Author: Joshi, G., Srivastava, A., Yagnik, B., Hasan, M., Saiyed, Z., Gabralla, L.A., Abraham,A., Walambe, R., Kotecha, K.
Explainable Misinformation Detection Across Multiple Social Media Platforms
Publisher: IEEE Access, 2023
Abstract
|
Links
Web Information Processing (W.I.P.) has enormously impacted modern society since a huge percentage of the population relies on the internet to acquire information. Social Media platforms provide a channel for disseminating information and a breeding ground for spreading misinformation, creating confusion and fear among the population. One of the techniques for the detection of misinformation is machine learning-based models. However, due to the availability of multiple social media platforms, developing and training AI-based models has become a tedious job. Despite multiple efforts to develop machine learning-based methods for identifying misinformation, more work must be done on developing an explainable generalized detector capable of robust detection and generating explanations beyond black-box outcomes. Knowing the reasoning behind the outcomes is essential to make the detector trustworthy. Hence employing explainable A.I. techniques is of utmost importance. In this work, the integration of two machine learning approaches, namely domain adaptation and explainable A.I., is proposed to address these two issues of generalized detection and explainability. Firstly the Domain Adversarial Neural Network (DANN) develops a generalized misinformation detector across multiple social media platforms. DANN generates the classification results for test domains with relevant but unseen data. The DANN-based, traditional black-box model cannot justify and explain its outcome, i.e., the labels for the target domain. Hence a Local Interpretable Model-Agnostic Explanations (LIME) explainable A.I. model is applied to explain the outcome of the DANN model. To demonstrate these two approaches and their integration for effective explainable generalized detection, COVID-19 misinformation is considered a case study. We experimented with two datasets and compared results with and without DANN implementation.
https://doi.org/10.1109/ACCESS.2023.3251892
Web Information Processing (W.I.P.) has enormously impacted modern society since a huge percentage of the population relies on the internet to acquire information. Social Media platforms provide a channel for disseminating information and a breeding ground for spreading misinformation, creating confusion and fear among the population. One of the techniques for the detection of misinformation is machine learning-based models. However, due to the availability of multiple social media platforms, developing and training AI-based models has become a tedious job. Despite multiple efforts to develop machine learning-based methods for identifying misinformation, more work must be done on developing an explainable generalized detector capable of robust detection and generating explanations beyond black-box outcomes. Knowing the reasoning behind the outcomes is essential to make the detector trustworthy. Hence employing explainable A.I. techniques is of utmost importance. In this work, the integration of two machine learning approaches, namely domain adaptation and explainable A.I., is proposed to address these two issues of generalized detection and explainability. Firstly the Domain Adversarial Neural Network (DANN) develops a generalized misinformation detector across multiple social media platforms. DANN generates the classification results for test domains with relevant but unseen data. The DANN-based, traditional black-box model cannot justify and explain its outcome, i.e., the labels for the target domain. Hence a Local Interpretable Model-Agnostic Explanations (LIME) explainable A.I. model is applied to explain the outcome of the DANN model. To demonstrate these two approaches and their integration for effective explainable generalized detection, COVID-19 misinformation is considered a case study. We experimented with two datasets and compared results with and without DANN implementation.
|
Author: Devi Priya, R., Karthikeyan, S., Indra, J., Kirubashankar, S., Abraham, A., Gabralla, L., Sivaraj, R., Nandhagopal, S.M.
