Typically, a Parkinson’s disease (PD) patient would display instances of tremor and bradykinesia (slowness of movement) at an early stage of the disease and later develop gait disturbances and postural instability. So, it is important to measure the tremor occurrences in subjects to detect the onset of PD. Also, it is equally essential to monitor the gait impairments that the patient displays, as the order at which the PD symptoms appear in subjects vary from one to another. The primary goal of this thesis is to develop a monitoring system for PD patients using wearable sensors. To achieve that objective, our work focused first on identifying the most significant features that would best distinguish between PD and normal healthy subjects. Here, the various gait and tremor features were extracted from the raw data collected from the wearable sensors and further analyzed using statistical analysis and pattern classification techniques to pick the most significant features. In statistical analysis, the analysis of variance (ANOVA) test was conducted to differentiate the subjects based on the values of the mean. Further, pattern classification was carried out using the Linear Discriminant Analysis (LDA) algorithm. The analysis of our results shows that the features of heel force, step distance, stance and swing phases contributed more significantly to achieving a better classification between a PD and a normal subject, in comparison with other features. Moreover, the tremor analysis based on the frequency-domain characteristics of the signal including amplitude, power distribution, frequency dispersion, and median frequency was carried out to identify PD tremor from different types of artifacts.

Background: The yearly incidence of people with Spinal Cord Injury (SCI) is between250,000 and 500,000, according to the World Health Organization (WHO). The injury often reduces the ability to walk. Various consequences affect the nervous system and, thus, the entire body. Therefore, the patient population with SCI is highly heterogeneous also in their gait patterns. Multiple tools are used to classify and understand the walking impairments caused by the injury. Objective: To underline the added value brought by the integration of 3D gait analysis to more standard methods (GDI, GPS, GVS, spatiotemporal parameters, ASIAgrade, muscle strength, and spasticity) in the evaluation and interpretation of gait patterns of subjects with SCI. Methods: 3D gait analysis with a passive optical motion capture system (Vicon)and four force plates was performed in 7 control subjects and 3 with SCI. The model used for marker placement and pre-processing was CGM 2.3. Matlab was used to analyze and plot the kinematic and kinetic joints’ data and calculate the GDI, GPS, and GVS indexes and spatiotemporal parameters for subjects with SCI and the control group. A specialized physiotherapist conducted the clinical assessment of the patients with SCI in a rehabilitation center. This included: ASIA grade and review, muscle strength, and spasticity with Daniels Whorthingham scale and Modified Ashworth scale, respectively. The evaluation of the result was qualitative. Results: The integration of 3D gait analysis show further understanding in the assessment of walking impairments. The indexes resumed the impairments and classified the subjects but lacked temporal and functional perspective. Gait phases and spatiotemporal parameters suggested difficulties in stability and balance but could not identify the problem’s origin. Lastly, clinical assessment enlightened the singular motor and sensory function impairments. 3D gait analysis contextualized these results identifying gait patterns and functional implications. Conclusion: Integrating 3D gait analysis might give a deeper understanding of subjects with SCI’s gait strategies and impairments. Indeed this complex technique links the other methods’ results, contextualizing them and gaining information.