Pub Date : 2023-04-20DOI: 10.5194/jsss-12-141-2023
Stefan Schreiber, Nadja Steinke, G. Gerlach
Abstract. Hydrogel sensors are well suited to measuring the concentration of substances in liquids, and, because the hydrogel is biocompatible, they are ideal for medical use. Hydrogels change their volume in response to stimuli. The larger the hydrogel, the more pronounced the measurement signal. However, a larger volume also leads to slower swelling due to the longer diffusion paths. One method of determining the degree of swelling is to measure the swelling pressure using a piezoresistive pressure sensor. With current approaches, measurement times of several minutes can be achieved. By exploiting the bimorph effect, we were able to reduce the thickness of the hydrogel and, thus, reduce the response time of the entire sensor to less than 1 min. The aim of this paper is now to show how a sensor with short response times can be designed and manufactured and, in particular, how to find a suitable hydrogel composition, how to appropriately structure the hydrogel layer and how a robust adhesion of the hydrogel to the sensor chip can be achieved. As a result, we were able to show that such hydrogel sensors with response times of just a few seconds are possible.
{"title":"Chemical hydrogel sensors based on the bimorph effect with short response time","authors":"Stefan Schreiber, Nadja Steinke, G. Gerlach","doi":"10.5194/jsss-12-141-2023","DOIUrl":"https://doi.org/10.5194/jsss-12-141-2023","url":null,"abstract":"Abstract. Hydrogel sensors are well suited to measuring the concentration of substances in liquids, and, because the hydrogel is biocompatible, they are ideal for medical use. Hydrogels change their volume in response to stimuli. The larger the hydrogel, the more pronounced the measurement signal. However, a larger volume also leads to slower swelling due to the longer diffusion paths. One method of determining the degree of swelling is to measure the swelling pressure using a piezoresistive pressure sensor. With current approaches, measurement times of several minutes can be achieved. By exploiting the bimorph effect, we were able to reduce the thickness of the hydrogel and, thus, reduce the response time of the entire sensor to less than 1 min. The aim of this paper is now to show how a sensor with short response times can be designed and manufactured and, in particular, how to find a suitable hydrogel composition, how to appropriately structure the hydrogel layer and how a robust adhesion of the hydrogel to the sensor chip can be achieved. As a result, we were able to show that such hydrogel sensors with response times of just a few seconds are possible.\u0000","PeriodicalId":17167,"journal":{"name":"Journal of Sensors and Sensor Systems","volume":" ","pages":""},"PeriodicalIF":1.0,"publicationDate":"2023-04-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43902179","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}
Pub Date : 2023-04-18DOI: 10.5194/jsss-12-133-2023
R. Jha, W. Lang, R. Jedermann
Abstract. The food industry relies on various technical processes, from storing, freezing, thawing, and packaging to logistics. With the increasing population and the equational growth in food production, it is preferred to have increased automation in the food industry to reduce human labor. To provide an automated and green solution, it is required to monitor and control food-processing steps, such as thawing. This research aims to design an ultrasound-based setup that can monitor the pre-thawing state of food. A change in the signal by 20 %–27 % for herring fish and 60.7 % for chicken soup was obtained when monitored from a frozen state to a room-temperature state. Various other sample food products were tested, and related challenges and observations are discussed.
