RESEARCH AND PUBLICATION

Research

  1. tuPOY: Mathematical and Analytical Characterization : The mathematical characterization of a concept embeds a logical element in it, giving the invention a concrete structure. The conducting and radiating properties of tuPOY are given a mathematical emblem in this chapter. The behavioral pattern of tuPOY to a stimuli and its subsequent molecular state change variation due to its conduction, and radiation properties are mathematically modeled, providing an insight into its metallic behavior. A new mathematical concept of interchange phenomenon at molecular level is proposed to support the claims. The numerical manifestations spout a gamut of operations of tuPOY in technologies of future.
  2. https://djsceietesf.com/events/2018-19/matlab-workshop/
  3. Performance Evaluation of Machine Learning and Deep Learning Techniques for Sentiment Analysis
  4. Segmentation Techniques for Differential Variations in Fingerprint Images
  5. Score Formulation and Parametric Synthesis of Musical Track as a Platform for Big Data in Hit Prediction
  6. Performance comparison of orientation sensitive filters for low quality fingerprints
  7. Performance evaluation of variable and modified Gabor kernels for filtering of fingerprint images
  8. 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, non-imaging, 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.
  9. 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.
  10. tuPOY as a Radiating Element: Antenna: The ability of tuPOY to emit electromagnetic radiations provides a playground to envision its role in antenna and wave propagation. This chapter analyzes the radiating properties of tuPOY and its use an antenna. A prototype of a nonmetallic antenna with tuPOY as its integral part of the design is developed. The novel construction of the antenna structure highlights the fact that apart from ministering its inherent objectives, tuPOY antenna emanates as a standalone power source. The proposed structure is capable of not only being self-sustaining from immanently generated power but also providing residual power for networked devices as well.
  11. Gesture controlled wheelchair for quadriplegic children
  12. IEEE Video Processing and Visual Communications Special Session INDIAcom 2016, 18th March New Delhi
  13. Pervasive Monitoring of Carbon Monoxide and Methane using Air Quality Prediction: The first step towards pollution control is monitoring pollution. In this paper, we present an innovative way of pollution monitoring in which any person can see the pollution content of a specific area where the sensors are installed and take measures to control the same. A prototype for monitoring a few major gas pollutants like CO, CH4 along with the temperature variations in the surroundings has been implemented. The semiconductor gas sensors (MQ7, MQ4) were calibrated according to standard methods and interfaced with Raspberry Pi Model B+ using Python 2.7. The readings are displayed in real time and also recorded using an online analytics and data visualization tool, Plotly. This model can further be improved by adding more number of sensors to create a low cost and portable system for pollution monitoring.
  14. Biometric identification system using fingerprint and knuckle as multimodality features
  15. The mathematical characterization of a concept embeds a logical element in it, giving the invention a concrete structure: The conducting and radiating properties of tuPOY are given a mathematical emblem in this chapter. The behavioral pattern of tuPOY to stimuli and its subsequent molecular state change variation due to its conduction and radiation properties are mathematically modeled, providing an insight into its metallic behavior. A new mathematical concept of interchange phenomenon at molecular level is proposed to support the claims. The numerical manifestations spout a gamut of operations of tuPOY in technologies of the future.
  16. tuPOY in Future of Computing: Internet of Things and Ubiquitous Sensing The utilitarian proficiency of tuPOY is exploited in an environment of the internet of things in this chapter. Use of tuPOY in pervasive environments is presented as a case study. Devices made of tuPOY, seamlessly integrated with 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 its future endeavors.
  17. tuPOY: Thermally Unstable Partially Oriented Yarns: This book provides a new direction in electronics research with the invention of a new material tuPOY, which changes our perception of developing electronics. Evolving on a relatively underplayed phenomenon of static electricity in scientific exploration and application, tuPOY upholds the potential to rival both silicon and metals as electronics of the future. Devices made of tuPOY present a new emblem to the technological world, where we could envision our electronic paraphernalia from a completely different perspective. The computer the size of a big wall, which could be neatly folded and kept in our pockets when not in use and laundered on a regular basis, can be imagined possible with this invention. The concept, manufacturing process, physics and uses of tuPOY as the next generation material of electronics is described in this book. The book covers the production process of tuPOY and goes on to conceptual advancement from manipulating the sensing, radiating and processing properties of tuPOY. Theoretical modeling of tuPOY is characterized by steady-state equations exploiting interchanges based on the lattice kinetics, which mathematizes an Interchange Phenomenon in tuPOY. The numerical manifestations calibrate mathematically, tuPOY’s response to any external physical impetus such as charge, heat or energy flow. The book validates the sensing properties and theoretical model by designing a tuPOY sensor which can be used in a plethora of applications. A novel microstrip antenna is designed by an amalgamation of tuPOY, raw silk, and poly nylon composites to experimentally verify the radiation properties of the new material. The conduction properties are verified by drawing fibers of tuPOY and using them as wires and connectors in electronics. A Power Generating Unit (PGU) is designed with tuPOY as its primary element. This is a first of its kind PGU that scavenges power from thermal energy presenting a new dimension in operational power dynamics. Overall this book should be of interest to a wide range of readers ranging from researchers, scientists, developers, manufacturers, engineers, graduate students and anyone who has satiety to think differently.
