Meem Arafat Manab
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Meem Arafat Manab has a total of 46 co-authors. Here are the top co-authors by number of shared publications:
- Jannatun Noor
C2SG Research Group, Computer Science and Engineering, United International University, Dhaka, Bangladesh
7 shared publications - Joyanta Jyoti Mondal
Department of Computer and Information Sciences University of Delaware United States
7 shared publications - Farhadul Islam
Department of CSE, BRAC University, Dhaka, Bangladesh
6 shared publications - Farig Sadeque
Department of Computer Science and Engineering Brac University Dhaka Bangladesh
3 shared publications - Sarah Zabeen
Computing for Sustainability and Social Good (C2SG) Research Group, Department of Computer Science and Engineering, United International University, Dhaka, Bangladesh; Department of Mathematics and Natural Sciences, School of Data and Sciences, BRAC University, Dhaka, Bangladesh
3 shared publications - Fardin Bin Rahman
School of Data and Sciences, BRAC University, Dhaka, Bangladesh
2 shared publications
Latest Publications
- 23 October 2026
- Published by Springer Nature
- p. 530-549
An Open Linked Data Portal for Benchmarking Web AI Agents in the European Health Data Space
- 23 October 2026
- Published by Springer Nature
- p. 530-549
An Open Linked Data Portal for Benchmarking Web AI Agents in the European Health Data Space
- 23 October 2026
- Published by Springer Nature
- p. 663-680
NORMA: A Semantic Framework for Legal Norm Representation from Annotated BPMN
- 23 October 2026
- Published by Springer Nature
- p. 663-680
NORMA: A Semantic Framework for Legal Norm Representation from Annotated BPMN
- Open Access
- 29 May 2026
- Published by Elsevier in SSRN Electronic Journal
Siliconwashing: How Claims of AI Autonomy Hide the Blood and Sweat of Invisible Workers
This paper introduces the term "siliconwashing", signifying the corporate practice of deploying narratives of AI autonomy to obscure the exploited human labor underpinning AI systems. We demonstrate how siliconwashing operates as the dialectical counterpart to "humanwashing": while humanwashing anthropomorphizes machines to exaggerate their capabilities, siliconwashing dehumanizes workers to render their labor invisible. Through the OpenAI case study, where content moderators earned $1.50 per hour reviewing traumatic material while the company marketed ChatGPT as autonomous and self-learning, we reveal how autonomy narratives systematically hide workers' blood and sweat. This dual legitimation strategy, elevating machines to autonomous agents while reducing humans to expendable components, creates hierarchies of worthiness that render Global South labor exploitation structurally invisible. We argue that every claim of AI autonomy conceals a chain of invisible workers whose suffering makes the "autonomous" system possible.
- 29 May 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessSiliconwashing: How Claims of AI Autonomy Hide the Blood and Sweat of Invisible Workers
This paper introduces the term "siliconwashing", signifying the corporate practice of deploying narratives of AI autonomy to obscure the exploited human labor underpinning AI systems. We demonstrate how siliconwashing operates as the dialectical counterpart to "humanwashing": while humanwashing anthropomorphizes machines to exaggerate their capabilities, siliconwashing dehumanizes workers to render their labor invisible. Through the OpenAI case study, where content moderators earned $1.50 per hour reviewing traumatic material while the company marketed ChatGPT as autonomous and self-learning, we reveal how autonomy narratives systematically hide workers' blood and sweat. This dual legitimation strategy, elevating machines to autonomous agents while reducing humans to expendable components, creates hierarchies of worthiness that render Global South labor exploitation structurally invisible. We argue that every claim of AI autonomy conceals a chain of invisible workers whose suffering makes the "autonomous" system possible.
