Karan Mitra | Monash University (original) (raw)

Papers by Karan Mitra

Research paper thumbnail of Measuring Quality of Experience in Pervasive Systems Using Probabilistic Context-Aware Approach

In this paper, we pioneer a context-aware approach for quality of experience (QoE) modeling, reas... more In this paper, we pioneer a context-aware approach for quality of experience (QoE) modeling, reasoning and inferencing in mobile and pervasive computing environments. The proposed model is based upon Context Spaces Theory (CST) and influence diagrams (IDs) to handle uncertain and hidden complex inter-dependencies between user-perceived and network level QoS and to calculate overall QoE of the users.

Research paper thumbnail of A Cloud-based Collaborative Video Story Authoring and Sharing Platform

Research paper thumbnail of Do-it-Yourself Content Delivery Network Orchestrator

Content delivery networks (CDNs)[1] provide fast and reliable content access to the end-users. CD... more Content delivery networks (CDNs)[1] provide fast and reliable content access to the end-users. CDN providers (eg, Akamai [2]), either own the entire infrastructure or it is outsourced to a single Cloud provider. Content owners (eg, clients and end-users) need to establish expensive contracts with third party ISPs or CDN providers. Hence, existing CDN services are out of reach for all but large enterprises.

Research paper thumbnail of QoE Estimation and Prediction using Hidden Markov Models in Heterogeneous Access Networks

Research paper thumbnail of MediaWise – Designing a Smart Media Cloud

The MediaWise project aims to expand the scope of existing media delivery systems with novel clou... more The MediaWise project aims to expand the scope of
existing media delivery systems with novel cloud, personalization
and collaboration capabilities that can serve the needs of more
users, communities, and businesses. The project develops a
MediaWise Cloud platform that supports do-it-yourself creation,
search, management, and consumption of multimedia content.
The MediaWise Cloud supports pay-as-you-go models and
elasticity that are similar to those offered by commercially
available cloud services. However, unlike existing commercial
CDN services providers such as Limelight Networks and Akamai
the MediaWise Cloud require no ownerships of computing
infrastructure and instead rely on the public Internet and public
cloud services (e.g., commercial cloud storage to store its content).
In addition to integrating such public cloud services into a public
cloud-based Content Delivery Network, the MediaWise Cloud
also provides advanced Quality of Service (QoS) management as
required for the delivery of streamed and interactive high
resolution multimedia content. In this paper, we give a brief
overview of MediaWise Cloud architecture and present a
comprehensive discussion on research objectives related to its
service components. Finally, we also compare the features
supported by the existing CDN services against the envisioned
objectives of MediaWise Cloud.

Research paper thumbnail of Performance Evaluation of a Decision-Theoretic Approach for Quality of Experience Measurement in Mobile and Pervasive Computing Scenarios

Measuring and predicting users quality of experience (QoE) in dynamic network conditions is a cha... more Measuring and predicting users quality of experience
(QoE) in dynamic network conditions is a challenging
task. This paper presents results related to a decision-theoretic
methodology incorporating Bayesian networks (BNs) and utility
theory for quality of experience (QoE) measurement and prediction in mobile computing scenarios. In particular, we show
how both generative and discriminative BNs can be used to
measure and predict users QoE accurately for voice applications
under several wireless network conditions such as wireless signal
fading, vertical handoffs, wireless network congestion and normal
hotspot traffic. Through extensive simulation studies and results
analysis, we show that our proposed methodology can achieve
an average accuracy of 98.70% using three different types of
Bayesian network.

Research paper thumbnail of Context-aware Vertical Handovers in a 4G Network

Research paper thumbnail of Dynamic bayesian networks for sequential quality of experience modelling and measurement

Smart Spaces and Next Generation …, Jan 1, 2011

his paper presents a novel context-aware methodology for modelling and measuring user-perceived q... more his paper presents a novel context-aware methodology for modelling and measuring user-perceived quality of experience (QoE) over time. In particular, we create a context-aware model for QoE modelling and measurement using dynamic Bayesian networks (DBN) and a context-aware state-space approach. The proposed model is then used to infer and determine users' QoE in a sequential manner. We performed experimentation to validate the proposed model. The results prove that it can efficiently model, reason and measure QoE of the users'.

Research paper thumbnail of Context-aware application mobility support in pervasive computing environments

Proceedings of the …, Jan 1, 2009

Research paper thumbnail of A probabilistic context-aware approach for quality of experience measurement in pervasive systems

… of the 2011 ACM Symposium on …, Jan 1, 2011

Research paper thumbnail of A decision-theoretic approach for quality of experience measurement and prediction

Multimedia and Expo (ICME), …, Jan 1, 2011

This paper presents a pioneering context-aware approach for quality of experience (QoE) measureme... more This paper presents a pioneering context-aware approach for quality of experience (QoE) measurement and prediction. The proposed approach incorporates an intuitive context-aware framework and decision theory. It is capable of incorporating several QoE related classes and context information to correctly measure and predict the overall QoE on a single scale. Our approach can be used in measuring and predicting QoE in both lab and living-lab settings based on user, device and network related context parameters. The predicted QoE can be beneficial for network operators to minimize network churn and can help application developers to build smart user-centric applications. We perform extensive experimentation and the results validate our approach.

