检索结果-内蒙古大学图书馆

Detecting the Auroral Oval through CSES-01 Electric Field Measurements in the Ionosphere

REMOTE SENSING 2023年第6期15卷 1568-1568页

作者： Papini, Emanuele Piersanti, Mirko D'Angelo, Giulia Cicone, Antonio Bertello, Igor Parmentier, Alexandra Diego, Piero Ubertini, Pietro Consolini, Giuseppe Zhima, Zeren INAF Ist Astrofis & Planetol Spaziali Via Fosso del Cavaliere I-00133 Rome Italy Univ Aquila Dipartimento Sci Fis & Chim Via Vetoio I-67100 Laquila Italy Univ Aquila Dipartimento Ingn & Sci Informaz & Matemat Via Vetoio I-67100 Laquila Italy Ist Nazl Fis Nucl Sez Roma Tor Vergata Via Ric Scientif I-00133 Rome Italy Minist Emergency Management China Natl Inst Nat Hazards Beijing 100085 Peoples R China

We present the results of a systematic study of the ionospheric electric field in the Auroral Oval (AO) region in the southern hemisphere. We exploit one year of electric field measurements taken by the Electric Field Detector (EFD) on board the Chinese Seismo-Electromagnetic Satellite-01 (CSES-01), flying at around 500 km altitude in a sun-synchronous orbit. We exploit the high temporal resolution of the EFD to devise a new technique for the detection of CSES-01 crossing of the AO using electric field measurements only. This new technique combines a Median-Weighted Local Variance Measure with Fast Iterative Filtering to automatically isolate high levels of electromagnetic activity caused by, e.g., particle precipitation and Field Aligned Currents (FACs) at auroral latitudes. We validate this new method against other standard proxies, such as the single-FAC product from the Swarm mission and the auroral radiance emission measured by the Special Sensor Ultraviolet Spectrographic Imager (SSUSI) units on board the Defense Meteorological Satellite Program (DMSP) constellation. Furthermore, we identify similar to 3000 orbits (out of a dataset of similar to 10,000) where CSES-01 crosses the AO boundary under conditions of high geomagnetic activity. This dataset represents the first step in the systematic study of the auroral electric field, with many potential applications to space weather, thanks to the large amount of continuous observations of the ionosphere by CSES-01 and the forthcoming CSES-02 mission.

关键词： auroral ionosphere electric field ionosphere-magnetosphere coupling detection algorithms

来源：评论

学校读者我要写书评

暂无评论

Targeted Manifold Manipulation Against Adversarial Attacks

Targeted Manifold Manipulation Against Adversarial Attacks

引用

Secure and Trustworthy Machine Learning (SaTML), IEEE Conference on

作者： Banibrata Ghosh Haripriya Harikumar Svetha Venkatesh Santu Rana Applied Artificial Intelligence Institute Deakin University Waurn Ponds Australia Department of Computer Science University of Manchester Manchester United Kingdom

ISBN: (数字)9798331517113

ISBN: (纸本)9798331517120

Adversarial attacks on deep models are often guaranteed to find a small and innocuous perturbation to easily alter the class label of a test input. We use a novel Targeted Manifold Manipulation (TMM) approach to direct the gradients from the genuine data manifold toward carefully planted traps during such adversarial attacks. The traps are assigned an additional class label (Trapclass) to make the attacks falling in them easily identifiable. Whilst low-perturbation budget attacks will necessarily end up in the traps, high-perturbation budget attacks may escape but only end up far away from the data manifold. Since our manifold manipulation is enforced only locally, we show that such out-of-distribution data can be easily detected by noting the absence of traps around them. Our detection algorithm, denoted as TMM-Def avoids learning a separate model for attack detection and thus remains semantically aligned with the original classifier. Further, since we manipulate the adversarial distribution, it avoids the fundamental difficulty associated with overlapping distributions of clean and attack samples for usual, unmanipulated models. We use nine state-of-the-art adversarial attacks with six well-known image datasets to evaluate our proposed defense. Our results show that the proposed method can detect ~99% attacks whilst also being robust to semantic-preserving, transformations, and adaptive attacks.

