Jebran Khan | Korea Aerospace University (original) (raw)

Papers by Jebran Khan

Research paper thumbnail of A Deep Learning-Based Framework for Offensive Text Detection in Unstructured Data for Heterogeneous Social Media

IEEE Access

Social media such as Facebook, Instagram, and Twitter are powerful and essential platforms where ... more Social media such as Facebook, Instagram, and Twitter are powerful and essential platforms where people express and share their ideas, knowledge, talents, and abilities with others. Users on social media also share harmful content, such as targeting gender, religion, race, and trolling. These posts may be in the form of tweets, videos, images, and memes. A meme is one of the mediums on social media which has an image and embedded text in it. These memes convey various views, including fun or offensiveness, that may be a personal attack, hate speech, or racial abuse. Such posts need to be filtered out immediately from social media. This paper presents a framework that detects offensive text in memes and prevents such nuisance from being posted on social media, using the collected KAU-Memes dataset 2582. The latter combines the ''2016 U.S. Election'' dataset with the newly generated memes from a series of offensive and non-offensive tweets datasets. In fact, this model uses the KAU-Memes dataset containing symbolic images and the corresponding text to validate the proposed model. We compare the performance of three proposed deep-learning algorithms to train and detect offensive text in memes. To the best of the authors knowledge and literature review, this is the first approach based on You Only Look Once (YOLO) for offensive text detection in memes. This framework uses YOLOv4, YOLOv5, and SSD MobileNetV2 to compare the model's performance on the newly labeled KAU-Memes dataset. The results show that the proposed model achieved 81.

Research paper thumbnail of An Efficient Character-Level Adversarial Attack Inspired by Textual Variations in Online Social Media Platforms

Computer Systems Science and Engineering

Research paper thumbnail of Artificial Intelligence and Internet of Things (AI-IoT) Technologies in Response to COVID-19 Pandemic: A Systematic Review

IEEE Access, 2022

The origin of the COVID-19 pandemic has given overture to redirection, as well as innovation to m... more The origin of the COVID-19 pandemic has given overture to redirection, as well as innovation to many digital technologies. Even after the progression of vaccination efforts across the globe, total eradication of this pandemic is still a distant future due to the evolution of new variants. To proactively deal with the pandemic, the health care service providers and the caretaker organizations require new technologies, alongside improvements in existing related technologies, Internet of Things (IoT), Artificial Intelligence (AI), and Machine Learning in terms of infrastructure, efficiency, privacy, and security. This paper provides an overview of current theoretical and application prospects of IoT, AI, cloud computing, edge computing, deep learning techniques, blockchain technologies, social networks, robots, machines, privacy, and security techniques. In consideration of these prospects in intersection with the COVID-19 pandemic, we reviewed the technologies within the broad umbrella of AI-IoT technologies in the most concise classification scheme. In this review, we illustrated that AI-IoT technological applications and innovations have most impacted the field of healthcare. The essential AI-IoT technologies found for healthcare were fog computing in IoT, deep learning, and blockchain. Furthermore, we highlighted several aspects of these technologies and their future impact with a novel methodology of using techniques from image processing, machine learning, and differential system modeling. INDEX TERMS Artificial intelligence, compartment model, COVID-19, internet of things, image processing.

Research paper thumbnail of Social Media as an Instant Source of Feedback on Water Quality

IEEE transactions on technology and society, 2023

This paper focuses on an important environmental challenge: water quality by analyzing the potent... more This paper focuses on an important environmental challenge: water quality by analyzing the potential of social media as an immediate source of feedback. The main goal of the work is to automatically analyze and retrieve social media posts relevant to water quality with particular attention to posts describing different aspects of water quality, such as watercolor, smell, taste, and related illnesses. To this aim, we propose a novel framework incorporating different preprocessing, data augmentation, and classification techniques. In total, three different Neural Networks (NNs) architectures, namely (i) Bidirectional Encoder Representations from Transformers (BERT), (ii) Robustly Optimized BERT Pre-training Approach (XLM-RoBERTa), and (iii) custom Long short-term memory (LSTM) model, are employed in a merit-based fusion scheme. For merit-based weight assignment to the models, several optimization and search techniques are compared including a Particle Swarm Optimization (PSO), a Genetic Algorithm (GA), Brute Force (BF), Nelder-Mead, and Powell's optimization methods. We also provide an evaluation of the individual models where the highest F1-score of 0.81 is obtained with the BERT model. Overall, in merit-based fusion, better results are obtained with BF achieving an F1-score score of 0.852. We also provide a comparison against existing methods, where a significant improvement for our proposed solutions is obtained. We believe such a rigorous analysis of this relatively new topic will provide a baseline for future research.

