Mechatronics Systems Engineering, School of

Receive updates for this collection

Validation of Accuracy of SVM-Based Fall Detection System Using Real-World Fall and Non-Fall Datasets

Peer reviewed: 
Yes, item is peer reviewed.
Date created: 
2017-07-05
Abstract: 

Falls are a major cause of injuries and deaths in older adults. Even when no injury occurs, about half of all older adults who fall are unable to get up without assistance. The extended period of lying on the floor often leads to medical complications, including muscle damage, dehydration, anxiety and fear of falling. Wearable sensor systems incorporating accelerometers and/or gyroscopes are designed to prevent long lies by automatically detecting and alerting care providers to the occurrence of a fall. Research groups have reported up to 100% accuracy in detecting falls in experimental settings. However, there is a lack of studies examining accuracy in the real-world setting. In this study, we examined the accuracy of a fall detection system based on real-world fall and non-fall data sets. Five young adults and 19 older adults went about their daily activities while wearing tri-axial accelerometers. Older adults experienced 10 unanticipated falls during the data collection. Approximately 400 hours of activities of daily living were recorded. We employed a machine learning algorithm, Support Vector Machine (SVM) classifier, to identify falls and non-fall events. We found that our system was able to detect 8 out of the 10 falls in older adults using signals from a single accelerometer (waist or sternum). Furthermore, our system did not report any false alarm during approximately 28.5 hours of recorded data from young adults. However, with older adults, the false positive rate among individuals ranged from 0 to 0.3 false alarms per hour. While our system showed higher fall detection and substantially lower false positive rate than the existing fall detection systems, there is a need for continuous efforts to collect real-world data within the target population to perform fall validation studies for fall detection systems on bigger real-world fall and non-fall datasets.

Document type: 
Article
File(s): 

Interface Properties of the Partially Oxidized Pt(111) Surface Using Hybrid DFT–Solvation Models

Peer reviewed: 
Yes, item is peer reviewed.
Date created: 
2019-10-25
Abstract: 

This article reports a theoretical–computational effort to model the interface between an oxidized platinum surface and aqueous electrolyte. It strives to account for the impact of the electrode potential, formation of surface-bound oxygen species, orientational ordering of near-surface solvent molecules, and metal surface charging on the potential profile along the normal direction. The computational scheme is based on the DFT/ESM-RISM method to simulate the charged Pt(111) surface with varying number of oxygen adatoms in acidic solution. This hybrid solvation method is known to qualitatively reproduce bulk metal properties like the work function. However, the presented calculations reveal that vital interface properties such as the electrostatic potential at the outer Helmholtz plane are highly sensitive to the position of the metal surface slab relative to the DFT-RISM boundary region. Shifting the relative position of the slab also affects the free energy of the system. It follows that there is an optimal distance for the first solvent layer within the ESM-RISM framework, which could be found by optimizing the position of the frozen Pt(111) slab. As it stands, manual sampling of the position of the slab is impractical and betrays the self-consistency of the method. Based on this understanding, we propose the implementation of a free energy optimization scheme of the relative position of the slab in the DFT-RISM boundary region. This optimization scheme could considerably increase the applicability of the hybrid method.

Document type: 
Article

Localized Mechanical Actuation using pn Junctions

Peer reviewed: 
Yes, item is peer reviewed.
Date created: 
2016-10-16
Abstract: 

We are reporting on the fabrication and characterization of microscale electromechanical actuators driven by the internal forces induced within the depletion region of a typical pn junction. Depletion region actuators operate based on the modulation of the interactions of the internal electric field and the net space charge within the depletion region of a pn junction by an external potential. In terms of performance, depletion region actuators fall between electrostatic actuators, where a physical gap separates the charges on two electrodes, and piezoelectric actuators, where the separation between the charges is on the order of lattice constants of the material. An analytic model of depletion region actuator response to an applied potential is developed and verified experimentally. The prototype micro-mechanical device utilized the local stresses produced by the depletion region actuators to generate mechanical vibrations at frequencies far below the resonance frequencies of the structure. A laser Doppler vibrometer was used to measure and compare the displacements and vibration patterns caused by the depletion region and electrostatic actuators. Utilizing depletion region actuators neither requires etching of narrow gaps, which is technically challenging nor is there a need for introducing piezoelectric materials into the fabrication process flow. The simple operating principle and the possibility of exploiting the technique for various optimized linear or nonlinear actuation at small scales provide opportunities for precise electro-mechanical transduction for micro- and nano-mechanical devices. These actuators are therefore suited for the co-fabrication of micro- and nano-mechanical systems and microelectronic circuits. Additionally, the produced strains depend only on the depletion region specifications and the excitation voltage and do not scale with device dimensions. As such, depletion region actuators can be candidates for efficient nanoscale electromechanical actuation.