关键词： Manifolds Deep learning Adaptation models Perturbation methods Detectors detection algorithms Resilience

来源：评论

学校读者我要写书评

暂无评论

Embedded real-time feature extraction for electrode inversion detection in telemedicine electrocardiograms

引用

BIOMEDICAL SIGNAL PROCESSING AND CONTROL 2020年第0期60卷 101946-101946页

作者： Torres, V. A. M. F. Silva, D. A. C. Torres, L. C. B. Braga, M. T. Cardoso, M. B. R. Lino, V. T. Torres, F. Sill Braga, A. P. Univ Fed Minas Gerais Grad Program Elect Engn Belo Horizonte MG Brazil Inst Protect Maritime Infrastruct German Aerosp Ctr Cologne Germany Univ Fed Ouro Preto Dept Comp & Syst Ouro Preto Brazil

Early detection of technical errors in medical examinations, especially in remote locations, is of utmost importance in order to avoid invalid measurements that would require costly and time consuming repetitions. This paper proposes a highly efficient method for the identification of an erroneous inversion of the measuring electrodes during a multichannel electrocardiogram. Therefore, a widely applied approach for heart beat detection is modified and approximated feature extraction techniques are employed. In contrast to existing works, the improved heart beat identification requires no removal of baseline wandering and no amplitude related thresholds. Furthermore, a piecewise linear approximation of the baseline and basic calculations are sufficient for extracting the cardiac axis, which allows the construction of a classifier capable of quickly detecting electrode reversals. Our implementation indicates that the proposed method has minimal hardware costs and is able to operate in real-time on a simple micro-controller. (C) 2020 Elsevier Ltd. All rights reserved.

关键词： Telemedicine Electrocardiography detection algorithms Electrodes inversion

来源：评论

学校读者我要写书评

暂无评论

SCONet: Convolutional Occupancy Networks for Multi-Organ Segmentation

SCONet: Convolutional Occupancy Networks for Multi-Organ Seg...

引用

IEEE International Symposium on Biomedical Imaging

作者： Maylis Jouvencel Razmig Kéchichian Julie Digne Sébastien Valette INSA-Lyon UCBL CNRS Inserm CREATIS UMR 5220 U1294 Lyon France Univ Lyon INSA-Lyon CNRS UCBL Centrale Lyon Univ Lyon 2 LIRIS UMR 5205 Lyon France

ISBN: (数字)9798331520526

ISBN: (纸本)9798331520533

Convolutional neural networks are the de facto standard for 3D multi-organ segmentation but still exhibit significant limitations, especially regarding their computational cost, with high running time and often prohibitive memory footprint for large 3D volumes. To overcome these limitations, we propose to replace the image voxel grid with a more compact point cloud representation. Recently, in the field of 3D object reconstruction, networks learning implicit functions from an input point cloud, such as Convolutional Occupancy Networks (ConvONet), have proven their good surface representation capabilities. We therefore propose SCONet (Segmentation Convolutional Occupancy Network), a lightweight ConvONet-based network adapted to the specific task of multi-organ segmentation. SCONet takes as input a point cloud extracted from the original volume with a standard contour detection algorithm, and enriches it with geometric and photometric features. Thanks to its ability to query per organ occupancy probabilities for any point in space, SCONet can be used to predict a multi-organ segmentation map at arbitrary resolution. We evaluate our method on an abdominal CT image dataset and compare its performances with those of discrete and implicit baselines. Our implementation is available at https://***/maylis-j/SCONet.

关键词： Point cloud compression Image segmentation Surface reconstruction Three-dimensional displays Image resolution Feature extraction Convolutional neural networks detection algorithms Standards Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Fog Vision for Roads and Rails

Fog Vision for Roads and Rails

引用

IEEE Students' Conference on Electrical, Electronics and Computer Science (SCEECS)

作者： Surat Pyari Atti Pranitha A Prakash Raj M Department of Electrical and Electronics Engineering New Horizon College of Engineering Bengaluru India

ISBN: (数字)9798331529833

ISBN: (纸本)9798331529840

Reduced visibility due to fog creates hazardous conditions in sectors like transportation, aviation, and outdoor navigation. This research introduces a dual-purpose monitoring system that combines fog detection with real-time object recognition, designed using a Raspberry Pi 3 Model B+ paired with an OV5647 5MP IR cut camera sensor and QuickDetect, a real-time object detection module utilizing Python and the Ultralytics YOLO v8 model [1] [2]. Our system processes video frames to assess fog presence through contrast and blurriness indicators via OpenCV while simultaneously detecting objects with YOLO v8, enabling a comprehensive environmental assessment. The unified design of fog detection and object recognition on a single, affordable platform allows the system to evaluate visibility and detect relevant obstacles, enhancing situational awareness. Preliminary testing has indicated promising results, with efficient detection of fog and accurate identification of objects. This project contributes a practical and accessible solution for safety improvements in low-visibility environments, with potential applications in smart transportation, environmental monitoring, and autonomous navigation.

