Faculty of Computing

Permanent URI for this communityhttps://rda.sliit.lk/handle/123456789/4202

Browse

Now showing 1 - 20 of 1136

Embargo
A novel modular neuro-fuzzy controller driven by natural language commands
(IEEE, 2001-07-27) Watanabe, K; Pulasinghe, K; Kiguchi, K; Izumi, K
A method of interpreting imprecise natural language commands to machine understandable manner is presented in this paper. The proposed method tries to ease the process of man-machine interaction by combining the theoretical understanding of artificial neural networks and fuzzy logic. Both fields are very popular to mimic the human behavior in different research areas in artificial intelligence. The proposed system tries to understand the natural language command rather than mere recognition. The distinctive features of the artificial neural networks in pattern recognition and classification and the abilities of manipulating imprecise data by fuzzy systems are merged to recognize the machine sensitive words in the natural language command and then to interpret them to machine in machine identifiable manner. Modularity of the design tries to break up the complete task into manageable parts where the presence of individual part is vital to bridge the so-called man-machine gap.
Open Access
Voice Communication in Performing a Cooperative Task with a Robot
(Springer, Tokyo, 2002) Pulasinghe, K; Watanabe, K; Kiguchi, K; Izumi, K
This paper investigates the credibility of voice (especially natural language commands) as a communication medium in sharing advanced sensory capacity and knowledge of the human with a robot to perform a cooperative task. Identification of the machine sensitive words in the unconstrained speech signal and interpretation of the imprecise natural language commands for the machine has been considered. The system constituents include a hidden Markov model (HMM) based continuous automatie speech recognizer (ASR) to identify the lexical content of the user's speech signal, a fuzzy neural network (FNN) to comprehend the natural language (NL) contained in identified lexical content, an artificial neural network (ANN) to activate the desired functional ability, and contral modules to generate output signals to the actuators of the machine. The characteristic features have been tested experimentally by utilizing them to navigate a Khepera® in real time using the user's visual information transferred by speech signals
Open Access
Accurate control position of belt drives under acceleration and velocity constraints
(Institute of Control, Robotics and Systems, 2003) Jayawardena, T. S. S; Nakamura, M; Goto, S
Belt drives provide freedom to position the motor relative to the load and this phenomenon enables reduction of the robot arm inertia. It also facilitates quick response when employed in robotics. Unfortunately, the flexible dynamics deteriorates the positioning accuracy. Therefore, there exists a trade-off between the simplicity of the control strategy to reject time varying disturbance caused by flexibility of the belt and precision in performance. Resonance of the system further leads to vibrations and poor accuracy in positioning. In this paper, accurate positioning of a belt driven mechanism using a feed-forward compensator under maximum acceleration and velocity constraints is proposed. The proposed method plans the desired trajectory and modifies it to compensate delay dynamics and vibration. Being an offline method, the proposed method could be easily and effectively adopted to the existing systems without any modification of the hardware setup. The effectiveness of the proposed method was proven by experiments carried out with an actual belt driven system. The accuracy of the simulation study based on numerical methods was also verified with the analytical solutions derived.
Open Access
An Approach to eTransform Enterprises in Developing Countries
(Proceedings of the 5th International Information Technology Conference, 2003) Kapurubandara, M; Arunatileka, S; Ginige, A
Developing countries differ form their affluent counterparts, the “developed”, in numerous ways. Infrastructure, cultural, social and regulatory differences are among the main factors. These differences or barriers tend to widen the digital divide. They stand in the way of the developing countries trying to achieve their goals towards a global economy by embracing eTechnologies The feeble and many unsuccessful attempts to re-cycle the methodologies used by the developed countries, have left the developing high and dry. In formulating strategies for e-transformation of developing countries, the barriers specific to countries with lower GDPs have to be taken into serious consideration. In this paper, an eTransformation model that is being successfully used with SMEs in Australia is being modified appropriately, proposed and applied as the approach for eTransformation for developing countries using a case study approach. The 7E’s in eTransformation is a model developed by researchers at the University of Western Sydney. It is currently being used successfully with a group of companies in Western Sydney. The model incorporates new business thinking, business models in the new e-economy and addresses issues such as analysing the external environment in eTransforming, re-engineering business, business-IT alignment, and change management issues. A company in the ceramic manufacturing sector in Sri Lanka – is being used as the case study for eTransformation.