{"title":"Ultrasonic measurement setup for monitoring pre-thawing stages of food","authors":"R. Jha, W. Lang, R. Jedermann","doi":"10.5194/jsss-12-133-2023","DOIUrl":"https://doi.org/10.5194/jsss-12-133-2023","url":null,"abstract":"Abstract. The food industry relies on various technical processes, from\u0000storing, freezing, thawing, and packaging to logistics. With the increasing\u0000population and the equational growth in food production, it is preferred to\u0000have increased automation in the food industry to reduce human labor. To\u0000provide an automated and green solution, it is required to monitor and\u0000control food-processing steps, such as thawing. This research aims to design an ultrasound-based setup that can monitor the pre-thawing state of food. A change in the signal by 20 %–27 % for herring fish and 60.7 % for\u0000chicken soup was obtained when monitored from a frozen state to a room-temperature state. Various other sample food products were tested, and related challenges and observations are discussed.\u0000","PeriodicalId":17167,"journal":{"name":"Journal of Sensors and Sensor Systems","volume":" ","pages":""},"PeriodicalIF":1.0,"publicationDate":"2023-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43354906","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}
Pub Date : 2023-04-12DOI: 10.5194/jsss-12-123-2023
A. Lambrecht, C. Bolwien, Hendrik Fuhr, G. Sulz, Annett Isserstedt-Trinke, A. Magi, S. Biermann, J. Wöllenstein
Abstract. Infrared attenuated total reflection (ATR) spectroscopy is a common laboratory technique for the analysis of highly absorbing liquids and solids, and a variety of ATR accessories for laboratory FTIR spectrometers are available. However, ATR spectroscopy is rarely found in industrial processes, where compact, robust, and cost-effective sensors for continuous operation are required. Here, narrowband photometers are more appropriate than FTIR instruments. We show the concept and implementation of a compact Si-based ATR module with a four-channel microelectromechanical systems (MEMS) detector. Measurements of liquid mixtures demonstrate the suitability for applications in the chemical industry. Apart from sapphire (for wavelengths below 5 µm) and diamond (extending to the far-infrared region), most materials for ATR elements do not have either high enough infrared transmission or sufficient mechanical and chemical stability to be exposed to process fluids, abrasive components, or aggressive cleaning agents. However, using diamond coatings on Si improves the stability of the sensor surface. In addition, by proper choice of incidence angle and coating thickness, an enhancement of the ATR absorbance is theoretically expected and demonstrated by first experiments using a compact sensor module with a diamond-coated Si ATR element.
{"title":"Compact silicon-based attenuated total reflection (ATR) sensor module for liquid analysis","authors":"A. Lambrecht, C. Bolwien, Hendrik Fuhr, G. Sulz, Annett Isserstedt-Trinke, A. Magi, S. Biermann, J. Wöllenstein","doi":"10.5194/jsss-12-123-2023","DOIUrl":"https://doi.org/10.5194/jsss-12-123-2023","url":null,"abstract":"Abstract. Infrared attenuated total reflection (ATR) spectroscopy is a common laboratory technique for the analysis of highly absorbing liquids and solids, and a variety of ATR accessories for laboratory FTIR spectrometers are available. However, ATR spectroscopy is rarely found in industrial processes, where compact, robust, and cost-effective sensors for continuous operation are required. Here, narrowband photometers are more appropriate than FTIR instruments. We show the concept and implementation of a compact Si-based ATR module with a four-channel microelectromechanical systems (MEMS) detector. Measurements of liquid mixtures demonstrate the suitability for applications in the chemical industry. Apart from sapphire (for wavelengths below 5 µm) and diamond (extending to the far-infrared region), most materials for ATR\u0000elements do not have either high enough infrared transmission or sufficient\u0000mechanical and chemical stability to be exposed to process fluids, abrasive\u0000components, or aggressive cleaning agents. However, using diamond coatings\u0000on Si improves the stability of the sensor surface. In addition, by proper\u0000choice of incidence angle and coating thickness, an enhancement of the ATR\u0000absorbance is theoretically expected and demonstrated by first experiments\u0000using a compact sensor module with a diamond-coated Si ATR element.\u0000","PeriodicalId":17167,"journal":{"name":"Journal of Sensors and Sensor Systems","volume":" 23","pages":""},"PeriodicalIF":1.0,"publicationDate":"2023-04-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41254922","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}
Pub Date : 2023-04-11DOI: 10.5194/jsss-12-111-2023
Abstract. For taking most advantage of live or real-time sensor measurements, data have to be processed by a single or even by a chain of models on the fly, in contrast to earlier offline simulation solutions. This requirement can be best met by concepts developed under the general term “digital twin” (DT). The step from the Internet of Things (IoT) to a full exploitation of DT solutions entails new challenges but also provides new features, which we discuss based on our example DT solution for remote monitoring of fruit during ocean transportation. A crucial challenge is the transformation of models into an updateable format, necessary to keep the physical object and its modelled representation in sync. A basic new feature of DTs is new software solutions for easy and flexible linking of different models through a streaming platform by implementing an event-driven architecture. We demonstrate a solution for controlling model execution during multiple life cycle phases of the fruit as physical object. An evaluation of response times showed that server performance is sufficient to handle more than 100 DT instances per second.