Self-Adaptive Hybridized Lion Optimization Algorithm with Transfer Learning for Ancient Tamil Character Recognition in Stone Inscriptions
Publisher: IEEE Access, 2023
Abstract
|
Links
Tamil character recognition serves as a vital research problem in pattern recognition since there are many serious technical difficulties due to similarity and complexity of characters when compared with other languages. Stone inscriptions reveal details of luxury, lifestyle, economic status, cultural practices, administrative tasks followed by various rulers and dynasties of Tamil Nadu. Since ancient stone inscriptions are in existence for a longer period, there are possibilities of natural erosion and no early protection measures are available. The ancient stone inscriptions are always not complete which creates many difficulties in reading and understanding them and their aesthetic appreciation. There is a difficulty in recognizing Tamil characters mainly because of the characters with a number of holes, loops and curves. The number of letters in Tamil language is higher when compared to other languages. Even though there are various approaches provided by the researchers, challenges and issues still prevail in recognition of tamil text in stone inscriptions. In the existing systems, detection algorithms fail to produce desired accuracy and hence stone inscription recognition using transfer learning, a promising method is proposed here. Lion Optimization Algorithm (LOA) is applied to optimize brightness and contrast and then stone inscription images are pre-processed for noise removal and then each character is separated by identifying contours. Characters are recognized using Transfer Learning (TL), a Deep Convolution Neural Network-based multi classification approach. The proposed hybrid model Self-Adaptive Lion Optimization Algorithm with Transfer Learning (SLOA-TL) when implemented in images of stone inscriptions achieves better accuracy and speed than other existing methods. It serves as an efficient design for recognition of tamil characters in stone inscriptions and preserving tamil traditional knowledge.
https://doi.org/10.1109/ACCESS.2023.3268545
Tamil character recognition serves as a vital research problem in pattern recognition since there are many serious technical difficulties due to similarity and complexity of characters when compared with other languages. Stone inscriptions reveal details of luxury, lifestyle, economic status, cultural practices, administrative tasks followed by various rulers and dynasties of Tamil Nadu. Since ancient stone inscriptions are in existence for a longer period, there are possibilities of natural erosion and no early protection measures are available. The ancient stone inscriptions are always not complete which creates many difficulties in reading and understanding them and their aesthetic appreciation. There is a difficulty in recognizing Tamil characters mainly because of the characters with a number of holes, loops and curves. The number of letters in Tamil language is higher when compared to other languages. Even though there are various approaches provided by the researchers, challenges and issues still prevail in recognition of tamil text in stone inscriptions. In the existing systems, detection algorithms fail to produce desired accuracy and hence stone inscription recognition using transfer learning, a promising method is proposed here. Lion Optimization Algorithm (LOA) is applied to optimize brightness and contrast and then stone inscription images are pre-processed for noise removal and then each character is separated by identifying contours. Characters are recognized using Transfer Learning (TL), a Deep Convolution Neural Network-based multi classification approach. The proposed hybrid model Self-Adaptive Lion Optimization Algorithm with Transfer Learning (SLOA-TL) when implemented in images of stone inscriptions achieves better accuracy and speed than other existing methods. It serves as an efficient design for recognition of tamil characters in stone inscriptions and preserving tamil traditional knowledge.
|
Author: Passah, A., Sur, S.N., Abraham, A., Kandar, D.
Synthetic Aperture Radar image analysis based on deep learning: A review of a decade of research
Publisher: Engineering Applications of Artificial Intelligence, 2023
Abstract
|
Links
Artificial intelligence research in the area of computer vision teaches machines to comprehend and interpret visual data. Machines can properly recognize and classify items using digital images captured by cameras and videos, deep learning models, and then respond to what they observe. Similarly, artificial intelligence has also been able to learn complex images captured by Synthetic Aperture Radar (SAR) that are widely used for various purposes but still leave room for improvements. Researchers have proposed numerous approaches in this field, from SAR target detection to SAR target recognition. This paper presents a survey on the different techniques and architectures proposed in the literature for various SAR image applications. The paper covers a survey on target detection models and target recognition models and their respective workflow to analyze the techniques involved and the performances of these models. This paper makes novel discussions, comparisons, and observations. It highlights the advantages and disadvantages of different approaches to give researchers the idea of how each technique can influence the performance for adoption in the future. The potential future directions along with hybrid models on each processing method are also highlighted based on the study.
