Magnetically Counting Hand Movements: Validation of a Calibration-Free Algorithm and Application to Testing the Threshold Hypothesis of Real-World Hand Use after Stroke

There are few wearable sensors suitable for daily monitoring of wrist and finger movements for hand-related healthcare applications. Here, we describe the development and validation of a novel algorithm for magnetically counting hand movements. We implemented the algorithm on a wristband that senses magnetic field changes produced by movement of a magnetic ring worn on the finger (the “Manumeter”). The “HAND” (Hand Activity estimated by Nonlinear Detection) algorithm assigns a “HAND count” by thresholding the real-time change in magnetic field created by wrist and/or finger movement. We optimized thresholds to achieve a HAND count accuracy of ~85% without requiring subject-specific calibration. Then, we validated the algorithm in a dexterity-impaired population by showing that HAND counts strongly correlate with clinical assessments of upper extremity (UE) function after stroke. Finally, we used HAND counts to test a recent hypothesis in stroke rehabilitation that real-world UE hand use increases only for stroke survivors who achieve a threshold level of UE functional capability. For 29 stroke survivors, HAND counts measured at home did not increase until the participants’ Box and Blocks Test scores exceeded ~50% normal. These results show that a threshold-based magnetometry approach can non-obtrusively quantify hand movements without calibration and also verify a key concept of real-world hand use after stroke.

Download Full-text

Overlapping Community Detection Based on Attribute Augmented Graph

Entropy ◽

10.3390/e23060680 ◽

2021 ◽

Vol 23 (6) ◽

pp. 680

Author(s):

Hanyang Lin ◽

Yongzhao Zhan ◽

Zizheng Zhao ◽

Yuzhong Chen ◽

Chen Dong

Keyword(s):

Community Detection ◽

Real World ◽

Detection Algorithm ◽

Overlapping Community Detection ◽

Overlapping Communities ◽

Adjustment Strategy ◽

Topology Information ◽

Overlapping Community ◽

Real World Datasets ◽

Community Detection Algorithm

There is a wealth of information in real-world social networks. In addition to the topology information, the vertices or edges of a social network often have attributes, with many of the overlapping vertices belonging to several communities simultaneously. It is challenging to fully utilize the additional attribute information to detect overlapping communities. In this paper, we first propose an overlapping community detection algorithm based on an augmented attribute graph. An improved weight adjustment strategy for attributes is embedded in the algorithm to help detect overlapping communities more accurately. Second, we enhance the algorithm to automatically determine the number of communities by a node-density-based fuzzy k-medoids process. Extensive experiments on both synthetic and real-world datasets demonstrate that the proposed algorithms can effectively detect overlapping communities with fewer parameters compared to the baseline methods.

Download Full-text

Using a Minimum Set of Wearable Sensors to Assess Quality of Movement in Stroke Survivors

2017 IEEE/ACM International Conference on Connected Health: Applications, Systems and Engineering Technologies (CHASE) ◽

10.1109/chase.2017.104 ◽

2017 ◽

Cited By ~ 1

Author(s):

Stefano Sapienza ◽

Catherine Adans-Dester ◽

Anne OBrien ◽

Gloria Vergara-Diaz ◽

Sunghoon Lee ◽

...

Keyword(s):

Wearable Sensors ◽

Stroke Survivors ◽

Quality Of Movement ◽

Assess Quality

Download Full-text

Abstract P505: Real-world Data Validation Of A Novel P-wave Based Automatic Atrial Fibrillation Detection Algorithm

Circulation ◽

10.1161/circ.141.suppl_1.p505 ◽

2020 ◽

Vol 141 (Suppl_1) ◽

Author(s):

Åke Olsson ◽

Magnus Samulesson

Keyword(s):

