检索结果-内蒙古大学图书馆

Multimodal Machine Learning Analysis of GaSe Molecular Beam Epitaxy Growth Conditions

ACS applied materials & interfaces 2025年第23期17卷 2025 May 28页

作者： Mingyu Yu Isaiah A Moses Wesley F Reinhart Stephanie Law Department of Materials Science and Engineering University of Delaware Newark Delaware 19716 United States. Materials Research Institute Pennsylvania State University University Park Pennsylvania 16827 United States. Department of Materials Science and Engineering Pennsylvania State University University Park Pennsylvania 16827 United States. Institute for Computational and Data Science Pennsylvania State University University Park Pennsylvania 16827 United States.

Autonomous synthesis platforms integrating machine learning with in situ diagnostics have the potential to revolutionize thin-film growth by enabling real-time process optimization and reducing the need for manual tuning. However, their application to molecular beam epitaxy (MBE) remains underdeveloped. Here, we present a machine learning-guided framework for MBE growth of GaSe films, leveraging reflection high-energy electron diffraction (RHEED) as an in situ diagnostic alongside characterization via X-ray diffraction and atomic force microscopy. Unsupervised learning on RHEED patterns reveals a well-defined boundary between high- and low-quality samples, capturing physically meaningful features. Mutual information analysis shows a strong correlation between RHEED embeddings and rocking curve full-width at half-maximum (fwhm), while the correlation with AFM root-mean-square (RMS) roughness is weak. Among key growth conditions, growth rate most strongly influences fwhm, whereas the Se/Ga flux ratio primarily affects RMS roughness and the RHEED embeddings. Supervised learning models trained to predict fwhm and RMS roughness demonstrate moderate accuracy, with significant improvement achieved by incorporating RHEED embeddings. Furthermore, anomaly detection via residual analysis in supervised learning aligns well with unsupervised classification from RHEED, reinforcing the reliability of the predictive models. This study establishes a data-driven framework for machine learning-assisted MBE, paving the way for real-time process control and accelerated optimization of thin-film synthesis.

关键词： autonomous synthesis platform in situ diagnostics machine learning molecular beam epitaxy van der Waals chalcogenides

来源：评论

学校读者我要写书评

暂无评论

Integrating Instruction-based Learning with Bidirectional LSTM for Autonomous Vehicle Pedestrian Detection

Integrating Instruction-based Learning with Bidirectional LS...

引用

Multi-Agent Systems for Collaborative Intelligence (ICMSCI), International Conference on

作者： B Shoba T Raghunathan S.Sam Peter Karthick K Akshya. J M. Sundarrajan Mani Deepak Choudhry Department of Electronics and Communication Engineering PSN College of Engineering and Technology Tirunelveli Department of Artificial Intelligence and Data Science Dr.NG.p.Institute of Technology Coimbatore Department of Computer Science and Engineering Sri Krishna College of Technology Coimbatore Department of Information Technology Sona College of Technology Salem Department of Computational Intelligence SRM Institute of Science and Technology Chennai Department of Networking and Communications SRM Institute of Science and Technology Chennai Department of Computing Technologies SRM Institute of Science and Technology Chennai

ISBN: (数字)9798331509828

ISBN: (纸本)9798331509835

Pedestrian detection is a crucial aspect of autonomous vehicle (A V) safety, as it enables accurate identification and tracking of individuals in an A V environment. Effective pedestrian detection supports essential A V functions like braking, steering, and speed control to prevent accidents in urban settings. Traditional computer vision methods, such as Support Vector Machines and Random Forests, rely on pre-designed features like the Histogram of Oriented Gradients. While the existing techniques offer some performance, it face significant challenges in dynamic environments, especially under varying lighting conditions, occlusions, and diverse pedestrian poses. Traditional models also require extensive manual feature engineering and tuning, which limits scalability and adaptability. Recent advances in deep learning, particularly with Convolutional Neural Networks (CNNs), have allowed for automatic feature learning, yielding practical improvements over classical methods. However, CNNs can struggle in low light and when facing adversarial attacks, as they mainly capture spatial features. To address these limitations, this research proposes a new methodology combining CNNs for spatial feature extraction with Bidirectional Long Short-Term Memory (BiLSTM) networks to capture temporal dependencies. This hybrid approach enhances detection capabilities by learning both static and dynamic patterns. Our proposed CNN-BiLSTM model achieves a 92 % detection accuracy and an F1 score of 88.5% across diverse conditions, outperforming existing models by up to 15%. By integrating temporal features, the model reduces missed detections and false positives by up to 20%, providing a more reliable and adaptable solution for pedestrian detection in autonomous vehicles.