关键词： YOLO Accuracy Navigation Streaming media Cameras Real-time systems Object recognition Environmental monitoring detection algorithms Testing

来源：评论

学校读者我要写书评

暂无评论

Time-Delay-Estimation-Liked detection Algorithm for LoRa Signals Over Multipath Channels

引用

IEEE WIRELESS COMMUNICATIONS LETTERS 2020年第7期9卷 1093-1096页

作者： Guo, Yurong Liu, Zujun Xidian Univ State Key Lab Integrated Serv Networks Xian 710071 Peoples R China

LoRa promises long range reliable communication for the Internet of Things (IoT). However, multipath fading severely affects LoRa's BER performance. In this letter, we propose a simple detection algorithm for the frame-based LoRa PHY signals mainly composed of a preamble and a variable-length PHY-payload. We first prove that detecting the frame-based LoRa signals over multipath fading channels can be formulated as a Time-delay-estimation (TDE)-liked problem. Based on this, a cyclic cross-correlation implemented by a matched filter is utilized to detect the LoRa signals. Additionally, the proposed TDE-liked detection algorithm is insensitive to the integer frequency offset due to the nature of implying a differential operation. The simulation results indicate that, the proposed algorithm significantly outperforms the existing detection algorithms for the LoRa signals over multipath fading channels. Under the multipath fading channel, the BER performance of the proposed algorithm is slightly inferior to that in the AWGN channel while the existing scheme fails to work.

关键词： Discrete Fourier transforms Fading channels detection algorithms Frequency-domain analysis Correlation Chirp Cascading style sheets LoRa Internet of Things (IoT) cross-correlation multipath channels

来源：评论

学校读者我要写书评

暂无评论

Multiple Line-Outage detection in Power System With Load Stochastic Perturbations

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS 2020年第10期67卷 1994-1998页

作者： Nie, Shihao Ding, Li Li, Wenqu Wuhan Univ Sch Elect Engn & Automat Wuhan 430072 Peoples R China

In this brief, we consider multiple line-outage detection problem based on dynamic model of the power system subjects to load stochastic perturbations. A novel detection algorithm is proposed using data obtained from phase measurement units (PMUs). In order to reduce the computation burden, the algorithm is further improved by means of introducing the original topology of power system. Moreover, we propose a predictive algorithm to solve the sampling interval problem of data acquisition. Finally, simulation results are given to demonstrate the applicability of the proposed algorithm.

关键词： Power system dynamics detection algorithms Phasor measurement units Generators Observers Perturbation methods Load modeling Power system multiple line-outage detection load stochastic perturbations

来源：评论

学校读者我要写书评

暂无评论

Seizures Prediction using Heart Rate Variability in ECG Signal

Seizures Prediction using Heart Rate Variability in ECG Sign...

引用

Intelligent Systems (ETIS), Emerging Technologies for

作者： Aman A Senthil Murugan Rajeshkannan Megalingam Department of Electronics and Communication Engineering Amrita Vishwa Vidyapeetham Amritapuri India

ISBN: (数字)9798331507541

ISBN: (纸本)9798331507558

An exploratory study was suggested to assess the efficacy of an automatic model, and this model helps to identify heart rate (HR) changes in individuals with severe epilepsy during seizures. Heart rate (HR) is one of the automatic body functions that can alter as a result of epileptic seizures. Mainly, the method proposed in the study was used to check disruptions in the heart signal, called movement artifacts, on the ECG. These disruptions in the heart signal make it harder to detect R-peaks, which are the main spikes in the ECG, and can also reduce the accuracy of seizure detection algorithms as well. Importantly, the Artefacts detection Algorithm introduced a new feature, which uses Principal Component Analysis (PCA) to analyze electrocardiogram (ECG) signals and can be used to describe the changes within ECG data as well. The new feature is highly focused to detect seizures by analyzing changes in the morphological characteristics (shape and structure) of the electrocardiogram signal, especially those in the QRS complex, which can indicate seizure activity. One type of machine learning model used to distinguish between normal and abnormal ECG signals is the Support Vector Machine (SVM). The clustering algorithm ‘K-means’ is used to identify seizures. The normal and abnormal signals can be easily differentiated by the system. SVM, along with k-means algorithms are used to detect seizures in a more accurate manner.

