2021 IEEE International Instrumentation and Measurement Technology Conference (I2MTC)最新文献

{"title":"Deep Transfer Learning Strategy for Invasive Lung Adenocarcinoma Classification Appearing as Ground Glass Nodules","authors":"Chen Ma, Shihong Yue, Qi Li","doi":"10.1109/I2MTC50364.2021.9459841","DOIUrl":"https://doi.org/10.1109/I2MTC50364.2021.9459841","url":null,"abstract":"Lung cancer is one of the deadliest diseases in which adenocarcinoma account for nearly 40%. To make an effective treatment and diagnosis, it is vital to accurately discriminate invasive adenocarcinoma (IA) from non-IA by analyzing ground glass nodules (GGNs) from patient's CT images. Compared with solid nodules and normal lung parenchyma, the contours of GGN are blurred and the gray scale is little changed. So far, the problem to accurately discriminate IA and non-IA remains unsolved due to insufficient labeled GGN images. In this paper, considering the generalization of convolutional neural network (CNN) and various flexible transfer strategies, we proposed a lung adenocarcinoma classification method after combining transfer learning and CNN, where the use of transfer learning strategies aims at overcoming the problem of insufficient GGN samples. Firstly, the CT image on IA and non-IA patients were collected which were labeled by surgical pathology. Secondly, two transfer learning strategies that consist of CNN feature extractor and fine-tuning network were applied to classify IA and non-IA. Finally, in the fine-tuning network process, a Progressive Fine-Tuning (PFT) strategy was combined to determine the effective depth of fine-tuning to avoid inaccurate induction of GGNs. In the CNN feature extractor experiment, four comparable models were used including linear discrimination, Support Vector Machines, K-nearest neighbor, and subspace discrimination. The indicators of sensitivity, specificity, accuracy, and AUC (area under curve) were used to quantitatively assess the performance of the two transfer strategies. Experiments show that the strategy of CNN feature extractor based on transfer learning had the highest accuracy, which was significantly higher than fine-tuning network strategy with PFT. In the experiment of CNN feature extractor, the model of linear discrimination to predict the invasiveness of GGNs has 94% accuracy whereas the other three models have 92.9%, 93.1% and 92.9%, respectively.","PeriodicalId":6772,"journal":{"name":"2021 IEEE International Instrumentation and Measurement Technology Conference (I2MTC)","volume":"28 1","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2021-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74231324","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}

{"title":"Reconstruction of Galvanic Skin Response Peaks via Sparse Representation","authors":"Grazia Iadarola, A. Poli, S. Spinsante","doi":"10.1109/I2MTC50364.2021.9459905","DOIUrl":"https://doi.org/10.1109/I2MTC50364.2021.9459905","url":null,"abstract":"Continuous and long-term measurement of physiological signals out of clinical settings may face different processing requirements resulting in higher costs or reduced performance. Improved techniques of signal reconstruction from compressed representation may be a solution. This paper presents an approach based on Compressed Sensing to reconstruct peaks of Galvanic Skin Response measured by a wrist-worn device. Specifically, a random measurement matrix is employed in the reconstruction phase. Results show that the proposed approach detects the correct number of peaks better than the Ledalab automatic toolbox, even with high compression rates.","PeriodicalId":6772,"journal":{"name":"2021 IEEE International Instrumentation and Measurement Technology Conference (I2MTC)","volume":"68 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2021-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91206500","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}

{"title":"Towards Always-on Event-based Cameras for Long-lasting Battery-operated Smart Sensor Nodes","authors":"Moritz Scherer, Philipp Mayer, Alfio Di Mauro, M. Magno, L. Benini","doi":"10.1109/I2MTC50364.2021.9460037","DOIUrl":"https://doi.org/10.1109/I2MTC50364.2021.9460037","url":null,"abstract":"A recent and promising approach to minimize the power consumption of always-on battery-operated sensors is to perform “smart” detection of events to trigger processing. This approach effectively reduces the data bandwidth and power consumption at the system-level and increases the lifetime of sensor nodes. This paper presents an always-on, event-driven ultra-low-power camera platform for motion detection applications. The platform exploits an event-driven VGA imager that features a motion detection mode based on a tunable scene background subtraction algorithm and a grayscale imaging mode. To reduce the power consumption in the motion detection mode, the platform implements a configurable refresh rate which allows for adaption to sensing requirements by trading off between power consumption and detection sensitivity. With accurate experimental evaluation the paper demonstrates that the proposed approach reduces the system-level power consumption for always-on motion sensing applications by switching between an active 15 FPS imaging mode, consuming 5.5 mW and a low-power motion detection mode consuming 1.8 mW. We further estimate the power consumption for a single-chip solution and show that the system-level power budget can be reduced to 2.4 mW in imaging, and $400 mumathrm{W}$ in detection mode.","PeriodicalId":6772,"journal":{"name":"2021 IEEE International Instrumentation and Measurement Technology Conference (I2MTC)","volume":"25 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2021-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91282273","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}

