Worldwide inflation in the count of road accidents has raised an alarming scenario wherein driver distraction is identified as one of the main causes. According to the National Highway Traffic Safety Administration survey, talking over the mobile or fellow passengers, eating or drinking while driving, and operating in-vehicle menus can lead to distract the driver. Therefore, this paper presents a new driver distraction detection method to cater such scenarios. The proposed method is a convolution-based capsule network with attention mechanism, termed as CAT-CapsNet, that combines the computation capabilities of capsule network with attention module and convolution filters. We evaluate the proposed CAT-CapsNet on two publicly available driver distraction datasets namely, American University in Cairo (AUC) distracted driver dataset and Statefarmŝ dataset. A comparative analysis of the proposed model is conducted against 16 (approx) state-of-the-art methods in terms of accuracy, number of parameters, and AUC curves. Experiments affirm that CAT-CapsNet outperforms with the accuracy of $99.88\%$ on SFD dataset and $96.7\%$ accuracy on the AUC dataset. Moreover, the proposed model has only $8.5M$ parameters to train and no data augmentation is needed in-case training samples are less.
Determining the correct number of clusters is essential for efficient clustering and cluster validity indices are widely used for the same. Generally, the effectiveness of a cluster validity index relies on two factors: first, separation, defined by the distance between a pair of cluster centroids or a pair of data points belonging to different clusters and second, compactness, which is determined in terms of the distance between a data point and a centroid or between a pair of data points belonging to the same cluster. However, the existing cluster validity indices for centroid-based clustering are unreliable when the clusters are too close, but corresponding centroids are distant. To mitigate this, a new cluster validity index, Saraswat-and-Mittal index, has been proposed in this article for hyperellipsoid or hyperspherical shape close clusters with distant centroids, generated by fuzzy c-means. The proposed index computes compactness in terms of the distance between data points and corresponding centroids, whereas the distance between data points of disjoint clusters defines separation. These parameters benefit the proposed index in the analysis of close clusters with distinct centroids efficiently. The performance of the proposed index is validated against ten state-of-the-art cluster validity indices on artificial, UCI, and image datasets, clustered by the fuzzy c-means.
27 September 2020 in Complex & Intelligent Systems
In the era of Web 2.0, the data are growing immensely and is assisting E-commerce websites for better decision-making. Collaborative filtering, one of the prominent recommendation approaches, performs recommendation by finding similarity. However, this approach fails in managing large-scale datasets. To mitigate the same, an efficient map-reduce-based clustering recommendation system is presented. The proposed method uses a novel variant of the whale optimization algorithm, tournament selection empowered whale optimization algorithm, to attain the optimal clusters. The clustering efficiency of the proposed method is measured on four large-scale datasets in terms of F-measure and computation time. The experimental results are compared with state-of-the-art map-reduce-based clustering methods, namely map-reduce-based K-means, map-reduce-based bat algorithm, map-reduce-based Kmeans particle swarm optimization, map-reduce-based artificial bee colony, and map-reduce-based whale optimization algorithm. Furthermore, the proposed method is tested as a recommendation system on the publicly available movie-lens dataset. The performance validation is measured in terms of mean absolute error, precision and recall, over a different number of clusters. The experimental results assert that the proposed method is a permissive approach for the recommendation over large-scale datasets.