via minimization of an objective function that uses a ROM based approximation of the vectorial wave field inside the inaccessible medium. We assess the performance of our inversion approach with numerical simulations and compare the results to those given by

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

Classification and Comprehension of Software Requirements Using Ensemble Learning

引用

Computers, Materials & Continua 2024年第8期80卷 2839-2855页

作者： Jalil Abbas Arshad Ahmad Syed Muqsit Shaheed Rubia Fatima Sajid Shah Mohammad Elaffendi Gauhar Ali School of Computer Science and Technology Anhui UniversityHefei230039China School of Computing Sciences Pak Austria FachhochschuleInstitute of Applied Sciences and TechnologyHaripur22620Pakistan Department of Computer Science and IT University of LahoreLahore55150Pakistan Department of Computer Science Emerson UniversityPunjabMultan60000Pakistan EIAS(Emerging Intelligent Autonomous Systems)Data Science Lab Prince Sultan UniversityRiyad12435Saudi Arabia

The software development process mostly depends on accurately identifying both essential and optional ***,user needs are typically expressed in free-form language,requiring significant time and human resources to translate these into clear functional and non-functional *** address this challenge,various machine learning(ML)methods have been explored to automate the understanding of these requirements,aiming to reduce time and human ***,existing techniques often struggle with complex instructions and large-scale *** our study,we introduce an innovative approach known as the Functional and Non-functional Requirements Classifier(FNRC).By combining the traditional random forest algorithm with the Accuracy Sliding Window(ASW)technique,we develop optimal sub-ensembles that surpass the initial classifier’s accuracy while using fewer *** results demonstrate that our FNRC methodology performs robustly across different datasets,achieving a balanced Precision of 75%on the PROMISE dataset and an impressive Recall of 85%on the CCHIT *** datasets consistently maintain an F-measure around 64%,highlighting FNRC’s ability to effectively balance precision and recall in diverse *** findings contribute to more accurate and efficient software development processes,increasing the probability of achieving successful project outcomes.

关键词： Ensemble learning machine learning non-functional requirements requirement engineering accuracy sliding window

来源：评论

学校读者我要写书评

暂无评论

IDS-INT:Intrusion detection system using transformer-based transfer learning for imbalanced network traffic

引用

Digital Communications and Networks 2024年第1期10卷 190-204页

作者： Farhan Ullah Shamsher Ullah Gautam Srivastava Jerry Chun-Wei Lin School of Software Northwestern Polytechnical UniversityXian710072ShaanxiChina Knowledge Unit of Systems and Technology University of Management and TechnologySialkot 51040Pakistan Department of Math and Computer Science Brandon UniversityBrandonMB R7A 6A9Canada Department of Computer Science and Math Lebanese American UniversityBeirut1102Lebanon Western Norway University of Applied Sciences BergenNorway Research Centre for Interneural Computing China Medical UniversityTaichungTaiwanChina

A network intrusion detection system is critical for cyber security against llegitimate *** terms of feature perspectives,network traffic may include a variety of elements such as attack reference,attack type,a subcategory of attack,host information,malicious scripts,*** terms of network perspectives,network traffic may contain an imbalanced number of harmful attacks when compared to normal *** is challenging to identify a specific attack due to complex features and data imbalance *** address these issues,this paper proposes an Intrusion Detection System using transformer-based transfer learning for Imbalanced Network Traffic(IDS-INT).IDS-INT uses transformer-based transfer learning to learn feature interactions in both network feature representation and imbalanced ***,detailed information about each type of attack is gathered from network interaction descriptions,which include network nodes,attack type,reference,host information,***,the transformer-based transfer learning approach is developed to learn detailed feature representation using their semantic ***,the Synthetic Minority Oversampling Technique(SMOTE)is implemented to balance abnormal traffic and detect minority ***,the Convolution Neural Network(CNN)model is designed to extract deep features from the balanced network ***,the hybrid approach of the CNN-Long Short-Term Memory(CNN-LSTM)model is developed to detect different types of attacks from the deep *** experiments are conducted to test the proposed approach using three standard datasets,i.e.,UNsWNB15,CIC-IDS2017,and *** explainable AI approach is implemented to interpret the proposed method and develop a trustable model.

