M. Rubaiyat Hossain Mondal

Bio: M. Rubaiyat Hossain Mondal is an academic researcher from Bangladesh University of Engineering and Technology. The author has contributed to research in topics: Orthogonal frequency-division multiplexing & Deep learning. The author has an hindex of 11, co-authored 49 publications receiving 416 citations. Previous affiliations of M. Rubaiyat Hossain Mondal include Monash University, Clayton campus & Monash University.

Diagnosis of Polycystic Ovary Syndrome Using Machine Learning Algorithms

Abstract: This paper focuses on the data-driven diagnosis of polycystic ovary syndrome (PCOS) in women. For this, machine learning algorithms are applied to a dataset freely available in Kaggle repository. This dataset has 43 attributes of 541 women, among which 177 are patients of PCOS disease. Firstly, univariate feature selection algorithm is applied to find the best features that can predict PCOS. The ranking of the attributes is computed and it is found that the most important attribute is the ratio of Follicle-stimulating hormone (FSH) and Luteinizing hormone (LH). Next, holdout and cross validation methods are applied to the dataset to separate the training and testing data. A number of classifiers such as gradient boosting, random forest, logistic regression, and hybrid random forest and logistic regression (RFLR) are applied to the dataset. Results show that the first 10 highest ranked attributed are good enough to predict the PCOS disease. Results also demonstrate that RFLR exhibits the best testing accuracy of 91.01% and recall value of 90% using 40-fold cross validation applied to the 10 most important features. Hence, RFLR is suitable for reliably classifying PCOS patients.

Data-driven diagnosis of spinal abnormalities using feature selection and machine learning algorithms.

Abstract: This paper focuses on the application of machine learning algorithms for predicting spinal abnormalities. As a data preprocessing step, univariate feature selection as a filter based feature selection, and principal component analysis (PCA) as a feature extraction algorithm are considered. A number of machine learning approaches namely support vector machine (SVM), logistic regression (LR), bagging ensemble methods are considered for the diagnosis of spinal abnormality. The SVM, LR, bagging SVM and bagging LR models are applied on a dataset of 310 samples publicly available in Kaggle repository. The performance of classification of abnormal and normal spinal patients is evaluated in terms of a number of factors including training and testing accuracy, recall, and miss rate. The classifier models are also evaluated by optimizing the kernel parameters, and by using the results of receiver operating characteristic (ROC) and precision-recall curves. Results indicate that when 78% data are used for training, the observed training accuracies for SVM, LR, bagging SVM and bagging LR are 86.30%, 85.47%, 86.72% and 85.06%, respectively. On the other hand, the accuracies for the test dataset for SVM, LR, bagging SVM and bagging LR are the same being 86.96%. However, bagging SVM is the most attractive as it has a higher recall value and a lower miss rate compared to others. Hence, bagging SVM is suitable for the classification of spinal patients when applied on the most five important features of spinal samples.

Analysis of the Effect of Vignetting on MIMO Optical Wireless Systems Using Spatial OFDM

Abstract: The performance of pixelated multiple-input mul-tiple-output optical wireless communication systems can be impaired by vignetting, which is the gradual fall-off in illumination at the edges of a received image. This paper investigates the effect of vignetting for a pixelated system using spatial orthogonal frequency division multiplexing (OFDM). Our analysis shows that vignetting causes attenuation and intercarrier interference (ICI) in the spatial frequency domain. MATLAB simulations indicate that for a given constellation size, spatial asymmetrically clipped optical OFDM (SACO-OFDM) is more robust to vignetting than spatial dc biased optical OFDM (SDCO-OFDM). Moreover, for the case of SDCO-OFDM, the very large zeroth subcarrier causes severe ICI in its neighbourhood causing flattening of the bit error rate (BER) curves. We show that this BER floor can be eliminated by leaving some of the lower spatial frequency subcarriers unused. The BER performance can also be improved by applying a vignetting estimation and equalization scheme. Finally, it is shown that equalized SACO-OFDM with 16-QAM has the same overall data rate as equalized SDCO-OFDM using 4-QAM, but requires less optical power.

Review of deep learning: concepts, CNN architectures, challenges, applications, future directions

Abstract: In the last few years, the deep learning (DL) computing paradigm has been deemed the Gold Standard in the machine learning (ML) community. Moreover, it has gradually become the most widely used computational approach in the field of ML, thus achieving outstanding results on several complex cognitive tasks, matching or even beating those provided by human performance. One of the benefits of DL is the ability to learn massive amounts of data. The DL field has grown fast in the last few years and it has been extensively used to successfully address a wide range of traditional applications. More importantly, DL has outperformed well-known ML techniques in many domains, e.g., cybersecurity, natural language processing, bioinformatics, robotics and control, and medical information processing, among many others. Despite it has been contributed several works reviewing the State-of-the-Art on DL, all of them only tackled one aspect of the DL, which leads to an overall lack of knowledge about it. Therefore, in this contribution, we propose using a more holistic approach in order to provide a more suitable starting point from which to develop a full understanding of DL. Specifically, this review attempts to provide a more comprehensive survey of the most important aspects of DL and including those enhancements recently added to the field. In particular, this paper outlines the importance of DL, presents the types of DL techniques and networks. It then presents convolutional neural networks (CNNs) which the most utilized DL network type and describes the development of CNNs architectures together with their main features, e.g., starting with the AlexNet network and closing with the High-Resolution network (HR.Net). Finally, we further present the challenges and suggested solutions to help researchers understand the existing research gaps. It is followed by a list of the major DL applications. Computational tools including FPGA, GPU, and CPU are summarized along with a description of their influence on DL. The paper ends with the evolution matrix, benchmark datasets, and summary and conclusion.

LED Based Indoor Visible Light Communications: State of the Art

Abstract: Visible Light Communication (VLC) is an emerging field in Optical Wireless Communication (OWC) which utilizes the superior modulation bandwidth of Light Emitting Diodes (LEDs) to transmit data. In modern day communication systems, the most popular frequency band is Radio Frequency (RF) mainly due to little interference and good coverage. However, the rapidly dwindling RF spectrum along with increasing wireless network traffic has substantiated the need for greater bandwidth and spectral relief. By combining illumination and communication, VLC provides ubiquitous communication while addressing the shortfalls and limitations of RF communication. This paper provides a comprehensive survey on VLC with an emphasis on challenges faced in indoor applications over the period 1979–2014. VLC is compared with infrared (IR) and RF systems and the necessity for using this beneficial technology in communication systems is justified. The advantages of LEDs compared to traditional lighting technologies are discussed and comparison is done between different types of LEDs currently available. Modulation schemes and dimming techniques for indoor VLC are discussed in detail. Methods needed to improve VLC system performance such as filtering, equalization, compensation, and beamforming are also presented. The recent progress made by various research groups in this field is discussed along with the possible applications of this technology. Finally, the limitations of VLC as well as the probable future directions are presented.