Case-Based Reasoning relies on the underlying hypothesis that similar problems have similar solutions. The extent to which this hypothesis holds good in the case base has been used by CBR designers as a measure of case base complexity, which in turn gives insights on the generalization ability of the reasoner. Several local and global complexity measures have been proposed in the literature. However, the existing measures rely only on the similarity knowledge to compute complexity. We propose a new complexity measure called Reachability-Based Complexity Measure (RBCM) that goes beyond the similarity knowledge to include the effects of all knowledge containers in the reasoner. The proposed measure is evaluated on several real-world datasets and results suggest that RBCM corroborates well with the generalization accuracy of the reasoner.

We propose a Case-Based Reasoning(CBR) approach for content selection, which is an intermediate step towards generating textual summaries of time series data in the weather prediction domain. Specifically, we handle two significant challenges, the first involving multivariate data that warrants modeling of the interaction of two `channels' (wind speed and direction in our context) and the second involving the effective integration of domain-specific knowledge in the form of rules with data from a case library of past instances of content selection. We present an approach that uses domain knowledge to transform a given raw time series instance into a representation that facilitates effective retrieval of relevant cases, which are then used for change point prediction. We empirically demonstrate that our approach combining CBR and domain rules outperforms classical content selection mechanisms that are based on rules or heuristics alone as well as those that are purely data-driven.

The success of a recommender system lies in capturing preferences of users and recommending products that best cater to their needs. We restrict our focus to knowledge based recommender systems where we have the flexibility to model users preferences on individual features of the product. In this work, along with learning users preferences, we bring in the idea of looking at the problem of recommending from the manufacturer's point of view. We model prospective buyers of each product in the domain and use this information in predicting products that would potentially be of interest to a given user.

We propose a novel variant of the UCB algorithm (referred to as Efficient-UCB-Variance (EUCBV)) for minimizing cumulative regret in the stochastic multi-armed bandit (MAB) setting. EUCBV incorporates the arm elimination strategy proposed in UCB-Improved, while taking into account the variance estimates to compute the arms' confidence bounds, similar to UCBV. Through a theoretical analysis we establish that EUCBV incurs a gap-dependent regret bound which is an improvement over that of existing state-of-the-art UCB algorithms (such as UCB1, UCB-Improved, UCBV, MOSS). Further, EUCBV incurs a gap-independent regret bound which is an improvement over that of UCB1, UCBV and UCB-Improved, while being comparable with that of MOSS and OCUCB. Through an extensive numerical study we show that EUCBV significantly outperforms the popular UCB variants (like MOSS, OCUCB, etc.) as well as Thompson sampling and Bayes-UCB algorithms.

Regular expressions are an important building block of rule-based information extraction systems. Regexes can encode rules to recognize instances of simple entities which can then feed into the identification of more complex cross-entity relationships. Manually crafting a regex that recognizes all possible instances of an entity is difficult since an entity can manifest in a variety of different forms. Thus, the problem of automatically generalizing manually crafted seed regexes to improve the recall of IE systems has attracted research attention. In this paper, we propose a bootstrapped approach to improve the recall for extraction of regex-formatted entities, with the only source of supervision being the seed regex. Our approach starts from a manually authored high precision seed regex for the entity of interest, and uses the matches of the seed regex and the context around these matches to identify more instances of the entity. These are then used to identify a set of diverse, high recall regexes that are representative of this entity. Through an empirical evaluation over multiple real world document corpora, we illustrate the effectiveness of our approach.

For over twenty-five years Ford Motor Company has been utilizing an AI-based system to manage process planning for vehicle assembly at its assembly plants around the world. The scope of the AI system, known originally as the Direct Labor Management System and now as the Global Study Process Allocation System (GSPAS), has increased over the years to include additional functionality on Ergonomics and Powertrain Assembly (Engines and Transmission plants). The knowledge about Ford's manufacturing processes is contained in an ontology originally developed using the KL-ONE representation language and methodology. In this article, we will discuss the process by which we re-engineered the existing GSPAS KL-ONE ontology and deployed semantic web technology in our application.

For over twenty-five years Ford Motor Company has been utilizing an AI-based system to manage process planning for vehicle assembly at its assembly plants around the world. The scope of the AI system, known originally as the Direct Labor Management System and now as the Global Study Process Allocation System (GSPAS), has increased over the years to include additional functionality on Ergonomics and Powertrain Assembly (Engines and Transmission plants). The knowledge about Ford’s manufacturing processes is contained in an ontology originally developed using the KL-ONE representation language and methodology. To preserve the viability of the GSPAS ontology and to make it easily usable for other applications within Ford, we needed to re-engineer and convert the KL-ONE ontology into a semantic web OWL/RDF format. In this article, we will discuss the process by which we re-engineered the existing GSPAS KL-ONE ontology and deployed semantic web technology in our application.

This paper introduces our initial investigation on the problem of providing a semi-autonomous robot collaborator with anticipative capabilities to predict human actions. Anticipative robot behavior is a desired characteristic of robot collaborators that lead to fluid, proactive interactions. We are particularly interested in improving reactive methods that rely on human action recognition to activate the corresponding robot action. Action recognition invariably causes delay in the robot’s response, and the goal of our method is to eliminate this delay by predicting the next human action. Prediction is achieved by using a lookup table containing variations of assembly sequences, previously demonstrated by different users. The method uses the nearest neighbor sequence in the table that matches the actual sequence of human actions. At the movement level, our method uses a probabilistic representation of interaction primitives to generate robot trajectories. The method is demonstrated using a 7 degree-of-freedom lightweight arm equipped with a 5-finger hand on an assembly task consisting of 17 steps.

We report on a novel use of parallel coordinates as a pedagogical tool for illustrating the non-intuitive properties of high dimensional spaces with special emphasis on the phenomenon of Curse of Dimensionality. Also, we have collated what we believe to be a representative sample of diverse approaches that exist in literature to conceptualize the Curse of Dimensionality. We envisage that the paper will have pedagogical value in structuring the way Curse of Dimensionality is presented in classrooms and associated lab sessions.

For over twenty five years Ford has been utilizing an AI-based system to manage process planning for vehicle assembly at our assembly plants around the world. The scope of the AI system, known originally as the Direct Labor Management System and now as the Global Study Process Allocation System (GSPAS),has increased over the years to include additional functionality on Ergonomics and Powertrain Assembly (Engine and Transmission plants). The knowledge about Ford’s manufacturing processes is contained in an ontology originally developed using the KL-ONE representation language and methodology. To preserve the viability of the GSPAS ontology and to make it easily usable for other applications within Ford, we needed to re-engineer and convert the KL-ONE ontology into a semantic web OWL/RDF format. In this paper, we will discuss the process by which we re-engineered the existing GSPAS KL-ONE ontology and deployed semantic web technology in our application.