Sundaresan Jayaraman

The Wearable Motherboard™: The first generation of adaptive and responsive textile structures (ARTS) for medical applications

Virtual reality (VR) has been making inroads into medicine in a broad spectrum of applications, including medical education, surgical training, telemedicine, surgery and the treatment of phobias and eating disorders. The extensive and innovative applications of VR in medicine, made possible by the rapid advancements in information technology, have been driven by the need to reduce the cost of healthcare while enhancing the quality of life for human beings.In this paper, we discuss the design, development and realisation of an innovative technology known as the Georgia Tech Wearable Motherboard™ (GTWM), or the “Smart Shirt”. The principal advantage of GTWM is that it provides, for the first time, a very systematic way of monitoring the vital signs of humans in an unobtrusive manner. The flexible databus integrated into the structure transmits the information to monitoring devices such as an EKG machine, a temperature recorder, a voice recorder, etc. GTWM is lightweight and can be worn easily by anyone, from infants to senior citizens. We present the universal characteristics of the interface pioneered by the Georgia Tech Wearable Motherboard™ and explore the potential applications of the technology in areas ranging from combat to geriatric care. The GTWM is the realisation of a personal information processing system that gives new meaning to the termubiquitous computing. Just as the spreadsheet pioneered the field of information processing that brought “computing to the masses”, it is anticipated that the Georgia Tech Wearable Motherboard™ will bring personalised and affordable healthcare monitoring to the population at large.

The Prediction of Yarn Tensile Properties by Using Artificial Neural Networks

This paper presents an artificial-neural-net model for predicting yarn tensile properties. A single hidden-layer neural network trained by using the back-propagation algorithm performs a functional mapping between material properties, process variables, and the resulting yarn tensile properties. The material and process variables, namely, yarn count, blend, and front- and back-nozzle pressures on an air-jet spinning machine, arc correlated with the experimentally determined yarn properties: breaking load and breaking elongation. The neural net was trained and then used to predict the tensile properties of yarns. The errors of prediction were low despite the availability of only a relatively small data set for training, and in each ease the prediction error was less than the standard deviation of experimentation. Use of the cross-validation technique ensured that the neural net obtained a generalized mapping of the inputs and outputs.

FDAS: A Knowledge-based Framework for Analysis of Defects in Woven Textile Structures

Defects in woven textile structures have been analyzed, and a novel scheme for their classification based on their visual attributes is proposed. The proposed scheme can serve as the underlying framework for a vision-based inspection system. The classification framework has been incorporated in software. The resulting knowledge-based system (FDAS — Fabric Defects Analysis System) identities defects, assigns probable causes for the defects, and suggests plausible remedies to avoid them. The system has been tested with actual fabric defects and has performed well. In addition to being used on the shopfloor, FDAS can be used for training new operators in fabric inspection in weaving and apparel-manufacturing plants.

A sensate liner for personnel monitoring applications

This program develops and demonstrates technologies useful for implementing a manageable cost effective systems approach to monitoring the medical condition of personnel by way of an instrumented uniform hereafter referred to as a Sensate Liner (SL). The SL consists of a form fitting garment which contains and interconnects sensing elements and devices to an electronics pack containing a processor and transmitter. The SL prototype requires fiber, textile, garment and sensor development. The SL textile consists of a mesh of electrically and optically conductive fibers integrated into the normal structure (woven or knitted) of fibers and yarns selected for comfort and durability. A suite of SL garment compatible embedded biological and physical sensors are then integrated into the SL. The initial SL sensor suite is selected to improve triage for combat casualties. Additional SL sensor concepts for medical monitoring will be discussed.

Smart Textile-Based Wearable Biomedical Systems: A Transition Plan for Research to Reality

The field of smart textile-based wearable biomedical systems (ST-WBSs) has of late been generating a lot of interest in the research and business communities since its early beginnings in the mid-nineties. However, the technology is yet to enter the marketplace and realize its original goal of enhancing the quality of life for individuals through enhanced real-time biomedical monitoring. In this paper, we propose a framework for analyzing the transition of ST-WBS from research to reality. We begin with a look at the evolution of the field and describe the major components of an ST-WBS. We then analyze the key issues encompassing the technical, medical, economic, public policy, and business facets from the viewpoints of various stakeholders in the continuum. We conclude with a plan of action for transitioning ST-WBS from ¿research to reality¿.

Ready to ware

Electronics and fabrics woven together (e-textiles) will make smart dressers of firefighters, football players, and fashionistas alike. The authors describe various prototypes that use the vast variety of fibers and fabrics that can be woven into clothing, carpets, upholstery, and wallcoverings. Coupled with fault-tolerant computing and network architectures, such e-textiles can constitute a platform for health monitoring, communications, multimedia devices, and changing decors.

ANALYSIS OF THE MODELING METHODOLOGIES FOR PREDICTING THE STRENGTH OF AIR-JET SPUN YARNS

The scope, usability, limitations and predictive power of four modeling methodologies are analyzed in this paper: mathematical models, empirical models, computer simulation models, and artificial neural network models. The predictive power of each of the four is estimated by comparing predicted yarn strength with experimentally obtained strengths for yarns spun using different process conditions and material parameters.

A Structured Methodology for the Design and Development of Textile Structures in a Concurrent Engineering Framework

A structured methodology for the design and development of textile structures within a concurrent engineering framework has been proposed and developed. The framework has been validated using the design and development of a Sensate Liner for Combat Casualty Care (or Sensate Liner) as an example. Key requirements for the product are identified using a modified QFD-type (Quality Function Deployment) approach and other tools used in concurrent engineering; and the design and development framework is established. This is followed by an in-depth analysis of the various issues involved in the design of the Sensate Liner (fabric/garment structure, materials and fabrication technologies) to meet the desired performance criteria. Candidate solutions are proposed with appropriate justifications. Finally, the successful application of the structured methodology in realizing the product is covered.

On mapping ER and relational models into OO schemas

The Entity-Relationship model (ER model) views data in the form of entities and relationships. The Object-Oriented model (OO model) views data as classes, types and their subtypes. A mapping procedure that considers various features of the ER model and transforms the ER schema and its associated relational schema into an OO schema is proposed. The mapping rules are illustrated with appropriate examples. A procedure for mapping constraints on the ER database into the OO schema is then discussed. Finally, OO representations are developed for ER schema operations.

Design and Development of an Architecture for Computer-Integrated Manufacturing in the Apparel Industry: Part I : Basic Concepts and Methodology Selection

To be successful and competitive and achieve excellence in manufacturing, the textile/apparel industry must successfully use the most advanced concepts and meth ods, including computer-integrated manufacturing (CIM). Successful implementation of CIM requires a fundamental analysis of the three major facets of the apparel en terprise : function, information, and dynamics. We discuss the concept of an architecture for apparel manufacturing, which will serve as the blueprint for implementing CIM. We present the various methodologies for developing the architecture, as well as a detailed disc on of the U.S. Air Forces integrated computer-aided manufacturing definition (IDEF). We also propose specific criteria for evaluating methodologies and software for developing the architecture.