  18. Microsmart signal generator
  19. Image Fusion in Variable Raster Media for Enhancement of Graphic Device Interface : In computer graphics, it often required to interface various display devices in the system. Each display device should provide high-resolution image quality. The proposed method enhances the display performance of the graphics device interface. We propose a novel application for image fusion methods which work on different raster operations to improve the quality of picture for higher or lower resolution interfaces. We have used image fusion performance considerations such as entropy, Mean intensity value, standard deviation, RMSE, and PSNR, etc to evaluate the interface results. Simulation results show that all raster operations be it blend or merge of source and/or destination images deliver superior objective as well as quantitative results and provide enhanced image quality for graphics data interface.
  20. Mobile Function Generator Using Android: The project attempts to create a cell-phone application using Android in order to implement a function generator which generates different A.C. sources (like sine, sawtooth, and square) so as to power different circuits. Function generators are available only in labs. Hence, if implemented on a phone which is commonly available, it can be used extensively at home or on the field. The audio port capability of the cell-phone is also explored in more detail. Replacing the function generator used in the lab with the Android-based function generator in times of emergency is the ultimate aim of the project and ways and means to accommodate the same along with extensive programming is the scope of this project.
  21. Augmentation in object tracking performance with hue preservation conditioned on frequency domain characteristics of video: Tracking of any given object forms an integral part in surveillance, control, and analysis applications. The video tracker presented here works on the principle of mean shift. Mean shift is an iterative algorithm which is extended to the field of object tracking. However, mean shift tracker losses track of the object when there are variations in illumination. In order to improve the performance of the tracker, the poorly illuminated video frames are pre-processed and enhancement is provided to only those frames based on hue preservation algorithm. Low illumination in a frame leads to low-value DC coefficient. Enhancement is provided to frames with low DC coefficient. The frames with corrected illumination are used to track an object of interest using the Mean shift algorithm. The proposed method is tried on a variety of video sequences. The results exhibit much-improved tracking. The graph plotted for the Bhattacharyya coefficient versus the frame index exhibits a significant increase in its values when the frames are pre-processed in comparison with the basic mean shift algorithm.
  22. Panoramic mosaic conception using optimal seam with graded colour correction:    We propose a duplex methodology for merging a set of aligned source images with exceedingly dissimilar colors and luminance into a composite panorama with amenable blending attributes. The algorithm performs an optimal seam to determine the suture point which consequently is expertly camouflaged using the graded color blending to create the vista. Exposure leveler is the pedestal on which the dual algorithms are juxtaposed. The individual Y components of each slice are normalized as the direct ratio of the maximum luminance averaged over the brightest source image. The graded color blending performs a smooth transition over the seam by weighing the colors of the pixels as an inverse function of the square of the distance from the seam. The technique has been exhaustively verified on divergent image sequences which generate progressively transcendent sutures in both indoor and outdoor scenarios providing comparatively low values of mse.
  23. A Simple Algorithm For Designing An Artificial Intelligence Based Tic Tac Toe Game: This paper proposes a simple technique to develop a game of Tic-Tac-Toe as a two player game, where one player is a computer itself. The designed uses soft computing techniques programmed using a Javascript, HTML and CSS Algorithm developed helps a computer to decide the most appropriate move so as to either win the game or to draw it.
  24. Image Cognizance through Fuzion – Blending: High dynamic range (HDR) imaging from a set of sequential exposures is not an easy way to capture high-quality images of static scenes due either observational constraints or design constraints. It also suffers from artifacts for scenes with significant motion. In this paper, we proposed a new approach to HDR reconstruction that not only draws information but also it is more robust to camera scene motion than previous techniques because it simply utilizes a single image. As the proposed method based on single image fusion, the alignment process is completely neglected. This allows us to produce an HDR result which is more accurately represent the range of intensity levels found in real scenes, ranging from direct sunlight to faint starlight. The main aim of this is to reproduce what the human eye can see in terms of exposure and that offer a heightened view of reality with greater saturation and tonal range.
