检索结果-内蒙古大学图书馆

Nanophononic metamaterials induced proximity effect in heat flux regulation

Frontiers of physics 2024年第2期19卷 149-156页

作者： Jian Zhang Haochun Zhang Gang Zhang School of Energy Science and Engineering Harbin Institute of TechnologyHarbin 150001China Institute of High Performance Computing Agency for ScienceTechnology and Research(A*STAR)Singapore 138632Singapore

Recent studies have shown that the construction of nanophononic metamaterials can reduce thermal conductivity without affecting electrical properties,making them promising in many fields of application,such as energy conversion and thermal ***,although extensive studies have been carried out on thermal conductivity reduction in nanophononic metamaterials,the local heat flux characteristic is still *** this work,we construct a heat flux regulator which includes a silicon nanofilm with silicon *** regulator has remarkable heat flux regulation ability,and various impacts on the regulation ability are ***,even in the region without nanopillars,the local heat current is still lower than that in pristine silicon nanofilms,reduced by the neighboring nanopillars through the thermal proximity *** combine the analysis of the phonon participation ratio with the intensity of localized phonon modes to provide a clear *** findings not only provide insights into the mechanisms of heat flux regulation by nanophononic metamaterials,but also will open up new research directions to control local heat flux for a broad range of applications,including heat management,thermoelectric energy conversion,thermal cloak,and thermal concentrator.

关键词： nanophononic metamaterials proximity effect

来源：评论

学校读者我要写书评

暂无评论

The impact of backbone selection in YOLOv8 models on brain tumor localization

引用

Iran Journal of Computer science 2025年 1-23页

作者： Ranjbarzadeh, Ramin Crane, Martin Bendechache, Malika School of Computing Faculty of Engineering and Computing Dublin City University Dublin Ireland ADAPT Research Centre School of Computer Science University of Galway Galway Ireland

This study investigates the utilization of the You Only Look Once (YOLOv8) deep learning framework for accurately identifying the location of brain tumors in medical imaging. We investigate the effects of model size and pretraining on the accuracy and computational efficiency of tumor detection by utilizing different setups of the YOLOv8 model. These setups include various configurations, ranging from very small to large, and can be pretrained on the COCO dataset or not. The experimental results, carried out on Google Colaboratory using NVIDIA Tesla T4 GPUs, show that pretrained models often achieve better performance by utilizing the extensive feature representations learned from the COCO dataset, resulting in increased precision in tumor location. For instance, the YOLOv8-XS model pretrained on COCO achieves an IoU of 0.278 and a Dice coefficient of 0.435, whereas its non-pretrained counterpart attains only 0.241 IoU and 0.388 Dice, indicating a 15% improvement in tumor localization accuracy. Similarly, pretrained YOLOv8-L achieves 0.269 IoU, outperforming standard object detection models such as Mask R-CNN (IoU: 0.212) and Faster R-CNN (IoU: 0.228). These results highlight the impact of pretraining on model performance, particularly for lightweight architectures, while also revealing diminishing returns for larger models. The research uncovers a subtle connection between the complexity of the model, pretraining, and the time required for training. It emphasizes the possible advantages and constraints of pretraining for various sizes of models. © The Author(s) 2025.

关键词： Brain tumor localization COCO dataset Deep learning Object detection Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Discovering Social Media Influencers Using a Deep Regression Analysis

引用

SN Computer science 2025年第4期6卷 1-18页

作者： Ramya, G.R. Bagavathi Sivakumar, P. Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Coimbatore India

Highly influential users (IUs) play a vital role in disseminating information on online social networks (OSNs). Recognizing IUs is crucial for brand awareness, strategic marketing and consumer engagement. Researchers have developed the temporal influential model (TIM) and incremental logistic regression (ILLR) to find out the probability of a user being influential on Twitter. However, accurately identifying IUs requires considering multiple user and tweet attributes. This study proposes a model for predicting IUs by analyzing user and trend-based attributes from tweets, calculating a weighted associated influence (WAI) score for each user and enhancing IU prediction through user similarity, influence degree, and trustworthiness metrics. The goal is to combine the TIM with deep regression (TIM-DeepReg) to improve accuracy in predicting high IUs on OSNs while handling large amounts of data and attributes. The TIM-DeepReg model combines convolutional neural network (CNN) with regression to automatically learn user and tweet attributes and enhance IU prediction efficiency. Lastly, the experimental findings show that the TIM-DeepReg model surpasses other models in IU prediction for the Tariff, Service, and Punctuality topics of airline services on Twitter and Facebook, with 87.4%, 88.9%, and 88.8% of the most influential individuals predicted. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Deep regression Influencer on social networks Influencer prediction from Facebook and Twitter Temporal influential model Weighted associated influence score