https://doi.org/10.1016/j.engappai.2023.106305
Artificial intelligence research in the area of computer vision teaches machines to comprehend and interpret visual data. Machines can properly recognize and classify items using digital images captured by cameras and videos, deep learning models, and then respond to what they observe. Similarly, artificial intelligence has also been able to learn complex images captured by Synthetic Aperture Radar (SAR) that are widely used for various purposes but still leave room for improvements. Researchers have proposed numerous approaches in this field, from SAR target detection to SAR target recognition. This paper presents a survey on the different techniques and architectures proposed in the literature for various SAR image applications. The paper covers a survey on target detection models and target recognition models and their respective workflow to analyze the techniques involved and the performances of these models. This paper makes novel discussions, comparisons, and observations. It highlights the advantages and disadvantages of different approaches to give researchers the idea of how each technique can influence the performance for adoption in the future. The potential future directions along with hybrid models on each processing method are also highlighted based on the study.
|
Author: Rajpal, S., Rajpal, A., Agarwal, M., Kumar, V., Abraham, A., Khanna, D., Kumar, N.
XAI-CNVMarker: Explainable AI-based copy number variant biomarker discovery for breast cancer subtypes
Publisher: Biomedical Signal Processing and Control, 2023
Abstract
|
Links
"Breast cancer is a leading cause of cancer-related deaths among women. The multi-omic data has revolutionized the methodology to unravel molecular heterogeneity in breast cancer. As genetic variations captured from Copy Number Variation (CNV) data are considered the most stable amongst the multi-omic data, it leads to robust biomarkers. Thus, this paper targets the discovery of a set of CNV biomarkers for dissecting this heterogeneity. The existing algorithms yield biomarkers, too huge to be interpreted clinically. So, in this paper, we have proposed XAI-CNVMarker—an explainable AI-based post-hoc biomarker discovery framework to discover a small set of interpretable biomarkers. We exploit the power of deep learning to build DLmodel—a deep learning model for breast cancer classification. Subsequently, the trained model is analyzed using different explainable AI methods to arrive at a set of 44 CNV biomarkers. Using 5-fold cross-validation, we obtained a classification accuracy of 0.712 (
0.048) at a 95% confidence interval. Gene set analysis revealed 37 subtype-specific enriched Reactome and Kegg pathways, 21 druggable genes, and 13 biomarkers linked with the prognostic outcome. Finally, we validated the efficacy of the identified biomarkers on METABRIC. Thus, the proposed framework demonstrates the role of explainable AI in discovering clinically reliable biomarkers."
https://doi.org/10.1016/j.bspc.2023.104979
"Breast cancer is a leading cause of cancer-related deaths among women. The multi-omic data has revolutionized the methodology to unravel molecular heterogeneity in breast cancer. As genetic variations captured from Copy Number Variation (CNV) data are considered the most stable amongst the multi-omic data, it leads to robust biomarkers. Thus, this paper targets the discovery of a set of CNV biomarkers for dissecting this heterogeneity. The existing algorithms yield biomarkers, too huge to be interpreted clinically. So, in this paper, we have proposed XAI-CNVMarker—an explainable AI-based post-hoc biomarker discovery framework to discover a small set of interpretable biomarkers. We exploit the power of deep learning to build DLmodel—a deep learning model for breast cancer classification. Subsequently, the trained model is analyzed using different explainable AI methods to arrive at a set of 44 CNV biomarkers. Using 5-fold cross-validation, we obtained a classification accuracy of 0.712 (
0.048) at a 95% confidence interval. Gene set analysis revealed 37 subtype-specific enriched Reactome and Kegg pathways, 21 druggable genes, and 13 biomarkers linked with the prognostic outcome. Finally, we validated the efficacy of the identified biomarkers on METABRIC. Thus, the proposed framework demonstrates the role of explainable AI in discovering clinically reliable biomarkers."
|
Author: Bhosale, H., Pandya, M.A., Chatterjee, I., Mukunth, A., Sureshkumar, B., Rajagopalan, R.S., Parlikkad, N.R., Valadi, J.
