Savita Gandhi
Research Subjects
Savita Gandhi has a total of 27 co-authors. Here are the top co-authors by number of shared publications:
- Prerna Agrawal
GLS University, India
8 shared publications - Nirbhay Kumar Chaubey
Ganpat University
4 shared publications - Suchit Purohit
Department of Computer Science, Gujarat University, Ahmedabad, India
3 shared publications Akshai Aggarwal
Gujarat Technol. Univ., Ahmedabad, India
2 shared publications- Jaykumar S. Patel
Gujarat University
2 shared publications Jyotika Doshi
GLS Inst.of Computer Technology Opp. Law Garden, Ellisbridge Ahmedabad-380006, India
2 shared publications
Latest Publications
- 16 October 2026
- Published by IGI Global Scientific Publishing
- p. 145-176
Artificial Intelligence, Machine Learning, and Collaborative Robots in Healthcare
Integration of Artificial Intelligence (AI), Machine Learning (ML), and Collaborative Robots (cobots) is leading the development of new patient-centered and intelligent systems and care models for the future of healthcare. This chapter will discuss how these technologies will improve clinical decision-making, automate manual labour and routine tasks, and provide improved efficiencies within the healthcare system, leading to improved patient outcomes. Also included in this chapter will be a discussion of the technologies already currently being used to support cobots to deliver patient-centered and team based care, including but not limited to AI data analytic tools, computer vision application tools, natural language processing (NLP) tools, and connected healthcare systems applications. Examples of application in each of the following areas will also be discussed: surgical assistance, rehabilitation, patient monitoring, hospital logistics, mental health, and telehealth.
- 16 October 2026
- Published by IGI Global Scientific Publishing
- p. 145-176
Artificial Intelligence, Machine Learning, and Collaborative Robots in Healthcare
Integration of Artificial Intelligence (AI), Machine Learning (ML), and Collaborative Robots (cobots) is leading the development of new patient-centered and intelligent systems and care models for the future of healthcare. This chapter will discuss how these technologies will improve clinical decision-making, automate manual labour and routine tasks, and provide improved efficiencies within the healthcare system, leading to improved patient outcomes. Also included in this chapter will be a discussion of the technologies already currently being used to support cobots to deliver patient-centered and team based care, including but not limited to AI data analytic tools, computer vision application tools, natural language processing (NLP) tools, and connected healthcare systems applications. Examples of application in each of the following areas will also be discussed: surgical assistance, rehabilitation, patient monitoring, hospital logistics, mental health, and telehealth.
- 25 September 2026
- Published by IGI Global Scientific Publishing
- p. 385-420
Digital Twin for Real-Time Traffic Congestion Prediction and Optimization in Smart Mobility Environments
The rapid growth of urban populations and vehicles has significantly increased traffic congestion, creating challenges for urban mobility and smart city development. Traditional traffic management systems based on static control methods are often ineffective in handling dynamic and real time traffic conditions. This chapter proposes an AI enabled digital twin framework for real time traffic congestion prediction and optimization in smart mobility environments. The framework integrates IoT technologies, real time traffic data, and hybrid deep learning models such as CNN and LSTM to analyze spatial and temporal traffic patterns. A digital twin environment is developed to simulate real world traffic conditions and evaluate optimization strategies including adaptive traffic signal control and route optimization. A conceptual case study of Ahmedabad and Gandhinagar smart cities is presented. Although not empirically validated, the framework shows strong potential for improving traffic prediction, intelligent decision making, and sustainable urban transportation systems.
- 25 September 2026
- Published by IGI Global Scientific Publishing
- p. 385-420
Digital Twin for Real-Time Traffic Congestion Prediction and Optimization in Smart Mobility Environments
The rapid growth of urban populations and vehicles has significantly increased traffic congestion, creating challenges for urban mobility and smart city development. Traditional traffic management systems based on static control methods are often ineffective in handling dynamic and real time traffic conditions. This chapter proposes an AI enabled digital twin framework for real time traffic congestion prediction and optimization in smart mobility environments. The framework integrates IoT technologies, real time traffic data, and hybrid deep learning models such as CNN and LSTM to analyze spatial and temporal traffic patterns. A digital twin environment is developed to simulate real world traffic conditions and evaluate optimization strategies including adaptive traffic signal control and route optimization. A conceptual case study of Ahmedabad and Gandhinagar smart cities is presented. Although not empirically validated, the framework shows strong potential for improving traffic prediction, intelligent decision making, and sustainable urban transportation systems.
