首页 > 最新文献

2022 IEEE Sensors Applications Symposium (SAS)最新文献

英文 中文
An Anomaly Detection System for Transparent Objects Using Polarized-Image Fusion Technique 基于偏振图像融合技术的透明物体异常检测系统
Pub Date : 2022-08-01 DOI: 10.1109/SAS54819.2022.9881251
Lixing Yu, Atsutake Kosuge, M. Hamada, T. Kuroda
An anomaly detection system using a polarized-image fusion technique has been developed for food inspection applications. It is capable of detecting (a) foreign objects among objects wrapped in transparent reflective material and (b) transparent foreign objects in transparent bottles. The conventional anomaly detection system using a traditional RGB camera has low accuracy for such detection, due to the large amount of glare that can occur from reflective surfaces. Regions with glare are often falsely perceived as anomalies. Since transparent foreign objects have few features, they are difficult to recognize. To address these problems, a polarized-image fusion (PIF) technique is developed. Four polarized images are fused to synthesize a high-quality image where glare is suppressed, and transparent foreign objects are highlighted. These polarized images are captured simultaneously by a single camera utilizing an advanced polarized CMOS image sensor. The PIF technique was evaluated with two kinds of data set: (1) cookie samples wrapped in transparent plastic bags and (2) transparent plastic bottles containing transparent plastic foreign objects. High anomaly detection accuracies of 0.851 AUC (area under receiver operating characteristic curve) for the cookie sample data set and 0.871 AUC for the plastic bottle data set were achieved. Compared with the deep one-class classification neural network with simple RGB data input, the accuracies were improved by 0.09 AUC for both cases.
本文开发了一种应用于食品检测的偏振图像融合异常检测系统。它能够检测(a)透明反射材料包裹的物体中的异物和(b)透明瓶中的透明异物。由于反射表面会产生大量的眩光,使用传统RGB相机的常规异常检测系统的检测精度较低。有眩光的区域经常被误认为是异常。由于透明异物的特征很少,因此很难识别。为了解决这些问题,提出了一种偏振图像融合技术。四幅偏振图像融合合成高质量图像,其中眩光被抑制,透明的异物被突出显示。这些偏振图像是由一个利用先进的偏振CMOS图像传感器的单个相机同时捕获的。采用两种数据集对PIF技术进行评估:(1)透明塑料袋包装的饼干样品和(2)含有透明塑料异物的透明塑料瓶。饼干样本数据集的异常检测精度为0.851 AUC,塑料瓶数据集的异常检测精度为0.871 AUC。与简单RGB数据输入的深度一类分类神经网络相比,准确率均提高了0.09 AUC。
{"title":"An Anomaly Detection System for Transparent Objects Using Polarized-Image Fusion Technique","authors":"Lixing Yu, Atsutake Kosuge, M. Hamada, T. Kuroda","doi":"10.1109/SAS54819.2022.9881251","DOIUrl":"https://doi.org/10.1109/SAS54819.2022.9881251","url":null,"abstract":"An anomaly detection system using a polarized-image fusion technique has been developed for food inspection applications. It is capable of detecting (a) foreign objects among objects wrapped in transparent reflective material and (b) transparent foreign objects in transparent bottles. The conventional anomaly detection system using a traditional RGB camera has low accuracy for such detection, due to the large amount of glare that can occur from reflective surfaces. Regions with glare are often falsely perceived as anomalies. Since transparent foreign objects have few features, they are difficult to recognize. To address these problems, a polarized-image fusion (PIF) technique is developed. Four polarized images are fused to synthesize a high-quality image where glare is suppressed, and transparent foreign objects are highlighted. These polarized images are captured simultaneously by a single camera utilizing an advanced polarized CMOS image sensor. The PIF technique was evaluated with two kinds of data set: (1) cookie samples wrapped in transparent plastic bags and (2) transparent plastic bottles containing transparent plastic foreign objects. High anomaly detection accuracies of 0.851 AUC (area under receiver operating characteristic curve) for the cookie sample data set and 0.871 AUC for the plastic bottle data set were achieved. Compared with the deep one-class classification neural network with simple RGB data input, the accuracies were improved by 0.09 AUC for both cases.","PeriodicalId":129732,"journal":{"name":"2022 IEEE Sensors Applications Symposium (SAS)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123306048","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 3
Metrological Analysis of a Contactless Inductive Position Measurement System 一种非接触电感式位置测量系统的计量分析
Pub Date : 2022-08-01 DOI: 10.1109/SAS54819.2022.9881383
S. Tagger, M. Neumayer, G. Gruber, H. Wegleiter
Inductive sensing offers a versatile approach for the realization of position sensors. Advantages of inductive sensing are its robustness with respect to environmental influences, such as dust, humidity, or pollution. The technique also allows the realization of contactless sensors, i.e. sensors without any connection elements. A flexible approach for contactless position sensing is based on voltage measurements between a transmitter coil and an array of receiver coils. E.g. the approach has also been presented for 3D tracking. In this work we study the characteristics of such a system for linear position measurement. The work is based on simulations and comparative measurements. Aspects for the modeling of the inductive coupling are addressed and verified by measurements. Based on this, the elements and exemplary results for an uncertainty quantification for different coil arrangements are presented. Finally a model based approach to assess different coil arrays by means of the Cramér–Rao lower bound (CRLB) is presented.