Research paper thumbnail of An Explainable Regression Framework for Predicting Remaining Useful Life of Machines

2022 27th International Conference on Automation and Computing (ICAC), Sep 1, 2022

Prediction of a machine's Remaining Useful Life (RUL) is one of the key tasks in predictive maint... more Prediction of a machine's Remaining Useful Life (RUL) is one of the key tasks in predictive maintenance. The task is treated as a regression problem where Machine Learning (ML) algorithms are used to predict the RUL of machine components. These ML algorithms are generally used as a black box with a total focus on the performance without identifying the potential causes behind the algorithms' decisions and their working mechanism. We believe, the performance (in terms of Mean Squared Error (MSE), etc.,) alone is not enough to build the stakeholders' trust in ML prediction rather more insights on the causes behind the predictions are needed. To this aim, in this paper, we explore the potential of Explainable AI (XAI) techniques by proposing an explainable regression framework for the prediction of machines' RUL. We also evaluate several ML algorithms including classical and Neural Networks (NNs) based solutions for the task. For the explanations, we rely on two model agnostic XAI methods namely Local Interpretable Model-Agnostic Explanations (LIME) and Shapley Additive Explanations (SHAP). We believe, this work will provide a baseline for future research in the domain.

Research paper thumbnail of Document Provenance and Authentication through Authorship Classification

arXiv (Cornell University), Mar 2, 2023

Style analysis, which is relatively a less explored topic, enables several interesting applicatio... more Style analysis, which is relatively a less explored topic, enables several interesting applications. For instance, it allows authors to adjust their writing style to produce a more coherent document in collaboration. Similarly, style analysis can also be used for document provenance and authentication as a primary step. In this paper, we propose an ensemble-based text-processing framework for the classification of single and multi-authored documents, which is one of the key tasks in style analysis. The proposed framework incorporates several state-of-the-art text classification algorithms including classical Machine Learning (ML) algorithms, transformers, and deep learning algorithms both individually and in merit-based late fusion. For the merit-based late fusion, we employed several weight optimization and selection methods to assign merit-based weights to the individual text classification algorithms. We also analyze the impact of the characters on the task that are usually excluded in NLP applications during pre-processing by conducting experiments on both clean and un-clean data. The proposed framework is evaluated on a large-scale benchmark dataset, significantly improving performance over the existing solutions.

Research paper thumbnail of Floods Relevancy and Identification of Location from Twitter Posts using NLP Techniques

arXiv (Cornell University), Dec 31, 2022

This paper presents our solutions for the MediaEval 2022 task on DisasterMM. The task is composed... more This paper presents our solutions for the MediaEval 2022 task on DisasterMM. The task is composed of two subtasks, namely (i) Relevance Classification of Twitter Posts (RCTP), and (ii) Location Extraction from Twitter Texts (LETT). The RCTP subtask aims at differentiating flood-related and non-relevant social posts while LETT is a Named Entity Recognition (NER) task and aims at the extraction of location information from the text. For RCTP, we proposed four different solutions based on BERT, RoBERTa, Distil BERT, and ALBERT obtaining an F1-score of 0.7934, 0.7970, 0.7613, and 0.7924, respectively. For LETT, we used three models namely BERT, RoBERTa, and Distil BERTA obtaining an F1-score of 0.6256, 0.6744, and 0.6723, respectively.

Research paper thumbnail of COVID-19 spread control policies based early dynamics forecasting using deep learning algorithm

Chaos, Solitons & Fractals

Research paper thumbnail of An Explainable Regression Framework for Predicting Remaining Useful Life of Machines

2022 27th International Conference on Automation and Computing (ICAC)

Prediction of a machine's Remaining Useful Life (RUL) is one of the key tasks in predictive maint... more Prediction of a machine's Remaining Useful Life (RUL) is one of the key tasks in predictive maintenance. The task is treated as a regression problem where Machine Learning (ML) algorithms are used to predict the RUL of machine components. These ML algorithms are generally used as a black box with a total focus on the performance without identifying the potential causes behind the algorithms' decisions and their working mechanism. We believe, the performance (in terms of Mean Squared Error (MSE), etc.,) alone is not enough to build the stakeholders' trust in ML prediction rather more insights on the causes behind the predictions are needed. To this aim, in this paper, we explore the potential of Explainable AI (XAI) techniques by proposing an explainable regression framework for the prediction of machines' RUL. We also evaluate several ML algorithms including classical and Neural Networks (NNs) based solutions for the task. For the explanations, we rely on two model agnostic XAI methods namely Local Interpretable Model-Agnostic Explanations (LIME) and Shapley Additive Explanations (SHAP). We believe, this work will provide a baseline for future research in the domain.