Real World ◽

False Negative ◽

Detection Algorithm ◽

P Wave ◽

Detection Accuracy ◽

The Novel ◽

Real World Data ◽

P Waves ◽

World Data ◽

Rr Variability

Background: Automatic ECG algorithms using only RR-variability in ECG to detect AF have shown high false positive rates. By including P-wave presence in the algorithm, research has shown that it can increase detection accuracy for AF. Methods: A novel RR- and P-wave based automatic detection algorithm implemented in the Coala Heart Monitor ("Coala", Coala Life AB, Sweden) was evaluated for detection accuracy by the comparison to blinded manual ECG interpretation based on real-world data. Evaluation was conducted on 100 consecutive anonymous printouts of chest- and thumb-ECG waveforms, where the algorithm had detected both irregular RR-rhythms and strong P-waves in either chest or thumb recording (non-AF episodes classified by algorithm as Category 12).The recordings, without exclusions, were generated from 5,512 real-world data recordings from actual Coala users in Sweden (both OTC and Rx users) during the period of March 5 to March 22, 2019, with no control or influence by the researchers or any other organization or individual. The prevalence of cardiac conditions in the user population was unknown.The blinded recordings were each manually interpreted by a trained cardiologist. The manual interpretation was compared with the automatic analysis performed by the detection algorithm to determine the number of additional false negative indications for AF as presented to the user. Results: The trained cardiologist manually interpreted 0 of the 100 recordings as AF. Manual interpretation showed that the novel automatic AF algorithm yielded 0 % False Negative error and 100 % Negative Predictive Value (NPV) for detection of AF. Irregular RR-rhythms were detected in 569 recordings (10 % of a total of 5,512 recordings). The 100 non-AF recordings containing both irregular RR-rhythms and strong P-waves constituted 18% of all recordings with irregular RR-rhythms. Respiratory sinus arrhythmia was the single most prevalent condition and was found in 47% of irregular RR-rhythms with strong P-waves. Conclusion: The novel, P-wave based automatic ECG algorithm used in the Coala, showed a zero percent False Negative error rate for AF detection in ECG recordings with RR-variability but presence of P-waves, as compared to manual interpretation by a cardiologist.

Download Full-text

Improved Illumination Independent Moving Object Detection Algorithm

Advances in Multimedia and Interactive Technologies - Video Surveillance Techniques and Technologies ◽

10.4018/978-1-4666-4896-8.ch002 ◽

2014 ◽

pp. 15-22

Keyword(s):

Real World ◽

Moving Objects ◽

Image Sequence ◽

Detection Algorithm ◽

Moving Object Detection ◽

Moving Object ◽

Detection Technique ◽

Real Image ◽

Illumination Changes ◽

Precision And Accuracy

A real time change detection technique is proposed in order to detect the moving objects in a real image sequence. The described method is independent of the illumination of the analyzed scene. It is based on a comparison of corresponding pixels that belong to different frames and combines time and space analysis, which augments the algorithm’s precision and accuracy. The efficiency of the described technique is illustrated on a real world interior video sequence recorded under significant illumination changes.

Download Full-text

Learning to Detect Cracks on Damaged Concrete Surfaces Using Two-Branched Convolutional Neural Network

Sensors ◽

10.3390/s19214796 ◽

2019 ◽

Vol 19 (21) ◽

pp. 4796

Author(s):

Jieun Lee ◽

Hee-Sun Kim ◽

Nayoung Kim ◽

Eun-Mi Ryu ◽

Je-Won Kang

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Real World ◽

Crack Detection ◽

Region Of Interest ◽

Detection Algorithm ◽

Image Sensors ◽

Final Output ◽

Gradient Component ◽

Functional Components

Image sensors are widely used for detecting cracks on concrete surfaces to help proactive and timely management of concrete structures. However, it is a challenging task to reliably detect cracks on damaged surfaces in the real world due to noise and undesired artifacts. In this paper, we propose an autonomous crack detection algorithm based on convolutional neural network (CNN) to solve the problem. To this aim, the proposed algorithm uses a two-branched CNN architecture, consisting of sub-networks named a crack-component-aware (CCA) network and a crack-region-aware (CRA) network. The CCA network is to learn gradient component regarding cracks, and the CRA network is to learn a region-of-interest by distinguishing critical cracks and noise such as scratches. Specifically, the two sub-networks are built on convolution-deconvolution CNN architectures, but also they are comprised of different functional components to achieve their own goals efficiently. The two sub-networks are trained in an end-to-end to jointly optimize parameters and produce the final output of localizing important cracks. Various crack image samples and learning methods are used for efficiently training the proposed network. In the experimental results, the proposed algorithm provides better performance in the crack detection than the conventional algorithms.

Download Full-text

A Robust Parking Detection Algorithm Against Electric Railway Magnetic Field Interference

IEEE Transactions on Intelligent Transportation Systems ◽

10.1109/tits.2019.2923465 ◽

2020 ◽

Vol 21 (2) ◽

pp. 882-893 ◽

Cited By ~ 2

Author(s):

Zusheng Zhang ◽

Xianmang He ◽

Huaqiang Yuan

Keyword(s):

Magnetic Field ◽

Detection Algorithm ◽

Electric Railway

Download Full-text

An Integrated ARMA-Based Deep Autoencoder and GRU Classifier System for Enhanced Recognition of Daily Hand Activities

International Journal of Pattern Recognition and Artificial Intelligence ◽

10.1142/s0218001421520066 ◽

2020 ◽

pp. 2152006

Author(s):

Patricio Rivera ◽

Edwin Valarezo ◽

Tae-Seong Kim

Keyword(s):

