检索结果-内蒙古大学图书馆

MLRP-KG: Mine Landslide Risk Prediction Based on Knowledge Graph

学校读者我要写书评

暂无评论

IEEE Transactions on Artificial Intelligence

IEEE Transactions on Artificial Intelligence 2022年第1期3卷 78-87页

作者： Ma, Lianbo Wang, Jingwei Cheng, Jian Wang, Xingwei Zhu, Wancheng Northeastern University Shenyang China College of Software Northeastern University Shenyang China Research Institute of Mine Big Data China Coal Research Institute Beijing China College of Computer Science and Engineering Northeastern University Shenyang China School of Resource and Civil Engineering Northeastern University Shenyang China

The mine landslide risk prediction is a fundamental task for the safety management of the digital mining system, which is dependent on the analysis of the open pit mine exploitation slope stability. Such stability analysis involves a lot of local natural and human factors. Training a learning model using these factors, with the aim of discovering their relationship with the slope stability, is an intuitive way for the mine landslide risk prediction. The key issue is how to explore the complex nonlinear relations among these factors by using a small amount of high-dimensional historical slope data. Traditional factor-led methods for the issue only focus on the impacts of landslide factors, but ignore the correlations between historical slope data, which in fact contain more useful information. In this article, we propose a new mine landslide risk prediction model using knowledge graph. The gradient boosting decision tree is applied to further exploit the crossed features within the historical data, and then a landslide semantic network is constructed using knowledge graph with the consideration of correlation information between historical slope data. In this way, the model is suitable to deal with the small set of high-dimensional data, and it makes a joint use of the features within the landslide factor values and correlations between historical slope data. We conduct a set of experiments on real historical slope data from the real-world open pit mining scene. The experiment results validate the effectiveness and efficiency of the proposed model in predicting landslide risks with a small set of high-dimensional historical data. © 2020 IEEE.

关键词： Landslides

DNGNN: Efficient Deep Noisy Graph Neural Network for Spatio-Temporal Series Forecasting

学校读者我要写书评

暂无评论

DNGNN: Efficient Deep Noisy Graph Neural Network for Spatio-...

2025 2nd International Conference on Algorithms, Software Engineering and Network Security (ASENS)

作者： Songbo Wang Yifan Chen Haizhi Xu Jianqiao Hu Peiyu Zeng Ziming Hu School of Computing and Data Science The University of Hong Kong Hong Kong China School of Microelectronics Science and Technology Sun Yat-sen University Zhuhai China School of Software Engineering South China University of Technology Guangzhou China School of Materials Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

ISBN: (数字)9798331520298

ISBN: (纸本)9798331520304

Spatio-temporal series forecasting plays a vital role in the domain of multivariate time series prediction. By leveraging accurate and comprehensive spatio-temporal sequence prediction models, it becomes possible to extract higher-order spatio-temporal interactions between real-world connections, thereby contributing to smart city construction. Spatio-Temporal Graph Neural Networks (STGNNs) have emerged as a highly effective approach for addressing spatio-temporal series prediction challenges. Nevertheless, most existing methods predominantly rely on traditional graph convolutional networks (GCNs) and their variants for spatial feature extraction. Due to inherent limitations such as over-smoothing, these models often constrain spatial feature encoding to shallow architectures, typically limited to 2-3 layers. Additionally, the presence of noisy data in real-world scenarios significantly impacts the prediction accuracy of existing STGNN models. In this paper, building upon the classic STGNN framework, we propose a graph neural network framework based on deep residual connections and noise injection mechanism to address the aforementioned issues. Specifically, inspired by the principles of initial residual connection and identity mapping, we proposed a deep spatio-temporal graph neural network framework of 12 layers to capture the high-dimensional interactions, while using noise injection mechanism to mitigate the adverse effects of noisy data. Sufficient experimental results on typical time-series datasets demonstrate the effectiveness of our proposed framework.

