University of Alabama Repository :: Browsing by Author "Sazonov, Edward"

Browsing by Author "Sazonov, Edward"

Now showing 1 - 20 of 77

Accelerometer-Based Detection of Food Intake in Free-living Individuals
Farooq, Muhammad; Sazonov, Edward; University of Alabama Tuscaloosa
Advanced mobile applications for law enforcement
(University of Alabama Libraries, 2012) York, Matthew; Ricks, Kenneth G.; University of Alabama Tuscaloosa
In this paper, a novel mobile application for law enforcement personnel, AlaCOP Mobile, is presented. The application is designed for the iPhone and iPad platforms, utilizing their intentionally mobile-minded hardware design as a low cost alternative to laptops and their peripherals. Features include the ability to: capture and securely upload photos, audio and video; visualize agent locations in near real-time with interactive maps; and allow access to the National Criminal Information Center (NCIC). In addition, novel rendering and message threading techniques are discussed which utilize the multicore architecture implemented in the more recent versions of the iPhone (iPhone 4s) and iPad (iPad 2).
Ankle Angle Prediction Using a Footwear Pressure Sensor and a Machine Learning Technique
(MDPI, 2021) Choffin, Zachary; Jeong, Nathan; Callihan, Michael; Olmstead, Savannah; Sazonov, Edward; Thakral, Sarah; Getchell, Camilee; Lombardi, Vito; University of Alabama Tuscaloosa
Ankle injuries may adversely increase the risk of injury to the joints of the lower extremity and can lead to various impairments in workplaces. The purpose of this study was to predict the ankle angles by developing a footwear pressure sensor and utilizing a machine learning technique. The footwear sensor was composed of six FSRs (force sensing resistors), a microcontroller and a Bluetooth LE chipset in a flexible substrate. Twenty-six subjects were tested in squat and stoop motions, which are common positions utilized when lifting objects from the floor and pose distinct risks to the lifter. The kNN (k-nearest neighbor) machine learning algorithm was used to create a representative model to predict the ankle angles. For the validation, a commercial IMU (inertial measurement unit) sensor system was used. The results showed that the proposed footwear pressure sensor could predict the ankle angles at more than 93% accuracy for squat and 87% accuracy for stoop motions. This study confirmed that the proposed plantar sensor system is a promising tool for the prediction of ankle angles and thus may be used to prevent potential injuries while lifting objects in workplaces.
Automatic Count of Bites and Chews From Videos of Eating Episodes
(IEEE, 2020) Hossain, Delwar; Ghosh, Tonmoy; Sazonov, Edward; University of Alabama Tuscaloosa
Methods for measuring of eating behavior (known as meal microstructure) often rely on manual annotation of bites, chews, and swallows on meal videos or wearable sensor signals. The manual annotation may be time consuming and erroneous, while wearable sensors may not capture every aspect of eating (e.g. chews only). The aim of this study is to develop a method to detect and count bites and chews automatically from meal videos. The method was developed on a dataset of 28 volunteers consuming unrestricted meals in the laboratory under video observation. First, the faces in the video (regions of interest, ROI) were detected using Faster R-CNN. Second, a pre-trained AlexNet was trained on the detected faces to classify images as a bite/no bite image. Third, the affine optical flow was applied in consecutively detected faces to find the rotational movement of the pixels in the ROIs. The number of chews in a meal video was counted by converting the 2-D images to a 1-D optical flow parameter and finding peaks. The developed bite and chew count algorithm was applied to 84 meal videos collected from 28 volunteers. A mean accuracy (+/- STD) of 85.4% (+/- 6.3%) with respect to manual annotation was obtained for the number of bites and 88.9% (+/- 7.4%) for the number of chews. The proposed method for an automatic bite and chew counting shows promising results that can be used as an alternative solution to manual annotation.
