Scholarly article on topic 'Fuzzy Inference System-based Recognition of Slow, Medium and Fast Running Conditions using a Triaxial Accelerometer'

Fuzzy Inference System-based Recognition of Slow, Medium and Fast Running Conditions using a Triaxial Accelerometer Academic research paper on "Materials engineering"

CC BY-NC-ND
0
0
Share paper
Academic journal
Procedia Computer Science
OECD Field of science
Keywords
{Accelerometer / "Fuzzy Inference System" / "Running Condition"}

Abstract of research paper on Materials engineering, author of scientific article — Nizam Uddin Ahamed, Lauren Benson, Christian Clermont, Sean T. Osis, Reed Ferber

Abstract This paper introduces a fuzzy inference system (FIS)-based model for recognizing running conditions using data collected with a triaxial accelerometer. Specifically, data from three axes of a triaxial accelerometer were used as the input, and various running conditions (slow, medium and fast) were considered the output of the FIS. The MATLAB® fuzzy toolbox, which includes processes such as fuzzification, sets of fuzzy rules, fuzzy inference engine and defuzzification, was used to model the system. Mamdani-type fuzzy modelling was selected for developing the FIS. The structure of the generated fuzzy inference system includes three fuzzy rules (using if-then) and an initial set of membership functions. The performance of the proposed FIS model was assessed using the root mean square error (RMSE), mean absolute error (MAE) and non-dimensional error index (NDEI), which were found to equal 0.059, 0.213 and 0.147, respectively, for the test data. Additionally, the correlation coefficients (r) and coefficient of determination (R2 ) between the FIS-predicted and the actual values were 0.89 and 0.81, respectively. Finally, the model performance accuracy was measured using Variance-Accounted-For (%VAF), which equaled 96.54%. Thus, the assessment of the overall performance suggests that the proposed FIS model has potential to detect slow, medium and fast running conditions.

Academic research paper on topic "Fuzzy Inference System-based Recognition of Slow, Medium and Fast Running Conditions using a Triaxial Accelerometer"

I Available online at www.sciencedirect.com -

A ScienceDirect PrOCediCI

Computer Science

Procedia Computer Science 114 (2017) 401-407

www.elsevier.com/locate/procedia

Complex Adaptive Systems Conference with Theme: Engineering Cyber Physical Systems, CAS October 30 - November 1, 2017, Chicago, Illinois, USA

Fuzzy Inference System-based Recognition of Slow, Medium and Fast Running Conditions using a Triaxial Accelerometer

Nizam Uddin Ahameda*, Lauren Bensona, Christian Clermont3, Sean T. Osisa,b, Reed

Ferber a,b

a Faculty of Kinesiology, University ofCalgary, 2500 University Drive N.W. Calgary, Alberta T2NIN4 b Running Injury Clinic, University of Calgary, 2500 University Drive N. W. Calgary, Alberta T2NIN4

Abstract

This paper introduces a fuzzy inference system (FIS)-based model for recognizing running conditions using data collected with a triaxial accelerometer. Specifically, data from three axes of a triaxial accelerometer were used as the input, and various running conditions (slow, medium and fast) were considered the output of the FIS. The MATLAB® fuzzy toolbox, which includes processes such as fuzzification, sets of fuzzy rules, fuzzy inference engine and defuzzification, was used to model the system. Mamdani-type fuzzy modelling was selected for developing the FIS. The structure of the generated fuzzy inference system includes three fuzzy rules (using if-then) and an initial set of membership functions. The performance of the proposed FIS model was assessed using the root mean square error (RMSE), mean absolute error (MAE) and non-dimensional error index (NDEI), which were found to equal 0.059, 0.213 and 0.147, respectively, for the test data. Additionally, the correlation coefficients (r) and coefficient of determination (R2^ between the FIS-predicted and the actual values were 0.89 and 0.81, respectively. Finally, the model performance accuracy was measured using Variance-Accounted-For (%VAF), which equaled 96.54%. Thus, the assessment of the overall performance suggests that the proposed FIS model has potential to detect slow, medium and fast running conditions.

© 2017 The Authors. Published by Elsevier B.V.

Peer-review under responsibility of the scientific committee of the Complex Adaptive Systems Conference with Theme: Engineering Cyber Physical Systems.

