检索结果-内蒙古大学图书馆

TSAGen: Synthetic Time Series Generation for KPI Anomaly detection

IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT 2022年第1期19卷 130-145页

作者： Wang, Chengyu Wu, Kui Zhou, Tongqing Yu, Guang Cai, Zhiping Natl Univ Def Technol Coll Comp Changsha 410073 Peoples R China Univ Victoria Dept Comp Sci Victoria BC V8P 5C2 Canada

A key performance indicator (KPI) consists of critical time series data that reflect the runtime states of network systems (e.g., response time and available bandwidth). Despite the importance of KPI, datasets for KPI anomaly detection available to the public are very limited, due to privacy concerns and the high overhead in manually labelling the data. The insufficiency of public KPI data poses a great barrier for network researchers and practitioners to evaluate and test what-if scenarios in the development of artificial intelligence for IT operations (AIOps) and anomaly detection algorithms. To tackle the difficulty, we develop a univariate time series generation tool called TSAGen, which can generate KPI data with anomalies and controllable characteristics for KPI anomaly detection. Experiment results show that the data generated by TSAGen can be used for comprehensive evaluation of anomaly detection algorithms with diverse user-defined what-if scenarios.

关键词： Key performance indicator Time series analysis Anomaly detection Detectors Tools detection algorithms Monitoring Time series generation time series anomaly detection fault injection AIOps

来源：评论

学校读者我要写书评

暂无评论

Predictive Braking With Brake Light detection-Field Test

引用

IEEE ACCESS 2022年 10卷 49771-49780页

作者： Pirhonen, Jesse Ojala, Risto Kivekas, Klaus Tammi, Kari Aalto Univ Dept Mech Engn Espoo 02150 Finland Univ Helsinki Fac Agr & Forestry Helsinki 00014 Finland

Driver assistance systems, such as adaptive cruise control, are an increasing commodity in modern vehicles. Our earlier experience of radar-based adaptive cruise control has indicated repeatable abrupt behavior when approaching a stopped vehicle at high speed, which is typical for extra-urban roads. Abrupt behavior in assisted driving not only decreases the passenger trust but also reduces the comfort levels of such systems. We present a design and proof-of-concept of a machine vision-enhanced adaptive cruise controller. A machine vision-based brake light detection system was implemented and tested in order to smoothen the transition from coasting to braking and ensure speed reduction early enough. The machine vision system detects the brake lights in front, then transmits a command to the cruise controller to reduce speed. The current paper reports the speed control system design and experiments carried out to validate the system. The experiments showed the system works as designed by reducing abrupt behavior. Measurements show that brake light-assisted cruise control was able to start deceleration about three seconds earlier than a cruise controller without brake light detection. Measurements also showed increased ride comfort with the maximum deceleration and minimum jerk levels improving from 5% to 31%.

关键词： Brakes Control systems Safety Cruise control Radar detection algorithms Cameras Advanced driver assistance systems automotive applications intelligent vehicles machine vision

来源：评论

学校读者我要写书评

暂无评论

Ex(o)plain: Subgroup-Level Analysis of Exoplanet Atmospheric Parameters

引用

IEEE ACCESS 2024年 12卷 139773-139788页

作者： Koudounas, Alkis Giobergia, Flavio Baralis, Elena Politecn Torino Dept Control & Comp Engn I-10129 Turin Italy

Deep learning has been shown to be a valuable tool in astrophysics. In the field of exoplanetary science, deep learning-based approaches are being used extensively to automate the characterization of exoplanet atmospheres, reducing computational costs when compared to conventional methods. However, many atmospheric reconstruction models lack interpretability. We introduce Ex(o)plain, a model-agnostic framework to identify and describe the most meaningful traits that characterize exoplanet atmospheres. Our approach categorizes exoplanets into subgroups based on combinations of various metadata, such as surface gravity, planet radius, and star temperature. We analyze these subgroups to identify those for which the deep learning model performs better or worse than average. This provides useful insights into what is being effectively learned by these black box models and where they still struggle. We explore a practical case based on the synthetic observations generated for the upcoming Ariel mission. Experimental results demonstrate the effectiveness of adopting explanation techniques in revealing meaningful variations in reconstruction quality between individual models and their aggregated ensemble. We additionally show that ensemble approaches significantly outperform single learners. We leverage the same subgroup-based exploration techniques to assess the situations that are most beneficial for the ensemble. Our work provides a more nuanced understanding of deep learning results for exoplanet characterization, aiming to delineate feasible accuracy limits and enable more informed evaluations of these techniques' atmospheric reconstruction capabilities.

