ORCID Profile
0000-0002-9251-7781
Current Organisation
University of South Australia
Does something not look right? The information on this page has been harvested from data sources that may not be up to date. We continue to work with information providers to improve coverage and quality. To report an issue, use the Feedback Form.
Publisher: IEEE
Date: 10-2019
Publisher: IEEE
Date: 10-2014
Publisher: IEEE
Date: 11-2013
Publisher: IEEE
Date: 12-2017
Publisher: IEEE
Date: 10-2019
Publisher: IEEE
Date: 05-2018
Publisher: IEEE
Date: 12-2017
Publisher: IEEE
Date: 10-2019
Publisher: IEEE
Date: 10-2015
Publisher: MDPI AG
Date: 24-04-2020
DOI: 10.3390/SYM12040679
Abstract: Classification in multi-modal data is one of the challenges in the machine learning field. The multi-modal data need special treatment as its features are distributed in several areas. This study proposes multi-codebook fuzzy neural networks by using intelligent clustering and dynamic incremental learning for multi-modal data classification. In this study, we utilized intelligent K-means clustering based on anomalous patterns and intelligent K-means clustering based on histogram information. In this study, clustering is used to generate codebook candidates before the training process, while incremental learning is utilized when the condition to generate a new codebook is sufficient. The condition to generate a new codebook in incremental learning is based on the similarity of the winner class and other classes. The proposed method was evaluated in synthetic and benchmark datasets. The experiment results showed that the proposed multi-codebook fuzzy neural networks that use dynamic incremental learning have significant improvements compared to the original fuzzy neural networks. The improvements were 15.65%, 5.31% and 11.42% on the synthetic dataset, the benchmark dataset, and the average of all datasets, respectively, for incremental version 1. The incremental learning version 2 improved by 21.08% 4.63%, and 14.35% on the synthetic dataset, the benchmark dataset, and the average of all datasets, respectively. The multi-codebook fuzzy neural networks that use intelligent clustering also had significant improvements compared to the original fuzzy neural networks, achieving 23.90%, 2.10%, and 15.02% improvements on the synthetic dataset, the benchmark dataset, and the average of all datasets, respectively.
Publisher: IEEE
Date: 09-2017
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2022
Publisher: IEEE
Date: 09-2018
Publisher: IEEE
Date: 11-2015
Publisher: IEEE
Date: 10-2015
Publisher: IEEE
Date: 09-2013
Publisher: IEEE
Date: 11-2015
Publisher: IEEE
Date: 09-2017
Publisher: IEEE
Date: 09-2013
Publisher: IEEE
Date: 07-2019
Publisher: IEEE
Date: 10-2017
Publisher: Elsevier BV
Date: 06-2022
Publisher: Walter de Gruyter GmbH
Date: 2015
Abstract: This paper proposed a system for detecting and approximating of a fetus in an ultrasound image. The fetal organs in the ultrasound image are detected using Multi Boundary Classifier based Adaboost.MH. The results of the fetal detection is then approximated Randomized Hough Transform and the whole showed a mean accuracy of 95.80%. The mean of the Hamming Error 0.019 and the Kappa coefficient value reaches 0.890.The proposed method has the best performancefor fetal organ detection. This is proven by the Hamming Error, the accuracy, and tthe Kappa Coefficient. The hitrate for fetal’s head, fetal’s femur, fetal’s humerus, and fetal’s abdomen are 95%, 97%, 97%, and 93% respectively. From the Experiment result, it is concluded that using detection by only usig the approximation method could not perform better than the previous methods.
Publisher: IEEE
Date: 10-2016
Publisher: IEEE
Date: 10-2014
Publisher: IEEE
Date: 12-2017
Publisher: IEEE
Date: 10-2014
Publisher: Walter de Gruyter GmbH
Date: 2019
Abstract: Technology is developed to benefit society. One of the applications of technology in the healthcare sector is telehealth monitoring system. The system proposes a new way of communication between the doctor and the patient, even in a very remote location. In this paper, we elaborate the progress and challenges regarding the development of Tele-ECG in Indonesia, which includes data acquisition, feature extraction, data compression, classification algorithm, mobile and web development system and small device implementation on an FPGA board. The classification is conducted by using LVQ, GLVQ, FNLVQ, FNLVQ-PSO, FNGLVQ, and AM-GLVQ. The compression is conducted by using SPIHT algorithm. Tele-ECG can assist in monitoring heartbeat anomalies and reduce the risk of heart attack. It could also be a solution for infrastructure discrepancy in healthcare.
Publisher: IEEE
Date: 09-2013
Publisher: MDPI AG
Date: 13-01-2020
DOI: 10.3390/COMPUTATION8010006
Abstract: One of the challenges in machine learning is a classification in multi-modal data. The problem needs a customized method as the data has a feature that spreads in several areas. This study proposed a multi-codebook fuzzy neural network classifiers using clustering and incremental learning approaches to deal with multi-modal data classification. The clustering methods used are K-Means and GMM clustering. Experiment result, on a synthetic dataset, the proposed method achieved the highest performance with 84.76% accuracy. Whereas on the benchmark dataset, the proposed method has the highest performance with 79.94% accuracy. The proposed method has 24.9% and 4.7% improvements in synthetic and benchmark datasets respectively compared to the original version. The proposed classifier has better accuracy compared to a popular neural network with 10% and 4.7% margin in synthetic and benchmark dataset respectively.
Publisher: IEEE
Date: 10-2016
Publisher: Scientific Societies
Date: 12-2018
Publisher: IEEE
Date: 10-2016
Publisher: IEEE
Date: 11-2011
Publisher: Walter de Gruyter GmbH
Date: 2015
Abstract: One of the most profound use of ultrasound imaging is fetal growth monitoring. Conventionally, physicians will perform manual measurements of several parameters of the ultrasound images to draw some conclusion of the fetal condition by manually annotating the fetal images on the ultrasound device interface. However, performing manual annotation of fetal images will require significant amount of time considering the number of patients an obstetrician can have. In this paper, an integrated automatic system for fetal growth monitoring and detection is proposed. This system will be able to automatically measuring the parameters of fetal head, abdomen, femur, and humerus. In addition to automated image detection, we also propose an integrated telehealth monitoring system to provide better access of ultrasound monitoring for patients that lives in rural areas. A new approach of fetal image detection is also proposed by using AdaBoost.MH boosting algorithm that is combined with an improved efficient Hough Transform for detecting ellipse-like organs such as head and abdomen. Experiments of the method are tested on real ultrasound image dataset. The detection was applied on 2D ultrasound images to perform fetal object measurement to approximate the Head Circumference (HC) and Biparietal Diameter (BPD), Femur Length (FL), and Humerus Length (HL).
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2021
Publisher: IEEE
Date: 07-2019
Publisher: IEEE
Date: 11-2011
Publisher: IEEE
Date: 10-2016
Publisher: IEEE
Date: 08-2019
Publisher: IEEE
Date: 07-2019
Publisher: IEEE
Date: 10-2016
Publisher: IEEE
Date: 05-2018
No related grants have been discovered for Muhammad Anwar Ma'sum.