电感传感为位置传感器的实现提供了一种通用的方法。电感传感的优点是它对环境影响的鲁棒性,如灰尘、湿度或污染。该技术还允许实现非接触式传感器,即没有任何连接元件的传感器。一种灵活的非接触式位置传感方法是基于发射线圈和一组接收线圈之间的电压测量。例如,该方法也被用于3D跟踪。在本工作中,我们研究了这种线性位置测量系统的特性。这项工作是基于模拟和比较测量。讨论了电感耦合建模的各个方面,并通过测量进行了验证。在此基础上,给出了不同线圈布置的不确定度定量的基本原理和示例性结果。最后提出了一种基于模型的基于cram - rao下界(CRLB)的线圈阵列评估方法。
{"title":"Metrological Analysis of a Contactless Inductive Position Measurement System","authors":"S. Tagger, M. Neumayer, G. Gruber, H. Wegleiter","doi":"10.1109/SAS54819.2022.9881383","DOIUrl":"https://doi.org/10.1109/SAS54819.2022.9881383","url":null,"abstract":"Inductive sensing offers a versatile approach for the realization of position sensors. Advantages of inductive sensing are its robustness with respect to environmental influences, such as dust, humidity, or pollution. The technique also allows the realization of contactless sensors, i.e. sensors without any connection elements. A flexible approach for contactless position sensing is based on voltage measurements between a transmitter coil and an array of receiver coils. E.g. the approach has also been presented for 3D tracking. In this work we study the characteristics of such a system for linear position measurement. The work is based on simulations and comparative measurements. Aspects for the modeling of the inductive coupling are addressed and verified by measurements. Based on this, the elements and exemplary results for an uncertainty quantification for different coil arrangements are presented. Finally a model based approach to assess different coil arrays by means of the Cramér–Rao lower bound (CRLB) is presented.","PeriodicalId":129732,"journal":{"name":"2022 IEEE Sensors Applications Symposium (SAS)","volume":"92 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116052970","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 2
Magnetic Sensor Array for Determining the Assembly Torsion and Preload of a Bolted Joint 用于确定螺栓连接总成扭矩和预紧力的磁传感器阵列
Pub Date : 2022-08-01 DOI: 10.1109/SAS54819.2022.9881362
Thorben Schuthe, K. Riemschneider, A. Meyer-Eschenbach
In this paper, we present an innovative concept for determining the assembly preload of a bolted joint. The torsion of the bolt is recorded as a measured variable. Two measurement methods are presented for this task. They are applied simultaneously and compared with each other. The optical method allows high accuracy and is suitable for test benches and characterization of screw parameters. The magnetic measuring method is suitable both for the test bench and for measurements in the practical application of bolted joints. The required measuring accuracy and robustness against geometric misalignment can be achieved by a magnetic sensor array. This offers many advantages over a single angle sensor. A test bench is presented on which both methods are applied simultaneously. Experimental results are shown and compared for verification. As a next development objective, a concept for a tool integrating a magnetic sensor array for torsion measurement is proposed.
