Indian Institute of Technology Palakkad&nbsp;(IIT Palakkad or IIT PKD) is a public autonomous&nbsp;engineering&nbsp;and&nbsp;research&nbsp;institute located in&nbsp;Palakkad,&nbsp;Kerala. It was&nbsp;one of the five new&nbsp;IITs&nbsp;proposed in the&nbsp;2014 Union budget of India. The campus was inaugurated on 3 August 2015. The institute has 94 faculty, 978 students, and 63 non-teaching staffs.

IT Palakkad currently offers four-year Bachelor of Technology (B.Tech) and two years MS programmes in 8 different engineering disciplines including&nbsp;Computer Science, Electrical, Mechanical, Civil among others.

&nbsp;

IIT Palakkad

Department of Computer Science and Engineering

World University root node

Distributed Graph Analytics

Introduction to Graph Analytics

Efficient Parallel Implementation of Graph Algorithms

Similar facts are often expressed in different ways in natural language text, which introduces the redundancy and ambiguity of Subject-Predicate-Object (SPO) triples in Open Information Extraction (Open IE). This work focuses on canonicalizing such SPO triples. We propose a clustering framework using non-negative matrix tri-factorization that jointly clusters predicate phrases and subject-object pairs and aligns them in a meaningful manner. The evaluation shows that our co-clustering method outperforms significantly over rule mining and Knowledge-Base-embedding approaches for two existing datasets.

Department of Data Science

PervasiveHealth: Pervasive Computing Technologies for Healthcare

Co-clustering triples from open information extraction

Quantities are more than numeric values. They represent measures for entities, expressed in numbers with associated units. Search queries often include quantities, such as athletes who ran 200m under 20 seconds or companies with quarterly revenue above $2 Billion. Processing such queries requires understanding the quantities, where capturing the surrounding context is an essential part of it. Although modern search engines or QA systems handle entity-centric queries well, they consider numbers and units as simple keywords and therefore fail to understand the condition (less than, above, etc.), the unit of interest (seconds, dollar, etc.) and the context of the quantity (200m race, quarterly revenue, etc.) As a result, they cannot generate the correct candidate answers. In this work, we demonstrate a prototype QA system, called Qsearch, that can handle advanced queries with quantity constraints using the common cues present in both query and the text sources.

WSDM 2020 - Proceedings of the 13th International Conference on Web Search and Data Mining

Entities with quantities: Extraction, search and ranking

This work aims to economically evaluate centralized and decentralized Sewage Treatment Plants (STPs) for a metropolitan city. For the same, centralized and decentralized wastewater treatments for a catchment area in Sharjah city (United Arab Emirates) were evaluated by Net Present Value (NPV) method. Three options meeting local government regulations were considered for the catchment. Options 1 and 2 were centralized, and Option 3 was decentralized. Option 1 was about connecting the catchment to the existing centralized STP location, Option 2 to connect the catchment to the new proposed location which may be situated at the lowest point around the catchment area, and Option 3 involved constructing three decentralized STPs. The results showed that Option 3 had the lowest NPV of costs including CAPEX and OPEX for 25 years. There was a saving in Option 3 of around 44% compared to Option 1, and 23% compared to Option 2. This finding is useful for engineering managers for infrastructure planning for a metropolitan city like Sharjah city. © IEOM Society International.

Department of Civil Engineering

Proceedings of the International Conference on Industrial Engineering and Operations Management

Centralized versus decentralized sewage treatment plant in a Metropolitan city

The concept of Public Private Partnerships (PPP) Projects is a widely used method of executing infrastructure projects around the world, where it utilizes the private sector's contribution to benefit both the public agency as well as the private sector implementing the project. The PPP project delivery methods are relatively new to the developing middle-eastern region generally, and to the UAE specifically and there has been very few completed PPP Projects. This paper aims towards investigating risks related to the PPP Projects by ranking such risks in order of importance and rate of occurrence. To achieve this task, relevant data that would contribute to the analysis of the risks are collected. The method of data collection for this paper was a series of surveys and semi-structured interviews directed towards informed targets representing the different stakeholders of PPP projects such as Private Proponent Managers, Federal Government Officers, Engineering Practitioners etc. The analysis of the survey results showed that the risks concerned with the private sector were significantly different than those concerned with the public sector. The research also concludes that proper risk mitigation measures must be implemented in order to optimize the process of utilizing the concept of PPPs in the UAE. © 2020 IEEE.

