Recognition of Abnormal Chest Compression Depth Using One-Dimensional Convolutional Neural Networks

When the displacement of an object is evaluated using sensor data, its movement back to the starting point can be used to correct the measurement error of the sensor. In medicine, the movements of chest compressions also involve a reciprocating movement back to the starting point. The traditional method of evaluating the effects of chest compression depth (CCD) is to use an acceleration sensor or gyroscope to obtain chest compression movement data; from these data, the displacement value can be calculated and the CCD effect evaluated. However, this evaluation procedure suffers from sensor errors and environmental interference, limiting its applicability. Our objective is to reduce the auxiliary computing devices employed for CCD effectiveness evaluation and improve the accuracy of the evaluation results. To this end, we propose a one-dimensional convolutional neural network (1D-CNN) classification method. First, we use the chest compression evaluation criterion to classify the pre-collected sensor signal data, from which the proposed 1D-CNN model learns classification features. After training, the model is used to classify and evaluate sensor signal data instead of distance measurements; this effectively avoids the influence of pressure occlusion and electromagnetic waves. We collect and label 937 valid CCD results from an emergency care simulator. In addition, the proposed 1D-CNN structure is experimentally evaluated and compared against other CNN models and support vector machines. The results show that after sufficient training, the proposed 1D-CNN model can recognize the CCD results with an accuracy rate of more than 95%. The execution time suggests that the model balances accuracy and hardware requirements and can be embedded in portable devices.

Download Full-text

Real-time optimization using gradient adaptive selection and classification from infrared sensors measurement for esterification oleic acid with glycerol

International Journal of Intelligent Computing and Cybernetics ◽

10.1108/ijicc-06-2016-0022 ◽

2017 ◽

Vol 10 (2) ◽

pp. 130-144 ◽

Cited By ~ 1

Author(s):

Iwan Aang Soenandi ◽

Taufik Djatna ◽

Ani Suryani ◽

Irzaman Irzaman

Keyword(s):

Real Time ◽

Sensor Data ◽

Necessary Condition ◽

Support Vector ◽

Adaptive Selection ◽

Content Type ◽

The Real ◽

Time Optimization ◽

Starting Point ◽

Real Time Optimization

Purpose The production of glycerol derivatives by the esterification process is subject to many constraints related to the yield of the production target and the lack of process efficiency. An accurate monitoring and controlling of the process can improve production yield and efficiency. The purpose of this paper is to propose a real-time optimization (RTO) using gradient adaptive selection and classification from infrared sensor measurement to cover various disturbances and uncertainties in the reactor. Design/methodology/approach The integration of the esterification process optimization using self-optimization (SO) was developed with classification process was combined with necessary condition optimum (NCO) as gradient adaptive selection, supported with laboratory scaled medium wavelength infrared (mid-IR) sensors, and measured the proposed optimization system indicator in the batch process. Business Process Modeling and Notation (BPMN 2.0) was built to describe the tasks of SO workflow in collaboration with NCO as an abstraction for the conceptual phase. Next, Stateflow modeling was deployed to simulate the three states of gradient-based adaptive control combined with support vector machine (SVM) classification and Arduino microcontroller for implementation. Findings This new method shows that the real-time optimization responsiveness of control increased product yield up to 13 percent, lower error measurement with percentage error 1.11 percent, reduced the process duration up to 22 minutes, with an effective range of stirrer rotation set between 300 and 400 rpm and final temperature between 200 and 210°C which was more efficient, as it consumed less energy. Research limitations/implications In this research the authors just have an experiment for the esterification process using glycerol, but as a development concept of RTO, it would be possible to apply for another chemical reaction or system. Practical implications This research introduces new development of an RTO approach to optimal control and as such marks the starting point for more research of its properties. As the methodology is generic, it can be applied to different optimization problems for a batch system in chemical industries. Originality/value The paper presented is original as it presents the first application of adaptive selection based on the gradient value of mid-IR sensor data, applied to the real-time determining control state by classification with the SVM algorithm for esterification process control to increase the efficiency.

