Department of Computer Science and Engineering

Indian Institute of Technology Hyderabad (IITH) is a premier institute of science and technology established in 2008. IITH has been consistently ranked in the&nbsp;<a href="https://iith.ac.in/reports/" rel="noopener noreferrer">top 10 institutes</a>&nbsp;in India for Engineering&nbsp;<a href="https://www.nirfindia.org/2021/EngineeringRanking.html" rel="noopener noreferrer" target="_blank">according to NIRF</a>&nbsp;making it one of the most coveted schools for science and technology in the country.

IITH offers&nbsp;<a href="https://iith.ac.in/academics/under-graduate/">undergraduate programs</a>&nbsp;in all the classical engineering disciplines, applied sciences, design, as well as several modern interdisciplinary areas. Students are given a flexibility to explore a broad set of areas, and potentially pursue a minor or double major in a discipline that is not their own. Students who wish to seek a deeper understanding of their own discipline are strongly encouraged to get involved in cutting-edge research with the help of a faculty to mentor them, and earn an Honors in their own field.

The very foundation of IIT Hyderabad is based on&nbsp;<a href="https://iith.ac.in/research/">research and innovation</a>. The vibrant research culture is evident from the number of patents and publications that IITH produces consistently every year. IITH offers&nbsp;<a href="https://iith.ac.in/academics/programmes-offered/">graduate programs</a>&nbsp;at both a masters, and a doctoral level, in several diverse areas. There are separate programs for technology, design, science, and liberal arts. The&nbsp;<a href="https://iith.ac.in/academics/post-graduate/">MTech program</a>&nbsp;is offered in various modes and durations to cater to the ever-growing need of postgraduate level professionals in the country.

IITH encourages and supports&nbsp;<a href="https://iic-iith.netlify.app/index.html" rel="noopener noreferrer" target="_blank">innovation and entrepreneurship</a>&nbsp;at every stage. The minor program in entrepreneurship is open to all students of IITH, and many of the courses are offered by industrialists who are entrepreneurs themselves. There are various&nbsp;<a href="https://iith.ac.in/research/centres-incubators/">innovation centers and incubators</a>&nbsp;that promote entrepreneurship and help mentor young innovators. IITH has been very successful in building tie-ups with leading academic institutions around the globe.

IITH enjoys a very special relationship with Japanese universities and industries that goes beyond academic and research collaborations. In fact, some of the iconic buildings in IITH campus will carry the signature of Japanese architecture.

IITH creates a unique holistic ecosystem for education that offers interactive learning, a very flexible academic structure, cutting-edge research, strong industry collaboration, and entrepreneurship. This is an environment which enables students and faculty to translate their dreams into realities.

IIT Hyderabad

The field of music and speech classification is quite mature with researchers having settled on the approximate best discriminative representation. In this regard, Zubair et al. showed the use of sparse coefficients alongwith SVM to classify audio signals as music or speech to get a near-perfect classification. In the proposed method, we go one step further, instead of using the sparse coefficients with another classifier they are directly used in a dictionary which is learned using on-line dictionary learning for music-speech classification. This approach removes the redundancy of using a separate classifier but also produces complete discrimination of music and speech on the GTZAN music/speech dataset. Moreover, instead of the high-dimensional feature vector space which inherently leads to high computation time and complicated decision boundary calculation on the part of SVM, the restricted dictionary size with limited computation serves the same purpose. © 2014 IEEE.

World University root node

International Conference on Digital Signal Processing, DSP

Learning sparse dictionaries for music and speech classification

In this paper, an approach for music genre classification based on sparse representation using MARSYAS features is proposed. The MARSYAS feature descriptor consisting of timbral texture, pitch and beat related features is used for the classification of music genre. On-line Dictionary Learning (ODL) is used to achieve sparse representation of the features for developing dictionaries for each musical genre. We demonstrate the efficacy of the proposed framework on the Latin Music Database (LMD) consisting of over 3000 tracks spanning 10 genres namely Axé, Bachata, Bolero, Forró, Gaúcha, Merengue, Pagode, Salsa, Sertaneja and Tango. © 2014 IEEE.

Proceedings of the International Joint Conference on Neural Networks

Music genre classification using On-line Dictionary Learning

Facial expression recognition is an active area of research with applications in the design of Human Computer Interaction (HCI) systems. In this paper, we propose an approach for facial expression recognition using deep convolutional neural networks (CNN) based on features generated from depth information only. The Gradient direction information of depth data is used to represent facial information, due its invariance to distance from the sensor. The ability of a convolutional neural networks (CNN) to learn local discriminative patterns from data is used to recognize facial expressions from the representation of unregistered facial images. Experiments conducted on EURECOM kinect face dataset demonstrate the effectiveness of the proposed approach. © 2014 IEEE.

Proceedings - 2014 13th International Conference on Machine Learning and Applications, ICMLA 2014

Facial expression recognition using kinect depth sensor and convolutional neural networks

In this paper, we proposed a method for classification of medical images captured by different sensors (modalities) based on multi-scale wavelet representation using dictionary learning. Wavelet features extracted from an image provide discrimination useful for classification of medical images, namely, diffusion tensor imaging (DTI), magnetic resonance imaging (MRI), magnetic resonance angiography (MRA) and functional magnetic resonance imaging (FRMI). The ability of On-line dictionary learning (ODL) to achieve sparse representation of an image is exploited to develop dictionaries for each class using multi-scale representation (wavelets) feature. An experimental analysis performed on a set of images from the ICBM medical database demonstrates efficacy of the proposed method. © 2014 IEEE.

