检索结果-内蒙古大学图书馆

Scalogram-energy based segmentation of surface electromyography signals from swallowing related muscles

COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2020年 194卷 105480-105480页

作者： Sebastian, Roldan-Vasco Estefania, Perez-Giraldo Andres, Orozco-Duque Inst Tecnol Metropolitano Fac Ingn Grp Invest Mat Avanzados & Energia Medellin Colombia Univ Antioquia Fac Ingn Grp Invest Telecomunicac Aplicadas Medellin Colombia Inst Tecnol Metropolitano Fac Ciencias Exactas & Aplicadas Grp Invest & Innovac Biomed Medellin Colombia

Background and Objective: The swallowing is a complex process mediated by the central nervous system, that implies voluntary and involuntary components, including 26 pairs of muscles. Non-invasive strategies, including the surface electromyography (sEMG), have been proposed to evaluate the swallowing. However, such analyses have been mostly descriptive, and the detection of neuromuscular activity has been limited to the visual inspection (VIS). Nonetheless, the VIS lacks reliability since the swallowing related muscles have small size, they are not completely shallow, suffer from cross-talk and have low signal-to-noise ratio (SNR). In this way, we propose a wavelet based method to automatically detect activations in sEMG signals acquired during praxis and swallowing tasks. Methods: The proposed strategy, namely Scalogram-Energy based Segmentation method, was applied on sEMG signals recorded in masseteric, orbicular, supra- and infrahyoid muscles. The method was trained in a database of 35 healthy subjects by the use of multi-objective genetic algorithms and tested via crossvalidation, aiming to maximize the F 1 score and minimize the timing error between the automatic and VIS related marks. Furthermore, the proposed method was tested in a database of semi-synthetic signals with variable SNR built from signals collected from 10 individuals. Additionally, the method was compared with a double threshold based algorithm as well as with other based on energy and morphological operators. Results: The algorithm achieved a F 1 score of 0.82 and almost 13 ms of error in the estimation of onset and offset. Afterwards, we applied the optimized algorithm to a set with semi-synthetic signals with variable SNR, that achieved F 1 score of 0.85 for SNR = 6 dB and 0.97 for SNR = 8 and 10 dB. The mean of the timing error was smaller than 9 ms for SNR = 6,8 and 10 dB. The method was also compared with a double threshold based algorithm as well as with other based on energy and morphol

关键词： Swallowing Segmentation Surface electromyography sEMG detection algorithm Wavelet transform

来源：评论

学校读者我要写书评

暂无评论

Detekce začátku a konce komplexu QRS s využitím hlubokého učení

Detekce začátku a konce komplexu QRS s využitím hluboké...

引用

作者： Malina, Ondřej Brno University of Technology

Tato práce se zabývá problematikou automatického měření doby trvání QRS komplexů v EKG signálech. Zvláštní důraz je zde pak kladen na možnosti automatické detekc... 详细信息

Tato práce se zabývá problematikou automatického měření doby trvání QRS komplexů v EKG signálech. Zvláštní důraz je zde pak kladen na možnosti automatické detekce komplexů QRS při současném buzení srdeční tkáně kardiostimulátorem. Obsah této práce je řazen do čtyř logických celků, kdy se v první části věnuje srdci jako orgánu. Popisuje vznik a šíření vzruchu v srdci, jeho možné patologie a jejich projevy v EKG záznamu, dále se zde věnuje kardiostimulaci a měření EKG záznamu při současné kardiostimulaci. Druhá část práce obsahuje stručný úvod do tématu strojového a hlubokého učení. Třetí část práce obsahuje rešerše aktuálních přístupů využívající k řešení detekce QRSd metody založené na hlubokém učení. Čtvrtá část se pak zabývá návrhem a implementací vlastního modelu hlubokého učení, schopného detekovat začátky a konce QRS komplexů z EKG záznamů. Je zde popsáno předzpracovaní dat realizované v programovacím prostředí MATLAB. Samotná implementace modelu byla uskutečněna v programovacím jazyce Python za využití modulů PyTorch a NumPy.

关键词： EKG signál detekce QRS komplexů QRSd kardiostimulace detekční algoritmus strojové učení hluboké učení Python LSTM ConvLSTM PyTorch ECG signal detection of QRS complexes QRSd cardiostimulation detection algorithm machine learning deep lear

来源：评论

学校读者我要写书评

暂无评论

Diagnostika ventrikulárních tachykardií z elektrokardiografického záznamu.

