scholarly journals Modelling Human Activity using Smartphone Data

2021 ◽  
Vol 15 (1) ◽  
pp. 58-70
Author(s):  
Suriya Badrinath ◽  
Raja Muthalagu
Keyword(s):  
Real Time ◽  
Human Activity ◽  
Human Activities ◽  
Time Series Data ◽  
Sensor Data ◽  
Series Data ◽  
Raspberry Pi ◽  
Healthy Human ◽  
Deep Cnn ◽  
Rate Sensor

Background: Over time, multichannel time series data were utilized for the purpose of modeling human activity. Instruments such as an accelerometer and gyroscope which had sensors embedded in them, recorded sensor data which were then utilized to record 6-axes, single dimensional convolution for the purpose of formulating a deep CNN. The resultant network achieved 94.79% activity recognition accuracy on raw sensor data, and 95.57% accuracy when Fast Fourier Transform (FFT) knowledge was added to the sensor data. Objective: This study helps to achieve an orderly report of daily Human activities for the overall balanced lifestyle of a healthy human being. Methods: Interfacing is done using Arduino Uno, Raspberry-Pi 3, heart rate sensor and accelerometer ADXL345 to generate real time values of day-to-day human activities such as walking, sleeping, climbing upstairs/downstairs and so on. Initially, the heart pulse of our four tested individuals is recorded and tabulated to depict and draw conclusions all the way from “Low BP” to “Heavy Exercise”. The convolution neural network is initially trained with an online human activity dataset and tested using our real time generated values which are sent to the MAC OS using a Bluetooth interface. Results: We obtain graphical representations of the amount of each activity performed by the test set of individuals, and in turn conclusions which suggest increase or decrease in the consistency of certain activities to the users, depicted through our developed iOS application, “Fitnesse”. Conclusion: The result of this works is used to improve the daily health routines and the overall lifestyle of distressed patients.

scholarly journals Design and Evaluation of IoT-Enabled Instrumentation for a Soil-Bentonite Slurry Trench Cutoff Wall

2019 ◽  
Vol 4 (1) ◽  
pp. 5 ◽  
Author(s):  
Alan Marchiori ◽  
Yadong Li ◽  
Jeffrey Evans
Keyword(s):  
Real Time ◽  
Web Application ◽  
Time Series Data ◽  
Sensor Data ◽  
Series Data ◽  
Raspberry Pi ◽  
Transmission Protocol ◽  
Cutoff Wall ◽  
Bentonite Slurry ◽  
Slurry Trench

In this work, we describe our approach and experiences bringing an instrumented soil-bentonite slurry trench cutoff wall into a modern IoT data collection and visualization pipeline. Soil-bentonite slurry trench cutoff walls have long been used to control ground water flow and contaminant transport. A Raspberry Pi computer on site periodically downloads the sensor data over a serial interface from an industrial datalogger and transmits the data wirelessly to a gateway computer located 1.3 km away using a reliable transmission protocol. The resulting time-series data is stored in a MongoDB database and data is visualized in real-time by a custom web application. The system has been in operation for over two years achieving 99.42% reliability and no data loss from the collection, transport, or storage of data. This project demonstrates the successful bridging of legacy scientific instrumentation with modern IoT technologies and approaches to gain timely web-based data visualization facilitating rapid data analysis without negatively impacting data integrity or reliability. The instrumentation system has proven extremely useful in understanding the changes in the stress state over time and could be deployed elsewhere as a means of on-demand slurry trench cutoff wall structural health monitoring for real-time stress detection linked to hydraulic conductivity or adapted for other infrastructure monitoring applications.

A Novel Approach to Time Series Forecasting Using Model-Free Adaptive Control Framework

2020 ◽  
Author(s):  
Meenakshi Narayan ◽  
Ann Majewicz Fey
Keyword(s):  
Time Series ◽  
Adaptive Control ◽  
Real Time ◽  
Time Series Data ◽  
Mean Squared Error ◽  
Force Sensor ◽  
Sensor Data ◽  
Series Data ◽  
Model Free ◽  
Control Framework

Abstract Sensor data predictions could significantly improve the accuracy and effectiveness of modern control systems; however, existing machine learning and advanced statistical techniques to forecast time series data require significant computational resources which is not ideal for real-time applications. In this paper, we propose a novel forecasting technique called Compact Form Dynamic Linearization Model-Free Prediction (CFDL-MFP) which is derived from the existing model-free adaptive control framework. This approach enables near real-time forecasts of seconds-worth of time-series data due to its basis as an optimal control problem. The performance of the CFDL-MFP algorithm was evaluated using four real datasets including: force sensor readings from surgical needle, ECG measurements for heart rate, and atmospheric temperature and Nile water level recordings. On average, the forecast accuracy of CFDL-MFP was 28% better than the benchmark Autoregressive Integrated Moving Average (ARIMA) algorithm. The maximum computation time of CFDL-MFP was 49.1ms which was 170 times faster than ARIMA. Forecasts were best for deterministic data patterns, such as the ECG data, with a minimum average root mean squared error of (0.2±0.2).

scholarly journals Remaining Useful Life Prediction Using Temporal Convolution with Attention

AI ◽  
2021 ◽  
Vol 2 (1) ◽  
pp. 48-70
Author(s):  
Wei Ming Tan ◽  
T. Hui Teo
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Time Series Data ◽  
Remaining Useful Life ◽  
Sensor Data ◽  
Series Data ◽  
Multiple Time ◽  
Data Set ◽  
Form Complex ◽  
Useful Life