Download Full-text

A Classification Method for Judging the Depth of Chest Compression Based on CNN

10.21203/rs.3.rs-38347/v1 ◽

2020 ◽

Author(s):

Liang Zhao ◽

Yu Bao ◽

Ruidong Ye ◽

Aijuan Zhang ◽

Yu Zhang

Keyword(s):

Chest Compression ◽

Classification Method ◽

Accuracy Rate ◽

One Dimensional ◽

Acceleration Signal ◽

Signal Waveform ◽

Wave Interference ◽

Starting Point ◽

Sample Data ◽

Two Stages

Abstract The displacement can be calculated based on the integrated value of the acceleration signal waveform obtained by the acceleration sensor or gyroscope. However, this method is not effective in accurate measurement. Although some studies have improved the method of calculating accurate distance values by overcoming the effects of sensor noise or integration delay, the evaluation is still affected by sensor accuracy and environment. However, there are some special displacements, such as the chest compression. The displacement is a reciprocating motion and will return to the starting point again. Therefore, the acceleration waveform changes have obvious characteristics in the two stages from moving to the equilibrium position and returning to the starting point. Therefore, we propose an embedded classification method based on one-dimensional Convolutional Neural Network (CNN), which directly learns from the data of chest compressions and performs the signal formed by the Classification, distinguish the signal waveform under the standard pressing distance, so as to replace the calculation of distance measurement, and is not affected by factors such as pressure occlusion and electromagnetic wave interference, and has certain practical value on site. We tagged compressions and collected data from the simulator. The experiment evaluates the proposed CNN structure, and compares the classification results of the sample data with several CNN networks and SVMs with different structures in the literature. The results show that with sufficient training, the proposed 1D-CNN method can achieve an accuracy rate of more than 95%, and balances the accuracy rate and the hardware requirements.

Download Full-text

Binary Spectrum Feature for Improved Classiﬁer Performance

10.36227/techrxiv.12993122 ◽

2020 ◽

Author(s):

Nalika Ulapane ◽

Karthick Thiyagarajan ◽

sarath kodagoda

Keyword(s):

Machine Learning ◽

Classification Performance ◽

Feature Reduction ◽

Sensor Data ◽

Machine Learning Techniques ◽

Support Vector ◽

Svm Classifier ◽

Monitoring Task ◽

Classifier Performance ◽

Spectrum Feature

<div>Classiﬁcation has become a vital task in modern machine learning and Artiﬁcial Intelligence applications, including smart sensing. Numerous machine learning techniques are available to perform classiﬁcation. Similarly, numerous practices, such as feature selection (i.e., selection of a subset of descriptor variables that optimally describe the output), are available to improve classiﬁer performance. In this paper, we consider the case of a given supervised learning classiﬁcation task that has to be performed making use of continuous-valued features. It is assumed that an optimal subset of features has already been selected. Therefore, no further feature reduction, or feature addition, is to be carried out. Then, we attempt to improve the classiﬁcation performance by passing the given feature set through a transformation that produces a new feature set which we have named the “Binary Spectrum”. Via a case study example done on some Pulsed Eddy Current sensor data captured from an infrastructure monitoring task, we demonstrate how the classiﬁcation accuracy of a Support Vector Machine (SVM) classiﬁer increases through the use of this Binary Spectrum feature, indicating the feature transformation’s potential for broader usage.</div><div><br></div>

Download Full-text

Ablation Analysis to Select Wearable Sensors for Classifying Standing, Walking, and Running

Sensors ◽

10.3390/s21010194 ◽

2020 ◽

Vol 21 (1) ◽

pp. 194

Author(s):

Sarah Gonzalez ◽

Paul Stegall ◽

Harvey Edwards ◽

Leia Stirling ◽

Ho Chit Siu

Keyword(s):

