检索结果-内蒙古大学图书馆

11th International Conference on Control, Automation and Information Sciences (ICCAIS)

作者： Moratuwage, Diluka Punchihewa, Yuthika Lee, Ji Youn Curtin Univ Sch Elect Engn Comp & Math Sci Bentley WA Australia

ISBN: (数字)9781665452489

ISBN: (纸本)9781665452489

The recent multi-sensor Generalized Labeled Multi-Bernoulli (GLMB) is an efficient analytic implementation to the multi-sensor multi-object state estimation problem. The multi-sensor multi-object posterior is recursively propagated using the multi-sensor multi-object filtering density, by updating it with multi-sensor measurements at each time step. The measurement update step requires solving a series of NP-hard multi-dimensional assignment problems. In this paper, we introduce a faster implementation of this algorithm by an intuitive approximation, and combine that with the Gibbs sampler based truncation approach to produce an efficient multi-sensor multi-object estimation solution suitable for practical applications.

关键词： Automation Density measurement filtering algorithms Information filters Approximation algorithms Time measurement Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Generalized Polynomial Chaos-based Ensemble Kalman filtering for Orbit Estimation

Generalized Polynomial Chaos-based Ensemble Kalman Filtering...

引用

American Control Conference (ACC)

作者： Bhusal, Rajnish Subbarao, Kamesh Univ Texas Arlington Dept Mech & Aerosp Engn Arlington TX 76019 USA

ISBN: (纸本)9781665441971

In this paper. a novel framework is proposed to carry out state and parameter estimation of a general nonlinear stochastic dynamical system in a prediction-correction fashion. The uncertainties in the initial states and parameters are propagated using generalized polynomial chaos expansion technique to compute the predicted estimates of states and parameters. Once the measurements are available, a nonlinear estimator is developed to update the predicted estimates in ensemble filtering framework. The methodology is then applied to estimate the states and uncertain parameters of a satellite for Low Earth Orbit (LEO) navigation using Global Positioning System (GPS) measurements. The results obtained from generalized polynomial chaos expansion-based ensemble filter are compared with that obtained from the unscented Kalman filter and the particle filter in terms of accuracy and computational efficiency.

关键词： Uncertainty filtering Low earth orbit satellites filtering algorithms Extraterrestrial measurements Particle filters Orbits

来源：评论

学校读者我要写书评

暂无评论

Fault Detection for Lithium-Ion Battery Using Smooth Variable Structure Filters

引用

IEEE ACCESS 2024年 12卷 156273-156284页

作者： Ebrahimi, Farzaneh Hosseininejad, Reza Al Akchar, Mahmoud Brice Tongkoua Bangmi, Christian Ahmed, Ryan Setoodeh, Peyman Habibi, Saeid McMaster Univ Dept Mech Engn Ctr Mechatron & Hybrid Technol CMHT Hamilton ON L8S 4L8 Canada

Batteries are prone to faults that may arise because of vibrations, deformations, collisions, or improper usage. These faults can be sorted into two main categories: internal and external faults. In this study, external battery faults, particularly sensor faults that affect the measurement of current and voltage, are investigated. This paper proposes a fault-detection strategy that is built on different variants of the Smooth Variable Structure Filter (SVSF) for the detection of such faults in a battery cell. SVSF is applied to estimate the State of Charge (SoC) and terminal voltage of the battery. A modified decision signal is calculated using the residual signals of the filters to detect faults using the Cumulative Sum (CUSUM) strategy. The performance of the SVSF is compared with that of the Extended Kalman Filter (EKF). The effectiveness of the proposed method is demonstrated for detecting and isolating different external faults in a wide range of fault scenarios. The proposed SVSF-based methods not only improve fault-detection accuracy but also significantly decrease the fault-detection time in some scenarios compared to EKF, which is a critical factor for safety.