Keywords: Accelerometer; Fuzzy Inference System; Running Condition.

* Corresponding author. Tel.: +1-403.220.8890 E-mail address: nizam.ahamed1@ucalgary.ca

1877-0509 © 2017 The Authors. Published by Elsevier B.V.

Peer-review under responsibility of the scientific committee of the Complex Adaptive Systems Conference with Theme:

Engineering Cyber Physical Systems.

10.1016/j.procs.2017.09.054

Nomenclature

Accl accelerometer data

FMS fast-medium-slow

FIS fuzzy inference system

MAE mean absolute error

MF membership function

NDEI non-dimensional error index

RMSE root mean square error

RMS root mean square

SISO single-input and single-output

VAF variance-accounted-for

1. Introduction

The number of studies in the field of human gait recognition using various artificial intelligence techniques has increased over the last two decades [1]. Fuzzy logic is an influential rule-based technique in the artificial intelligence domain that helps predict and identify patterns of human gait movement and running conditions [2, 3]. However, few studies have utilized FIS to predict running conditions (e.g. slow, medium and fast) and patterns.

A recent study conducted by Mikolajewska et al. assessed the results of post-stroke gait re-education through the application of traditional and fuzzy-based analyses [4]. Specifically, these researchers assessed spatiotemporal gait parameters before and after therapy and compared the results using a fuzzy-based assessment tools. Xu et al. used fuzzy logic and neural network techniques and four parameters, namely the Staheli index, Chippaux-Smirak index, arch index and modified arch index, as the classification features and collected gait data using various instruments, such as a force platform, stereometric system, accelerometer and pressure platform [5]. Another fuzzy-and-neural-network-based study focused on the gait performance, postural stability, and depression of Parkinson's patients [6], using the Berg Balance Scale, the Dynamic Gait index, and the Geriatric Depression Scale. In another medical-based expert system using fuzzy and neural networks for patients with idiopathic scoliosis, researchers extracted kinetic data and used time and walking parameters in the analysis [7]. Several studies have applied fuzzy systems for the development of a mechatronic-based system (such as a robotic haptic or exoskeleton device) that can be used for assessing gait [8-10]. Researchers have selected different input-output parameters related to walking, force and motion velocity, such as ground reaction force, impulse disturbance, and internal biological electromyography noise interference, for evaluating their fuzzy system with the aim of improving the tracking performance and driving the exoskeleton. In contrast, fuzzy logic has been applied for identifying different speed patterns in cases such as vehicles, electronic motors and wind turbines, but not for detecting human running speed [11-13].

While these aforementioned studies have shown the use of fuzzy-based systems, these studies have generally used multiple camera-based gait analysis systems for the input data. However, these gait analysis tools are relatively expensive and restricted to gait labs. In contrast, wireless accelerometers are inexpensive and portable. Unfortunately, few studies have incorporated FIS-analysis techniques using accelerometer gait data [14, 15]. Thus, the FIS-based recognition of running conditions using a triaxial accelerometer is a novel idea in gait analysis. Therefore, this study investigated whether the developed Single-Input and Single-Output (SISO)-based fuzzy model was able to accurately identify different running conditions. Specifically, we proposed the following hypotheses: (i) if the triaxial accelerometer yields low, average and high RMS values, the output will be slow, medium and fast running condition, respectively, and (ii) the calculated RMSE, MSE, VAF, NDEI and correlation results from the actual and predicted values are acceptable in terms of evaluating performance and error evaluation. To the best of our knowledge, this study provides the first FIS-based running conditions identification approach based on signals generated by a single triaxial accelerometer.

2. Methodology

Three runners participated in the study and provided written informed consent. The runners did not have any history of disorder or pain in their lower limbs. This protocol was approved by the University of Calgary Conjoint

Health Research Ethics Board and the runners were treated in accordance with the ethical standards of the Declaration of Helsinki. A 3D accelerometer (Shimmer3 GSR+®±8 g, Shimmer Inc., Dublin IE) was placed over top the sacrum of each runner to record center of mass acceleration at a sampling frequency of 201.03 Hz. The runner was then instructed to run on a treadmill for approximately 60 s (about 12,000 data points) for each of three running trials with a maximum 2-min rest interval between the trials. Accelerometer data were collected for the three axes of the accelerometer (X, Y and Z). Ten thousand data points from the middle of each trial were considered which was divided into 10 approximately 5-s data epoch windows (1,000 data points in each window) with no overlapping. The acceleration signal from each window was Band-pass filtered at 20-100 Hz using a third-order Butterworth filter. A feature extraction metric, namely the root mean square (RMS), was calculated from the X, Y and Z axes. To consider the three-dimensional acceleration uniformly, the resultant of the three axes was considered, and the corresponding RMS was ca lculated in a manner similar to that proposed by Purwar et al. [16].