在本文中,我们提出了一种确定螺栓连接的装配预紧力的创新概念。螺栓的扭转被记录为一个测量变量。针对这一任务,提出了两种测量方法。它们同时应用并相互比较。光学方法精度高,适用于试验台和螺杆参数的表征。磁测法既适用于试验台架,也适用于螺栓连接实际应用中的测量。磁传感器阵列可以达到所需的测量精度和抗几何偏差的鲁棒性。与单角度传感器相比,这提供了许多优点。给出了两种方法同时应用的试验台。给出了实验结果,并进行了对比验证。作为下一个发展目标,提出了一种集成磁传感器阵列的扭矩测量工具的概念。
{"title":"Magnetic Sensor Array for Determining the Assembly Torsion and Preload of a Bolted Joint","authors":"Thorben Schuthe, K. Riemschneider, A. Meyer-Eschenbach","doi":"10.1109/SAS54819.2022.9881362","DOIUrl":"https://doi.org/10.1109/SAS54819.2022.9881362","url":null,"abstract":"In this paper, we present an innovative concept for determining the assembly preload of a bolted joint. The torsion of the bolt is recorded as a measured variable. Two measurement methods are presented for this task. They are applied simultaneously and compared with each other. The optical method allows high accuracy and is suitable for test benches and characterization of screw parameters. The magnetic measuring method is suitable both for the test bench and for measurements in the practical application of bolted joints. The required measuring accuracy and robustness against geometric misalignment can be achieved by a magnetic sensor array. This offers many advantages over a single angle sensor. A test bench is presented on which both methods are applied simultaneously. Experimental results are shown and compared for verification. As a next development objective, a concept for a tool integrating a magnetic sensor array for torsion measurement is proposed.","PeriodicalId":129732,"journal":{"name":"2022 IEEE Sensors Applications Symposium (SAS)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122944534","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Modeling of a Bacterial Cellulose-based Composite in Bending Configuration 弯曲构型细菌纤维素基复合材料的建模
Pub Date : 2022-08-01 DOI: 10.1109/SAS54819.2022.9881353
R. Caponetto, Andrea Cincotta, G. Pasquale, S. Graziani, A. Pollicino, C. Trigona
Composites obtained by bio-derived polymers are promising materials for the realization of green sensors. Bio-derived composites consisting of a sheet of bacterial cellulose, covered on both faces by two layers of conducting polymers and infused by ionic liquids have been demonstrated to have generating properties when used as deformation sensor. In the paper, the frequency analysis of the composite is investigated in order to experimentally determine the dependence of the transduction property on the frequency of the applied mechanical deformation. A model has been proposed to fit experimental data.
生物聚合物复合材料是实现绿色传感器的理想材料。生物衍生的复合材料由一层细菌纤维素组成,表面覆盖两层导电聚合物,并注入离子液体,当用作变形传感器时,已被证明具有产生特性。本文对复合材料的频率分析进行了研究,以实验确定其传导特性与外加机械变形频率的关系。提出了一个拟合实验数据的模型。
{"title":"Modeling of a Bacterial Cellulose-based Composite in Bending Configuration","authors":"R. Caponetto, Andrea Cincotta, G. Pasquale, S. Graziani, A. Pollicino, C. Trigona","doi":"10.1109/SAS54819.2022.9881353","DOIUrl":"https://doi.org/10.1109/SAS54819.2022.9881353","url":null,"abstract":"Composites obtained by bio-derived polymers are promising materials for the realization of green sensors. Bio-derived composites consisting of a sheet of bacterial cellulose, covered on both faces by two layers of conducting polymers and infused by ionic liquids have been demonstrated to have generating properties when used as deformation sensor. In the paper, the frequency analysis of the composite is investigated in order to experimentally determine the dependence of the transduction property on the frequency of the applied mechanical deformation. A model has been proposed to fit experimental data.","PeriodicalId":129732,"journal":{"name":"2022 IEEE Sensors Applications Symposium (SAS)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123670254","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
A Bending Angle Sensor Based on Magnetic Coupling Suitable for Soft Robotic Finger 一种适用于柔性机器人手指的磁耦合弯曲角度传感器
Pub Date : 2022-08-01 DOI: 10.1109/SAS54819.2022.9881348
Debasrita Kar, B. George, K. Sridharan
Sensing the angle of bending of a soft robotic finger is valuable in many applications but it is a non-trivial task. In this paper, a simple but effective sensing approach based on variable mutual inductance is presented to sense the bending angle. Existing inductive bend sensors use concentric coil based designs and they are not easy to manufacture and integrate into the finger. The planar coil based bend sensor, proposed in this work, is integrated inside the soft robotic finger. The sensor comprises of two flexible printed circuit boards based spiral coils that are magnetically coupled. Three such units are proposed to use in a finger. Each set of planar coils is arranged in such a manner that they give a measure of the curvature of the finger. It can give localized bending of the corresponding parts of the structure which is useful if the bending is not uniform. The measurement circuit required for the sensor is very simple. A prototype sensor built and tested showed a repeatable input-output characteristic with a repeatability error of 0.6%. The proposed sensor does not use the grasping area, is easy to integrate and less expensive. The output of the sensor is immune to moisture, dust and oil.
