Supervised approaches for text summarisation suffer from the problem of mismatch between the target labels/scores of individual sentences and the evaluation score of the final summary. Reinforcement learning can solve this problem by providing a learning mechanism that uses the score of the final summary as a guide to determine the decisions made at the time of selection of each sentence. In th...

A market-based algorithm is presented which autonomously apportions complex tasks to multiple cooperating agents giving each agent the motivation of improving performance of the whole system. A speciic model, called \The Hayek Machine" is proposed and tested on a simulated Blocks World (BW) planning problem. Hayek learns to solve more complex BW problems than any previous learning algorithm. Gi...

Sequential forward selection (SFS) is one of the most widely used feature selection procedures. It starts with an empty set and adds one feature at each step. The estimate of the quality of the candidate subsets usually depends on the training/testing split of the data. Therefore different sequences of features may be returned from repeated runs of SFS. A substantial discrepancy between such se...

In recent years, we have presented many algorithms for polarimetric SAR image segmentation that show the continually improving developments in the field. However, there are two distinct and divergent approaches one using highly flexible textured models for the covariance matrix statistics (such as the Wishart, K-Wishart, and U-distribution), and the other using simple features extracted from su...

Received on: 09/10/10 Accepted after Revision: 13/12/10 1,4Professor, 2Ex-Professor, 3Implantologist 1Department of Prosthodontics, Rama Dental College, Hospital and Research Centre, Kanpur, Uttar Pradesh, India 2Department of Orthodontics, Teerthanker Mahaveer Dental College Moradabad, Uttar Pradesh, India 3Private Practice, SFS Sector 14, Faridabad, Haryana, India 4Department of Prosthodontic...

Past research suggests Facebook use is linked to perceptions of social capital, a concept that taps into the resources people gain from interactions with their social network. In this study, we examine a sample of public Facebook status updates (N=20,000) for instances in which users request a response from their network. These attempts to mobilize resources offer insight into the mechanisms th...

We present concept detection and normalization experiments on the French and English CLEF eHealth 2017 death certificate datasets. For this purpose, we start from our last published system, which relied upon dictionary projection and supervised multi-class, mono-label text classification using simple features. We extend this system in several dimensions with multi-label classification and new f...

This paper studies the robustness of SIFT and SURF against different image transforms (rigid body, similarity, affine and projective) by quantitatively analyzing the variations in the extent of transformations. Previous studies have been comparing the two techniques on absolute transformations rather than the specific amount of deformation caused by the transformation. The paper establishes an ...

Cloud computing is an important part of today’s world because offloading computations is a method to reduce costs. In this paper, we investigate computing the Speeded Up Robust Features (SURF) using Fully Homomorphic Encryption (FHE). Performing SURF in FHE enables a method to offload the computations while maintaining security and privacy of the original data. In support of this research, we d...

Current state-of-the-art methods for object tracking perform adaptive tracking-by-detection, meaning that a detector predicts the position of an object and adapts its parameters to the object’s appearance at the same time. While suitable for cases when the object does not disappear from the scene, these methods tend to fail on occlusions. In this work, we build on a novel approach called Tracki...