Research paper thumbnail of Social Media as an Instant Source of Feedback on Water Quality

IEEE Transactions on Technology and Society

This paper focuses on an important environmental challenge: water quality by analyzing the potent... more This paper focuses on an important environmental challenge: water quality by analyzing the potential of social media as an immediate source of feedback. The main goal of the work is to automatically analyze and retrieve social media posts relevant to water quality with particular attention to posts describing different aspects of water quality, such as watercolor, smell, taste, and related illnesses. To this aim, we propose a novel framework incorporating different preprocessing, data augmentation, and classification techniques. In total, three different Neural Networks (NNs) architectures, namely (i) Bidirectional Encoder Representations from Transformers (BERT), (ii) Robustly Optimized BERT Pre-training Approach (XLM-RoBERTa), and (iii) custom Long short-term memory (LSTM) model, are employed in a merit-based fusion scheme. For merit-based weight assignment to the models, several optimization and search techniques are compared including a Particle Swarm Optimization (PSO), a Genetic Algorithm (GA), Brute Force (BF), Nelder-Mead, and Powell's optimization methods. We also provide an evaluation of the individual models where the highest F1-score of 0.81 is obtained with the BERT model. Overall, in merit-based fusion, better results are obtained with BF achieving an F1-score score of 0.852. We also provide a comparison against existing methods, where a significant improvement for our proposed solutions is obtained. We believe such a rigorous analysis of this relatively new topic will provide a baseline for future research.

Research paper thumbnail of Mobile sensors based platform of Human Physical Activities Recognition for COVID-19 spread minimization

Computers in Biology and Medicine

Research paper thumbnail of Document Provenance and Authentication through Authorship Classification

2023 1st International Conference on Advanced Innovations in Smart Cities (ICAISC)

Research paper thumbnail of A Real-Time Framework for Human Face Detection and Recognition in CCTV Images

Mathematical Problems in Engineering, 2022

This paper aims to develop a machine learning and deep learning-based real-time framework for det... more This paper aims to develop a machine learning and deep learning-based real-time framework for detecting and recognizing human faces in closed-circuit television (CCTV) images. The traditional CCTV system needs a human for 24/7 monitoring, which is costly and insufficient. The automatic recognition system of faces in CCTV images with minimum human intervention and reduced cost can help many organizations, such as law enforcement, identifying the suspects, missing people, and people entering a restricted territory. However, image-based recognition has many issues, such as scaling, rotation, cluttered backgrounds, and variation in light intensity. This paper aims to develop a CCTV image-based human face recognition system using different techniques for feature extraction and face recognition. The proposed system includes image acquisition from CCTV, image preprocessing, face detection, localization, extraction from the acquired images, and recognition. We use two feature extraction alg...

Research paper thumbnail of Online Social Networks (OSN) Evolution Model Based on Homophily and Preferential Attachment

Symmetry, 2018

In this paper, we propose a new scale-free social networks (SNs) evolution model that is based on... more In this paper, we propose a new scale-free social networks (SNs) evolution model that is based on homophily combined with preferential attachments. Our model enables the SN researchers to generate SN synthetic data for the evaluation of multi-facet SN models that are dependent on users’ attributes and similarities. Homophily is one of the key factors for interactive relationship formation in SN. The synthetic graph generated by our model is scale-invariant and has symmetric relationships. The model is dynamic and sustainable to changes in input parameters, such as number of nodes and nodes’ attributes, by conserving its structural properties. Simulation and evaluation of models for large-scale SN applications need large datasets. One way to get SN data is to generate synthetic data by using SN evolution models. Various SN evolution models are proposed to approximate the real-life SN graphs in previous research. These models are based on SN structural properties such as preferential ...

Research paper thumbnail of Merit-based Fusion of NLP Techniques for Instant Feedback on Water Quality from Twitter Text

This paper focuses on an important environmental challenge; namely, water quality by analyzing th... more This paper focuses on an important environmental challenge; namely, water quality by analyzing the potential of social media as an immediate source of feedback. The main goal of the work is to automatically analyze and retrieve social media posts relevant to water quality with particular attention to posts describing different aspects of water quality, such as watercolor, smell, taste, and related illnesses. To this aim, we propose a novel framework incorporating different preprocessing, data augmentation, and classification techniques. In total, three different Neural Networks (NNs) architectures, namely (i) Bidirectional Encoder Representations from Transformers (BERT), (ii) Robustly Optimized BERT Pre-training Approach (XLM-RoBERTa), and (iii) custom Long short-term memory (LSTM) model, are employed in a merit-based fusion scheme. For merit-based weight assignment to the models, several optimization and search techniques are compared including a Particle Swarm Optimization (PSO),...

