N. Sarat Chandra Babu

Design and Implementation of a Prototype Smart PARKing (SPARK) System Using Wireless Sensor Networks

With the rapid proliferation of vehicle availability and usage in recent years, finding a vacant car parking space is becoming more and more difficult, resulting in a number of practical conflicts. Parking problems are becoming ubiquitous and ever growing at an alarming rate in every major city. Lot of research and development is being done all over the world to implement better and smarter parking management mechanisms. Widespread use of wireless technologies paired with the recent advances in wireless applications for parking, manifests that digital data dissemination could be the key to solve emerging parking problems. Wireless Sensor Network (WSN) technology has attracted increased attention and is rapidly emerging due to their enormous application potential in diverse fields. This buoyant field is expected to provide an efficient and cost-effective solution to the effluent car parking problems. This paper proposes a Smart Parking (SPARK) Management System based on wireless sensor network technology which provides advanced features like remote parking monitoring, automated guidance, and parking reservation mechanism. The paper describes the overall system architecture of SPARK from hardware to software implementation in the view point of sensor networks. We implemented a full-fledged prototype system for parking management to realize the design functionalities and features mentioned. Our preliminary test results show that the performance of this WSN based system can effectively satisfy the needs and requirements of existing parking hassles thereby minimizing the time consumed to find vacant parking lot, real-time information rendering, and smart reservation mechanisms.

A Hybrid Recommender System Using Weighted Ensemble Similarity Metrics and Digital Filters

Recommender Systems aim to predict the rating or preference of a user given to an item and provide suggestions of further resources that are likely to be of interest. The critical part of the recommender algorithm is finding the similarity metrics, which yield predictions with different accuracies and varieties. In the case of high dimensional feature space, the recommender systems using traditional similarity metrics suffer from several problems such as cold-start problem, scalability, over-specialization and data imbalance. In this paper, a recommender system using weighted ensemble hybrid similarity metric model is proposed by combining two or more traditional similarity metrics such as Pearson correlation, log-likelihood and Tanimoto coefficient. The digital filter is extended and adapted in order to handle the posterior intractability and spatial smoothing of high dimensional recommender space. The proposed recommender system is implemented using Apache Mahout. The evaluation of the model has been done using three large MovieLens datasets consist of 100 thousand ratings, 1 Million ratings and 10 Million ratings. We provide a quantitative and a qualitative evaluation. Interesting conclusions were extracted from the real-time execution of the proposed system on the above-mentioned data sets. The comparison with the results obtained from the traditional recommender systems shows that the proposed system achieved significant improvement in the accuracy for large data sets.

Linux bonding approach for heterogeneous networks

Our proposed solution is a Linux bonding approach to vertical handoff for heterogeneous networks. Currently, there are approaches of Linux bonding implementation for wired & wireless interfaces. The Linux bonding provides methods to aggregate multiple wired or wireless interfaces to support fault-tolerance and throughput improvement. The existing interface bonding allows the aggregation of homogeneous wired or wireless interfaces. There is no heterogeneity available in bonding of various interfaces together, such as Ethernet, WLAN etc. We are particularly interested in using the Linux bonding to bond multiple wireless and wired interfaces in order to achieve faster vertical handoff by providing heterogeneity. In this paper, we propose a daemon that accomplishes the handoff process between various radio interfaces both wired & wireless supporting IP. This daemon runs at the user level of the Linux Operating System and the results show that the handoff is significantly faster for all applications.