{"title":"Digital twin concepts for linking live sensor data with real-time models","authors":"","doi":"10.5194/jsss-12-111-2023","DOIUrl":"https://doi.org/10.5194/jsss-12-111-2023","url":null,"abstract":"Abstract. For taking most advantage of live or real-time sensor measurements, data have to be processed by a single or even by a chain of models on the fly, in contrast to earlier offline simulation solutions. This requirement can be best met by concepts developed under the general term “digital twin” (DT). The step from the Internet of Things (IoT) to a full\u0000exploitation of DT solutions entails new challenges but also provides new\u0000features, which we discuss based on our example DT solution for remote\u0000monitoring of fruit during ocean transportation. A crucial challenge is the\u0000transformation of models into an updateable format, necessary to keep the\u0000physical object and its modelled representation in sync. A basic new feature\u0000of DTs is new software solutions for easy and flexible linking of different\u0000models through a streaming platform by implementing an event-driven\u0000architecture. We demonstrate a solution for controlling model execution\u0000during multiple life cycle phases of the fruit as physical object. An\u0000evaluation of response times showed that server performance is sufficient to\u0000handle more than 100 DT instances per second.\u0000","PeriodicalId":17167,"journal":{"name":"Journal of Sensors and Sensor Systems","volume":" ","pages":""},"PeriodicalIF":1.0,"publicationDate":"2023-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45308619","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}
Pub Date : 2023-04-05DOI: 10.5194/jsss-12-103-2023
Anke Fischer, T. Wendt, Lukas Stiglmeier, P. Gawron, K. Van Laerhoven
Abstract. Novel approaches for the design of assistive technology controls propose the usage of eye tracking devices such as for smart wheelchairs and robotic arms. The advantages of artificial feedback, especially vibrotactile feedback, as opposed to their use in prostheses, have not been sufficiently explored. Vibrotactile feedback reduces the cognitive load on the visual and auditory channel. It provides tactile sensation, resulting in better use of assistive technologies. In this study the impact of vibration on the precision and accuracy of a head-worn eye tracking device is investigated. The presented system is suitable for further research in the field of artificial feedback. Vibration was perceivable for all participants, yet it does not produce any significant deviations in precision and accuracy.
{"title":"Evaluation of precision, accuracy and threshold for the design of vibrotactile feedback in eye tracking applications","authors":"Anke Fischer, T. Wendt, Lukas Stiglmeier, P. Gawron, K. Van Laerhoven","doi":"10.5194/jsss-12-103-2023","DOIUrl":"https://doi.org/10.5194/jsss-12-103-2023","url":null,"abstract":"Abstract. Novel approaches for the design of assistive technology controls propose the usage of eye tracking devices such as for smart wheelchairs and robotic arms. The advantages of artificial feedback, especially vibrotactile feedback, as opposed to their use in prostheses, have not been sufficiently explored. Vibrotactile feedback reduces the cognitive load on the visual and auditory channel. It provides tactile sensation, resulting in better use of assistive technologies. In this study the impact of vibration on the precision and accuracy of a head-worn eye tracking device is investigated. The presented system is suitable for further research in the field of artificial feedback. Vibration was perceivable for all participants, yet it does not produce any significant deviations in precision and accuracy.\u0000","PeriodicalId":17167,"journal":{"name":"Journal of Sensors and Sensor Systems","volume":" ","pages":""},"PeriodicalIF":1.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41922022","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}
Andreas T. Grasskamp, Satnam Singh, Helen Haug, T. Sauerwald
Abstract. Exhaustive analysis of chemical measurements requires considerable expenditure of time and personnel. However, many aspects of this can be automated by translating manual work into objective algorithmic routines. To this end, we developed adaptable software for gas chromatography data and validated analysis steps using whisky samples. We employed an unspecific, larger, in-house volatile organic compound (VOC) database and another specifically curated database of 217 known whisky chemicals, to automate database-matching based on mass spectra and retention indices. We managed to reduce the amount of necessary interaction, facilitated complex analysis for the less experienced user, and showed that characteristic whisky components constituted the majority of detected molecules in all 16 analyzed samples. With this approach, we present a decisive contribution towards the automated assessment of aroma profiles in food.