Research paper thumbnail of Wearable IoTs and Geo-Fencing Based Framework for COVID-19 Remote Patient Health Monitoring and Quarantine Management to Control the Pandemic

Electronics

The epidemic disease of Severe Acute Respiratory Syndrome (SARS) called COVID-19 has become a mor... more The epidemic disease of Severe Acute Respiratory Syndrome (SARS) called COVID-19 has become a more frequently active disease. Managing and monitoring COVID-19 patients is still a challenging issue for advanced technologies. The first and foremost critical issue in COVID-19 is to diagnose it timely and cut off the chain of transmission by isolating the susceptible and patients. COVID-19 spreads through close interaction and contact with an infected person. It has affected the entire world, and every country is facing the challenges of having adequate medical facilities along with the availability of medical staff in rural and urban areas that have a high number of patients due to the pandemic. Due to the invasive method of treatment, SARS-COVID is spreading swiftly. In this paper, we propose an intelligent health monitoring framework using wearable Internet of Things (IoT) and Geo-fencing for COVID-19 susceptible and patient monitoring, and isolation and quarantine management to cont...

Research paper thumbnail of Enhancement of Text Analysis Using Context-Aware Normalization of Social Media Informal Text

Applied Sciences

We proposed an application and data variations-independent, generic social media Textual Variatio... more We proposed an application and data variations-independent, generic social media Textual Variations Handler (TVH) to deal with a wide range of noise in textual data generated in various social media (SM) applications for enhanced text analysis. The aim is to build an effective hybrid normalization technique that ensures the use of useful information of the noisy text in its intended form instead of filtering them out to analyze SM text better. The proposed TVH performs context-aware text normalization based on intended meaning to avoid the wrong word substitution. We integrate the TVH with state-of-the-art (SOTA) deep-learning-based text analysis methods to enhance their performance for noisy SM text data. The proposed scheme shows promising improvement in the text analysis of informal SM text in terms of precision, recall, accuracy, and F1-score in simulation.

Research paper thumbnail of Enhancement of Sentiment Analysis by Utilizing Noisy Social Media Texts

The Journal of Korean Institute of Communications and Information Sciences

Research paper thumbnail of Implicit User Trust Modeling Based on User Attributes and Behavior in Online Social Networks

IEEE Access

In this paper, we present a new user trustworthiness estimation model for social networks (SN), w... more In this paper, we present a new user trustworthiness estimation model for social networks (SN), whereas most of existing researches have been focused on the user-user/item relationship trustworthiness estimation. Users share information of their interest on various social media without their trustworthiness verification. Therefore, SN are susceptible to malicious users for misinformation spreading. In SN, the original information source is generally unknown and the user who is sharing the contents is the only known information about the source. Therefore, the user's trustworthiness is an effective criterion for SN content's trustworthiness estimation. However, the users are unable to identify trustworthy/untrustworthy users, and the existing user-user/item relationship models do not provide user trustworthiness information. Our proposed model provides a systematic way to assess the user trustworthiness based on user attributes and interaction behavior. The proposed model is helpful to avoid the trust sparsity (implicit trust model), trust subjectivity (user's objective/collective trustworthiness estimation model) and cold-start user's trustworthiness (user's attributes-based trust modeling) problems. We employ friends-recommendation (FR) as an exemplary application to evaluate the performance of our proposed model in trust-aware recommendations. Simulation results illustrate that our trust-aware FR model outperformed the existing trust and FR models.

Research paper thumbnail of Online Social Networks (OSN) Evolution Model Based on Homophily and Preferential Attachment

In this paper, we propose a new scale-free social networks (SNs) evolution model that is based on... more In this paper, we propose a new scale-free social networks (SNs) evolution model that is based on homophily combined with preferential attachments. Our model enables the SN researchers to generate SN synthetic data for the evaluation of multi-facet SN models that are dependent on users' attributes and similarities. Homophily is one of the key factors for interactive relationship formation in SN. The synthetic graph generated by our model is scale-invariant and has symmetric relationships. The model is dynamic and sustainable to changes in input parameters, such as number of nodes and nodes' attributes, by conserving its structural properties. Simulation and evaluation of models for large-scale SN applications need large datasets. One way to get SN data is to generate synthetic data by using SN evolution models. Various SN evolution models are proposed to approximate the real-life SN graphs in previous research. These models are based on SN structural properties such as preferential attachment. The data generated by these models is suitable to evaluate SN models that are structure dependent but not suitable to evaluate models which depend on the SN users' attributes and similarities. In our proposed model, users' attributes and similarities are utilized to synthesize SN graphs. We evaluated the resultant synthetic graph by analyzing its structural properties. In addition, we validated our model by comparing its measures with the publicly available real-life SN datasets and previous SN evolution models. Simulation results show our resultant graph to be a close representation of real-life SN graphs with users' attributes.

