scholarly journals Visualization-Driven Time-Series Extraction from Wearable Systems Can Facilitate Differentiation of Passive ADL Characteristics among Stroke and Healthy Older Adults

Sensors ◽  
2022 ◽  
Vol 22 (2) ◽  
pp. 598
Author(s):  
Joby John ◽  
Rahul Soangra
Keyword(s):  
Time Series ◽  
Extraction Methods ◽  
Rehabilitation Program ◽  
Healthy Adults ◽  
Accelerometer Data ◽  
Healthy Older Adults ◽  
Wearable Systems ◽  
Deep Recurrent Neural Network ◽  
Naturalistic Environment ◽  
Natural Settings

Wearable technologies allow the measurement of unhindered activities of daily living (ADL) among patients who had a stroke in their natural settings. However, methods to extract meaningful information from large multi-day datasets are limited. This study investigated new visualization-driven time-series extraction methods for distinguishing activities from stroke and healthy adults. Fourteen stroke and fourteen healthy adults wore a wearable sensor at the L5/S1 position for three consecutive days and collected accelerometer data passively in the participant’s naturalistic environment. Data from visualization facilitated selecting information-rich time series, which resulted in classification accuracy of 97.3% using recurrent neural networks (RNNs). Individuals with stroke showed a negative correlation between their body mass index (BMI) and higher-acceleration fraction produced during ADL. We also found individuals with stroke made lower activity amplitudes than healthy counterparts in all three activity bands (low, medium, and high). Our findings show that visualization-driven time series can accurately classify movements among stroke and healthy groups using a deep recurrent neural network. This novel visualization-based time-series extraction from naturalistic data provides a physical basis for analyzing passive ADL monitoring data from real-world environments. This time-series extraction method using unit sphere projections of acceleration can be used by a slew of analysis algorithms to remotely track progress among stroke survivors in their rehabilitation program and their ADL abilities.

scholarly journals Identifying resting locations of a small elusive forest carnivore using a two-stage model accounting for GPS measurement error and hidden behavioral states

2021 ◽  
Vol 9 (1) ◽  
Author(s):  
Dalton J. Hance ◽  
Katie M. Moriarty ◽  
Bruce A. Hollen ◽  
Russell W. Perry
Keyword(s):  
Time Series ◽  
Measurement Error ◽  
Gaussian State ◽  
Parameter Estimates ◽  
Accelerometer Data ◽  
Two Stage ◽  
Location Data ◽  
Gps Measurement ◽  
Activity Measurements ◽  
Behavioral States

Abstract Background Studies of animal movement using location data are often faced with two challenges. First, time series of animal locations are likely to arise from multiple behavioral states (e.g., directed movement, resting) that cannot be observed directly. Second, location data can be affected by measurement error, including failed location fixes. Simultaneously addressing both problems in a single statistical model is analytically and computationally challenging. To both separate behavioral states and account for measurement error, we used a two-stage modeling approach to identify resting locations of fishers (Pekania pennanti) based on GPS and accelerometer data. Methods We developed a two-stage modelling approach to estimate when and where GPS-collared fishers were resting for 21 separate collar deployments on 9 individuals in southern Oregon. For each deployment, we first fit independent hidden Markov models (HMMs) to the time series of accelerometer-derived activity measurements and apparent step lengths to identify periods of movement and resting. Treating the state assignments as given, we next fit a set of linear Gaussian state space models (SSMs) to estimate the location of each resting event. Results Parameter estimates were similar across collar deployments. The HMMs successfully identified periods of resting and movement with posterior state assignment probabilities greater than 0.95 for 97% of all observations. On average, fishers were in the resting state 63% of the time. Rest events averaged 5 h (4.3 SD) and occurred most often at night. The SSMs allowed us to estimate the 95% credible ellipses with a median area of 0.12 ha for 3772 unique rest events. We identified 1176 geographically distinct rest locations; 13% of locations were used on > 1 occasion and 5% were used by > 1 fisher. Females and males traveled an average of 6.7 (3.5 SD) and 7.7 (6.8 SD) km/day, respectively. Conclusions We demonstrated that if auxiliary data are available (e.g., accelerometer data), a two-stage approach can successfully resolve both problems of latent behavioral states and GPS measurement error. Our relatively simple two-stage method is repeatable, computationally efficient, and yields directly interpretable estimates of resting site locations that can be used to guide conservation decisions.

scholarly journals Time–frequency time–space LSTM for robust classification of physiological signals