The calculated RMS value was adjusted automatically by the developed FIS system to obtain the exact connection between the input and the output. Statistical analysis was performed using MedCalc for Windows, version 17.6 (MedCalc Software Ostend, Belgium).

2.1. Fuzzy Inference System

A fuzzy inference system (FIS) operates on knowledge stated in terms of 'if-then' rules and can be applied to predict the behavior of many undefined systems and data-driven decision-making process [17]. The main advantage of FIS is that it does not require any knowledge of the underlying physical process as a prerequisite for its application. Fig. 1 illustrated the simple block diagram of the developed Single-Input and Single-Output (SISO)-based FIS system. As shown in the figure, the accelerometer data from three axes (X, Y and Z) were served as the input variables to the system, and the running conditions, which were classified as 'slow', 'medium' or 'fast', was the output of the system. The accelerometer data were first used as the input variables for a fuzzification process, wherein fuzzy arithmetic and criteria were applied based on the input variables with certain rules, and the final results were defuzzified to yield the output. A simple MATLAB code to evaluate the Mamdani FIS (predicted value) with actual data is given below. Here, 'FMS' was the name which stored actual data, 'mamdani' was the name of the developed FIS model, 'evalfis' was the built-in keyword which performed the evaluation process between actual ('FMS') and the generated data ('fis'), and then, the predicted data from the model was stored in 'output'. Finally, the actual data ('FMS') and the predicted data ('output') from the developed model were used to evaluate the performance and error. load FMS;

fis = readfis('mamdani'); output = evalfis (FMS, fis);

In this study, a single-input and single-output (SISO)-based Mamdani fuzzy model with the following three rules was developed:

i) If Accl is Low, then Running Condition is Slow

ii) If Accl is Average, then Running Condition is Medium

iii) If Accl is High, then Running Condition is Fast

Note that Accl represents the RMS value of the triaxial accelerometer data and that value was the classification of the running condition. Table 1 presents the overall parameters used to develop the FIS model. The first column presents the different conditions of the accelerometer data, which correspond to changes in the predicted running condition. Accordingly, the rules were set to change the output parameters according to the different conditions of the input parameters. Table 2 represents the fuzzy input and output ranges as well as fuzzy sets.

Fig. 1 Block Diagram of FIS Table 1 Different parameters of FIS

Parameter type Name/value

Input 01

Output 01

Rules 03

MF Type Triangular-shaped

Defuzzification Centroid

MF: Membership Function

Table 2: Fuzzy sets for the input and output variables.

Input Output

Accelerometer Ranges 0.35-1.5 Fuzzy Sets Low Results(RMS); Running Conditions Ranges <1.5 Fuzzy Sets Slow

(RMS) 1.5-1.8 1.7-2.0 Average High 1.5-1.8 1.8-2.0 Medium Fast

The results of the FIS were simulated using the MATLAB® (Matlab Version 2016b) Fuzzy Logic Toolbox, which also provides graphical user interface tools, including the FIS Editor, the Membership Function Editor, the Rule Editor, the Rule Viewer and the Surface Viewer. The FIS Editor handles the high-level issues of the system, in which several input and output variables were defined with specific names. This editor was used to define the shapes of all the membership functions (MF) associated with each variable. A few membership functions were available for fuzzy inference systems. In this model, triangular membership function was used [17], defined as:

MPmangular (x\a,b,C) =

0, x < a

x - a a < x < b b - a

c - x b < x < c

c - b 0, c < x

3. Results and discussion

The root mean square error (RMSE), mean absolute error (MAE) and and variance-accounted-for (VAF) were calculated using Equations (3), (4) and (5):

RMSE =

—Ye2 (3)

MAE = N Lfi (4)

VAF = 11--XlOO (5)

where e = (x - X), xi and x. were the actual and predicted RMS values, respectively, and N is the total number of

samples. Finally, NDEI (non-dimensional error index) was the value of RMSE divided by standard deviation. These performance measurement techniques have been used for evaluating performance and error of the developed model.

