Paper submission deadline extended

Abstracts

Abstract :

Deep Learning has become a rapidly growing research area, redefining state-of-theart performances in a wide range of applications such as object recognition, image segmentation, speech recognition, natural language processing etc. Considering the capability of deep learning to address largescale data and learn high-level representation, deep learning can be a powerful and effective solution for real world challenges in object recognition. Object recognition facilitates many applications, ranging from indoor to outdoor, such as surveillance, security, counting etc. It aims to find and identify objects in a given image. For this purpose, image quality plays a very important role. The image inferior in quality may lead to poor results and thereby degrade the performance of an entire application. The quality degradation can occur due to several noises and environmental effects. Various methodologies exist in the literature which deals with such images.
Recognition of objects in outdoor scenes may degrade during image acquisition and transmission due to various noises and environmental factors such as haze, fog etc. It causes contrast reduction, colour fading, loss of features and many more.

By:

Dr. Nischal K. Verma
Indian Institute of Technology, Kanpur.

Abstract :

Recycling environmental waste can avoid many hazardous environmental scenarios and save our resources. Our aerogel technology can recycle various environmental wastes to high-value engineering materials. Common paper, fabric and plastic wastes are selected to develop the lightest aerogel materials for novel applications such as oil-spill cleaning, heat and sound insulation, winter garment materials, packaging, CO2 filtering, personal care and medical products.
Using an cost-effective and green sol gel technique with no toxic solvents and cross-linkers, recycled fibres from the wastes are converted into ultralight porous, biodegradable and non-toxic aerogels. Our method uses 70% less energy and results in reduced polluting emissions into the air and water. It is also faster as the entire process takes only 8 hrs to 1 day. This is 20 times faster than current commercial processes. Thus we can significantly reduce manufacturing and equipment costs. The manufacturing cost of an A4-size aerogel sheet is approx. US$0.5-2.0, much cheaper than commercial Aspen aerogels for heat insulation or commercial sorbents for oil spill cleaning. The developed aerogels are highly compressible for the first time; hence storage and transportation costs are greatly reduced. The compressed aerogels can very quickly recover 97 % of their original size when placed in water. The used aerogels can be recycled so no waste is disposed to the environment.
The above highly compressible, cost-effective and biocompatible hybrid aerogel pellets can be easy integrated into a clinical syringe to be used as a haemorrhage control device. Each compressed aerogel pallet can expand in volume to 16 times its size in 4.5 seconds, 3 times faster than commercial haemorrhage devices, while retaining their structural integrity. The fast aerogel expansion also exerts high pressure to stop the wound bleeding within 5 seconds.
The aerogel surface can be functionalized effectively by the nanocoating method at low temperature for the above-mentioned applications. For example, the MTMS-coated aerogel can absorb oil 99 times of their dry weight and 4 times as effective as commercial oil sorbents. They can be reused several times and can be recovered by squeezing out over 99 % of oil absorbed. At the end of their useful life, the used aerogel can be safely ground into fine particles and discarded. This potential market has been estimated at US$143.5 billion. With amine group coating, the amine-coated aerogels can absorb large amounts of CO2 from air. Also with fire retardant coating, the aerogels can withstand an ambient temperature of 600-620 oC and prevent fire from spreading inside buildings. The potential market of thermal insulation is US$3.3 billion globally. Beside the heat and sound insulation of the buildings, we also developed successfully a lightweight thermal jacket using aerogels, to insulate water bottles, to maintain the temperature of ice slurry at -1oC for 4 hours. A thermal jacket consists of an aerogel layer embedded within common fabrics to provide effective heat insulation. The aerogel-insulated bottle offers better heat insulation performance than commercial FLOE bottles and is highly comparable to that of vacuum flasks, but at a fraction of the cost.

By:

HAI M. DUONG
Associate Professor, Department of Mechanical Engineering National University of Singapore (NUS), Singapore.

Abstract :

Rapid advance of various technologies associated with unmanned aerial vehicles (UAVs) has enabled many complex tasks to be carried out autonomously with no human intervention. UAVs can be deployed for numerous applications such as reconnaissance and surveillance, traffic monitoring, detection and containment of hazardous leakages in industries and so on. Both hovering capability and agility of quad-copter UAVs (popularly known as “drones”) comes very handy in many of these applications. However, for harnessing the true potential, it is quite obvious that drones should have a good built-in mechanism and associated guidance logic to autonomously land successfully and on the designated target with high precision.
This talk will essentially present a bio-inspired Tau-guidance approach for smooth and precision landing of drones. The approach is essentially based on the Tau theory, which has been established by studying the landing behaviour of birds, thereby generating a desired reference trajectory. Next, the differential geometric (dynamic inversion) philosophy is used to generate the necessary guidance commands to the drone. Experimental studies were performed using commercially available low-cost AR-Drone. To overcome the navigational error associated with the sensors, built-in monocular SLAM (Simultaneous Localization And Mapping) and INS (Inertial Navigation System) data were fused using a Kalman Filter, which improved the navigation accuracy remarkably. To improve the accuracy even further in the final terminal area, the landing site was supported by a range-sensing Kinect camera. With this low-cost navigation solution, hardware experimental results show that autonomous landing of drones is possible with high precision using the bio-inspired Tau-theory. Details of the Tau-guidance philosophy and the results obtained will be presented in this talk.

By:

Prof. Radhakant Padhi
IISC, Bangalore

Abstract :

This paper briefly discusses some important energy problems facing the third world countries and presents the current electric generation scenario in most of the developing countries with facts and figures in respect of India. It is hoped that, with systematic, advance planning, through measures like co-generation, energy management, and energy conservation, the electric energy supply scenario of AD 2020 will be free of the perennial problems of power shortages, voltage fluctuations etc. Also , problems will be solved using soft computing techniques such as ANN , Fuzzy Logic , GE , PSO etc.

By:

D.P.Kothari,
FNAE, FNASc, FNAE, FIE(I), Fellow-IEEE, Hon Fellow – ISTE, FIETE
Director Research , Waingangā College of Engineering & Management , Nagpur.

Abstract :

The social group optimization algorithm is recently developed population based algorithm by Satapathy et al .It mimics the social behavior of the human beings in the society. The problems encountered in the society are generally non-linear and complex in nature. Typically, every individual uses their behavioral traits to solve such problems. It is also possible that the individuals may form in groups to solve some complex problems which cannot be solved with the knowledge possessed by an individual. This group formation facilitates the knowledge exchange or sharing that allows solving complex problems which require a high degree of knowledge coefficient. The knowledge coefficient of an individual and his capability to solve a problem or execute a task in life is composed of several behavioral traits of the individual itself. Some of these behavioral aspects are loyalty, fairness, team play, braveness etc.The negative shade like disloyalty of loyalty and other aspects are also listed under these traits. Based on the above aspect SGO is developed. In this talk its effectiveness to solve many optimization functions will be shown and some applications to data engg. will be discussed.

By:

Suresh Chandra Satapathy
KIIT Deemed to be University, Bhubaneswar