Lakshmi Dandabani

Dr. Lakshmi Dandabani

orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
21 December 2023
Verified
Book Chapter
Closed access
IKIsha Kondurkar
Isha Kondurkar
ARAkanksha Raj
Akanksha Raj
LDLakshmi Dandabani
Lakshmi Dandabani
Generative AI (GAI) and natural language processing (NLP) have emerged as the most exciting and rapidly growing fields in artificial intelligence (AI). This book chapter provides a comprehensive exploration of the advanced applications of GAI and NLP models, with a specific focus on the renowned ChatGPT model. The chapter commences by offering a concise historical overview of the development of GAI and NLP, highlighting crucial milestones and advancements in the field over the period. In order to understand the workings of the current technology sensation, we will take a brief look at the basic building blocks of GPT models, such as transformers. Subsequently, the chapter delves into the introduction of ChatGPT, presenting an extensive overview of the model, elucidating its underlying architecture, and emphasizing its unique capabilities. Furthermore, it will illustrate the training process of the GPT model followed by a fine-tuning process to deal with the current model's shortcomings.

2 October 2023
Verified
Book Chapter
Closed access
SMSakalya Mitra
Sakalya Mitra
LDLakshmi Dandabani
Lakshmi Dandabani
VGVishnuvarthanan Govindaraj
Vishnuvarthanan Govindaraj
Artificial intelligence and related technological advancements have been a matter of discussion in recent times. There has been regular growth in AI-based methods that have proven useful for various industry verticals. Education is one such critical field where AI can play a monumental role in improving quality and helping individuals strive for better education. Meeting the educational requirements of all children, adolescents, and adults has received more attention in recent years. Recent advancements in technology, such as data analysis and ML, can potentially revolutionize how we approach special education. By using these technologies to personalize learning experiences, track progress, and provide individualized support, educators can improve outcomes for students with special needs. With the right approach, data analysis and ML can be powerful tools for improving special education and supporting students with special needs. The main idea of the study is to outline in detail the various applications of AI-assisted special education and discover the depths of the methods.

19 September 2023 in IEEE Transactions on Industry Applications
Verified
Journal Article
Closed access
LDLakshmi Dandabani
Lakshmi Dandabani
RTRavi Shekhar Tiwari
Ravi Shekhar Tiwari
NNNeelu Nagpal
Neelu Nagpal
NKNeelam Kassarwani
Neelam Kassarwani
Vishnuvarthanan GovindarajVishnuvarthanan Govindaraj
Vishnuvarthanan Govindaraj
ASAbhishek Srivastava
Abhishek Srivastava
The increasing use of Renewable Energy Resources (RES) in energy generation has led to the transformation of the conventional electrical grid into a more adaptable and interactive system, and this has made electrical load prediction a crucial aspect of smart grid operation. Short-Term Load Forecasting (STLF) is the ultimate requirement for the essentialities, such as planning, scheduling, management, and trading of electricity. In the proposed work, a forecasting engine model is developed to figure out the load of the upcoming twelve months (2020) in the Delhi metropolis, and this is accomplished by integrating real and dynamic meteorological data, calendar data, and load patterns for the successive two years (2017-2018). It is performed using different ensemble models, such as XGBoost, Gradient Boosting, AdaBoost, Random Forest (RF) algorithms, and deep learning models such as Long Short-Term Memory (LSTM), Recurrent Neural Network (RNN), Gated Recurrent Unit (GRU) and the Prophet algorithm. The simulation results of the proposed models are obtained on the Python platform using Delhi weather, load, and calendar data. Further, the STLF is analyzed using 14 different models on the basis of 78 scenarios, and 8 data sets are analyzed in conjunction. The train, validation, and test accuracy have been considered as validation metrics, both on hourly and daily load forecasting, to validate the overfitting in terms of the train, validation, and test loss. A comparative study is made to show that the predictions of LSTM and GRU outperform with 100% accuracy.


