Ensemble Learning Approach via Kalman Filtering for a Passive Wearable Respiratory Monitor

Acharya, Sayandeep; Mongan, William M.; Rasheed, Ilhaan; Liu, Yuqiao; Anday, Endla K.; Dion, Geneviève; Fontecchio, Adam K.; Kurzweg, Timothy P.; Dandekar, Kapil R.

doi:10.1109/jbhi.2018.2857924

Cited by 24 publications

(18 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We conducted a logistic regression analysis to test Hypotheses 5 and 7, given the dichotomous nature of the satisficing dependent variable ( Gong, 2003 ). Model 1 is the base model with all the control variables.…”

Section: Resultsmentioning

confidence: 99%

Opportunity Finding by Nascent Entrepreneurs: Accidental or Purposeful?

Rong-ji

2021

Front. Psychol.

View full text Add to dashboard Cite

PurposeThis research studies an important, but relatively unexplored entrepreneurial aspect: motivation and aspiration on opportunity finding/discovery.Design/Methodology/ApproachThis study surveyed 230 nascent entrepreneurs on their opportunity finding behavior. A poisson regression and a logistic analysis were conducted to discover the relationship between motivation/aspiration and opportunity search behavior.FindingsMotivation and aspiration interact to influence active search in a positive way. However, only willingness to become an entrepreneur is found to search for opportunities purposefully.Research Limitations/ImplicationsParticipants of the research are from a Midwest state in United States. Future research may collect sample from more and larger areas.Practical ImplicationsBankers may use entrepreneurial opportunity search behavior as one criterion determining if to fund a person or not.Originality/ValueThis article answers the call to study motivation/aspiration on opportunity finding (Yitshaki and Kropp, 2018; Murnieks et al., 2020). It is one of the first studies to explore the above relationship.

show abstract

Section: Resultsmentioning

confidence: 99%

Opportunity Finding by Nascent Entrepreneurs: Accidental or Purposeful?

Rong-ji

2021

Front. Psychol.

View full text Add to dashboard Cite

show abstract

“…To limit the amount of noise in the return signal, the Bellyband uses an ARIMA model to find the best possible parameters for a Kalman filter. This process was originally used with a reference tag to help identify and remove noise artifacts [21]. For this paper, the reference tag was not used in data collection, however, some of the noise reduction techniques used with the reference tag were imported for this project.…”

Section: ) Noise Reductionmentioning

confidence: 99%

“…For this paper, the reference tag was not used in data collection, however, some of the noise reduction techniques used with the reference tag were imported for this project. Using those imported noise reduction methods, data can be distinguished as valid increases in P rx compared to increases in P rx due to noise components [21].…”

Section: ) Noise Reductionmentioning

confidence: 99%

An Adaptive Search Algorithm for Detecting Respiratory Artifacts Using a Wireless Passive Wearable Device

O'Neill

Mongan

Ross

et al. 2019

2019 IEEE Signal Processing in Medicine and Biology Symposium (SPMB)

View full text Add to dashboard Cite

With the use of a wireless, wearable, passive knitted smart fabric device as a strain gauge sensor, the proposed algorithm can estimate biomedical feedback such as respiratory activity. Variations in physical properties of Radio Frequency Identification (RFID) signals can be used to wirelessly detect physiological processes and states. However, it is typical for ambient noise artifacts to appear in the RFID signal making it difficult to identify physiological processes. This paper introduces a new technique for finding these repetitive physiological signals and identifying them into two states, active and inactive, using k-means clustering. The algorithm detects these biomedical events without the need to completely remove the noise components using a semiunsupervised approach, and with these results, predict the next biomedical event using these classification results. This approach enables real-time noninvasive monitoring for use with actuating medical devices for therapy. Using this approach, the algorithm predicts the onset of respiratory activity in a simulated environment within approximately one second.

show abstract

“…Although there are many HAR studies based on ensemble learning technology [39,40,41,42,43,44], to our best knowledge, there is still no work attempting to improve the performance of HAR through a selective ensemble approach. Most of the ensemble learning-based HAR studies [17,30,39] combined all the trained base classifiers for recognition.…”

Section: Introductionmentioning

confidence: 99%

Selective Ensemble Based on Extreme Learning Machine for Sensor-Based Human Activity Recognition

Tian

Jie

Geng

et al. 2019

Sensors

View full text Add to dashboard Cite

Sensor-based human activity recognition (HAR) has attracted interest both in academic and applied fields, and can be utilized in health-related areas, fitness, sports training, etc. With a view to improving the performance of sensor-based HAR and optimizing the generalizability and diversity of the base classifier of the ensemble system, a novel HAR approach (pairwise diversity measure and glowworm swarm optimization-based selective ensemble learning, DMGSOSEN) that utilizes ensemble learning with differentiated extreme learning machines (ELMs) is proposed in this paper. Firstly, the bootstrap sampling method is utilized to independently train multiple base ELMs which make up the initial base classifier pool. Secondly, the initial pool is pre-pruned by calculating the pairwise diversity measure of each base ELM, which can eliminate similar base ELMs and enhance the performance of HAR system by balancing diversity and accuracy. Then, glowworm swarm optimization (GSO) is utilized to search for the optimal sub-ensemble from the base ELMs after pre-pruning. Finally, majority voting is utilized to combine the results of the selected base ELMs. For the evaluation of our proposed method, we collected a dataset from different locations on the body, including chest, waist, left wrist, left ankle and right arm. The experimental results show that, compared with traditional ensemble algorithms such as Bagging, Adaboost, and other state-of-the-art pruning algorithms, the proposed approach is able to achieve better performance (96.7% accuracy and F1 from wrist) with fewer base classifiers.

show abstract

Ensemble Learning Approach via Kalman Filtering for a Passive Wearable Respiratory Monitor

Abstract: The proposed system can be useful in remote non-invasive breathing state monitoring and sleep apnea detection.

Cited by 24 publications

References 24 publications

Opportunity Finding by Nascent Entrepreneurs: Accidental or Purposeful?

Opportunity Finding by Nascent Entrepreneurs: Accidental or Purposeful?

An Adaptive Search Algorithm for Detecting Respiratory Artifacts Using a Wireless Passive Wearable Device

Selective Ensemble Based on Extreme Learning Machine for Sensor-Based Human Activity Recognition

Contact Info

Product

Resources

About