Open Access
Voice-controlled modular fuzzy neural controller with enhanced user autonomy
(Springer-Verlag, 2003-03) Pulasinghe, K; Watanabe, K; Kiguchi, K; Izumi, K
In this article, a fuzzy neural network (FNN)- based approach is presented to interpret imprecise natural language (NL) commands for controlling a machine. This system, (1) interprets fuzzy linguistic information in NL commands for machines, (2) introduces a methodology to implement the contextual meaning of NL commands, and (3) recognizes machine-sensitive words from the running utterances which consist of both in-vocabulary and out-ofvocabulary words. The system achieves these capabilities through a FNN, which is used to interpret fuzzy linguistic information, a hidden Markov model-based key-word spotting system, which is used to identify machine-sensitive words among unrestricted user utterances, and a possible framework to insert the contextual meaning of words into the knowledge base employed in the fuzzy reasoning process. The system is a complete system integration which converts imprecise NL command inputs into their corresponding output signals in order to control a machine. The performance of the system specifications is examined by navigating a mobile robot in real time by unconditional speech utterances.
Embargo
Control of redundant manipulators by fuzzy linguistic commands
(IEEE, 2003-08-04) Pulasinghe, K; Watanabe, K; Izumi, K; Kiguchi, K
This paper presents a method of controlling redundant manipulator by spoken language commands consisting fuzzy linguistic information. The present system introduces the fuzzyneuro control paradigm to the contemporary speech controlled robotic systems, which are based on on-off control paradigm. The system is sensitive to the action activation commands, action modification commands, and action repetition commands of the human-robot conversation carried out by practical dialogues. C.redibility of the proposed system is experimentally proved by controlling a manipulator with seven degrees-of-freedom by fuzzy linguistic information enriched spoken language commands to perform an assembling task.
Open Access
A Fuzzy-Neural Network Based Human-Machine Interface for Voice Controlled Robots Trained by a Particle Swarm Optimization
(Korean Institute of Intelligent Systems, 2003-09-25) Watanabe, K; Chatterjee, A; Pulasinghe, K; Izumi, K; Kiguchi, K
Particle swarm optimization (PSO) is employed to train fuzzy-neural networks (FNN), which can be employed as an important building block in real life robot systems, controlled by voice-based commands. The FNN is also trained to capture the user spoken directive in the context of the present performance of the robot system. The system has been successfully employed in a real life situation for navigation of a mobile robot.
Open Access
Training of Fuzzy-Neural Network for Voice-Controlled Robot Systems by a Particle Swarm Optimization
(Institute of Control, Robotics and Systems, 2003-10-23) Watanabe, K; Chatterjee, A; Pulasinghe, K; Jin, S. O; Izumi, K; Kiguchi, K
The present paper shows the possible development of particle swarm optimization (PSO) based fuzzy-neural networks (FNN) which can be employed as an important building block in real life robot systems, controlled by voice-based commands. The PSO is employed to train the FNNs which can accurately output the crisp control signals for the robot systems, based on fuzzy linguistic spoken language commands, issued by an user. The FNN is also trained to capture the user spoken directive in the context of the present performance of the robot system. Hidden Markov Model (HMM) based automatic speech recognizers are developed, as part of the entire system, so that the system can identify important user directives from the running utterances. The system is successfully employed in a real life situation for motion control of a redundant manipulator.
Open Access
Incorporating business requirements and constraints in database conceptual models
(2004-01-23) Khan, K. M; Chadha, U; Kapurubandara, M
Entity relationship (ER) approach is predominantly used for conceptual modelling of database systems in terms of entities and their relationships. The approach does not provide sufficient support for incorporating business constraints and their impact on the entity relationships, thus leaving a gap between the requirements elicitation and database implementation. This paper makes an attempt to bridge this gap by proposing a construct that would enable the system architects to illustrate business requirements and constraints at the conceptual model with minimal effort. To do this, we have proposed an approach called attribute-oriented business requirements and constraints (BRCs). We classify five different categories of attribute-oriented BRCs for binary relationships. Based on this approach, we propose a construct to enhance the modelling capabilities and expressiveness of the ER approach without introducing any conflict with the current features. Our main contribution in this paper is a new construct to specify the business rules and constraints along with the systems requirements in database conceptual modelling.
Embargo
Modular fuzzy-neuro controller driven by spoken language commands
(IEEE, 2004-01-30) Pulasinghe, K; Watanabe, K; Izumi, K; Kiguchi, K
We present a methodology of controlling machines using spoken language commands. The two major problems relating to the speech interfaces for machines, namely, the interpretation of words with fuzzy implications and the out-of-vocabulary (OOV) words in natural conversation, are investigated. The system proposed in this paper is designed to overcome the above two problems in controlling machines using spoken language commands. The present system consists of a hidden Markov model (HMM) based automatic speech recognizer (ASR), with a keyword spotting system to capture the machine sensitive words from the running utterances and a fuzzy-neural network (FNN) based controller to represent the words with fuzzy implications in spoken language commands. Significance of the words, i.e., the contextual meaning of the words according to the machine's current state, is introduced to the system to obtain more realistic output equivalent to users' desire. Modularity of the system is also considered to provide a generalization of the methodology for systems having heterogeneous functions without diminishing the performance of the system. The proposed system is experimentally tested by navigating a mobile robot in real time using spoken language commands.