- Open Access
- 27 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 48683-48702
Aerial Flood Scene Classification Using Fine-Tuned Attention-Based Architecture for Flood-Prone Countries in South Asia
Countries in South Asia experience many catastrophic flooding events regularly. It takes time to execute Search and Rescue (SAR) missions in such flooded areas.With the help of image classification, it is possible to expedite such initiatives by classifying flood zones and other locations of interest like houses and humans within such regions. In this paper, we propose a new dataset to enhance SAR by collecting various aerial imagery of flooding events across South Asian countries. For the classification, we propose a fine-tuned Compact Convolutional Transformer (CCT) based approach and some other cutting-edge transformer-based and Convolutional Neural Network-based architectures (CNN). We also implement the YOLOv12 object detection model and detect houses and humans within the imagery of our proposed dataset, and then compare the performance with our classification-based approach. Since the countries in South Asia have similar topography, housing structure, the color of flood water, and vegetation, this work can be more applicable to such a region as opposed to the rest of the world. The images are divided evenly into four classes: ‘flood’, ‘flood with domicile’, ‘flood with humans’, and ‘no flood’. After experimenting with our proposed dataset on our fine-tuned CCT model, which has a comparatively lower number of weight parameters than many other transformer-based architectures designed for computer vision, it exhibits an accuracy and macro average precision of 98.62% and 98.50%. The other transformer-based architectures that we implement are the Vision Transformer (ViT), Swin Transformer, and External Attention Transformer (EANet), which give an accuracy of 88.66%, 84.74%, and 66.56% respectively. We also implement DCECNN (Deep Custom Ensembled Convolutional Neural Network), which is a custom ensemble model that we create by combining MobileNetV3-Small, InceptionV3 , and EfficientNetB0, and we obtain an accuracy of 98.78%. The architectures we implement are fine-tuned to achieve optimal performance on our dataset.
- 27 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 48683-48702
Open AccessAerial Flood Scene Classification Using Fine-Tuned Attention-Based Architecture for Flood-Prone Countries in South Asia
Countries in South Asia experience many catastrophic flooding events regularly. It takes time to execute Search and Rescue (SAR) missions in such flooded areas.With the help of image classification, it is possible to expedite such initiatives by classifying flood zones and other locations of interest like houses and humans within such regions. In this paper, we propose a new dataset to enhance SAR by collecting various aerial imagery of flooding events across South Asian countries. For the classification, we propose a fine-tuned Compact Convolutional Transformer (CCT) based approach and some other cutting-edge transformer-based and Convolutional Neural Network-based architectures (CNN). We also implement the YOLOv12 object detection model and detect houses and humans within the imagery of our proposed dataset, and then compare the performance with our classification-based approach. Since the countries in South Asia have similar topography, housing structure, the color of flood water, and vegetation, this work can be more applicable to such a region as opposed to the rest of the world. The images are divided evenly into four classes: ‘flood’, ‘flood with domicile’, ‘flood with humans’, and ‘no flood’. After experimenting with our proposed dataset on our fine-tuned CCT model, which has a comparatively lower number of weight parameters than many other transformer-based architectures designed for computer vision, it exhibits an accuracy and macro average precision of 98.62% and 98.50%. The other transformer-based architectures that we implement are the Vision Transformer (ViT), Swin Transformer, and External Attention Transformer (EANet), which give an accuracy of 88.66%, 84.74%, and 66.56% respectively. We also implement DCECNN (Deep Custom Ensembled Convolutional Neural Network), which is a custom ensemble model that we create by combining MobileNetV3-Small, InceptionV3 , and EfficientNetB0, and we obtain an accuracy of 98.78%. The architectures we implement are fine-tuned to achieve optimal performance on our dataset.
