Debasish Kundu

A novel approach towards designing a wearable Smart Health Monitoring System measuring the vital parameters and emergency situations in real-time and providing the necessary medical care through telemedicine

Health Monitoring systems are progressively evolving with the potential to change the way health care is currently delivered. A Smart Health Monitoring System, such as the one designed in this study, aims to automate patient monitoring tasks. In the present study we have designed and developed a GSM (Global System for Mobile) based smart wearable system with 3-axis Accelerometer, 3-lead ECG recording system and real-time NIBP analysis system. The device is capable of detecting sudden fall situations, cardiac abnormalities & hyper/hypotension; thereby rendering it suitable for real-time monitoring, self-diagnosis and remote diagnosis purposes. The system is also capable of sending notifications to healthcare professionals immediately after the detection of any of the aforementioned health abnormalities so that the necessary steps are taken. The complete analysis and evaluation of the signals acquired from the patient have been performed using a software platform: NI LabVIEW. It is a cost-effective, smart and wearable health monitoring system that is of immense importance not only to the elderly and post-operative patients, but also to those residing in remote locations and are incapable of affording expensive healthcare in urban hospitals or clinics.

A Fuzzy Logic Approach in Emotion Detection and Recognition and Formulation of an Odor-Based Emotional Fitness Assistive System

This paper aims at a Fuzzy relational approach for similar emotions expressed by different subjects by facial expressions and predefined parameters. Different Facial attributes contribute to a wide variety of emotions under varied circumstances. These same features also vary widely from person to person, introducing uncertainty to the process. Facial features like eye-opening, mouth-opening and length of eye-brow constriction from localized areas from a face are Fuzzified and converted into emotion space by employing relational models. This is dealt with Fuzzy Type-2 logic, which reigns supreme in reducing uncertainty.

An Automated Graphical User Interface based System for the Extraction of Retinal Blood Vessels using Kirsch’s Template

The assessment of Blood Vessel networks plays an important role in a variety of medical disorders. The diagnosis of Diabetic Retinopathy (DR) and its repercussions including micro aneurysms, haemorrhages, hard exudates and cotton wool spots is one such field. This study aims to develop an automated system for the extraction of blood vessels from retinal images by employing Kirsch’s Templates in a MATLAB based Graphical User Interface (GUI). Here, a RGB or Grey image of the retina (Fundus Photography) is used to obtain the traces of blood vessels. We have incorporated a range of Threshold values for the blood vessel extraction which would provide the user with greater flexibility and ease. This paper also deals with the more generalized implementation of various MATLAB functions present in the image processing toolbox of MATLAB to create a basic image processing editor with different features like noise addition and removal, image cropping, resizing & rotation, histogram adjust, separately viewing the red, green and blue components of a colour image along with brightness control, that are used in a basic image editor. We have combined both Kirsch’s Template and various MATLAB Algorithms to obtain enhanced images which would allow the ophthalmologist to edit and intensify the images as per his/her requirement for diagnosis. Even a non technical person can manage to identify severe discrepancies because of its user friendly appearance. The GUI contains very commonly used English Language viz. Load, Colour Contrast Panel, Image Clarity etc that can be very easily understood. It is an attempt to incorporate maximum number of image processing techniques under one GUI to obtain higher performance. Also it would provide a cost effective solution towards obtaining high definition and resolution images of blood vessel extracted Retina in economically backward regions where costly machine like OCT (Optical Coherence Tomography), MRI (Magnetic Resonance Imaging) are not available. Hence an early detection of irregularity will be possible especially in rural areas.

A novel approach towards detecting faces and gender using skin segmentation and template matching

Human face detection has become a major field of interest in current research due to the lack of deterministic algorithm to find face(s) in a given image. Further the algorithms that exist are very specific to the kind of images they would take as input and detect faces. The approach we take is a mixture of heuristic and novel algorithms. To detect faces we can put a number of simple rejection blocks in series, until we get the faces. Deeper the rejection block, more specifically it can be trained to eliminate non-faces. Various methods like template matching, maximal rejection and Eigen faces have been tried. Finally, a combination of skin colour segmentation, morphological operations, and Template Matching with Eigen faces has been used. The same technique is further expanded and used to classify genders.

