Pen-based Computers Research Articles

A Genetic-LVQ neural networks approach for handwritten Arabic character recognition

Handwritten recognition systems are a dynamic field of research in areas of artificial intelligence. Many smart devices available in the market such as pen-based computers, tablets, mobiles with handwritten recognition technology need to rely on efficient handwritten recognition systems. In this paper we present a novel Arabic character handwritten recognition system based on a hybrid method consisting of a genetic algorithm and a Learning vector quantization (LVQ) neural network. Sixty different handwritten Arabic character datasets are used for training the neural network. Each character dataset contains 28 letters written twice with 15 distinct shaped alphabets, and each handwritten Arabic letter is represented by a binary matrix that is used as an input to a genetic algorithm for feature selection and dimension reduction to include only the most effective features to be fed to the LVQ classifier. The recognition process in the system involves several essential steps such as: handwritten letter acquisition, dataset preparation, feature selection, training, and recognition. Comparing our results to those acquired by the whole feature dataset without selection, and to the results using other classification algorithms confirms the effectiveness of our proposed handwritten recognition system with an accuracy of 95.4%, hence, showing a promising potential for improving future handwritten Arabic recognition devices in the market.

Integrating automated data acquisition technologies for progress reporting of construction projects

Controlling construction projects necessitates controlling their time and cost in an effort to meet the planned targets. Management needs timely data that represent the status of the project to take corrective actions, if needed. This paper presents a control model that integrates different automated data acquisition technology to collect data from construction sites required for progress measurement purposes. Current automated data acquisition technologies are described, and their suitability for use in tracking and controlling construction activities is assessed. This includes bar coding, Radio Frequency Identification (RFID) 3D laser scanning, photogrammetry, multimedia, and pen-based computers. The user can move with a tablet PC in the construction site and record, take snapshots and also hand written comments about activities on site. The proposed cost/schedule control model integrates with the automated data acquisition technologies, a planning and scheduling software system, a relational database, and AutoCAD to generate progress reports that can assist project management teams in decision making.

Sketch recognition in interspersed drawings using time-based graphical models

Sketching is a natural mode of interaction used in a variety of settings. With the increasing availability of pen-based computers, sketch recognition has gained attention as an enabling technology for natural pen-based interfaces. Previous work in sketch recognition has shown that in certain domains the stroke orderings used when drawing objects contain temporal patterns that can aid recognition. So far, systems that use temporal information for recognition have assumed that objects are drawn one at a time. This paper shows how this assumption can be relaxed to permit temporal interspersing of strokes from different objects. We describe a statistical framework based on dynamic Bayesian networks that explicitly models the fact that objects can be drawn interspersed. We present recognition results for hand-drawn electronic circuit diagrams, showing that handling interspersed drawing provides a significant increase in accuracy.

Zoledronic acid (ZA) to prevent bone loss during combined androgen blockade with finasteride (CAB+F) for clinically localized or recurrent non-osseous prostate cancer (PC)