关键词： Circuit faults Batteries Fault detection filtering algorithms Integrated circuit modeling Voltage measurement Noise measurement Mathematical models Fault diagnosis Trajectory Cumulative sum fault detection filtering sensor fault smooth variable structure filter

来源：评论

学校读者我要写书评

暂无评论

Contrastive Learning for Space-time Correspondence via Self-cycle Consistency

Contrastive Learning for Space-time Correspondence via Self-...

引用

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Son, Jeany GIST AI Grad Sch Gwangju South Korea

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

We propose a novel probabilistic method employing Bayesian Model Averaging and self-cycle regularization for spatio-temporal correspondence learning in videos within a self-supervised learning framework. Most existing methods for self-supervised correspondence learning suffer from noisy labels that come with the data for free, and the presence of occlusion exacerbates the problem. We tackle this issue within a probabilistic framework that handles model uncertainty inherent in the path selection problem built on a complete graph. We propose a self-cycle regularization to consider a cycle-consistency property on individual edges in order to prevent converging on noisy matching or trivial solutions. We also utilize a mixture of sequential Bayesian filters to estimate posterior distribution for targets. In addition, we present a domain contrastive loss to learn discriminative representation among videos. Our algorithm is evaluated on various datasets for video label propagation tasks including DAVIS2017, VIP and JHMDB, and shows outstanding performances compared to the state-of-the-art self-supervised learning based video correspondence algorithms. Moreover, our method converges significantly faster than previous methods.

关键词： Training Uncertainty Government Self-supervised learning filtering algorithms Probabilistic logic Bayes methods

来源：评论

学校读者我要写书评

暂无评论

Distributed Density filtering for Large-Scale Systems Using Mean-Filed Models

Distributed Density Filtering for Large-Scale Systems Using ...

引用

American Control Conference (ACC)

作者： Zheng, Tongjia Lin, Hai Univ Notre Dame Dept Elect Engn Notre Dame IN 46556 USA

ISBN: (纸本)9781665441971

This work studies distributed (probability) density estimation of large-scale systems. Such problems are motivated by many density-based distributed control tasks in which the real-time density of the swarm is used as feedback information, such as sensor deployment and city traffic scheduling. This work is built upon our previous work [1] which presented a (centralized) density filter to estimate the dynamic density of large-scale systems through a novel integration of mean-field models, kernel density estimation (KDE), and infinite-dimensional Kalman filters. In this work, we further study how to decentralize the density filter such that each agent can estimate the global density only based on its local observation and communication with neighbors. This is achieved by noting that the global observation constructed by KDE is an average of the local kernels. Hence, dynamic average consensus algorithms are used for each agent to track the global observation in a distributed way. We present a distributed density filter which requires very little information exchange, and study its stability and optimality using the notion of input-to-state stability. Simulation results suggest that the distributed filter is able to converge to the centralized filter and remain close to it.

关键词： Heuristic algorithms Decentralized control Urban areas filtering algorithms Information filters Stability analysis Large-scale systems

来源：评论

学校读者我要写书评

暂无评论

Differentiable Channel Sparsity Search via Weight Sharing within Filters 26

Differentiable Channel Sparsity Search via Weight Sharing wi...

引用

26th International Conference on Pattern Recognition / 8th International Workshop on Image Mining - Theory and Applications (IMTA)

作者： Zhao, Yu Lee, Chung-Kuei Xidian Univ Xian Peoples R China HiSilicon Shanghai Peoples R China

ISBN: (数字)9781665490627

ISBN: (纸本)9781665490627

In this paper, we propose the differentiable channel sparsity search (DCSS) for convolutional neural networks. Unlike traditional channel pruning algorithms which require users to manually set prune ratios for each convolutional layer, DCSS automatically searches the optimal combination of sparsities. Inspired by the differentiable architecture search (DARTS), we draw lessons from the continuous relaxation and leverage the gradient information to balance the computational cost and metrics. Since directly applying the scheme of DARTS causes shape mismatching and excessive memory consumption, we introduce a novel technique called weight sharing within filters. This technique elegantly eliminates the problem of shape mismatching with negligible additional resources. We conduct comprehensive experiments on not only image classification but also find-grained tasks including semantic segmentation and image super resolution to verify the effectiveness of DCSS. Compared with previous network pruning approaches, DCSS achieves state-of-the-art results for image classification. Experimental results of semantic segmentation and image super resolution indicate that task-specific search achieves better performance than transferring slim models, demonstrating the wide applicability and high efficiency of DCSS.