关键词： Accuracy Noise Time series analysis Predictive models Feature extraction Transformers Graph neural networks Spatiotemporal phenomena Noise measurement Forecasting

Few-Shot Learning-Based Machine Fault Diagnosis Using EMD-Gammatone Spectrogram with Limited Labeled Audio dataset

学校读者我要写书评

暂无评论

Few-Shot Learning-Based Machine Fault Diagnosis Using EMD-Ga...

2025 IEEE International Conference on Big data and Smart computing, BigComp 2025

作者： Zabin, Mahe Ayon, Syed Tasnimul Karim Siraj, Farhan Md Shuvo, Mehedi Hasan Choi, Ho-Jin Uddin, Jia Korea Advanced Institute of Science and Technology School of Computing Daejeon Korea Republic of BRAC University Department of Computer Science and Engineering Dhaka Bangladesh Dhaka University of Engineering & Technology Department of Computer Science and Engineering Dhaka Gazipur Bangladesh Woosong University AI and Big Data Department Endicott College Daejeon Korea Republic of

The deep learning models are computationally burdensome, and their accuracy depends on the number of labeled datasets used in training. The scarcity of the labeled dataset in industrial machine diagnosis is a significant concern as it is pretty impossible to collect data from faulty machines in industrial environments. To address this issue, in this paper, we presented a few-shot learning-based machine fault diagnosis model on a lightweight SqueezeNet architecture using generated texture images from audio sensor data. Subsets of two public audio datasets, MIMII and ToyADMOS, containing limited data- 10 images per class were used to validate the model. The experimental results demonstrate that the model has exhibited 89.6% and 98.3% accuracy for MIMII and ToyADMOS, respectively, with only ten labeled images of each fault class. As the model has only 73 thousand trainable parameters and requires only 300 KB of memory, it is expected to be deployable in a portal device for machine fault diagnosis. © 2025 IEEE.

关键词： Deep learning

QiMINT: Quantum-Inspired Mobile Intelligence - Advancing Complex Signal Processing with Machine Learning

学校读者我要写书评

暂无评论

QiMINT: Quantum-Inspired Mobile Intelligence - Advancing Com...

International Conference on Trends in Electronics and Informatics (ICEI)

作者： Vinothkumar Kolluru E. Helen Parimala Kokilavani T Sunil Raj Y Bastin Jesuraj Afrig Aminuddin Department of Data Science Stevens Institute of Technology NJ USA Department of Computer Science Gitam Deemed to be University Bangalore India Department of Computer Science School of Sciences Christ (Deemed) University Bangalore India Department of Data Science St. Xavier's College (Autonomous) Palayamkottai India Department of Computer Science Mother Theresa Arts and Science College Theni Tamilnadu India Department of Information System Faculty of Computer Science Universitas Amikom Yogyakarta Sleman Indonesia

ISBN: (数字)9798331544607

ISBN: (纸本)9798331544614

Integrating mobile intelligence with quantum-inspired machine learning (QiML) opens space for challenging mobile signal processing tasks. By utilizing superposition and entanglement, quantum computing principles, QiML boosts the agility of mobile devices by allowing real-time data processing, pattern recognition, and decision making. This work introduces Quantum-Inspired Mobile Intelligence (QiMINT) a new mobile computing framework that integrates quantum-inspired designs with classical machine learning, which increases mobile devices' accuracy, latency, and energy efficiency. Results show that medical QiML based models exceeded traditional machine learning methods in most key performance indicators. The quantum convolutional neural network (QCNN) achieved an accuracy of 92.3% in contrast with the CNNs' 87.5%, but with a processing time of 80 ms as to 120 ms, energy consumption of 10 mJ in comparison to the CNNs' 15mJ. Also, quantum-inspired random forests lowered processing delay by 40%, sustaining superior accuracy than the classical-base system. These results demonstrate that QiML can effectively balance computation complexity while making it suitable for edge computing, IoT, and mobile intelligence systems.

