Page 281 - Handbook of Biomechatronics

274 Georgios A. Bertos and Evangelos G. Papadopoulos

Walking Standing
Standing Walking
Sitting
1 Sitting
1
1
X 3 0 0
X 3 0.5
–1 X 3 0
1 1
–1
1 –0.5
0 –1 0
X 2 1 0 –1 1 X 1
0 X 1 0 0
–1 –1 –1 1 X 2 X 3 –1 –1
X 1
(A) (B)
Fig. 23 (A) PCA (left) and LDA (right) dimension reduced features extracted from 200
sample-long frames. (B) GMMs surface plots for standing, walking, and sitting showing
the portions of the feature space, where probability density function is greater than
0.05, for 3D LDA reduced data. (From Varol, H.A., Sup, F., Goldfarb, M., 2010. Multiclass
real-time intent recognition of a powered lower limb prosthesis. IEEE Trans. Biomed. Eng.
57(3), 542–551. https://doi.org/10.1109/TBME.2009.2034734.)

7 DISCUSSION/REALIGNMENT

As discussed in this chapter, basic walking especially for transtibial
amputees can be achieved in a satisfactory degree by conventional prosthe-
ses. When we start seeking sports performance or ability to walk on slope,
ascend and descend stairs, dancing, jumping, etc., then we are looking at
more specialized and advanced prostheses.
Current cutting-edge technologies such as pattern recognition, TMR,
osseointegration, and active prostheses are going to enable the unification
all the necessary ambulatory tasks to be satisfied and executed seamlessly
by a single prosthesis, while advancing performance. In particular,
osseointegration can be an enabler technique for bilateral transfemoral
amputees.
Further clinical studies are needed in order to quantify the effect of active
prostheses on walking speed and metabolic energy.
Attention has to be paid to make sure needs and amputee voice of cus-
tomer (VOC) are considered when investing in new research threads.

AUTHORS’ CONTRIBUTIONS

GAB was responsible for the outline, the structure, and the content of
the chapter. GAB wrote all sections. EGP reviewed the chapter.