Sunil Karamchandani

OCR-based chassis-number recognition using artificial neural networks

The automatic detection and recognition of car number plates has become an important application of artificial vision systems. Since the license plates can be replaced, stolen or simply tampered with, they are not the ultimate answer for vehicle identification. The objective is to develop a system whereby vehicle identification number (VIN) or vehicle chassis number is digitally photographed, and then identified electronically by segmenting the characters from the embossed VIN. In this paper we present a novel algorithm for vehicle chassis number identification based on optical character recognition (OCR) using artificial neural network. The algorithm is tested on over thousand vehicle images of different ambient illumination. While capturing these images, the VIN was kept in-focus, while the angle of view and the distance from the vehicle varied according to the experimental setup. These images were subjected to pre-processing which comprises of some standard image processing algorithms. The resultant images were then fed to the proposed OCR system. The OCR system is a three-layer artificial neural network (ANN) with topology 504-600-10. The major achievement of this work is the rate of correct identification, which is 95.49% with zero false identification.

Principal component analysis based backpropagation algorithm for diagnosis of peripheral arterial occlusive diseases

Impedance cardio-vasography (ICVG) serves as a non-invasive screening procedure prior to invasive and expensive angiographic studies. Parameters like Blood Flow Index (BFI) and Differential Pulse Arrival Time (DPAT) at different locations in both lower limbs are computed from impedance measurements on the Impedance Cardiograph. A Backpropagation neural network is developed which uses these parameters for the diagnosis of peripheral vascular diseases such as Leriches syndrome. The target outputs at the various locations are provided to the network with the help of a medical expert. The paper proposes the use of Principal Component Analysis (PCA) based Backpropagation network where the variance in the data is captured in the first seven principal components out of a set of fourteen features. Such a Backpropagation algorithm with three hidden layers provides the least mean squared error for the network parameters. The results demonstrated that the elimination of correlated information in the training data by way of the PCA method improved the networks estimation performance. The cases of arterial Narrowing were predicted accurately with PCA based technique than with the traditional Backpropagation Technique. The diagnostic performance of the neural network to discriminate the diseased cases from normal cases, evaluated using Receiver Operating Characteristic (ROC) analysis show a sensitivity of 95.5% and specificity of 97.36% an improvement over the performance of the conventional Backpropagation algorithm. The proposed approach is a potential tool for diagnosis and prediction for non-experts and clinicians.

Application of crisp and fuzzy clustering algorithms for identification of hidden patterns from plethysmographic observations on the Radial Pulse

Radial Pulse forms the most basic and essential physical sign in clinical medicine. The paper proposes the application of crisp and fuzzy clustering algorithms under supervised and unsupervised learning scenarios for identifying non-trivial regularities and relationships of the radial pulse patterns obtained by using the Impedance Plethysmographic technique. The objective of our paper is to unearth the hidden patterns to capture the physiological variabilities from the arterial pulse for clinical analysis, thus providing a very useful tool for disease characterization. A variety of fuzzy algorithms including Gustafson-Kessel (GK) and Gath-Geva (GG)have been intensively tested over a diverse group of subjects and over 4855 data sets. Exhaustive testing over the data set show that about 80 % of the patterns are successfully classified thus providing promising results. A Rank Index of 0.7739 is obtained under supervised learning, which provides an excellent conformity of our process with the results of plethysmographic experts. A correlation of the patterns with the diseases of heart, liver and lungs is judiciously performed.

Dual band M-shaped UWB patch antenna for Wireless Body Area Networks

Increased health awareness in people and evolution of wearable computing, has unarguably attracted heightened interest and potential in development of comprehensive and practically feasible Wireless Body Area Networks (WBAN). The paper reports on the full realization of ‘M’ shaped dual band on-body antenna for wireless body area networks operating in the ultra wide band range. The resonant bands are obtained in the frequency range of 5.47 to 5.68 GHz and 6.15 to 6.23 GHz offering a bandwidth of 200 and 80 megahertz respectively. Experimental results of the proposed antenna are demonstrated on universal software radio peripheral kit with a dual, frequency shift keying — frequency modulation. The input impedance, antenna efficiency, directivity, gain and radiation efficiency of the proposed antenna are72 Ω, 64 %, 7.30 dBi, 3.521 dBi and 75 % respectively. Furthermore, the compact size and negligible on body radiation makes it an ideal choice for operation in WBAN environment. Comparison with the existing dual band ‘E’ and ‘V’ shaped antennas vouches a strong candidature for the proposed architecture.