Diagnostika ventrikulárních tachykardií z elektrokardiogr...

引用

作者： Šrutová, Martina Brno University of Technology

Cílem této práce je diagnostika ventrikulárních tachykardií, fibrilací a flutterů z elektrokardiogramu. Tyto poruchy srdečního rytmu patří mezi život ohrožující a... 详细信息

Cílem této práce je diagnostika ventrikulárních tachykardií, fibrilací a flutterů z elektrokardiogramu. Tyto poruchy srdečního rytmu patří mezi život ohrožující arytmie. V následující práci je presentována vlastní metoda automatické detekce vytvořená pro EKG holterovský monitorovací systém. Navržený algoritmus je založen na detekci ve spektrální oblasti podpořený detekcí v oblasti časové. Výsledek práce je ověřen na diskriminaci nalezených arytmií vůči normálnímu EKG záznamu a na diskriminaci vůči šumu. Úspěšnost detekce je testována na signálech z databází The AHA Database (The American Heart Association) a The MIT-BIH Malignant Ventricular Arrhythmia Database.

关键词： komorová tachykardie fibrilace flutter detekční algoritmus EKG ventricular tachycardia fibrillation flutter detection algorithm ECG Text

来源：评论

学校读者我要写书评

暂无评论

Detekce začátku a konce komplexu QRS s využitím hlubokého učení

Detekce začátku a konce komplexu QRS s využitím hluboké...

引用

作者： Malina, Ondřej Brno University of Technology

Tato práce se zabývá problematikou automatického měření doby trvání QRS komplexů v EKG signálech. Zvláštní důraz je zde pak kladen na možnosti automatické detekc... 详细信息

来源：评论

学校读者我要写书评

暂无评论

Moderní metody detekce QRS komplexů

Moderní metody detekce QRS komplexů

引用

作者： Fajkus, Jiří Brno University of Technology

Tato bakalářská se zabývá metodami, které slouží ke zpracovávání EKG signálů, konkrétně k detekci QRS komplexu. Detekce QRS komplexu je nezbytnou součást... 详细信息

Tato bakalářská se zabývá metodami, které slouží ke zpracovávání EKG signálů, konkrétně k detekci QRS komplexu. Detekce QRS komplexu je nezbytnou součástí každé analýzy EKG signálu, jelikož slouží k určení bodů v časovém průběhu EKG, od kterých se poté odvíjí detekce a rozměření ostatních vln a intervalů potřebných k diagnostice. V práci je popsáno několik způsobů detekce QRS komplexů a rozbor detektoru navrženého v programovém prostředí MATLAB, založeného na principu počítání průchodů nulovou hladinou. Tento detektor QRS komplexů byl následně testován na CSE databázi a signálech z holterovského vyšetření.

关键词： Detekční algoritmus charakteristický signál komplex QRS neuronové sítě pozitivní prediktivita práh průchod nulovou hladinou robustnost sensitivita signál EKG vlnková transformace. detection algorithm ECG signal feature signal neural networks

来源：评论

学校读者我要写书评

暂无评论

Development and experimental analysis of an intelligent sensor for monitoring seed flow rate based on a seed flow reconstruction technique

引用

COMPUTERS AND ELECTRONICS IN AGRICULTURE 2019年 164卷 104899-000页

作者： Liu, Wei Hu, Jianping Zhao, Xingsheng Pan, Haoran Lakhiar, Imran Ali Wang, Wei Jiangsu Univ Sch Agr Equipment Engn Zhenjiang 212013 Jiangsu Peoples R China

