Institution
Universiti Teknologi Malaysia
Education•Johor Bahru, Malaysia•
About: Universiti Teknologi Malaysia is a education organization based out in Johor Bahru, Malaysia. It is known for research contribution in the topics: Membrane & Control theory. The organization has 21644 authors who have published 39500 publications receiving 520635 citations.
Topics: Membrane, Control theory, Adsorption, Antenna (radio), Population
Papers published on a yearly basis
Papers
More filters
••
TL;DR: This paper is the first SLR specifically on the deep learning based RS to summarize and analyze the existing studies based on the best quality research publications and indicated that autoencoder models are the most widely exploited deep learning architectures for RS followed by the Convolutional Neural Networks and the Recurrent Neural Networks.
Abstract: These days, many recommender systems (RS) are utilized for solving information overload problem in areas such as e-commerce, entertainment, and social media. Although classical methods of RS have achieved remarkable successes in providing item recommendations, they still suffer from many issues such as cold start and data sparsity. With the recent achievements of deep learning in various applications such as Natural Language Processing (NLP) and image processing, more efforts have been made by the researchers to exploit deep learning methods for improving the performance of RS. However, despite the several research works on deep learning based RS, very few secondary studies were conducted in the field. Therefore, this study aims to provide a systematic literature review (SLR) of deep learning based RSs that can guide researchers and practitioners to better understand the new trends and challenges in the field. This paper is the first SLR specifically on the deep learning based RS to summarize and analyze the existing studies based on the best quality research publications. The paper particularly adopts an SLR approach based on the standard guidelines of the SLR designed by Kitchemen-ham which uses selection method and provides detail analysis of the research publications. Several publications were gathered and after inclusion/exclusion criteria and the quality assessment, the selected papers were finally used for the review. The results of the review indicated that autoencoder (AE) models are the most widely exploited deep learning architectures for RS followed by the Convolutional Neural Networks (CNNs) and the Recurrent Neural Networks (RNNs) models. Also, the results showed that Movie Lenses is the most popularly used datasets for the deep learning-based RS evaluation followed by the Amazon review datasets. Based on the results, the movie and e-commerce have been indicated as the most common domains for RS and that precision and Root Mean Squared Error are the most commonly used metrics for evaluating the performance of the deep leaning based RSs.
144 citations
••
01 Jan 2018
TL;DR: In this paper, the authors provide practical guidelines for researchers to successfully conceptualise, test and interpret mediation models and discourage researchers from using outdated mediation approaches in their theses/manuscripts.
Abstract: This editorial outlines and responds to some of the most frequently asked questions regarding mediation analysis. Specifically, six key issues are addressed with reference to the state-of-the-art mediation literature. In doing this, we provide practical guidelines for researchers to successfully conceptualise, test and interpret mediation models. Recent references are also provided to discourage researchers from using outdated mediation approaches in their theses/manuscripts. It is our hope that this effort will clarify misconceptions regarding mediation analysis and provide up-to-date guidelines for researchers to make informed decisions and conduct the analysis appropriately.
143 citations
••
TL;DR: In this paper, hollow fiber membranes were manufactured using a dry/wet spinning process with forced convection in the dry gap and two different bore coagulants: pure water and one with reduced water activity.
143 citations
••
TL;DR: In this article, a mixed matrix membranes (MMM) comprised of multi-walled carbon nanotubes (MWCNTs) inside polyethersulfone (PES) matrix were fabricated and characterized for gas separation performance.
143 citations
••
TL;DR: Exoelectrogens are catalytic microorganisms competent to shuttle electrons exogenously to the electrode surface without utilizing artificial mediators and cyclic voltammetry has suggested the role of multifarious redox‐active compounds secreted by the exoelectosterone in direct electron transport mechanisms.
Abstract: Summary
Exoelectrogens are catalytic microorganisms competent to shuttle electrons exogenously to the electrode surface without utilizing artificial mediators. Diverse microorganisms acting as exoelectrogens in the fluctuating ambience of microbial fuel cells (MFCs) propose unalike metabolic pathways and incompatible, specific proteins or genes for their inevitable performance toward bioelectricity generation. A pivotal mechanism known as quorum sensing allows bacterial population to communicate and regulates the expression of biofilm-related genes. Moreover, it has been found that setting the anode potential affects the metabolism of the exoelectrogens and hence the output of MFCs. Microscopic, spectrometry investigations and gene deletion studies have confirmed the expression of certain genes for outer-membrane multiheme cytochromes and conductive pili, and their potential roles in the exoelectrogenic activity. Further, cyclic voltammetry has suggested the role of multifarious redox-active compounds secreted by the exoelectrogens in direct electron transport mechanisms. Besides, it also explores the various mechanisms of exoelectrogens with genetic and molecular approaches, such as biofilm formation, microbial metabolism, bioelectrogenesis, and electron transfer mechanisms from inside the exoelectrogens to the electrodes and vice versa. Copyright © 2015 John Wiley & Sons, Ltd.
143 citations
Authors
Showing all 21852 results
Name | H-index | Papers | Citations |
---|---|---|---|
Xin Li | 114 | 2778 | 71389 |
Muhammad Imran | 94 | 3053 | 51728 |
Ahmad Fauzi Ismail | 93 | 1357 | 40853 |
Bin Tean Teh | 92 | 471 | 33359 |
Muhammad Farooq | 92 | 1341 | 37533 |
M. A. Shah | 92 | 583 | 37099 |
Takeshi Matsuura | 85 | 540 | 26188 |
Peter Willett | 76 | 479 | 29037 |
Peter C. Searson | 74 | 374 | 21806 |
Ozgur Kisi | 73 | 478 | 19433 |
Imran Ali | 72 | 300 | 19878 |
S.M. Sapuan | 70 | 713 | 19175 |
Peter J. Fleming | 66 | 529 | 24395 |
Mohammad Jawaid | 65 | 503 | 19471 |
Muhammad Tahir | 65 | 1636 | 23892 |