Browsing by Author "Anagha, H.C."

Filter results by typing the first few letters
Now showing 1 - 3 of 3
  • No Thumbnail Available
    Item
    Fairness in CPU Scheduling: A Probabilistic Algorithm
    (Institute of Electrical and Electronics Engineers Inc., 2024) Prasanna, S.; Gulati, A.; Anagha, H.C.
    This paper introduces a novel CPU scheduling algorithm for uniprocessor systems that employs a probabilistic function to enhance fair resource allocation. Unlike traditional algorithms, our approach specifically tackles the challenge of equitable resource distribution by integrating a probabilistic methodology whilst also keeping the priority of each process in mind. We detail the implementation and evaluate its performance against established algorithms, assessing metrics such as average turnaround time, average waiting time and the gini index. All the related code, data used for testing and a working webpage to try out the algorithm first hand can be found at GitHub. © 2024 IEEE.
  • No Thumbnail Available
    Item
    Petri Net-Based Verification of Adaptive Traffic Light Control with AIMD Algorithm
    (Institute of Electrical and Electronics Engineers Inc., 2024) Prasanna, S.; Gulati, A.; Anagha, H.C.; Prabhu, A.; Das, M.; Mohan, B.R.
    This paper introduces and analyses the performance of the Petri net model created to simulate a traffic control system using the Additive Increase Multiplicative Decrease (AIMD) algorithm. The Petri net model was designed using TimeNET [1] tool. The model was evaluated by analysing the Reachability Graph generated by a Depth First Search (DFS) and Backtracking based algorithm. Several criteria such as Stability, Boundedness, Deadlock, etc. were verified by our proposed algorithm. The model was then validated through a C++ code to ensure it performs correctly under different situations. All the related code, images, and tables used in this paper can be found at GitHub 1 © 2024 IEEE.
  • No Thumbnail Available
    Item
    ScalarLab@TRAC2024: Exploring Machine Learning Techniques for Identifying Potential Offline Harm in Multilingual Commentaries
    (European Language Resources Association (ELRA), 2024) Anagha, H.C.; Krishna, S.M.; Jha, S.S.; Rao, V.T.; Anand Kumar, M.
    The objective of the shared task, Offline Harm Potential Identification (HarmPot-ID), is to build models to predict the offline harm potential of social media texts. "Harm potential" is defined as the ability of an online post or comment to incite offline physical harm such as murder, arson, riot, rape, etc. The first subtask was to predict the level of harm potential, and the second was to identify the group to which this harm was directed towards. This paper details our submissions for the shared task that includes a cascaded SVM model, an XGBoost model, and a TF-IDF weighted Word2Vec embedding-supported SVM model. Our system ranked 4th in the first subtask and 3rd in the second. Several other models that were explored have also been detailed. © 2024 ELRA Language Resource Association.