14628 Background: Androgen suppression (AS) is increasingly used as primary therapy for early PC and recurrent PSA-only PC. AS decreases bone mineral density (BMD), increases markers of osteoclastic and osteoblastic activity, and increases fracture risk. CAB+F is a maximal form of AS which has not been described in prospective trials. We present the first analysis of a prospective study of ZA to prevent bone loss in men receiving CAB+F. Methods: We performed a prospective non-randomized study of ZA in men receiving CAB+F for non-osseous PC. CAB+F consisted of 48 weeks of an LH-RH agonist and antiandrogen (bicalutamide or flutamide) plus finasteride 5 mg QD. Men received ZA 4 mg intravenous at entry and every 3 months. Calcium 1000 mg and calcitriol 0.5 mcg were given QD. Baseline and serial measures of osteocalcin (OC) and deoxypyridinoline (DPD) were assayed. Baseline BMD of the lumbar spine (LS) was measured by DEXA. Quality of life (QOL) was measured with a validated symptom-based scale for pen-based computers. Results: From 7/2004 through 12/2005, 26 men with PC met eligibility criteria and enrolled. ECOG status at entry was 0 for all. Mean age was 64 (range 46–81), mean PSA was 10.6 ng/mL (range 3.23–33.0) and median Gleason sum (GS) was 7 (range 5–9). Mean testosterone was 455 ng/dL. High risk PC (PSA > 20, or GS > 7, or T3 stage) was seen in 7/26 men. In preliminary analysis of men completing 48 weeks of CAB+F (n = 13), mean (±SD) LS BMD (gm/cm2) increased significantly from 1.245 (±0.170) to 1.425 (±0.198) (p = 0.002). Baseline mean OC (ng/ml) decreased from 7.69 (±0.20) to 2.50 (±1.48) and baseline mean DPD (nmol/mmol Cr) decreased from 6.75 (±5.72) to 4.20 (±2.03). All men achieved PSA < 0.1 by 24 weeks. Serial QOL data is significant for decreased sexual interest and mild fatigue compared with baseline. No grade 3 or 4 toxicities were seen. Expanded QOL and toxicity data will be described. Conclusion: ZA given at baseline and every 3 months in conjunction with maximal AS, CAB+F, significantly improves BMD of the lumbar spine and suppresses biochemical markers of both bone resorption and formation. No significant financial relationships to disclose.

An evaluation of a broad deployment of DyKnow software to support note taking and interaction using pen-based computers

This paper describes a department-wide deployment of DyKnow software to support collaborative note taking; classroom interaction; out of class review, replay, and grading of classroom materials; an...

Promoting classroom interactivity in computer science courses using laptops, pen-based computers, Tablet PC's, and Dyknow software

This tutorial will teach participants about the use of pen-based hardware and a software system named DyKnow Vision (www.dyknow.com, patents pending) to teach computer science classes. The tutorial...

A new gesture recognition algorithm and segmentation method of Korean scripts for gesture-allowed ink editor

Electronic ink is a form of multimedia data that has recently emerged from the development of pen-based computers which incorporate a stylus pen as the major input device. Gestures have proven to be a useful feature for pen-based user interface. In this paper, we studied some techniques in order to develop a gesture-allowed electronic ink editor for PDAs with hardware constraints. We designed eleven gestures, presented a new feature-based recognition algorithm to identify gestures, and proposed a method for segmenting ink data which mainly consists of Korean scripts into logical units. We implemented GesEdit, the gesture-allowed ink editor on PDAs using the proposed methods. A variety of experiments involving twenty users showed that a gesture recognition rate reaching 99.6% and a correct segmentation rate surpassing 99.8%.

Using pen-based computers across the computer science curriculum

This paper describes our use of pen-based electronic classrooms to enhance several computer science courses. After presenting our motivation for undertaking this work, and its relevance to the growing interest in using tablet PC's in the classroom, we present an overview of our use of this technology to engage students during class. Finally, we present the students' reaction to the approach as measured through attitude surveys and a focus group.

The Cancer Care Monitor: psychometric content evaluation and pilot testing of a computer administered system for symptom screening and quality of life in adult cancer patients

Technology is making the routine screening of symptoms and the measurement of quality of life (QoL) more feasible at the point of care. However, most existing symptom screening scales and QoL measures were not developed for clinical use and were not formatted and validated for administration through computerized mediums. The Cancer Care Monitor (CCM) is a symptom-based scale developed for administration on pen-based computers. This study is an initial evaluation of the reliability and validity of the CCM. Three samples of adult outpatients provided ratings on 38 physical, psychological, and functional oriented items of the CCM that comprise six symptom scales and one global QoL index. All additive scales are converted to normalized T scores. Reliability was examined through internal consistency and confirmatory factor analysis. Convergent and divergent validity were examined by comparing CMM scores to established measures of corresponding constructs and physician judgments. Alternative forms reliability was established by comparing paper and pencil administration with computer administration. Internal consistency reliability and factor analyses confirmed the structure of the CCM as comprising six primary symptom scales and one global QoL index. Internal consistency reliabilities ranged from 0.80 to 0.89. The pattern of correlations between CCM scales and established measures supported the convergent and divergent validity of the CCM scales. Alternate forms reliability based on paper and computer forms of the CCM scales was high. Patients indicated a preference for the computer-administered version. Results suggest that CCM items can be scored as a reliable and valid measure of constructs related to physical, psychological, and functional status, and global health-related QoL in adult cancer patients. Future studies should replicate and further evaluate the properties of the CCM, especially in relation to clinical utility.