Automatic food intake detection based on swallowing sounds
(Elsevier, 2012) Makeyev, Oleksandr; Lopez-Meyer, Paulo; Schuckers, Stephanie; Besio, Walter; Sazonov, Edward; University of Rhode Island; University of Alabama Tuscaloosa; Clarkson University
This paper presents a novel fully automatic food intake detectior methodology, an important step toward objective monitoring of ingestive behavior. The aim of such monitoring is to improve our understanding of eating behaviors associated with obesity and eating disorders. The proposed methodology consists of two stages. First, acoustic detection of swallowing instances based on mel-scale Fourier spectrum features and classification using support vector machines is performed. Principal component analysis and a smoothing algorithm are used to improve swallowing detection accuracy. Second, the frequency of swallowing is used as a predictor for detection of food intake episodes. The proposed methodology was tested on data collected from 12 subjects with various degrees of adiposity. Average accuracies of >80% and >75% were obtained for intra-subject and inter-subject models correspondingly with a temporal resolution of 30 s. Results obtained on 44.1 h of data with a total of 7305 swallows show that detection accuracies are comparable for obese and lean subjects. They also suggest feasibility of food intake detection based on swallowing sounds and potential of the proposed methodology for automatic monitoring of ingestive behavior. Based on a wearable non-invasive acoustic sensor the proposed methodology may potentially be used in free-living conditions. (C) 2012 Elsevier Ltd. All rights reserved.
Automatic identification of the number of food items in a meal using clustering techniques based on the monitoring of swallowing and chewing
(Elsevier, 2012) Lopez-Meyer, Paulo; Schuckers, Stephanie; Makeyev, Oleksandr; Fontana, Juan M.; Sazonov, Edward; University of Alabama Tuscaloosa; Clarkson University; University of Rhode Island
The number of distinct foods consumed in a meal is of significant clinical concern in the study of obesity and other eating disorders. This paper proposes the use of information contained in chewing and swallowing sequences for meal segmentation by food types. Data collected from experiments of 17 volunteers were analyzed using two different clustering techniques. First, an unsupervised clustering technique, Affinity Propagation (AP), was used to automatically identify the number of segments within a meal. Second, performance of the unsupervised AP method was compared to a supervised learning approach based on Agglomerative Hierarchical Clustering (AHC). While the AP method was able to obtain 90% accuracy in predicting the number of food items, the AHC achieved an accuracy >95%. Experimental results suggest that the proposed models of automatic meal segmentation may be utilized as part of an integral application for objective Monitoring of Ingestive Behavior in free living conditions. (C) 2011 Elsevier Ltd. All rights reserved.
Automatic Ingestion Monitor Version 2 - A Novel Wearable Device for Automatic Food Intake Detection and Passive Capture of Food Images
(IEEE, 2021) Doulah, Abul; Ghosh, Tonmoy; Hossain, Delwar; Imtiaz, Masudul H.; Sazonov, Edward; University of Alabama Tuscaloosa
Use of food image capture and/or wearable sensors for dietary assessment has grown in popularity. Active - methods rely on the user to take an image of each eating episode. "Passive" methods use wearable cameras that continuously capture images. Most of "passively" captured images are not related to food consumption and may present privacy concerns. In this paper, we propose a novel wearable sensor (Automatic Ingestion Monitor. AIM-2) designed to capture images only during automatically detected eating episodes. The capture method was validated on a dataset collected from 30 volunteers in the community wearing the AIM-2 for 24h in pseudo-free-living and 24h in a free-living environment. The AIM-2 was able to detect food intake over 10-second epochs with a (mean and standard deviation) Fl-score of 81.8 +/- 10.1%. The accuracy of eating episode detection was 82.7%. Out of a total of 180,570 images captured, 8,929 (4.9%) images belonged to detected eating episodes. Privacy concerns were assessed by a questionnaire on a scale 1-7. Continuous capture had concern value of 5.0 +/- 1.6 (concerned) while image capture only during food intake had concern value of 1.9 +/- 1.7 (not concerned). Results suggest that AIM-2 can provide accurate detection of food intake, reduce the number of images for analysis and alleviate the privacy concerns of the users.
