Browsing by Author "Kaushalya, U"

Now showing 1 - 2 of 2

Embargo
LISA : Enhance the explainability of medical images unifying current XAI techniques
(IEEE, 2022-07-18) Abeyagunasekera, S. H. P; Perera, Y; Chamara, K; Kaushalya, U; Sumathipala, P
This work proposed a unified approach to increase the explainability of the predictions made by Convolution Neural Networks (CNNs) on medical images using currently available Explainable Artificial Intelligent (XAI) techniques. This method in-cooperates multiple techniques such as LISA aka Local Interpretable Model Agnostic Explanations (LIME), integrated gradients, Anchors and Shapley Additive Explanations (SHAP) which is Shapley values-based approach to provide explanations for the predictions provided by Blackbox models. This unified method increases the confidence in the black-box model’s decision to be employed in crucial applications under the supervision of human specialists. In this work, a Chest X-ray (CXR) classification model for identifying Covid-19 patients is trained using transfer learning to illustrate the applicability of XAI techniques and the unified method (LISA) to explain model predictions. To derive predictions, an image-net based Inception V2 model is utilized as the transfer learning model.
Embargo
Towards a Smart City: Application of Optimization for a Smart Transportation Management System
(IEEE, 2018-12) Thiranjaya, C; Rushan, R; Udayanga, P; Kaushalya, U; Rankothge, W
Intelligent traffic planning, the efficiency of public transport and the improved connectivity of all road users in a city, comprise the mobility characteristics of a smart city. In the era of smart cities, efficient and well managed public transportation systems play a crucial role. The planning and allocation of public transportation systems, especially the public bus scheduling is one of the major resource allocation problems where the optimal resource allocation increases the passenger's as well as bus owner's satisfaction. In this research, we have proposed a platform for public transportation management, especially for optimal planning and scheduling of buses. We have used two approaches for our algorithms: Iterated Local Search (ILS) and Genetic Algorithm (GA). In this paper, we are presenting our optimization algorithms and their performances. Our results show that, using our algorithms, we can decide the optimal allocations of buses and plan the bus schedules dynamically in the order of seconds.