{"title":"Influence of Parameters in Kalman-filter-based Method on Image Quality for Electrical Capacitance Tomography","authors":"Ying Wang, Lijun Xu, Shijie Sun, Xupeng Lu, Jiangtao Sun","doi":"10.1109/I2MTC50364.2021.9459913","DOIUrl":"https://doi.org/10.1109/I2MTC50364.2021.9459913","url":null,"abstract":"As a powerful tool to get a recursive solution of least squares estimation, the Kalman filter has been used for image reconstruction in Electrical Capacitance Tomography (ECT). In the Kalman-filter-based image reconstruction method, some key parameters, e.g., initial guess, observation noise covariance and initial estimate error covariance, greatly influence the performance of the method. Inappropriate values of these parameters may cause a series of problems, such as lower convergence rate, artifacts, or filter divergence. This paper aims to analyze the influence of the parameters on the image quality for ECT and guide the selection of the parameters. Numerical simulation and experiment were carried out and the results show that with an initial guess obtained by linear back projection (LBP) method and a good match of observation noise covariance and initial estimate error covariance, the performance of the Kalman-filter-based method can be improved.","PeriodicalId":6772,"journal":{"name":"2021 IEEE International Instrumentation and Measurement Technology Conference (I2MTC)","volume":"5 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2021-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83509730","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}

{"title":"Determination of Fat, SNF and Protein Content in Cow Milk from the Voltage Output of ‘MilkTester’","authors":"Suman Biswas, A. Mandal, Moupali Chakraborty, K. Biswas","doi":"10.1109/I2MTC50364.2021.9459873","DOIUrl":"https://doi.org/10.1109/I2MTC50364.2021.9459873","url":null,"abstract":"In this work, we report estimation of fat, protein and solid not fat (SNF) of cow milk using the output voltage obtained from the ‘MilkTester’, developed by the authors at Indian Institute of Technology Kharagpur (IIT Kharagpur). The estimation is carried out in three phases named as “Training”, “Interrelation”, and “Validation”. In the “Training Phase”, output voltage from the “MilkTester” is expressed as multivariate equation of fat, SNF and protein. The data sets of fat, SNF and protein are collected using the commercial instrument, “MilkoScreen”(from FOSS, Denmark). This instrument is installed in National Dairy Research Institute Kalyani, India to measure the constituents of milk. Interrelations between “protein & SNF” and “SNF & fat” are estimated by linear regression analysis using the software, OriginPro 8.5, which return the value of the coefficients of the equations. Finally, relation between output voltage and fat is obtained. Once the value of fat percentage is known, the other two parameters can be found out by using the interrelation equations. In the ‘Validation Phase’, fat, SNF and protein are regarded as unknown components and estimated using voltage data (from the ‘MilkTester’). The error between the estimated value (from regression analysis) and true value (obtained from the “MilkoScreen’) is also evaluated for all the three parameters for randomly chosen samples. The maximum error, 12.21 %, is found for estimation of protein. But the difference of absolute value is only 0.59. Maximum error for fat estimation is 10.01 %, where absolute difference is 0.63. The SNF estimation shows error of 4.61 % with absolute error of 0.45.","PeriodicalId":6772,"journal":{"name":"2021 IEEE International Instrumentation and Measurement Technology Conference (I2MTC)","volume":"1 1","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2021-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83512333","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}

{"title":"ECG Noise Removal and Efficient Arrhythmia Identification Based on Effective Signal-Piloted Processing and Machine Learning","authors":"S. Qaisar, D. Dallet","doi":"10.1109/I2MTC50364.2021.9459846","DOIUrl":"https://doi.org/10.1109/I2MTC50364.2021.9459846","url":null,"abstract":"For a viable classification of electrocardiogram (ECG) signals, a signal-piloted adaptive rate processing approach is suggested for the efficient reduction of noise and extraction of features. By using an adaptive rate wavelet decomposition scheme, recognizable features are derived from the preconditioned signal. These attributes are then analyzed for arrhythmia recognition. By using a known arrhythmia, MIT-BIH, database, the output of the framework is studied. It is demonstrated that the system is able to adapt its parameters by analyzing the incoming signal variations. It permits the processing of a lower dimension dataset, for arrhythmia recognition, by the computationally efficient adaptive-rate denoising and subbands decomposition stages. This results in a major decrease in the system's computational costs. The amount of information, required to be sent to the health server is also drastically diminished. This aptitude shows a measurable decrease in the activity of data transmission and processing load of the post classifier. Moreover, the classification performance of the devised method is tested. Findings demonstrated a good performance by achieving 99.3 percent accuracy.","PeriodicalId":6772,"journal":{"name":"2021 IEEE International Instrumentation and Measurement Technology Conference (I2MTC)","volume":"29 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2021-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78224578","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}