9 November 2023 in Diagnostics
Verified
Journal Article
Open access
PDF file
RTRavi Shekhar Tiwari
Ravi Shekhar Tiwari
LDLakshmi Dandabani
Lakshmi Dandabani
TDTapan Kumar Das
Tapan Kumar Das
SBSurbhi Bhatia
Surbhi Bhatia
SBShakila Basheer
Shakila Basheer
MAMohammed S. Alqahtani
Mohammed S. Alqahtani
The mortality rates of patients contracting the Omicron and Delta variants of COVID-19 are very high, and COVID-19 is the worst variant of COVID. Hence, our objective is to detect COVID-19 Omicron and Delta variants from lung CT-scan images. We designed a unique ensemble model that combines the CNN architecture of a deep neural network—Capsule Network (CapsNet)—and pre-trained architectures, i.e., VGG-16, DenseNet-121, and Inception-v3, to produce a reliable and robust model for diagnosing Omicron and Delta variant data. Despite the solo model’s remarkable accuracy, it can often be difficult to accept its results. The ensemble model, on the other hand, operates according to the scientific tenet of combining the majority votes of various models. The adoption of the transfer learning model in our work is to benefit from previously learned parameters and lower data-hunger architecture. Likewise, CapsNet performs consistently regardless of positional changes, size changes, and changes in the orientation of the input image. The proposed ensemble model produced an accuracy of 99.93%, an AUC of 0.999 and a precision of 99.9%. Finally, the framework is deployed in a local cloud web application so that the diagnosis of these particular variants can be accomplished remotely.

13 February 2025
Verified
Book Chapter
Closed access
PDF file
SCSrija Chattopadhyay
Srija Chattopadhyay
SBSubhadeep Barman
Subhadeep Barman
LDLakshmi Dandabani
Lakshmi Dandabani
Explainable artificial intelligence (XAI) is a way to improve transparency and understanding of artificial intelligence (AI) models. The use of AI in medicine is expanding rapidly. It has the potential to improve patient problems at a significantly lower cost. However, due to the complexity of AI models, it can be difficult to understand how they arrive at their conclusions, which can be a barrier to adoption of this overwhelming technology. XAI offers a solution to this problem by identifying potential flaws in AI models prior to certification, thereby improving the safety and effectiveness of AI-based medical systems. XAI’s main goal is to help people understand the reasons behind AI decisions and outcomes, promoting trust, credibility, and accountability. XAI is crucial in healthcare because it is critical that AI models used for clinical decision-making are transparent and provide human-explainable results. By detecting potential errors in AI models and providing suggestions for improvement, XAI can improve the adaptability and reliability of AI models. This ultimately leads to improved patient trust and an efficient healthcare system. To understand the basics of how XAI works, it can be categorized in different ways based on the desired results. These methods include rule-based, model-based, and post-explainability techniques. A rule-based method is a decision tree or system that makes decisions based on predefined rules. These rules can be written by subject matter experts or learned through machine learning algorithms. Model-based approaches use machine learning models such as decision trees and linear regression models designed for interpretation. Analyze model inputs and outputs using posterior explainability techniques to provide insight into how the model arrived at its decisions. These approaches justify the decisions made by the model by examining the results. XAI has a wide range of medical use cases, including medical image classification and segmentation, patient monitoring, and clinical decision support systems. Empowering physicians to make decisions by providing explanations for the results of AI-based models. XAI has the potential to improve medical outcomes by helping medical professionals detect, monitor, and treat complex diseases more quickly. The system improves clinical decision-making by justifying its recommendations, helping physicians make more informed and valuable decisions. For example, in the field of neurology, XAI is used to study EEG signals and identify changes in brain activity associated with epilepsy and other neurological disorders. In cardiology, XAI is used to analyze ECG signals and identify abnormalities that may indicate a potential risk of cardiovascular disease. In the field of oncology, XAI analyzes medical images to identify cancerous tumors and help predict disease progression. XAI can revolutionize the healthcare industry by improving disease detection, diagnosis, and treatment, ultimately improving patient outcomes. Nonetheless, adaptation of XAI may have some barriers that need to be overcome, such as the need for interpretable deep learning models and the ethical and legal implications associated with AI implementation. Addressing these challenges will enable XAI to be used responsibly and effectively for the benefit of patients and healthcare providers. <!----> <!----> <!----> <!---->