  25. PCA Encrypted Short Acoustic Data Inculcated in Digital Color ImagesWe propose developing a generalized algorithm for hiding audio signal using image steganography. The authors suggest transmitting short audio messages camouflaged in digital images using Principal Component Analysis as an encryption technique. The quantum of Principal components required to represent the audio signal by removing the redundancies is a measure of the magnitude of the Eigen values. The aforementioned technique follows a dual task of encryption and in turn also compresses the audio data, sufficient enough to be buried in the image. A 57Kb audio signal is deciphered from the Stego image with a high PSNR of 47.49 and a correspondingly low MSE of 3.3266×10 -6 with an equalized high-quality audio output.
  26. Optimizied techniques for image hashing: For the identification and verification of image contents, extremely efficient automated techniques are needed that require digital images to be processed and propagated. Digital data is prone to attacks leaving absolutely no clues about the attacker. Image hashing is the ability to categorize an image irrespective of the change in features like resolution and format as well as corruption. It is used to identify and verify images with similar structural content. We make use of the hash function which purposes to extract a fixed length bit code from a text or image. Hash functions have found varied applications in cryptography, video surveillance in addition to rummage the database. In this review paper, a detailed comparison of three techniques of image hashing is performed which include the Discrete Wavelet Transform, Singular Value Decomposition and the third technique of optimized Feature Extraction. The results of our experimentation reveal optimized values of Feature extraction as the best technique for image hashing.
  27. Objective Speech Analysis and Vowel Detection: In considering the application of digital signal processing techniques to speech communication problems, it is helpful to focus on three main topics: the representation of speech signal in digital form, the implementation of sophisticated processing techniques, and the classes of applications which rely heavily on digital processing. The objective analysis of the signal in terms of its various parameters is of primary concern. Pitch and Intensity are the most important parameters of a sound signal. Characteristics of a sound signal can be defined by observing the waveforms of pitch and intensity. A Spectrogram gives an efficient representation of the signal. Vowels and consonants can be separated by measuring the formant frequencies measured from the spectrogram.
  28. The Gesture Replicating Robotic Arm:The Gesture Replicating Robotic arm is a servo controlled robotic arm which replicates gestures in a three-dimensional environment. It makes use of cameras which detect the motion of one’s hand in three dimensions. The cameras provide frames as input to the software which performs segmentation algorithms like background subtraction, color detection, and contour detection. Pixel to angle mapping gives the appropriate commands to the respective servo motors. Thus, replication of the human hand movements is done. The crux of the project is to create software which can detect hand gestures without any involvement of sensors like accelerometers attached to the human arm, with no involvement of artificial intelligence. Thus it can avoid large blocks of code to perform a simple function which humans can perform easily like pouring coffee into a mug. That is robots will be able to move like people and they don’t need to be intelligent. Such lifelike robotic arms can be teleoperated to protect human workers in hazardous environments, such as on assembly lines, in space, undersea, and amid nuclear radiation.

  29. Parallel Multiclass Support Vector Interpretation of Haemodynamic Parameters for Manifestation of Aortic and Arterial Occlusive Diseases:Aortic and arterial occlusive diseases are congenital conditions manifested in impedance plethysmography and are difficult to interpret. A parallel multiclass support vector classification of hemodynamic parameters computed from plethysmographic observations is proposed for the diagnosis of aortoarteritis, atherosclerotic narrowing, and coarctation of the aorta. The proposed support vector algorithm was able to detect more precisely the presence of thrombotic occlusions at proximal and distal arteries. The proposed method provided better accuracy and sensitivity of 97.46% and 98.3% compared to principal component analysis (PCA) based backpropagation and non-weighted support vector architectures respectively. The results of the genotype were ably supported by receiver operating characteristics (ROC) curves which depict a ratio of true positive rate and false positive rate of over 0.9 for all classes as compared with ratios varying from 0.7 to 0.9 for the majority of classes as observed in case of non-weighted architecture. A reduction of over 60% in negative likelihood ratio with a 5% increase in negative predictive value was observed as compared to Elman and PCA based backpropagation architectures. The results were validated from angiographic findings at Grant Medical College, J.J. Hospital, and Bhabha Atomic Research Centre (BARC) all in Mumbai. The proposed method also distinguished cases with nephritic syndrome, lymphangitis, and venous disorders against those with arterial occlusive diseases. Application of the proposed method has the potential to enhance the performance of impedance plethysmography.