Activity Recognition ◽

Principal Components ◽

Classification Accuracy ◽

Wearable Sensors ◽

Sensor Data ◽

Machine Learning Techniques ◽

Support Vector ◽

Learning Techniques ◽

Measurement Units ◽

The Difference

The field of human activity recognition (HAR) often utilizes wearable sensors and machine learning techniques in order to identify the actions of the subject. This paper considers the activity recognition of walking and running while using a support vector machine (SVM) that was trained on principal components derived from wearable sensor data. An ablation analysis is performed in order to select the subset of sensors that yield the highest classification accuracy. The paper also compares principal components across trials to inform the similarity of the trials. Five subjects were instructed to perform standing, walking, running, and sprinting on a self-paced treadmill, and the data were recorded while using surface electromyography sensors (sEMGs), inertial measurement units (IMUs), and force plates. When all of the sensors were included, the SVM had over 90% classification accuracy using only the first three principal components of the data with the classes of stand, walk, and run/sprint (combined run and sprint class). It was found that sensors that were placed only on the lower leg produce higher accuracies than sensors placed on the upper leg. There was a small decrease in accuracy when the force plates are ablated, but the difference may not be operationally relevant. Using only accelerometers without sEMGs was shown to decrease the accuracy of the SVM.

Download Full-text

Interpretable deep learning for the remote characterisation of ambulation in multiple sclerosis using smartphones

Scientific Reports ◽

10.1038/s41598-021-92776-x ◽

2021 ◽

Vol 11 (1) ◽

Author(s):

Andrew P. Creagh ◽

Florian Lipsmeier ◽

Michael Lindemann ◽

Maarten De Vos

Keyword(s):

Multiple Sclerosis ◽

Deep Learning ◽

Inertial Sensor ◽

Heterogeneous Data ◽

Fine Tuning ◽

Sensor Data ◽

Support Vector ◽

Deep Convolutional Neural Networks ◽

Healthcare Applications ◽

Feature Based

AbstractThe emergence of digital technologies such as smartphones in healthcare applications have demonstrated the possibility of developing rich, continuous, and objective measures of multiple sclerosis (MS) disability that can be administered remotely and out-of-clinic. Deep Convolutional Neural Networks (DCNN) may capture a richer representation of healthy and MS-related ambulatory characteristics from the raw smartphone-based inertial sensor data than standard feature-based methodologies. To overcome the typical limitations associated with remotely generated health data, such as low subject numbers, sparsity, and heterogeneous data, a transfer learning (TL) model from similar large open-source datasets was proposed. Our TL framework leveraged the ambulatory information learned on human activity recognition (HAR) tasks collected from wearable smartphone sensor data. It was demonstrated that fine-tuning TL DCNN HAR models towards MS disease recognition tasks outperformed previous Support Vector Machine (SVM) feature-based methods, as well as DCNN models trained end-to-end, by upwards of 8–15%. A lack of transparency of “black-box” deep networks remains one of the largest stumbling blocks to the wider acceptance of deep learning for clinical applications. Ensuing work therefore aimed to visualise DCNN decisions attributed by relevance heatmaps using Layer-Wise Relevance Propagation (LRP). Through the LRP framework, the patterns captured from smartphone-based inertial sensor data that were reflective of those who are healthy versus people with MS (PwMS) could begin to be established and understood. Interpretations suggested that cadence-based measures, gait speed, and ambulation-related signal perturbations were distinct characteristics that distinguished MS disability from healthy participants. Robust and interpretable outcomes, generated from high-frequency out-of-clinic assessments, could greatly augment the current in-clinic assessment picture for PwMS, to inform better disease management techniques, and enable the development of better therapeutic interventions.