{"title":"Assisting the automated analysis of chemical–analytical measurements in spirits using validated algorithms and an intuitive user interface","authors":"Andreas T. Grasskamp, Satnam Singh, Helen Haug, T. Sauerwald","doi":"10.5194/jsss-12-93-2023","DOIUrl":"https://doi.org/10.5194/jsss-12-93-2023","url":null,"abstract":"Abstract. Exhaustive analysis of chemical measurements requires considerable expenditure of time and personnel. However, many aspects of this can be automated by translating manual work into objective algorithmic routines. To this end, we developed adaptable software for gas chromatography data and\u0000validated analysis steps using whisky samples. We employed an unspecific, larger, in-house volatile organic compound (VOC) database and another specifically curated database of\u0000217 known whisky chemicals, to automate database-matching based on mass spectra and retention indices. We managed to reduce the amount of necessary\u0000interaction, facilitated complex analysis for the less experienced user, and showed that characteristic whisky components constituted the majority\u0000of detected molecules in all 16 analyzed samples. With this approach, we present a decisive contribution towards the automated assessment of aroma\u0000profiles in food.\u0000","PeriodicalId":17167,"journal":{"name":"Journal of Sensors and Sensor Systems","volume":" ","pages":""},"PeriodicalIF":1.0,"publicationDate":"2023-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48034667","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}
Jonas Wiegner, H. Volker, Fabian Mainz, Andreas Backes, Michael Loeken, F. Huening
Abstract. This article describes an Internet of things (IoT) sensing device with a wireless interface which is powered by the energy-harvesting method of the Wiegand effect. The Wiegand effect, in contrast to continuous sources like photovoltaic or thermal harvesters, provides small amounts of energy discontinuously in pulsed mode. To enable an energy-self-sufficient operation of the sensing device with this pulsed energy source, the output energy of the Wiegand generator is maximized. This energy is used to power up the system and to acquire and process data like position, temperature or other resistively measurable quantities as well as transmit these data via an ultra-low-power ultra-wideband (UWB) data transmitter. A proof-of-concept system was built to prove the feasibility of the approach. The energy consumption of the system during start-up was analysed, traced back in detail to the individual components, compared to the generated energy and processed to identify further optimization options. Based on the proof of concept, an application prototype was developed.
{"title":"Energy analysis of a wireless sensor node powered by a Wiegand sensor","authors":"Jonas Wiegner, H. Volker, Fabian Mainz, Andreas Backes, Michael Loeken, F. Huening","doi":"10.5194/jsss-12-85-2023","DOIUrl":"https://doi.org/10.5194/jsss-12-85-2023","url":null,"abstract":"Abstract. This article describes an Internet of things (IoT) sensing device\u0000with a wireless interface which is powered by the energy-harvesting method of the\u0000Wiegand effect. The Wiegand effect, in contrast to continuous sources like\u0000photovoltaic or thermal harvesters, provides small amounts of energy\u0000discontinuously in pulsed mode. To enable an energy-self-sufficient\u0000operation of the sensing device with this pulsed energy source, the output\u0000energy of the Wiegand generator is maximized. This energy is used to power up\u0000the system and to acquire and process data like position, temperature or\u0000other resistively measurable quantities as well as transmit these data via an\u0000ultra-low-power ultra-wideband (UWB) data transmitter. A proof-of-concept\u0000system was built to prove the feasibility of the approach. The energy\u0000consumption of the system during start-up was analysed, traced back in\u0000detail to the individual components, compared to the generated energy and\u0000processed to identify further optimization options. Based on the\u0000proof of concept, an application prototype was developed.\u0000","PeriodicalId":17167,"journal":{"name":"Journal of Sensors and Sensor Systems","volume":" ","pages":""},"PeriodicalIF":1.0,"publicationDate":"2023-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45230724","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}
R. Werner, J. Kita, M. Gollner, F. Linseis, R. Moos
Abstract. A new high temperature gauge to simultaneously determine the electrical conductivity, the Hall constant, and the Seebeck coefficient has been developed. Screen-printed heating structures on a ceramic sample holder are used to generate temperatures up to 800 ∘C by Joule heating. The heating structures were designed using the finite element method (FEM) simulations and the temperature distribution was validated by thermal imaging. To measure the Seebeck coefficient, Au/Pt thermocouples with different geometries were investigated and successfully integrated into the gauge. Measurements on constantan, a typical Seebeck coefficient reference material with high electrical conductivity, high charge carrier concentration, and a known Seebeck coefficient, as well as on a well-described boron-doped silicon wafer confirm the functionality of the gauge up to 800 ∘C.
