TDTanaji Dhaigude

Tanaji Dhaigude

*This is an algorithmically generated author record based on publicly available information.

Tanaji Dhaigude has a total of 14 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Towards a Holistic Approach to Chronic Disease Management: Integrating Federated Learning and IoT for Personalized health Care

    by Dipika Birari, Kalyan Devappa Bamane, Pratik Bibhishan Kamble, Tanaji Anandrao Dhaigude, Ravindra Shendge, Aarti Dandavate

    Chronic diseases, specifically Cardiovascular Disease (CVD), pose a substantial worldwide health obstacle, requiring innovative and comprehensive approaches to management. This study presents an innovative method for managing chronic diseases by combining Federated Learning (FL) and the Internet of Things (IoT). The goal is to offer tailored healthcare solutions. The study presents a new approach called Federated Transfer Learning (FTL) that incorporates Adaptive Gradient Clipping (AGC) to improve the performance of models and maintain privacy in a distributed network of healthcare devices. The primary objective of this study is to develop a holistic framework that seamlessly amalgamates data from various sources, including wearables, medical devices, and electronic health records, utilizing FL to build a centralized model while preserving data privacy at the individual level. The proposed Faster Than Light (FTL) algorithm with Automatic Gain Control (AGC) enhances the process of model convergence, guaranteeing stability and dependability in a federated learning environment. The research methodology entails implementing the suggested framework in the management of Cardiovascular Disease (CVD). The performance of the model is assessed using the Area Under the Curve (AUC) metric, resulting in an impressive AUC score of 92.4%. This highlights the efficacy of the integrated approach in precisely forecasting and controlling risks associated with cardiovascular diseases (CVD), showcasing its potential for widespread use in managing chronic diseases. The key findings emphasize the advantages of integrating IoT devices into the FL ecosystem, enabling the immediate surveillance and gathering of various health data. The decentralized nature of the learning process enables model training to occur without compromising data privacy, making it suitable for large-scale healthcare systems. Moreover, the implementation of Faster Than Light (FTL) with Automatic Gain Control (AGC) improves the resilience and effectiveness of the federated learning procedure, thereby enhancing the overall achievement of the suggested framework. In conclusion, this study presents a groundbreaking contribution to the field of chronic disease management, specifically targeting Cardiovascular Disease. The combination of Federated Learning and IoT, along with the innovative Federated Transfer Learning with Adaptive Gradient Clipping, not only achieves outstanding predictive accuracy but also guarantees the privacy and security of sensitive health data. The proposed framework holds significant promise for revolutionizing personalized healthcare solutions, paving the way for a more effective and patient-centric approach to chronic disease management.


  • Open Access

    Real-time Cardiac Arrhythmia Detection Using Machine Learning and Wearable Devices

    by Nilesh Sable, Tanaji Dhaigude, Shinde Babaso, Sagar Shinde, Pramod Dhamdhere, Priya Shelke

    Cardiac arrhythmia, a condition characterized by sporadic heartbeats, postures critical wellbeing dangers in the event that not identified instantly. Conventional checking strategies, such as Holter screens, are regularly awkward and restricted in their capacity to supply ceaseless, real-time observing. This think about presents a novel approach for real-time cardiac arrhythmia location utilizing machine learning calculations coordinates with wearable gadgets. The proposed framework leverages progressed machine learning procedures to analyse electrocardiogram (ECG) information collected from wearable gadgets, empowering persistent observing and opportune discovery of arrhythmias. The wearable gadgets are prepared with sensors that capture high-resolution ECG signals, which are at that point transmitted to a cloud-based stage for investigation. We utilize a combination of profound learning and conventional machine learning calculations, counting Convolutional Neural network (CNNs) and Support Vector Machines (SVMs), to classify diverse sorts of arrhythmias. The models are prepared on a comprehensive dataset of commented on ECG recordings, guaranteeing tall precision and vigor. To approve the adequacy of the proposed framework, broad tests were conducted utilizing real-world ECG information. The comes about illustrate that our approach accomplishes prevalent location precision compared to conventional methods, with the included advantage of real-time handling capabilities. Furthermore, the integration with wearable gadgets upgrades client consolation and comfort, advancing broad appropriation for ceaseless cardiac observing.


  • Open Access

    Sharing Secret Colour Images with Embedded Visual Cryptography Using the Stamping Algorithm and OTP Procedure

    by Nilesh N. Thorat, Amit Singla, Tanaji Dhaigude

    Finding a way to ensure the safety of media is becoming increasingly common in the modern world as digital media usage increases. Visual cryptography (VC) offers an efficient method for sending images securely. Images that have been protected using visual encryption can be decoded using features of human vision. Emails are not a highly safe method of exchanging private data because someone else can quickly weaken the content. In the visual cryptography technique, we presented for colour pictures, the divided shares are enclosed in additional pictures using stamping. Using a random number generator, the shares are created. Visual cryptography schemes (VCS) are a method of encoding pictures that conceals the secret information which is present in images. A secret image is encrypted using a straightforward visual cryptography technique by splitting it into n shares, and the stamping operation is carried out by overlapping k shares. It can be beneficial for hiding a secret image. There is a chance that employing cryptography for information exchange could cause security problems because the process of decryption of simple visual cryptographic algorithms can be completed by the human eye. To address this issue, we are using the OTP procedure. In the past, static ID and passwords were employed, making them susceptible to replay and eavesdropping attacks. One Time Password technology, which generates a unique password each time, is utilized to solve this issue. The suggested approach strengthens the security of the created transparencies by applying an envelope to each share and employing a stamping technique to address security vulnerabilities that the previous methods had, such as pixel expansion and noise.