关键词： Image resolution Shape Semantic segmentation Memory management filtering algorithms Information filters Stability analysis

来源：评论

学校读者我要写书评

暂无评论

Nonlinear Model Predictive Control Based on Constraint-Aware Particle filtering/Smoothing

Nonlinear Model Predictive Control Based on Constraint-Aware...

引用

American Control Conference (ACC)

作者： Askari, Iman Zeng, Shen Fang, Huazhen Univ Kansas Dept Mech Engn Lawrence KS 66045 USA Washington Univ Dept Elect & Syst Engn St Louis MO 63130 USA

ISBN: (纸本)9781665441971

Nonlinear model predictive control (NMPC) has gained widespread use in many applications. Its formulation traditionally involves repetitively solving a nonlinear constrained optimization problem online. In this paper, we investigate NMPC through the lens of Bayesian estimation and highlight that the Monte Carlo sampling method can offer a favorable way to implement NMPC. We develop a constraint-aware particle filtering/smoothing method and exploit it to implement NMPC. The new sampling-based NMPC algorithm can be executed easily and efficiently even for complex nonlinear systems, while potentially mitigating the issues of computational complexity and local minima faced by numerical optimization in conventional studies. The effectiveness of the proposed algorithm is evaluated through a simulation study.

关键词： Monte Carlo methods filtering Estimation Optimal control filtering algorithms Prediction algorithms Bayes methods

来源：评论

学校读者我要写书评

暂无评论

AI-aided Hidden Camera Detection and Localization based on Raw IoT Network Traffic 47

AI-aided Hidden Camera Detection and Localization based on R...

引用

47th IEEE Conference on Local Computer Networks (LCN)

作者： Lee, Jihyeon Seo, Sangwon Yang, Taehun Park, Soochang Korea Adv Inst Sci & Technol Culture Technol Daejoen South Korea Korea Univ Elect Engn Seoul South Korea Chungnam Natl Univ Comp Engn Daejeon South Korea Chungbuk Natl Univ Comp Engn Cheongju South Korea

ISBN: (数字)9781665480017

ISBN: (纸本)9781665480017

This paper proposes a novel scheme to detect and localize the spy cameras based on AI algorithm based raw traffic analytics, named AI-aided Hidden Camera Locator (AHCL). In AHCL, the video streaming data are filtered via the SVM (support vector machine) algorithm to quickly monitor whole raw network traffic from a router to the networks first. Then, gathered traffic data are denoised by the Denoising Autoencoder (DAE) technique to improve the data quality of classification for localization, where a camera transmits video streaming. Based on the proof-of-concept implementation, the proposed scheme can achieve 99.5% positioning accuracy of camera detection with the Ensemble Neural Networks (NNs).

关键词： Support vector machines Location awareness Data integrity Noise reduction Telecommunication traffic Streaming media filtering algorithms

来源：评论

学校读者我要写书评

暂无评论

An Improved Deep Learning Unsupervised Approach for MRI Tissue Segmentation for Alzheimer's Disease Detection