Research paper thumbnail of PRONET: Proactive context-aware support for mobility in heterogeneous access networks

Local Computer Networks, …, Jan 1, 2009

Research paper thumbnail of Measuring Quality of Experience in Pervasive Systems Using Probabilistic Context-Aware Approach

In this paper, we pioneer a context-aware approach for quality of experience (QoE) modeling, reas... more In this paper, we pioneer a context-aware approach for quality of experience (QoE) modeling, reasoning and inferencing in mobile and pervasive computing environments. The proposed model is based upon Context Spaces Theory (CST) and influence diagrams (IDs) to handle uncertain and hidden complex inter-dependencies between user-perceived and network level QoS and to calculate overall QoE of the users.

Research paper thumbnail of A Cloud-based Collaborative Video Story Authoring and Sharing Platform

Research paper thumbnail of Do-it-Yourself Content Delivery Network Orchestrator

Content delivery networks (CDNs)[1] provide fast and reliable content access to the end-users. CD... more Content delivery networks (CDNs)[1] provide fast and reliable content access to the end-users. CDN providers (eg, Akamai [2]), either own the entire infrastructure or it is outsourced to a single Cloud provider. Content owners (eg, clients and end-users) need to establish expensive contracts with third party ISPs or CDN providers. Hence, existing CDN services are out of reach for all but large enterprises.

Research paper thumbnail of QoE Estimation and Prediction using Hidden Markov Models in Heterogeneous Access Networks

Research paper thumbnail of MediaWise – Designing a Smart Media Cloud

The MediaWise project aims to expand the scope of existing media delivery systems with novel clou... more The MediaWise project aims to expand the scope of
existing media delivery systems with novel cloud, personalization
and collaboration capabilities that can serve the needs of more
users, communities, and businesses. The project develops a
MediaWise Cloud platform that supports do-it-yourself creation,
search, management, and consumption of multimedia content.
The MediaWise Cloud supports pay-as-you-go models and
elasticity that are similar to those offered by commercially
available cloud services. However, unlike existing commercial
CDN services providers such as Limelight Networks and Akamai
the MediaWise Cloud require no ownerships of computing
infrastructure and instead rely on the public Internet and public
cloud services (e.g., commercial cloud storage to store its content).
In addition to integrating such public cloud services into a public
cloud-based Content Delivery Network, the MediaWise Cloud
also provides advanced Quality of Service (QoS) management as
required for the delivery of streamed and interactive high
resolution multimedia content. In this paper, we give a brief
overview of MediaWise Cloud architecture and present a
comprehensive discussion on research objectives related to its
service components. Finally, we also compare the features
supported by the existing CDN services against the envisioned
objectives of MediaWise Cloud.

Research paper thumbnail of Performance Evaluation of a Decision-Theoretic Approach for Quality of Experience Measurement in Mobile and Pervasive Computing Scenarios

Measuring and predicting users quality of experience (QoE) in dynamic network conditions is a cha... more Measuring and predicting users quality of experience
(QoE) in dynamic network conditions is a challenging
task. This paper presents results related to a decision-theoretic
methodology incorporating Bayesian networks (BNs) and utility
theory for quality of experience (QoE) measurement and prediction in mobile computing scenarios. In particular, we show
how both generative and discriminative BNs can be used to
measure and predict users QoE accurately for voice applications
under several wireless network conditions such as wireless signal
fading, vertical handoffs, wireless network congestion and normal
hotspot traffic. Through extensive simulation studies and results
analysis, we show that our proposed methodology can achieve
an average accuracy of 98.70% using three different types of
Bayesian network.

Research paper thumbnail of Context-aware Vertical Handovers in a 4G Network

Research paper thumbnail of Dynamic bayesian networks for sequential quality of experience modelling and measurement

Smart Spaces and Next Generation …, Jan 1, 2011

his paper presents a novel context-aware methodology for modelling and measuring user-perceived q... more his paper presents a novel context-aware methodology for modelling and measuring user-perceived quality of experience (QoE) over time. In particular, we create a context-aware model for QoE modelling and measurement using dynamic Bayesian networks (DBN) and a context-aware state-space approach. The proposed model is then used to infer and determine users' QoE in a sequential manner. We performed experimentation to validate the proposed model. The results prove that it can efficiently model, reason and measure QoE of the users'.

Research paper thumbnail of Context-aware application mobility support in pervasive computing environments

Proceedings of the …, Jan 1, 2009

Research paper thumbnail of A probabilistic context-aware approach for quality of experience measurement in pervasive systems

… of the 2011 ACM Symposium on …, Jan 1, 2011

Research paper thumbnail of A decision-theoretic approach for quality of experience measurement and prediction

Multimedia and Expo (ICME), …, Jan 1, 2011

This paper presents a pioneering context-aware approach for quality of experience (QoE) measureme... more This paper presents a pioneering context-aware approach for quality of experience (QoE) measurement and prediction. The proposed approach incorporates an intuitive context-aware framework and decision theory. It is capable of incorporating several QoE related classes and context information to correctly measure and predict the overall QoE on a single scale. Our approach can be used in measuring and predicting QoE in both lab and living-lab settings based on user, device and network related context parameters. The predicted QoE can be beneficial for network operators to minimize network churn and can help application developers to build smart user-centric applications. We perform extensive experimentation and the results validate our approach.

Research paper thumbnail of PRONET: Proactive context-aware support for mobility in heterogeneous access networks

Local Computer Networks, …, Jan 1, 2009