Download Full-text

Effect of the Use of Metronome Feedback on the Quality of Pediatric Cardiopulmonary Resuscitation

International Journal of Environmental Research and Public Health ◽

10.3390/ijerph18158087 ◽

2021 ◽

Vol 18 (15) ◽

pp. 8087

Author(s):

Dongjun Yang ◽

Wongyu Lee ◽

Jehyeok Oh

Keyword(s):

Cardiopulmonary Resuscitation ◽

Chest Compression ◽

Healthcare Providers ◽

Compression Rate ◽

Audio Feedback ◽

Simple Method ◽

Compression Depth ◽

Pediatric Resuscitation ◽

Cpr Quality

Although the use of audio feedback with devices such as metronomes during cardiopulmonary resuscitation (CPR) is a simple method for improving CPR quality, its effect on the quality of pediatric CPR has not been adequately evaluated. In this study, 64 healthcare providers performed CPR (with one- and two-handed chest compression (OHCC and THCC, respectively)) on a pediatric resuscitation manikin (Resusci Junior QCPR), with and without audio feedback using a metronome (110 beats/min). CPR was performed on the floor, with a compression-to-ventilation ratio of 30:2. For both OHCC and THCC, the rate of achievement of an adequate compression rate during CPR was significantly higher when performed with metronome feedback than that without metronome feedback (CPR with vs. without feedback: 100.0% (99.0, 100.0) vs. 94.0% (69.0, 99.0), p < 0.001, for OHCC, and 100.0% (98.5, 100.0) vs. 91.0% (34.5, 98.5), p < 0.001, for THCC). However, the rate of achievement of adequate compression depth during the CPR performed was significantly higher without metronome feedback than that with metronome feedback (CPR with vs. without feedback: 95.0% (23.5, 99.5) vs. 98.5% (77.5, 100.0), p = 0.004, for OHCC, and 99.0% (95.5, 100.0) vs. 100.0% (99.0, 100.0), p = 0.003, for THCC). Although metronome feedback during pediatric CPR could increase the rate of achievement of adequate compression rates, it could cause decreased compression depth.

Download Full-text

Bipartite Network of Interest (BNOI): Extending Co-Word Network with Interest of Researchers Using Sensor Data and Corresponding Applications as an Example

Sensors ◽

10.3390/s21051668 ◽

2021 ◽

Vol 21 (5) ◽

pp. 1668

Author(s):

Zongming Dai ◽

Kai Hu ◽

Jie Xie ◽

Shengyu Shen ◽

Jie Zheng ◽

...

Keyword(s):

Feature Fusion ◽

Extraction Methods ◽

Knowledge Network ◽

Sensor Data ◽

Support Vector ◽

Bipartite Network ◽

Classification Models ◽

Text Data ◽

Domain Experts ◽

Problems And Solutions

Traditional co-word networks do not discriminate keywords of researcher interest from general keywords. Co-word networks are therefore often too general to provide knowledge if interest to domain experts. Inspired by the recent work that uses an automatic method to identify the questions of interest to researchers like “problems” and “solutions”, we try to answer a similar question “what sensors can be used for what kind of applications”, which is great interest in sensor- related fields. By generalizing the specific questions as “questions of interest”, we built a knowledge network considering researcher interest, called bipartite network of interest (BNOI). Different from a co-word approaches using accurate keywords from a list, BNOI uses classification models to find possible entities of interest. A total of nine feature extraction methods including N-grams, Word2Vec, BERT, etc. were used to extract features to train the classification models, including naïve Bayes (NB), support vector machines (SVM) and logistic regression (LR). In addition, a multi-feature fusion strategy and a voting principle (VP) method are applied to assemble the capability of the features and the classification models. Using the abstract text data of 350 remote sensing articles, features are extracted and the models trained. The experiment results show that after removing the biased words and using the ten-fold cross-validation method, the F-measure of “sensors” and “applications” are 93.2% and 85.5%, respectively. It is thus demonstrated that researcher questions of interest can be better answered by the constructed BNOI based on classification results, comparedwith the traditional co-word network approach.

Download Full-text