Electronic Data Collection for Rockfall Analysis

Rockfall analysis traditionally has used conventional stationery tools, that is, pencil and paper, for data collection. Traditional methodologies are being revisited with the advent of personal digital assistants (PDAs) or pen-based computers that enable field data to be collected electronically. The advantages over data collection with pencil and paper include automatic error and data integrity checks during data input and the elimination of manual data entry. PDAs also allow automatic branching to solicit data input on the basis of previous data entered and support for code or scripting, which can be used to create unique files names from the data entered. These advantages are illustrated in an electronic data collection methodology as implemented within a rockfall hazard rating system for the Tennessee Department of Transportation.

Visual input for pen-based computers

The design and implementation of a camera-based, human-computer interface for acquisition of handwriting is presented. The camera focuses on a standard sheet of paper and images a common pen; the trajectory of the tip of the pen is tracked and the contact with the paper is detected. The recovered trajectory is shown to have sufficient spatio-temporal resolution and accuracy to enable handwritten character recognition. More than 100 subjects have used the system and have provided a large and heterogeneous set of examples showing that the system is both convenient and accurate.

Teaching theory of computation using pen-based computers and an electronic whiteboard

This paper describes a Theory of Computation course that was taught in an electronic classroom equipped with a network of pen-based computers, a touch-sensitive electronic whiteboard, and locally written groupware that was designed to enhance the ability of teachers and students to share written information during class. We first describe the technology that was used to support the course, and then provide an overview of the instructor's use of this technology to engage students during class. Finally, we present the students' reaction to the approach.

The design of an interface for student note annotation in a networked electronic classroom

Groupware that supports shared work surfaces generally adheres to the WYSIWIS (What You See Is What I See) paradigm which means that each user has the same view of the shared work surface at all times. We present a variation of the standard WYSIWIS paradigm which we call WYSIWISOW (What You See Is What I See, One Way) which has been found to be more appropriate than WYSIWIS for certain applications. The paradigm is motivated by describing an application that helps students and teachers share written information during class sessions using an electronic whiteboard and pen-based computers that communicate through a network. We next present a problem, which we call the collision problem, which is inherent to the new paradigm but not to the standard WYSIWIS paradigm. Several solutions to the collision problem are proposed, and our implementation of one of these solutions is described.

Computer-Aided Facilities Inspection

This paper presents the development of a computer-aided facilities inspection system based on Web-centric technologies and pen-based computers. The system, called field inspection reporting system, was field tested at the Boulder campus of the University of Colorado. More than 20 employees from the Department of Facilities Management at the University of Colorado participated in the 2-month study that included 18 building inspections in the mechanical, electrical, and architectural areas. Results show an improved process with better quality, greater speed, enhanced service, and lower cost. The field inspection reporting system demonstrates the viability of Web-centric technologies to support complex processes. When a Web-centric system is implemented, there is a paradigm shift from isolation to collaboration. The characteristics of this new paradigm shift were found to be centered on the concepts of ownership, accessibility, availability, and timeliness of information together with the notions of process implementation and control.

A Health Information Network for Managing Innercity Tuberculosis: Bridging Clinical Care, Public Health, and Home Care

The purpose of this study was to use a health information network and innovative technology to coordinate tuberculosis care. An innercity medical center, a local health department, and a home care nurse service in northern Manhattan were used. The organizations were linked with computer networks. An automated decision support system with a natural language processor was used to detect tuberculosis cases and report them to the health department, and to select patients for respiratory isolation. Educational materials were placed on the World Wide Web and a Web-based kiosk. Home care nurses were outfitted with wireless pen-based computers, and data were relayed to the medical center. Automated tuberculosis case reporting resulted in time savings but not improved accuracy. Automated rules resulted in significant improvements in respiratory isolation. Kiosk educational materials were well-used. Wireless computing led to better access to information for both nurses and physicians, but not to reduction of workload. The key success element was recognition of critical priorities. It is concluded that innovative technology can facilitate the coordination of clinical care, public health, and home care.