Research paper thumbnail of A Deep Learning-Based Framework for Offensive Text Detection in Unstructured Data for Heterogeneous Social Media

IEEE Access

Social media such as Facebook, Instagram, and Twitter are powerful and essential platforms where ... more Social media such as Facebook, Instagram, and Twitter are powerful and essential platforms where people express and share their ideas, knowledge, talents, and abilities with others. Users on social media also share harmful content, such as targeting gender, religion, race, and trolling. These posts may be in the form of tweets, videos, images, and memes. A meme is one of the mediums on social media which has an image and embedded text in it. These memes convey various views, including fun or offensiveness, that may be a personal attack, hate speech, or racial abuse. Such posts need to be filtered out immediately from social media. This paper presents a framework that detects offensive text in memes and prevents such nuisance from being posted on social media, using the collected KAU-Memes dataset 2582. The latter combines the ''2016 U.S. Election'' dataset with the newly generated memes from a series of offensive and non-offensive tweets datasets. In fact, this model uses the KAU-Memes dataset containing symbolic images and the corresponding text to validate the proposed model. We compare the performance of three proposed deep-learning algorithms to train and detect offensive text in memes. To the best of the authors knowledge and literature review, this is the first approach based on You Only Look Once (YOLO) for offensive text detection in memes. This framework uses YOLOv4, YOLOv5, and SSD MobileNetV2 to compare the model's performance on the newly labeled KAU-Memes dataset. The results show that the proposed model achieved 81.

Research paper thumbnail of An Efficient Character-Level Adversarial Attack Inspired by Textual Variations in Online Social Media Platforms

Computer Systems Science and Engineering

Research paper thumbnail of Artificial Intelligence and Internet of Things (AI-IoT) Technologies in Response to COVID-19 Pandemic: A Systematic Review

IEEE Access, 2022

The origin of the COVID-19 pandemic has given overture to redirection, as well as innovation to m... more The origin of the COVID-19 pandemic has given overture to redirection, as well as innovation to many digital technologies. Even after the progression of vaccination efforts across the globe, total eradication of this pandemic is still a distant future due to the evolution of new variants. To proactively deal with the pandemic, the health care service providers and the caretaker organizations require new technologies, alongside improvements in existing related technologies, Internet of Things (IoT), Artificial Intelligence (AI), and Machine Learning in terms of infrastructure, efficiency, privacy, and security. This paper provides an overview of current theoretical and application prospects of IoT, AI, cloud computing, edge computing, deep learning techniques, blockchain technologies, social networks, robots, machines, privacy, and security techniques. In consideration of these prospects in intersection with the COVID-19 pandemic, we reviewed the technologies within the broad umbrella of AI-IoT technologies in the most concise classification scheme. In this review, we illustrated that AI-IoT technological applications and innovations have most impacted the field of healthcare. The essential AI-IoT technologies found for healthcare were fog computing in IoT, deep learning, and blockchain. Furthermore, we highlighted several aspects of these technologies and their future impact with a novel methodology of using techniques from image processing, machine learning, and differential system modeling. INDEX TERMS Artificial intelligence, compartment model, COVID-19, internet of things, image processing.

Research paper thumbnail of Social Media as an Instant Source of Feedback on Water Quality

IEEE transactions on technology and society, 2023

This paper focuses on an important environmental challenge: water quality by analyzing the potent... more This paper focuses on an important environmental challenge: water quality by analyzing the potential of social media as an immediate source of feedback. The main goal of the work is to automatically analyze and retrieve social media posts relevant to water quality with particular attention to posts describing different aspects of water quality, such as watercolor, smell, taste, and related illnesses. To this aim, we propose a novel framework incorporating different preprocessing, data augmentation, and classification techniques. In total, three different Neural Networks (NNs) architectures, namely (i) Bidirectional Encoder Representations from Transformers (BERT), (ii) Robustly Optimized BERT Pre-training Approach (XLM-RoBERTa), and (iii) custom Long short-term memory (LSTM) model, are employed in a merit-based fusion scheme. For merit-based weight assignment to the models, several optimization and search techniques are compared including a Particle Swarm Optimization (PSO), a Genetic Algorithm (GA), Brute Force (BF), Nelder-Mead, and Powell's optimization methods. We also provide an evaluation of the individual models where the highest F1-score of 0.81 is obtained with the BERT model. Overall, in merit-based fusion, better results are obtained with BF achieving an F1-score score of 0.852. We also provide a comparison against existing methods, where a significant improvement for our proposed solutions is obtained. We believe such a rigorous analysis of this relatively new topic will provide a baseline for future research.

