Browsing by Author "Varadarajan, R."

Filter results by typing the first few letters
Now showing 1 - 3 of 3
  • No Thumbnail Available
    Item
    Image Augmentation Strategies to Train GANs with Limited Data
    (Springer Science and Business Media Deutschland GmbH, 2023) Lanka, S.; Velingkar, G.; Varadarajan, R.; Anand Kumar, M.
    Training modern generative adversarial networks (GANs) to produce high-quality images requires massive datasets, which are challenging to obtain in many real-world scenarios, like healthcare. Training GANs on a limited dataset overfits the discriminator on the data to the extent that it cannot correctly distinguish between real and fake images. This paper proposes an augmentation mechanism to improve the dataset’s size, quality, and diversity using a set of different augmentations, namely flipping of images, rotations, shear, affine transformations, translations, and a combination of these to form some hybrid augmentation. Fretchet distance has been used as the evaluation metric to analyze the performance of different augmentations on the dataset. It is observed that as the number of augmentations increase, the quality of generated images improves, and the Fretchet distance reduces. The proposed augmentations successfully improve the quality of generated images by the GAN when trained with limited data. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
  • No Thumbnail Available
    Item
    Movie Box-Office Success Prediction Using Machine Learning
    (Institute of Electrical and Electronics Engineers Inc., 2022) Velingkar, G.; Varadarajan, R.; Lanka, S.; Anand Kumar, M.
    Being a multi-billion dollar business, the film industry contributes largely to helping sustain a country's economy. A movie's box office (the revenue generated by the number of tickets sold of a movie) is an essential indicator of the movie's popularity. It varies depending upon several factors, including a production company, genre, budget, reviews, ratings, etc. Predicting an approximate value for a movie's box office based upon the various parameters helps investors with this business make intelligent and informed decisions. Thus, this paper designs a machine learning model that can predict the revenue a film will generate based on the information available before the movie's release. It also provides a model capable of taking in the planned genre, the required revenue, and using the Random Forest Regression model, provides recommended budget, runtime, star power, and expected popularity. © 2022 IEEE.
  • No Thumbnail Available
    Item
    Task Scheduling Using Deep Q-Learning
    (Springer Science and Business Media Deutschland GmbH, 2022) Velingkar, G.; Kumar, J.K.; Varadarajan, R.; Lanka, S.; Anand Kumar, A.M.
    Process scheduling is a very crucial task of operating systems. Effective scheduling ensures system efficiency and minimizes wastage of resources and cost overall, enhancing productivity. Most commonly, it is an exhaustive task to select the most accurate resources in executing these tasks. The solution for this effective job scheduling and resource management would preferably be dependent on the nature of the workload and adapt to any given environment compared to an algorithmic one. Thus, to meet this rising demand for an automated, self-assigning system, a deep Q-learning (Reinforcement learning technique)-based implementation has been done, which schedules tasks to maximize CPU utilization and memory utilization. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.