Amir Atapour Abarghouei

Amir Atapour Abarghouei
Newcastle University | NCL · School of Computing Science

Doctor of Philosophy

About

60
Publications
12,217
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
1,201
Citations
Introduction
Skills and Expertise
Additional affiliations
January 2021 - present
Newcastle University
Position
  • Lecturer
Description
  • Lecturer of Computer Science with a research focus on Machine Learning, Computer Vision, Robotic Navigation, Natural Language Processing, etc.
May 2019 - December 2020
Newcastle University
Position
  • Research Associate
Description
  • CRITiCaL/EMPHASIS Projects - Research on combating criminal behaviour on the cloud and preventing ransomware attacks, with data from multiple modalities such as NLP, Images, etc. - Supervision of three MSC students. - Member of the SAgE Research Ethics Committee. Webpage for the CRITiCaL project: https://northerncloudcrimecentre.org/ Webpage for the EMPHASIS project: https://www.emphasis.ac.uk/
October 2015 - April 2018
Durham University
Position
  • Demonstrator / Senior Demonstrator
Description
  • Teaching: Software Engineering, Software Methodologies, Programming Paradigms, Real-time Computing.
Education
August 2015 - January 2020
Durham University
Field of study
  • Computer Science - Computer Vision and Machine Learning
December 2008 - April 2010
Universiti Teknologi Malaysia
Field of study
  • Computer Science
September 2004 - April 2008
Shahid Bahonar University of Kerman
Field of study
  • Software Engineering