关键词： Atmospheric modeling Exoplanet Atmospheric measurements Computational modeling Atmospheric waves Metadata Deep learning Explainable AI detection algorithms divergence exoplanet atmospheric parameters explainable AI subgroup detection

来源：评论

学校读者我要写书评

暂无评论

On Lattice Network Coding Based Cell-Free MIMO With Uncoordinated Base Stations

引用

IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS 2024年第8期23卷 9672-9686页

作者： Yang, Tao Beihang Univ Beijing 100191 Peoples R China Beihang Univ Shenzhen Inst Shenzhen Guangdong Peoples R China

This paper studies a cell-free MIMO (cf-MIMO)system that consists of a central unit (CU),N distributed base stations (BSs) and K users. The BSs are connected to CU via N independent backh aul (BH) links of finite capacities. The BSs are uncoordinated, i.e. each one is ignorant of the others. We studya lattice network coding (LNC) scheme for cf-MIMO. In the u plink, the K users encode their messages with a practica l2(m)-ary channel code mapped to 2(m)-PAM, belonging to the ensemble of lattice codes, and transmit simultaneously. Each BScomputes independent streams of integer-combinations of theusers' messages, referred to as network coding(NC) *** NC streams are forwarded to the CU via BH. The CU aggregates all NC streams from theNBSs, and recovers Kusers' messages. We derive the achievable symmetric rate of the LNC scheme. Further, we solve a "bounded independent vectors problem" (BIVP) which identifies a near-optimal setof NC coefficient vectors. The solution maximizes the numberof correctly computed NC streams at each BS. For practical implementation, we develop new soft detection algorithms for LNC decoding. The per-user complexity is proved to be no greater than O(K), suitable for cf-MIMO with a large number of *** developed LNC based cf-MIMO exhibits superior frame error rate (FER) and spectral efficiency over existing non-LNC based schemes. Such advances are achieved with low-cost parallel processing and efficient usage of the BH.

关键词： Lattices Streams Backhaul networks Network coding MIMO communication Uplink detection algorithms Cell-free distributed MIMO multi-user MIMO massive access coded modulation lattice-codes compute-forward physical-layer network coding soft detection NOMA

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Feature Selection and Ensemble Stacked Learning Models on Multi-Variant CVD Datasets for Effective Classification

引用

IEEE ACCESS 2024年 12卷 87023-87038页

作者： Mahajan, Abhigya Kaushik, Baijnath Rahmani, Mohammad Khalid Imam Banga, Abdulbasid S. Shri Mata Vaishno Devi Univ Sch Comp Sci & Engn Katra 182320 Jammu And Kashm India Saudi Elect Univ Coll Comp & Informat Riyadh 11673 Saudi Arabia

Predicting cardiac or heart disease has emerged as a formidable challenge in the medical domain recently. It is recognized as a major global health concern, and stands as one of the primary causes of mortality, posing a significant threat to human life. Early detection of heart disease helps to reduce mortality. This study has experimented with three benchmark datasets such as UCI Heart Disease, Framingham, and Z-Alizadeh Saini containing important clinical information for cardiac vascular disease (CVD). These three datasets' multi-variant (categorical and continuous) features, variable dimensions, and multicollinearity characteristics provide substantial challenges for machine learning (ML) and other models aiming to achieve the desired results. This study proposes a statistical feature selection (SFS) stacking framework using four feature engineering techniques, Chi-Square, Gini Index, Information Gain, and ANOVA F-test, to select the optimal features from the datasets. Further, the likelihood of developing CVD based on characteristics extracted from the three benchmark datasets using a reduced set of optimized features from the initial feature set is fed to ensemble stacked learning models: stacking using Support Vector Machine (SFS-SVM) and stacking using Cross-Validation Classifier (SFS-SCVC). The SFS-SCVC model has achieved significant performance metrics and outperformed the SFS-SVM and traditional ML models on all three datasets.

关键词： Diseases Accuracy Heart Stacking Feature extraction Predictive models Prediction algorithms Cardiology detection algorithms Multi-variant CVD datasets gini index chi-square ANOVA F-test stacking SVM stacking cross-validation

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Approach for Fixed and Rotary-Wing Target detection and Classification in Radars

引用

IEEE AEROSPACE AND ELECTRONIC SYSTEMS MAGAZINE 2022年第3期37卷 32-42页

作者： Rizvi, S. M. Danish Ahmad, Shahzor Khan, Khurram Hasan, Azhar Masood, Ammar Imperial Coll London Sch Design Engn London SW7 2BX England Natl Univ Sci & Technol Dept Elect Engn Coll Elect & Mech Engn Islamabad Pakistan Air Univ Dept Av Engn Islamabad 44000 Pakistan Natl Univ Sci & Technol Coll Aeronaut Engn Dept Av Engn Islamabad Pakistan

