检索结果-内蒙古大学图书馆

Deep learning for brain age estimation: A systematic review

学校读者我要写书评

暂无评论

Information Fusion 2023年 96卷 130-143页

作者： Tanveer, M. Ganaie, M.A. Beheshti, Iman Goel, Tripti Ahmad, Nehal Lai, Kuan-Ting Huang, Kaizhu Zhang, Yu-Dong Del Ser, Javier Lin, Chin-Teng Department of Mathematics Indian Institute of Technology Indore Simrol Indore453552 India Department of Robotics University of Michigan Ann ArborMI48109 United States Department of Human Anatomy and Cell Science Rady Faculty of Health Sciences Max Rady College of Medicine University of Manitoba WinnipegMB Canada Biomedical Imaging Lab National Institute of Technology Silchar Assam 788010 India Department of Electrical Engineering and Computer Science National Taipei University of Technology Taipei Taiwan Department of Electronic Engineering National Taipei University of Technology Taipei Taiwan Data Science Research Center Duke Kunshan University China School of Computing and Mathematical Sciences University of Leicester LeicesterLE1 7RH United Kingdom Derio48160 Spain Bilbao48013 Spain School of Computer Science Faculty of Engineering and Information Technology University of Technology Sydney Sydney Australia

Over the years, Machine Learning models have been successfully employed on neuroimaging data for accurately predicting brain age. Deviations from the healthy brain aging pattern are associated with the accelerated brain aging and brain abnormalities. Hence, efficient and accurate diagnosis techniques are required to elicit accurate brain age estimations. Several contributions have been reported in the past for this purpose, resorting to different data-driven modeling methods. Recently, deep neural networks (also referred to as deep learning) have become prevalent in manifold neuroimaging studies, including brain age estimation. In this review, we offer a comprehensive analysis of the literature related to the adoption of deep learning for brain age estimation with neuroimaging data. We detail and analyze different deep learning architectures used for this application, pausing at research works published to date quantitatively exploring their application. We also examine different brain age estimation frameworks, comparatively exposing their advantages and weaknesses. Finally, the review concludes with an outlook towards future directions that should be followed by prospective studies. The ultimate goal of this paper is to establish a common and informed reference for newcomers and experienced researchers willing to approach brain age estimation by using deep learning models. © 2023 Elsevier B.V.

关键词： Deep neural networks

Learning Across Decentralized Multi-Modal Remote Sensing Archives with Federated Learning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Büyüktaş, Barış Sumbul, Gencer Demir, Begüm Faculty of Electrical Engineering and Computer Science Technische Universität Berlin Germany BIFOLD - Berlin Institute for the Foundations of Learning and Data Germany

The development of federated learning (FL) methods, which aim to learn from distributed databases (i.e., clients) without accessing data on clients, has recently attracted great attention. Most of these methods assume that the clients are associated with the same data modality. However, remote sensing (RS) images in different clients can be associated with different data modalities that can improve the classification performance when jointly used. To address this problem, in this paper we introduce a novel multi-modal FL framework that aims to learn from decentralized multi-modal RS image archives for RS image classification problems. The proposed framework is made up of three modules: 1) multimodal fusion (MF);2) feature whitening (FW);and 3) mutual information maximization (MIM). The MF module performs iterative model averaging to learn without accessing data on clients in the case that clients are associated with different data modalities. The FW module aligns the representations learned among the different clients. The MIM module maximizes the similarity of images from different modalities. Experimental results show the effectiveness of the proposed framework compared to iterative model averaging, which is a widely used algorithm in FL. The code of the proposed framework is publicly available at https://***/rsim/MMFL. © 2023, CC BY.

关键词： Image classification

Active Learning Guided Fine-Tuning for Enhancing Self-Supervised based Multi-Label Classification of Remote Sensing Images

学校读者我要写书评

暂无评论

Active Learning Guided Fine-Tuning for Enhancing Self-Superv...

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Lars Möllenbrok Begüm Demir Faculty of Electrical Engineering and Computer Science Technische Universität Berlin Germany Bifold - Berlin Institute for the Foundations of Learning and Data Germany

In recent years, deep neural networks (DNNs) have been found very successful for multi-label classification (MLC) of remote sensing (RS) images. Self-supervised pre-training combined with fine-tuning on a randomly selected small training set has become a popular approach to minimize annotation efforts of data-demanding DNNs. However, finetuning on a small and biased training set may limit model performance. To address this issue, we investigate the effectiveness of the joint use of self-supervised pre-training with active learning (AL). The considered AL strategy aims at guiding the MLC fine-tuning of a self-supervised model by selecting informative training samples to annotate in an iterative manner. Experimental results show the effectiveness of applying AL-guided fine-tuning (particularly for the case where strong class-imbalance is present in MLC problems) compared to the application of fine-tuning using a randomly constructed small training set.

关键词：

An Efficient Shortest Path Optimized Algorithm for Vehicle Adhoc Networks System 7

学校读者我要写书评

暂无评论

An Efficient Shortest Path Optimized Algorithm for Vehicle A...