- Open Access
- 8 July 2026
- Published by Elsevier in Procedia Computer Science
- Vol. 283, 3407-3423
PneumoSense++: An Enhanced Pneumonia Detection with Deep Learning and Comparative Optimizer Analysis
- 8 July 2026
- Published by Elsevier in Procedia Computer Science
- Vol. 283, 3407-3423
Open AccessPneumoSense++: An Enhanced Pneumonia Detection with Deep Learning and Comparative Optimizer Analysis
- 3 June 2026
- Published by Springer Nature
- p. 76-87
ShlokaSage: AI Driven Emotion-Based Bhagavad Gita Shloka Recommendation
- 3 June 2026
- Published by Springer Nature
- p. 76-87
ShlokaSage: AI Driven Emotion-Based Bhagavad Gita Shloka Recommendation
- 17 April 2026
- Published by IGI Global Scientific Publishing
- p. 37-74
Artificial Intelligence
Artificial intelligence is changing healthcare by bettering medical diagnoses and augmentations and efficiencies in treatment plans. This chapter addresses AI use in healthcare in India through the role and demands for AI technologies and activities. Due to the increased incidence of infectious and non-communicable diseases there is a necessity for scalable, technology-enabled diagnostics. The current shortage of physicians combined with increasing digital infrastructure create benefits of value for AI in healthcare delivery. The medical specialties of radiology and pathology and ophthalmology and primary care are changing swiftly with advancements in deep learning and computer vision and natural language processing and machine learning. AI is increasing access to care, especially in constrained and rural areas, through application examples such as PneumoSense and DiabChatBot. HealthCare has complex issues in general like bias outcomes and comparative variances of data conflicts of regulatory disconnect and validity of outcomes with the advisory could be automated.
- 17 April 2026
- Published by IGI Global Scientific Publishing
- p. 37-74
Artificial Intelligence
Artificial intelligence is changing healthcare by bettering medical diagnoses and augmentations and efficiencies in treatment plans. This chapter addresses AI use in healthcare in India through the role and demands for AI technologies and activities. Due to the increased incidence of infectious and non-communicable diseases there is a necessity for scalable, technology-enabled diagnostics. The current shortage of physicians combined with increasing digital infrastructure create benefits of value for AI in healthcare delivery. The medical specialties of radiology and pathology and ophthalmology and primary care are changing swiftly with advancements in deep learning and computer vision and natural language processing and machine learning. AI is increasing access to care, especially in constrained and rural areas, through application examples such as PneumoSense and DiabChatBot. HealthCare has complex issues in general like bias outcomes and comparative variances of data conflicts of regulatory disconnect and validity of outcomes with the advisory could be automated.
- 17 April 2026
- Published by IGI Global Scientific Publishing
- p. 55-90
Intelligent Imaging
Deep learning (DL) is remodeling medical imaging by providing potent tools for detection, diagnosis, and treatment planning in many medical conditions. In various modalities like MRI, CT, ultrasound, X-rays, DL models have yielded excellent results on several different tasks such as image classification, segmentation, disease detection because of the use of different architectures like convolutional neural networks (CNNs). Hence, this chapter covers how DL advancements will allow doctors to quickly diagnose their patients, ultimately provide better personal care for their patients, and improve clinic outcomes. Overall, this chapter aims to help readers appreciate how deep learning is critical for pattern recognition in medical data. This chapter discusses the important components of DL, what the most common tasks are, what medical conditions are addressed using DL, what the barriers to DL are, and the future of DL may look like. These considerations may help clinicians make accurate diagnoses for their patients and start implementing effective treatment plans as early as possible.
- 17 April 2026
- Published by IGI Global Scientific Publishing
- p. 55-90
Intelligent Imaging
Deep learning (DL) is remodeling medical imaging by providing potent tools for detection, diagnosis, and treatment planning in many medical conditions. In various modalities like MRI, CT, ultrasound, X-rays, DL models have yielded excellent results on several different tasks such as image classification, segmentation, disease detection because of the use of different architectures like convolutional neural networks (CNNs). Hence, this chapter covers how DL advancements will allow doctors to quickly diagnose their patients, ultimately provide better personal care for their patients, and improve clinic outcomes. Overall, this chapter aims to help readers appreciate how deep learning is critical for pattern recognition in medical data. This chapter discusses the important components of DL, what the most common tasks are, what medical conditions are addressed using DL, what the barriers to DL are, and the future of DL may look like. These considerations may help clinicians make accurate diagnoses for their patients and start implementing effective treatment plans as early as possible.
- 6 February 2026
- Published by IGI Global Scientific Publishing
- p. 303-332
Intelligent Learning
The integration of Artificial Intelligence (AI) into digital education marks a major shift in pedagogy, learner engagement, and institutional functions. AI-driven systems such as intelligent tutoring, adaptive learning, and learning analytics are transforming how knowledge is delivered and assessed. This chapter explores AI's role in creating adaptive learning environments, supporting both cognitive and emotional assessment, and improving institutional efficiency through automation. Global platforms including Squirrel AI, Carnegie Learning, Duolingo, and DIKSHA are examined. The chapter also addresses ethical, technical, and infrastructural challenges, including privacy, algorithmic bias, and the digital divide. It synthesizes current literature and promotes comparative perspectives to support ethical, equitable, and learner-centered AI integration, while outlining key AI tools for education, research, paraphrasing, and collaboration.