In practical grain sowing operation, it is difficult to detect the accurate seed flow rate in large flow rate condition because the discharged seeds flow in a continuous dense state. Therefore, the objective of this study was to develop a sensor based on a seed flow reconstruction technique to monitor the seed flow rate. The technique transforms the continuous seed flow into separated particles, which can effectively reduce the measurement errors caused by the seed overlapping. A signal processing unit was designed to transform seed falling time to a high-level of sustaining time. Based on the number of continuous high-level sampling points, a particle counting method (PCM) was proposed. Moreover, to verify the performance of the designed sensor and its supportive algorithm, a specific testing bed was developed, and comparison experiments were conducted with the PCM and a conventional mass estimating method (MEM). The verifying results demonstrated that the seed flow rate detected by the PCM was slightly lower than the actual seed number;therefore, a correcting coefficient (1.066) was introduced to multiply with original detection result for improving the accuracy. As for the MEM, the linear regression analysis validated that the proportional relationship between the overall output of sensor versus the total seed mass was very strong (R = 0.997). The detection results of the PCM and the MEM were not significantly different from their actual values, respectively. The mean absolute percentage error (MAPE) of the PCM and the MEM values were 1.89% and 5.91%, respectively. Moreover, the experiments detected by the PCM at 100% and the MEM at 57.7% were exceeded the accuracy 95%. According to the MAPE and accuracy, it was demonstrated that the PCM has a better performance than the MEM in terms of seed flow rate detection. These results show that the developed sensor can be used in practical sowing process to detect the seed flow rate on grain drills.

关键词： Seed flow rate detection Seed flow reconstruction Infrared ray sensor Particle counting method detection algorithm

来源：评论

学校读者我要写书评

暂无评论

Multi-Scale Object Histogram Distance for LCCD Using Bi-Temporal Very-High-Resolution Remote Sensing Images

引用

REMOTE SENSING 2018年第11期10卷 1809-1809页

作者： Lv, ZhiYong Liu, TongFei Benediktsson, Jon Atli Lei, Tao Wan, YiLiang XiAn Univ Technol Sch Comp Sci & Engn Xian 710048 Shaanxi Peoples R China Key Lab Geospatial Big Data Min & Applicat Changsha 410081 Hunan Peoples R China Univ Iceland Fac Elect & Comp Engn IS-107 Reykjavik Iceland Shaanxi Univ Sci & Technol Sch Elect & Informat Engn Xian 710021 Shaanxi Peoples R China Hunan Normal Univ Coll Resources & Environm Sci Changsha 410081 Hunan Peoples R China

To improve the performance of land-cover change detection (LCCD) using remote sensing images, this study utilises spatial information in an adaptive and multi-scale manner. It proposes a novel multi-scale object histogram distance (MOHD) to measure the change magnitude between bi-temporal remote sensing images. Three major steps are related to the proposed MOHD. Firstly, multi-scale objects for the post-event image are extracted through a widely used algorithm called the fractional net evaluation approach. The pixels within a segmental object are taken to construct the pairwise frequency distribution histograms. An arithmetic frequency-mean feature is then defined from the red, green and blue band histogram. Secondly, bin-to-bin distance is adapted to measure the change magnitude between the pairwise objects of bi-temporal images. The change magnitude image (CMI) of the bi-temporal images can be generated through object-by-object. Finally, the classical binary method Otsu is used to divide the CMI to a binary change detection map. Experimental results based on two real datasets with different land-cover change scenes demonstrate the effectiveness of the proposed MOHD approach in detecting land-cover change compared with three widely used existing approaches.

关键词： land use and land cover remote sensing application detection algorithm histogram distance

来源：评论

学校读者我要写书评

暂无评论

Spatio-temporal variability of the equatorial front in the eastern tropical Pacific from remote sensing salinity data (2010-2015)

引用

DEEP-SEA RESEARCH PART II-TOPICAL STUDIES IN OCEANOGRAPHY 2019年 169卷

作者： Asto, Cristhian Chaigneau, Alexis Gutierrez, Dimitri Inst Mar Peru Direcc Gen Invest Oceanog & Cambio Climat Callao Peru Univ Peruana Cayetano Heredia Lima Peru Univ Toulouse CNES CNRD LEGOSIRDUPS Toulouse France IRHOB Cotonou Benin Univ Abomey Calavi ICMPA UNESCO Chair Cotonou Benin