Development of Gradient Boosting Machines for Estimation of Total and Dynamic Liquid Holdup in Trickle Bed Reactor
Publisher: Industrial & Engineering Chemistry Research, 2023
Abstract
|
Links
Prediction of liquid holdup is of significance in designing and in evaluating the performance of trickle bed contactors. The present work focuses on the development of Gradient Boosting Machines (GBM) for the prediction of total and dynamic liquid holdup in trickle bed reactors. A comprehensive data set of 394 data points of total liquid holdup and 416 data points of dynamic liquid holdup curated from open literature is used in this study. We built GBM models with the input data sets containing 11 governing variables. GBM provided excellent predictions for both data sets. We have also compared the GBM predictions with that of the Random Forest (RF) and Artificial Neural Networks (ANN) predictions. As GBM provided the best performance, we further employed SHAP (SHapley Additive exPlanations) with GBM black box models to get local and global interpretability. Also, we have used SHAP to identify informative subsets of governing variables. The work shall pave the way for use of GBM in prediction of hydrodynamic parameters in multiphase systems.
https://doi.org/10.1021/acs.iecr.3c00231
Prediction of liquid holdup is of significance in designing and in evaluating the performance of trickle bed contactors. The present work focuses on the development of Gradient Boosting Machines (GBM) for the prediction of total and dynamic liquid holdup in trickle bed reactors. A comprehensive data set of 394 data points of total liquid holdup and 416 data points of dynamic liquid holdup curated from open literature is used in this study. We built GBM models with the input data sets containing 11 governing variables. GBM provided excellent predictions for both data sets. We have also compared the GBM predictions with that of the Random Forest (RF) and Artificial Neural Networks (ANN) predictions. As GBM provided the best performance, we further employed SHAP (SHapley Additive exPlanations) with GBM black box models to get local and global interpretability. Also, we have used SHAP to identify informative subsets of governing variables. The work shall pave the way for use of GBM in prediction of hydrodynamic parameters in multiphase systems.
|
Author: Jain, P., Sharma, S.
“Children of the Soil” to “Dark Wind”: Nature, Environment and Climate in Indian Films
Publisher: Visual Anthropology, 2023
Abstract
|
Links
India is widely known as the biggest producer of films, now globally known with the portmanteau “Bollywood.” India also grabs the media attention for another reason—climate change. In 2015, The New York Times published an op-ed with a cartoon showing India as the proverbial “elephant” blocking the progress at the Paris Climate Change Conference. With the staggering number of films India produces and the steady increase in climate change-related disasters that India faces, the critics embraced the film Kadvi Hawa (literally, Dark Wind or Bitter Wind, 2017) as the “pioneering” film raising the critical issue of climate change. However, the issues raised in the movie were amply dealt with in several other Indian films in the last several decades. This article is a survey of Indian films that have shown or dealt with nature, environment, or climate starting from the 1940s till the present time.
https://doi.org/10.1080/08949468.2022.2129258
India is widely known as the biggest producer of films, now globally known with the portmanteau “Bollywood.” India also grabs the media attention for another reason—climate change. In 2015, The New York Times published an op-ed with a cartoon showing India as the proverbial “elephant” blocking the progress at the Paris Climate Change Conference. With the staggering number of films India produces and the steady increase in climate change-related disasters that India faces, the critics embraced the film Kadvi Hawa (literally, Dark Wind or Bitter Wind, 2017) as the “pioneering” film raising the critical issue of climate change. However, the issues raised in the movie were amply dealt with in several other Indian films in the last several decades. This article is a survey of Indian films that have shown or dealt with nature, environment, or climate starting from the 1940s till the present time.
|
Author: Chaudhry, S., Ghura, A.S.
Primes and Zooms: A Need for Growth Strategy
Publisher: Ivey Publishing, 2023
|
Author: Bodhanwala, S., Bodhanwala, R.
Tata Motors: The Dividend Dilemma
Publisher: Ivey Publishing, 2023
|
Author: Karim, U., Kapur, S.