Table 3 Performance indices: actual vs. predicted values

Testing conditions RMSE MAE NDEI r p VAF (%)

FMS 0.059 0.213 0.147 0.89 0.001 96.54

FMS: Fast-Medium-Slow

Table 3 shows the relationship between the actual and predicted values under the criteria in which the data were arranged and tested as Fast-Medium-Slow (FMS). The correlation between the actual and predicted RMS value was found to be strong (r = 0.89, p < 0.001). Variance-Accounted-For (%VAF) was used to quantify the quality of the fitting, with an accuracy as high as 96.54%. Fig. 2 shows three running conditions between predicted and actual RMS value. Here, each running condition has 10 data points (RMS value), i.e. total 30 data points for three conditions. However, the figure shows a total of 21 data points due to duplicity of some data and as such, the remaining 9 data points are invisible. Fig. 2 also represents the coefficient of determination (R2), which determined an acceptable percentage for the model as 81%. Coefficient of determination also revealed the result of residual standard deviation equal to 0.178 which gives the difference between observed and predicted values. In addition, the

Predicted Vs. Actual, by Model

1.4 1.5 1.6 1.7 1.8 1.9 2.0

Actual Value (RMS)

Fig. 2: Coefficient of determination between actual and predicted (model) values.

RMSE, MAE and NDEI of the prediction was found to equal 5.9%, 21.3% and 14.7% respectively, indicating that the proposed FIS demonstrates satisfactory performance. As a result, the developed FIS model can be effectively used as a prediction tool for running speed (slow, medium and fast) identification.

The FIS rule viewer is shown in Fig. 3. This figure illustrates the FIS simulation results for the slow and fast predicted running conditions. In this application, the fuzzy controller estimated the running condition as a function of triaxial accelerometer data. Note a lower accelerometer value corresponds to a lower predicted RMS, whereas a high accelerometer value results in higher predicted RMS values. Similar results were also obtained when the data were arranged according to the following sequences and tested with the developed FIS: Medium-Fast-Slow (MFS), Slow-Fast-Medium (SFM), Fast-Slow-Medium (FSM), Slow-Medium-Fast (SMF) and using a large group of randomly selected samples.

2 Input

Running-Condition = 0.849

ACCL(X+Y+Z) =1.9

'Slow" Running:/ Condition \

Running-Condition = 1.86

"Fast" Running: Condition

(a) (b) Fig. 3: FIS relationship between accelerometer data and running condition (a) during slow running (b) during fast running.

Output

The FIS surface viewer is shown in Fig. 4. The purpose of the surface viewer was to display the relationship between input(s) and output(s) by generating and plotting output surface maps for the system. It also shows that increases with RMS in a particular manner in different running conditions such as slow, medium and fast. The generated surface view shows that an increase in the target input value results in increase in RMS for the associated running speed, but this increment order was not linear with respect to the increase in the accelerometer value because the FIS was driven by the fuzzy rules.

Fig. 4: Surface viewer of the FIS simulation result.

Finally, the findings of this study could aid the development of gait recognition system. Additionally, the results can be applied in diverse biomedical applications, such as neuromuscular system analysis, ergonomics, biomechanics and rehabilitation engineering. Additionally, the results of this study might expand the current understanding of running mechanics. However, despite its satisfactory results and findings, this study has a few

limitations. Namely, only three subjects were included in the study, the reliability of the method is dependent on one sensor and the reliability of running condition recognition could be improved by adding more sensors, such as a GPS for outdoor overground running. Thus, there is a need to further investigate a larger number of subjects, as will be considered in our future works.

4. Conclusions

A running condition (slow, medium and fast) recognizing model was developed in this study using single-input single-output fuzzy logic technique. The main advantage of the proposed method is its simplicity. Only one sensor, i.e., an accelerometer, was used for assessing three main running conditions. Additionally, the fuzzy rules are simple and effectively estimate running condition. Therefore, the proposed FIS model is readable, rapid, and easily extendable, which makes it suitable and valuable for real-time running condition classification. In addition, the surface viewer of the system shows a smooth surface, which can easily provide a clearer image for evaluating the running condition.

