Reducing Overfitting in Diabetic Retinopathy Detection Using Transfer Learning

2020 IEEE 5th International Conference on Computing, Communication and Automation (ICCCA)

Diabetic retinopathy is a diabetes complication which causes damage to the retina. It is highly prevalent in patients who have had diabetes for 20 years or more. Current deep learning methods of detection of this disease are not efficient with the respect to the number of images required for training and the transfer learning methods use pre-trained networks, which contains many features that are irrelevant to the original task data. In this paper, the network is pre-trained in a self supervised manner on the training data, such that the network learns features relevant to the task data without overfitting. This paper proposes a data efficient architecture based on autoencoder and VGG network and a method to train the network such that it is regularized by an autoencoder network to prevent overfitting and improve test data performance.

A Review- and Reviewer-Based Approach for Fake Review Detection

2021 IEEE 4th International Conference on Electrical, Computer and Communication Technologies (ICECCT)

This paper presents an approach to fake review detection, essentially for online hotel reviews, by combining the review-based approach and reviewer-based approach. Different Natural Language Processing techniques such as tokenization, lemmatization, vectorization, etc. are used to extract insightful features from the review text data. After text mining, the data is used to train different classification models using machine learning algorithms that detect fake reviews. After evaluating the models, a comparison is made based on the performance metrics. Furthermore, a web based user interface is created to provide a platform that combines the knowledge of the input user information with the chosen machine learning model to perform fake review detection on the input data.

Joint Secretary and Treasurer - Student Chapter, S.P.I.T.
Fire and Security Association of India (F.S.A.I)

Held the positions of Joint Secretary and Treasurer in the S.P.I.T. Student Chapter of F.S.A.I.

Successfully organized multiple impactful events, including:
1. Safety and Security Audit of Ganesh Mandals over Mumbai:
   • Led a team of 150 volunteers to collect data on safety and security measures implemented in Ganesh Mandals across Mumbai.
   • Submitted the collected data to the Disaster Management Cell of the Brihanmumbai Municipal Corporation (B.M.C.) to enhance response time and improve safety standards.
2. Student Evaluation of SE students:
   • Coordinated talks by industry leaders, such as Dr. Abbasaheb Kale from MARSH, to provide insights into real-world practices.
   • Organized a competition comprising activities like Poster Making, Project Competition, Short Film Making, Skit Presentation, and Case Study Presentation.

Demonstrated effective event management skills, including planning, coordination, delegation and execution.

Showcased strong leadership abilities in ensuring the success and impact of these events.

Senior Correspondent
SPark - College Editorial of S.P.I.T.

Served as a Senior Correspondent at SPark, the official editorial of Sardar Patel Institute of Technology.

Contributed to the Photography and Operations teams, undertaking diverse responsibilities.

Provided comprehensive event coverage through photography, capturing key moments and visually documenting college events.

Collaborated with a talented team of writers, photographers, and designers to produce high-quality content.

Maintained strict adherence to deadlines, delivering quality work within specified timeframes.

Gained valuable experience in journalistic practices, honing skills in writing, photography, and editorial operations.