感知柔软机器人手指的弯曲角度在许多应用中都很有价值,但这是一项艰巨的任务。本文提出了一种简单而有效的基于可变互感的弯曲角传感方法。现有的感应弯曲传感器采用基于同心线圈的设计,它们不容易制造和集成到手指中。本文提出的基于平面线圈的弯曲传感器集成在柔软的机器人手指中。该传感器由两个磁性耦合的柔性印刷电路板螺旋线圈组成。建议在一个手指上使用三个这样的单位。每一组平面线圈以这样一种方式排列,它们给出了手指曲率的测量。它可以给出结构相应部位的局部弯曲,在弯曲不均匀的情况下是有用的。传感器所需的测量电路非常简单。建立并测试的原型传感器显示出可重复的输入输出特性,重复性误差为0.6%。所提出的传感器不使用抓取区域,易于集成且成本较低。传感器的输出不受湿气、灰尘和油的影响。
{"title":"A Bending Angle Sensor Based on Magnetic Coupling Suitable for Soft Robotic Finger","authors":"Debasrita Kar, B. George, K. Sridharan","doi":"10.1109/SAS54819.2022.9881348","DOIUrl":"https://doi.org/10.1109/SAS54819.2022.9881348","url":null,"abstract":"Sensing the angle of bending of a soft robotic finger is valuable in many applications but it is a non-trivial task. In this paper, a simple but effective sensing approach based on variable mutual inductance is presented to sense the bending angle. Existing inductive bend sensors use concentric coil based designs and they are not easy to manufacture and integrate into the finger. The planar coil based bend sensor, proposed in this work, is integrated inside the soft robotic finger. The sensor comprises of two flexible printed circuit boards based spiral coils that are magnetically coupled. Three such units are proposed to use in a finger. Each set of planar coils is arranged in such a manner that they give a measure of the curvature of the finger. It can give localized bending of the corresponding parts of the structure which is useful if the bending is not uniform. The measurement circuit required for the sensor is very simple. A prototype sensor built and tested showed a repeatable input-output characteristic with a repeatability error of 0.6%. The proposed sensor does not use the grasping area, is easy to integrate and less expensive. The output of the sensor is immune to moisture, dust and oil.","PeriodicalId":129732,"journal":{"name":"2022 IEEE Sensors Applications Symposium (SAS)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124068375","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Rx position effect on Device Free Indoor Localization in the 28 GHz band Rx位置对28ghz频段设备自由室内定位的影响
Pub Date : 2022-08-01 DOI: 10.1109/SAS54819.2022.9881244
Verónica Ojeda, Juan C. Aviles
By taking advantage of the received power variation in a communication link due to the presence of a person, this study explores the effect of different distributions of 8 receivers in an indoor free device localization method operating in the 28 GHz band. Uniform linear arrays with 9 antennas (ULA-9) are applied to the transmitting side whereas the receivers are equipped with omnidirectional antennas. Simulation results using data from a ray tracing tool and a machine learning method suggest that for the setup considered, classification accuracy depends more on the number of person’s locations that can be sensed between the transmitter and receiver whether this can occur through direct links or by reflections in nearby walls. Additionally, it is observed that an approximate uniform layout of receivers is not necessarily the optimum distribution and there are some distributions that do not reach better positioning performance than others in any case of the transmitter combinations considered.
