检索结果-内蒙古大学图书馆

Federated Conference on computer science and Information Systems (FedCSIS)

作者： Przemysław Głomb Michał Cholewa Paweł Foszner Jakub Bularz Institute of Theoretical and Applied Informatics Polish Academy of Sciences Gliwice Poland Department of Computer Graphics Vision and Digital Systems Faculty of Automatic Control Electronics and Computer Science Silesian University of Technology Gliwice Poland AIUT Sp. z o.o. ul Gliwice Poland

This paper presents an application of a mixture of Hidden Markov Models (HMMs) as a tool for verification of IoT fuel sensors. The IoT fuel sensors report the level of fuel in tanks of a petrol station, and are a key component for monitoring system reliability (billing), safety (fuel/oil leak detection) and security (theft prevention). We propose an algorithm for learning a mixture of HMMs based on a continual learning principle, i.e. it adapts the model while monitoring a sensor over time, signalling unexpected or anomalous sensor reports. We have tested the proposed approach on a real-life data of 15 fuel tanks being monitored with the FuelPrime system, where it has shown a very good performance (average area under ROC curve of 0.94) of detecting anomalies in the sensor data. Additionally we show that the proposed method can be used for trend monitoring and present qualitative analysis of the short and long term learning performance. The proposed method has promising performance score, the resulting model has a high degree of explainability, limited memory and computation requirements and can be easily generalized to other domains of sensor verification.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Anticoncentration of random vectors via the strong perfect graph theorem

arXiv

引用

arXiv 2023年

作者： Juškevičius, Tomas Kurauskas, Valentas Institute of Computer Science The Czech Academy of Sciences Pod Vodárenskou věží 271/2 Praha 8182 00 Czech Republic Faculty of Mathematics and Informatics Vilnius University Aka-demijos 4 Vilnius08412 Lithuania

In this paper we give anticoncentration bounds for sums of independent random vectors in finite-dimensional vector spaces. In particular, we asymptotically establish a conjecture of Leader and Radcliffe (1994) and a question of Jones (1978). The highlight of this work is an application of the strong perfect graph theorem by Chudnovsky, Robertson, Seymour and Thomas (2003) in the context of anticoncentration. © 2023, CC BY.

关键词： Vector spaces

来源：评论

学校读者我要写书评

暂无评论

A neuro-genetic Hopfield associative memory (HAM) with improved noise immunity

引用

Materials Today: Proceedings 2022年 49卷 3482-3487页

作者： Sudeep Varshney T.P. Singh Amit Singh Pushpendra K. Rajput Amit Singhal Gunjan Varshney Sharda University Greater Noida India Deaprtment of Informatics School of Computer Science University of Petroleum and Energy Studies Dehradun India Deaprtment of Cybernetics School of Computer Science University of Petroleum and Energy Studies Dehradun India Raj Kumar Goel Institute of Technology Ghaziabad India JSS Academy of Technical Education Noida India

Artificial Neural Network (ANN) is a form of computation inspired by the arrangement and purpose of the brain. Pattern Recognition is one of the demanding areas under Artificial Neural Network and pattern association is one of the major tasks through which pattern recognition is realized. Nowadays researchers are taking interest in the combination of evolutionary algorithms and ANN. In the present work, an attempt is being made to analyze the performance of Hopfield Associative Memory with Monte Carlo adaptation rule and evolutionary searching (Genetic Algorithm) for pattern storage and recall. The training pattern set has been taken a set of five Greek alphabet letters as different objects. The aim is to store Patterns with MC adaptation rule and get the best weight matrices for efficient recalling of any given set patterns. The neural networks architectures have been taken up for storing the given set of inputs, for which conventional Hebbian and Monte Carlo adaptation rule is considered. During the mutation process, various mutation probabilities are supposed to be evaluated. The detailed simulated results thus obtained will be presented with the help of tables and graph.