Parallel support vector architectures for taxonomy of radial pulse morphology

Application of impedance plethysmography (IP) for impedance measurement is the paradigm in assessment of central and peripheral blood flow. We propose the expediency of IP to unearth hidden patterns from Plethysmographic observations on a radial pulse. The variability analysis in one thousand control and disease subjects evolves an archetype of eight different morphological patterns. The peripheral pulse waveforms not only characterize the physiology of control subjects, but also define the morphology of patients suffering from Myocardial Infarction, cirrhosis of liver, and disorder of lungs. Diverse parallel support vector machine (pSVM) topologies are designed as an aid to the physician for multiclass pattern recognition problem. Besides a lowest confusion coefficient (0.133), the PCA-based pSVM classifier offers a comparatively higher generalized correlation coefficient and κ value of 0.6586 and 0.8407, respectively. However, the ROC characteristics and the benchmark parameters suggest that wavelet-based pSVM is the optimum classifier with a sensitivity of 85.33 %, an elevated MCC (0.69), and a least upper bound on the expected error. pSVM stands out as a model classifier as compared with identified indices such as, Fishers Ratio, Morphology Index, and Heart rate variability.

tuPOY: Epitomizing a New Epoch in Communications With Polymer Textiles

The paper presents a new paradigm from the perspective of pervasive on-body computing through an innovative polymerized textile, which exhibits sensing and radiation properties. A radical, first of its kind, sensor fabricated from unsaturated polymer resin textile, establishes a dynamic link connecting human thermodynamics to electrical ambiance. A dynamic fabrication process of esterification and η-polymerization is developed, which is articulately arrested using an innovatively formulated retardant, yielding a permanent thermally unstable partially oriented yarn (tuPOY). A prudently established nontrivial interchange phenomenon is founded, presenting an inimitable calibration mechanism of the sensors and charting a novel relationship of exuberated energy to lattice kinetics of tuPOY. This meticulously researched conducting medium of tuPOY, fabricated from aromatic polyamides, also presents an avant-garde architecture for proliferation of electrical and thermal signals concomitantly between the sensors and its transmission circuit. A power generating unit (PGU) delineates the power mining from thermal energy dissipated from the body, presenting a new dimension in operational power dynamics. A textile composite antenna is premeditated exclusively from radiating tuPOY-based patch and substrate, an archetype reporting in published literature. The judiciously designed antenna, with tuPOY coupled as its patch, and substrate operate as shields against the radiations directed towards the body leading to a self-sustained sculpt. The back-end hardware of the test setup conceptualizes an automated physician machine (APM) presenting a standalone architecture. The artificial intelligence core of APM is modeled on weighted multiclass support vector machines (wmSVMs). The capturing of signal variations, devoid of any metallic components, presents a singular facet of research and amalgamates various interdisciplinary fields, while providing a robust architecture with minimum tradeoffs.

Non-invasive, reflection coefficient based channel estimation on PLC systems

The major advantage of a PLC system is the unification of the communication architecture into a singular medium. In our efforts towards this unification, we propose a non-invasive, reflection coefficient based channel estimation technique over low voltage powerlines. The novel model accounts for all the parameters of the signal viz., quality, strength, attenuation etc., by simplistic inference from the measured magnetic field intensity. To validate the proposed model experimental results are conducted over real time low voltage PLC architecture. Results of the extensively measured values are compared with its respective actual conditions. We obtain an average accuracy of 97.61 %, 97.49 %, and 97.86 % for the varying frequency, load and voltage profiles, respectively. The proposed model is further compared with three existing PLC models. We attain a mean error of 2.5 % which is lower than all the existing models, thus promising a strong candidature for PLC systems.

tuPOY in Future of Computing: Internet of Things and Ubiquitous Sensing

The utilitarian proficiency of tuPOY is exploited in an environment of internet of things in this chapter. Use of tuPOY in pervasive environments is presented as a case study. Devices made of tuPOY, seamlessly integrated in the ubiquitous environment, are detailed with explicitly designed experimental test beds in this chapter. These devices are shown to compute, communicate, and have embedded intelligence in them. The chapter illustrates the functionality of tuPOY as a bridge between the physical and digital worlds. These applications advocate and give an insight into the logical processing capabilities of the innovative material. tuPOY as a diode, a transistor, an amplifier, and in general the heart of the next generation processor takes the invention to its eventual conclusion and lays down it future endeavors.

Thermal Unstability Analysis

The physics of tuPOY in relation to its molecular structure forms the essence of this chapter. The manufacturing process is experimentally and theoretically justified by a variety of spectroscopical imaging, nonimaging, and micro graphical procedures. These techniques provide us with a physical insight into the conducting and radiating behavior of tuPOY. The juxtaposition of these investigations outlines the mechanism of tuPOY as the next generation processing element.

Manufacturing Process of Thermally Unstable Partially Oriented Yarns

The metamorphosis of tuPOY from basic organic raw materials to an advanced conducting fiber having metallic properties is discussed in this chapter. A step by step process of embedding conduction and radiation properties in tuPOY, with an elaborated stagewise analysis is presented. The production process is justified with parametric evaluation and analysis. Production process flow from a commercial manufacturing viewpoint is outlined.