来源：评论

学校读者我要写书评

暂无评论

HybridViT: An Approach for Alzheimer’s Disease Classification with ADNI Neuroimaging Data

引用

SN Computer science 2025年第4期6卷 1-18页

作者： Tekumudi, Vivek Sai Surya Chaitanya Ramanathan, Annamalai Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Chennai India

Alzheimer’s disease (AD) is a prevalent neurological disorder characterized by progressive brain cell degeneration and atrophy, leading to a gradual decline in cognitive and functional abilities. Timely diagnosis is paramount in potentially delaying or preventing the course of this debilitating condition. Magnetic Resonance Imaging presents a non-invasive means for longitudinal monitoring and serves as a crucial biomarker for tracking disease progression. In particular, Structural Magnetic Resonance Imaging (sMRI) enables the quantification of atrophy, which is a reliable indicator for assessing the precise stage and severity of AD-related neurodegeneration. In this research, we employ advanced machine learning techniques to address the challenge of accurate and early diagnosis of AD. We utilize a comprehensive dataset comprising five stages of 2D sMRI Image data, encompassing AD, Cognitively Normal, Mild Cognitive Impairment, Early Mild Cognitive Impairment, and Late Mild Cognitive Impairment classes. To optimize the classification process, we explore a novel approach that combines a Vision Transformer with pre-trained convolutional neural networks. Our study includes binary and multi-class classification tasks, and the performance of 26 pre-trained Keras Deep Learning models is assessed. Notably, The DenseNet121+ViT model achieves 91.26% accuracy in multi-class classification. For binary classification, MobileNetV2+ViT, EfficientNetB4+ViT, and MobileNet+ViT achieve accuracies of 92.33%, 97.82%, and 94.81%, respectively. These results highlight our approach’s potential to improve AD diagnosis accuracy and underscore the importance of deep learning in early detection of neurological disorders. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Alzheimer’s disease (AD) Alzheimer’s disease neuroimaging initiative (ADNI) HybridViT Pre-trained models Vision transformer

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Based Attack Detection for Cyber-Physical System Cybersecurity:A Survey

引用

IEEE/CAA Journal of Automatica Sinica 2022年第3期9卷 377-391页

作者： Jun Zhang Lei Pan Qing-Long Han Chao Chen Sheng Wen Yang Xiang IEEE the School of Science Computing and Engineering TechnologiesSwinburne University of Technology the School of Information Technology Deakin University the College of Science and Engineering James CookUniversity

With the booming of cyber attacks and cyber criminals against cyber-physical systems(CPSs),detecting these attacks remains *** might be the worst of times,but it might be the best of times because of opportunities brought by machine learning(ML),in particular deep learning(DL).In general,DL delivers superior performance to ML because of its layered setting and its effective algorithm for extract useful information from training *** models are adopted quickly to cyber attacks against CPS *** this survey,a holistic view of recently proposed DL solutions is provided to cyber attack detection in the CPS context.A six-step DL driven methodology is provided to summarize and analyze the surveyed literature for applying DL methods to detect cyber attacks against CPS *** methodology includes CPS scenario analysis,cyber attack identification,ML problem formulation,DL model customization,data acquisition for training,and performance *** reviewed works indicate great potential to detect cyber attacks against CPS through DL ***,excellent performance is achieved partly because of several highquality datasets that are readily available for public ***,challenges,opportunities,and research trends are pointed out for future research.