关键词： Artificial Neural Network (ANN) Genetic Algorithms (GA) Hopfield Associative Memory (HAM) Neuro-genetic models

来源：评论

学校读者我要写书评

暂无评论

A Queueing-theoretic Analysis of the Performance of a Cloud Computing Infrastructure: Accounting for Task Reneging or Dropping

A Queueing-theoretic Analysis of the Performance of a Cloud ...

引用

2022 International Conference on Electrical, computer, Communications and Mechatronics Engineering, ICECCME 2022

作者： Kuaban, Godlove Suila Soodan, Bhavneet Singh Kumar, Rakesh Czekalski, Piotr Institute of Theoretical and Applied Informatics Polish Academy of Sciences Baltycka 5 Gliwice44-100 Poland Chandigarh University Department of Mathematics Punjab 140413 India Namibia University of Science and Technology Department of Mathematics and Statistics Namibia Department of Computer Graphics Vision and Digital Systems Silesian University of Technology Akademicka 16 Gliwice44-100 Poland

ISBN: (数字)9781665470957

ISBN: (纸本)9781665470957

Cloud computing has revolutionized the information technology era. It offers high-speed computing, storage, and ICT resources on demand. One of the significant challenges in cloud computing is the impact of impatient users or request (task) reneging. When a request has been compromised, missed its execution deadline, or depends on other rejected ones, it must be removed from the queue without being processed. The reneging or removal of tasks from queues may trigger the reneging or removal of other tasks that depend of them. We refer to this reneging of requests from the load balancing or computing queues as correlated reneging. We presented the performance analysis of a network of queues that constitute a queueing model of a simplified cloud computing infrastructure. We show the relationship between the load, delay, and probability of buffer saturation (blocking probability). It is seen that at about 80% utilization, a small increase in utilization (due to a small increase in the arrival rate Δλ for a fixed service rate μ) results in a sharp increase in the delay experienced by the tasks, and on the probability of task rejection or blocking. © 2022 IEEE.

关键词： Cloud computing

来源：评论

学校读者我要写书评

暂无评论

Improving Sharpness-Aware Minimization with Fisher Mask for Better Generalization on Language Models

Improving Sharpness-Aware Minimization with Fisher Mask for ...

引用

2022 Findings of the Association for Computational Linguistics: EMNLP 2022

作者： Zhong, Qihuang Ding, Liang Shen, Li Mi, Peng Liu, Juhua Du, Bo Tao, Dacheng National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence School of Computer Science Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University China JD Explore Academy China School of Informatics Xiamen University China Research Center for Graphic Communication Printing and Packaging Institute of Artificial Intelligence Wuhan University China

Fine-tuning large pretrained language models on a limited training corpus usually suffers from poor generalization. Prior works show that the recently-proposed sharpness-aware minimization (SAM) optimization method can improve the model generalization. However, SAM adds a perturbation to each model parameter equally (but not all parameters contribute equally to the optimization of training), which we argue is sub-optimal and will lead to excessive computation. In this paper, we propose a novel optimization procedure, namely FSAM, which introduces a Fisher mask to improve the efficiency and performance of SAM. In short, instead of adding perturbation to all parameters, FSAM uses the Fisher information to identity the important parameters and formulates a Fisher mask to obtain the sparse perturbation, i.e., making the optimizer focus on these important parameters. Experiments on various tasks in GLUE and SuperGLUE benchmarks show that FSAM consistently outperforms the vanilla SAM by 0.67∼1.98 average score among four different pretrained models. We also empirically show that FSAM works well in other complex scenarios, e.g., fine-tuning on generation tasks or limited training data. Encouragingly, when training data is limited, FSAM improves the SAM by a large margin, i.e., up to 15.1. © 2022 Association for Computational Linguistics.