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Tuan D. Pham
Keyword(s):  
Time Series ◽  
Network Architecture ◽  
Time Series Data ◽  
Short Term Memory ◽  
Physiological Signals ◽  
Series Data ◽  
Time Frequency ◽  
Time Space ◽  
Deep Recurrent Neural Network

AbstractAutomated analysis of physiological time series is utilized for many clinical applications in medicine and life sciences. Long short-term memory (LSTM) is a deep recurrent neural network architecture used for classification of time-series data. Here time–frequency and time–space properties of time series are introduced as a robust tool for LSTM processing of long sequential data in physiology. Based on classification results obtained from two databases of sensor-induced physiological signals, the proposed approach has the potential for (1) achieving very high classification accuracy, (2) saving tremendous time for data learning, and (3) being cost-effective and user-comfortable for clinical trials by reducing multiple wearable sensors for data recording.

Processing gender stereotypes in dementia patients and older healthy adults: a self-paced reading study

2019 ◽  
Vol 5 (s2) ◽  
Author(s):  
Daniel Müller-Feldmeth ◽  
Katharina Ahnefeld ◽  
Adriana Hanulíková
Keyword(s):  
Older Adults ◽  
Young Adults ◽  
Sentence Processing ◽  
Gender Stereotypes ◽  
Time Course ◽  
Healthy Adults ◽  
Control Group ◽  
Healthy Older Adults ◽  
Dementia Patients ◽  
Age Related

AbstractWe used self-paced reading to examine whether stereotypical associations of verbs with women or men as prototypical agents (e.g. the craftsman knits a sweater) are activated during sentence processing in dementia patients and healthy older adults. Effects of stereotypical knowledge on language processing have frequently been observed in young adults, but little is known about age-related changes in the activation and integration of stereotypical information. While syntactic processing may remain intact, semantic capacities are often affected in dementia. Since inferences based on gender stereotypes draw on social and world knowledge, access to stereotype information may also be affected in dementia patients. Results from dementia patients (n = 9, average age 86.6) and healthy older adults (n = 14, average age 79.5) showed slower reading times and less accuracy in comprehension scores for dementia patients compared to the control group. While activation of stereotypical associations of verbs was visible in both groups, they differed with respect to the time-course of processing. The effect of stereotypes on comprehension accuracy was visible for healthy adults only. The evidence from reading times suggests that older adults with and without dementia engage stereotypical inferences during reading, which is in line with research on young adults.

scholarly journals A Comparison of Feature Extraction Methods for the Classification of Dynamic Activities From Accelerometer Data

2009 ◽  
Vol 56 (3) ◽  
pp. 871-879 ◽  
Author(s):  
Stephen J. Preece ◽  
John Yannis Goulermas ◽  
Laurence P. J. Kenney ◽  
David Howard
Keyword(s):  
Feature Extraction ◽  
Extraction Methods ◽  
Accelerometer Data

scholarly journals Development of a Dementia-Focused End-of-Life Planning Tool: The LEAD Guide (Life-Planning in Early Alzheimer’s and Dementia)

2019 ◽  
Vol 3 (3) ◽  
Author(s):  
Kara Dassel ◽  
Rebecca Utz ◽  
Katherine Supiano ◽  
Sara Bybee ◽  
Eli Iacob
Keyword(s):  
Older Adults ◽  
Clinical Practice ◽  
Focus Groups ◽  
End Of Life ◽  
Family Caregivers ◽  
Early Stage ◽  
Healthy Adults ◽  
Planning Tool ◽  
Healthy Older Adults ◽  
Life Planning

Abstract Background and Objectives To address the unique characteristics of Alzheimer’s disease and related dementias (ADRD) that complicate end-of-life (EOL), we created, refined, and validated a dementia-focused EOL planning instrument for use by healthy adults, those with early-stage dementia, family caregivers, and clinicians to document EOL care preferences and values within the current or future context of cognitive impairment. Research Design and Methods A mixed-method design with four phases guided the development and refinement of the instrument: (1) focus groups with early-stage ADRD and family caregivers developed and confirmed the tool content and comprehensiveness; (2) evaluation by content experts verified its utility in clinical practice; (3) a sample of healthy older adults (n = 153) and adults with early-stage ADRD (n = 38) completed the tool, whose quantitative data were used to describe the psychometrics of the instrument; and (4) focus groups with healthy older adults, family caregivers, and adults with early-stage ADRD informed how the guide should be used by families and in clinical practice. Results Qualitative data supported the utility and feasibility of a dementia-focused EOL planning tool; the six scales have high internal consistency (α = 0.66–0.89) and high test–rest reliability (r = .60–.90). On average, both participant groups reported relatively high concern for being a burden to their families, a greater preference for quality over length of life, a desire for collaborative decision-making process, limited interest in pursuing life-prolonging measures, and were mixed in their preference to control the timing of their death. Across disease progression, preferences for location of care changed, whereas preferences for prolonging life remained stable. Discussion and Implications The LEAD Guide (Life-Planning in Early Alzheimer’s and Dementia) has the potential to facilitate discussion and documentation of EOL values and care preferences prior to loss of decisional capacity, and has utility for healthy adults, patients, families, providers, and researchers.

