Loading [MathJax]/extensions/MathMenu.js
Muhammad Aminul Islam - IEEE Xplore Author Profile
Subscribe
ADVANCED SEARCH

Author details

< Back

Muhammad Aminul Islam

Also published under: Md Aminul Islam, Muhammad Aminul Islam, Muhammad A. Islam, M. Aminul Islam

Publications
23
Citations
191
Publications by Year
20152021
Co-Authors:
Show All Co-Authors (43)
Image of author Muhammad Aminul Islam

Muhammad Aminul Islam

Also published under: Md Aminul Islam, Muhammad Aminul Islam, Muhammad A. Islam, M. Aminul Islam

Affiliation

Department of Electrical and Computer Engineering & Computer Science
University of New Haven
West Haven, Connecticut

Publication Topics

Biography

Muhammad Aminul Islam (Member, IEEE) received the B.Sc. degree in electrical and electronic engineering from the Bangladesh University of Engineering and Technology, Dhaka, Bangladesh, in 2005 and the Ph.D. degree in electrical and computer engineering from Mississippi State University, Starkville, MS, USA in 2018. He is currently an Assistant Professor in the Department of Electrical & Computer Engineering and Computer Science at the University of New Haven. His research interests include deep learning, computer vision, data/information fusion, autonomous driving, and remote sensing.(Based on document published on 27 July 2020).
Publications
23
Citations
191
Publications by Year
20152021
Co-Authors:
Show All Co-Authors (43)
Author's Published Works

Showing 1-23 of 23 results

  • Sort

Filter Results

Show

Sort By

Results

Attribution Modeling for Deep Morphological Neural Networks using Saliency Maps

Muhammad Aminul Islam;Charlie Veal;Yashaswini Gouru;Derek T. Anderson

2021 International Joint Conference on Neural Networks (IJCNN)
Year: 2021 | Conference Paper |
Cited by: Papers (1)
Mathematical morphology has been explored in deep learning architectures, as a substitute to convolution, for problems like pattern recognition and object detection. One major advantage of using morphology in deep learning is the utility of morphological erosion and dilation. Specifically, these operations naturally embody interpretability due to their underlying connections to the analysis of geo...Show More

Attribution Modeling for Deep Morphological Neural Networks using Saliency Maps

Muhammad Aminul Islam;Charlie Veal;Yashaswini Gouru;Derek T. Anderson

Year: 2021 | Conference Paper |

Extending the Morphological Hit-or-Miss Transform to Deep Neural Networks

Muhammad Aminul Islam;Bryce Murray;Andrew Buck;Derek T. Anderson;Grant J. Scott;Mihail Popescu;James Keller

IEEE Transactions on Neural Networks and Learning Systems
Year: 2021 | Volume: 32, Issue: 11 | Journal Article |
Cited by: Papers (11)
While most deep learning architectures are built on convolution, alternative foundations such as morphology are being explored for purposes such as interpretability and its connection to the analysis and processing of geometric structures. The morphological hit-or-miss operation has the advantage that it considers both foreground information and background information when evaluating the target sh...Show More

Extending the Morphological Hit-or-Miss Transform to Deep Neural Networks

Muhammad Aminul Islam;Bryce Murray;Andrew Buck;Derek T. Anderson;Grant J. Scott;Mihail Popescu;James Keller

Year: 2021 | Volume: 32, Issue: 11 | Journal Article |

Explainable AI for the Choquet Integral

Bryce J. Murray;Muhammad Aminul Islam;Anthony J. Pinar;Derek T. Anderson;Grant J. Scott;Timothy C. Havens;James M. Keller

IEEE Transactions on Emerging Topics in Computational Intelligence
Year: 2021 | Volume: 5, Issue: 4 | Journal Article |
Cited by: Papers (21)
The modern era of machine learning is focused on data-driven solutions. While this has resulted in astonishing leaps in numerous applications, explainability has not witnessed the same growth. The reality is, most machine learning solutions are black boxes. Herein, we focus on data/information fusion in machine learning. Specifically, we explore four eXplainable Artificial Intelligence (XAI) quest...Show More

Explainable AI for the Choquet Integral

Bryce J. Murray;Muhammad Aminul Islam;Anthony J. Pinar;Derek T. Anderson;Grant J. Scott;Timothy C. Havens;James M. Keller

Year: 2021 | Volume: 5, Issue: 4 | Journal Article |

Novel Regularization for Learning the Fuzzy Choquet Integral With Limited Training Data

Siva Krishna Kakula;Anthony J. Pinar;Muhammad Aminul Islam;Derek T. Anderson;Timothy C. Havens