关键词： Fisher information matrix

来源：评论

学校读者我要写书评

暂无评论

IoT system for AQI monitoring and control

IoT system for AQI monitoring and control

引用

Automatics and informatics (ICAI), International Conference

作者： Ivan Ganchev Zhanlin Ji University of Plovdiv "Paisii Hilendarski" Plovdiv Bulgaria Institute of Mathematics and Informatics Bulgarian Academy of Sciences Sofia Bulgaria Telecommunications Research Centre (TRC) University of Limerick Limerick Ireland College of Mathematics and Computer Science Zhejiang A&F University Hangzhou P. R. China

ISBN: (数字)9798350353907

ISBN: (纸本)9798350353914

A horizontal-type IoT platform, named EMULSION, is presented * , which was developed for fast IoT system prototyping and speedy roll-out of respective IoT services. The successful use of the platform as a basis of various pilot systems, operating in different IoT areas, is show-cased on the example of ‘smart environment’ monitoring and control.

关键词： Navigation Heuristic algorithms Software algorithms Weather forecasting Software Real-time systems Internet of Things Quality of experience Monitoring Smart phones

来源：评论

学校读者我要写书评

暂无评论

Fusion-then-Distillation: Toward Cross-modal Positive Distillation for Domain Adaptive 3D Semantic Segmentation

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Wu, Yao Xing, Mingwei Zhang, Yachao Xie, Yuan Peng, Kaibei Qu, Yanyun Xiamen University School of Informatics Xiamen361005 China Xiamen University Institute of Artificial Intelligence Xiamen361005 China East China Normal University School of Computer Science and Technology Shanghai200062 China East China Normal University Chongqing Institute Chongqing401120 China China Academy of Railway Sciences Corporation Limited Beijing100080 China

In cross-modal unsupervised domain adaptation, a model trained on source-domain data (e.g., synthetic) is adapted to target-domain data (e.g., real-world) without access to target annotation. Previous methods seek to mutually mimic cross-modal outputs in each domain, which enforces a class probability distribution that is agreeable in different domains. However, they overlook the complementarity brought by the heterogeneous fusion in cross-modal learning. In light of this, we propose a novel fusion-then-distillation (FtD++) method to explore cross-modal positive distillation of the source and target domains for 3D semantic segmentation. FtD++ realizes distribution consistency between outputs not only for 2D images and 3D point clouds but also for source-domain and augment-domain. Specially, our method contains three key ingredients. First, we present a model-agnostic feature fusion module to generate the cross-modal fusion representation for establishing a latent space. In this space, two modalities are enforced maximum correlation and complementarity. Second, the proposed cross-modal positive distillation preserves the complete information of multi-modal input and combines the semantic content of the source domain with the style of the target domain, thereby achieving domain-modality alignment. Finally, cross-modal debiased pseudo-labeling is devised to model the uncertainty of pseudo-labels via a self-training manner. Extensive experiments report state-of-the-art results on several domain adaptive scenarios under unsupervised and semi-supervised settings. Code is available at https://***/Barcaaaa/FtD-PlusPlus. © 1991-2012 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

FROM FLIP PROCESSES TO DYNAMICAL SYSTEMS ON GRAPHONS

arXiv

引用

arXiv 2022年

作者： Garbe, Frederik Hladký, Jan Šileikis, Matas Skerman, Fiona Faculty of Informatics Masaryk University Brno Czech Republic Institute of Computer Science Czech Academy of Sciences Prague Czech Republic Department of Mathematics Uppsala University Uppsala Sweden

