International Institute of Information Technology, Hyderabad

About: International Institute of Information Technology, Hyderabad is a education organization based out in Hyderabad, India. It is known for research contribution in the topics: Authentication & Internet security. The organization has 2048 authors who have published 3677 publications receiving 45319 citations. The organization is also known as: IIIT Hyderabad & International Institute of Information Technology (IIIT).

A novel approach for quantification of retinal vessel tortuosity using quadratic polynomial decomposition

Abstract: This paper describes a novel tortuosity measure, based on the premise that tortuosity is a measure of deviation from an ideal non-tortuous vessel. Hence, we propose to model the overall shape of an ideal vessel as a quadratic polynomial at a larger scale while the deviations are modeled as quadratic polynomials at smaller scales. Thus, a given vessel center-line is decomposed as a sum of quadratic polynomials of decreasing scale. This Quadratic Polynomial Decomposition is used as a framework for defining a quantitative measure of tortuosity. As opposed to the existing proposed measures, our method can distinguish between the relative size, shapes and orientations of the vessel bends. The measure is position and scale invariant and satisfies two key desired properties: it varies directly with frequency of twists at fixed amplitude and it varies directly with amplitude of twists when their frequency is fixed. The proposed method has been tested on a standard data set containing 30 artery and 30 vein vessel segments, and shown to be among the best measures as compared to the results of existing methods.

Fair resource allocation for D2D communication in mmwave 5G networks

Abstract: The fifth generation (5G) networks employing millimeter wave (mmwave) technology will gain the advantages of short distance directive propagation and more spectrum for communication. Device-to-Device communication (D2D) when integrated with mmWave technology can reach the demand for high capacity. In this paper, resource allocation for underlay D2D in outdoor mmWave scenario is presented. We emphasize on fair distribution of resources in a cell while maximizing the spectral efficiency. Also, we discuss the aspects in ad-hoc and cellular communication using the same scheme based on the requirement. The problem is formulated mathematically to maximize sum rate and an approach for resource allocation is proposed. This work aims to achieve higher system capacity with the proposed resource allocation scheme that does not have exclusivity in resource allocation and allows more than one user to share the same resource block without degrading the system spectral efficiency. However, to reduce the complexity, an upper limit on the number of users per resource block is imposed which is adaptive to the traffic environment. Results show that the proposed scheme can significantly enhance the system performance in terms of fairness and spectral efficiency.

Natural Language Processing for Less Privileged Languages: Where do we come from? Where are we going?

Abstract: In the context of the IJCNLP workshop on Natural Language Processing (NLP) for Less Privileged Languages, we discuss the obstacles to research on such languages. We also briefly discuss the ways to make progress in removing these obstacles. We mention some previous work and comment on the papers selected for the workshop.

An Exploration towards Joint Acoustic Modeling for Indian Languages: IIIT-H Submission for Low Resource Speech Recognition Challenge for Indian Languages, INTERSPEECH 2018.

Abstract: India being a multilingual society, a multilingual automatic speech recognition system (ASR) is widely appreciated. Despite different orthographies, Indian languages share same phonetic space. To exploit this property, a joint acoustic model has been trained for developing multilingual ASR system using a common phone-set. Three Indian languages namely Telugu, Tamil and, Gujarati are considered for the study. This work studies the amenability of two different acoustic modeling approaches for training a joint acoustic model using common phone-set. Sub-space Gaussian mixture models (SGMM), and recurrent neural networks (RNN) trained with connectionst temporal classification (CTC) objective function are explored for training joint acoustic models. From the experimental results, it can be observed that the joint acoustic models trained with RNN-CTC have performed better than SGMM system even on 120 hours of data (approx 40 hrs per language). The joint acoustic model trained with RNN-CTC has performed better than monolingual models, due to an efficient data sharing across the languages. Conditioning the joint model with language identity had a minimal advantage. Sub-sampling the features by a factor of 2 while training RNN-CTC models has reduced the training times and has performed better.

The English-Only Myth: Multilingual Education in India

Abstract: The first section of this overview starts by briefly sketching the state of the school education system in India. We then note that English-medium private schools are often not much better than government schools (whether English-medium or not). The second section argues that English-medium education in India must be seen in the larger context of a mother-tongue-medium education. English-medium-only education in India gives poor educational results, and it increases social inequalities. The way forward lies in a mother-tongue-based multilingual education that includes English.