IEEE Transactions on Fuzzy Systems
Year: 2021 | Volume: 29, Issue: 10 | Journal Article |
Cited by: Papers (3)
Fuzzy integrals (FIs) are powerful aggregation operators that fuse information from multiple sources. The aggregation is parameterized using a fuzzy measure (FM), which encodes the worths of all subsets of sources. Since the FI is defined with respect to an FM, much consideration must be given to defining the FM. However, in practice this is a difficult task—the number of values in an FM scales as...Show More

Novel Regularization for Learning the Fuzzy Choquet Integral With Limited Training Data

Siva Krishna Kakula;Anthony J. Pinar;Muhammad Aminul Islam;Derek T. Anderson;Timothy C. Havens

Year: 2021 | Volume: 29, Issue: 10 | Journal Article |

A Generalized Fuzzy Extension Principle and Its Application to Information Fusion

Muhammad Aminul Islam;Derek T. Anderson;Timothy C. Havens;John E. Ball

IEEE Transactions on Fuzzy Systems
Year: 2021 | Volume: 29, Issue: 9 | Journal Article |
Cited by: Papers (2)
Zadeh's extension principle (ZEP) is a fundamental concept in fuzzy set (FS) theory that enables crisp mathematical operation on FSs. A well-known shortcoming of ZEP is that the height of the output FS is determined by the lowest height of the input FSs. In this article, we introduce a generalized extension principle (GEP) that eliminates this weakness and provides flexibility and control over how...Show More

A Generalized Fuzzy Extension Principle and Its Application to Information Fusion

Muhammad Aminul Islam;Derek T. Anderson;Timothy C. Havens;John E. Ball

Year: 2021 | Volume: 29, Issue: 9 | Journal Article |

Differential Morphological Profile Neural Network for Object Detection in Overhead Imagery

Grant J. Scott;J. Alex Hurt;Alex Yang;Muhammad Aminul Islam;Derek T. Anderson;Curt H. Davis

2020 International Joint Conference on Neural Networks (IJCNN)
Year: 2020 | Conference Paper |
Cited by: Papers (6)
Deep convolutional neural networks (DCNN) have been the dominant methodology in the field of computer vision over the last decade, using various architectural organizations of successive convolutional layers to extract and assemble low level image features into visual component detectors. One of the tradeoffs that have been made as the community has migrated to deep neural models is the loss of ex...Show More

Differential Morphological Profile Neural Network for Object Detection in Overhead Imagery

Grant J. Scott;J. Alex Hurt;Alex Yang;Muhammad Aminul Islam;Derek T. Anderson;Curt H. Davis

Year: 2020 | Conference Paper |

A Weighted Matrix Visualization for Fuzzy Measures and Integrals

Andrew R. Buck;Derek T. Anderson;James M. Keller;Timothy Wilkin;Muhammad Aminul Islam

2020 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)
Year: 2020 | Conference Paper |
Cited by: Papers (6)
Fuzzy integrals are useful general purpose aggregation operators, but they can be difficult to understand and visualize in practice. The interaction between an exponentially increasing number of variables–2n fuzzy measure variables for n inputs–makes it hard to understand what exactly is going on in a high dimensional space. We propose a new visualization scheme based on a weighted indicator matri...Show More

A Weighted Matrix Visualization for Fuzzy Measures and Integrals

Andrew R. Buck;Derek T. Anderson;James M. Keller;Timothy Wilkin;Muhammad Aminul Islam

Year: 2020 | Conference Paper |

Possibilistic Clustering Enabled Neuro Fuzzy Logic

Blake Ruprecht;Wenlong Wu;Muhammad Aminul Islam;Derek Anderson;James Keller;Grant Scott;Curt Davis;Fred Petry;Paul Elmore;Kristen Nock;Elizabeth Gilmour

2020 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)
Year: 2020 | Conference Paper |
Cited by: Papers (3)
Artificial neural networks are a dominant force in our modern era of data-driven artificial intelligence. The adaptive neuro fuzzy inference system (ANFIS) is a neural network based on fuzzy logic versus a more traditional premise like convolution. Advantages of ANFIS include the ability to encode and potentially understand machine learned neural information in the pursuit of explainable, interpre...Show More

Possibilistic Clustering Enabled Neuro Fuzzy Logic

Blake Ruprecht;Wenlong Wu;Muhammad Aminul Islam;Derek Anderson;James Keller;Grant Scott;Curt Davis;Fred Petry;Paul Elmore;Kristen Nock;Elizabeth Gilmour