scholarly journals Near-Zero Phase-Lag Hyperscanning in a Novel Wireless EEG System

2021 ◽  
Author(s):  
Chun-Hsiang Chuang ◽  
Shao-Wei Lu ◽  
Yi-Ping Chao ◽  
Po-Hsun Peng ◽  
Hao-Che Hsu ◽  
...  
Keyword(s):  
Time Series ◽  
Video Gaming ◽  
Phase Lag ◽  
Analog To Digital ◽  
Synchronous Sampling ◽  
Asynchronous Sampling ◽  
Custom Made ◽  
Natural Settings ◽  
Wireless Eeg ◽  
Zero Phase

Hyperscanning is an emerging technology that concurrently scans the neural dynamics of multiple individuals to study interpersonal interactions. In particular, hyperscanning with wireless electroencephalography (EEG) is increasingly popular owing to its mobility and ability to decipher social interactions in natural settings at the millisecond scale. To align multiple EEG time series with sophisticated event markers in a single time domain, a precise and unified timestamp is required for stream synchronization. This study proposed a clock-synchronized method using a custom-made RJ45 cable to coordinate the sampling between wireless EEG amplifiers to prevent incorrect estimation of interbrain connectivity due to asynchronous sampling. In this method, analog-to-digital converters are driven by the same sampling clock. Additionally, two clock-synchronized amplifiers leverage additional RF channels to keep the counter of their receiving dongles updated, guaranteeing that binding event markers received by the dongle with the EEG time series have the correct timestamp. The results of two simulation experiments and one video gaming experiment revealed that the proposed method ensures synchronous sampling in a system with multiple EEG devices, achieving near-zero phase-lag and negligible amplitude difference between signals. According to all of the signal-similarity metrics, the suggested method is a promising option for wireless EEG hyperscanning and can be utilized to precisely assess the interbrain couplings underlying social-interaction behaviors.

scholarly journals Short and Medium-Term Prediction of Winter Wheat NDVI Based on the DTW–LSTM Combination Method and MODIS Time Series Data

2021 ◽  
Vol 13 (22) ◽  
pp. 4660
Author(s):  
Fa Zhao ◽  
Guijun Yang ◽  
Hao Yang ◽  
Yaohui Zhu ◽  
Yang Meng ◽  
...  
Keyword(s):  
Time Series ◽  
Winter Wheat ◽  
Vegetation Index ◽  
Time Series Data ◽  
Short Term Memory ◽  
Combination Method ◽  
Series Data ◽  
Medium Term ◽  
Short Term ◽  
Deep Recurrent Neural Network

The normalized difference vegetation index (NDVI) is an important agricultural parameter that is closely correlated with crop growth. In this study, a novel method combining the dynamic time warping (DTW) model and the long short-term memory (LSTM) deep recurrent neural network model was developed to predict the short and medium-term winter wheat NDVI. LSTM is well-suited for modelling long-term dependencies, but this method may be susceptible to overfitting. In contrast, DTW possesses good predictive ability and is less susceptible to overfitting. Therefore, by utilizing the combination of these two models, the prediction error caused by overfitting is reduced, thus improving the final prediction accuracy. The combined method proposed here utilizes the historical MODIS time series data with an 8-day time resolution from 2015 to 2020. First, fast Fourier transform (FFT) is used to decompose the time series into two parts. The first part reflects the inter-annual and seasonal variation characteristics of winter wheat NDVI, and the DTW model is applied for prediction. The second part reflects the short-term change characteristics of winter wheat NDVI, and the LSTM model is applied for prediction. Next, the results from both models are combined to produce a final prediction. A case study in Hebei Province that predicts the NDVI of winter wheat at five prediction horizons in the future indicates that the DTW–LSTM model proposed here outperforms the LSTM model according to multiple evaluation indicators. The results of this study suggest that the DTW–LSTM model is highly promising for short and medium-term NDVI prediction.

Sign in / Sign up

Export Citation Format

Share Document