Developing a Low-Cost Force Treadmill via Dynamic Modeling.

By incorporating force transducers into treadmills, force platform-instrumented treadmills (commonly called force treadmills) can collect large amounts of gait data and enable the ground reaction force (GRF) to be calculated. However, the high cost of force treadmills has limited their adoption. This paper proposes a low-cost force treadmill system with force sensors installed underneath a standard exercise treadmill. It identifies and compensates for the force transmission dynamics from the actual GRF applied on the treadmill track surface to the force transmitted to the force sensors underneath the treadmill body. This study also proposes a testing procedure to assess the GRF measurement accuracy of force treadmills. Using this procedure in estimating the GRF of "walk-on-the-spot motion," it was found that the total harmonic distortion of the tested force treadmill system was about 1.69%, demonstrating the effectiveness of the approach.

Assessing postural stability via the correlation patterns of vertical ground reaction force components.

BACKGROUND: Many methods have been proposed to assess the stability of human postural balance by using a force plate. While most of these approaches characterize postural stability by extracting features from the trajectory of the center of pressure (COP), this work develops stability measures derived from components of the ground reaction force (GRF). METHODS: In comparison with previous GRF-based approaches that extract stability features from the GRF resultant force, this study proposes three feature sets derived from the correlation patterns among the vertical GRF (VGRF) components. The first and second feature sets quantitatively assess the strength and changing speed of the correlation patterns, respectively. The third feature set is used to quantify the stabilizing effect of the GRF coordination patterns on the COP. RESULTS: In addition to experimentally demonstrating the reliability of the proposed features, the efficacy of the proposed features has also been tested by using them to classify two age groups (18-24 and 65-73 years) in quiet standing. The experimental results show that the proposed features are considerably more sensitive to aging than one of the most effective conventional COP features and two recently proposed COM features. CONCLUSIONS: By extracting information from the correlation patterns of the VGRF components, this study proposes three sets of features to assess human postural stability during quiet standing. As demonstrated by the experimental results, the proposed features are not only robust to inter-trial variability but also more accurate than the tested COP and COM features in classifying the older and younger age groups. An additional advantage of the proposed approach is that it reduces the force sensing requirement from 3D to 1D, substantially reducing the cost of the force plate measurement system.

Detecting slow wave sleep using a single EEG signal channel.

BACKGROUND: In addition to the cost and complexity of processing multiple signal channels, manual sleep staging is also tedious, time consuming, and error-prone. The aim of this paper is to propose an automatic slow wave sleep (SWS) detection method that uses only one channel of the electroencephalography (EEG) signal. NEW METHOD: The proposed approach distinguishes itself from previous automatic sleep staging methods by using three specially designed feature groups. The first feature group characterizes the waveform pattern of the EEG signal. The remaining two feature groups are developed to resolve the difficulties caused by interpersonal EEG signal differences. RESULTS AND COMPARISON WITH EXISTING METHODS: The proposed approach was tested with 1,003 subjects, and the SWS detection results show kappa coefficient at 0.66, an accuracy level of 0.973, a sensitivity score of 0.644 and a positive predictive value of 0.709. By excluding sleep apnea patients and persons whose age is older than 55, the SWS detection results improved to kappa coefficient, 0.76; accuracy, 0.963; sensitivity, 0.758; and positive predictive value, 0.812. CONCLUSIONS: With newly developed signal features, this study proposed and tested a single-channel EEG-based SWS detection method. The effectiveness of the proposed approach was demonstrated by applying it to detect the SWS of 1003 subjects. Our test results show that a low SWS ratio and sleep apnea can degrade the performance of SWS detection. The results also show that a large and accurately staged sleep dataset is of great importance when developing automatic sleep staging methods.

A comparative study for 2D and 3D computer-aided diagnosis methods for solitary pulmonary nodules.

Many computer-aided diagnosis (CAD) methods, including 2D and 3D approaches, have been proposed for solitary pulmonary nodules (SPNs). However, the detection and diagnosis of SPNs remain challenging in many clinical circumstances. One goal of this work is to investigate the relative diagnostic accuracy of 2D and 3D methods. An additional goal is to develop a two-stage approach that combines the simplicity of 2D and the accuracy of 3D methods. The experimental results show statistically significant differences between the diagnostic accuracy of 2D and 3D methods. The results also show that with a very minor drop in diagnostic performance the two-stage approach can significantly reduce the number of nodules needed to be processed by the 3D method, streamlining the computational demand.

One-class-at-a-time removal sequence planning method for multiclass classification problems.

Using dynamic programming, this work develops a one-class-at-a-time removal sequence planning method to decompose a multiclass classification problem into a series of two-class problems. Compared with previous decomposition methods, the approach has the following distinct features. First, under the one-class-at-a-time framework, the approach guarantees the optimality of the decomposition. Second, for a K-class problem, the number of binary classifiers required by the method is only K-1. Third, to achieve higher classification accuracy, the approach can easily be adapted to form a committee machine. A drawback of the approach is that its computational burden increases rapidly with the number of classes. To resolve this difficulty, a partial decomposition technique is introduced that reduces the computational cost by generating a suboptimal solution. Experimental results demonstrate that the proposed approach consistently outperforms two conventional decomposition methods.

Effect of keyswitch design of desktop and notebook keyboards related to key stiffness and typing force.

This study aimed to compare and analyse rubber-dome desktop, spring-column desktop and notebook keyboards in terms of key stiffness and fingertip typing force. The spring-column keyboard resulted in the highest mean peak contact force (0.86N), followed by the rubber dome desktop (0.68N) and the notebook (0.59N). All these differences were statistically significant. Likewise, the spring-column keyboard registered the highest fingertip typing force and the notebook keyboard the lowest. A comparison of forces showed the notebook (rubber dome) keyboard had the highest fingertip-to-peak contact force ratio (overstrike force), and the spring-column generated the least excess force (as a ratio of peak contact force). The results of this study could aid in optimizing computer key design that could possibly reduce subject discomfort and fatigue.