  30. Parallel Multiclass Support Vector Interpretation of Haemodynamic Parameters for Manifestation of Aortic and Arterial Occlusive DiseasesAortic and arterial occlusive diseases are congenital conditions manifested in impedance plethysmography and are difficult to interpret. A parallel multiclass support vector classification of hemodynamic parameters computed from plethysmographic observations is proposed for the diagnosis of aortoarteritis, atherosclerotic narrowing, and coarctation of the aorta. The proposed support vector algorithm was able to detect more precisely the presence of thrombotic occlusions at proximal and distal arteries. The proposed method provided better accuracy and sensitivity of 97.46% and 98.3% compared to principal component analysis (PCA) based backpropagation and non-weighted support vector architectures respectively. The results of the genotype were ably supported by receiver operating characteristics (ROC) curves which depict a ratio of true positive rate and false positive rate of over 0.9 for all classes as compared with ratios varying from 0.7 to 0.9 for the majority of classes as observed in case of non-weighted architecture. A reduction of over 60% in negative likelihood ratio with a 5% increase in negative predictive value was observed as compared to Elman and PCA based backpropagation architectures. The results were validated from angiographic findings at Grant Medical College, J.J. Hospital, and Bhabha Atomic Research Centre all in Mumbai. The proposed method also distinguished cases with nephritic syndrome, lymphangitis, and venous disorders against those with arterial occlusive diseases. Application of the proposed method has the potential to enhance the performance of impedance plethysmography.
  31. Parallel Support Vector Configuration for Identification of Fast Independent Components in Morphological Patterns Derived by Cardiovasographic Analysis on the Radial PulseThe paper proposes the identification of eight morphologically different pulse waveforms obtained from cardiotocographic observations on the radial pulse. Eight patterns correlated with normal subjects and those suffering from diseases of heart, lungs, and liver are analyzed by genotyping of their independent components under the umbrella of parallel multiclass support vector architecture. The algorithm is computationally faster on the basis of its lower number of support vectors (10%) besides providing higher accuracy (81.6%) as compared with parallel multiclass architecture. The confusion parameters for Fast ICA based SVM suggest 3% improvement in the sensitivity and specificity causing similar improvements in the F scores and positive predictive value with a decrease in the negative likelihood ratio indicating a reduction in the number of false positives.
  32. tuPOY: Epitomizing a New Epoch in Communications With Polymer TextilesThe 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 the 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 the 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 min- mum tradeoffs.
  33. Scanning the Issue
  34. MPTA: Modified polymer textile antennas for green symbiotic cloud communicationsWe propose a completely metal gratis antenna, developed from modified polymer textile. The antenna operating in the UWB range is lightweight, low cost, rugged and can be ambidextrously positioned under a cloud environment. The judiciously designed antenna can be easily amalgamated or sewn into wearable apparels suggesting its strong candidature in green symbiotic cloud communications. The short pulse UWB transmission capabilities of designed antenna provide benefits such as the low probability of intercept, good resistance to multipath fading in addition to its low visual profile. Tensile strength of about 60 MPa and a high operating temperature of 300°C allow the antenna to be soldier mounted under frequent physical abrasion. With a VSWR less than 2 and an operational efficiency of about 55 %, in the 5.5-6.5 GHz range, the proposed modified polymer textile antenna (MPTA) validates its usage as a viable option in a plethora of cloud computing architectures.
  35. Parallel support vector architectures for taxonomy of radial pulse morphology  Application of impedance plethysmography (IP) for impedance measurement is the paradigm in the 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 the 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 the 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.
  36. 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 the 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 wideband 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 for a strong candidature for the proposed architecture.
  37. Manifold signal receiver for powerline communication systemsAmalgamation of multiple signal transmission through a singular medium is the paramount advantage offered in the Powerline Communications (PLC) architecture. We propose a PLC paradigm, which allows for one receiver to control all types of signals, effectively delineating a universal communication system. Firstly, when different types of signals are received on power lines the receiver needs intelligent channel estimation for decoupling these signals. An intelligent blind channel estimation scheme is proposed for achieving this. Secondly, the received signals (telephone, broadband, radio, television, etc.,) need to be classified and routed to the appropriate devices. To accomplish this we propose a novel optimized coulomb energy neural network (OCEAN) for classification of incoming signals. Experimental results over real-time PLC low voltage system shows that the Universal Powerline Receiver (UPR) achieves a throughput of 75 Mbps, 63 Mbps, and 56 Mbps at SNR of 30 dB for the data, telephone and television transmissions respectively. Comparative analysis of UPR with the existing state of art OFDM and FMT modems is presented, which shows UPR as a viable prospective option.
