Conference Papers

Permanent URI for this collectionhttps://idr.nitk.ac.in/handle/123456789/28506

Browse

Author: search.filters.author.Kumsetty, N.V.

Search Results

Now showing 1 - 3 of 3
  • No Thumbnail Available
    Item
    TrashBox: Trash Detection and Classification using Quantum Transfer Learning
    (IEEE Computer Society, 2022) Kumsetty, N.V.; Bhat Nekkare, A.; Kamath S․, S.; Anand Kumar, M.
    The problem of effective disposal of the trash generated by people has rightfully attracted major interest from various sections of society in recent times. Recently, deep learning solutions have been proposed to design automated mechanisms to segregate waste. However, most datasets used for this purpose are not adequate. In this paper, we introduce a new dataset, TrashBox, containing 17,785 images across seven different classes, including medical and e-waste classes which are not included in any other existing dataset. To the best of our knowledge, TrashBox is the most comprehensive dataset in this field. We also experiment with transfer learning based models trained on TrashBox to evaluate its generalizability, and achieved a remarkable accuracy of 98.47%. Furthermore, a novel deep learning framework leveraging quantum transfer learning was also explored. Experimental evaluation on benchmark datasets has shown very promising results. Further, parallelization was incorporated, which helped optimize the time taken to train the models, recording a 10.84% improvement in the performance and 27.4% decline in training time. © 2022 FRUCT Oy.
  • No Thumbnail Available
    Item
    Messaging Application Using Bluetooth Low Energy
    (Springer Science and Business Media Deutschland GmbH, 2023) Kumsetty, N.V.; Sawant, S.V.; Rudra, B.
    Bluetooth Low Energy is a cutting-edge technology that consumes far less energy than classical Bluetooth, especially for low-data transmission tasks. It is of interest to various IoT applications due to its low maintenance and high self-operability. Most messaging apps in the industry consume a lot of energy and storage from their devices, requiring a diverse set of resources to operate. This can be a problem when dealing with constant data transmission in smart devices and machines. Especially in the circumstances and ideas of the present age, energy and storage are valuable commodities. We propose a method to build a messaging interface that can be used to communicate among various IoT devices with the help of Bluetooth Low Energy which consumes significantly less energy and storage space. The messaging interface is being designed and developed as per the Bluetooth Low Energy official documentation and guidelines provided. It involves making the messaging interface connect and communicate to an IoT device possessing Bluetooth Low Energy feature on Chromium-based web browsers. This approach only takes up a fraction of the resources required for traditional data communication techniques. However, there is a minimum resource requirement regarding RAM, Storage, and CPU usage affecting the performance of the proposed scheme. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
  • No Thumbnail Available
    Item
    An Approach for Waste Classification Using Data Augmentation and Transfer Learning Models
    (Springer Science and Business Media Deutschland GmbH, 2023) Kumsetty, N.V.; Bhat Nekkare, A.B.; Kamath S․, S.; Anand Kumar, M.
    Waste segregation has become a daunting problem in the twenty-first century, as careless waste disposal manifests significant ecological and health concerns. Existing approaches to waste disposal primarily rely on incineration or land filling, neither of which are sustainable. Hence, responsible recycling and then adequate disposal is the optimal solution promoting both environment-friendly practices and reuse. In this paper, a computer vision-based approach for automated waste classification across multiple classes of waste products is proposed. We focus on improving the quality of existing datasets using data augmentation and image processing techniques. We also experiment with transfer learning based models such as ResNet and VGG for fast and accurate classification. The models were trained, validated, and tested on the benchmark TrashNet and TACO datasets. During experimental evaluation, the proposed model achieved 93.13% accuracy on TrashNet and outperformed state-of-the-art models by a margin of 16% on TACO. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.