Recent advancements demonstrate the application of machine learning techniques to radar signal processing, particularly the use of neural networks in one-dimensional (1-D) radar data to assist constant false alarm rate (CFAR) based target detection. However, the efficacy of using neural networks alone on 2-D data for target extraction remains to be explored. This research aims to develop a novel approach of designing a convolution neural network (CNN) based target detection system for real radar data. We propose a dual neural network detection scheme in which the first neural net filters out noisy images. Thereafter, we employ a second CNN-based target detector that extracts information from both radar data axes (fast-time and slow-time), thus utilizing additional information for better detection of targets even with low SNR. Moreover, the same CNN, in conjunction with a region-based convolutional network, exploits micro-Doppler features of rotary-wing aircraft in radar returns and uses them to further classify detected targets as fixed-wing or rotary-wing aircraft. To the best of our knowledge, no generalized methodology exists to address these two issues together. The proposed solution replaces the critical CFAR and peak detection algorithms from the radar signal processing chain. This article also introduces a labeled range-Doppler images dataset obtained from real-world air traffic control radar data. Experimental results demonstrate the superior performance of the proposed technique over 1-D and 2-D CFAR and peak detection algorithms.

关键词： Deep learning Radar detection Radar imaging Object detection Doppler radar Convolutional neural networks Doppler effect Neural networks Radar signal processing detection algorithms

来源：评论

学校读者我要写书评

暂无评论

Continuous Seizure detection Based on Transformer and Long-Term iEEG

引用

IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS 2022年第11期26卷 5418-5427页

作者： Sun, Yulin Jin, Weipeng Si, Xiaopeng Zhang, Xingjian Cao, Jiale Wang, Le Yin, Shaoya Ming, Dong Tianjin Univ Acad Med Engn & Translat Med Tianjin 300072 Peoples R China Tianjin Univ Tianjin Key Lab Brain Sci & Neural Engn Tianjin 300072 Peoples R China Tianjin Univ Sch Elect & Informat Engn Tianjin 300072 Peoples R China Tianjin Univ Huanhu Hosp Dept Neurol Tianjin 300072 Peoples R China

Automatic seizure detection algorithms are necessary for patients with refractory epilepsy. Many excellent algorithms have achieved good results in seizure detection. Still, most of them are based on discontinuous intracranial electroencephalogram (iEEG) and ignore the impact of different channels on detection. This study aimed to evaluate the proposed algorithm using continuous, long-term iEEG to show its applicability in clinical routine. In this study, we introduced the ability of the transformer network to calculate the attention between the channels of input signals into seizure detection. We proposed an end-to-end model that included convolution and transformer layers. The model did not need feature engineering or format transformation of the original multi-channel time series. Through evaluation on two datasets, we demonstrated experimentally that the transformer layer could improve the performance of the seizure detection algorithm. For the SWEC-ETHZ iEEG dataset, we achieved 97.5% event-based sensitivity, 0.06/h FDR, and 13.7 s latency. For the TJU-HH iEEG dataset, we achieved 98.1% event-based sensitivity, 0.22/h FDR, and 9.9 s latency. In addition, statistics showed that the model allocated more attention to the channels close to the seizure onset zone within 20 s after the seizure onset, which improved the explainability of the model. This paper provides a new method to improve the performance and explainability of automatic seizure detection.

关键词： Electroencephalography Feature extraction Transformers Recording Brain modeling detection algorithms Sensitivity Seizure detection iEEG transformer self-attention deep learning epilepsy

来源：评论

学校读者我要写书评

暂无评论

A Snowfall detection Algorithm for ATMS Over Ocean, Sea Ice, and Coast

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2022年 15卷 1411-1420页

作者： You, Yalei Meng, Huan Dong, Jun Fan, Yongzhen Ferraro, Ralph R. Gu, Guojun Wang, Likun Univ Maryland Cooperat Inst Satellite Faith Syst Studies CISESS Earth Syst Sci Interdisciplinary Ctr ESSIC College Pk MD 20740 USA NOAA NESDIS STAR College Pk MD 20740 USA Univ Maryland Earth Syst Sci Interdisciplinary Ctr ESSIC College Pk MD 20740 USA