7th International Conference on Circuit Power and Computing Technologies, ICCPCT 2024

作者： Shalini, K. Reddy, K. Harinath Punati, Kondalarao Kavin, K.S. Veena, P. Pushpalatha, K. Vardhaman College of Engineering Department of Artificial Intelligence and Data Science Shamshabad India Annamacharya Institute of Technology and Sciences Department of Electrical and Electronics Engineering Rajampet India Hyderabad Institute of Technology and Management Faculty of Electronics and Communication Engineering Hyderabad500090 India Government College of Engineering Department of Electrical and Electronics Engineering Tamilnadu Tirunelveli India N. S. S. Polytechnic College Department of Computer Engineering Pandalam Pathanamthitta India Coimbatore Institute of Engineering and Technology Department of Computer Science and Engineering Coimbatore641109 India

ISBN: (纸本)9798350372816

VANET (Vehicular ad-hoc network) is a network of advanced automobiles designed to solve the problem of mobility and, as a result, reduce the number of accidents. Because VANET is a type of MANET (mobile ad hoc network) surrounded by human-driven nodes, the social concept can be used to explain VANET routing decisions. This motivates academics to look into the possibilities of using Social Network Analysis (SNA) to create routing strategies. The most critical problem in any system is parcel drop. Social characteristics-based architectures encounter comparable challenges, resulting in inefficient message delivery. In this research, the dragonfly method is used to the shortest path methodology for fixed line VANET with the purpose of reducing package drop and increasing network reliability. This is made achievable by sculpted system of values centralization analysis, which improves the decision via dragonfly optimization methodology. The behavior of the using nodes capability then be determined by the importance computation. In this study, the sustainability of the optimized shortest path system is measured in terms of End to End delay, Energy Consumption, Packet Loss, and Throughput. The dragonfly algorithm's throughput evaluation is 650 kbps as compared to the traditional way. © 2024 IEEE.

关键词： Vehicular ad hoc networks

Machine Learning-Integrated Modeling of Thermal Properties and Relaxation Dynamics in Metallic Glasses

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Que, Ngo T. Phan, Anh D. Tran, Truyen Huy, Pham T. Trang, Mai X. Luong, Thien V. Phenikaa Institute for Advanced Study Phenikaa University Hanoi12116 Viet Nam Faculty of Materials Science and Engineering Phenikaa University Hanoi12116 Viet Nam Deakin University Australia Faculty of Computer Science Phenikaa University Hanoi12116 Viet Nam Business AI Lab Faculty of Data Science and Artificial Intelligence National Economics University Hanoi10000 Viet Nam

Metallic glasses are a promising class of materials celebrated for their exceptional thermal and mechanical properties. However, accurately predicting and understanding the melting temperature (Tm) and glass transition temperature (Tg) remains a significant challenge. In this study, we present a comprehensive approach that integrates machine learning (ML) models with theoretical methods to predict and analyze these key thermal properties in metallic glasses. Our ML models using distributional data derived from elemental composition-based features obtain high accuracy while minimizing data preprocessing complexity. Furthermore, we explore the correlation between Tm and Tg to elucidate their dependence on alloy composition and thermodynamic behavior. When the Tgvalue of metallic glasses is known, further analysis using the Elastically Collective Nonlinear Langevin Equation (ECNLE) theory provides a deeper understanding of structural relaxation dynamics. This integrated framework establishes a quantitative description consistent with experimental data and previous works and paves the way for the efficient design and discovery of advanced materials with tailored thermal properties. Copyright © 2025, The Authors. All rights reserved.

关键词： Amorphous alloys

Thailand Stock Index Forecasting Based on Multiple data Sources Using RNN-LSTM Approach

学校读者我要写书评

暂无评论

Thailand Stock Index Forecasting Based on Multiple Data Sour...

2022 Research, Invention, and Innovation Congress: Innovative Electricals and Electronics, RI2C 2022

作者： Boonrawd, Pudsadee Phonyiam, Korawat King Mongkut's University of Technology North Bangkok Faculty of Information Technology and Digital Innovation Bangkok Thailand Data Science and Analytics Research Group National Electronics and Computer Technology Center Pathumthani Thailand

ISBN: (数字)9781665473248

ISBN: (纸本)9781665473248

Stock investment is an interesting option that has attracted the attention of investors. This research presents Thailand Stock Index Forecasting, a case study of the Stock Exchange of Thailand (SET) applying Recurrent Neural Networks with Long Short-Term Memory (RNN-LTSM). The research used multiple data sources 15 years of SET Market data from 2006 to 2020 for stock forecasting divided into Training Set 80% and Test Set 20%. Mean Square Error (MSE) was used for the evaluation model. The results showed that RNN-LTSM Approach optimized the model's performance based on 5 stock asset companies used in this research. Therefore, the proposed model can be used to develop related forecasting or recommendation systems in the future to help investors consider the risks of investment and support investment decisions. © 2022 IEEE.

关键词： Long short-term memory

Real-Time Traffic Flow Optimization using Adaptive IoT and data Analytics: A Novel DeepStreamNet Model

学校读者我要写书评

暂无评论

Real-Time Traffic Flow Optimization using Adaptive IoT and D...