Medical images modality classification using multi-scale dictionary learning

We study the problem of testing if the polynomial computed by an arithmetic circuit is identically zero. We give a deterministic polynomial time algorithm for this problem when the inputs are read-twice or read-thrice formulas. In the process, these algorithms also test if the input circuit is computing a multilinear polynomial. We further study three related computational problems on arithmetic circuits. Given an arithmetic circuit C, (1) ZMC: test if a given monomial in C has zero coefficient or not, (2) MonCount: compute the number of monomials in C, and (3) MLIN: test if C computes a multilinear polynomial or not. These problems were introduced by Fournier, Malod and Mengel (2012) [11], and shown to characterise various levels of the counting hierarchy (CH). We address the above problems on read-restricted arithmetic circuits and branching programs. We prove several complexity characterisations for the above problems on these restricted classes of arithmetic circuits. © 2014 Elsevier B.V.

Theoretical Computer Science

Monomials, multilinearity and identity testing in simple read-restricted circuits

In this chapter, we describe how the p-values derived from the conformal predictions framework can be used for active learning; that is, to select the informative examples from a data collection that can be used to train a classifier for best performance. We show the connection of this approach to information-theoretic methods, as well as show how the methodology can be generalized to multiple classifier models and information fusion settings. © 2014 Elsevier Inc. All rights reserved.

Conformal Prediction for Reliable Machine Learning: Theory, Adaptations and Applications

Active Learning

Due to the ubiquitous coverage and seamless connectivity, cellular systems are very promising to support Machine-to-Machine (M2M) communications. But, all of the cellular networks are designed and optimized for Human-to-Human (H2H) or Human-to-Machine (H2M) communications and therefore facing several challenges due to incorporation of M2M communications. One of such challenges is efficient resource allocation to M2M applications without affecting or least affecting H2H applications. In order to address this challenge, we need application specific priority based scheduling algorithms in which based on the QoS of the application, radio resources are allocated. In this paper, we have classified and prioritized all H2H and M2M flows based on their QoS requirements. Resources are allocated first to higher priority classes and in a given class, they are allocated to H2H flows first. In order to ensure the QoS of H2H flows, a threshold is kept on the maximum number of radio resource blocks to be assigned to M2M flows in a scheduling interval. Performance of the proposed scheduling algorithm is evaluated using various metrics such as system throughput and average utility per class and compared against existing scheduling schemes. © 2014 IEEE.

2014 20th National Conference on Communications, NCC 2014

Class based priority scheduling to support Machine to Machine communications in LTE systems

User Equipments (UEs) are integrated with multiple interfaces to facilitate the usage of various wireless technologies. However, due to the limitations of each technology, expected data rates are not achieved even when the best of available interfaces is chosen for data transfer. Link aggregation is used to aggregate data rates over multiple interfaces for achieving higher data rates. Even though there are multiple link aggregation schemes proposed, they are highly complicated and do not consider dynamics of wireless links. In this paper, we propose a simple and application layer Dynamic Link aggregation Scheme (DLAS) where data can be dynamically transferred through multiple links parallelly or sequentially. We tested the performance of the proposed DLAS schemes in NS-3 simulator and found that DLAS schemes achieve considerable improvement in the data rates in heterogeneous networks comprising of LTE and Wi-Fi technologies. In our experiments for 10 UEs, DLAS achieved 65% improvement in maximum achievable throughput when compared to an existing application layer link aggregation technique. © 2014 IEEE.

IEEE CONECCT 2014 - 2014 IEEE International Conference on Electronics, Computing and Communication Technologies

A Dynamic Link aggregation Scheme for heterogeneous wireless networks

Perpetually rising energy costs are forcing research communities to focus their efforts on a reduction of the global CO2 footprint, and since Information and Communication Technologies (ICT) account for a significant percentage of the overall global energy consumption, energy efficiency is becoming increasingly important in the operation of ICT infrastructure, especially in enterprise and data center networks. Simultaneously, the proliferation of devices such as smartphones and tablets, which have to use battery powered wireless radio adapters, and whose battery life is dependent on the power consumption of the radio adapters used for wireless communication indicates that efficient radio power saving strategies are needed to increase the battery life of such devices. This paper extends an earlier proposal by [1], and examines the performance of the same on IEEE 802.11n networks. It also extrapolates the results to estimate performance on 802.11ac WLANs, the planned successor to 802.11n WLAN in 5 GHz unlicensed band. The results indicate that this approach can be used to save over 59% of the RX energy (i.e., energy consumed by Wi-Fi radio while operating in receive mode) without any loss whatsoever in throughput unlike 802.11 power save mode and that this approach is completely backward compatible. © 2014 IEEE.

Ubersleep: An innovative mechanism to save energy in IEEE 802.11 based WLANs

A family F of permutations of the vertices of a hypergraph H is called pairwise suitable for H if, for every pair of disjoint edges in H, there exists a permutation in F in which all the vertices in one edge precede those in the other. The cardinality of a smallest such family of permutations for H is called the separation dimension of H and is denoted by π(H). Equivalently, π(H) is the smallest natural number k so that the vertices of H can be embedded in ℝk such that any two disjoint edges of H can be separated by a hyperplane normal to one of the axes. We show that the separation dimension of a hypergraph H is equal to the boxicity of the line graph of H. This connection helps us in borrowing results and techniques from the extensive literature on boxicity to study the concept of separation dimension. © Springer International Publishing Switzerland 2014.