Overview of Three Expert Systems for Crash Data Collection

There is a demand by the highway safety community for better quality crash data to meet a wide variety of needs. The goal of the FHWA Crash Data Collection Expert System Program was to use expert systems technology to improve the accuracy and consistency of police-reported data. The program and the three expert systems developed and evaluated—seat belt use derivation; vehicle damage rating, including extent of deformation; and roadside barrier problem identification—are discussed here. In the program, police officers used pen-based computers that contain the expert systems to collect on-scene crash data. Embedded in the expert systems is data collection knowledge derived from experts in crash data collection and analysis. The expert systems use this knowledge to intelligently select the data to collect and assign values to elements. This knowledge is also included in on-line help screens that help the officer accurately identify the physical characteristics of the crash scene. The expert systems were evaluated during two field tests. The field test results indicate that the expert systems were well accepted by the officers, that the systems were validated by experts in the expert system domain areas, and that the officers collected data at an average of about 2 min per expert system.

Combining Neural Networks and Context-Driven Search for Online, Printed Handwriting Recognition in the NEWTON

While online handwriting recognition is an area of long-standing and ongoing research, the recent emergence of portable, pen-based computers has focused urgent attention on usable, practical solutions. We discuss a combination and improvement of classical methods to produce robust recognition of hand-printed English text for a recognizer shipping in new models of Apple Computer's NEWTON MESSAGEPAD and EMATE. Combining an artificial neural network (ANN) as a character classifier with a context-driven search over segmentation and word-recognition hypotheses provides an effective recognition system. Long-standing issues relative to training, generalization, segmentation, models of context, probabilistic formalisms, and so on, need to be resolved, however, to achieve excellent performance. We present a number of recent innovations in the application of ANNs as character classifiers for word recognition, including integrated multiple representations, normalized output error, negative training, stroke warping, frequency balancing, error emphasis, and quantized weights. User adaptation and extension to cursive recognition pose continuing challenges.

Introduction of Wireless, Pen-Based Computing Among Visiting Nurses in the Inner City: A Qualitative Study

The purpose of this qualitative study is to understand how a sample of visiting nurses experienced the practice of home health nursing in the inner city and how they perceived the anticipated introduction of wireless, pen-based computing into their practice. Focus groups were held with visiting nurses 1 week before the introduction of the wireless, pen-based computers. The data were analyzed using Strauss and Corbin's (1990) method for concept development. The following central concepts emerged from the focus groups with visiting nurses: "Missing contact in the field," "Consumption of time writing on forms," "Using the computer to help with the practice of home health nursing," and "Home nursing is a lifeline." These concepts, based on the commentaries by visiting nurses, help one to understand the problems encountered by visiting nurses in the delivery of home health care, identify ways to incorporate evolving technologies to enhance nursing practice, and consider approaches to computer skill acquisition.

Inferring 3D models from freehand sketches and constraints

This paper describes ‘Quick-sketch’, a 2D and 3D modelling tool for pen-based computers. Users of this system define a model by simple pen strokes, drawn directly on the screen of a pen-based PC. Exact shapes and geometric relationships are interpreted from the sketch. The system can also be used to sketch 3D solid objects and B-spline surfaces. These objects may be refined by defining 2D and 3D geometric constraints. A novel graph-based constraint solver is used to establish the geometric relationships, or to maintain them when manipulating the objects interactively. The approach presented here is a first step towards a conceptual design system. Quick-sketch can be used as a hand sketching front-end to more sophisticated modelling, rendering or animation systems.

Software tools to improve note-taking in the classroom

This paper describes the functionalities and some implementation details of software tools to assist and to improve the process of note taking by students during a traditional lecture. The software tools allow professors to interact effectively with the students during lectures and help students to take relevant notes. They are based on a previously described software, and use a network of pen-based computers as well as a large screen projection system.