Sustainable Expert Systems (ICSES), International Conference on

作者： V.S. Saranya Garimidi Subbarao Dega Balakotaiah Maloth Bhavsingh K. Suresh Babu Srinivasa Rao Dhanikonda Department of Computing Technologies School of Computing SRM Institute of Science and Technology Chennai Department o Computer Science and Engineering (AIDS) Pace Institute of Technology and Sciences Department of Computer Science and Engineering Vignan's Founadation for Science Technology & Research (Deemed to be University) Department of Computer Science and Engineering Ashok: Womens Engineering College Kurnool Andhra Pradesh Department of Computer Science and Engineering Narasaraopeta Engineering College(Autonomous) Narasaraopet A.P Department of Artificial Intelligence and Data Science Faculty of Science and Technology (IcfaiTech) ICFAI Foundation for Higher Education (Deemed to Be University) Hyderabad Telangana India

ISBN: (数字)9798331540364

ISBN: (纸本)9798331540371

Thisstudy introduces the DeepStreamNet model, an advanced framework for enhancing real-time traffic management in urban environments using adaptive IoT and sophisticated big data analytics. Central to our approach is the integration of convolutional neural networks (CNNs), recurrent neural networks (RNNs), and long short-term memory (LSTM) units, which synergize with IoT devices to facilitate dynamic adaptation to fluctuating traffic conditions. The model excels in operational performance, achieving a notable accuracy of 94.7% in congestion prediction with an exceptionally low latency of only 45 ms per decision cycle and the capability to process up to 50,000 data points per second. These technical achievements have marked significant improvements over traditional traffic management systems, enhancing traffic flow efficiency and reducing congestion effectively. The results underscore the transformative potential of the DeepStreamNet model in urban traffic management and public safety, offering actionable insights for intelligent transportation systems and setting the stage for more informed urban planning. Looking forward, we suggest extending the application of our model to areas such as logistics and broader smart city initiatives, highlighting its adaptability and broad utility in various urban contexts

关键词： Adaptation models Analytical models Accuracy Smart cities Urban planning data models Real-time systems Internet of Things Optimization Context modeling

ANNOTATION COST EFFICIENT ACTIVE LEARNING FOR CONTENT BASED IMAGE RETRIEVAL

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Henkel, Julia Hoxha, Genc Sumbul, Gencer Möllenbrok, Lars Demir, Begüm Faculty of Electrical Engineering and Computer Science Technische Universität Berlin Germany BIFOLD Berlin Institute for the Foundations of Learning and Data Germany

Deep metric learning (DML) based methods have been found very effective for content-based image retrieval (CBIR) in remote sensing (RS). For accurately learning the model parameters of deep neural networks, most of the DML methods require a high number of annotated training images, which can be costly to gather. To address this problem, in this paper we present an annotation cost efficient active learning (AL) method (denoted as ANNEAL). The proposed method aims to iteratively enrich the training set by annotating the most informative image pairs as similar or dissimilar, while accurately modelling a deep metric space. This is achieved by two consecutive steps. In the first step the pairwise image similarity is modelled based on the available training set. Then, in the second step the most uncertain and diverse (i.e., informative) image pairs are selected to be annotated. Unlike the existing AL methods for CBIR, at each AL iteration of ANNEAL a human expert is asked to annotate the most informative image pairs as similar/dissimilar. This significantly reduces the annotation cost compared to annotating images with land-use/land cover class labels. Experimental results show the effectiveness of our method. The code of ANNEAL is publicly available at https://***/rsim/ANNEAL. © 2023, CC BY.

关键词： Remote sensing

Persian Semantic Role Labeling Using Transfer Learning and BERT-Based Models

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Aghdam, Saeideh Niksirat Hossayni, Sayyed Ali Sadeh, Erfan Khedersolh Khozouei, Nasim Bidgoli, Behrouz Minaei Department of Computer Engineering Iran University of Science and Technology Tehran Iran Data Mining Lab School of Computer Engineering Iran University of Science & Technology Tehran Iran Department of computer Engineering Faculty of Engineering Yasouj University Yasouj Iran

Semantic role labeling (SRL) is the process of detecting the predicate-argument structure of each predicate in a sentence. SRL plays a crucial role as a pre-processing step in many NLP applications such as topic and concept extraction, question answering, summarization, machine translation, sentiment analysis, and text mining. Recently, in many languages, unified SRL dragged lots of attention due to its outstanding performance, which is the result of overcoming the error propagation problem. However, regarding the Persian language, all previous works have focused on traditional methods of SRL leading to a drop in accuracy and imposing expensive feature extraction steps in terms of financial resources, time and energy consumption. In this work, we present an end-to-end SRL method that not only eliminates the need for feature extraction but also outperforms existing methods in facing new samples in practical situations. The proposed method does not employ any auxiliary features and shows more than 16 (83.16) percent improvement in accuracy against previous methods in similar circumstances. © 2023, CC BY-NC-ND.

关键词： Deep neural networks