Embargo
Application of e-business strategies for SMEs in developing countries
(IEEE, 2004-03-28) Kapurubandara, M; Arunatileka, S; Gnige, A
Through e-business, information and communications technology (ICT) has changed the way trade and commerce is carried out. The developed nations of the world are taking advantage of these new technologies to expand their markets. Many countries, developed as well as developing, encourage the SMEs to form clusters to strengthen their marketing and buying power. Clustering is found to be a good strategy for SMEs all over the world to accept as a means to achieving competitive advantage. The Seven E's in e-transformation, a model developed by the University of Western Sydney, that is being successfully used with SMEs in Australia is applied as the approach to e-transform industries in developing countries towards e-business. The model incorporates new business thinking, business models in the new e-economy and it also depicts how clustering can be used to gain competitive advantage. The ceramic industry sector in Sri Lanka is used for the study of e-transforming a cluster of organisations.
Open Access
Syntactic Approach to Predict Membrane Spanning Regions of Transmembrane Proteins
(Springer, Berlin, Heidelberg, 2005-03-30) Pulasinghe, K; Rajapakse, J. C
This paper exploits “biological grammar” of transmembrane proteins to predict their membrane spanning regions using hidden Markov models and elaborates a set of syntactic rules to model the distinct features of transmembrane proteins. This paves the way to identify the characteristics of membrane proteins analogous to the way that identifies language contents of speech utterances by using hidden Markov models. The proposed method correctly predicts 95.24% of the membrane spanning regions of the known transmembrane proteins and correctly predicts 79.87% of the membrane spanning regions of the unknown transmembrane proteins on a benchmark dataset.
Embargo
Integrating industrial technologies, tools and practices to the IT curriculum: an innovative course with .NET and java platforms
(acm.org, 2005-10-20) Athauda, R; Kodagoda, N; Wickramaratne, J; Sumathipala, P; Rupasinghe, L; Edirisighe, A; Gamage, A; De Silva, D
Exposure to state-of-art industry technologies, tools and practices by students provide CS/IT graduates highly desirable skills and marketability. A key expectation of the industry from their new cadre is a speedy integration into the business environment resulting in productive work. This usually requires having a sound technological background, a maturity to assess the environment and adapt quickly, and highly-developed soft skills to be productive in a team environment. Incorporating such experience and skills into a CS/IT curriculum is challenging and is still in its infancy stages. We undertook such as an endeavor in integrating .NET into the IT curriculum. Microsoft's .NET platform is becoming increasingly popular in the industry. Incorporating .NET into the undergraduate IT curriculum provides a plethora of skills and increases the employability of our graduates. We integrated .NET without a major revision to the existing curriculum by introducing an optional course in the final year (senior-level) of the IT undergraduate program. In addition to the .NET platform, the course covered the Java platform, which is similar in architecture to .NET. The course emulated an industry-based environment with real-world based assignments, focused on deliverables, used state-of-art IDEs and documentation, and pair programming to create a highly productive environment. The “soft skills” were integrated into the course with a project that implemented a virtual marketplace. Students in groups played different entities in the virtual marketplace and communicated with each other via Web Services. The project provided a virtual business environment and exposure to teamwork, collaboration, competition, negotiating, and creativity skills. Our first offering of the course in semester 1, 2005, attracted 128 students. The course created a highly productive environment throughout the semester. Students completed 7 assignments and the project within the 14-week semester. The initial results are encouraging and provide many insights to CS/IT departments planning to incorporate such courses.
Embargo
Teaching a tele-robot using natural language commands
(IEEE, 2005-11-07) Jayawardena, C; Watanabe, K; Izumi, K
For Internet-based teleoperation systems, user-friendly natural interfaces are advantageous because those systems are intended to be used by non-experts. In developing user friendly interfaces, natural language communication is mandatory. This work presents a system in which a sub-set of natural language is used to command a tele-robot manipulator doing an object sorting task. The paper discusses about referring to objects with natural language commands such as "pick the small red cube". This is achieved by learning individual lexical symbols that refer to colors, shapes, and sizes independently, and then inferring the meaning of a combination of them.
Embargo
A particle-swarm-optimized fuzzy-neural network for voice-controlled robot systems
(IEEE, 2005-12-05) Chatterjee, A; Pulasinghe, K; Watanabe, K; Izumi, K
This paper shows the possible development of particle swarm optimization (PSO)-based fuzzy-neural networks (FNNs) that can be employed as an important building block in real robot systems, controlled by voice-based commands. The PSO is employed to train the FNNs that can accurately output the crisp control signals for the robot systems, based on fuzzy linguistic spoken language commands, issued by a user. The FNN is also trained to capture the user-spoken directive in the context of the present performance of the robot system. Hidden Markov model (HMM)-based automatic speech recognizers (ASRs) are developed, as part of the entire system, so that the system can identify important user directives from the running utterances. The system has been successfully employed in two real-life situations, namely: 1) for navigation of a mobile robot; and 2) for motion control of a redundant manipulator.
