The e-Learning refers to the use of networking technologies to create, foster, deliver and facilitate learning anytime, anywhere. This chapter discusses our research on personalization of e-Learning content based on the learner’s profile.... more
The e-Learning refers to the use of networking technologies to create, foster, deliver and facilitate learning anytime, anywhere. This chapter discusses our research on personalization of e-Learning content based on the learner’s profile. After justifying the feasibility of using mobile agents in distributed computing systems for information retrieval, processing and mining, the authors deal with the relevance of mobile agents in e-Learning domain. The chapter discusses the proposed Case-Based Reasoning (CBR) as an approach to context-aware adaptive content delivery. Different parameters like technological, cultural and educational background of a learner are taken as the basis for forming the case-base that determines the type of content to be delivered. Along with the CBR, a diagnostic assessment to gauge an insight into the student’s current skills is done to determine the type of content to deliver. The implementation observations of such implementation vis-à-vis traditional e-L...
Research Interests:
Research Interests:
Research Interests:
Abstract. Group communication in wireless multimedia networks must consider the Quality of Service (QoS) parameters for efficient and quality aware multicast route computation. QoS parameters such as bandwidth, channel reliability,... more
Abstract. Group communication in wireless multimedia networks must consider the Quality of Service (QoS) parameters for efficient and quality aware multicast route computation. QoS parameters such as bandwidth, channel reliability, buffers, delays, jitters, etc. play a vital role in wireless multimedia networks. Multicast tree development for group communication must press for more than one or two QoS parameters for better services. This paper proposes a scheme for constructing a multicast tree based on a spanning tree by employing a fuzzy controller. Fuzzy controller uses three fuzzy input parameters namely, link bandwidth, link delay and link reliability for the construction of multicast spanning tree. The scheme is simulated to test its effectiveness in terms of multicast tree computation time, iterations required for multicast tree computation, packet delay and packet delivery ratio.
Research Interests:
Mobile networks that handle multicast communication services such as video conferencing, audio-conferencing, collaboration works, etc., require a kind of reliable and guaranteed point-to-multipoint communications. A multicast tree... more
Mobile networks that handle multicast communication services such as video conferencing, audio-conferencing, collaboration works, etc., require a kind of reliable and guaranteed point-to-multipoint communications. A multicast tree provides an efficient connectivity between the multicast mobile group members through base stations (point of attachment). Mobility of the hosts of a group necessitates maintenance of service quality multicast routes. This position paper
Research Interests: Computer Science, Fuzzy Logic, Service Quality, Group communication, Video Conferencing, and 14 moreComputer Network, Multimedia Networking, Quality of Service, Multicast, Collaborative Work, Multicast Communication, Group, Mobile Network, Base station, Ip Multicast, Mobile Host, MULTICAST routing, Distance Vector Multicast Routing Protocol, and Protocol Independent Multicast
Group communication in wireless multimedia networks must consider the Quality of Service (QoS) parameters for efficient and quality aware multicast route computation. QoS parameters such as bandwidth, channel reliability, buffers, delays,... more
Group communication in wireless multimedia networks must consider the Quality of Service (QoS) parameters for efficient and quality aware multicast route computation. QoS parameters such as bandwidth, channel reliability, buffers, delays, jitters, etc. play a vital role in wireless multimedia networks. Multicast tree development for group communication must press for more than one or two QoS parameters for better services. This paper proposes a scheme for constructing a multicast tree based on a spanning tree by employing a fuzzy controller. Fuzzy controller uses three fuzzy input parameters namely, link bandwidth, link delay and link reliability for the construction of multicast spanning tree. The scheme is simulated to test its effectiveness in terms of multicast tree computation time, iterations required for multicast tree computation, packet delay and packet delivery ratio.
Research Interests: Computer Science, Distributed Computing, Fuzzy Logic, Group communication, Computer Network, and 10 moreMultimedia Networking, Quality of Service, Multicast, Fuzzy Controller, Spanning Tree, Packet Delivery Ratio, Ip Multicast, MULTICAST routing, Distance Vector Multicast Routing Protocol, and Protocol Independent Multicast
Research Interests:
A neural learning and adaptive scheme, called inverse-dynamics adaptive control (IDAC) is presented. The IDAC scheme provides a learn-while-functioning capability. The error signal, defined as a difference between the desired and the... more
A neural learning and adaptive scheme, called inverse-dynamics adaptive control (IDAC) is presented. The IDAC scheme provides a learn-while-functioning capability. The error signal, defined as a difference between the desired and the actual outputs, modifies the controller weights until the controller structure becomes an approximate inverse-dynamics model of the process under control, making the transfer function from output-to-input unity. The necessary learning and adaptive algorithm is derived, and the computer simulation results to evaluate the performance of the IDAC algorithm are presented.<<ETX>>
Research Interests:
The performance evaluation of a dynamic neural unit (DNU) in the control of linear and nonlinear dynamical systems is described. The architecture of the dynamic neural unit embodies feedforward and feedback flow of signals weighted by the... more
The performance evaluation of a dynamic neural unit (DNU) in the control of linear and nonlinear dynamical systems is described. The architecture of the dynamic neural unit embodies feedforward and feedback flow of signals weighted by the synaptic weights in a dynamical structure. Because of the dynamical nature of the neuron, it can be trained to learn and control unknown linear dynamical systems. Nonlinear functions can be approximated using multistage dynamic neural units, and hence can be trained to control nonlinear dynamical systems. The DNUs not only emulate, to some extent, the learning and control actions of the biological neurons, but also have the potential of a parallel-distributed intelligent control scheme for a large-scale complex dynamic system.<<ETX>>
