Browsing by Author "Ali, Md Asraf"

Filter results by typing the first few letters
Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    A Review on Crosstalk in Myographic Signals
    (Scopus, 2020) Talib, Irsa; Sundaraj, Kenneth; Lam, Chee Kiang; Hussain, Jawad; Ali, Md Asraf
    Purpose: Crosstalk in myographic signals is a major hindrance to the understanding of local information related to individual muscle function. This review aims to analyse the problem of crosstalk in electromyography and mechanomyography. Methods: An initial search of the SCOPUS database using an appropriate set of keywords yielded 290 studies, and 59 potential studies were selected after all the records were screened using the eligibility criteria. This review on crosstalk revealed that signal contamination due to crosstalk remains a major challenge in the application of surface myography techniques. Various methods have been employed in previous studies to identify, quantify and reduce crosstalk in surface myographic signals. Results: Although correlation-based methods for crosstalk quantification are easy to use, there is a possibility that co-contraction could be interpreted as crosstalk. High-definition EMG has emerged as a new technique that has been successfully applied to reduce crosstalk. Conclusions: The phenomenon of crosstalk needs to be investigated carefully because it depends on many factors related to muscle task and physiology. This review article not only provides a good summary of the literature on crosstalk in myographic signals but also discusses new directions related to techniques for crosstalk identification, quantification and reduction. The review also provides insights into muscle-related issues that impact crosstalk in myographic signals.
  • No Thumbnail Available
    Item
    Ensemble-based Machine Learning Algorithms for Classifying Breast Tissue Based on Electrical Impedance Spectroscopy
    (Advances in Intelligent Systems and Computing, Springer, 2019-06-19) Rahman, Sam Matiur; Ali, Md Asraf; Altwijri, Omar; Alqahtani, Mahdi; Ahmed, Nasim; Ahamed, Nizam U.
    The initial identification of breast cancer and the prediction of its category have become a requirement in cancer research because they can simplify the subsequent clinical management of patients. The application of artificial intelligence techniques (e.g., machine learning and deep learning) in medical science is becoming increasingly important for intelligently transforming all available information into valuable knowledge. Therefore, we aimed to classify six classes of freshly excised tissues from a set of electrical impedance measurement variables using five ensemble-based machine learning (ML) algorithms, namely, the random forest (RF), extremely randomized trees (ERT), decision tree (DT), gradient boosting tree (GBT) and AdaBoost (Adaptive Boosting) (ADB) algorithms, which can be subcategorized as bagging and boosting methods. In addition, the ranked order of the variables based on their importance differed across the ML algorithms. The results demonstrated that the three bagging ensemble ML algorithms, namely, RF ERT and DT, yielded better classification accuracies (78–86%) compared with the two boosting algorithms, GBT and ADB (60–75%). We hope that these our results would help improve the classification of breast tissue to allow the early prediction of cancer susceptibility.