Acknowledgements

This study was partially funded by the Natural Sciences and Engineering Research Council of Canada (NSERC: Discovery Grant 1028495 and Accelerator Award 1030390), a University of Calgary Eyes High Postdoctoral Research award, and a Strategic Research Grant from the Vice-President (Research) at the University of Calgary.

References

1. Lapham A, Bartlett R. The use of artificial intelligence in the analysis of sports performance: A review of applications in human gait analysis and future directions for sports biomechanics. Journal of Sports Sciences. 1995;13(3):229-37.

2. Chau T. A review of analytical techniques for gait data. Part 1: fuzzy, statistical and fractal methods. Gait & posture. 2001;13(1):49-66.

3. Ali A, Sundaraj K, Ahmad B, Ahamed N, Islam A. Gait disorder rehabilitation using vision and non-vision based sensors: a systematic review. Bosnian journal of basic medical sciences. 2012;12(3):193.

4. Mikolajewska E, Prokopowicz P, Mikolajewski D. Computational gait analysis using fuzzy logic for everyday clinical purposes-preliminary findings. Bio-Algorithms and Med-Systems. 2017;13(1):37-42.

5. Xu S, Zhou X, Sun Y-N. A novel gait analysis system based on adaptive neuro-fuzzy inference system. Expert Systems with Applications. 2010;37(2):1265-9.

6. Woo Y, Lee J, Hwang S, Hong CP. Use of an adaptive neuro-fuzzy inference system to obtain the correspondence among balance, gait, and depression for Parkinson's disease. Journal of the Korean Physical Society. 2013;62(6):959-65.

7. Choi A, Yun TS, Suh SW, Yang JH, Park H, Lee S, et al. Determination of input variables for the development of a gait asymmetry expert system in patients with idiopathic scoliosis. International Journal of Precision Engineering and Manufacturing. 2013;14(5):811-8.

8. Chen B-S, Wu C-C, Chen Y-W. Human walking gait with 11-DOF humanoid robot through robust neural fuzzy networks tracking control. International Journal of Fuzzy Systems. 2013;15(1):22-35.

9. Jin X, Zhu S, Zhu X, Chen Q, Zhang X. Single-input adaptive fuzzy sliding mode control of the lower extremity exoskeleton based on human-robot interaction. Advances in Mechanical Engineering. 2017;9(2):1687814016686665.

10. Bakircioglu V, §en MA, Kalyoncu M, editors. Adaptive Neural-Network Based Fuzzy Logic (ANFIS) Based Trajectory Controller Design for One Leg of a Quadruped Robot. Proceedings of the 5th International Conference on Mechatronics and Control Engineering; 2016: ACM.

11. Perng J-W, Lai Y-H. Robust Longitudinal Speed Control of Hybrid Electric Vehicles with a Two-Degree-of-Freedom Fuzzy Logic Controller. Energies. 2016;9(4):290.

12. Chekroun S, Zerikat M, Mechernene A, Benharir N, editors. Novel Observer Scheme of Fuzzy-MRAS Sensorless Speed Control of Induction Motor Drive. Journal of Physics: Conference Series; 2017: IOP Publishing.

13. Rezvani A, Esmaeily A, Etaati H, Mohammadinodoushan M. Intelligent hybrid power generation system using new hybrid fuzzy-neural for photovoltaic system and RBFNSM for wind turbine in the grid connected mode. Frontiers in Energy. 2017:1-18.

14. Kepski M, Kwolek B, Austvoll I, editors. Fuzzy inference-based reliable fall detection using Kinect and accelerometer. Artificial Intelligence and Soft Computing; 2012: Springer.

15. Kwolek B, Kepski M. Fuzzy inference-based fall detection using kinect and body-worn accelerometer. Applied Soft Computing. 2016;40:305-18.

16. Purwar A, Jeong DU, Chung WY, editors. Activity monitoring from real-time triaxial accelerometer data using sensor network. Control, Automation and Systems, 2007 ICCAS'07 International Conference on; 2007: IEEE.

17. Ahamed NU, Taha ZB, Khairuddin IBM, Rabbi M, Rahaman SM, Sundaraj K, editors. Fuzzy logic controller design for intelligent air-conditioning system. Control Science and Systems Engineering (ICCSSE), 2016 2nd International Conference on; 2016: IEEE.