Seminar Topics

Submitted by Presil K K Roll no: 36

The ultimate signature identifier

Abstract

Biometric identification is the need of hour, as automatic recognition systems are such biometric techniques to look upon. Accurate automatic recognition systems are important for a wide range of applications such as banks, restricted areas, government classified areas etc. As traditional identity recognition methods such as pins, passwords etc. suffer from some serious flaws and are unable to satisfy the security requirements this has become a field of great importance. Biometrics consists of methods for uniquely recognizing humans based upon one or more intrinsic physical or behavioral traits. In computer science, in particular, biometrics is used as a form of identity access management and access control. Although you may not think about it, your driver's license contains biometric information about you. Your height, weight, hair color and eye color are all physical characteristics that can easily be checked. However, your height changes with age (18 years old drivers get taller, senior citizens get shorter). Your hair color changes naturally (and on purpose). You can wear colored contact lenses that change your eye color; everyone's weight fluctuates over time. Now by using biometric identification we mean to look for biometric data that does not change over the course of your life; that is, they look for physical characteristics that stay constant and that are difficult to fake or change on purpose. It is also used to identify individuals in groups that are under surveillance. The paper aims to consider a more reliable biometric feature, signature verification for the considering. The paper presents an experimental comparison of different signature verification methods. It can be effectively employed to reduce the risk of forgery by releasing the trouble of carrying ATM cards by the users, by employing a signature verification system. The paper compares four of the most extremely efficient methods used for signature verification like CDTW (Continuous Dynamic Time Warping), DTW (Dynamic Time Wrapping), Vector Quantization followed by HMM (Hidden Markov Model) employed for signature verification and the best method was stated. The paper also aims at improving the efficiency by integrating the methodologies introduced in the paper with each other. The

methods were tested on synthetic and further applied on real time signature datasets. It is proved that superiority is achieved by combination of different methods.
References: 1. http://ieeexplore.ieee.org/search/freesrchabstract.jsp? tp=&arnumber=5941654&queryText%3Dthe+ultimate+signature+identifier %26openedRefinements%3D*%26searchField%3DSearch+All 2. http://www.technovelgy.com/ct/Technology-Article.asp?ArtNum=10

Paper details: Authors: Singh, Amarjot Choubey, Akash Bandaru, Sreedhar Mohan, Lalit Dhiman, Mohit Dept of Electrical Engineering, NIT Warangal Warangal, India Issue Date: 8-10 April 2011 Date of Current Version: 07 July 2011

Nano robotics as medicament: (Perfect solution for cancer)

Abstract Nanorobotics is the emerging technology field of creating machines or robots whose components are at or close to the microscopic scale of a nanometer (109 meters). More specifically, nanorobotics refers to the nanotechnology engineering discipline of designing and building nanorobots, with devices ranging in size from 0.1-10 micrometers and constructed of nanoscale or molecular components. Since nanorobots would be microscopic in size, it would probably be necessary for very large numbers of them to work together to perform microscopic and macroscopic tasks. The integration of nanotechnology into medicine is likely to bring some new challenges in medical treatment. Let us peep inside the real world of NANOTECHNOLOGY. Nanorobot is a wonderful vision of medicine in the future. The most advanced nanomedicine involves the use of nanorobots as miniature surgeons. Advancement in nanotechnology may allow us to build artificial red blood cells called Respirocytes capable of carrying oxygen and carbon dioxide molecules (i.e, functions of natural blood cells). The artificial red blood cell or "respirocyte" proposed here is a bloodborne spherical 1-micron diamondoid 1000-atm pressure vessel with active pumping powered by endogenous serum glucose, able to deliver 236 times more oxygen to the tissues per unit volume than natural red cells and to manage carbonic acidity. An onboard nanocomputer and numerous chemical and pressure sensors enable complex device behaviors remotely reprogrammable by the physician via externally applied acoustic signals. Respirocytes can provide a temporary replacement for natural blood cells in the case of an emergency. Thus respirocytes will literally change the treatment of heart disease. We can envision a day when you could inject billions of these nanorobots that would float around in your body. One of the most realistic and nearly feasible achievements is the cure for cancer which is

one of the main focuses of this work. Nanorobots could carry and deliver large amounts of anticancer drugs into cancerous cells without harming healthy cells, reducing the side effects related to current therapies. These nanorobots will be able to repair tissues, clean blood vessels and airways, transform our physiological capabilities, and even potentially counteract the aging process. Other applications include transfusable blood substitution; partial treatment for anemia, perinatal/neonatal and lung disorders; enhancement of cardiovascular/neurovascular procedures, tumor therapies and diagnostics; prevention of asphyxia; artificial breathing; and a variety of sports, veterinary, battlefield and other uses.
References: 1. http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=5706153 2. http://www.foresight.org/Nanomedicine/Respirocytes.html

Paper details: Authors: Hariharan, R.; Manohar, J.,St. Peter's Univ., Chennai, India Issue Date: 3-5 Dec. 2010 Date of Current Version: 31 January 2011

A Multi-Agent Memetic System for Human-Based Knowledge Selection

Abstract

In these last decades, both industrial and academic organizations have used extensively different learning methods to improve humans' capabilities and, as consequence, their overall performance and competitiveness in the new economy context. However, the rapid change in modern knowledge due to exponential growth of information sources is complicating learners' activity. At the same time, new technologies offer, if used in a right way, a range of possibilities for the efficient design of learning scenarios. For that reason, novel approaches are necessary to obtain suitable learning solutions which are able to generate efficient, personalized, and flexible learning experiences. From this point of view, computational intelligence methodologies can be exploited to provide efficient and intelligent tools to be able to analyze learner's needs and preferences and, consequently, personalize its knowledge acquirement. This paper reports an attempt to achieve these results by exploiting an ontological representation of learning environment and an adaptive memetic approach, integrated into a cooperative multiagent framework. Memetics is a new science that has attracted increasing attentions in the recent decades. Beyond the formalism of simple hybrids, adaptive hybrids and memetic algorithms, the notion of memetic automaton as an adaptive entity that is self-contained and uses memes as building blocks of information is recently conceptualized in the context of computational intelligence as potential tools for effective problem-solving In particular, a collection of agents analyzes learner preferences and generate high-quality learning presentations by executing, in a parallel way, different cooperating optimization strategies. This cooperation is

performed by jointly exploiting data mining via fuzzy decision trees, together with a decisionmaking framework exploiting fuzzy methodologies.
References: 1. http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=5735234 2. http://www.c2i.ntu.edu.sg/Courses/papers/conference/CEC2011_MemeticAuto maton.pdf

Paper details: Authors: Acampora, G.; Cadenas, J. M.; Loia, V.; Muoz Ballester, E.,G. Acampora and V. Loia are with the Department of Mathematics and Computer Science, University of Salerno, 84084 Salerno, Italy. Issue Date: 22 March 2011