Publications

Publications (60)
Preprint
Full-text available
It is a sad reflection of modern academia that code is often ignored after publication -- there is no academic 'kudos' for bug fixes / maintenance. Code is often unavailable or, if available, contains bugs, is incomplete, or relies on out-of-date / unavailable libraries. This has a significant impact on reproducibility and general scientific progre...
Preprint
Convolutional Neural Networks have demonstrated human-level performance in the classification of melanoma and other skin lesions, but evident performance disparities between differing skin tones should be addressed before widespread deployment. In this work, we utilise a modified variational autoencoder to uncover skin tone bias in datasets commonl...
Preprint
Biases can filter into AI technology without our knowledge. Oftentimes, seminal deep learning networks champion increased accuracy above all else. In this paper, we attempt to alleviate biases encountered by semantic segmentation models in urban driving scenes, via an iteratively trained unlearning algorithm. Convolutional neural networks have been...
Preprint
Convolutional Neural Networks have demonstrated dermatologist-level performance in the classification of melanoma and other skin lesions, but prediction irregularities due to biases seen within the training data are an issue that should be addressed before widespread deployment is possible. In this work, we robustly remove bias and spurious variati...
Preprint
As online news has become increasingly popular and fake news increasingly prevalent, the ability to audit the veracity of online news content has become more important than ever. Such a task represents a binary classification challenge, for which transformers have achieved state-of-the-art results. Using the publicly available ISOT and Combined Cor...
Preprint
Full-text available
The use of mobiles phones when driving have been a major factor when it comes to road traffic incidents and the process of capturing such violations can be a laborious task. Advancements in both modern object detection frameworks and high-performance hardware has paved the way for a more automated approach when it comes to video surveillance. In th...
Conference Paper
As cybercriminals scale up their operations to increase their profits or inflict greater harm, we argue that there is an equal need to respond to their threats by scaling up cyber-security. To achieve this goal, we have to develop a co-productive approach towards data collection and sharing by overcoming the cybersecurity data sharing paradox. This...
Preprint
As cybercriminals scale up their operations to increase their profits or inflict greater harm, we argue that there is an equal need to respond to their threats by scaling up cybersecurity. To achieve this goal, we have to develop a co-productive approach towards data collection and sharing by overcoming the cybersecurity data sharing paradox. This...
Preprint
With the growing significance of graphs as an effective representation of data in numerous applications, efficient graph analysis using modern machine learning is receiving a growing level of attention. Deep learning approaches often operate over the entire adjacency matrix -- as the input and intermediate network layers are all designed in proport...
Preprint
Text classification has long been a staple in natural language processing with applications spanning across sentiment analysis, online content tagging, recommender systems and spam detection. However, text classification, by nature, suffers from a variety of issues stemming from dataset imbalance, text ambiguity, subjectivity and the lack of lingui...
Chapter
While recent growth in modern machine learning techniques has led to remarkable strides in computer vision applications, one of the most significant challenges facing learning-based vision systems is the scarcity of large, high-fidelity datasets required for training large-scale models. This has necessitated the creation of transfer learning and do...
Preprint
Full-text available
Recent advances in generalized image understanding have seen a surge in the use of deep convolutional neural networks (CNN) across a broad range of image-based detection, classification and prediction tasks. Whilst the reported performance of these approaches is impressive, this study investigates the hitherto unapproached question of the impact of...
Preprint
Full-text available
Recently, substantial progress has been made in the area of Brain-Computer Interface (BCI) using modern machine learning techniques to decode and interpret brain signals. While Electroencephalography (EEG) has provided a non-invasive method of interfacing with a human brain, the acquired data is often heavily subject and session dependent. This mak...
Preprint
Full-text available
With the rapidly growing expansion in the use of UAVs, the ability to autonomously navigate in varying environments and weather conditions remains a highly desirable but as-of-yet unsolved challenge. In this work, we use Deep Reinforcement Learning to continuously improve the learning and understanding of a UAV agent while exploring a partially obs...
Preprint
Full-text available
With the recent growth in the number of malicious activities on the internet, cybersecurity research has seen a boost in the past few years. However, as certain variants of malware can provide highly lucrative opportunities for bad actors, significant resources are dedicated to innovations and improvements by vast criminal organisations. Among thes...
Chapter
Even though obtaining 3D information has received significant attention in scene capture systems in recent years, there are currently numerous challenges within scene depth estimation which is one of the fundamental parts of any 3D vision system focusing on RGB-D images. This has lead to the creation of an area of research where the goal is to comp...
Preprint
Full-text available
Graphs have become a crucial way to represent large, complex and often temporal datasets across a wide range of scientific disciplines. However, when graphs are used as input to machine learning models, this rich temporal information is frequently disregarded during the learning process, resulting in suboptimal performance on certain temporal infer...
Preprint
Full-text available
Newly emerging variants of ransomware pose an ever-growing threat to computer systems governing every aspect of modern life through the handling and analysis of big data. While various recent security-based approaches have focused on detecting and classifying ransomware at the network or system level, easy-to-use post-infection ransomware classific...
Preprint
Full-text available
Robust three-dimensional scene understanding is now an ever-growing area of research highly relevant in many real-world applications such as autonomous driving and robotic navigation. In this paper, we propose a multi-task learning-based model capable of performing two tasks:- sparse depth completion (i.e. generating complete dense scene depth give...
Article
Increased growth in the global Unmanned Aerial Vehicles (UAV) (drone) industry has expanded possibilities for fully autonomous UAV applications. A particular application which has in part motivated this research is the use of UAV in wide area search and surveillance operations in unstructured outdoor environments. The critical issue with such envir...
Preprint
Full-text available
Increased growth in the global Unmanned Aerial Vehicles (UAV) (drone) industry has expanded possibilities for fully autonomous UAV applications. A particular application which has in part motivated this research is the use of UAV in wide area search and surveillance operations in unstructured outdoor environments. The critical issue with such envir...