关键词： Cyber-physical system cybersecurity deep learning intrusion detection pattern classification

来源：评论

学校读者我要写书评

暂无评论

ReCSA:a dedicated sort accelerator using ReRAM-based content addressable memory

引用

Frontiers of Computer science 2023年第2期17卷 1-13页

作者： Huize LI Hai JIN Long ZHENG Yu HUANG Xiaofei LIAO National Engineering Research Center for Big Data Technology and System Services Computing Technology and System LabClusters and Grid Computing LabSchool of Computer Science and TechnologyHuazhong University of Science and TechnologyWuhan 430074China

With the increasing amount of data,there is an urgent need for efficient sorting algorithms to process large data *** sorting algorithms have attracted much attention because they can take advantage of different hardware's *** the traditional hardware sort accelerators suffer“memory wall”problems since their multiple rounds of data transmission between the memory and the *** this paper,we utilize the in-situ processing ability of the ReRAM crossbar to design a new ReCAM array that can process the matrix-vector multiplication operation and the vector-scalar comparison in the same array *** this designed ReCAM array,we present ReCSA,which is the first dedicated ReCAM-based sort *** hardware designs,we also develop algorithms to maximize memory utilization and minimize memory exchanges to improve sorting *** sorting algorithm in ReCSA can process various data types,such as integer,float,double,and *** also present experiments to evaluate the performance and energy efficiency against the state-of-the-art sort *** experimental results show that ReCSA has 90.92×,46.13×,27.38×,84.57×,and 3.36×speedups against CPU-,GPU-,FPGA-,NDP-,and PIM-based platforms when processing numeric data *** also has 24.82×,32.94×,and 18.22×performance improvement when processing string data sets compared with CPU-,GPU-,and FPGA-based platforms.

关键词： ReCAM parallel sorting architecture design processing-in-memory

来源：评论

学校读者我要写书评

暂无评论

Weighted Concept Factorization Based Incomplete Multi-view Clustering

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第11期5卷 5699-5708页

作者： Khan, Ghufran Ahmad Khan, Jalaluddin Anwar, Taushif Ashraf, Zubair Javed, Mohammad Hafeez Diallo, Bassoma Koneru Lakshmaiah Education Foundation Department of Computer Science and Engineering Andhra Pradesh Vaddeswaram522502 India Southwest Jiaotong University School of Computing and Artificial Intelligence Chengdu611756 China VIT Bhopal University School of Computing Science and Engineering Kothrikalan Madhya Pradesh Sehore466114 India

The primary objective of classical multiview clustering (MVC) is to categorize data into separate clusters under the assumption that all perspectives are completely available. However, in practical situations, it is common to encounter cases where not all viewpoints of the data are accessible. This limitation can impede the effectiveness of traditional MVC methods. The incompleteness of the clustering of multiview data has witnessed substantial progress in recent years due to its promising applications. In response to the aforementioned issue, we have tackled it by introducing an inventive MVC algorithm that is tailored to handle incomplete data from various views. Additionally, we have proposed a distinct objective function that leverages a weighted concept factorization technique to address the absence of data instances within each incomplete perspective. To address inconsistencies between different views, we introduced a coregularization factor, which operates in conjunction with a shared consensus matrix. It is important to highlight that the proposed objective function is intrinsically nonconvex, presenting challenges in terms of optimization. To secure the optimal solution for this objective function, we have implemented an iterative optimization approach to reach the local minima for our method. To underscore the efficacy and validation of our approach, we experimented with real-world datasets and used state-of-the-art methods to perform comparative assessments. © 2024 IEEE.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Development of a diacritic-aware large vocabulary automatic speech recognition for Hausa language

引用

International Journal of Speech Technology 2024年第3期27卷 687-700页

作者： Abubakar, Abdulqahar Mukhtar Gupta, Deepa Vekkot, Susmitha Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India Department of Electronics & amp Communication Engineering Amrita School of Engineering Amrita Vishwa Vidyapeetham Bengaluru India