{"title":"A novel measurement technique for DC voltage and current reducing the DMM loading effects","authors":"Emilio Torres, Carlos Monzo, F. Reverter","doi":"10.1109/I2MTC50364.2021.9460022","DOIUrl":"https://doi.org/10.1109/I2MTC50364.2021.9460022","url":null,"abstract":"A novel technique for the measurement of DC voltage and current that reduces the loading effects of a digital multimeter is presented in this work. When the variable of interest is a current (voltage), instead of connecting an ammeter (voltmeter) in series (parallel), it is proposed to connect a voltmeter (ammeter) and an ohmmeter in series (parallel) at the same two terminals conventionally employed. The application of this new measurement technique reduces the loading effects by a factor of at least 100 but up to 500, in comparison with those obtained in the conventional method.","PeriodicalId":6772,"journal":{"name":"2021 IEEE International Instrumentation and Measurement Technology Conference (I2MTC)","volume":"47 1","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2021-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78419242","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}

{"title":"Miniaturised bidirectional acoustic tag to enhance marine animal tracking studies","authors":"I. Masmitja, Daniel Corregidor, Juan-Manuel López-Navarro, E. Martínez, J. Navarro, S. Gomáriz","doi":"10.1109/I2MTC50364.2021.9459945","DOIUrl":"https://doi.org/10.1109/I2MTC50364.2021.9459945","url":null,"abstract":"Acoustic underwater tags are key devices to study marine animals and comprehend their patterns, which provide essential behavioural information for applying new conservation policies. At present, all the acoustic tags have a unidirectional communication protocol, which introduces important limitations for their localisation such as range measurement, and in situ reconfiguration. To solve these issues and improve the current state-of-the-art acoustic tags, a new bidirectional tag device is presented in this paper. This innovative tag will allow new studies and will open a wide tracking capability by using autonomous underwater vehicles and range-based algorithms. Here, the main architecture of the tag, and its characteristics are presented alongside the first laboratory tests, and the results obtained.","PeriodicalId":6772,"journal":{"name":"2021 IEEE International Instrumentation and Measurement Technology Conference (I2MTC)","volume":"9 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2021-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72835494","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}

{"title":"A Machine Learning Approach for a Vision-Based Van-Herick Measurement System","authors":"Tommaso Fedullo, Davide Cassanelli, G. Gibertoni, F. Tramarin, L. Quaranta, G. Angelis, L. Rovati","doi":"10.1109/I2MTC50364.2021.9459946","DOIUrl":"https://doi.org/10.1109/I2MTC50364.2021.9459946","url":null,"abstract":"The application of Artificial Intelligence to the instrumentation and measurements field is nowadays an attractive research area. Indeed, Artificial Intelligence gives the possibility to perform activities also in case of inability to perfectly model a phenomenon or a system. Furthermore, making machines learn from data how to perform an activity, rather than hard code sequential instructions, is a common and effective practice in many modern research areas. This paper investigates the possibility to use Machine Learning techniques in an ophthalmic vision–based system performing automatic Anterior Chamber Angle measurements. Currently, this procedure can be performed only by appropriately trained medical personnel. For this reason, Machine Learning and Vision–Based techniques may greatly improve both test objectiveness and diagnostic accessibility, by allowing to automatically carry out the measurement procedure.","PeriodicalId":6772,"journal":{"name":"2021 IEEE International Instrumentation and Measurement Technology Conference (I2MTC)","volume":"40 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2021-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77331890","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}

{"title":"A Wireless Flexible Electrooculogram Monitoring System With Printed Electrodes","authors":"Shibam Debbarma, Seyedfakhreddin Nabavi, S. Bhadra","doi":"10.1109/I2MTC50364.2021.9459971","DOIUrl":"https://doi.org/10.1109/I2MTC50364.2021.9459971","url":null,"abstract":"Electroocugraphy (EOG) is a popular method of measuring biopotentials developed across the eyes during eye activities such as eye-blinking, vertical, and horizontal eye-movements. The measured signal is called electrooculogram (EOG) and has been known to be used in behavioral studies, cognitive neuroscience and sleep monitoring. In this work a single channel wearable wireless EOG monitoring system is presented. The entire system is implemented on a double sided polymide flexible substrate. The recording silver electrodes are printed on the bottom side of the substrate whereas the EOG signal recording and transmission circuitries are implemented on the top side of the substrate with printed silver traces. The system is run by a rechargeable battery and uses a BLE 5.0 transceiver for wireless connectivity. Design considerations for the wearable EOG monitoring system are discussed in details. The system performance is validated by successfully monitoring different eye movements with it. Additionally, comparison between the EOG signals observed using the printed silver electrodes and commercial gold electrodes of same dimensions demonstrate that the printed electrodes provide similar EOG signal amplitude like the commercial gold electrodes. With a 5.2 gram mass and flexibility the system has potential for monitoring EOG signal without causing discomfort to the wearer.","PeriodicalId":6772,"journal":{"name":"2021 IEEE International Instrumentation and Measurement Technology Conference (I2MTC)","volume":"17 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2021-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86932065","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}