Keynote 1: Internet of Things(IoT) and augmented reality for e-learning

With the advent of the Internet of Things (IOT) technology, we will be expecting all the smart devices around us to provide various services in real-time. When this IoT technology is combined with Augmented Reality (AR), it will provide end users with real time as well as real world information. One of the prime advantages of AR combining with IoT is the bridging of the gap between the real and digital worlds around us. The ease of downloading features and scope of dynamic usage which AR brings to the smart devices and is expected to bring to the IoT is beyond human imagination! The education sector is expected to gain significantly using these technologies. The goal of technology in education is to make, learning easier, faster and more engaging for the students and to equip the instructor with powerful tools to provide more relevant courseware to their students. With introducing AR in education, we shall be able to provide contextually aware, more relevant, engaging and interactive courseware to the students, which would keep them interested in subject. Also, through IoT, the physical devices can provide context that the AR ecosystem would use for contextually aware rendering of multimedia content. Medical education domain is expected to gain significantly using IOT and AR. It is also observed that the training in the areas of equipment maintenance could gain significantly by applying these technologies judiciously. For eg. The conventional software virtual lab solution does not provide a real feel of performing an experiment. However, using IOT and AR technology, a sensor enabled Hardware based real lab environment can be created for performing the volumetric analysis experiments in chemistry by using WATER instead of Chemicals. C-DAC has developed few AR products in education domain — AR Board, AR Book and AR Game. AR Board is a virtual writing board on which a user can write with a laser pointer. It uses projection based AR Technology by creating a virtual environment for contextual information presentation, and facilitates real-time interaction with the content. AR Book is a standard book that has been instrumented with AR markers printed, which when scanned would show augmented, 3D interactive content, videos, audio and animations contextually, on a printed book, thus adding new dimensionality to it. AR Game is a game based learning mobile application that can be used by students for learning through playing, and for evaluating their knowledge. The technology of these products has been transferred to industry for their further development and proliferation to various educational institutes.

Implementation of learning analytics framework for MOOCs using state-of-the-art in-memory computing

MOOC aims at delivering online courses to tens of thousands to millions of heterogeneous learners at the same time, with minimal or no charge. It provides an alternate way to disseminate quality education to the section of people who cannot reach premier institutions. It has great potential to overcome the barriers of traditional learning systems. However, there are several challenges in MOOCs such as huge drop-out rates, improper automated assessments, varied student engagement, and attention etc. Learning Analytics helps us to contain such issues. Learning analytics, with the help of Big Data Technologies, helps us to interpret humongous MOOCs data to assess progress, predict performance and identify problems. To perform analytics, we developed a workflow using Apache Spark, a scalable inmemory computing framework. The data from edX platform has been used for experiments. It contains the information of more than 2 Lakh students from 39 courses. Initially, detailed statistical analysis has been carried out to understand the learning patterns and the behavior of online learners. Later, we have developed drop-out prediction models using various machine learning algorithms such as Random Forest, Gradient Boost, and Logistic Regression. A stacked ensemble model is developed and performance comparison with baseline models is carried out. It outperformed all other models with an accuracy of 91.2%.

GARUDA: Pan-Indian distributed e-infrastructure for compute-data intensive collaborative science

GARUDA is a nation-wide grid of computational nodes, mass storage and scientific instruments with an aim to provide technological advancements required to enable compute-data intensive, collaborative applications for the twenty-first century. From a Proof-of-Concept, the GARUDA has evolved to an operational grid, aggregating nearly 70TF-15TB compute–storage power, via high-speed National Knowledge Network and hosts a stack of middleware and tools to enable hundreds of users from diverse communities like life science, earth science, computer aided engineering, material science, etc. Evolution and confluence of research and technologies has led to the maturity of GARUDA grid: there have been addition of several hundred CPUs, large data stores, standardization of grid middleware, research on interoperability between grids and participation from varied application communities that have made significant impact to GARUDA. The GARUDA partner institutes are using this e-infrastructure to grid enable applications of societal and national importance. The authors in this paper present the manner of building a nation-wide operational grid and its evolution, its deliverables, architecture and applications.

Fault Diagnosis of Analog Circuits Utilizing Reconfigurable Computing System

Advances in the field of Integrated Circuits (ICs) has resulted in high density Very Large Scale Integrated (VLSI) chips comprising of both digital and analog components onto a single chip. Consequently, testing of these ICs with analog and digital components are challenging and time consuming. Moreover, the techniques available for testing analog components when compared to digital are less and also difficult. This paper describes a approach of utilizing Field Programmable Gate Arrays (FPGAs) for fault diagnosis of analog circuits describing the technique of Reconfigurable Computing Systems (RCS). The paper provides a brief about Fault diagnosis, FPGAs and utilization of FPGAs for RCS followed with the approach of the research. In summary the paper provides a brief about utilizing a digital hardware to perform testing of analog cicuits.

A transparent end-to-end security solution

Looking through the past couple of decades in information security we can say that sophistication and advancements are not limited to information security solutions alone but also in parallel applies to cyber exploits and crimes which have grown both in number and in their capacity to create havoc in cyber space. Originated in the form of malicious code and unauthorized access, cyber security threats have come a long way, today posing threats to end systems and applications. This resulted in an exponential growth in end systems and application security threats.In this paper we present a new approach to address end-to-end security issues. This security solution is designed to be transparent to applications, offering flexibility to deploy any cryptographic algorithm and also providing features for efficient administration.