Research paper thumbnail of An Explainable Regression Framework for Predicting Remaining Useful Life of Machines

2022 27th International Conference on Automation and Computing (ICAC), Sep 1, 2022

Prediction of a machine's Remaining Useful Life (RUL) is one of the key tasks in predictive maint... more Prediction of a machine's Remaining Useful Life (RUL) is one of the key tasks in predictive maintenance. The task is treated as a regression problem where Machine Learning (ML) algorithms are used to predict the RUL of machine components. These ML algorithms are generally used as a black box with a total focus on the performance without identifying the potential causes behind the algorithms' decisions and their working mechanism. We believe, the performance (in terms of Mean Squared Error (MSE), etc.,) alone is not enough to build the stakeholders' trust in ML prediction rather more insights on the causes behind the predictions are needed. To this aim, in this paper, we explore the potential of Explainable AI (XAI) techniques by proposing an explainable regression framework for the prediction of machines' RUL. We also evaluate several ML algorithms including classical and Neural Networks (NNs) based solutions for the task. For the explanations, we rely on two model agnostic XAI methods namely Local Interpretable Model-Agnostic Explanations (LIME) and Shapley Additive Explanations (SHAP). We believe, this work will provide a baseline for future research in the domain.

Research paper thumbnail of Document Provenance and Authentication through Authorship Classification

arXiv (Cornell University), Mar 2, 2023

Style analysis, which is relatively a less explored topic, enables several interesting applicatio... more Style analysis, which is relatively a less explored topic, enables several interesting applications. For instance, it allows authors to adjust their writing style to produce a more coherent document in collaboration. Similarly, style analysis can also be used for document provenance and authentication as a primary step. In this paper, we propose an ensemble-based text-processing framework for the classification of single and multi-authored documents, which is one of the key tasks in style analysis. The proposed framework incorporates several state-of-the-art text classification algorithms including classical Machine Learning (ML) algorithms, transformers, and deep learning algorithms both individually and in merit-based late fusion. For the merit-based late fusion, we employed several weight optimization and selection methods to assign merit-based weights to the individual text classification algorithms. We also analyze the impact of the characters on the task that are usually excluded in NLP applications during pre-processing by conducting experiments on both clean and un-clean data. The proposed framework is evaluated on a large-scale benchmark dataset, significantly improving performance over the existing solutions.

Research paper thumbnail of Floods Relevancy and Identification of Location from Twitter Posts using NLP Techniques

arXiv (Cornell University), Dec 31, 2022

This paper presents our solutions for the MediaEval 2022 task on DisasterMM. The task is composed... more This paper presents our solutions for the MediaEval 2022 task on DisasterMM. The task is composed of two subtasks, namely (i) Relevance Classification of Twitter Posts (RCTP), and (ii) Location Extraction from Twitter Texts (LETT). The RCTP subtask aims at differentiating flood-related and non-relevant social posts while LETT is a Named Entity Recognition (NER) task and aims at the extraction of location information from the text. For RCTP, we proposed four different solutions based on BERT, RoBERTa, Distil BERT, and ALBERT obtaining an F1-score of 0.7934, 0.7970, 0.7613, and 0.7924, respectively. For LETT, we used three models namely BERT, RoBERTa, and Distil BERTA obtaining an F1-score of 0.6256, 0.6744, and 0.6723, respectively.

Research paper thumbnail of COVID-19 spread control policies based early dynamics forecasting using deep learning algorithm

Chaos, Solitons & Fractals

Research paper thumbnail of An Explainable Regression Framework for Predicting Remaining Useful Life of Machines

2022 27th International Conference on Automation and Computing (ICAC)

Prediction of a machine's Remaining Useful Life (RUL) is one of the key tasks in predictive maint... more Prediction of a machine's Remaining Useful Life (RUL) is one of the key tasks in predictive maintenance. The task is treated as a regression problem where Machine Learning (ML) algorithms are used to predict the RUL of machine components. These ML algorithms are generally used as a black box with a total focus on the performance without identifying the potential causes behind the algorithms' decisions and their working mechanism. We believe, the performance (in terms of Mean Squared Error (MSE), etc.,) alone is not enough to build the stakeholders' trust in ML prediction rather more insights on the causes behind the predictions are needed. To this aim, in this paper, we explore the potential of Explainable AI (XAI) techniques by proposing an explainable regression framework for the prediction of machines' RUL. We also evaluate several ML algorithms including classical and Neural Networks (NNs) based solutions for the task. For the explanations, we rely on two model agnostic XAI methods namely Local Interpretable Model-Agnostic Explanations (LIME) and Shapley Additive Explanations (SHAP). We believe, this work will provide a baseline for future research in the domain.