  38. 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 the 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.
  39. Non linear and Dynamic Time Warping classification of morphological patterns identified from Plethysmographic observations in the radial pulseImpedance Plethysmographic (IP) observations from the arterial pulse forms a powerful tool for deciphering various cardiovascular diseases. However, a major bottleneck for applying this technique effectively is the assignment of variable waveform morphology to its respective diseases. The rationale of this work is to investigate Non-linear and Dynamic Time Warping (DTW) approaches for classifying Impedance Plethysmographic (IP) waveforms. Our adaptation is two-fold, firstly, where we establish the IP waveforms as a dynamic system using the embedding dimension. Analysis of IP waveforms reveals the existence of eight different patterns corresponding to normal subjects and those suffering from diseases of the heart, liver, and lungs. Secondly, we take up the task of classification of these patterns with template matching using DTW technique. Parametric evaluations reveal that IP waveforms exhibit dynamical nature in a three-dimensional attractor. This observation is further validated by an exhibition of determinism in recurrence plots and by parameters determined using recurrence quantification analysis. Classification of the IP patterns by DTW on 1200 samples selected meticulously from 5628 patterns shows an average accuracy of 94%, 95% sensitivity, high statistical predictive values and kappa value of 0.9314 for the eight different classes.
  40. Thermally unstable intelligent polymer textile biosensors A radical, first of its kind, biosensor fabricated from unsaturated polymer resin textile, establishes a dynamic link connecting human thermodynamics to the electrical ambiance. The fabrication process involves the esterification of dimethyl terephthalate (DMT) and ethylene glycol (EG). This polymerization is articulately arrested using an innovatively formulated retardant, yielding a permanent thermally unstable textile based sensor. An established non-trivial energy interchange phenomenon is founded, presenting an inimitable calibration mechanism of the developed sensors and charting a novel relationship of exuberated kinematical energy to medicinal prognosis. The calibration mechanism is verified from a health care perspective wherein the sensor is regulated against recordings obtained from volume changes in the radial artery. A quantitative and qualitative comparison is performed with existing foam and metallic sensors. The proposed sensor not only outperforms the existing sensors in durability and stability but also obtains an impressive accuracy of 87%. The novelty of the proposed invention lies in the ability of the biosensors to be fabricated as textile threads, which can be easily sewn and dyed, hence enabling amalgamation into the daily apparel. The capturing of physiological signal variations, devoid of any metallic components presents a singular facet of research and amalgamates various interdisciplinary fields while providing a robust architecture with minimal tradeoffs.
  41. Application of Crisp and Fuzzy Clustering Algorithms for Identification of Hidden Patterns from Plethysmographic Observations on the Radial PulseRadial 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 shows 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 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.
  42. OCR-based chassis-number recognition using artificial neural networks The automatic detection and recognition of car number plates have 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 an artificial neural network. The algorithm is tested on over a 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.
  43. Principal component analysis based backpropagation algorithm for diagnosis of peripheral arterial occlusive diseases An 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 Leriche’s 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 showed a sensitivity of 95.5% and specificity of 97.36% 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.
  44. Application of Neural Networks in the Interpretation of Impedance Cardiovasograms for the Diagnoses of Peripheral Vascular DiseasesAn Impedance Cardio-vasographic (ICVG) system has been developed at the Electronics Division, Bhabha Atomic Research Centre (B.A.R.C) for the assessment of Peripheral Blood Flow and has been installed at the Department of Medicine, J.J. Hospital, Mumbai, India. Impedance cardio-vasography (ICVG) gives an indirect assessment of blood volume changes by measurement of the normalized rate of change of electrical impedance (N dZ/dt) of the body segment. Parameters like Blood Flow Index (BFI) and Differential Pulse Arrival Time (DPAT) at different locations in both lower extremities (upper thigh, knee, calf, and ankle) can be computed from these measurements. This work deals with the analysis of these parameters by a neural network system for obtaining a proper diagnosis of subjects with peripheral vascular diseases. The designed network identified the presence of anatomical block or narrowing for most of the cases presented to it during testing and also the status of collateral circulation in the lower limbs. The neural network was trained again, with a few cases, which were not predicted correctly. The collaterals after the site of occlusion were classified as good, moderate or poor as an aid to the physician. The network identified cases with atherosclerotic narrowing satisfactorily and was also able to categorize cases where changes are observed only in one extremity, other remaining normal as in the cases of hemi-Leriche’s syndrome. An additional parameter CVS (Coefficient of venous Statis) was calculated which is useful for the diagnosis of primary and secondary varicosity of the veins.