关键词： Adaptation models Pedestrians Heuristic algorithms Feature extraction Real-time systems Vehicle dynamics Collision avoidance Autonomous vehicles Optimization Logistics

来源：评论

学校读者我要写书评

暂无评论

Genre Classification of Bangla Poem Using Machine Learning and Deep Learning Techniques

Genre Classification of Bangla Poem Using Machine Learning a...

引用

AI IoT Congress (AIIoT), World

作者： Syed Tangim Pasha Ashraful Islam Mohammed Masudur Rahman Eshtiak Ahmed Md. Ferdouse Ahmed Foysal Md Zahangir Alam Department of Computing and Information System Daffodil International University Bangladesh Center for Computational and Data Sciences Independent University Bangladesh Department of Computer Science and Engineering Independent University Bangladesh Department of Computer Science and Engineering International Standard University Bangladesh Department of Computer Science and Engineering Daffodil International University Bangladesh

The computational analysis of the Bangla poems is a challenging task due to the diverse linguistic, stylistic, and semantic features of the Bangla language. In this work, we prepared a dataset of 1311 Bangla poems of two separate categories: Love and Miscellaneous poem, which contain 500 and 811 poems respectively. We used word or semantic-based features to classify Bangla poems using the TF-IDF feature techniques. We used Logistic Regression, Naïve Bayes (NB), and Support Vector Machine (SVM) models for classification through machine learning, and we used Bayesian optimization techniques for hyperparameters tuning of these three models. We also used LSTM, CNN, and transformer models for this research. For the performance evaluation of the classification models, we used four evaluation metrics of precision, recall, F1-score, and accuracy. We also used the ROC-AUC curve to distinguish between all the machine learning and deep learning models. The experimental results expressed that, the transformer model achieved the highest accuracy compared to all the typical machine learning and deep learning models with an accuracy of 87%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Theory of Non-Linear Feature Learning with One Gradient Step in Two-Layer Neural Networks

arXiv

引用

arXiv 2023年

作者： Moniri, Behrad Lee, Donghwan Hassani, Hamed Dobriban, Edgar Department of Electrical and Systems Engineering University of Pennsylvania United States Graduate Group in Applied Mathematics and Computational Science University of Pennsylvania United States Department of Statistics and Data Science University of Pennsylvania United States

Feature learning is thought to be one of the fundamental reasons for the success of deep neural networks. It is rigorously known that in two-layer fully-connected neural networks under certain conditions, one step of gradient descent on the first layer can lead to feature learning;characterized by the appearance of a separated rank-one component—spike—in the spectrum of the feature matrix. However, with a constant gradient descent step size, this spike only carries information from the linear component of the target function and therefore learning non-linear components is impossible. We show that with a learning rate that grows with the sample size, such training in fact introduces multiple rank-one components, each corresponding to a specific polynomial feature. We further prove that the limiting large-dimensional and large sample training and test errors of the updated neural networks are fully characterized by these spikes. By precisely analyzing the improvement in the training and test errors, we demonstrate that these non-linear features can enhance learning. © 2023, CC BY.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Demystifying Disagreement-on-the-Line in High Dimensions

arXiv

引用

arXiv 2023年

作者： Lee, Donghwan Moniri, Behrad Huang, Xinmeng Dobriban, Edgar Hassani, Hamed Graduate Group in Applied Mathematics and Computational Science University of Pennsylvania United States Department of Electrical and Systems Engineering University of Pennsylvania United States Department of Statistics and Data Science University of Pennsylvania United States

Evaluating the performance of machine learning models under distribution shift is challenging, especially when we only have unlabeled data from the shifted (target) domain, along with labeled data from the original (source) domain. Recent work suggests that the notion of disagreement, the degree to which two models trained with different randomness differ on the same input, is a key to tackle this problem. Experimentally, disagreement and prediction error have been shown to be strongly connected, which has been used to estimate model performance. Experiments have led to the discovery of the disagreement-on-the-line phenomenon, whereby the classification error under the target domain is often a linear function of the classification error under the source domain;and whenever this property holds, disagreement under the source and target domain follow the same linear relation. In this work, we develop a theoretical foundation for analyzing disagreement in high-dimensional random features regression;and study under what conditions the disagreement-on-the-line phenomenon occurs in our setting. Experiments on CIFAR-10-C, Tiny ImageNet-C, and Camelyon17 are consistent with our theory and support the universality of the theoretical findings. © 2023, CC BY.