本研究利用通信链路中由于人的存在而产生的接收功率变化,探讨了在28ghz频段工作的室内自由设备定位方法中8个接收器的不同分布对定位的影响。发射侧采用9根天线的均匀线性阵列(ULA-9),接收侧采用全向天线。使用来自光线追踪工具和机器学习方法的数据的模拟结果表明,对于所考虑的设置,分类准确性更多地取决于发射器和接收器之间可以感知的人员位置的数量,无论这是通过直接连接还是通过附近墙壁的反射发生。此外,观察到接收器的近似均匀布局不一定是最佳分布,并且在考虑的任何发射机组合情况下,有些分布都不能达到比其他分布更好的定位性能。
{"title":"Rx position effect on Device Free Indoor Localization in the 28 GHz band","authors":"Verónica Ojeda, Juan C. Aviles","doi":"10.1109/SAS54819.2022.9881244","DOIUrl":"https://doi.org/10.1109/SAS54819.2022.9881244","url":null,"abstract":"By taking advantage of the received power variation in a communication link due to the presence of a person, this study explores the effect of different distributions of 8 receivers in an indoor free device localization method operating in the 28 GHz band. Uniform linear arrays with 9 antennas (ULA-9) are applied to the transmitting side whereas the receivers are equipped with omnidirectional antennas. Simulation results using data from a ray tracing tool and a machine learning method suggest that for the setup considered, classification accuracy depends more on the number of person’s locations that can be sensed between the transmitter and receiver whether this can occur through direct links or by reflections in nearby walls. Additionally, it is observed that an approximate uniform layout of receivers is not necessarily the optimum distribution and there are some distributions that do not reach better positioning performance than others in any case of the transmitter combinations considered.","PeriodicalId":129732,"journal":{"name":"2022 IEEE Sensors Applications Symposium (SAS)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115763664","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 2
Automatic Extraction of Muscle Fascicle Pennation Angle from Raw Ultrasound Data 从原始超声数据中自动提取肌束夹角
Pub Date : 2022-08-01 DOI: 10.1109/SAS54819.2022.9881341
Soley Hafthorsdottir, S. Vostrikov, A. Cossettini, Michael Rieder, Christoph Leitner, M. Magno, L. Benini
Compact, wearable, wireless ultrasound (US) sensing systems are promising devices for the observation of human muscle dynamics, offering low power, non-invasive continuous monitoring of contracting muscles. Plane wave imaging is an ideal imaging modality to meet the high frame rate requirements of fast contracting muscles. However, the low power requirements of wearable wireless US constrain the data transfer rates from the probe to the host computer, and limit the maximum number of transducer channels, at the same time discouraging beamforming on the probe. Therefore, it is crucial to extract physiological parameters directly from raw US data for applications demanding fast imaging speeds (like monitoring muscles and tendons in motion). Machine Learning (ML) methods can be employed to effectively extract such features. Although a few recent works demonstrated A-mode US for motion and force prediction, the automatic extraction of structural muscle features from raw data is still in its infancy. This paper demonstrates the feasibility of extracting pennation angles from raw US data on a small dataset of contracting medial gastrocnemius muscles. Automatically extracted labels from US images are used as ground truth to train ML algorithms that predict pennation angles directly from raw US data, without the need for image reconstruction. We employ statistical features, Principle Components Analysis (PCA) and Covolutional Autoencoder (AE) for feature extraction and evaluate Random Forest (RF), Gradient Boosting (XGBoost) and Convoltional Neural Network (CNN) as regressors. Experimental results show that the best method (AE + XGBoost) achieves a mean absolute error of ~ 0.43° that is consistent with the variability of the manually annotated pennation angles reported in the literature, with a memory footprint smaller than 400 kB and less than 5 ms execution time.