- 6 February 2026
- Published by IGI Global Scientific Publishing
- p. 303-332
Intelligent Learning
The integration of Artificial Intelligence (AI) into digital education marks a major shift in pedagogy, learner engagement, and institutional functions. AI-driven systems such as intelligent tutoring, adaptive learning, and learning analytics are transforming how knowledge is delivered and assessed. This chapter explores AI's role in creating adaptive learning environments, supporting both cognitive and emotional assessment, and improving institutional efficiency through automation. Global platforms including Squirrel AI, Carnegie Learning, Duolingo, and DIKSHA are examined. The chapter also addresses ethical, technical, and infrastructural challenges, including privacy, algorithmic bias, and the digital divide. It synthesizes current literature and promotes comparative perspectives to support ethical, equitable, and learner-centered AI integration, while outlining key AI tools for education, research, paraphrasing, and collaboration.
- Open Access
- 8 September 2025
- Published by Gujarat University in VIDYA - A JOURNAL OF GUJARAT UNIVERSITY
- Vol. 4 (2) , 514-520
TOWARDS ACCURATE AND RELIABLE AUTOMATED CLASSROOM ATTENDANCE USING FACE RECOGNITION AND CNNS
In real world classroom settings, traditional classroom attendance methods are often time consuming, prone to human errors, and inefficient in terms of accuracy. Different solutions have been introduced from time to time, to make them easy, accurate and automatic. Use of computer vision and face recognition is gaining momentum as it provides automation and increases the precision and effectiveness of attendance system. The research aims to design automated attendance systems capable of working seamlessly in real classroom settings, focusing on increasing the accuracy as well as reliability for the development of automated attendance system. With the goal of providing effective fast automatic classroom attendance, this research focusses on evaluating performance of different Convolutional Neural Network architectures performance, such as VGGNet, ResNet, and DenseNet. For the evaluation of the performance of these Convolutional Neural Networks, we have used parameters like accuracy, precision, recall, and F1 score for a real world classroom scenario with different lighting conditions, poses, and occlusions. Our research shows that the ResNet performs better with respect to speed and accuracy in comparison to VGGNet and DenseNet. This makes ResNet an optimum choice for real time deployment.
- 8 September 2025
- Published by Gujarat University in VIDYA - A JOURNAL OF GUJARAT UNIVERSITY
- Vol. 4 (2) , 514-520
Open AccessTOWARDS ACCURATE AND RELIABLE AUTOMATED CLASSROOM ATTENDANCE USING FACE RECOGNITION AND CNNS
In real world classroom settings, traditional classroom attendance methods are often time consuming, prone to human errors, and inefficient in terms of accuracy. Different solutions have been introduced from time to time, to make them easy, accurate and automatic. Use of computer vision and face recognition is gaining momentum as it provides automation and increases the precision and effectiveness of attendance system. The research aims to design automated attendance systems capable of working seamlessly in real classroom settings, focusing on increasing the accuracy as well as reliability for the development of automated attendance system. With the goal of providing effective fast automatic classroom attendance, this research focusses on evaluating performance of different Convolutional Neural Network architectures performance, such as VGGNet, ResNet, and DenseNet. For the evaluation of the performance of these Convolutional Neural Networks, we have used parameters like accuracy, precision, recall, and F1 score for a real world classroom scenario with different lighting conditions, poses, and occlusions. Our research shows that the ResNet performs better with respect to speed and accuracy in comparison to VGGNet and DenseNet. This makes ResNet an optimum choice for real time deployment.
- 29 October 2024
- Published by Springer Nature
- p. 215-225
A Comparative Evaluation of Different Distance Measures for Determining Initial Seeds in the K-means Algorithm
- 29 October 2024
- Published by Springer Nature
- p. 215-225
A Comparative Evaluation of Different Distance Measures for Determining Initial Seeds in the K-means Algorithm
- 4 October 2024
- Published by IGI Global Scientific Publishing
- p. 21-48
Big Data Cyber Security Analytics
The prevalence of social media usage is rapidly escalating. In January 2024, India alone recorded a total of 462 million social media users. The rise in online users has led to a corresponding surge in cybersecurity frauds. Cybersecurity experts can utilize big data analytic tools to identify, prevent, and mitigate cyber assaults, as these technologies are capable of handling the enormous amounts of data collected from diverse sources. This chapter examines cybercrimes that can be identified using Big Data Analytics (BDA). The primary aim of this chapter is to offer readers a comprehensive understanding of how Big Data Analytics (BDA) is applied in the field of cybersecurity. It also aims to enlighten readers about current advancements in the application of BDA in cybersecurity and the challenges that are encountered in this domain.
- 4 October 2024
- Published by IGI Global Scientific Publishing
- p. 21-48
Big Data Cyber Security Analytics
The prevalence of social media usage is rapidly escalating. In January 2024, India alone recorded a total of 462 million social media users. The rise in online users has led to a corresponding surge in cybersecurity frauds. Cybersecurity experts can utilize big data analytic tools to identify, prevent, and mitigate cyber assaults, as these technologies are capable of handling the enormous amounts of data collected from diverse sources. This chapter examines cybercrimes that can be identified using Big Data Analytics (BDA). The primary aim of this chapter is to offer readers a comprehensive understanding of how Big Data Analytics (BDA) is applied in the field of cybersecurity. It also aims to enlighten readers about current advancements in the application of BDA in cybersecurity and the challenges that are encountered in this domain.