Automatic Ingestion Monitor: A Novel Wearable Device for Monitoring of Ingestive Behavior
(IEEE, 2014) Fontana, Juan M.; Farooq, Muhammad; Sazonov, Edward; University of Alabama Tuscaloosa; Universidad Nacional Rio Cuarto
Objective monitoring of food intake and ingestive behavior in a free-living environment remains an open problem that has significant implications in study and treatment of obesity and eating disorders. In this paper, a novel wearable sensor system (automatic ingestion monitor, AIM) is presented for objective monitoring of ingestive behavior in free living. The proposed device integrates three sensor modalities that wirelessly interface to a smartphone: a jaw motion sensor, a hand gesture sensor, and an accelerometer. A novel sensor fusion and pattern recognition method was developed for subject-independent food intake recognition. The device and the methodology were validated with data collected from 12 subjects wearing AIM during the course of 24 h in which both the daily activities and the food intake of the subjects were not restricted in any way. Results showed that the system was able to detect food intake with an average accuracy of 89.8%, which suggests that AIM can potentially be used as an instrument to monitor ingestive behavior in free-living individuals.
Automatic Measurement of Chew Count and Chewing Rate during Food Intake
(2016-09-23) Farooq, Muhammad; Sazonov, Edward; University of Alabama Tuscaloosa
Research suggests that there might be a relationship between chew count as well as chewing rate and energy intake. Chewing has been used in wearable sensor systems for the automatic detection of food intake, but little work has been reported on the automatic measurement of chew count or chewing rate. This work presents a method for the automatic quantification of chewing episodes captured by a piezoelectric sensor system. The proposed method was tested on 120 meals from 30 participants using two approaches. In a semi-automatic approach, histogram-based peak detection was used to count the number of chews in manually annotated chewing segments, resulting in a mean absolute error of 10.40% ± 7.03%. In a fully automatic approach, automatic food intake recognition preceded the application of the chew counting algorithm. The sensor signal was divided into 5-s non-overlapping epochs. Leave-one-out cross-validation was used to train a artificial neural network (ANN) to classify epochs as “food intake” or “no intake” with an average F1 score of 91.09%. Chews were counted in epochs classified as food intake with a mean absolute error of 15.01% ± 11.06%. The proposed methods were compared with manual chew counts using an analysis of variance (ANOVA), which showed no statistically significant difference between the two methods. Results suggest that the proposed method can provide objective and automatic quantification of eating behavior in terms of chew counts and chewing rates.
Bandwidth Optimization in 802.15.4 Networks through Evolutionary Slot Assignment
(2009-09) Krishnamurthy, Vidya; Sazonov, Edward; University of Alabama Tuscaloosa
Traditional Wireless Sensor Networks (WSNs) based on carrier sense methods for channel access suffer from reduced bandwidth utilization, increase energy consumptions and latency problems in networks with high traffic. In this work, a novel Evolutionary Slot Assignment (ESA) algorithm has been developed to increase the throughput of large wireless mesh networks with no centralized controller. In the presented scheme, the sensor nodes self-adapt to the traffic patterns of the network by selecting transmission slots using evolutionary learning methods. Each sensor node evolves an independent transmission schedule. Unlike traditional evolutionary methods, fitness evaluation of every node impacts fitness of every other sensor node in the network. The ESA algorithm has been simulated using Network Simulator-2 and compared with the IEEE 802.15.4 CSMA-CA, a Static Slot Assignment (SSA) and a Random Slot Assignment schemes (RSA). Results show a remarkable improvement in the network throughput using the proposed ESA method as opposed to other compared methods.