- 24 April 2025
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 192 (Pt A) , 110174
Involution-based efficient autoencoder for denoising histopathological images with enhanced hybrid feature extraction
- 24 April 2025
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 192 (Pt A) , 110174
Involution-based efficient autoencoder for denoising histopathological images with enhanced hybrid feature extraction
- Open Access
Aerial Flood Scene Classification Using Fine-Tuned Attention-based Architecture for Flood-Prone Countries in South Asia
Countries in South Asia experience many catastrophic flooding events regularly. Through image classification, it is possible to expedite search and rescue initiatives by classifying flood zones, including houses and humans. We create a new dataset collecting aerial imagery of flooding events across South Asian countries. For the classification, we propose a fine-tuned Compact Convolutional Transformer (CCT) based approach and some other cutting-edge transformer-based and Convolutional Neural Network-based architectures (CNN). We also implement the YOLOv8 object detection model and detect houses and humans within the imagery of our proposed dataset, and then compare the performance with our classification-based approach. Since the countries in South Asia have similar topography, housing structure, the color of flood water, and vegetation, this work can be more applicable to such a region as opposed to the rest of the world. The images are divided evenly into four classes: 'flood', 'flood with domicile', 'flood with humans', and 'no flood'. After experimenting with our proposed dataset on our fine-tuned CCT model, which has a comparatively lower number of weight parameters than many other transformer-based architectures designed for computer vision, it exhibits an accuracy and macro average precision of 98.62% and 98.50%. The other transformer-based architectures that we implement are the Vision Transformer (ViT), Swin Transformer, and External Attention Transformer (EANet), which give an accuracy of 88.66%, 84.74%, and 66.56% respectively. We also implement DCECNN (Deep Custom Ensembled Convolutional Neural Network), which is a custom ensemble model that we create by combining MobileNet, InceptionV3, and EfficientNetB0, and we obtain an accuracy of 98.78%. The architectures we implement are fine-tuned to achieve optimal performance on our dataset.
Open AccessAerial Flood Scene Classification Using Fine-Tuned Attention-based Architecture for Flood-Prone Countries in South Asia
Countries in South Asia experience many catastrophic flooding events regularly. Through image classification, it is possible to expedite search and rescue initiatives by classifying flood zones, including houses and humans. We create a new dataset collecting aerial imagery of flooding events across South Asian countries. For the classification, we propose a fine-tuned Compact Convolutional Transformer (CCT) based approach and some other cutting-edge transformer-based and Convolutional Neural Network-based architectures (CNN). We also implement the YOLOv8 object detection model and detect houses and humans within the imagery of our proposed dataset, and then compare the performance with our classification-based approach. Since the countries in South Asia have similar topography, housing structure, the color of flood water, and vegetation, this work can be more applicable to such a region as opposed to the rest of the world. The images are divided evenly into four classes: 'flood', 'flood with domicile', 'flood with humans', and 'no flood'. After experimenting with our proposed dataset on our fine-tuned CCT model, which has a comparatively lower number of weight parameters than many other transformer-based architectures designed for computer vision, it exhibits an accuracy and macro average precision of 98.62% and 98.50%. The other transformer-based architectures that we implement are the Vision Transformer (ViT), Swin Transformer, and External Attention Transformer (EANet), which give an accuracy of 88.66%, 84.74%, and 66.56% respectively. We also implement DCECNN (Deep Custom Ensembled Convolutional Neural Network), which is a custom ensemble model that we create by combining MobileNet, InceptionV3, and EfficientNetB0, and we obtain an accuracy of 98.78%. The architectures we implement are fine-tuned to achieve optimal performance on our dataset.
- Open Access
Med-IC: Fusing a Single Layer Involution with Convolutions for Enhanced Medical Image Classification and Segmentation
The majority of medical images, especially those that resemble cells, have similar characteristics. These images, which occur in a variety of shapes, often show abnormalities in the organ or cell region. The convolution operation possesses a restricted capability to extract visual patterns across several spatial regions of an image. The involution process, which is the inverse operation of convolution, complements this inherent lack of spatial information extraction present in convolutions. In this study, we investigate how applying a single layer of involution prior to a convolutional neural network (CNN) architecture can significantly improve classification and segmentation performance, with a comparatively negligible amount of weight parameters. The study additionally shows how excessive use of involution layers might result in inaccurate predictions in a particular type of medical image. According to our findings from experiments, the strategy of adding only a single involution layer before a CNN-based model outperforms most of the previous works.
