Monument recognition is a challenging problem in the domain of image classification due to huge variations in the architecture of different monuments. Different orientations of the structure play an important role in the recognition of the monuments in their images. The paper proposes an approach for classification of various monuments based on the features of the monument images. The state-of-the-art Deep Convolutional Neural Networks (DCNN) is used for extracting representations. The model is trained on representations of different Indian monuments, obtained from cropped images, which exhibit geographic and cultural diversity. Experiments have been carried out on the manually acquired dataset that is composed of images of different monuments where each monument has images from different angular views. The experiments show the performance of the model when it is trained on representations of cropped images of the various monuments. The overall accuracy achieved is 92.7%, using DCNN, for a total of 100 different monuments that have been considered in the dataset for classification.
Our results for performance prediction show that the tree-based machine-learning models outperform all other models with median absolute percentage error of less than 5% followed by bagging and boosting models that help to improve weak learners. We have collected performance data both from simulation-based hardware as well as from physical systems and observed that prediction accuracy is higher on simulation-based hardware due to its deterministic nature as compared to physical systems. Moreover in physical systems, prediction accuracy of memory-bound applications is higher as compared to compute-bound algorithms due to manufacturer variability in processors. Furthermore, our result shows the prediction error of 15% in case of cross-systems prediction whereas in case of the cross-platform prediction error of 17% for simulation-based X86 to ARM prediction and 23% for physical Intel Core to Intel-Xeon system using best performing tree-based machine-learning model. We have employed several machine learning univariate or multivariate models for our experiments. Our result shows that runtime and power prediction accuracy of more than 80% and 90% respectively is achieved for multivariate deep neural network model in cross-platform prediction. Similarly, for cross-system prediction runtime accuracy of 90% and power accuracy of 75% is achieved for the multivariate deep neural network
This repository contains all the state-of-the-art algorithms for the task of energy disaggregation implemented using NILMTK's Rapid Experimentation API. You can find the paper here. All the notebooks that were used to can be found here.