Body mass index and variability in meal duration and association with rate of eating
(Frontiers, 2022) Simon, Stacey L.; Pan, Zhaoxing; Marden, Tyson; Zhou, Wenru; Ghosh, Tonmoy; Hossain, Delwar; Thomas, J. Graham; McCrory, Megan A.; Sazonov, Edward; Higgins, Janine; University of Colorado Anschutz Medical Campus; University of Alabama Tuscaloosa; Brown University; Boston University
BackgroundA fast rate of eating is associated with a higher risk for obesity but existing studies are limited by reliance on self-report and the consistency of eating rate has not been examined across all meals in a day. The goal of the current analysis was to examine associations between meal duration, rate of eating, and body mass index (BMI) and to assess the variance of meal duration and eating rate across different meals during the day. MethodsUsing an observational cross-sectional study design, non-smoking participants aged 18-45 years (N = 29) consumed all meals (breakfast, lunch, and dinner) on a single day in a pseudo free-living environment. Participants were allowed to choose any food and beverages from a University food court and consume their desired amount with no time restrictions. Weighed food records and a log of meal start and end times, to calculate duration, were obtained by a trained research assistant. Spearman's correlations and multiple linear regressions examined associations between BMI and meal duration and rate of eating. ResultsParticipants were 65% male and 48% white. A shorter meal duration was associated with a higher BMI at breakfast but not lunch or dinner, after adjusting for age and sex (p = 0.03). Faster rate of eating was associated with higher BMI across all meals (p = 0.04) and higher energy intake for all meals (p < 0.001). Intra-individual rates of eating were not significantly different across breakfast, lunch, and dinner (p = 0.96). ConclusionShorter beakfast and a faster rate of eating across all meals were associated with higher BMI in a pseudo free-living environment. An individual's rate of eating is constant over all meals in a day. These data support weight reduction interventions focusing on the rate of eating at all meals throughout the day and provide evidence for specifically directing attention to breakfast eating behaviors.
Cigarette Smoking Detection with an Inertial Sensor and a Smart Lighter
(MDPI, 2019) Senyurek, Volkan; Imtiaz, Masudul; Belsare, Prajakta; Tiffany, Stephen; Sazonov, Edward; University of Alabama Tuscaloosa; State University of New York (SUNY) Buffalo
In recent years, a number of wearable approaches have been introduced for objective monitoring of cigarette smoking based on monitoring of hand gestures, breathing or cigarette lighting events. However, non-reactive, objective and accurate measurement of everyday cigarette consumption in the wild remains a challenge. This study utilizes a wearable sensor system (Personal Automatic Cigarette Tracker 2.0, PACT2.0) and proposes a method that integrates information from an instrumented lighter and a 6-axis Inertial Measurement Unit (IMU) on the wrist for accurate detection of smoking events. The PACT2.0 was utilized in a study of 35 moderate to heavy smokers in both controlled (1.5-2 h) and unconstrained free-living conditions (similar to 24 h). The collected dataset contained approximately 871 h of IMU data, 463 lighting events, and 443 cigarettes. The proposed method identified smoking events from the cigarette lighter data and estimated puff counts by detecting hand-to-mouth gestures (HMG) in the IMU data by a Support Vector Machine (SVM) classifier. The leave-one-subject-out (LOSO) cross-validation on the data from the controlled portion of the study achieved high accuracy and F1-score of smoking event detection and estimation of puff counts (97%/98% and 93%/86%, respectively). The results of validation in free-living demonstrate 84.9% agreement with self-reported cigarettes. These results suggest that an IMU and instrumented lighter may potentially be used in studies of smoking behavior under natural conditions.
A CNN-LSTM neural network for recognition of puffing in smoking episodes using wearable sensors
(Springer Nature, 2020) Senyurek, Volkan Y.; Imtiaz, Masudul H.; Belsare, Prajakta; Tiffany, Stephen; Sazonov, Edward; University of Alabama Tuscaloosa; State University of New York (SUNY) Buffalo
A detailed assessment of smoking behavior under free-living conditions is a key challenge for health behavior research. A number of methods using wearable sensors and puff topography devices have been developed for smoking and individual puff detection. In this paper, we propose a novel algorithm for automatic detection of puffs in smoking episodes by using a combination of Respiratory Inductance Plethysmography and Inertial Measurement Unit sensors. The detection of puffs was performed by using a deep network containing convolutional and recurrent neural networks. Convolutional neural networks (CNN) were utilized to automate feature learning from raw sensor streams. Long Short Term Memory (LSTM) network layers were utilized to obtain the temporal dynamics of sensor signals and classify sequence of time segmented sensor streams. An evaluation was performed by using a large, challenging dataset containing 467 smoking events from 40 participants under free-living conditions. The proposed approach achieved an F1-score of 78% in leave-one-subject-out cross-validation. The results suggest that CNN-LSTM based neural network architecture sufficiently detect puffing episodes in free-living condition. The proposed model be used as a detection tool for smoking cessation programs and scientific research.
