Nithya Rajamani

Characteristics of document similarity measures for compliance analysis

Due to increased competition in the IT Services business, improving quality, reducing costs and shortening schedules has become extremely important. A key strategy being adopted for achieving these goals is the use of an asset-based approach to service delivery, where standard reusable components developed by domain experts are minimally modified for each customer instead of creating custom solutions. One example of this approach is the use of contract templates, one for each type of service offered. A compliance checking system that measures how well actual contracts adhere to standard templates is critical for ensuring the success of such an approach. This paper describes the use of document similarity measures - Cosine similarity and Latent Semantic Indexing - to identify the top candidate templates on which a more detailed (and expensive) compliance analysis can be performed. Comparison of results of using the different methods are presented.

Human sensors: Case-study of open-ended community sensing in developing regions

With the growing number of cities and population, continuous monitoring of citys infrastructure and automated collection of day-to-day events (such as traffic jam) is essential and can help in improving life style of citizens. It is extremely costly and ineffective to install hardware sensors to sense these events in developing regions. Due to advent of smartphones, citizens can play role of sensors and actively participate in collection of the events which can be shared with others for information or can be used in decisions which affects city development. In this paper, we describe an architecture of crowdsensing testbed for capturing and processing events affecting citizens in cities in India. One of the design principle of our testbed is that it encourages users to do an open-ended sensing under five broad categories: Civic complaints, traffic, neighbourhood issues, emergency and others. As part of testbed, we allow events submissions from different submission modes i.e. mobile application, SMSes and web. Our mobile application exploits different sensing interfaces provided by todays smartphones to add contextual data with event reports such as images, audio, fine-grained location etc. Proposed testbed is used by university students across India to report event happening around them. Finally, we describe the data collected and uncover some of challenges and opportunities which may help future designs of crowdsensing based systems.

A Policy Evaluation Tool for Multisite Resource Management

An enterprise typically operates multiple data center sites, each handling workloads according to an enterprise-level strategy. Sharing resources across multiple sites (or enterprises) brings up several important problems. Each site may have its own policies that govern its interactions with other remote sites. Different policies impact the system performance in different ways. The site administrators and system designers need to understand the effects of a given set of policies on different workloads. In this paper, we describe an analysis methodology that determines the impact of policies on the workloads, and we present results and validation for a prototypical multi-site resource sharing system. Our analytical tool is capable of evaluating complex policies on a large scale system and permits independent policies for each site, so that policy makers can quickly evaluate several alternatives and their effects on the workloads before deploying them.

Efficient Multi-stage Image Classification for Mobile Sensing in Urban Environments

With the recent dramatic increase in the popularity of mobile electronic devices equipped with cameras, there is a growing number of real-world applications for image classification. Nevertheless, some of these real-world applications aim to classify images captured in an unconstrained manner and in complex environments where existing image classification techniques may not perform well. We propose an efficient image classification system that is robust enough to cope with challenging imaging conditions, and demonstrate its effectiveness in the context of classification of real-world images of dumpsters captured by mobile phones in the Indian metropolitan city of Hyderabad. Our system is able to achieve accurate classification of the cleanliness state of the dumpsters despite the challenging uncontrolled urban environment by utilizing a multi-stage approach, where the first stage is the efficient detection of the dumpster, and the second stage is the classification of its state. We analyze the performance of the system and provide comprehensive experimental results on a real-world public dataset.

Traffic density state estimation based on acoustic fusion

In this paper, we propose an acoustic fusion based approach to classify the traffic density states. In particular, we combine the information from mel-frequency cepstral coefficients (MFCC) based classifier, which models the cumulative road side signal and honk event based classifier. Honk based classifier is obtained by modeling the honk statistics for each traffic class, viz., Jam, Medium and Free. We study in detail the discriminative capabilities of honk information based classifier. Decisions from MFCC and honk classifier are then combined in probabilistic framework with an appropriate fusion strategy. We also propose to use prior honk information in-order to further improve the classification results. Classification results show good performance even with 10s of audio data.

Improving Information Access for a Community of Practice Using Business Process as Context

This paper addresses the important problem of finding relevant information in the context of a business process. It presents an information access solution called EIL (enterprise information leverage) which combines information extraction and semantic search to support information needs of professionals selling IT services. EIL leverages structured and unstructured data using novel architecture and special purpose algorithms. Our approach is to organize information around business activities (e.g. a sale), and the system supports semantic concept based information retrieval by utilizing both database query and document search where the relevant business activities act as a contextual constraint. We experimentally show that this approach is promising for reducing noise in search results. EIL is currently under pilot deployment in one of the IBM services sales units.

A Multi-Stage Framework for Classification of Unconstrained Image Data from Mobile Phones

During the past decade, the number of mobile electronic devices equipped with cameras has increased dramatically and so has the number of real-world applications for image classification. In many of these applications, the image data is captured in an uncontrolled manner and in complex environments and conditions under which existing image classification techniques may not perform well. In this paper, the authors provide a detailed description of an efficient multi-stage image classification framework that is robust enough to remain effective also under challenging imaging conditions, and demonstrate its effectiveness in the context of classification of real-world images of dumpsters captured by mobile phones in the metropolitan city of Hyderabad. Their system is able to achieve accurate classification of the cleanliness state of the dumpsters by utilizing a multi-stage approach, where the first stage is the efficient detection of the dumpster and the second stage is the classification of its state. The authors provide a detailed analysis of the performance of the system as well as comprehensive experimental results on real-world image data.