Change search
ReferencesLink to record
Permanent link

Direct link
Real-Time Gait Analysis Algorithm for Patient Activity Detection to Understand and Respond to the Movements
Blekinge Institute of Technology, School of Computing.
Blekinge Institute of Technology, School of Computing.
2012 (English)Independent thesis Advanced level (degree of Master (Two Years))Student thesis
Abstract [en]

Context: Most of the patients suffering from any neurological disorder pose ambulatory disturbance at any stage of disease which may result in falling without showing any warning sign and every patient is different from another. So there is a need to develop a mechanism to detect shaky motion. Objectives: The major objectives are: (i) To check different gait parameters in walking disorders using Shimmer platform (R). (ii) Wearing SHIMMER wireless sensors on hip, waist and chest, to check which one is the most suitable. (iii) To draw effective conclusion/results based on calibrated data in real time and offline processing in EyesWeb/Matlab.To develop an effective mechanism/algorithm for security warning and activating alarm systems. Methods: Our thesis project is related to analyze real-time gait of the patient suffering from Parkinson's disease for actively responding to the shaky movements. Based on real world data, we have developed a mechanism to monitor a real time gait analysis algorithm to detect any gait deviation. This algorithm is efficient, sensitive to detect miner deviation and not hard coded i.e. user can set Sampling Rate & Threshold values to analyze motion. Researchers can directly use this algorithm in their study without need to implement themselves. It works on pre-calculated threshold values while initial sampling rate is set to 100MHz. Results: Accelerometers putting on the chest shows high unnecessary acceleration during fall, suggest putting on waist position. Also, if a patient initiates steps with energy, his/her gait may become more stable as shown in the conscious gait. Results show that after DBS surgical procedure, the patient still experiences postural instability with fall. So it is evident to show that such patients may have reduced cognition even after surgery. Another finding is that such patients may lean left or right during turning. Conclusions: We have presented a real time gait analysis algorithm, capable of detecting the motion of the patient with PD to actively respond to the shakier motion setting threshold values. Our proposed algorithm is easy to implement, reusable and can affectively generate healthcare alarms. Additionally, this system might be used by other researchers without the need to implement by themselves. The proposed method is sensitive to detect fall therefore objectively can be used for fall risk assessment as well .The same algorithm with minor modifications can be used for seizure detection in other disorders mainly epileptic seizers to alert health providers for emergency.

Abstract [sv]

Any malfunctioning of neurons in the nervous system is called Neurological disorder. Over 100 neurological disorders have been discovered throughout the world. In our study, we have chosen one disorder: Falling in Parkinson’s disease. Experiments can be performed on different gait parameters like body velocity, time ratio, ground slope, stance/swing, body gestures and gait patterns. Sensors can be put on hips, knees, thighs, limbs, neck, head, chest or any other suitable body part to capture motion data for further pre-and post-processing. Pre-processing is real time gait analysis through time domain and frequency domain to trigger various security steps and messages for patient care. Post -processing is offline analysis of motion data in different tools such as EyesWeb, BioMOBIUS and Matlab for calculations, analysis and plotting of motion to take decisions to formulate a mechanism for patient activity detection and monitoring. The area which we choose is pretty interesting, pertaining to rehabilitation, wellness and healthcare for older people. Other related keywords may include keywords may be helpful using one or combination of more than one. WSN, BAN or WBAN, biosensors, neurological disorders, gait analysis, fall detection, fall avoidance, Parkinson’s disease, wireless accelerometer, ambulatory monitoring, freezing of gait and fall risk assessment. Most of the patients suffering from any neurological disorder in later stages of disease pose ambulatory disturbance especially falling. Such patients may fall without showing any warning sign and every patient is different from another. So there is a need to develop a mechanism to detect shaky motion to avoid such patients from falling. Therefore, a real time gait analysis algorithm is implemented to trigger security alarms. In order to assess & evaluate gait analysis, accurate, reliable & consistent measurement tools need to be utilized. Even slight deviation in the data monitoring through measurement tools is not encouraged to use [21]. Gait disturbance can be measured using 3 axis accelerometers like SHIMMER(R) for real time motion analysis. In the wireless sensor network, SHIMMER platform provides wireless Body Area Network (BAN) to capture motion data. This data can be saved in CSV (Comma Separated Version) file for post processing or a 2 GB MicroSD card can be used to capture data in the SHIMMER accelerometer itself. The use of accelerometer is more suitable due to the fact that we are 66 capturing data from postural instability. One two or combinations of accelerometers can be put on different body parts. SHIMMER Gyroscope is more suitable for jerky motion with disease such as epilepsy. Mostly accelerometers and gyroscopes are used for gait analysis [4]. Defining our research work, this study is carried out on the patient with Parkinson’s disease (PD), to study various gait parameters, test wireless accelerometers on different body parts, and implementing an algorithm to trigger a security alarm system by setting a threshold value. Criteria for setting threshold value are calculating standard deviation and employed by different researchers like [3]. The main motivation to perform this experimental research work is to avoid the patient with PD from falling during unstable shaky gait. Security alarms can be activated whenever a patient poses a shakier gait. Two types of alarms or sirens can be activated in the lgorithm. First, to activate Warning Alarms when the value from motion data exceeds maximum threshold value 1 and second to activate Emergency Alarms when the value from motion data exceeds maximum threshold value 2. Later on airbag can be put on the patient’s hip position to avoid him/her from injury and hip fracture. The results show the proposed system is fairly simple to implement in the real time environment, flexible to adjust to any necessary change in the future.The major advantage of this algorithm is its reusability. Algorithm is not hard coded because a user can set his own sampling rate or threshold value or both, and check results. This algorithm is further modifiable to trigger airbag, a security push button, SOS calls, messages, siren activation system, automatic email forwarding, health care alert, and many more. The same algorithm with minor modifications can be used for fall avoidance or health care assurance on other disorders mainly in epileptic seizers to alert health providers in case of emergency, can be used for other seizures and disorders such as epilepsy, etc. Overall, this report presents the analysis of an experiment to measure the usability of wireless accelerometer data to monitor the activity of the patient suffering from Parkinson disease. Our research and experimental work can be quoted toward fall risk assessment.

Place, publisher, year, edition, pages
2012. , 80 p.
Keyword [en]
Parkinson's disease, Gait Analysis, Movement Disorder, Wireless Sensors
National Category
Computer Science Human Computer Interaction
URN: urn:nbn:se:bth-2004Local ID: diva2:829264
Inam-ul-Haq Lindblomsvagen 37233 Ronneby +46 760609660Available from: 2015-04-22 Created: 2012-11-28 Last updated: 2015-06-30Bibliographically approved

Open Access in DiVA

fulltext(2108 kB)140 downloads
File information
File name FULLTEXT01.pdfFile size 2108 kBChecksum SHA-512
Type fulltextMimetype application/pdf

By organisation
School of Computing
Computer ScienceHuman Computer Interaction

Search outside of DiVA

GoogleGoogle Scholar
Total: 140 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Total: 61 hits
ReferencesLink to record
Permanent link

Direct link