Conference Papers

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

Browse

Filters

2020 - 20212

Settings

Author: search.filters.author.Khatri, A.

Search Results

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Sarcasm detection in tweets with BERT and GloVe embeddings
    (Association for Computational Linguistics (ACL), 2020) Khatri, A.; Pranav, P.
    Sarcasm is a form of communication in which the person states opposite of what he actually means. It is ambiguous in nature. In this paper, we propose using machine learning techniques with BERT and GloVe embeddings to detect sarcasm in tweets. The dataset is preprocessed before extracting the embeddings. The proposed model also uses the context in which the user is reacting to along with his actual response. © 2020 Association for Computational Linguistics.
  • No Thumbnail Available
    Item
    Design and implementation of SDN-based handover in 5G mmWave
    (Institute of Electrical and Electronics Engineers Inc., 2021) Dhruvik, N.; Karia, A.J.; Khatri, A.; Manjappa, M.
    5G networks are more reliable than the widely used 4G network. They have extremely low latency and greater capacity. Apart from these benefits, 5G networks have speeds ranging from 1 gigabit - 10 gigabits per second. For accommodating such high rates, the User Equipment(UE) has to continuously keep switching between base stations once the signal from the previous is below some threshold. This is known as handover. Further, in a 5G scenario, where the base station coverage area is much smaller compared to 4G, UE frequently encounters handover because of its mobility. Hence, an efficient handover algorithm is required, and Software-Defined Networking (SDN) is the best option to design such algorithms. SDN, a fore-front technology, uses software-defined controllers which enable the centralised supervision of the entire network. The proposed research work has defined a software controller based handover for the 5G mmWave, which ensures Quality of Service(QoS) to the UEs. For the communication, a new interface called HOinterface has also been defined. The proposed architecture reduces the handover delay and is flexible, scalable, and efficient. The proposed SDN architecture is implemented in the NS3-mmWave patch and it was evaluated for its strengths and weaknesses. The results obtained are encouraging. © 2021 IEEE.