Research paper thumbnail of Social Media as an Instant Source of Feedback on Water Quality

IEEE Transactions on Technology and Society

This paper focuses on an important environmental challenge: water quality by analyzing the potent... more This paper focuses on an important environmental challenge: water quality by analyzing the potential of social media as an immediate source of feedback. The main goal of the work is to automatically analyze and retrieve social media posts relevant to water quality with particular attention to posts describing different aspects of water quality, such as watercolor, smell, taste, and related illnesses. To this aim, we propose a novel framework incorporating different preprocessing, data augmentation, and classification techniques. In total, three different Neural Networks (NNs) architectures, namely (i) Bidirectional Encoder Representations from Transformers (BERT), (ii) Robustly Optimized BERT Pre-training Approach (XLM-RoBERTa), and (iii) custom Long short-term memory (LSTM) model, are employed in a merit-based fusion scheme. For merit-based weight assignment to the models, several optimization and search techniques are compared including a Particle Swarm Optimization (PSO), a Genetic Algorithm (GA), Brute Force (BF), Nelder-Mead, and Powell's optimization methods. We also provide an evaluation of the individual models where the highest F1-score of 0.81 is obtained with the BERT model. Overall, in merit-based fusion, better results are obtained with BF achieving an F1-score score of 0.852. We also provide a comparison against existing methods, where a significant improvement for our proposed solutions is obtained. We believe such a rigorous analysis of this relatively new topic will provide a baseline for future research.

Research paper thumbnail of Mobile sensors based platform of Human Physical Activities Recognition for COVID-19 spread minimization

Computers in Biology and Medicine

Research paper thumbnail of Document Provenance and Authentication through Authorship Classification

2023 1st International Conference on Advanced Innovations in Smart Cities (ICAISC)

Research paper thumbnail of A Real-Time Framework for Human Face Detection and Recognition in CCTV Images

Mathematical Problems in Engineering, 2022

This paper aims to develop a machine learning and deep learning-based real-time framework for det... more This paper aims to develop a machine learning and deep learning-based real-time framework for detecting and recognizing human faces in closed-circuit television (CCTV) images. The traditional CCTV system needs a human for 24/7 monitoring, which is costly and insufficient. The automatic recognition system of faces in CCTV images with minimum human intervention and reduced cost can help many organizations, such as law enforcement, identifying the suspects, missing people, and people entering a restricted territory. However, image-based recognition has many issues, such as scaling, rotation, cluttered backgrounds, and variation in light intensity. This paper aims to develop a CCTV image-based human face recognition system using different techniques for feature extraction and face recognition. The proposed system includes image acquisition from CCTV, image preprocessing, face detection, localization, extraction from the acquired images, and recognition. We use two feature extraction alg...

Research paper thumbnail of Online Social Networks (OSN) Evolution Model Based on Homophily and Preferential Attachment

Symmetry, 2018

In this paper, we propose a new scale-free social networks (SNs) evolution model that is based on... more In this paper, we propose a new scale-free social networks (SNs) evolution model that is based on homophily combined with preferential attachments. Our model enables the SN researchers to generate SN synthetic data for the evaluation of multi-facet SN models that are dependent on users’ attributes and similarities. Homophily is one of the key factors for interactive relationship formation in SN. The synthetic graph generated by our model is scale-invariant and has symmetric relationships. The model is dynamic and sustainable to changes in input parameters, such as number of nodes and nodes’ attributes, by conserving its structural properties. Simulation and evaluation of models for large-scale SN applications need large datasets. One way to get SN data is to generate synthetic data by using SN evolution models. Various SN evolution models are proposed to approximate the real-life SN graphs in previous research. These models are based on SN structural properties such as preferential ...

Research paper thumbnail of Merit-based Fusion of NLP Techniques for Instant Feedback on Water Quality from Twitter Text

This paper focuses on an important environmental challenge; namely, water quality by analyzing th... more This paper focuses on an important environmental challenge; namely, water quality by analyzing the potential of social media as an immediate source of feedback. The main goal of the work is to automatically analyze and retrieve social media posts relevant to water quality with particular attention to posts describing different aspects of water quality, such as watercolor, smell, taste, and related illnesses. To this aim, we propose a novel framework incorporating different preprocessing, data augmentation, and classification techniques. In total, three different Neural Networks (NNs) architectures, namely (i) Bidirectional Encoder Representations from Transformers (BERT), (ii) Robustly Optimized BERT Pre-training Approach (XLM-RoBERTa), and (iii) custom Long short-term memory (LSTM) model, are employed in a merit-based fusion scheme. For merit-based weight assignment to the models, several optimization and search techniques are compared including a Particle Swarm Optimization (PSO),...

