ORCID Profile
0000-0001-7169-0318
Current Organisations
Newcastle University
,
North South University
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: Elsevier BV
Date: 2016
Publisher: IEEE
Date: 10-01-2021
Publisher: Springer Science and Business Media LLC
Date: 24-07-2020
Publisher: Springer International Publishing
Date: 2021
Publisher: Public Library of Science (PLoS)
Date: 15-05-2023
DOI: 10.1371/JOURNAL.PONE.0285668
Abstract: Deep learning techniques have recently demonstrated remarkable success in numerous domains. Typically, the success of these deep learning models is measured in terms of performance metrics such as accuracy and mean average precision (mAP). Generally, a model’s high performance is highly valued, but it frequently comes at the expense of substantial energy costs and carbon footprint emissions during the model building step. Massive emission of CO 2 has a deleterious impact on life on earth in general and is a serious ethical concern that is largely ignored in deep learning research. In this article, we mainly focus on environmental costs and the means of mitigating carbon footprints in deep learning models, with a particular focus on models created using knowledge distillation (KD). Deep learning models typically contain a large number of parameters, resulting in a ‘heavy’ model. A heavy model scores high on performance metrics but is incompatible with mobile and edge computing devices. Model compression techniques such as knowledge distillation enable the creation of lightweight, deployable models for these low-resource devices. KD generates lighter models and typically performs with slightly less accuracy than the heavier teacher model (model accuracy by the teacher model on CIFAR 10, CIFAR 100, and TinyImageNet is 95.04%, 76.03%, and 63.39% model accuracy by KD is 91.78%, 69.7%, and 60.49%). Although the distillation process makes models deployable on low-resource devices, they were found to consume an exorbitant amount of energy and have a substantial carbon footprint (15.8, 17.9, and 13.5 times more carbon compared to the corresponding teacher model). The enormous environmental cost is primarily attributable to the tuning of the hyperparameter, Temperature ( τ ). In this article, we propose measuring the environmental costs of deep learning work (in terms of GFLOPS in millions, energy consumption in kWh, and CO 2 equivalent in grams). In order to create lightweight models with low environmental costs, we propose a straightforward yet effective method for selecting a hyperparameter ( τ ) using a stochastic approach for each training batch fed into the models. We applied knowledge distillation (including its data-free variant) to problems involving image classification and object detection. To evaluate the robustness of our method, we ran experiments on various datasets (CIFAR 10, CIFAR 100, Tiny ImageNet, and PASCAL VOC) and models (ResNet18, MobileNetV2, Wrn-40-2). Our novel approach reduces the environmental costs by a large margin by eliminating the requirement of expensive hyperparameter tuning without sacrificing performance. Empirical results on the CIFAR 10 dataset show that the stochastic technique achieves an accuracy of 91.67%, whereas tuning achieves an accuracy of 91.78%—however, the stochastic approach reduces the energy consumption and CO 2 equivalent each by a factor of 19. Similar results have been obtained with CIFAR 100 and TinyImageNet dataset. This pattern is also observed in object detection classification on the PASCAL VOC dataset, where the tuning technique performs similarly to the stochastic technique, with a difference of 0.03% mAP favoring the stochastic technique while reducing the energy consumptions and CO 2 emission each by a factor of 18.5.
Publisher: Springer International Publishing
Date: 2021
Publisher: IEEE
Date: 06-2021
Publisher: IEEE
Date: 10-2019
Publisher: Academy Publisher
Date: 10-2011
Publisher: Informa UK Limited
Date: 04-12-2017
DOI: 10.1080/02713683.2017.1410179
Abstract: Clinical trials have demonstrated that retinal blood flow deficiencies are present in patients with open-angle glaucoma (OAG). We introduce a method for facilitating retinal vessel analysis: The intensity of the distal shadow of vessels in optical coherence tomography (OCT) caused by the scattered signal is analyzed, compared between healthy subjects and OAG patients and correlated with OCT angiography (OCT-A) flow density. We recruited 80 patients with diagnosed OAG (mean age 63.4 ± 13.2 years) and 80 healthy age-matched control subjects for comparison, and 20 patients for the correlation with OCT-A flow density. Patients received perimetry, peripapillary OCT measurements, and selected patients OCT-A of the papillary area. The vessel shadow intensity (VSI) is based on peripapillary OCT scans: the intensity of the distal vessel shadow was automatically compared to its surroundings, separated by arteries and veins. Flow density of the OCT-A scan was calculated by binarization and quantification of the pixel density. The VSI for arteries was in OAG patients with 7.52 ± 2.62 [%] significantly lower compared to healthy subjects (9.03 ± 3.38 [%], p = 0.0029). In veins, the VSI was as well significantly lower for OAG patients (14.9 ± 3.59 [%]) compared to healthy subjects (17.46 ± 4.45 [%], p 0.05). We conclude that the OCT-based analysis of the scattering properties of retinal vessels differs significantly between patients with OAG and healthy subjects. Furthermore, changes in the scattering properties of veins correlated with the stage of the disease in terms of visual field deficits. These properties might complement existing measurements of ocular blood flow including OCT-A flow density.