2020 Advances in Science and Engineering Technology International Conferences, ASET 2020

Investigation of Project Delivery Risks in Public-Private-Partnership (PPP) Infrastructure Projects in UAE - A Stakeholder's Perspective

Validation of network state of Network Function Virtualization Infrastructure (NFVI) under various uncertainties are of primary importance as they directly affect Service Function Chain (SFC) provisioning and its performance. SFC provisioning against the uncertainties, including variable traffic demand and failures of link and switch makes validation challenging because the number of scenarios to validate grows exponentially with the number of such failures. This letter takes advantage of a two-stage validation framework and proposes a validation strategy to verify the underlying NFVI network state that supports SFC provisioning despite various uncertainty in the network. We demonstrate the effectiveness of our strategy through different failure and SFC placement scenarios using realistic network topologies and traffic matrix. © 1997-2012 IEEE.

IEEE Communications Letters

Predicting Dynamic Network State of SFC Operation with Uncertainties

We study the joint probability distributions of separation R and radial component of the relative velocity VR of particles settling under gravity in a turbulent flow. We also obtain the moments of these distributions and analyze their anisotropy using spherical harmonics. We find that the qualitative nature of the joint distributions remains the same as no-gravity case. Distributions of VR for fixed values of R show a power-law dependence on VR for a range of VR; the exponent of the power law depends on the gravity. Effects of gravity are also manifested in the following ways: (a) Moments of the distributions are anisotropic; degree of anisotropy depends on particle's Stokes number, but does not depend on R for small values of R. (b) Mean velocity of collision between two particles is decreased for particles having equal Stokes numbers but increased for particles having different Stokes numbers. For the later, collision velocity is set by the difference in their settling velocities. © 2020 authors. Published by the American Physical Society.

Department of Physics

Physical Review E

Statistics of relative velocity for particles settling under gravity in a turbulent flow

Autonomous robots in the real world should avert collisions with pedestrians and react quickly to sudden changes in the environment. Most local planners rely on static environment maps that cannot capture such critical elements of uncertainty. Learning based methods for end-to-end navigation have become popular recently, but it is still unclear how to incorporate collision avoidance in a simple, safe and quick manner. We propose a reinforcement learning curriculum based on domain randomization to train a high performing policy entirely in simulation. The policy is first trained in a simple obstacle-free environment to quickly learn point to point navigation. The learned policy is transferred to a dynamic environment to learn collision avoidance. The key idea is to randomize the obstacle dynamics to obtain a robust planner that can be directly deployed to the real world. The resultant policy outperforms conventional planners in dynamic real world environments, even when the robot is intentionally obstructed. © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2020.

Department of Mechanical Engineering

Mechanisms and Machine Science

Crashing to Learn, Learning to Survive: Planning in Dynamic Environments via Domain Randomization

Electric discharge machining (EDM) is the most promising one to machine conductive materials irrespective of their hardness with good accuracy and precision. The plasma discharge phenomenon during EDM involves complex physics which needs to be understood. Several attempts are being tried by researchers in this direction but still, it required further efforts. The present study made to develop an FEA-based electrothermal model to simulate the temperature distribution and material removal rate in EDM of the aluminum alloy AA6061. The cylindrical disk-type heat source was assumed for the current model. To have more realistic machining conditions, the model has introduced a discharge current term in addition to discharge duration in defining the plasma radius and used the Gaussian heat flux. Also, both the conductive (due to plasma) and convective heat transfer (due to dielectric) modes were taken into consideration. The theoretical material removal rate (MRR) was estimated by assuming the cavity produced in the model as a hemispherical type. The EDM experimentation was performed on the AA6061 work material at similar electrical conditions used in the model. The experimental MRR was calculated from the weight difference (before and after machining) method. The results showed that the difference in theoretical (understated assumptions) and experimental MRR as 12%. The reasons for the MRR difference were also discussed in detail. © Springer Nature Singapore Pte Ltd. 2020.