Regional Security in South Asia and the Gulf
Publisher: Routledge, 2023
Links
https://www.routledge.com/Regional-Security-in-South-Asia-and-the-Gulf/Karim-Kapur/p/book/9781032254142#
|
Author: Kapur, S.
India, the Persian Gulf, and the Emergence of a Supercomplex
Publisher: Routledge, 2023
|
Author: Walia, R.
“A Great Republic of Hurt Sentiments”: Counter Histories, Nationalism, and the Controversy of the Historical. In: Gopinath, S., Deshmukh, R. (eds.)Historicizing Myths in Contemporary India: Cinematic Representations and Nationalist Agendas in Hindi Cinema
Publisher: Routledge, 2023
Links
https://www.taylorfrancis.com/chapters/edit/10.4324/9781003363149-11/great-republic-hurt-sentiments-ramna-walia?context=ubx&refId=b92c36e6-814c-4dd9-b731-40af341ef02b
|
Author: Latif, R., Sohoni, P.
Sultanate Ahmadabad And Its Monuments: The City Of Muzaffarids (Ahmad Shahis)
Publisher: Primus Books, 2023
|
Author: Kushik, R.
The Indian National Innovation System: historical perspective and key characteristics
Publisher: Bite-Sized Books Ltd., 2023
|
Author: Sottong, H.
Hypermedievalizing and de-medievalizing Dante: Leopoldo Lugones’s and Jorge Luis Borges’s Rewritings of Inferno V
Publisher: ARC Humanities Press, 2023
|
Author: Valadi, J.
Challenges in Eventing Horizontal Gene Transfer
Publisher: Springer, 2023
Links
https://doi.org/10.1007/978-981-19-9342-8_16
|
Author: Patki, S.
A Cognitive and Socio-cultural Perspective on the Tendency to use Gmail’s Smart Reply-like AI-based Texting Features
2023
|
Author: Patki, S.
Bridging the Digital Divide in Online Learning in Maharashtra, India: Learnings from the Pandemic
2023
|
Author: Jain D K
Inclusive Finanace
2023
|
Author: Jain, D.K.
How much big adjacent large economies can influence foreign exchange markets of small economies? : Evidence from the tri polar study of Fiji, Australia and New Zealand
2023
Links
https://drive.google.com/file/d/14D-Tgn0OWNwsmn3uoPTigA3d_sIKqVdm/view?usp=sharing
|
Author: Ajith Abraham
Synergy of climate change with country success and city quality of life
Publisher: Scientific Reports, 2023
Abstract
|
Links
Most people around the world have felt the effects of climate change on their quality of life. This study sought to achieve the maximum efficiency for climate change actions with the minimum negative impact on the well-being of countries and cities. The Climate Change and Country Success (C3S) and Climate Change and Cities’ Quality of Life (C3QL) models and maps of the world created as part of this research showed that as economic, social, political, cultural, and environmental metrics of countries and cities improve, so do their climate change indicators. For the 14 climate change indicators, the C3S and C3QL models indicated 68.8% average dispersion dimensions in the case of countries and 52.8% in the case of cities. Our research showed that increases in the success of 169 countries saw improvements in 9 climate change indicators out of the 12 considered. Improvements in country success indicators were accompanied by a 71% improvement in climate change metrics.
https://doi.org/10.1038/s41598-023-35133-4
Most people around the world have felt the effects of climate change on their quality of life. This study sought to achieve the maximum efficiency for climate change actions with the minimum negative impact on the well-being of countries and cities. The Climate Change and Country Success (C3S) and Climate Change and Cities’ Quality of Life (C3QL) models and maps of the world created as part of this research showed that as economic, social, political, cultural, and environmental metrics of countries and cities improve, so do their climate change indicators. For the 14 climate change indicators, the C3S and C3QL models indicated 68.8% average dispersion dimensions in the case of countries and 52.8% in the case of cities. Our research showed that increases in the success of 169 countries saw improvements in 9 climate change indicators out of the 12 considered. Improvements in country success indicators were accompanied by a 71% improvement in climate change metrics.
|