Year: 2020 | Conference Paper |

Enabling Explainable Fusion in Deep Learning With Fuzzy Integral Neural Networks

Muhammad Aminul Islam;Derek T. Anderson;Anthony J. Pinar;Timothy C. Havens;Grant Scott;James M. Keller

IEEE Transactions on Fuzzy Systems
Year: 2020 | Volume: 28, Issue: 7 | Journal Article |
Cited by: Papers (51)
Information fusion is an essential part of numerous engineering systems and biological functions, e.g., human cognition. Fusion occurs at many levels, ranging from the low-level combination of signals to the high-level aggregation of heterogeneous decision-making processes. While the last decade has witnessed an explosion of research in deep learning, fusion in neural networks has not observed the...Show More

Enabling Explainable Fusion in Deep Learning With Fuzzy Integral Neural Networks

Muhammad Aminul Islam;Derek T. Anderson;Anthony J. Pinar;Timothy C. Havens;Grant Scott;James M. Keller

Year: 2020 | Volume: 28, Issue: 7 | Journal Article |

Transfer Learning for the Choquet Integral

Bryce Murray;Muhammad Aminul Islam;Anthony Pinar;Derek T. Anderson;Grant Scott;Timothy C. Havens;Fred Petry;Paul Elmore

2019 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)
Year: 2019 | Conference Paper |
Cited by: Papers (1)
The Choquet integral (ChI) is a proven tool for information aggregation. In prior work, we showed that learning a ChI from data results in missing variables. Herein, we explore two ways to transfer a known ChI from a source domain to a new under sampled target domain. The first method is based on regularization and it listens to the full source domain ChI. The second method optimizes what we can o...Show More

Transfer Learning for the Choquet Integral

Bryce Murray;Muhammad Aminul Islam;Anthony Pinar;Derek T. Anderson;Grant Scott;Timothy C. Havens;Fred Petry;Paul Elmore

Year: 2019 | Conference Paper |

Linear Order Statistic Neuron

Charlie Veal;Alex Yang;Alex Hurt;Muhammad Aminul Islam;Derek T. Anderson;Grant Scott;James M Keller;Timothy C. Havens;Bo Tang

2019 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)
Year: 2019 | Conference Paper |
Cited by: Papers (5)
Herein, a generalization of the ordered weighted average (OWA) is put forth relative to pattern recognition. The resultant linear order statistic neuron (LOSN) is unique in that it bridges fuzzy sets, specifically fuzzy data/information aggregation, with neural networks. This article discusses the gradient descent-based optimization and geometric interpretation of the LOSN. An advantage is that th...Show More

Linear Order Statistic Neuron

Charlie Veal;Alex Yang;Alex Hurt;Muhammad Aminul Islam;Derek T. Anderson;Grant Scott;James M Keller;Timothy C. Havens;Bo Tang

Year: 2019 | Conference Paper |

Explainable AI for Understanding Decisions and Data-Driven Optimization of the Choquet Integral

Bryce Murray;M. Aminul Islam;Anthony J. Pinar;Timothy C. Havens;Derek T. Anderson;Grant Scott

2018 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)
Year: 2018 | Conference Paper |
Cited by: Papers (10)
To date, numerous ways have been created to learn a fusion solution from data. However, a gap exists in terms of understanding the quality of what was learned and how trustworthy the fusion is for future-i.e., new-data. In part, the current paper is driven by the demand for so-called explainable AI (XAI). Herein, we discuss methods for XAI of the Choquet integral (ChI), a parametric nonlinear aggr...Show More

Explainable AI for Understanding Decisions and Data-Driven Optimization of the Choquet Integral

Bryce Murray;M. Aminul Islam;Anthony J. Pinar;Timothy C. Havens;Derek T. Anderson;Grant Scott

Year: 2018 | Conference Paper |

Evaluating Document Analysis with kNN Based Approaches in Judicial Offices of Bangladesh

Md. Aminul Islam;Md. Jahidul Haque

2018 Second International Conference on Computing Methodologies and Communication (ICCMC)
Year: 2018 | Conference Paper |
Cited by: Papers (2)
In this contemporary era of artificial intelligence, machine learning (ML) algorithms are getting significant attention for the analysis of textual analysis. In recent years, operational improvement in different corporate sectors of Bangladesh are achieved by implementing digitization of the process flow instead of using manual paper trails in offices. Nowadays, judicial sectors are included into ...Show More

Evaluating Document Analysis with kNN Based Approaches in Judicial Offices of Bangladesh