Research on voice recognition for African languages is limited due to the scarcity of digital resources for training and adaptation, despite its broad usefulness. The Hausa language, spoken by almost fifty million inhabitants in West and Central Africa, is an example of a linguistic domain that has not been thoroughly studied. The Hausa language employs diacritics, which are symbols located above alphabetical characters to convey further information. By removing diacritics, the number of homographs increases, making it difficult to distinguish between similar words. This paper presents a study on speech recognition in the Hausa Language, specifically focusing on diacritized words. The study utilises the state-of-the-art wave2vec2.0 and Whisper deep learning architecture models, for transcribing audio signals into corresponding Hausa text. According to the results obtained in the study, the Whisper-large deep model emerged as the best, achieving a word error rate of 4.23% representing a considerable improvement of 43.9% when compared to the existing state-of-the-art model for Hausa language speech recognition. Additionally, the Whsiper-large model demonstrated a diacritic coverage of 92%, precision of 98.87%, with a diacritic error rate of 2.1%. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Improved Double Deep Q Network-Based Task Scheduling Algorithm in Edge computing for Makespan Optimization

引用

Tsinghua science and Technology 2024年第3期29卷 806-817页

作者： Lei Zeng Qi Liu Shigen Shen Xiaodong Liu School of Computer Science Nanjing University of Information Science and TechnologyNanjing 210044China School of Software Nanjing University of Information Science and TechnologyNanjing 210044China School of Information Engineering Huzhou UniversityHuzhou 313000China School of Computing Edinburgh Napier UniversityEdinburghEH105DTUK

Edge computing nodes undertake an increasing number of tasks with the rise of business ***,how to efficiently allocate large-scale and dynamic workloads to edge computing resources has become a critical *** study proposes an edge task scheduling approach based on an improved Double Deep Q Network(DQN),which is adopted to separate the calculations of target Q values and the selection of the action in two networks.A new reward function is designed,and a control unit is added to the experience replay unit of the *** management of experience data are also modified to fully utilize its value and improve learning *** learning agents usually learn from an ignorant state,which is *** such,this study proposes a novel particle swarm optimization algorithm with an improved fitness function,which can generate optimal solutions for task *** optimized solutions are provided for the agent to pre-train network parameters to obtain a better cognition *** proposed algorithm is compared with six other methods in simulation *** show that the proposed algorithm outperforms other benchmark methods regarding makespan.

关键词： edge computing task scheduling reinforcement learning makespan Double Deep Q Network(DQN)

来源：评论

学校读者我要写书评

暂无评论

An Automated Identification Approach for Partial Discharge Detection Using Density-Based Clustering Without User Inputs

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第1期5卷 310-320页

作者： Rahman, Md Anisur Ang, Li-Minn Seng, Kah Phooi Charles Sturt University School of Computing Mathematics & Engineering BathurstNSW2795 Australia University of the Sunshine Coast School of Science and Engineering Sippy DownsQLD4556 Australia Xi'an Jiaotong Liverpool University School of AI & Advanced Computing Suzhou215123 China Queensland University of Technology School of Computer Science BrisbaneQLD4000 Australia

A recently published state-of-the-art density-based clustering technique called ICFSFDP for partial discharge (PD) detection requires various sensitive user-defined input parameters. This article presents a parameter-free clustering technique called PDAutoClust for PD detection. The PDAutoClust algorithm can produce high-quality clusters for PD datasets without requiring user-defined input parameters. PDAutoClust produces high-quality clustering results by utilizing a vein-based density clustering approach. The vein of a cluster is produced by using multivariate kernel density estimation and a unique neighborhood set. We compared the performance of PDAutoClust against ICFSFDP and seven other state-of-the-art density-based and non-density-based clustering techniques by using four PD datasets in terms of adjusted rand index, normalized mutual information, F1-score, and purity. Another contribution of the article is a novel merging technique used with PDAutoClust to merge small non-viable clusters that a clustering technique may produce. PDAutoClust produces the final clusters for a dataset by merging the non-viable clusters that a clustering technique may produce. We also evaluate the performance of PDAutoClust with merging technique versus PDAutoClust without merging technique using four datasets. Simulation results for PDAutoClust with the merging technique show good performance compared to ICFSFDP and seven other state-of-the-art clustering techniques. We also performed an ablation study to demonstrate the importance of the steps involved in PDAutoClust. © 2020 IEEE.

关键词： Merging

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：