Cognitive heterogeneous sensor platform for human biometric and activity pattern analysis
(University of Alabama Libraries, 2016) Ma, Rui; Hu, Fei; University of Alabama Tuscaloosa
Human biometric and activities can be acquired from their motions and postures. Conventional video cameras have many limitations. In this dissertation research our goal is to develop sensor hardware as well as machine learning algorithms/software to achieve motion recognition with low communication bandwidth and processing complexity. We have designed the wireless sensing systems targeting the following two applications: (1) Binary compressive sensing (CS) systems for smart home. The binary sensing systems are designed to obtain the geometric information of human motions for the recognition of indoor activities. CS theory is used in the design of sensor sampling structure. We employ Buffon's Needle model of integral geometry to describe human gait changes, and use Hidden Markov Model (HMM) to extract the statistic features for motion recognition. Pyroelectric Infrared (PIR) sensors are used for human gait recognition. Both passive PIR sensor network and active PIR sensors are developed to detect moving and static thermal targets respectively. Laser sensors are used for gait disorder recognition with metrics of symmetry, coordination, and balance. Fiber optic sensors have been deployed and encoded on the ground for multiple human subject location based on Low density parity check (LDPC) codes. (2) Motion capture system for rehabilitation training. Many patients who suffer from the paralysis can recover body functions by taking appropriate rehabilitation training. This study aims to develop a home-oriented cyber-physical system (CPS) to help the patients improve their motion ability via physical training. The system provides quantitative evaluation for the performed motions. The measures evaluated by the system include the motion style of the legs, the periodicity of the foot trajectory, and the foot balance level. The motions of legs and feet are recorded by the thermal camera, and the plantar pressure is measured by the insole pressure sensors. We have developed algorithms to extract the leg skeletons from the thermal images, and to implement motion auto-segmentation, recognition and analysis for the above mentioned measures. This dissertation explores the frontier of intelligent sensing systems for human motion recognition. We have conducted many experiments to demonstrate the efficiency and capability of our methods and systems.
A Comparative Review of Footwear-Based Wearable Systems
(2016-08-10) Hegde, Nagaraj; Bries, Matthew; Sazonov, Edward; University of Alabama Tuscaloosa
Footwear is an integral part of daily life. Embedding sensors and electronics in footwear for various different applications started more than two decades ago. This review article summarizes the developments in the field of footwear-based wearable sensors and systems. The electronics, sensing technologies, data transmission, and data processing methodologies of such wearable systems are all principally dependent on the target application. Hence, the article describes key application scenarios utilizing footwear-based systems with critical discussion on their merits. The reviewed application scenarios include gait monitoring, plantar pressure measurement, posture and activity classification, body weight and energy expenditure estimation, biofeedback, navigation, and fall risk applications. In addition, energy harvesting from the footwear is also considered for review. The article also attempts to shed light on some of the most recent developments in the field along with the future work required to advance the field.