Optimized bio-mems design for heart signal acquisition — A novel hardware implementation

Micro-electro mechanical systems (Mems) in biological applications has occupied one of finest research challenge in medical engineering and research. As a part of this, the paper presents a simple hardware prototype which may be used for the acquisition of heart sound. The hardware design takes the advantage of wireless technology and thus implemented using IEEE 802.15.1 Bluetooth technology. To cope up with drawbacks of traditional stethoscope and electronic stethoscope in view of noise elimination, cost, portability, internet connectivity for remote access of data and power consumptions, the prototype has been implemented. It also gives physiological information about the health of heart such as different stenosis, septal defects etc. by analysis of the heart sounds in time domain as well as in frequency domain. The core architecture of the model has been presented in this paper and also verified for some samples using Matlab Simulink software.

Controlling an embedded robot through image processing based object tracking using MATLAB

Object detection is a well-researched technology related to computer vision(CV) and image processing that deals with detecting instances of semantic objects of a certain class (such as humans, buildings, or cars) in digital images and videos. It has got some real-world applications such as smart-home automation, etc. Detection of a particular object by the computers camera is an important aspect. In this paper, we have proposed a method by which a particular coloured object is detected by the computer and according to the movement of the object, a robot, which is being interfaced with the computer using a wired medium is also moved. The arduino controlled robot is interfaced with the computer which acts as a slave. The object movement is the determining factor of the movement of the robot. The experimental results and analysis shown in the paper illustrates the performance of the proposed methodology in real-time.

Application of Fuzzy Abduction Technique in Aerospace Dynamics

The purpose of this paper is to apply Fuzzy Abduction Technique in aerospace dynamical problem. A model of an aeroplane is proposed for consideration at different air density level of the atmosphere and at different speed of the plane. Different air density of the atmosphere, angle of wings and speed of the plane are selected as parameters to be studied. In this paper a method is developed to determine the angle of wings of the plane with respect to its axis at different air density level of the atmosphere and at different speed of the plane. Data are given to justify our proposed method theoretically.

A Hybrid Color Plane Approach Towards Color Based Object Detection and Modeling of a Real-Time Gesture Based Intelligent Virtual Aid Using Artificial Neural Network

Augmented and Virtual Reality has become a highly researched subfield in the Computer Vision domain. Among various researched topics, object detection and tracking is a major field of interest, with various algorithms being developed for it. Various algorithms exist that employs different approaches to solving the problem of object detection. The approach that we take is a mixture of investigating and evaluating the previous approaches and coming up with a novel algorithm that is able to detect and track objects in real-time that is not tightly bound to specific colours. In order to implement a dynamic algorithm, we look into various colour planes and then take in multiple dimensions from a given colour plane and use a combination of the results obtained from the individual dimensions to get a result that is capable of detecting various range of colours. After the objects are satisfactorily detected, we proceed to track them and implement gestures that allow the users to elect a single colour to be tracked without any direct interactions, using a novel algorithm that we developed over the course of the research. After the election, the algorithm is expanded further to be able to integrate the ability to detect various gestures and patterns. The system is also capable of basic intelligence and is able to modify its phases as necessary based on the users interaction with the system. As such most of the system is user action dependent and free of any physical interaction. All the while, the algorithm is designed to be able to do all the processing in real-time.

A Real-Time Face Motion Based Approach towards Modeling Socially Assistive Wireless Robot Control with Voice Recognition

The robotics domain has a couple of specific general design requirements which requires the close integration of planning, sensing, control and modeling and for sure the robot must take into account the interactions between itself, its task and its environment surrounding it. Thus considering the fundamental configurations, the main motive is to design a system with user-friendly interfaces that possess the ability to control embedded robotic systems by natural means. While earlier works have focused primarily on issues such as manipulation and navigation only, this proposal presents a conceptual and intuitive approach towards man-machine interaction in order to provide a secured live biometric logical authorization to the user access, while making an intelligent interaction with the control station to navigate advanced gesture controlled wireless Robotic prototypes or mobile surveillance systems along desired directions through required displacements. The intuitions are based on tracking real-time 3-Dimensional Face Motions using skin tone segmentation and maximum area considerations of segmented face-like blobs, Or directing the system with voice commands using real-time speech recognition. The system implementation requires designing a user interface to communicate between the Control station and prototypes wirelessly, either by accessing the internet over an encrypted Wi-Fi Protected Access (WPA) via a HTML web page for communicating with face motions or with the help of natural voice commands like “Trace 5 squares”, “Trace 10 triangles”, “Move 10 meters”, etc. evaluated on an iRobot Create over Bluetooth connectivity using a Bluetooth Access Module (BAM). Such an implementation can prove to be highly effective for designing systems of elderly aid and maneuvering the physically challenged.