Document type: 
Article
File(s): 

Improved Capacitive Proximity Detection for Conductive Objects through Target Profile Estimation

Peer reviewed: 
Yes, item is peer reviewed.
Date created: 
2019-09-08
Abstract: 

The accuracy of a capacitive proximity sensor is affected by various factors, including the geometry and composition of the nearby object. The quantitative regression models that are used to seek out the relationship between the measured capacitances and distances to objects are highly dependent on the geometrical properties of the objects. Consequently, the application of capacitive proximity sensors has been mainly limited to detection of objects rather than estimation of distances to them. This paper presents a capacitive proximity sensing system for the detection of metallic objects with improved accuracy based on target profile estimation. The presented approach alleviates large errors in distance estimation by implementing a classifier to recognize the surface profiles before using a suitable regression model to estimate the distance. The sensing system features an electrode matrix that is configured to sweep a series of inner-connection patterns and produce features for profile classification. The performance of the sensing modalities is experimentally assessed with an industrial robot. Two-term exponential regression models provide a high degree of fittings for an object whose shape is known. Recognizing the shape of the object improved the regression models and reduced the close-distance measurement error by a factor of five compared to methods that did not take the geometry into account. The breakthroughs made through this work will make capacitive sensing a viable low-cost alternative to existing technologies for proximity detection in robotics and other fields.

Document type: 
Article
File(s): 

SLAM in Dynamic Environments: A Deep Learning Approach for Moving Object Tracking Using ML-RANSAC Algorithm

Peer reviewed: 
Yes, item is peer reviewed.
Date created: 
2019-08-26
Abstract: 

The important problem of Simultaneous Localization and Mapping (SLAM) in dynamic environments is less studied than the counterpart problem in static settings. In this paper, we present a solution for the feature-based SLAM problem in dynamic environments. We propose an algorithm that integrates SLAM with multi-target tracking (SLAMMTT) using a robust feature-tracking algorithm for dynamic environments. A novel implementation of RANdomSAmple Consensus (RANSAC) method referred to as multilevel-RANSAC (ML-RANSAC) within the Extended Kalman Filter (EKF) framework is applied for multi-target tracking (MTT). We also apply machine learning to detect features from the input data and to distinguish moving from stationary objects. The data stream from LIDAR and vision sensors are fused in real-time to detect objects and depth information. A practical experiment is designed to verify the performance of the algorithm in a dynamic environment. The unique feature of this algorithm is its ability to maintain tracking of features even when the observations are intermittent whereby many reported algorithms fail in such situations. Experimental validation indicates that the algorithm is able to perform consistent estimates in a fast and robust manner suggesting its feasibility for real-time applications.

Document type: 
Article
File(s): 

Controlling a Motorized Orthosis to Follow Elbow Volitional Movement: Tests with Individuals with Pathological Tremor

Peer reviewed: 
Yes, item is peer reviewed.
Date created: 
2019-02-01
Abstract: 

Background:  There is a need for alternative treatment options for tremor patients who do not respond well to medications or surgery, either due to side effects or poor efficacy, or that are excluded from surgery. The study aims to evaluate feasibility of a voluntary-driven, speed-controlled tremor rejection approach with individuals with pathological tremor. The suppression approach was investigated using a robotic orthosis for suppression of elbow tremor. Importantly, the study emphasizes the performance in relation to the voluntary motion.

Methods:  Nine participants with either Essential Tremor (ET) or Parkinson’s disease (PD) were recruited and tested off medication. The participants performed computerized pursuit tracking tasks following a sinusoid and a random target, both with and without the suppressive orthosis. The impact of the Tremor Suppression Orthosis (TSO) at the tremor and voluntary frequencies was determined by the relative power change calculated from the Power Spectral Density (PSD). Voluntary motion was, in addition, assessed by position and velocity tracking errors.

Results:  The suppressive orthosis resulted in a 94.4% mean power reduction of the tremor (p < 0.001) – a substantial improvement over reports in the literature. As for the impact to the voluntary motion, paired difference tests revealed no statistical effect of the TSO on the relative power change (p = 0.346) and velocity tracking error (p = 0.283). A marginal effect was observed for the position tracking error (p = 0.05). The interaction torque with the robotic orthosis was small (0.62 Nm) when compared to the maximum voluntary torque that can be exerted by adult individuals at the elbow joint.

Conclusions:  Two key contributions of this work are first, a recently proposed approach is evaluated with individuals with tremor demonstrating high levels of tremor suppression; second, the impact of the approach to the voluntary motion is analyzed comprehensively, showing limited inhibition. This study also seeks to address a gap in studies with individuals with tremor where the impact of engineering solutions on voluntary motion is unreported. This study demonstrates feasibility of the wearable technology as an effective treatment that removes tremor with limited impediment to intentional motion. The goal for such wearable technology is to help individuals with pathological tremor regain independence in activities affected by the tremor condition. Further investigations are needed to validate the technology.