Open Access
An exploratory study of SME barriers for adoption of ICT and e-commerce in the Developing Countries -An empirical pilot study of Sri Lanka
(Proceedings of the International Conference on Information Management and Business, 2006) Kapurubandara, M
Embracing ICT and e-commerce for stability in international markets and competitive advantage are becoming imperative for Small and Medium Enterprises (SMEs,) to survive in a global economy. Yet, SMEs in developing countries, forming the backbone of the economy, are relatively slow in adopting ICT and ecommerce. Literature reveals many significant reasons contributing towards this reluctance.This paper looks into more in-depth information about the reasons why SMEs in Sri Lanka – a developing country in Asia, are reluctant to adopt ICT and e-commerce technologies. . The barriers were identified through a pilot studyof 17 SMEs carried out in Sri Lanka. It identifies the similarities and differences between the SMEs in developing countries and the developed. The author hopes to develop a methodology to effectively help e-transform SMEs in developing countries.
Open Access
Controlling a robot manipulator with fuzzy voice commands using a probabilistic neural network
(Springer-Verlag, 2006-07-06) Jayawardena, C; Watanabe, K; Izumi, K
Natural language commands are generated by intelligent human beings. As a result, they contain a lot of information. Therefore, if it is possible to learn from such commands and reuse that knowledge, it will be a very efficient process. In this paper, learning from such information rich voice commands for controlling a robot is studied. First, new concepts of fuzzy coachplayer system and sub-coach are proposed for controlling robots with natural language commands. Then, the characteristics of the subjective human decision making process are discussed and a Probabilistic Neural Network (PNN) based learning method is proposed to learn from such commands and to reuse the acquired knowledge. Finally, the proposed concept is demonstrated and confirmed with experiments conducted using a PA-10 redundant manipulator.
Embargo
Casterless Wheelchair Robot Using Inverted Pendulum Control
(IEEE, 2006-08-08) Abeygunawardhana, P. K. W; Toshiyuki, M
Power assist wheelchair robot is playing a key role in the field of medical welfare robotics. But, to a certain extend, there is a setback in development due to presence of caster wheels. Hence, this paper proposes a casterless wheelchair and its control on a straight line path. That is, straight line driving of two wheel power assist wheelchair robot was proposed in this paper while keeping stability of wheelchair body itself. Balancing of wheelchair body is proposed to achieve by controlling the inverted pendulum mounted on the wheelchair. Control equations of the system are derived using Lagrange equation of motion. Two separate controllers are designed for two wheels. In addition to these two controllers, there is another controller for pendulum. Body controller is designed combining pendulum controller and wheel controller. Disturbance observer is used to cancel disturbance effects. Simulation was carried out to prove the applicability of the proposed system
Embargo
Intelligent interface using natural voice and vision for supporting the acquisition of robot behaviors
(IEEE, 2006-10-22) Watanabe, K; Jayawardena, C; Izumi, K
Natural language usage for robot control is essential for developing successful human-friendly robotic systems. In spite of the fact that the realization of robots with high cognitive capabilities that understand natural instructions as humans is quite difficult, there is a high potential for introducing voice interfaces for most of the existing robotic systems. Although there have been some interesting work in this domain, usually the scope and the efficiency of natural language controlled robots are limited due to constraints in the number of built in commands, the amount of information contained in a command, the reuse of excessive commands, etc. We present a multimodal interface for a robotic manipulator, which can learn both from human user voice instructions and vision input to overcome some of these drawbacks. Results of three experiments, i.e., learning situations, learning actions, and learning objects are presented.
Embargo
Approximate decision making by natural language commands for robots
(IEEE, 2006-11-06) Watanabe, K; Jayawardena, C; Izumi, K
Inferring the correct meaning of natural language commands, as judged by the person who issues commands, is mandatory for natural language commanded robotic systems. There have been some successful research on this; but one of the important and related aspects has not been addressed, i.e. the possibility of learning from natural language commands. Since natural language commands are generated by human users, they contain valuable information. Nevertheless, the learning from such commands, as well as the interpretation of them face many challenges due to the inherent subjectiveness of natural languages. In this paper, we propose a decision making process for natural language commanded robots which is influenced by certain characteristics of human decision making process. The proposed concept is demonstrated with an experiment conducted using a robotic manipulator. First, the robot is controlled with natural language commands to perform some pick and place operations during which the robot builds a knowledge base. After learning, the robot is capable of performing approximately similar tasks by making approximate decisions with the gained knowledge. For the decision making a probabilistic neural network is used