Publisher: MDPI AG
Date: 21-01-2021
DOI: 10.20944/PREPRINTS202101.0418.V1
Abstract: Over the last decade, there has been a renewed interest in oral health workforce planning. The purpose of this review is to examine oral health workforce planning models on supply, demand and needs, mainly in respect to their data sources, modelling technique and use of skill mix. A search was carried out on PubMed, Web of Science, and Google Scholar databases for published scientific articles on oral health workforce planning models between 2010 to 2020. No restrictions were placed on the type of modelling philosophy, and all studies including supply, demand or needs based models were included. Rapid review methods guided the review process. Twenty-three studies from 15 different countries were included in the review. A majority were from high income countries (n=17). Dentists were the sole oral health workforce group modelled in 13 studies only five studied included skill mix (allied dental personnel) considerations. The most common application of modelling was a workforce to population ratio or a needs-based demand weighted variant. Nearly all studies presented weaknesses in modelling process due to the limitations in data sources and/or non availability of necessary data to inform oral health workforce planning. Skill mix considerations in planning models were also limited to horizontal integration within oral health professionals. Planning for the future oral health workforce is heavily reliant on quality data being available for supply, demand and needs models. Integrated methodologies that expand skill mix considerations and account for uncertainty are essential for future planning exercises.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2022
Publisher: Elsevier BV
Date: 12-2016
Publisher: Elsevier BV
Date: 11-2015
DOI: 10.1016/J.VISRES.2015.01.010
Abstract: In the past decade, a large number of computational models of visual saliency have been proposed. Recently a number of comprehensive benchmark studies have been presented, with the goal of assessing the performance landscape of saliency models under varying conditions. This has been accomplished by considering fixation data, annotated image regions, and stimulus patterns inspired by psychophysics. In this paper, we present a high-level examination of challenges in computational modeling of visual saliency, with a heavy emphasis on human vision and neural computation. This includes careful assessment of different metrics for performance of visual saliency models, and identification of remaining difficulties in assessing model performance. We also consider the importance of a number of issues relevant to all saliency models including scale-space, the impact of border effects, and spatial or central bias. Additionally, we consider the biological plausibility of models in stepping away from exemplar input patterns towards a set of more general theoretical principles consistent with behavioral experiments. As a whole, this presentation establishes important obstacles that remain in visual saliency modeling, in addition to identifying a number of important avenues for further investigation.
Publisher: IEEE
Date: 10-2021
Publisher: Springer International Publishing
Date: 2021
Publisher: Springer International Publishing
Date: 2021
Publisher: MDPI AG
Date: 12-03-2021
Abstract: Over the last decade, there has been a renewed interest in oral health workforce planning. The purpose of this review is to examine oral health workforce planning models on supply, demand and needs, mainly in respect to their data sources, modelling technique and use of skill mix. A limited search was carried out on PubMed and Web of Science for published scientific articles on oral health workforce planning models between 2010 to 2020. No restrictions were placed on the type of modelling philosophy, and all studies including supply, demand or needs based models were included. Rapid review methods guided the review process. Twenty-three studies from 15 countries were included in the review. A majority were from high-income countries (n = 17). Dentists were the sole oral health workforce group modelled in 13 studies only five studies included skill mix (allied dental personnel) considerations. The most common application of modelling was a workforce to population ratio or a needs-based demand weighted variant. Nearly all studies presented weaknesses in modelling process due to the limitations in data sources and/or non-availability of the necessary data to inform oral health workforce planning. Skill mix considerations in planning models were also limited to horizontal integration within oral health professionals. Planning for the future oral health workforce is heavily reliant on quality data being available for supply, demand and needs models. Integrated methodologies that expand skill mix considerations and account for uncertainty are essential for future planning exercises.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2020
Publisher: Springer International Publishing
Date: 2021
Publisher: Informa UK Limited
Date: 15-10-2018
Publisher: Springer Science and Business Media LLC
Date: 04-08-2022
Publisher: Springer International Publishing
Date: 2019
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2022
Publisher: Springer International Publishing
Date: 2019
Publisher: Public Library of Science (PLoS)
Date: 14-09-2015
Publisher: Springer Nature Switzerland
Date: 2022
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 11-2018
Publisher: Springer International Publishing
Date: 2021
Location: United Kingdom of Great Britain and Northern Ireland
Location: United Kingdom of Great Britain and Northern Ireland
Location: United Kingdom of Great Britain and Northern Ireland
Location: United Kingdom of Great Britain and Northern Ireland
No related grants have been discovered for Shafin Rahman.