Prognostic techniques attempt to predict the Remaining Useful Life (RUL) of a subsystem or a component. Such techniques often use sensor data which are periodically measured and recorded into a time series data set. Such multivariate data sets form complex and non-linear inter-dependencies through recorded time steps and between sensors. Many current existing algorithms for prognostic purposes starts to explore Deep Neural Network (DNN) and its effectiveness in the field. Although Deep Learning (DL) techniques outperform the traditional prognostic algorithms, the networks are generally complex to deploy or train. This paper proposes a Multi-variable Time Series (MTS) focused approach to prognostics that implements a lightweight Convolutional Neural Network (CNN) with attention mechanism. The convolution filters work to extract the abstract temporal patterns from the multiple time series, while the attention mechanisms review the information across the time axis and select the relevant information. The results suggest that the proposed method not only produces a superior accuracy of RUL estimation but it also trains many folds faster than the reported works. The superiority of deploying the network is also demonstrated on a lightweight hardware platform by not just being much compact, but also more efficient for the resource restricted environment.

scholarly journals Study on Fractal Multistep Forecast for the Prediction of Driving Behavior

2020 ◽  
Vol 2020 ◽  
pp. 1-10
Author(s):  
Longhai Yang ◽  
Hong Xu ◽  
Xiqiao Zhang ◽  
Shuai Li ◽  
Wenchao Ji
Keyword(s):  
Prediction Model ◽  
Real Time ◽  
Time Series Data ◽  
Back Propagation ◽  
Series Data ◽  
Vehicle Speed ◽  
Trajectory Data ◽  
Time Data ◽  
Characteristic Analysis ◽  
Real Time Data

The application and development of new technology make it possible to acquire real-time data of vehicles. Based on these real-time data, the behavior of vehicles can be analyzed. The prediction of vehicle behavior provides data support for the fine management of traffic. This paper proposes speed and acceleration have fractal features by R/S analysis of the time series data of speed and acceleration. Based on the characteristic analysis of microscopic parameters, the characteristic indexes of parameters are quantified, the fractal multistep prediction model of microparameters is established, and the BP (back propagation neural networks) model is established to estimate predictable step of fractal prediction model. The fractal multistep prediction model is used to predict speed acceleration in the predictable step. NGSIM trajectory data are used to test the multistep prediction model. The results show that the proposed fractal multistep prediction model can effectively realize the multistep prediction of vehicle speed.

scholarly journals Antibiotics-induced monodominance of a novel gut bacterial order

Gut ◽  
2019 ◽  
Vol 68 (10) ◽  
pp. 1781-1790 ◽  
Author(s):  
Falk Hildebrand ◽  
Lucas Moitinho-Silva ◽  
Sonja Blasche ◽  
Martin T Jahn ◽  
Toni Ingolf Gossmann ◽  
...  
Keyword(s):  
Community Dynamics ◽  
Time Series Data ◽  
Abundant Species ◽  
Series Data ◽  
Healthy Human ◽  
Shotgun Metagenomics ◽  
Community Shift ◽  
Unknown Species ◽  
Permanent Loss ◽  
Functional Profiles

ObjectiveThe composition of the healthy human adult gut microbiome is relatively stable over prolonged periods, and representatives of the most highly abundant and prevalent species have been cultured and described. However, microbial abundances can change on perturbations, such as antibiotics intake, enabling the identification and characterisation of otherwise low abundant species.DesignAnalysing gut microbial time-series data, we used shotgun metagenomics to create strain level taxonomic and functional profiles. Community dynamics were modelled postintervention with a focus on conditionally rare taxa and previously unknown bacteria.ResultsIn response to a commonly prescribed cephalosporin (ceftriaxone), we observe a strong compositional shift in one subject, in which a previously unknown species, UBorkfalki ceftriaxensis, was identified, blooming to 92% relative abundance. The genome assembly reveals that this species (1) belongs to a so far undescribed order of Firmicutes, (2) is ubiquitously present at low abundances in at least one third of adults, (3) is opportunistically growing, being ecologically similar to typical probiotic species and (4) is stably associated to healthy hosts as determined by single nucleotide variation analysis. It was the first coloniser after the antibiotic intervention that led to a long-lasting microbial community shift and likely permanent loss of nine commensals.ConclusionThe bloom of UB. ceftriaxensis and a subsequent one of Parabacteroides distasonis demonstrate the existence of monodominance community states in the gut. Our study points to an undiscovered wealth of low abundant but common taxa in the human gut and calls for more highly resolved longitudinal studies, in particular on ecosystem perturbations.

A hybrid fuzzy quantum time series and linear programming model: Special application on TAIEX index dataset

2019 ◽  
Vol 34 (25) ◽  
pp. 1950201 ◽  
Author(s):  
Pritpal Singh ◽  
Gaurav Dhiman ◽  
Sen Guo ◽  
Ritika Maini ◽  
Harsimran Kaur ◽  
...  
Keyword(s):  
Time Series ◽  
Linear Programming ◽  
Real Time ◽  
Time Series Data ◽  
Programming Model ◽  
Series Data ◽  
Quantum Model ◽  
Quantum Time ◽  
Degree Of Membership ◽  
Quantum Approach

The supremacy of quantum approach is able to provide the solutions which are not practically feasible on classical machines. This paper introduces a novel quantum model for time series data which depends on the appropriate length of intervals. In this study, the effects of these drawbacks are elaborately illustrated, and some significant measures to remove them are suggested, such as use of degree of membership along with mid-value of the interval. All these improvements signify the effective results in case of quantum time series, which are verified and validated with real-time datasets.

Sign in / Sign up

Export Citation Format

Share Document