关键词： Support vector machines Machine learning algorithms Accuracy Clustering algorithms Electrocardiography Prediction algorithms Feature extraction detection algorithms Unsupervised learning Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

algorithms of Reliability Data Processing for Navigation Systems

Algorithms of Reliability Data Processing for Navigation Sys...

引用

Integrated Communications, Navigation and Surveillance Conference, ICNS

作者： Maksym Zaliskyi Ivan Ostroumov Nataliia Kuzmenko Viktoriia Ivannikova Department of Telecommunication and Radioelectronic Systems SU “Kyiv Aviation Institute” Kyiv Ukraine Department of Air Navigation Systems SU “Kyiv Aviation Institute” Kyiv Ukraine Scientific and Research Group SU “Kyiv Aviation Institute” Kyiv Ukraine Dublin City University Business School Dublin City University Dublin Ireland

ISBN: (数字)9798331534738

ISBN: (纸本)9798331534745

Navigation systems in civil aviation are used to ensure the safety and regularity of aircraft flights. In general, navigation equipment can be a source of various types of data, including coordinates of aircraft, results of monitoring for internal system parameters, reliability, and efficiency indicators. The operating environment including weather conditions, instability of power sources, the influence of the human factor, and others, lead to random and gradual changes in the technical condition of the equipment. These changes can lead to failures and malfunctions occurrence in the different units of equipment, a decrease in the remaining useful life of the navigation system, and an increase in operational costs for implementation of unplanned maintenance and repair procedures. This paper concentrates on the synthesis and analysis of new data processing procedures regarding the operation of navigation systems in the case of possible changes in their technical condition. The processing algorithms include two stages: a) determination of the technical condition of the equipment and b) evaluation of reliability indicators. The proposed procedures of data processing are based on the methods of classification and estimation of mathematical statistics. The paper gives recommendations for improving strategies for the predictive maintenance of navigation systems in terms of determining the preventive threshold. It is also theoretically proven that the proposed recommendations can significantly reduce the operational costs of the aviation enterprise. The results of the research can be used during the improvement of algorithmic support systems for maintenance and repair processes in terms of making management decisions when determining the technical condition of equipment. In general, the proposed data processing algorithms allow for solving two main tasks during operation: providing a given level of reliability and reducing operational costs.

关键词： Costs Prediction algorithms Data processing Aircraft navigation Maintenance Classification algorithms Reliability detection algorithms Aircraft Predictive maintenance

来源：评论

学校读者我要写书评

暂无评论

Detecting Routing Attacks in WSN: A Novel Cartesian Product-Based Method

Detecting Routing Attacks in WSN: A Novel Cartesian Product-...

引用

ICT Conference (AICTC), Arab

作者： Saad Salman Ahmed Zainab Alansari Mohammad Riyaz Belgaum College of Computing and Information Sciences University of Technology and Applied Sciences Muscat Sultanate of Oman G. Pullaiah College of Engineering and Technology Kurnool India Faculty of Computing and Informatics Multimedia University Cyberjaya Malaysia

ISBN: (数字)9798350342086

ISBN: (纸本)9798350342093

Routing attacks pose a substantial security risk in Wireless Sensor Networks (WSNs), compromising network performance and reliability. Utilizing the Cartesian product concept to identify these routing attacks in WSNs is an emerging and promising approach. This strategy involves generating a Cartesian product graph from the original network graph and subsequently extracting relevant features to detect potential threats. The success of this approach is dependent on several factors, such as feature selection, the detection algorithm employed, and the prevailing network conditions. This research presents an innovative framework that leverages the Cartesian product approach to identify routing attacks in WSNs. The performance of this framework is evaluated using the Cooja simulator, yielding results that indicate high detection accuracy, low energy usage, and minimal overhead. A comparative analysis with contemporary studies illustrates the superior ability of this framework to handle a wide range of attack scenarios and network conditions. The introduced framework significantly advances the field of routing attack detection in WSNs and provides an actionable solution for easy integration into existing WSNs.

关键词： Wireless sensor networks Accuracy Network topology Scalability Routing Feature extraction Topology Security Reliability detection algorithms

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：