This study developed a snowfall detection algorithm over ocean, sea ice, and coast for the advanced technology microwave sounder (ATMS) onboard both NPP and NOAA-20 satellites. The detection algorithm was trained from collocated observations between ATMS-NPP and CloudSat cloud profiling radar (CPR) snowfall product. Both brightness temperature (TB) variables and global forecast system (GFS) output variables are evaluated for snowfall detection in this algorithm. Results show that combining TB variables and GFS variables provide the optimal snowfall detection performance. The Heidke skill score (HSS) values are about 0.56 over all three surface types, and the probability of detection (POD) values are 0.76, 0.70, and 0.72 over ocean, sea ice, and coast, respectively. The importance of the GFS variables differs greatly among these three surface types. The detection algorithm primarily depends on TB variables over ocean and HSS only increased by 0.05 by adding GFS variables. In contrast, GFS variables are critically important to snowfall detection over sea ice and coastal regions. Without GFS variables, the HSS values over both sea ice and coastal regions decrease sharply from about 0.56 to about 0.40. Over ocean, we also developed a regional snowfall detection model in each 10 degrees grid box, which greatly outperform the global detection model over certain regions (e.g., sea of Okhotsk and Labrador Sea). Case studies and validation against NOAA-20 observations showed that the snowfall detection algorithm performs well, which will benefit coastal communities by providing information on snowstorms offshore before they transition to land.

关键词： Ocean temperature Oceans Sea surface Microwave radiometry Microwave integrated circuits Microwave FET integrated circuits detection algorithms Microwave radiometry satellite applications snow

来源：评论

学校读者我要写书评

暂无评论

A Multifeature-Assisted Road and Vehicle detection Method Based on Monocular Depth Estimation and Refined U-V Disparity Mapping

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2022年第9期23卷 16763-16772页

作者： Ma, Weixuan Zhu, Sa Hubei Univ Sch Comp Sci & Informat Engn Wuhan 430062 Peoples R China Wuhan Univ Sch Remote Sensing & Informat Engn Wuhan 430061 Peoples R China

Usually, the detection process of traffic objects, such as vehicles, finds the visual input lacks the necessary depth information, so it is difficult to directly and quickly obtain the results. Typically, to separate the objects from the complex background, it is necessary to utilize a complex model or prior knowledge, which can be computationally expensive or simply infeasible. To battle this issue, depth visual information is used in this paper to accurately segment roads and vehicles, so it doesn't need to use complex models to detect objects in the visual input. First, an unsupervised deep learning-based monocular depth estimation method is used to obtain the stereo disparity map. Then a non-parametric, refined U-V disparity mapping method is used to obtain the road region of interest. Next, this paper uses the road parallel scanning to determine the source and vanishing points and uses the adjacent disparity similarity algorithm to complement and extract the target region to detect roads and vehicles. This algorithm uses multi-feature fusion such as height-width ratio, perspective ratio, and area ratio to accurately segment the target region, and the effectiveness of the proposed method is tested on a public dataset. The experimental results show that the proposed model can accurately and efficiently detect roads and vehicles in a variety of scenarios.

关键词： Roads Estimation Vehicle detection Feature extraction Cameras detection algorithms Computational modeling Deep learning U-V disparity mapping depth estimation road and vehicle detection

来源：评论

学校读者我要写书评

暂无评论

Rapid Adaptive Matched Filter for Detecting Radar Targets With Unknown Velocity

引用

IEEE ACCESS 2024年 12卷 25411-25428页

作者： Kononov, Anatolii A. Ka, Min-Ho Yonsei Univ Sch Integrated Technol Seoul 21983 South Korea

This paper introduces a Doppler domain localized (DDL) implementation of the adaptive matched filter (AMF) for radar target detection in severely heterogeneous clutter environments with limited training data. The proposed detector uses the concept of a region of possible target detection (RPTD), a small set of Doppler bins that captures most of the target signal power. This RPTD-based DDL-AMF detector outperforms an earlier suggested DDL implementation of the generalized likelihood ratio (GLR) test, which employs the region of detection improvement (RODI) concept. Unlike the RODI-based DDL-GLR detector, the proposed DDL-AMF detector requires no information on clutter spectrum parameters and no measurements to determine the number and locations of RODIs. Moreover, the RODI-based DDL-GLR detector's performance falls far below the optimum when the target Doppler frequency is unknown. In contrast, the RPTD-based DDL-AMF detector ensures rapid adaptive detection with near-optimum performance under unknown target Doppler frequency and multimodal clutter spectra.

关键词： Doppler effect Detectors Clutter Training Time-domain analysis Object detection Discrete Fourier transforms Adaptive control detection algorithms Matched filters Alarm systems Heterogeneous networks Adaptive detection adaptive matched filter (AMF) constant false alarm rate (CFAR) Doppler domain localized (DDL) adaptivity generalized likelihood ratio (GLR) heterogeneous clutter

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：