Research paper thumbnail of Wearable IoTs and Geo-Fencing Based Framework for COVID-19 Remote Patient Health Monitoring and Quarantine Management to Control the Pandemic

Electronics

The epidemic disease of Severe Acute Respiratory Syndrome (SARS) called COVID-19 has become a mor... more The epidemic disease of Severe Acute Respiratory Syndrome (SARS) called COVID-19 has become a more frequently active disease. Managing and monitoring COVID-19 patients is still a challenging issue for advanced technologies. The first and foremost critical issue in COVID-19 is to diagnose it timely and cut off the chain of transmission by isolating the susceptible and patients. COVID-19 spreads through close interaction and contact with an infected person. It has affected the entire world, and every country is facing the challenges of having adequate medical facilities along with the availability of medical staff in rural and urban areas that have a high number of patients due to the pandemic. Due to the invasive method of treatment, SARS-COVID is spreading swiftly. In this paper, we propose an intelligent health monitoring framework using wearable Internet of Things (IoT) and Geo-fencing for COVID-19 susceptible and patient monitoring, and isolation and quarantine management to cont...

Research paper thumbnail of Enhancement of Text Analysis Using Context-Aware Normalization of Social Media Informal Text

Applied Sciences

We proposed an application and data variations-independent, generic social media Textual Variatio... more We proposed an application and data variations-independent, generic social media Textual Variations Handler (TVH) to deal with a wide range of noise in textual data generated in various social media (SM) applications for enhanced text analysis. The aim is to build an effective hybrid normalization technique that ensures the use of useful information of the noisy text in its intended form instead of filtering them out to analyze SM text better. The proposed TVH performs context-aware text normalization based on intended meaning to avoid the wrong word substitution. We integrate the TVH with state-of-the-art (SOTA) deep-learning-based text analysis methods to enhance their performance for noisy SM text data. The proposed scheme shows promising improvement in the text analysis of informal SM text in terms of precision, recall, accuracy, and F1-score in simulation.

Research paper thumbnail of Enhancement of Sentiment Analysis by Utilizing Noisy Social Media Texts

The Journal of Korean Institute of Communications and Information Sciences

Research paper thumbnail of Implicit User Trust Modeling Based on User Attributes and Behavior in Online Social Networks

IEEE Access

In this paper, we present a new user trustworthiness estimation model for social networks (SN), w... more In this paper, we present a new user trustworthiness estimation model for social networks (SN), whereas most of existing researches have been focused on the user-user/item relationship trustworthiness estimation. Users share information of their interest on various social media without their trustworthiness verification. Therefore, SN are susceptible to malicious users for misinformation spreading. In SN, the original information source is generally unknown and the user who is sharing the contents is the only known information about the source. Therefore, the user's trustworthiness is an effective criterion for SN content's trustworthiness estimation. However, the users are unable to identify trustworthy/untrustworthy users, and the existing user-user/item relationship models do not provide user trustworthiness information. Our proposed model provides a systematic way to assess the user trustworthiness based on user attributes and interaction behavior. The proposed model is helpful to avoid the trust sparsity (implicit trust model), trust subjectivity (user's objective/collective trustworthiness estimation model) and cold-start user's trustworthiness (user's attributes-based trust modeling) problems. We employ friends-recommendation (FR) as an exemplary application to evaluate the performance of our proposed model in trust-aware recommendations. Simulation results illustrate that our trust-aware FR model outperformed the existing trust and FR models.

Research paper thumbnail of Online Social Networks (OSN) Evolution Model Based on Homophily and Preferential Attachment

In this paper, we propose a new scale-free social networks (SNs) evolution model that is based on... more In this paper, we propose a new scale-free social networks (SNs) evolution model that is based on homophily combined with preferential attachments. Our model enables the SN researchers to generate SN synthetic data for the evaluation of multi-facet SN models that are dependent on users' attributes and similarities. Homophily is one of the key factors for interactive relationship formation in SN. The synthetic graph generated by our model is scale-invariant and has symmetric relationships. The model is dynamic and sustainable to changes in input parameters, such as number of nodes and nodes' attributes, by conserving its structural properties. Simulation and evaluation of models for large-scale SN applications need large datasets. One way to get SN data is to generate synthetic data by using SN evolution models. Various SN evolution models are proposed to approximate the real-life SN graphs in previous research. These models are based on SN structural properties such as preferential attachment. The data generated by these models is suitable to evaluate SN models that are structure dependent but not suitable to evaluate models which depend on the SN users' attributes and similarities. In our proposed model, users' attributes and similarities are utilized to synthesize SN graphs. We evaluated the resultant synthetic graph by analyzing its structural properties. In addition, we validated our model by comparing its measures with the publicly available real-life SN datasets and previous SN evolution models. Simulation results show our resultant graph to be a close representation of real-life SN graphs with users' attributes.