{"title":"Gauge to simultaneously determine the electrical conductivity, the Hall constant, and the Seebeck coefficient up to 800 °C","authors":"R. Werner, J. Kita, M. Gollner, F. Linseis, R. Moos","doi":"10.5194/jsss-12-69-2023","DOIUrl":"https://doi.org/10.5194/jsss-12-69-2023","url":null,"abstract":"Abstract. A new high temperature gauge to simultaneously determine\u0000the electrical conductivity, the Hall constant, and the Seebeck coefficient\u0000has been developed. Screen-printed heating structures on a ceramic sample\u0000holder are used to generate temperatures up to 800 ∘C by Joule\u0000heating. The heating structures were designed using the finite element method (FEM) simulations and the\u0000temperature distribution was validated by thermal imaging. To measure the\u0000Seebeck coefficient, Au/Pt thermocouples with different geometries were\u0000investigated and successfully integrated into the gauge. Measurements on\u0000constantan, a typical Seebeck coefficient reference material with high\u0000electrical conductivity, high charge carrier concentration, and a known\u0000Seebeck coefficient, as well as on a well-described boron-doped silicon\u0000wafer confirm the functionality of the gauge up to 800 ∘C.\u0000","PeriodicalId":17167,"journal":{"name":"Journal of Sensors and Sensor Systems","volume":" ","pages":""},"PeriodicalIF":1.0,"publicationDate":"2023-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46800902","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}
Abstract. To tackle global warming, the reduction of greenhouse gas leaks is of great public interest. While state-of-the-art optical gas imaging (OGI) cameras can visualize larger gas leaks with magnitudes of liters per minute in the case of methane, a much more sensitive laser-based approach is introduced here. This is accomplished using an infrared camera in combination with an interband cascade laser (ICL) as active illumination. The laser beam diverges such that it covers roughly half of the camera's field of view. Three-image batches are recorded to perform classic direct absorption spectroscopy (DAS) at the image scale. The obtained concentration length in parts per million meter (ppm m) is validated using measurements with varying known methane concentrations, different reflective elements, and varying distances. The real-time camera was able to record and quantify a methane leak as low as 40 mL min−1. Possible incorrect information due to moving objects is taken into account using an adapted frame-difference approach.
摘要为应对全球变暖，减少温室气体泄漏事关重大公共利益。虽然最先进的光学气体成像(OGI)相机可以看到更大的气体泄漏，在甲烷的情况下，每分钟泄漏升的数量级，但这里介绍了一种更灵敏的基于激光的方法。这是使用红外相机与带间级联激光器(ICL)作为主动照明相结合来完成的。激光束发散，覆盖了相机大约一半的视野。记录三个图像批次，在图像尺度上执行经典的直接吸收光谱(DAS)。使用不同已知甲烷浓度、不同反射元件和不同距离的测量来验证以百万分之一米(ppm m)为单位获得的浓度长度。实时摄像机能够记录和量化低至40 mL min - 1的甲烷泄漏。由于移动物体可能导致的不正确信息被考虑使用一种适应的帧差方法。
{"title":"Real-time active-gas imaging of small gas leaks","authors":"Max Bergau, T. Strahl, B. Scherer, J. Wöllenstein","doi":"10.5194/jsss-12-61-2023","DOIUrl":"https://doi.org/10.5194/jsss-12-61-2023","url":null,"abstract":"Abstract. To tackle global warming, the reduction of greenhouse gas leaks is of great public interest. While state-of-the-art optical gas imaging (OGI) cameras can visualize larger gas leaks with magnitudes of liters per minute in the case of methane, a much more sensitive laser-based approach is introduced here. This is accomplished using an infrared camera in combination with an interband cascade laser (ICL) as active illumination. The laser beam diverges such\u0000that it covers roughly half of the camera's field of view. Three-image batches are recorded to perform classic direct absorption\u0000spectroscopy (DAS) at the image scale. The obtained concentration length in parts per million meter (ppm m) is validated using measurements with varying known methane\u0000concentrations, different reflective elements, and varying distances. The real-time camera was able to record and quantify a methane\u0000leak as low as 40 mL min−1. Possible incorrect information due to moving objects\u0000is taken into account using an adapted frame-difference approach.\u0000","PeriodicalId":17167,"journal":{"name":"Journal of Sensors and Sensor Systems","volume":" ","pages":""},"PeriodicalIF":1.0,"publicationDate":"2023-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46918480","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}