引用

IEEE ACCESS 2024年 12卷 188114-188121页

作者： Kumar, Karan Suwalka, Isha Uche-Ezennia, Adaora Iwendi, Celestine Biamba, Cresantus N. Maharishi Markandeshwar Maharishi Markandeshwar Engn Coll Elect & Commun Engn Dept Ambala 1332070 India Indira IVF Hosp Private Ltd Udaipur 313007 Rajasthan India Univ Bolton Bolton BL3 5AB England Univ Bolton Sch Creat Technol Bolton BL3 5AB England Univ Gavle Dept Educ Sci S-80176 Gavle Sweden

Alzheimer's disease (AD) ranks as the sixth leading cause of death, emphasizing the need for early-stage prediction to prevent its progression. Due to the complexity and heterogeneity of medical tests, manually comparing, visualizing, and analyzing data is often difficult and time-consuming. As a result, a computational approach for accurately predicting brain changes through the classification of magnetic resonance imaging (MRI) scans becomes highly valuable, though challenging. This paper introduces a novel method for diagnosing the early stages of AD by utilizing an efficient mapping technique to differentiate between affected and normal MRI scans. The approach combines a hybrid unsupervised learning framework, specifically the adaptive moving self-organizing map (AMSOM) method integrated with Fuzzy K-means. To ensure optimal feature extraction, we introduce a hybrid learning framework that embeds feature vectors in a subspace. The analysis compares various mapping approaches to identify features linked to Alzheimer's disease. The proposed method achieves a classification accuracy of 95.75% on the Open Access Series of Imaging Studies (OASIS) MRI brain image database, outperforming existing methods.

关键词： Magnetic resonance imaging Feature extraction Convolutional neural networks Noise Diseases Deep learning filtering algorithms Alzheimer's disease Image segmentation Accuracy Adaptive moving mapping Alzheimer's disease clustering feature extraction OASIS

来源：评论

学校读者我要写书评

暂无评论

WMSNs Data Hidden Anomaly Detection Based on OH-KFJLT Bloom Filter

引用

IEEE ACCESS 2024年 12卷 174519-174526页

作者： Xiao, Chenkai Li, Zhongsheng Wu, Yanming Minxi Vocat & Tech Coll Informat Engn Dept Longyan 364021 Peoples R China Tsinghua Univ Sch Environm Beijing 100084 Peoples R China Zijin Intelligent Automat Xiamen Technol Co Ltd Xiamen 361026 Peoples R China

With the rapid development of the Industrial Internet of Things (IIoT), the volume and size of data handled by Wireless Multimedia Sensor Networks(WMSNs) have increased dramatically. Sensors suffer from damage due to continuous high-load usage and wear, leading to anomalies in sensor data collected and recorded. To solve the problem, this paper proposes an anomaly detection algorithm that is based on the Bloom Filter model, combined with the Optimal Hyperplane-based Kronecker Fast Johnson-Lindenstrauss Transform (OH-KFJLT) mapping and Reciprocal Competition Strategy(RCS), called Optimal Hyperplane Kronecker Fast Johnson-Lindenstrauss Transform Bloom Filter Anomaly Detection(OFBFAD). Firstly, the data is hashed by using the OH-KFJLT mapping method based on optimal hyperplane. Then, the RCS is adopted to de-noise the data. Finally, the Bloom Filter is constructed by 0-1 coding. In the simulation experiments conducted on the NAB, SMD, and COCO benchmark datasets, the False Alarm Rate (FAR) of the OFBFAD algorithm is all lower than 5%. The experimental results show that the OFBFAD has a higher Detection Rate (DR) and lower FAR than the current mainstream anomaly detection algorithm, and can be effectively applied to the anomaly detection of WMSNs data.

关键词： Anomaly detection filtering algorithms Feature extraction Classification algorithms Codes Encoding Industrial Internet of Things Sparse matrices Atmospheric modeling Wireless sensor networks Industrial Internet of Things (IIoT) wireless multimedia sensor networks (WMSNs) anomaly detection optimal hyperplane-based Kronecker Fast Johnson-Lindenstrauss transform (OH-KFJLT) reciprocal competition strategy(RCS)

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：