In the eastern Pacific, the Equatorial Front (EF) separates the relatively cold and salty Equatorial Surface Water to the South from the relatively warm and fresh Surface Tropical Water to the North. Although previous studies have succinctly described the main EF characteristics, little is known about its spatial pattern and temporal variability beyond seasonal scale. In this study, we used 5 years of remote-sensing sea surface salinity (SSS) data, acquired by SMOS in a synoptic and continuous manner, to describe the spatio-temporal variability of the haline EF (HEF). After validating the SSS satellite dataset with concomitant in situ data, we developed an algorithm based on maximum SSS gradients to automatically identify the HEF position on every SMOS SSS map. This algorithm applied to the 4-day resolution SMOS SSS product, allows us to investigate the spatio-temporal variability of the HEF between 2010 and 2015. Seasonally, west of the Galapagos Islands, the HEF is centered at 2 N and shows relatively weak meridional displacements. In contrast, east of the Galapagos Archipelago, the HEF varies on average between similar to 4 degrees S in spring and similar to 2 degrees N in autumn. At intraseasonal scales, the HEF shows meridional fluctuations of +/- 1.25 degrees around its average position. These intraseasonal fluctuations are partly related to Kelvin Waves, which was more noticeable since 2014. Over the 5-year studied period, the HEF position showed a northward trend of 0.3-0.4 latitudinal degrees per year between 2010 and 2015. However, the relatively short time series does not permit to investigate whether this low-frequency trend is due to long-term variability or interdecadal fluctuations.

关键词： Eastern tropical pacific Equatorial front Sea surface salinity detection algorithm

来源：评论

学校读者我要写书评

暂无评论

Research on detecting moving targets with an improved Kalman filter algorithm

引用

KSII TRANSACTIONS ON INTERNET AND INFORMATION SYSTEMS 2023年第9期17卷 2348-2360页

作者： Zhou, Jia Quan Wei, Wei Guangxi Sci & Technol Normal Univ Laibin 546199 Angola Xian Univ Technol Xian 740048 Peoples R China

As science and technology evolve, object detection of moving objects has been widely used in the context of machine learning and artificial intelligence. Traditional moving object detection algorithms, however, are characterized by relatively poor real-time performance and low accuracy in detecting moving objects. To tackle this issue, this manuscript proposes a modified Kalman filter algorithm, which aims to expand the equations of the system with the Taylor series first, ignoring the higher order terms of the second order and above, when the nonlinear system is close to the linear form, then it uses standard Kalman filter algorithms to measure the situation of the system. which can not only detect moving objects accurately but also has better real-time performance and can be employed to predict the trajectory of moving objects. Meanwhile, the accuracy and real-time performance of the algorithm were experimentally verified.

关键词： Moving objects machine learning artificial intelligence detection algorithm improved Kalman filter algorithm

来源：评论

学校读者我要写书评

暂无评论

An Improved New YOLOv7 algorithm for Detecting Building Air Conditioner External Units from Street View Images

引用

SENSORS 2023年第22期23卷 9118-9118页

作者： Tian, Zhongmin Yang, Fei Qin, Donghong Guangxi Minzu Univ Coll Artificial Intelligence Nanning 530006 Peoples R China Chinese Acad Sci State Key Lab Resources & Environm Informat Syst Inst Geog Sci & Nat Resources Res Beijing 100101 Peoples R China Jiangsu Ctr Collaborat Innovat Geog Informat Resou Nanjing 210023 Peoples R China

Street view images are emerging as new street-level sources of urban environmental information. Accurate detection and quantification of urban air conditioners is crucial for evaluating the resilience of urban residential areas to heat wave disasters and formulating effective disaster prevention policies. Utilizing street view image data to predict the spatial coverage of urban air conditioners offers a simple and effective solution. However, detecting and accurately counting air conditioners in complex street-view environments remains challenging. This study introduced 3D parameter-free attention and coordinate attention modules into the target detection process to enhance the extraction of detailed features of air conditioner external units. It also integrated a small target detection layer to address the challenge of detecting small target objects that are easily missed. As a result, an improved algorithm named SC4-YOLOv7 was developed for detecting and recognizing air conditioner external units in street view images. To validate this new algorithm, we extracted air conditioner external units from street view images of residential buildings in Guilin City, Guangxi Zhuang Autonomous Region, China. The results of the study demonstrated that SC4-YOLOv7 significantly improved the average accuracy of recognizing air conditioner external units in street view images from 87.93% to 91.21% compared to the original YOLOv7 method while maintaining a high speed of image recognition detection. The algorithm has the potential to be extended to various applications requiring small target detection, enabling reliable detection and recognition in real street environments.

关键词： YOLO heat wave hazards street view air conditioner detection algorithm

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：