关键词： Errors

来源：评论

学校读者我要写书评

暂无评论

ACCELERATING ILL-CONDITIONED HANKEL MATRIX RECOVERY VIA STRUCTURED NEWTON-LIKE DESCENT∗

arXiv

引用

arXiv 2024年

作者： Cai, Hanqin Huang, Longxiu Lu, Xiliang You, Juntao Department of Statistics and Data Science Department of Computer Science University of Central Florida OrlandoFL32816 United States Department of Computational Mathematics Science and Engineering Department of Mathematics Michigan State University East LansingMI48823 United States School of Mathematics and Statistics Hubei Key Laboratory of Computational Science Wuhan University Wuhan430072 China Institute for Advanced Study Shenzhen University Shenzhen518000 China

This paper studies the robust Hankel recovery problem, which simultaneously removes the sparse outliers and fulfills missing entries from the partial observation. We propose a novel non-convex algorithm, coined Hankel Structured Newton-Like Descent (HSNLD), to tackle the robust Hankel recovery problem. HSNLD is highly efficient with linear convergence, and its convergence rate is independent of the condition number of the underlying Hankel matrix. The recovery guarantee has been established under some mild conditions. Numerical experiments on both synthetic and real datasets show the superior performance of HSNLD against state-of-the-art *** Codes 15A29, 15A83, 47B35, 90C17, 90C26, 90C53 Copyright © 2024, The Authors. All rights reserved.

关键词： Recovery

来源：评论

学校读者我要写书评

暂无评论

Optimized Transfer Learning Model for Lung Cancer Stage Classification Using Computed Tomography Images

Optimized Transfer Learning Model for Lung Cancer Stage Clas...

引用

IoT Based Control Networks and Intelligent Systems (ICICNIS), International Conference on

作者： R Deepika P. Shanmugam K. Moorthi P. K. Manoj Kumar S. L. Swarna Ramnath. K Department of Artificial Intelligence and Data Science B V Raju Institute of Technology Narsapur Telangana India Department of Computer Science and Engineering Rajalakshmi Engineering College Chennai India Department of Electronics and Communication Engineering Sri Sairam Engineering College Chennai India School of Computational Intelligence Joy University Tirunelveli India Department of Computer Science and Engineering Sona college of Technology Salem Tamilnadu India Department of Computer Science and Engineering K.L.N College of Information Technology Madurai Tamilnadu India

ISBN: (数字)9798331518097

ISBN: (纸本)9798331518103

Lung cancer has become one of the primary causes of death worldwide due to cancer, which indicates the necessity of early diagnosis. In this regard, the present work proposes an optimized model of transfer learning based on characterizing different stages of lung cancer by using computed tomography images acquired from the IQ-OTH/NCCD lung cancer database downloadable from Kaggle. It makes use of a two-step process: first, a U-Net model is used on the patient's CT images to reconstruct anatomical features and reduce noise; second, a ShuffleNet architecture is used to predict the patient's CT stage using the reconstructed image. In addition, to enhance classification, PSO was incorporated into the model so that it can optimize the hyperparameters. The accuracy of the model was at 97.85 percent, and it suggests that the model can become a very useful tool for clinicians to bring about earliest identification and staging for lung cancer.

关键词： Accuracy databases computational modeling Computed tomography Transfer learning Noise Lung cancer Predictive models Image reconstruction Optimization

来源：评论

学校读者我要写书评

暂无评论

Version Innovation Age and Age of Incorrect Version for Monitoring Markovian Sources

Version Innovation Age and Age of Incorrect Version for Moni...

引用

International Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks (WiOpt)

作者： Mehrdad Salimnejad Marios Kountouris Anthony Ephremides Nikolaos Pappas Department of Computer and Information Science Linköping University Linköping Sweden Department of Computer Science and Artificial Intelligence Andalusian Research Institute in Data Science and Computational Intelligence (DaSCI) University of Granada Spain Electrical and Computer Engineering University of Maryland College Park MD USA

ISBN: (数字)9783903176652

ISBN: (纸本)9798331508722

In this paper, we study the problem of real-time remote tracking of a two-state Markov process. We introduce a modified randomized stationary sampling and transmission policy where the decision to perform sampling occurs probabilistically depending on the current state of the source and whether the system was in a sync state during the previous time slot or not. We then propose two new performance metrics, coined the Version Innovation Age (VIA) and the Age of Incorrect Version (AoIV), and analyze their performance under the modified randomized stationary and other state-of-the-art sampling and transmission policies. Specifically, we derive closed-form expressions for the distribution and the average of VIA and AoIV under these policies. Furthermore, we formulate and solve two constrained optimization problems. The first optimization problem aims to minimize the average VIA subject to constraints on the time-averaged sampling cost and time-averaged reconstruction error. In the second problem, the objective is to minimize the average AoIV while considering a constraint on the time-averaged sampling cost. Finally, we compare the performance of various sampling and transmission policies and identify the conditions under which each policy outperforms the others in optimizing the proposed metrics.