Document type: 
Article
File(s): 

An Adaptive Augmented Vision-based Ellipsoidal SLAM for Indoor Environments

Peer reviewed: 
Yes, item is peer reviewed.
Date created: 
2019-06-21
Abstract: 

In this paper, the problem of Simultaneous Localization And Mapping (SLAM) is addressed via a novel augmented landmark vision-based ellipsoidal SLAM. The algorithm is implemented on a NAO humanoid robot and is tested in an indoor environment. The main feature of the system is the implementation of SLAM with a monocular vision system. Distinguished landmarks referred to as NAOmarks are employed to localize the robot via its monocular vision system. We henceforth introduce the notion of robotic augmented reality (RAR) and present a monocular Extended Kalman Filter (EKF)/ellipsoidal SLAM in order to improve the performance and alleviate the computational effort, to provide landmark identification, and to simplify the data association problem. The proposed SLAM algorithm is implemented in real-time to further calibrate the ellipsoidal SLAM parameters, noise bounding, and to improve its overall accuracy. The augmented EKF/ellipsoidal SLAM algorithms are compared with the regular EKF/ellipsoidal SLAM methods and the merits of each algorithm is also discussed in the paper. The real-time experimental and simulation studies suggest that the adaptive augmented ellipsoidal SLAM is more accurate than the conventional EKF/ellipsoidal SLAMs.

Document type: 
Article
File(s): 

Assessing Anxiety Disorders Using Wearable Devices: Challenges and Future Directions

Peer reviewed: 
No, item is not peer reviewed.
Date created: 
2019-03-01
Abstract: 

Wearable devices (WD) are starting to increasingly be used for interventions to promote well-being by reducing anxiety disorders (AD). Electrocardiogram (ECG) signal is one of the most commonly used biosignals for assessing the cardiovascular system as it significantly reflects the activity of the autonomic nervous system during emotional changes. Little is known about the accuracy of using ECG features for detecting ADs. Moreover, during our literature review, a limited number of studies were found that involve ECG collection usingWDfor promoting mental well-being. Thus, for the sake of validating the reliability of ECG features for detecting anxiety in WD, we screened 1040 articles, and only 22 were considered for our study; specifically 6 on panic, 4 on post-traumatic stress, 4 on generalized anxiety, 3 on social, 3 on mixed, and 2 on obsessive-compulsive anxiety disorder articles. Most experimental studies had controversial results. Upon reviewing each of these papers, it became apparent that the use of ECG features for detecting different types of anxiety is controversial, and the use of ECG-WD is an emerging area of research, with limited evidence suggesting its reliability. Due to the clinical nature of most studies, it is difficult to determine the specific impact of ECG features on detecting ADs, suggesting the need for more robust studies following our proposed recommendations.

Document type: 
Article
File(s): 

Measurement of Mechanical Strain based on Piezo-Avalanche Effect

Peer reviewed: 
Yes, item is peer reviewed.
Date created: 
2019-05-13
Abstract: 

We are reporting on the use of the breakdown voltage of a pn junction to measure mechanical strain in micro-structures. The working principle relies on the dependence of silicon band gap to the mechanical stress which affects the current-voltage characteristics of the pn junction. An analytic model is developed and verified experimentally for the phenomenon. A micromechanical device with integrated junctions was designed and fabricated. Mechanical stress was applied onto the structure by subjecting it to mechanical vibrations. It is shown that the breakdown voltage of the device exhibited a high stress sensitivity of about 240ߤ/ܸܯ .ܽܲ.  The mechanical stress can also be measured by monitoring the device current while biased at a constant current. In this mode, the steep changes of the junction current in breakdown region led to nearly a tenfold higher stress sensitivity compared to a piezoresistive sensor. The high sensitivity, simple measurement, and potential for miniaturization for piezo-avalanche sensing make it a promising technique for measurement of stress in micro- and nano-mechanical devices.

Document type: 
Article
File(s): 

A New Approach to Compute the Porosity and Surface Roughness of Porous Coated Capillary-Assisted Low Pressure Evaporators

Peer reviewed: 
Yes, item is peer reviewed.
Date created: 
2018-08-03
Abstract: 

The fundamental characteristics of metal coatings that influence heat transfer are porosity and surface roughness. It is a challenge to analyze the porosity and surface roughness due to the inadequate amount of copper per coated area. In this study, a new approach to non-invasively determine the porosity of metal films utilizing a helium pycnometer and computed micro-tomography (CMT) is presented. Furthermore, a telescope-goniometer is used to measure the surface roughness. Experiments are conducted on four varieties of thin film samples coated with copper powder using wire flame and plasma thermal spray coating methods. The porosities of the thin films were determined to be between 39 and 43%. The thermal spray coating increased the hydrophobicity of the surface and the plasma coating created super-hydrophobic surfaces. The new approach establishes that the porosity of thin films can be non-invasively determined and may also be applied to a wide variety of coated surfaces.

Document type: 
Article