紧凑,可穿戴,无线超声(US)传感系统是很有前途的设备,用于观察人体肌肉动力学,提供低功耗,非侵入性连续监测收缩肌肉。平面波成像是一种理想的成像方式,以满足快速收缩肌肉的高帧率要求。然而,可穿戴无线US的低功耗要求限制了从探头到主机的数据传输速率,并限制了传感器通道的最大数量,同时阻止了探头上的波束形成。因此,对于需要快速成像速度的应用(如监测运动中的肌肉和肌腱),直接从原始美国数据中提取生理参数至关重要。机器学习(ML)方法可以有效地提取这些特征。虽然最近的一些工作证明了运动和力预测的a -mode US,但从原始数据中自动提取结构肌肉特征仍处于起步阶段。本文展示了从原始US数据中提取笔角的可行性,该数据来自于收缩内侧腓肠肌的小数据集。从美国图像中自动提取的标签被用作训练机器学习算法的基础事实,该算法直接从原始美国数据中预测笔角,而不需要图像重建。我们使用统计特征、主成分分析(PCA)和卷积自编码器(AE)进行特征提取,并评估随机森林(RF)、梯度增强(XGBoost)和卷积神经网络(CNN)作为回归量。实验结果表明,最佳方法(AE + XGBoost)的平均绝对误差为~ 0.43°,与文献中报道的手动标注笔触角的可变性一致,内存占用小于400 kB,执行时间小于5 ms。
{"title":"Automatic Extraction of Muscle Fascicle Pennation Angle from Raw Ultrasound Data","authors":"Soley Hafthorsdottir, S. Vostrikov, A. Cossettini, Michael Rieder, Christoph Leitner, M. Magno, L. Benini","doi":"10.1109/SAS54819.2022.9881341","DOIUrl":"https://doi.org/10.1109/SAS54819.2022.9881341","url":null,"abstract":"Compact, wearable, wireless ultrasound (US) sensing systems are promising devices for the observation of human muscle dynamics, offering low power, non-invasive continuous monitoring of contracting muscles. Plane wave imaging is an ideal imaging modality to meet the high frame rate requirements of fast contracting muscles. However, the low power requirements of wearable wireless US constrain the data transfer rates from the probe to the host computer, and limit the maximum number of transducer channels, at the same time discouraging beamforming on the probe. Therefore, it is crucial to extract physiological parameters directly from raw US data for applications demanding fast imaging speeds (like monitoring muscles and tendons in motion). Machine Learning (ML) methods can be employed to effectively extract such features. Although a few recent works demonstrated A-mode US for motion and force prediction, the automatic extraction of structural muscle features from raw data is still in its infancy. This paper demonstrates the feasibility of extracting pennation angles from raw US data on a small dataset of contracting medial gastrocnemius muscles. Automatically extracted labels from US images are used as ground truth to train ML algorithms that predict pennation angles directly from raw US data, without the need for image reconstruction. We employ statistical features, Principle Components Analysis (PCA) and Covolutional Autoencoder (AE) for feature extraction and evaluate Random Forest (RF), Gradient Boosting (XGBoost) and Convoltional Neural Network (CNN) as regressors. Experimental results show that the best method (AE + XGBoost) achieves a mean absolute error of ~ 0.43° that is consistent with the variability of the manually annotated pennation angles reported in the literature, with a memory footprint smaller than 400 kB and less than 5 ms execution time.","PeriodicalId":129732,"journal":{"name":"2022 IEEE Sensors Applications Symposium (SAS)","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114580619","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
Printed wireless battery-free sensor tag for structural health monitoring of natural fiber composites 用于天然纤维复合材料结构健康监测的印刷无线无电池传感器标签
Pub Date : 2022-08-01 DOI: 10.1109/SAS54819.2022.9881368
Lukas Rauter, Johanna Zikulnig, L. Neumaier, L. Faller, H. Zangl, J. Kosel
This paper presents a fully printed wireless sensor tag for measuring temperature and strain. The sensor concept was developed in the spirit of sustainability and in line with the European Green Deal, without the use of a battery or a chip. This makes it a promising candidate for integration in natural fiber reinforced composites. Measurement results show the function of the wireless read-out over a distance of 2.5 mm. In the case of both sensors, the measurement data follows a linear dependence and is in good agreement with literature and reference data. The temperature sensor shows a TCR of 1.61*10-3 K-1, the strain sensor a sensitivity of 16.5 kHz per 0.1 % strain.
