Identifying and extracting information from web tables is not a trivial task, and understanding the semantics of a web table proves to be even harder.

This paper introduces a machine learning based approach to understand the semantics in the data residing in tabular web sources. The approach includes suggesting features that reflect the characteristics of the content in the tables and analyze their impact on the accuracy of the classification process.

Moratuwa Engineering Research Conference (MERCon), 2016
MERCon 2016

Due to the increasing number of online interaction in travel industry, there is a rich corpus of textual information available online.To make sense of these information specially online reviews, the essential first step is to understand the semantics that lie therein. This paper discusses a system that uses machine learning based classifiers to label the entities found in text into semantic concepts defined in an ontology.

Packaging basic vacation components to generate the highest revenue is a hectic task for a tour operator. This would cost many man hours.

The paper presents a linear programming approach which ensures the maximum revenue to the tour operator, where all the contract constraints are satisfied. From LP model formulation to the solving algorithm and its results will be presented in this paper. Karmarkar’s Projective Scaling algorithm, which is the solving algorithm will be explained in the process, with its implementation approach

ACAN2016 The 9th International Workshop on Agent-based Complex Automated Negotiations Singapore
May 9, 2016

Existing Agent-Based Negotiation (ABN) frameworks for bargaining are based on the assumption that private information of agents such as reserve price and with fixed deadlines.

Real world bargaining scenarios, negotiators change their deadline due to their bargaining strategies, personal reasons or market issues. Existing Agent-Based Negotiation (ABN) frameworks are based on the assumption that private information of agents such as reserve price and with fixed deadlines which limits the usability and performance of the existing ABN approaches. This paper presents a global optimization model for offer generation in one-to-many bilateral negotiations that takes dynamism of the deadline into account. In this approach the agents profess a deadline that is shorter than the actual, thus pressurizing the opponent to get a quick counter offer and finally selects the best opponent to deal with.To support agents with incomplete information, the model incorporates Bayesian learning.

This paper describes a solution for creating a 360-degree real time panoramic video stream from an array of webcams whose positions are fixed.  The algorithm provides a mechanism to correct errors in positioning. Normalization of luminance is done to compensate for variance in lighting and picture quality of webcams.

DOI: 10.1109/ICIAFS.2012.6419900
Information and Automation for Sustainability (ICIAfS)
2012 IEEE 6th International Conference

Accurate decision making is the key to make a business profitable. Decision support systems are used to make the decision making process accurate and easy. Even though there are many business specific decision support systems they cannot be used for general purpose decision making or outside their domain. DecisionAI provides a framework which can be used in any decision making domain with similar decision types and allows detailed analysis of data with the integrated intelligence.