关键词： Quantum computing Accuracy Decision making Machine learning Signal processing Real-time systems Mobile handsets Pattern recognition Optimization Edge computing

Strictly positive definite kernels on compact Riemannian manifolds

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Guella, Jean Carlo Jäger, Janin Unicamp Institute of Mathematics Statistics and Scientific Computing Campinas Brazil KU Eichstätt-Ingolstadt Mathematisches Institute for machine learning and data science Ingolstadt Germany

The paper studies strictly positive definite kernels on compact Riemannian manifolds. We state new conditions to ensure strict positive definiteness for general kernels and kernels with certain convolutional structure. We also state conditions for such kernels on product manifolds. As an example conditions for products of two-point homogeneous spaces are *** Codes 33B10, 33C20, 42A16, 46E22, 65D05 Copyright © 2023, The Authors. All rights reserved.

关键词： Geometry

ECLIPSE: Expunging Clean-label Indiscriminate Poisons via Sparse Diffusion Purification

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Xianlong Hu, Shengshan Zhang, Yechao Zhou, Ziqi Zhang, Leo Yu Xu, Peng Wan, Wei Jin, Hai National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab China Cluster and Grid Computing Lab China Hubei Engineering Research Center on Big Data Security China Hubei Key Laboratory of Distributed System Security China School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430074 China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China School of Information and Communication Technology Griffith University SouthportQLD4215 Australia

Clean-label indiscriminate poisoning attacks add invisible perturbations to correctly labeled training images, thus dramatically reducing the generalization capability of the victim models. Recently, defense mechanisms such as adversarial training, image transformation techniques, and image purification have been proposed. However, these schemes are either susceptible to adaptive attacks, built on unrealistic assumptions, or only effective against specific poison types, limiting their universal applicability. In this research, we propose a more universally effective, practical, and robust defense scheme called ECLIPSE. We first investigate the impact of Gaussian noise on the poisons and theoretically prove that any kind of poison will be largely assimilated when imposing sufficient random noise. In light of this, we assume the victim has access to an extremely limited number of clean images (a more practical scene) and subsequently enlarge this sparse set for training a denoising probabilistic model (a universal denoising tool). We then introduce Gaussian noise to absorb the poisons and apply the model for denoising, resulting in a roughly purified dataset. Finally, to address the trade-off of the inconsistency in the assimilation sensitivity of different poisons by Gaussian noise, we propose a lightweight corruption compensation module to effectively eliminate residual poisons, providing a more universal defense approach. Extensive experiments demonstrate that our defense approach outperforms 10 state-of-the-art defenses. We also propose an adaptive attack against ECLIPSE and verify the robustness of our defense scheme. Our code is available at https://***/CGCL-codes/ECLIPSE. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep neural networks

Learning rate adaptive stochastic gradient descent optimization methods: numerical simulations for deep learning methods for partial differential equations and convergence analyses

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Dereich, Steffen Jentzen, Arnulf Riekert, Adrian Institute for Mathematical Stochastics University of Münster Germany School of Data Science Shenzhen Research Institute of Big Data The Chinese University of Hong Kong CUHK-Shenzhen Shenzhen China Applied Mathematics Institute for Analysis and Numerics University of Münster Germany

It is known that the plain vanilla standard stochastic gradient descent (SGD) optimization method, accelerated SGD methods such as the momentum SGD optimization method, adaptive SGD methods such the Adagrad and the RMSprop optimization methods, as well as accelerated and adaptive SGD optimization methods such as the Adam optimizer fail to converge if the learning rates do not converge to zero (as, for example, in the situation of constant learning rates). In numerical simulations SGD optimization methods are sometimes applied with learning rate schedules that are determined through human based tuning procedures and are also sometimes applied with small but constant learning rates. In standard machine learning implementation frameworks such as TensorFlow and Pytorch the default learning rate schedules for SGD optimization methods are constant learning rates. In this work we propose and study a learning-rate-adaptive approach for SGD optimization methods in which the learning rate is adjusted based on empirical estimates for the values of the objective function of the optimization problem (the function that one intends to minimize in the considered optimization problem). In particular, we propose a learning-rate-adaptive variant of the Adam optimizer and implement it in Pytorch in case of several neural network learning problems, particularly, in the context of deep learning approximation methods for partial differential equations (PDEs) such as deep Kolmogorov methods (DKMs), physics-informed neural networks (PINNs), and deep Ritz methods (DRMs). In each of the presented learning problems the proposed learning-rate-adaptive variant of the Adam optimizer faster reduces the value of the objective function than the Adam optimizer with the default learning rate. For a simple class of quadratic minimization problems we also rigorously prove that a learning-rate-adaptive variant of the SGD optimization method converges to the minimizer of the considered minimization proble