Chapter
Anomaly detection is a classical problem in computer vision, namely the determination of the normal from the abnormal when datasets are highly biased towards one class (normal) due to the insufficient sample size of the other class (abnormal). While this can be addressed as a supervised learning problem, a significantly more challenging problem is...
Preprint
Full-text available
Robust geometric and semantic scene understanding is ever more important in many real-world applications such as autonomous driving and robotic navigation. In this paper, we propose a multi-task learning-based approach capable of jointly performing geometric and semantic scene understanding, namely depth prediction (monocular depth estimation and d...
Article
In this work, the issue of depth filling is addressed using a self-supervised feature learning model that predicts missing depth pixel values based on the context and structure of the scene. A fully-convolutional generative model is conditioned on the available depth information and full RGB colour information from the scene and trained in an adver...
Preprint
Full-text available
Despite inherent ill-definition, anomaly detection is a research endeavor of great interest within machine learning and visual scene understanding alike. Most commonly, anomaly detection is considered as the detection of outliers within a given data distribution based on some measure of normality. The most significant challenge in real-world anomal...
Preprint
Full-text available
Despite significant recent progress in the area of Brain-Computer Interface, there are numerous shortcomings associated with collecting Electroencephalography (EEG) signals in real-world environments. These include, but are not limited to, subject and session data variance, long and arduous calibration processes and performance generalisation issue...
Preprint
Full-text available
We introduce style augmentation, a new form of data augmentation based on random style transfer, for improving the robustness of convolutional neural networks (CNN) over both classification and regression based tasks. During training, our style augmentation randomizes texture, contrast and color, while preserving shape and semantic content. This is...
Chapter
Recent automotive vision work has focused almost exclusively on processing forward-facing cameras. However, future autonomous vehicles will not be viable without a more comprehensive surround sensing, akin to a human driver, as can be provided by 360\(^\circ \)panoramic cameras. We present an approach to adapt contemporary deep network architecture...
Preprint
Full-text available
Recent automotive vision work has focused almost exclusively on processing forward-facing cameras. However, future autonomous vehicles will not be viable without a more comprehensive surround sensing, akin to a human driver, as can be provided by 360{\deg} panoramic cameras. We present an approach to adapt contemporary deep network architectures de...
Chapter
We address the problem of hole filling in depth images, obtained from either active or stereo sensing, for the purposes of depth image completion in an exemplar-based framework. Most existing exemplar-based inpainting techniques, designed for color image completion, do not perform well on depth information with object boundaries obstructed or surro...
Preprint
Full-text available
Anomaly detection is a classical problem in computer vision, namely the determination of the normal from the abnormal when datasets are highly biased towards one class (normal) due to the insufficient sample size of the other class (abnormal). While this can be addressed as a supervised learning problem, a significantly more challenging problem is...
Article
Despite significant research focus on 3D scene capture systems, numerous unresolved challenges remain in relation to achieving full coverage scene depth estimation which is the key part of any modern 3D sensing system. This has created an area of research where the goal is to complete the missing 3D information post capture via a secondary depth fi...
Conference Paper
Full-text available
We address plausible hole filling in depth images in a computationally lightweight methodology that leverages recent advances in semantic scene segmentation. Firstly, we perform such segmentation over a co-registered color image, commonly available from stereo depth sources, and non-parametrically fill missing depth values based on a multipass basi...
Article
Full-text available
The "digital Michelangelo project" was a seminal computer vision project in the early 2000's that pushed the capabilities of acquisition systems and involved multiple people from diverse fields, many of whom are now leaders in industry and academia. Reviewing this project with modern eyes provides us with the opportunity to reflect on several issue...
Article
Full-text available
Iris-based biometric systems identify individuals based on the characteristics of their iris, since they are proven to remain unique for a long time. An iris recognition system includes four phases, the most important of which is preprocessing in which the iris segmentation is performed. The accuracy of an iris biometric system critically depends o...
Conference Paper
Full-text available
In this paper, an efficient particle swarm optimization (PSO) algorithm based on fuzzy logic for solving the single source shortest path problem (SPP) is proposed. A particle encoding/decoding scheme has been devised for particle-representation of the SPP parameters, which is free of the previously randomized path construction methods in computatio...
Conference Paper
Full-text available
In this paper, some of the image processing and pattern recognition methods that have been used on medical images for cancer diagnosis are reviewed. Previous studies on Artificial Neural Networks, Genetic Programming, and Wavelet Analysis are described with their working process and advantages. The definition of each method is provided in this stud...
Conference Paper
This paper proposes a robust edge detection method based on Fuzzy Sets and Cellular Learning Automata (CLA). The proposed method includes two steps: (a) extracting the edges and (b) enhancing them by removing unwanted edges and eliminating false edges caused by noise. The performance of the proposed edge detector is tested on various test images wi...
Conference Paper
Graph Coloring is a classic NP-hard problem; hence, it is theoretically of great importance. The wide range of its applications has also made the scientific community to be constantly in search of an efficient solution to graph coloring. In this paper, a modified particle swarm optimization is combined with fuzzy logic to obtain a high performance...
Article
Full-text available
Artificial Intelligence (AI) techniques are now commonly used tosolve complex and ill-defined problems. AI a broad field and willbring different meanings for different people. John McCarthy wouldprobably use AI as “computational intelligence”, while Zadehclaimed that computational intelligence is actually Soft Computing(SC) techniques. Regardless o...
Article
Full-text available
Artificial Intelligence (AI) techniques are now commonly used to solve complex and ill-defined problems. AI a broad field and will bring different meanings for different people. John McCarthy would probably use AI as “computational intelligence”, while Zadeh claimed that computational intelligence is actually Soft Computing (SC) techniques. Regardl...

Network

Cited By