本文提出了一种用于测量温度和应变的全印刷无线传感器标签。传感器概念是在可持续发展的精神下开发的,符合欧洲绿色协议,不使用电池或芯片。这使得它成为天然纤维增强复合材料中一个很有前途的候选材料。测量结果显示无线读出功能在2.5毫米的距离。在这两种传感器的情况下,测量数据遵循线性依赖关系,并与文献和参考数据很好地一致。温度传感器的TCR为1.61*10-3 K-1,应变传感器的灵敏度为16.5 kHz / 0.1%应变。
{"title":"Printed wireless battery-free sensor tag for structural health monitoring of natural fiber composites","authors":"Lukas Rauter, Johanna Zikulnig, L. Neumaier, L. Faller, H. Zangl, J. Kosel","doi":"10.1109/SAS54819.2022.9881368","DOIUrl":"https://doi.org/10.1109/SAS54819.2022.9881368","url":null,"abstract":"This paper presents a fully printed wireless sensor tag for measuring temperature and strain. The sensor concept was developed in the spirit of sustainability and in line with the European Green Deal, without the use of a battery or a chip. This makes it a promising candidate for integration in natural fiber reinforced composites. Measurement results show the function of the wireless read-out over a distance of 2.5 mm. In the case of both sensors, the measurement data follows a linear dependence and is in good agreement with literature and reference data. The temperature sensor shows a TCR of 1.61*10-3 K-1, the strain sensor a sensitivity of 16.5 kHz per 0.1 % strain.","PeriodicalId":129732,"journal":{"name":"2022 IEEE Sensors Applications Symposium (SAS)","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114760332","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 2
Integration of fiber optic sensors in organ-on-a-chip devices towards label-free cell viability assays 将光纤传感器集成到器官芯片设备中,实现无标签细胞活力分析
Pub Date : 2022-08-01 DOI: 10.1109/SAS54819.2022.9881355
Sanzhar Shakarim, D. Tosi, G. Kulsharova
In this paper, we report a microfluidic polymer organ-on-a-chip device integrated with a fiber optic sensor towards online monitoring of cell viability on-chip. As preliminary model applications, absorbance-based measurements of various concentrations of sucrose solution and of AlluraRed dye in the chip were carried out. Absorbance peaks were correlated to concentrations of the solutions and analyzed. Accurate sensing of analytes in a continuous flow through the device was achieved. Fiber optic sensor integrated microfluidic chip can be used as a label-free assay for cell viability measurements and other applications based on change of absorbance and luminescence values of the cellular microenvironment in organ-on-a-chip devices.
在本文中,我们报道了一种集成了光纤传感器的微流控聚合物器官芯片装置,用于芯片上细胞活力的在线监测。作为初步的模型应用,对芯片中不同浓度的蔗糖溶液和AlluraRed染料进行了基于吸光度的测量。吸光度峰与溶液浓度相关,并进行分析。在通过该装置的连续流动中实现了对分析物的精确传感。光纤传感器集成微流控芯片可以作为一种基于细胞微环境吸光度和发光值变化的无标记检测方法,用于细胞活力测量和其他应用。
{"title":"Integration of fiber optic sensors in organ-on-a-chip devices towards label-free cell viability assays","authors":"Sanzhar Shakarim, D. Tosi, G. Kulsharova","doi":"10.1109/SAS54819.2022.9881355","DOIUrl":"https://doi.org/10.1109/SAS54819.2022.9881355","url":null,"abstract":"In this paper, we report a microfluidic polymer organ-on-a-chip device integrated with a fiber optic sensor towards online monitoring of cell viability on-chip. As preliminary model applications, absorbance-based measurements of various concentrations of sucrose solution and of AlluraRed dye in the chip were carried out. Absorbance peaks were correlated to concentrations of the solutions and analyzed. Accurate sensing of analytes in a continuous flow through the device was achieved. Fiber optic sensor integrated microfluidic chip can be used as a label-free assay for cell viability measurements and other applications based on change of absorbance and luminescence values of the cellular microenvironment in organ-on-a-chip devices.","PeriodicalId":129732,"journal":{"name":"2022 IEEE Sensors Applications Symposium (SAS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116484314","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Classification of batteries in waste streams using magnetic induction spectroscopy 利用磁感应光谱法对废物流中的电池进行分类
Pub Date : 2022-08-01 DOI: 10.1109/SAS54819.2022.9881242
Kane C. Williams, M. O’Toole, L. A. Marsh, A. Peyton