关键词： Network intrusion detection Transfer learning Features extraction Imbalance data Explainable AI Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of Recent 2D Human Pose Estimation Methods 6

A Comparative Study of Recent 2D Human Pose Estimation Metho...

引用

6th International Conference on computing and Informatics, ICCI 2024

作者： Elshami, Nada E. Salah, Ahmad Mohsen, Heba Department of Computer Science Faculty of Computers and Information Technology Future University in Egypt New Cairo Egypt College of Computing and Information Sciences University of Technology and Applied Sciences Ibri Oman College of Computers and Informatics Zagazig University Zagazig Egypt

ISBN: (纸本)9798350373875

Human Pose Estimation is a computer vision technique utilized in various fields such as healthcare, security, and sports to detect the pose of single or multi-person utilizing various machine learning and deep learning methodologies. These methodologies can be applied in a variety of ways, including top-down and bottom-up approaches. Furthermore, this technique can be used with images or videos, as well as in 2D or 3D domains. This paper delves into recent advancements in deep learning methods used for estimating the pose, covering commonly employed datasets, evaluation metrics, and the challenges encountered in this field. It aims to assist new researchers in getting familiar with this technique based on work published between 2019 and 2023, with a spotlight on 2D and omitting 3D. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

GACL-Net:Hybrid Deep Learning Framework for Accurate Motor Imagery Classification in Stroke Rehabilitation

引用

Computers, Materials & Continua 2025年第4期83卷 517-536页

作者： Chayut Bunterngchit Laith H.Baniata Mohammad H.Baniata Ashraf ALDabbas Mohannad A.Khair Thanaphon Chearanai Sangwoo Kang State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of AutomationChinese Academy of SciencesBeijing100190China School of Computing Gachon UniversitySeongnam13120Republic of Korea Computer Science Department Faculty of Information TechnologyThe World Islamic Sciences and Education UniversityAmman11947Jordan Intelligent Systems Department Faculty of Artificial IntelligenceAl-Balqa Applied UniversityAl-Salt19117Jordan IT Infrastructure Department Qatrana Cement CompanyAmman11821Jordan Division of Industrial and Logistics Engineering Technology Faculty of Engineering and TechnologyKing Mongkut’s University of Technology North BangkokRayong CampusRayong21120Thailand

Stroke is a leading cause of death and disability worldwide,significantly impairing motor and cognitive *** rehabilitation is often hindered by the heterogeneity of stroke lesions,variability in recovery patterns,and the complexity of electroencephalography(EEG)signals,which are often contaminated by *** classification of motor imagery(MI)tasks,involving the mental simulation of movements,is crucial for assessing rehabilitation strategies but is challenged by overlapping neural signatures and patient-specific *** address these challenges,this study introduces a graph-attentive convolutional long short-term memory(LSTM)network(GACL-Net),a novel hybrid deep learning model designed to improve MI classification accuracy and ***-Net incorporates multi-scale convolutional blocks for spatial feature extraction,attention fusion layers for adaptive feature prioritization,graph convolutional layers to model inter-channel dependencies,and bidi-rectional LSTM layers with attention to capture temporal *** on an open-source EEG dataset of 50 acute stroke patients performing left and right MI tasks,GACL-Net achieved 99.52%classification accuracy and 97.43%generalization accuracy under leave-one-subject-out cross-validation,outperforming existing state-of-the-art ***,its real-time processing capability,with prediction times of 33–56 ms on a T4 GPU,underscores its clinical potential for real-time neurofeedback and adaptive *** findings highlight the model’s potential for clinical applications in assessing rehabilitation effectiveness and optimizing therapy plans through precise MI classification.

关键词： Motor imagery EEG stroke rehabilitation deep learning brain-computer interface

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：