关键词： Partial differential equations

Robust Federated Learning in Unreliable Wireless Networks: A Client Selection Approach

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Wang, Yanmeng Ji, Wenkai Zhou, Jian Xiao, Fu Chang, Tsung-Hui School of Computer Science Nanjing University of Posts and Telecommunications Nanjing210023 China School of Science and Engineering The Chinese University of Hong Kong Shenzhen518172 China Shenzhen Research Institute of Big Data Shenzhen518172 China

Federated learning (FL) has emerged as a promising distributed learning paradigm for training deep neural networks (DNNs) at the wireless edge, but its performance can be severely hindered by unreliable wireless transmission and inherent data heterogeneity among clients. Existing solutions primarily address these challenges by incorporating wireless resource optimization strategies, often focusing on uplink resource allocation across clients under the assumption of homogeneous client-server network standards. However, these approaches overlooked the fact that mobile clients may connect to the server via diverse network standards (e.g., 4G, 5G, Wi-Fi) with customized configurations, limiting the flexibility of server-side modifications and restricting applicability in real-world commercial networks. This paper presents a novel theoretical analysis about how transmission failures in unreliable networks distort the effective label distributions of local samples, causing deviations from the global data distribution and introducing convergence bias in FL. Our analysis reveals that a carefully designed client selection strategy can mitigate biases induced by network unreliability and data heterogeneity. Motivated by this insight, we propose FedCote, a client selection approach that optimizes client selection probabilities without relying on wireless resource scheduling. Experimental results demonstrate the robustness of FedCote in DNN-based classification tasks under unreliable networks with frequent transmission failures. Copyright © 2025, The Authors. All rights reserved.

关键词： Federated learning

Finite-time analysis of globally nonstationary multi-armed bandits

学校读者我要写书评

暂无评论

The Journal of Machine Learning Research

The Journal of Machine Learning Research 2024年第1期25卷 5481-5536页

作者： Junpei Komiyama Edouard Fouché Junya Honda Stern School of Business New York University Institute for Program Structures and Data Organization Karlsruhe Institute of Technology Germany Department of Systems Science Graduate School of Informatics Kyoto University Japan Center for Advanced Intelligence Project RIKEN Japan

We consider nonstationary multi-armed bandit problems where the model parameters of the arms change over time. We introduce the adaptive resetting bandit (ADR-bandit), a bandit algorithm class that leverages adaptive windowing techniques from literature on data streams. We first provide new guarantees on the quality of estimators resulting from adaptive windowing techniques, which are of independent interest. Furthermore, we conduct a finite-time analysis of ADR-bandit in two typical environments: an abrupt environment where changes occur instantaneously and a gradual environment where changes occur progressively. We demonstrate that ADR-bandit has nearly optimal performance when abrupt or gradual changes occur in a coordinated manner that we call global changes. We demonstrate that forced exploration is unnecessary when we assume such global changes. Unlike the existing nonstationary bandit algorithms, ADR-bandit has optimal performance in stationary environments as well as nonstationary environments with global changes. Our experiments show that the proposed algorithms outperform the existing approaches in synthetic and real-world environments.

关键词： multi-armed bandits adaptive windows nonstationary bandits changepoint detection sequential learning