Comparison of Wearable Sensors for Estimation of Chewing Strength
(IEEE, 2020) Hossain, Delwar; Imtiaz, Masudul Haider; Sazonov, Edward; University of Alabama Tuscaloosa
This paper presents wearable sensors for detecting differences in chewing strength while eating foods with different hardness (carrot as a hard, apple as moderate and banana as soft food). Four wearable sensor systems were evaluated. They were: (1) a gas pressure sensor measuring changes in ear pressure proportional to ear canal deformation during chewing, (2) a flexible, curved bend sensor attached to right temple of eyeglass measuring the contraction of the temporalis muscle, (3) a piezoelectric strain sensor placed on the temporalis muscle, and (4) an electromyography sensor with electrodes placed on the temporalis muscle. Data from 15 participants, wearing all four sensors at once were collected. Each participant took and consumed 10 bites of carrot, apple, and banana. The hardness of foods were measured by a food penetrometer. Single-factor ANOVA found a significant effect of food hardness on the standard deviation of signals for all four sensors (P-value <.001). Tukey's multiple comparison test with 5% significance level confirmed that the mean of the standard deviations were significantly different for the provided test foods for all four sensors. Results of this study indicate that the wearable sensors may potentially be used for measuring chewing strength and assessing the food hardness.
Computation of Cigarette Smoke Exposure Metrics From Breathing
(IEEE, 2020) Belsare, Prajakta; Senyurek, Volkan Yusuf; Imtiaz, Masudul H.; Tiffany, Stephen; Sazonov, Edward; University of Alabama Tuscaloosa; State University of New York (SUNY) Buffalo
Traditional metrics of smoke exposure in cigarette smokers are derived either from self-report, biomarkers, or puff topography. Methods involving biomarkers measure concentrations of nicotine, nicotine metabolites, or carbon monoxide. Puff-topography methods employ portable instruments to measure puff count, puff volume, puff duration, and inter-puff interval. In this article, we propose smoke exposure metrics calculated from the breathing signal and describe a novel algorithm for the computation of these metrics. The Personal Automatic Cigarette Tracker v2 (PACT-2) sensors, puff topography devices (CReSS), and video observation were used in a study of 38 moderate to heavy smokers in a controlled environment. Parameters of smoke inhalation including the start and end of each puff, inhale and exhale cycle, and smoke holding were computed from the breathing signal. From these, the traditional metrics of puff duration, inhale-exhale cycle duration, smoke holding duration, inter-puff interval, and novel Respiratory Smoke Exposure Metrics (RSEMs) such as inhale-exhale cycle volume, and inhale-exhale volume over time were calculated. The proposed RSEM algorithm to extract smoke exposure metrics named generated interclass correlations (ICCs) of 0.85 and 0.87 and Pearson's correlations of 0.97 and 0.77 with video observation and CReSS, respectively, for puff duration. Similarly, for the inhale-exhale duration, an ICC of 0.84 and Pearson's correlation of 0.81 was obtained with video observation. The RSEMs provided measures previously unavailable in research that are proportional to the depth and duration of smoke inhalation. The results suggest that the breathing signal may be used to compute smoke exposure metrics.
Damage detection and sensor placement optimization in composite structures
(University of Alabama Libraries, 2012) Zheng, Hao; Roy, Samit; University of Alabama Tuscaloosa
Structural health monitoring, damage identification method and sensor placement optimization for carbon fiber reinforced polymer (CFRP) composite beam were studied in this thesis. In this work, different methodologies were investigated for the damage detection process to enhance the use of current structural health monitoring systems by identifying the optimal sensor placement. Carbon fiber reinforced polymer composite materials were fabricated and the fabrication process based on vacuum assisted resin transfer molding (VARTM) is briefly introduced. Numerical analysis using finite element method was subsequently performed for a composite beam based on the material properties determined by performing experimental material characterization tests. Three benchmarking tests with different types of elements were performed to verify the best method for modeling the composite panel. Moreover, shear lag analysis was also presented to model an embedded crack in the composite panel which would be used in damage detection and optimization process. Based on the finite element analysis and static strain data extracted, a comparative study on two damage detection algorithms based on artificial neural network (ANN) and support vector machine (SVM) is presented. The viability of these two methods was demonstrated by analysis of the numerical model of composite beam with a crack embedded in it and the performance for each algorithm is also presented with different number of sensors and different noise levels. Two experiments are presented for the performance evaluation of damage detection and identification. To identify the optimal locations of sensors in the optimization process, a statistical probability based method using the combination of artificial neural networks and evolutionary strategy were developed to increase the detection rate of damage in a structure. The proposed method was able to efficiently increase the detection accuracy compared with a uniform distribution of sensors for a composite beam that was damaged in different locations. The finite element model of the composite coupon was used as a representation of the real structure. Static strain data from finite element simulation was extracted with different damage scenarios and used as feature vector for the classification process. Based on the performance of the classification for a given sensor configuration, updated sensor locations would be selected by changing the coordinates of these sensor locations using strategy parameters. The viability of this method was demonstrated by conducting different examples and significant number of simulations was performed to check the repeatability of the algorithm.