Md. Aminul Islam;Md. Jahidul Haque

Year: 2018 | Conference Paper |

Data-Driven Compression and Efficient Learning of the Choquet Integral

Muhammad Aminul Islam;Derek T. Anderson;Anthony J. Pinar;Timothy C. Havens

IEEE Transactions on Fuzzy Systems
Year: 2018 | Volume: 26, Issue: 4 | Journal Article |
Cited by: Papers (31)
The Choquet integral (ChI) is a parametric nonlinear aggregation function defined with respect to the fuzzy measure (FM). To date, application of the ChI has sadly been restricted to problems with relatively few numbers of inputs; primarily as the FM has 2N variables for N inputs and N(2N-1 - 1) monotonicity constraints. In return, the community has turned to density-based imputation (e.g., Sugeno...Show More

Data-Driven Compression and Efficient Learning of the Choquet Integral

Muhammad Aminul Islam;Derek T. Anderson;Anthony J. Pinar;Timothy C. Havens

Year: 2018 | Volume: 26, Issue: 4 | Journal Article |

The fuzzy integral for missing data

Muhammad Aminul Islam;Derek T. Anderson;Fred Petry;Denson Smith;Paul Elmore

2017 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)
Year: 2017 | Conference Paper |
Cited by: Papers (5)
Numerous applications in engineering are plagued by incomplete data. The subject explored in this article is how to extend the fuzzy integral (FI), a parametric nonlinear aggregation function, to missing data. We show there is no universally correct solution. Depending on context, different types of uncertainty are present and assumptions are applicable. Two major approaches exist, use just observ...Show More

The fuzzy integral for missing data

Muhammad Aminul Islam;Derek T. Anderson;Fred Petry;Denson Smith;Paul Elmore

Year: 2017 | Conference Paper |

Visualization and learning of the Choquet integral with limited training data

Anthony J. Pinar;Timothy C. Havens;Muhammad Aminul Islam;Derek T. Anderson

2017 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)
Year: 2017 | Conference Paper |
Cited by: Papers (11)
The fuzzy integral (FI) is a nonlinear aggregation operator whose behavior is defined by the fuzzy measure (FM). As an aggregation operator, the FI is commonly used for evidence fusion where it combines sources of information based on the worth of each subset of sources. One drawback to FI-based methods, however, is the specification of the FM. Defining the FM manually quickly becomes too tedious ...Show More

Visualization and learning of the Choquet integral with limited training data

Anthony J. Pinar;Timothy C. Havens;Muhammad Aminul Islam;Derek T. Anderson

Year: 2017 | Conference Paper |

Binary fuzzy measures and Choquet integration for multi-source fusion

Derek T. Anderson;Muhammad Aminul Islam;Roger King;Nicolas H. Younan;Joshua R. Fairley;Stacy Howington;Frederick Petry;Paul Elmore;Alina Zare

2017 International Conference on Military Technologies (ICMT)
Year: 2017 | Conference Paper |
Cited by: Papers (10)
Countless challenges in engineering require the intelligent combining (aka fusion) of data or information from multiple sources. The Choquet integral (ChI), a parametric aggregation function, is a well-known tool for multi-source fusion, where source refers to sensors, humans and/or algorithms. In particular, a selling point of the ChI is its ability to model and subsequently exploit rich interact...Show More

Binary fuzzy measures and Choquet integration for multi-source fusion

Derek T. Anderson;Muhammad Aminul Islam;Roger King;Nicolas H. Younan;Joshua R. Fairley;Stacy Howington;Frederick Petry;Paul Elmore;Alina Zare

Year: 2017 | Conference Paper |

Fusion of diverse features and kernels using LP-norm based multiple kernel learning in hyperspectral image processing

Muhammad Aminul Islam;Derek T. Anderson;John E. Ball;Nicholas H. Younan

2016 8th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS)
Year: 2016 | Conference Paper |
Cited by: Papers (2)
Multiple kernel learning (MKL) is an elegant tool for heterogeneous fusion. In support vector machine (SVM) based classification, MK is a homogenization transform and it provides flexibility in searching for high-quality linearly separable solutions in the reproducing kernel Hilbert space (RKHS). However, performance often depends on input and kernel diversity. Herein, we explore a new way to extr...Show More

Fusion of diverse features and kernels using LP-norm based multiple kernel learning in hyperspectral image processing

