![\"\"](\"https:\/\/project.inria.fr\/bowi\/files\/2019\/06\/simu1.png\")
<\/a>Figure 1: Principle of the BoWI simulator<\/p><\/div>\n
Outcomes<\/strong><\/h3>\nThe simulator has been successfully used to compare and select a set of algorithms that have been partially implemented on the Zyggie V1 demonstrator and will be fully implemented on Zyggie V2. These algorithms are also necessary for the design of a dedicated Node Architecture that will be evaluated as candidate for an ultra low-power ASIC implementation. Figure 2 shows how the simulator can be used to test different algorithms in the context of gesture and posture identification. The algorithms first tested using the simulator were:<\/p>\n
\n- The Extended Kalman Filter (EKF) computes the orientation of the node.<\/li>\n
- The LMS filter is used to predict position and speed.<\/li>\n
- IPE is an iterative and cooperative algorithm to compute node positions based on estimates of other nodes’ position.<\/li>\n
- A classification algorithm (PCA-based for the first version) is also introduced to estimate a posture according to a library of partial postures (arm, back, legs) proposed by BoWI designers. This classification is distributed among the sensor nodes and central node (the user\u2019s smartphone). The classification is based on posture radio signatures that take advantage of BoWI intrinsic redundancy.<\/li>\n<\/ul>\n
![\"\"](\"https:\/\/project.inria.fr\/bowi\/files\/2019\/06\/BoWI_Simulator_scheme-1024x617.png\")
<\/a>Figure 2: BoWI Simulator instance to test different algorithms in the context of posture detection.<\/p><\/div>\n
As a relevant example, Figure 3 depicts the results of simulator outputs on a continuous\u00a0Capoeira<\/em>\u00a0movement.\u00a0The simulator was absolutely necessary to design and refine the sets of algorithms and was also an essential tool to identify opportunities and limitations of the BoWI approach.<\/p>\n![\"\"](\"https:\/\/project.inria.fr\/bowi\/files\/2019\/06\/BoWI_Simulator_scheme2-1024x742.png\")
<\/a>Figure 3: Illustration, with a Capoeira movement, of possible signatures to be extracted during a PCA-based classification.<\/p><\/div>\n
he different algorithms were designed and simulated in the context of three application classes:<\/p>\n
\n- Static Posture<\/strong>\u00a0recognition based on accelerometer, magnetometer and\/or RSSI measurements and classification algorithms (e.g. PCA).\n
\n- Applications<\/strong>: Simon Posture Game (repetition of postures), Home Control.<\/li>\n<\/ul>\n<\/li>\n
- Gesture Recognition<\/strong>\u00a0is considered as a temporal sequence of static postures, including sparse use of gyroscopes.\n
\n- Applications<\/strong>: Remote (at home) Functional Rehabilitation, Sport gesture monitoring, Musculoskeletal disorders risk monitoring (workplace risk prevention).<\/li>\n<\/ul>\n<\/li>\n
- Motion Capture<\/strong>\u00a0is not based on classification but on orientation determination and 3D geolocation of the nodes.\n
\n- Applications<\/strong>: Gesture recording, Video Game, etc.<\/li>\n<\/ul>\n<\/li>\n<\/ol>\n
igure 4 shows an example of 12 postures that were used for an application of static posture recognition. Results in Figure 5 represent the error rate for each posture as a function of the orientation error of the user. This orientation error represents the tolerance of the system to recognize inexact postures with a PCA using two eigenvalues with orientation data only (Fig. 5 left) and orientation + RSSI (Fig. 5 right).<\/p>\n
![\"\"](\"https:\/\/project.inria.fr\/bowi\/files\/2019\/06\/simu2-1024x196.png\")
<\/a>igure 4: Example of Static Posture recognition on 12 postures.<\/p><\/div>\n
<\/a>Figure 2: BoWI Simulator instance to test different algorithms in the context of posture detection.<\/p><\/div>\n
As a relevant example, Figure 3 depicts the results of simulator outputs on a continuous\u00a0Capoeira<\/em>\u00a0movement.\u00a0The simulator was absolutely necessary to design and refine the sets of algorithms and was also an essential tool to identify opportunities and limitations of the BoWI approach.<\/p>\n Figure 3: Illustration, with a Capoeira movement, of possible signatures to be extracted during a PCA-based classification.<\/p><\/div>\n he different algorithms were designed and simulated in the context of three application classes:<\/p>\n igure 4 shows an example of 12 postures that were used for an application of static posture recognition. Results in Figure 5 represent the error rate for each posture as a function of the orientation error of the user. This orientation error represents the tolerance of the system to recognize inexact postures with a PCA using two eigenvalues with orientation data only (Fig. 5 left) and orientation + RSSI (Fig. 5 right).<\/p>\n igure 4: Example of Static Posture recognition on 12 postures.<\/p><\/div>\n<\/a>\n
\n
\n
\n
<\/a>