关键词： Measurement Technological innovation Costs Transmitters Wireless networks System performance Receivers Synchronization Optimization Monitoring

来源：评论

学校读者我要写书评

暂无评论

Defense Strategy against Byzantine Attacks in Federated Machine Learning: Developments towards Explainability

Defense Strategy against Byzantine Attacks in Federated Mach...

引用

IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)

作者： Nuria Rodríguez-Barroso Javier Del Ser M. Victoria Luzón Francisco Herrera Dept. of Computer Science and Artificial Intelligence Andalusian Research Institute in Data Science and Computational Intelligence (DaSCI) University of Granada Granada Spain TECNALIA Basque Research and Technology Alliance (BRTA) Derio Bizkaia Spain University of the Basque Country (UPV/EHU) Bilbao Bizkaia Spain Department of Software Engineering Andalusian Research Institute in Data Science and Computational Intelligence (DaSCI) University of Granada Granada Spain

ISBN: (数字)9798350319545

ISBN: (纸本)9798350319552

The rise of high-risk AI systems has led to escalating concerns, prompting regulatory efforts such as the recently approved EU AI Act. In this context, the development of responsible AI systems is crucial. To this end, trustworthy AI techniques aim at requirements (including transparency, privacy awareness and fairness) that contribute to the development of responsible, robust and safe AI systems. Among them, Federated Learning (FL) has emerged as a key approach to safeguarding data privacy while enabling the collaborative training of AI models. However, FL is prone to adversarial attacks, particularly byzantine attacks, which aim to modify the behavior of the model. This work addresses this issue by proposing an eXplainable and Impartial Dynamic Defense against Byzantine Attacks (XI-DDaBA). This defense mechanism relies on robust aggregation operators and filtering techniques to mitigate the effects of adversarial attacks in FL, while providing explanations for its decisions and ensuring that clients with poor data quality are not discriminated. Experimental simulations are discussed to assess the performance of XI-DDaBA against other baselines from the literature, and to showcase its provided explanations. Overall, XI-DDaBA aligns with the need for responsible AI systems in high-risk collaborative learning scenarios through the explainable and impartial provision of robustness against attacks.

关键词： Fuzzy logic Training Privacy data privacy Federated learning Filtering Robustness

来源：评论

学校读者我要写书评

暂无评论

Multi-Modal Person Re-Identification Using Depth Estimation and Edge Detection

SSRN

引用

SSRN 2023年

作者： Rayani, Mohammad Saleh Keshavaz, Ahmad Ghimatgar, Hojat Mojtaba Mansorinejad, Mojtaba Computational Neuroscience Laboratory ICT Research Institute Faculty of Intelligent Systems Engineering and Data Science Persian Gulf University Bushehr*** Iran Department of Electrical Engineering Faculty of Intelligent Systems Engineering and Data Science Persian Gulf University Bushehr*** Iran Internet of Things Laboratory ICT Research Institute Faculty of Intelligent Systems Engineering and Data Science Persian Gulf University Bushehr*** Iran

Person re-identification is the task of identifying people across different non-overlapping cameras. Despite significant advancements in this field, several key issues remain, such as viewpoint variation, illumination variation, clothing variation and random occlusions. Notable efforts have been made to leverage the information existing in additional modalities, such as depth, infrared, thermal, skeleton some of which can be obtained by using RGB-D sensors. Notwithstanding the existence of these sensors, various limitations such as monetary or technical, may disincentivize some people from using them. Nevertheless, leveraging other modalities can help significantly in improving re-identification accuracy. In this paper we use depth estimation and edge detection algorithms to extract dept and edge maps and use the fusion in dissimilarity space framework for levering both depth and edge information. We train four models RGB, RGB-D, RGB-E, and RGB-DE with the corresponding modality as the extra input channel. Then for ensemble, we fuse the dissimilarity scores computed from each model to form a final ranking. We compare the performance of different combinations of models. Experimental results on the public iLIDS-VID and Market1501 datasets show that, using a simple ResNet50 backbone, for the iDILS-VID dataset our 3-modal ensemble achieves up to 12.9% and 16% improvement in mAP and Rank 1 metrics, and for the Market1501 dataset achieves up to 12.44% and 13.81% improvement. © 2023, The Authors. All rights reserved.

关键词： Convolutional neural networks

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：