Magnetic induction is widely used to detect and classify metal objects over a range of applications; this paper considers the potential of this technique to inspect for the presence and characteristics of batteries within waste streams. As the number of batteries used across the world increases, an efficient method is needed to ensure batteries can be classified to allow for more efficient recycling. The detection of batteries would also reduce the risk of fire and pollution by identifying the battery before they are crushed or shredded.In this study, a magnetic induction sensor measured the batteries and scrap metal between 781 Hz and 95282 Hz to allow a significant frequency range to be observed. The real component (in-phase) of a battery’s electromagnetic response is different from scrap metal; this could allow for an algorithm to be trained to detect batteries within metal waste or when inside non-metallic objects. The response observed shows that batteries could be grouped into size, which is useful if no line of sight is available, which a traditional camera system requires. Once grouped into size the batteries could be further separated according to their internal contents when the real component is used; this would reduce the risk of cross-contamination when they are recycled. The real component response of lithium and NiMH batteries is different when compared to the other batteries; this could allow them to be detected and removed from a waste stream, which is important as lithium batteries can set on fire.
磁感应被广泛用于探测和分类金属物体的一系列应用;本文考虑了这种技术的潜力,以检查的存在和废物流中的电池的特性。随着世界各地使用的电池数量的增加,需要一种有效的方法来确保电池可以分类,以便更有效地回收。对电池的检测还可以通过在电池被压碎或粉碎之前识别电池来降低火灾和污染的风险。在这项研究中,磁感应传感器测量了781 Hz和95282 Hz之间的电池和废金属,以允许观察到一个显著的频率范围。电池电磁响应的真实分量(同相)不同于废金属;这可以训练一种算法来检测金属废物或非金属物体中的电池。观察到的反应表明,电池可以按大小分组,这在没有视线的情况下很有用,而传统的相机系统需要视线。当使用真正的组件时,一旦分组成尺寸,电池可以根据其内部内容进一步分离;这将减少回收时交叉污染的风险。锂电池和镍氢电池的实际分量响应与其他电池不同;这可以让它们被检测到并从废物流中移除,这一点很重要,因为锂电池可能会着火。
{"title":"Classification of batteries in waste streams using magnetic induction spectroscopy","authors":"Kane C. Williams, M. O’Toole, L. A. Marsh, A. Peyton","doi":"10.1109/SAS54819.2022.9881242","DOIUrl":"https://doi.org/10.1109/SAS54819.2022.9881242","url":null,"abstract":"Magnetic induction is widely used to detect and classify metal objects over a range of applications; this paper considers the potential of this technique to inspect for the presence and characteristics of batteries within waste streams. As the number of batteries used across the world increases, an efficient method is needed to ensure batteries can be classified to allow for more efficient recycling. The detection of batteries would also reduce the risk of fire and pollution by identifying the battery before they are crushed or shredded.In this study, a magnetic induction sensor measured the batteries and scrap metal between 781 Hz and 95282 Hz to allow a significant frequency range to be observed. The real component (in-phase) of a battery’s electromagnetic response is different from scrap metal; this could allow for an algorithm to be trained to detect batteries within metal waste or when inside non-metallic objects. The response observed shows that batteries could be grouped into size, which is useful if no line of sight is available, which a traditional camera system requires. Once grouped into size the batteries could be further separated according to their internal contents when the real component is used; this would reduce the risk of cross-contamination when they are recycled. The real component response of lithium and NiMH batteries is different when compared to the other batteries; this could allow them to be detected and removed from a waste stream, which is important as lithium batteries can set on fire.","PeriodicalId":129732,"journal":{"name":"2022 IEEE Sensors Applications Symposium (SAS)","volume":"209 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123577565","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 3
期刊
2022 IEEE Sensors Applications Symposium (SAS)
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1