Daily Living ◽

Recurrent Network ◽

Hand Movements ◽

Human Hand ◽

Open Door ◽

Wearable Sensor ◽

Human Computer Interactions ◽

Healthcare Applications ◽

Classifier System ◽

Gated Recurrent Unit

Recognition of hand activities of daily living (hand-ADL) is useful in the areas of human–computer interactions, lifelogging, and healthcare applications. However, developing a reliable human activity recognition (HAR) system for hand-ADL with only a single wearable sensor is still a challenge due to hand movements that are typically transient and sporadic. Approaches based on deep learning methodologies to reduce noise and extract relevant features directly from raw data are becoming more promising for implementing such HAR systems. In this work, we present an ARMA-based deep autoencoder and a deep recurrent network (RNN) using Gated Recurrent Unit (GRU) for recognition of hand-ADL using signals from a single IMU wearable sensor. The integrated ARMA-based autoencoder denoises raw time-series signals of hand activities, such that better representation of human hand activities can be made. Then, our deep RNN-GRU recognizes seven hand-ADL based upon the output of the autoencoder: namely, Open Door, Close Door, Open Refrigerator, Close Refrigerator, Open Drawer, Close Drawer, and Drink from Cup. The proposed methodology using RNN-GRU with autoencoder achieves a mean accuracy of 84.94% and F1-score of 83.05% outperforming conventional classifiers such as RNN-LSTM, BRNN-LSTM, CNN, and Hybrid-RNNs by 4–10% higher in both accuracy and F1-score. The experimental results also showed the use of the autoencoder improves both the accuracy and F1-score of each conventional classifier by 12.8% in RNN-LSTM, 4.37% in BRNN-LSTM, 15.45% CNN, 14.6% Hybrid RNN, and 12.4% for the proposed RNN-GRU.

Download Full-text

At-Risk Driving Behavior in Drivers with Diabetes: A Neuroergonomics Approach

Proceedings of the Human Factors and Ergonomics Society Annual Meeting ◽

10.1177/1541931213601950 ◽

2017 ◽

Vol 61 (1) ◽

pp. 1881-1885

Author(s):

Jennifer Merickel ◽

Robin High ◽

Lynette Smith ◽

Chris Wichman ◽

Emily Frankel ◽

...

Keyword(s):

At Risk ◽

Real World ◽

Driver Behavior ◽

Wearable Sensors ◽

Sensor Data ◽

Continuous Glucose Monitor ◽

Glucose Levels ◽

Driver Performance ◽

Safety Interventions ◽

And Behavior

This pilot study tackles the overarching need for driver-state detection through real-world measurements of driver behavior and physiology in at-risk drivers with type 1 diabetes mellitus (DM). 35 drivers (19 DM, 14 comparison) participated. Real-time glucose levels were measured over four weeks with continuous glucose monitor (CGM) wearable sensors. Contemporaneous real-world driving performance and behavior were measured with in-vehicle video and electronic sensor instrumentation packages. Results showed clear links between at-risk glucose levels (particularly hypoglycemia) and changes in driver performance and behavior. DM participants often drove during at-risk glucose levels (low and high) and showed cognitive impairments in key domains for driving, which are likely linked to frequent hypoglycemia. The finding of increased driving risk in DM participants was mirrored in state records of crashes and traffic citations. Combining sensor data and phenotypes of driver behavior can inform patients, caregivers, safety interventions, policy, and design of supportive in-vehicle technology that is responsive to driver state.

Download Full-text

Numerical Investigation of Laser Oscillation in a Recombining Hydrogen Plasma Interacting with Helium Gas in TPD-I

Zeitschrift für Naturforschung A ◽

10.1515/zna-1985-0512 ◽

1985 ◽

Vol 40 (5) ◽

pp. 485-489 ◽

Cited By ~ 2

Author(s):

Toshiatsu Oda ◽

Utaro Furukane

Keyword(s):

Magnetic Field ◽

Numerical Investigation ◽

Axial Magnetic Field ◽

Hydrogen Plasma ◽

Plasma Source ◽

Threshold Level ◽

Laser Oscillation ◽

Quantum Numbers ◽

Magnetically Confined ◽

Helium Gas

A numerical investigation on the basis of a collisional-radiative (CR) model has shown that laser oscillation between the levels with the principal quantum numbers i = 2 and 3 can be generated in a recombining hydrogen plasma interacting with a dense helium gas as a cooling medium in TPD-I, which is a magnetically confined quiescent high-density plasma source consisting basically of two parts, namely, the discharge region with the cathode at the center of the cusped magnetic field and the plasma column region with the axial magnetic field. The population inversion is found to exceed significantly a threshold level for the laser oscillation even in the quasi-steady state when the hydrogen plasma with ne = 1013 ~ 1014 cm−3 interacts with the helium gas with a pressure of about 50 Torr.

Download Full-text