Open AccessMed-IC: Fusing a Single Layer Involution with Convolutions for Enhanced Medical Image Classification and Segmentation
The majority of medical images, especially those that resemble cells, have similar characteristics. These images, which occur in a variety of shapes, often show abnormalities in the organ or cell region. The convolution operation possesses a restricted capability to extract visual patterns across several spatial regions of an image. The involution process, which is the inverse operation of convolution, complements this inherent lack of spatial information extraction present in convolutions. In this study, we investigate how applying a single layer of involution prior to a convolutional neural network (CNN) architecture can significantly improve classification and segmentation performance, with a comparatively negligible amount of weight parameters. The study additionally shows how excessive use of involution layers might result in inaccurate predictions in a particular type of medical image. According to our findings from experiments, the strategy of adding only a single involution layer before a CNN-based model outperforms most of the previous works.
- Open Access
Uncovering local aggregated air quality index with smartphone captured images leveraging efficient deep convolutional neural network
The prevalence and mobility of smartphones make these a widely used tool for environmental health research. However, their potential for determining aggregated air quality index (AQI) based on PM2.5 concentration in specific locations remains largely unexplored in the existing literature. In this paper, we thoroughly examine the challenges associated with predicting location-specific PM2.5 concentration using images taken with smartphone cameras. The focus of our study is on Dhaka, the capital of Bangladesh, due to its significant air pollution levels and the large population exposed to it. Our research involves the development of a Deep Convolutional Neural Network (DCNN), which we train using over a thousand outdoor images taken and annotated. These photos are captured at various locations in Dhaka, and their labels are based on PM2.5 concentration data obtained from the local US consulate, calculated using the NowCast algorithm. Through supervised learning, our model establishes a correlation index during training, enhancing its ability to function as a Picture-based Predictor of PM2.5 Concentration (PPPC). This enables the algorithm to calculate an equivalent daily averaged AQI index from a smartphone image. Unlike, popular overly parameterized models, our model shows resource efficiency since it uses fewer parameters. Furthermore, test results indicate that our model outperforms popular models like ViT and INN, as well as popular CNN-based models such as VGG19, ResNet50, and MobileNetV2, in predicting location-specific PM2.5 concentration. Our dataset is the first publicly available collection that includes atmospheric images and corresponding PM2.5 measurements from Dhaka. Our codes and dataset are available at https://github.com/lepotatoguy/aqi.
Open AccessUncovering local aggregated air quality index with smartphone captured images leveraging efficient deep convolutional neural network
The prevalence and mobility of smartphones make these a widely used tool for environmental health research. However, their potential for determining aggregated air quality index (AQI) based on PM2.5 concentration in specific locations remains largely unexplored in the existing literature. In this paper, we thoroughly examine the challenges associated with predicting location-specific PM2.5 concentration using images taken with smartphone cameras. The focus of our study is on Dhaka, the capital of Bangladesh, due to its significant air pollution levels and the large population exposed to it. Our research involves the development of a Deep Convolutional Neural Network (DCNN), which we train using over a thousand outdoor images taken and annotated. These photos are captured at various locations in Dhaka, and their labels are based on PM2.5 concentration data obtained from the local US consulate, calculated using the NowCast algorithm. Through supervised learning, our model establishes a correlation index during training, enhancing its ability to function as a Picture-based Predictor of PM2.5 Concentration (PPPC). This enables the algorithm to calculate an equivalent daily averaged AQI index from a smartphone image. Unlike, popular overly parameterized models, our model shows resource efficiency since it uses fewer parameters. Furthermore, test results indicate that our model outperforms popular models like ViT and INN, as well as popular CNN-based models such as VGG19, ResNet50, and MobileNetV2, in predicting location-specific PM2.5 concentration. Our dataset is the first publicly available collection that includes atmospheric images and corresponding PM2.5 measurements from Dhaka. Our codes and dataset are available at https://github.com/lepotatoguy/aqi.