Muhammad Aminul Islam;Derek T. Anderson;John E. Ball;Nicholas H. Younan

Year: 2016 | Conference Paper |

Automated soil clustering for crops cultivation

Afrida Islam;Akash Bhuiyan;Junaeid Ahmed;Md. Aminul Islam;Mohammad Nurul Huda

2016 3rd International Conference on Electrical Engineering and Information Communication Technology (ICEEICT)
Year: 2016 | Conference Paper |
Cited by: Papers (1)
This paper focuses on the idea of cultivating a certain crop to a certain District-Sub District-Union of Bangladesh. The cluster and classification are done first on the basis of soil features and then comparing the soil features with the common features of the corps to be cultivated, is being searched for. Here k-mean Clustering, Fuzzy c-Mean clustering and SOM (Self-Organizing Map) based cluster...Show More

Automated soil clustering for crops cultivation

Afrida Islam;Akash Bhuiyan;Junaeid Ahmed;Md. Aminul Islam;Mohammad Nurul Huda

Year: 2016 | Conference Paper |

Effects of heuristics in path planning for mobile robots in uncertain and dynamic environments

Kazi Shah Nawaz Ripon;Khandker M Qaiduzzaman;Md. Aminul Islam

2016 19th International Conference on Computer and Information Technology (ICCIT)
Year: 2016 | Conference Paper |
Cited by: Papers (1)
In this work, several heuristics are proposed to assess their effects in path planning for mobile robots in uncertain and dynamic environments. Path planning for mobile robots is a widely used technique where an optimal collision-free path is searched through an environment. It is one of the most important primitives in robotics and is considered to be a hard problem. Since environments may contai...Show More

Effects of heuristics in path planning for mobile robots in uncertain and dynamic environments

Kazi Shah Nawaz Ripon;Khandker M Qaiduzzaman;Md. Aminul Islam

Year: 2016 | Conference Paper |

CLODD based band group selection

Muhammad A. Islam;Derek T. Anderson;John E. Ball;Nicolas H. Younan

2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS)
Year: 2016 | Conference Paper |
Cited by: Papers (1)
Herein, we explore both a new supervised and unsupervised technique for dimensionality reduction or multispectral sensor design via band group selection in hyperspectral imaging. Specifically, we investigate two algorithms, one based on the improved visual assessment of clustering tendency (iVAT) and the other based on the automatic extraction of “blocklike” structure in a dissimilarity matrix (CL...Show More

CLODD based band group selection

Muhammad A. Islam;Derek T. Anderson;John E. Ball;Nicolas H. Younan

Year: 2016 | Conference Paper |

Projection-based features: A superior domain for handwritten Bangla basic characters recognition

Kazi Lutful Kabir;Md. Kishwar Shafin;Tasmiah Tamzid Anannya;Deepon Debnath;Md. Rayhan Kabir;Md. Aminul Islam;Hasan Sarwar

2015 IEEE 9th International Conference on Intelligent Systems and Control (ISCO)
Year: 2015 | Conference Paper |
Cited by: Papers (5)
In spite of wide use of projection-based features in handwritten character recognition of several languages, its implementation was somewhat scanty in Bangla handwritten character recognition. This paper introduces the usage of projection profile features in recognizing handwritten Bangla basic characters. Alongside it also demonstrates a qualitative and quantitative analysis to visualize the effe...Show More

Projection-based features: A superior domain for handwritten Bangla basic characters recognition

Kazi Lutful Kabir;Md. Kishwar Shafin;Tasmiah Tamzid Anannya;Deepon Debnath;Md. Rayhan Kabir;Md. Aminul Islam;Hasan Sarwar

Year: 2015 | Conference Paper |

Multi-criteria based learning of the Choquet integral using Goal programming

Muhammad Aminul Islam;Derek T. Anderson;Timothy C. Havens

2015 Annual Conference of the North American Fuzzy Information Processing Society (NAFIPS) held jointly with 2015 5th World Conference on Soft Computing (WConSC)
Year: 2015 | Conference Paper |
Cited by: Papers (2)
In this paper, we explore a new way to learn an aggregation operator for fusion based on a combination of one or more labeled training data sets and information from one or more experts. One problem with learning an aggregation from training data alone is that it often results in solutions that are overly complex and expensive to implement. It also runs the risk of over-fitting and the quality of ...Show More

Multi-criteria based learning of the Choquet integral using Goal programming

Muhammad Aminul Islam;Derek T. Anderson;Timothy C. Havens

Year: 2015 | Conference Paper |

IEEE Account

Purchase Details

Profile Information

Need Help?

A not-for-profit organization, IEEE is the world's largest technical professional organization dedicated to advancing technology for the benefit of humanity.
© Copyright 2025 IEEE - All rights reserved. Use of this web site signifies your agreement to the terms and conditions.