No abstract

Anteflexion of the spine is essential for many physical activities of daily living. However, this motion places the lumbar disks because it generats heavy load due to changes in the shape of the lumbar spine and can lead to low back pain. In older to reduce low back pain, here we proposed a wearable sensor system configuration that can estimate lumbosacral alignment and lumbar load by measuring the shape of the lumbar skin when the lumbosacral alignment changes. The shape of the lumbar skin and posture angle are measured by using curvature sensors and accelerometers. In addition, the system must be constructed in consideration of the physique, in order to absorb in a variety of human. We proposed this system by measuring the body parameters of anteflexion and studied the change in dimensions of the lumbar spine from changes in posture. By extracting the dimensions of the lumbosacral spine in X-ray images, the attitude angle, body surface area and the dimensions of the lumbosacral spine have relevance. The lumbosacral dimensions calibration method was developed by using that relation. Lumbosacral alignment estimation considering the difference in physiques is developed, and lumbosacral spine alignment was to improve the estimation accuracy. The proposed method could improve accuracy lumbosacral alignment estimation.

No abstract

Anteflexion of the spine is essential for many physical activities in everyday life. However, this motion places the lumbar disks under heavy load due to changes in the shape of the lumbar spine and can lead to low back pain. With the aim of reducing low back pain, here we developed a wearable sensor system that can estimate lumbosacral alignment and lumbar load by measuring the shape of the lumbar skin when the lumbosacral alignment changes. In addition, we used this system to measure the parameters of anteflexion and studied the change in dimensions of the lumbar spine from changes in posture. By determining the dimensions of the lumbosacral spine on an X-ray image, a lumbosacral dimensions calibration method based on body surface area and height was developed. By using this method, lumbosacral alignment and lumbar load could be accurately estimated using the wearable sensor system.

This paper presents a novel low cost learning algorithm for a test feature classifier by use of an overlap index list (OIL). In general, classifiers need a large amount of training data to achieve the high performance, which results in long computation times. The proposed algorithm using OIL can maintain search and check elemental combinatorial features from lower dimensions up to higher ones.