a b s t r a c tFeature selection is used in many application areas relevant to expert and intelligent systems, such as data mining and machine learning, image processing, anomaly detection, bioinformatics and natural language processing. Feature selection based on information theory is a popular approach due its computational efficiency, scalability in terms of the dataset dimensionality, and independence from the classifier. Common drawbacks of this approach are the lack of information about the interaction between the features and the classifier, and the selection of redundant and irrelevant features. The latter is due to the limitations of the employed goal functions leading to overestimation of the feature significance.To address this problem, this article introduces two new nonlinear feature selection methods, namely Joint Mutual Information Maximisation (JMIM) and Normalised Joint Mutual Information Maximisation (NJMIM); both these methods use mutual information and the 'maximum of the minimum' criterion, which alleviates the problem of overestimation of the feature significance as demonstrated both theoretically and experimentally. The proposed methods are compared using eleven publically available datasets with five competing methods. The results demonstrate that the JMIM method outperforms the other methods on most tested public datasets, reducing the relative average classification error by almost 6% in comparison to the next best performing method. The statistical significance of the results is confirmed by the ANOVA test. Moreover, this method produces the best trade-off between accuracy and stability.
Quantitative assessment of movement impairment in Huntington’s disease (HD) is essential to monitoring of disease progression. This paper aimed to develop and validate a novel low cost, objective automated system for the evaluation of upper limb movement impairment in HD in order to eliminate the inconsistency of the assessor and offer a more sensitive, continuous assessment scale. Patients with genetically confirmed HD and healthy controls were recruited to this observational study. Demographic data, including age (years), gender, and unified HD rating scale total motor score (UHDRS-TMS), were recorded. For the purposes of this paper, a modified upper limb motor impairment score (mULMS) was generated from the UHDRS-TMS. All participants completed a brief, standardized clinical assessment of upper limb dexterity while wearing a tri-axial accelerometer on each wrist and on the sternum. The captured acceleration data were used to develop an automatic classification system for discriminating between healthy and HD participants and to automatically generate a continuous movement impairment score (MIS) that reflected the degree of the movement impairment. Data from 48 healthy and 44 HD participants was used to validate the developed system, which achieved 98.78% accuracy in discriminating between healthy and HD participants. The Pearson correlation coefficient between the automatic MIS and the clinician rated mULMS was 0.77 with a p-value < 0.01. The approach presented in this paper demonstrates the possibility of an automated objective, consistent, and sensitive assessment of the HD movement impairment.
BACKGROUND Movement analysis in the clinical setting is frequently restricted to observational methods to inform clinical decision making, which has limited accuracy. Fixed-site optical expensive movement analysis laboratories provide ‘gold-standard’ kinematic measurements, however they are rarely accessed for routine clinical use. Wearable inertial measurement units (IMUs) have been demonstrated as comparable, inexpensive and portable movement analysis toolkit. MoJoXlab has therefore been developed to work with generic wearable IMUs. However, before using MoJoXlab in clinical practice there is a need to establish its validity in participants with and without knee conditions across a range of tasks with varying complexity. OBJECTIVE This paper presents the validation of MoJoXlab software for using generic wearable IMUs in calculating hip, knee and ankle joint angle measurements in the sagittal, frontal and transverse planes, for walking, squatting and jumping in healthy participants and those with anterior cruciate ligament reconstruction. METHODS Movement data were collected from 27 healthy participants and 20 participants with Anterior Cruciate Ligament (ACL) reconstruction. In each case, participants wore seven ‘MTw2’ IMUs to monitor their movement in walking, jumping and squatting tasks. Hip, knee and ankle joint angles were calculated in the sagittal, frontal and transverse plane using two different software packages: Xsens’s validated proprietary MVN Analyze, and MoJoXlab. Results were validated by comparing the generated waveforms, cross-correlation (CC) and normalized root mean square error (NRMSE) values. RESULTS Across all joints and activities, for both healthy and ACL reconstruction data, the cross-correlation and normalized root mean square error for the sagittal plane are: 0.99 ± 0.01 and 0.042 ± 0.025 respectively; for the frontal plane: 0.88 ± 0.048 and 0.18 ± 0.078; and for the transverse plane (hip and knee joints only): 0.85 ± 0.027 and 0.23 ± 0.065. On comparing results from the two different software systems, the sagittal plane is very highly correlated, with frontal and transverse planes showing strong correlation. CONCLUSIONS This paper demonstrates that non-proprietary software such as MoJoXlab can accurately calculate joint angles for movement analysis applications comparable to proprietary software, for walking, squatting and jumping, in healthy individuals and those following anterior cruciate ligament reconstruction. MoJoXlab can be used with generic wearable IMUs that can provide clinicians accurate objective data when assessing patients’ movement, even when changes are too small to be observed visually. The availability of easy-to-setup, non-proprietary software for calibration, data collection and joint angle calculation has the potential to increase the adoption of wearable IMU sensors in clinical practice, as well as in free living conditions, and may provide wider access to accurate, objective assessment of patients’ progress over time. CLINICALTRIAL
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.