Abstract. Humans spend most of their lives indoors, so indoor air quality (IAQ) plays a key role in human health. Thus, human health is seriously threatened by indoor air pollution, which leads to 3.8 ×106 deaths annually, according to the World Health Organization (WHO). With the ongoing improvement in life quality, IAQ monitoring has become an important concern for researchers. However, in machine learning (ML), measurement uncertainty, which is critical in hazardous gas detection, is usually only estimated using cross-validation and is not directly addressed, and this will be the main focus of this paper. Gas concentration can be determined by using gas sensors in temperature-cycled operation (TCO) and ML on the measured logarithmic resistance of the sensor. This contribution focuses on formaldehyde as one of the most relevant carcinogenic gases indoors and on the sum of volatile organic compounds (VOCs), i.e., acetone, ethanol, formaldehyde, and toluene, measured in the data set as an indicator for IAQ. As gas concentrations are continuous quantities, regression must be used. Thus, a previously published uncertainty-aware automated ML toolbox (UA-AMLT) for classification is extended for regression by introducing an uncertainty-aware partial least squares regression (PLSR) algorithm. The uncertainty propagation of the UA-AMLT is based on the principles described in the Guide to the Expression of Uncertainty in Measurement (GUM) and its supplements. Two different use cases are considered for investigating the influence on ML results in this contribution, namely model training with raw data and with data that are manipulated by adding artificially generated white Gaussian or uniform noise to simulate increased data uncertainty, respectively. One of the benefits of this approach is to obtain a better understanding of where the overall system should be improved. This can be achieved by either improving the trained ML model or using a sensor with higher precision. Finally, an increase in robustness against random noise by training a model with noisy data is demonstrated.
{"title":"Influence of measurement uncertainty on machine learning results demonstrated for a smart gas sensor","authors":"T. Dorst, T. Schneider, S. Eichstädt, A. Schütze","doi":"10.5194/jsss-12-45-2023","DOIUrl":"https://doi.org/10.5194/jsss-12-45-2023","url":null,"abstract":"Abstract. Humans spend most of their lives indoors, so indoor air quality (IAQ) plays a key role in human health. Thus, human health is seriously threatened by indoor air pollution, which leads to 3.8 ×106 deaths annually, according to the World Health Organization (WHO). With the ongoing improvement in life quality, IAQ monitoring has become an important concern for researchers. However, in machine learning (ML), measurement uncertainty, which is critical in hazardous gas detection, is usually only estimated using cross-validation and is not directly addressed, and this will be the main focus of this paper. Gas concentration can be determined by using gas sensors in temperature-cycled operation (TCO) and ML on the measured logarithmic resistance of the sensor. This contribution focuses on formaldehyde as one of the most relevant carcinogenic gases indoors and on the sum of volatile organic compounds (VOCs), i.e., acetone, ethanol, formaldehyde, and toluene, measured in the data set as an indicator for IAQ. As gas concentrations are continuous quantities, regression must be used. Thus, a previously published uncertainty-aware automated ML toolbox (UA-AMLT) for classification is extended for regression by introducing an uncertainty-aware partial least squares regression (PLSR) algorithm. The uncertainty propagation of the UA-AMLT is based on the principles described in the Guide to the Expression of Uncertainty in Measurement (GUM) and its supplements. Two different use cases are considered for investigating the influence on ML results in this contribution, namely model training with raw data and with data that are manipulated by adding artificially generated white Gaussian or uniform noise to simulate increased data uncertainty, respectively. One of the benefits of this approach is to obtain a better understanding of where the overall system should be improved. This can be achieved by either improving the trained ML model or using a sensor with higher precision. Finally, an increase in robustness against random noise by training a model with noisy data is demonstrated.\u0000","PeriodicalId":17167,"journal":{"name":"Journal of Sensors and Sensor Systems","volume":" ","pages":""},"PeriodicalIF":1.0,"publicationDate":"2023-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46868417","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：