Dũng Phạm - Academia.edu (original) (raw)

Papers by Dũng Phạm

This paper focuses on a specific word recognition technique for an online handwriting recognition... more This paper focuses on a specific word recognition technique for an online handwriting recognition system which uses Multiple Component Neural Networks (MCNN) as the exchangeable parts of the classifier. As the most recent of approaches, the system proceeds by segmenting handwriting words into smaller pieces (usually characters), which are recognized separately. The recognition results are then a composition of individually recognized characters. They are sent to the input of a word recognition module to choose the most suitable one by applying some dictionary search algorithms. The proposed classifier overcomes obstacles and difficulties of traditional ones to large character classes. Furthermore, the proposed classifier also has expandable capacity, which can recognize other character classes by adding or changing component networks and built-in dictionaries dynamically. Keywordsonline handwriting; recognition; convolution; neural network.

2006 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2006

Abstract Workspace analysis and optimization is a critical issue in robot manipulator design. For... more Abstract Workspace analysis and optimization is a critical issue in robot manipulator design. For a cable-driven parallel manipulator (CDPM), due to the unilateral driving properties of the cables, maintaining positive cable tension is essential to maneuver the moving ...

2006 IEEE Conference on Robotics, Automation and Mechatronics, 2006

Abstract This paper presents a novel mechanical design of a 3-DOF wrist prosthesis. Mimicking bi... more Abstract This paper presents a novel mechanical design of a 3-DOF wrist prosthesis. Mimicking biological solutions from the human arm anatomy, the wrist prosthesis is designed to have a parallel structure and is cable-driven. This results in a much lighter prosthesis, with higher ...

2010 International Conference on Information and Emerging Technologies, 2010

2006 13th IEEE International Conference on Electronics, Circuits and Systems, 2006

Abstract Three simple logic threshold conversion circuits are proposed. The proposed simple logic... more Abstract Three simple logic threshold conversion circuits are proposed. The proposed simple logic threshold conversion circuits can be implemented using normal conventional MOS transistors. Conversion characteristics of the proposed circuit have been confirmed ...

Lecture Notes in Computer Science, 2012

This paper presents a library written by C# language for the online handwriting recognition syste... more This paper presents a library written by C# language for the online handwriting recognition system using UNIPEN-online handwritten training set. The recognition engine based on convolution neural networks and yields recognition rates to 99% to MNIST training set, 97% to UNIPEN's digit training set (1a), 89% to a collection of 44022 capital letters and digits (1a,1b) and 89% to lower case letters (1c). These networks are combined to create a larger system which can recognize 62 English characters and digits. A proposed handwriting segmentation algorithm is carried out which can extract sentences, words and characters from handwritten text. The characters then are given as the input to the network.

Advances in Chitin and Chitosan, 1992

Journal of Mathematical Analysis and Applications, 2014

Abstract Let F : = ( f 1 , … , f p ) : R n → R p be a polynomial map. This paper studies the exis... more Abstract Let F : = ( f 1 , … , f p ) : R n → R p be a polynomial map. This paper studies the existence of the following global Łojasiewicz-type inequality ‖ F ( x ) ‖ α + ‖ F ( x ) ‖ β ⩾ c d ( x , F − 1 ( 0 ) ) for all x ∈ R n , for some constants c > 0 , α > 0 , and β > 0 . We show that the above inequality holds if one of the following conditions is satisfied: (i) F is convenient and Khovanskii non-degenerate at infinity; (ii) F is convenient and non-degenerate at infinity; (iii) F is Mikhailov–Gindikin non-degenerate. Further, in cases (ii) and (iii), the exponents α and β can be determined explicitly.

Applied Mathematics, 2014

The use of robotic manipulators in remote and sensitive areas calls for more robust solutions whe... more The use of robotic manipulators in remote and sensitive areas calls for more robust solutions when handling joint failure, and the industry demands mathematically robust approaches to handle even the worst case scenarios. For both serial and parallel manipulators torque failure is indeed a worst case scenario. Thus, a systematic analysis of the effects of external forces on manipulators with passive joints is presented. For serial manipulators we find under what conditions the robot is conditionally equilibrated, that is, equilibrated with respect to a specific external force. These conditions are, as expected, very restrictive. The serial, or subchain, case serves as a good platform for analyzing parallel manipulators. In parallel manipulators passive joints can appear as a design choice or as a result of torque failure. In both cases a good understanding of the effects that passive joints have on the mobility and motion of the parallel manipulator is crucial. We first look at the effects that passive joints have on the mobility of the mechanism. Then, if the mobility considering passive joints only is not zero we find a condition similar to the serial case for which the parallel manipulator is conditionally equilibrated with respect to a specific external force.

PAMM, 2014

Modeling, Identification and Control: A Norwegian Research Bulletin, 2014

This paper studies in detail how different evaluation methods perform when it comes to describing... more This paper studies in detail how different evaluation methods perform when it comes to describing the performance of haptically controlled mobile manipulators. Particularly, we investigate how well subjective metrics perform compared to objective metrics. To find the best metrics to describe the performance of a control scheme is challenging when human operators are involved; how the user perceives the performance of the controller does not necessarily correspond to the directly measurable metrics normally used in controller evaluation. It is therefore important to study whether there is any correspondence between how the user perceives the performance of a controller, and how it performs in terms of directly measurable metrics such as the time used to perform a task, number of errors, accuracy, and so on. To perform these tests we choose a system that consists of a mobile manipulator that is controlled by an operator through a haptic device. This is a good system for studying different performance metrics as the performance can be determined by subjective metrics based on feedback from the users, and also as objective and directly measurable metrics. The system consists of a robotic arm which provides for interaction and manipulation, which is mounted on a mobile base which extends the workspace of the arm. The operator thus needs to perform both interaction and locomotion using a single haptic device. While the position of the on-board camera is determined by the base motion, the principal control objective is the motion of the manipulator arm. This calls for intelligent control allocation between the base and the manipulator arm in order to obtain intuitive control of both the camera and the arm. We implement three different approaches to the control allocation problem, i.e., whether the vehicle or manipulator arm actuation is applied to generate the desired motion. The performance of the different control schemes is evaluated, and our findings strongly suggest that objective metrics better describe the performance of the controller, even though there is a clear correlation between subjective and objective performance metrics.