Detection of Food Intake Sensor's Wear Compliance in Free-Living
(IEEE, 2021) Ghosh, Tonmoy; Hossain, Delwar; Sazonov, Edward; University of Alabama Tuscaloosa
Objective detection of periods of wear and non-wear is critical for human studies that rely on information from wearable sensors, such as food intake sensors. In this paper, we present a novel method of compliance detection on the example of the Automatic Ingestion Monitor v2 (AIM-2) sensor, containing a tri-axial accelerometer, a still camera, and a chewing sensor. The method was developed and validated using data from a study of 30 participants aged 18-39, each wearing the AIM-2 for two days (a day in pseudo-free-living and a day in free-living). Four types of wear compliance were analyzed: 'normal-wear', 'non-compliant-wear', 'non-wear-carried', and 'non-wear-stationary'. The ground truth of those four types of compliance was obtained by reviewing the images of the egocentric camera. The features for compliance detection were the standard deviation of acceleration, average pitch, and roll angles, and mean square error of two consecutive images. These were used to train three random forest classifiers 1) accelerometer-based, 2) image-based, and 3) combined accelerometer and image-based. Satisfactory wear compliance measurement accuracy was obtained using the combined classifier (89.24%) on leave one subject out cross-validation. The average duration of compliant wear in the study was 9h with a standard deviation of 2h or 70.96% of total on-time. This method can be used to calculate the wear and non-wear time of AIM-2, and potentially be extended to other devices. The study also included assessments of sensor burden and privacy concerns. The survey results suggest recommendations that may be used to increase wear compliance.
Determination of Multi-Mode Component Failure and Time-To-Failure with Machine Learning and Deep Learning
(University of Alabama Libraries, 2023) O'Donnell, John Lewis; Yoon, Hwan-Sik
A hybrid deep learning and machine learning approach for both failure mode classification and time-to-failure prediction is proposed in this dissertation, with a focus on a multi-mode failure regime where the state of health of components can vary. To validate the potential performance of the proposed approach, a vehicle's leaking hydraulic suspension system is simulated via a quarter car model as a proof of concept. Next, the quarter car model is expanded to include a model of a failing engine mount. The dynamic data from these models is employed to train a NARX net with the health condition and degradation rate as an output. The predictive capabilities of the NARX given this data is significant, validating the proposed approach. To develop the hybrid approach, a four-cylinder diesel engine with EGR and VGT is simulated over a prescribed operational range for four failure types. A multi-label CNN model is utilized to classify which multi-mode failure modes are occurring while hiding health condition information. The approach resulted in significant performance in classifying the failure modes. This data is then employed in regression models to determine the health condition of various components. It was determined that utilizing this data and previous state information with ensemble tree methods and neural networks results in predictive accuracy with less than 3% normalized root mean square error. Finally, a NARX net approach for determining the degradation rate and time-to-failure of a component utilizing this health condition information is verified. A discussion on how these approaches can be combined to create a hybrid predictive model that determines the engine's probable failing time is presented. Based on the results from each stage of the hybrid model, it is expected that this approach can provide significant predictive performance in monitoring the health of a diesel engine as well as any similar system with comparable failure modes.

Browsing by Author "Sazonov, Edward"

Results Per Page

Sort Options