We introduce a class of random graph processes, which we call flip processes. Each such process is given by a rule which is a function R : Hk → Hk from all labeled k-vertex graphs into itself (k is fixed). The process starts with a given n-vertex graph G0. In each step, the graph Gi is obtained by sampling k random vertices v1, . . ., vk of Gi−1 and replacing the induced graph F := Gi−1[v1, . . ., vk] by R(F). This class contains several previously studied processes including the Erdős–Rényi random graph process and the triangle removal process. Actually, our definition of flip processes is more general, in that R(F) is a probability distribution on Hk, thus allowing randomised replacements. Given a flip process with a rule R, we construct time-indexed trajectories Φ: W0 ×[0, ∞) → W0 in the space of graphons. We prove that for any T > 0 starting with a large finite graph G0 which is close to a graphon W0 in the cut norm, with high probability the flip process will stay in a thin sausage around the trajectory (formula presented) (after rescaling the time by the square of the order of the graph). These graphon trajectories are then studied from the perspective of dynamical systems. Among others topics, we study continuity properties of these trajectories with respect to time and initial graphon, existence and stability of fixed points and speed of convergence (whenever the infinite time limit exists). We give an example of a flip process with a periodic trajectory. © 2022, CC BY-NC-ND.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

A Multi-Resolution Deep Forest Framework with Hybrid Feature Fusion for CT Whole Heart Segmentation

A Multi-Resolution Deep Forest Framework with Hybrid Feature...

引用

2021 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2021

作者： Xu, Fei Lin, Lingli Li, DIhan Hong, Qingqi Liu, Kunhong Wu, Qingqiang Li, Qingde Zheng, Yinhuan Tian, Jie Xiamen University School of Informatics China University of Hull Department of Computer Science HullHU6 7RX United Kingdom Xiamen Institute of Technology College of Computer and Artificail Intelligence China Institute of Automation Chinese Academy of Sciences Beijing100190 China

ISBN: (纸本)9781665401265

Cardiac medical image segmentation plays an important role in the diagnosis and clinical treatment of cardiovascular diseases. However, due to the variability of cardiac anatomy and the ambiguity between cardiac substructures, it is still difficult to quickly segment the entire heart from medical images. Most of the current researches utilize neural network structure to perform whole heart segmentation. Although good segmentation accuracy has been achieved, it usually requires a long training time. This paper aims to build a new whole heart segmentation model based on Deep Forest, called Multi-Resolution Deep Forest Framework(MRDFF), which performs segmentation through two stages. In the first stage, the heart region is located by rough binary classification, and similarity screening is used to reduce redundancy. The second stage subdivides the heart substructures based on the results of the first stage and uses multi-scale fusion to achieve high segmentation accuracy. The experimental results conducted on the public data set MM-WHS show that under the same training data and configuration, our model can be trained in only 4.5 hours, which is about 1/2 of the training time of neural network models, and can reach the accuracy not lower than neural network models, which shows the feasibility and efficiency of our model. The code will be made publicly available at https://***/xufeixf/MRDFF. © 2021 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

HumanNeRF-SE: A Simple yet Effective Approach to Animate HumanNeRF with Diverse Poses

arXiv

引用

arXiv 2023年

作者： Ma, Caoyuan Liu, Yu-Lun Wang, Zhixiang Liu, Wu Liu, Xinchen Wang, Zheng National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence School of Computer Science Wuhan University China National Yang Ming Chiao Tung University Taiwan The University of Tokyo Japan National Institute of Informatics Japan School of Information Science and Technology University of Science and Technology of China China JD Explore Academy

We present HumanNeRF-SE, a simple yet effective method that synthesizes diverse novel pose images with simple input. Previous HumanNeRF works require a large number of optimizable parameters to fit the human images. Instead, we reload these approaches by combining explicit and implicit human representations to design both generalized rigid deformation and specific non-rigid deformation. Our key insight is that explicit shape can reduce the sampling points used to fit implicit representation, and frozen blending weights from SMPL constructing a generalized rigid deformation can effectively avoid overfitting and improve pose generalization performance. Our architecture involving both explicit and implicit representation is simple yet effective. Experiments demonstrate our model can synthesize images under arbitrary poses with few-shot input and increase the speed of synthesizing images by 15 times through a reduction in computational complexity without using any existing acceleration modules. Compared to the state-of-the-art HumanNeRF studies, HumanNeRF-SE achieves better performance with fewer learnable parameters and less training time. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

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：