Research Interests:
Neural networks potentially offer a general framework for modeling and control of nonlinear systems. The conventional neural network models are a parody of biological neural structures, and have the disadvantage of very slow learning. In... more
Neural networks potentially offer a general framework for modeling and control of nonlinear systems. The conventional neural network models are a parody of biological neural structures, and have the disadvantage of very slow learning. In this paper, we develop a dynamic neural network structure which is based upon the collective computation of subpopulation of neurons, thus different from the conventionally assumed structure of neural networks. The architecture and the learning algorithm to modify weights of the proposed neural model are elucidated. Three applications of this dynamic neural network, namely (i) functional approximation, (ii) control of unknown nonlinear dynamic systems, and (iii) coordination and control of multiple systems, are described through computer simulations.<<ETX>>
Research Interests:
Research Interests:
The authors describe the use of a dynamic model of the biological neuron called the dynamic neural unit (DNU) and examine briefly how it can be used in a channel equalization problem. The DNU, which comprises an infinite impulse response... more
The authors describe the use of a dynamic model of the biological neuron called the dynamic neural unit (DNU) and examine briefly how it can be used in a channel equalization problem. The DNU, which comprises an infinite impulse response (IIR) structure followed by a nonlinear activation function, is used to obtain an inverse model of unknown channel dynamics. Once a unity mapping from output to input is achieved, the channel passes the source signal with almost no distortion to the receiver end. The DNU architecture and algorithm are described.<<ETX>>
Research Interests: Computer Science and IEEE
ABSTRACT By virtue of their functional approximation, learning and adaptive capabilities, the computational neural networks can be suitably employed for learning robot coordinate transformations. The major drawback of conventional static... more
ABSTRACT By virtue of their functional approximation, learning and adaptive capabilities, the computational neural networks can be suitably employed for learning robot coordinate transformations. The major drawback of conventional static feedforward neural networks based on back-propagation learning algorithm is in their very large convergence time for a given task. Any attempts to accelerate the learning process by increasing the values of learning constants in the algorithm often result in unstable systems. The intent of this paper is to describe a neural network structure called dynamic neural processor (DNP), and examine briefly how it can be used in developing a learning scheme for computing robot inverse kinematic transformations. The architecture and learning algorithm of the proposed dynamic neural network structure, the DNP, are described. Computer simulations are provided to demonstrate the effectiveness of the proposed learning scheme using the DNP.
Research Interests:
Research Interests:
In this paper we are proposing a student performance evaluation method using Fuzzy Inference System (FIS) for Network Analysis (NA) course studied by third semester Electronics and Communication Engineering students. This paper explains... more
In this paper we are proposing a student performance evaluation method using Fuzzy Inference System (FIS) for Network Analysis (NA) course studied by third semester Electronics and Communication Engineering students. This paper explains about importance of Bloom's levels in studying and developing critical thinking skills for NA course and designing scoring rubric by aligning the rubric criteria with Bloom's Taxonomy levels which are intern given as inputs to the FIS. The five inputs identify, understand, apply, analyze and design/create are fuzzified using Mamdani Fuzzy Inference System. With the help of fuzzy rules the predicted results are expressed in linguistic variables.
Research Interests:
Research Interests:
It has been demonstrated by many researchers that an unknown dynamic plant can be made to track an input command signal if the plant is preceded by a controller which approximates the inverse of the plant’s transfer function. Precascading... more
It has been demonstrated by many researchers that an unknown dynamic plant can be made to track an input command signal if the plant is preceded by a controller which approximates the inverse of the plant’s transfer function. Precascading a plant with its inverse model provides an unity mapping between the input and output signal space. This concept of inverse modeling has been referred to as adaptive inverse control. However, the concept of transfer function is limited to linear systems, and the control algorithms developed under this framework can not be extended to nonlinear systems. Due to the functional approximation and learning capabilities, the artificial neural networks can be employed to extend the concept of adaptive inverse control to nonlinear systems. In this paper, two dynamic neural structures, called recurrent neural network and dynamic neural processor, are used to coerce the nonlinear systems to follow the desired trajectories based on the principle of adaptive in...
Research Interests:
Research Interests:
A complex control system, in general, consists of two or more independently designed and mutually affecting subsystems. Proper coordination and control of multiple subsystems is responsible for the overall functioning of the system. This... more
A complex control system, in general, consists of two or more independently designed and mutually affecting subsystems. Proper coordination and control of multiple subsystems is responsible for the overall functioning of the system. This necessitates the development of control schemes for multivariable systems. This is a formidable task; more so if the systems involved are nonlinear with unknown dynamics. Because of their parallelism, functional approximation and learning capabilities, artificial neural networks can be effectively employed to control multivariable systems. The intent of this paper is to describe a neural network called the dynamic neural processor (DNP), and to use this structure to control nonlinear multivariable systems. The DNP is a dynamic neural network developed based on the concept of neural subpopulations which is in sharp contrast with the conventionally assumed structure of artificial neural networks
Research Interests:
In recent years, ANNs have been successfully used in various applications such as system identification and control, robotics, pattern recognition and vision. One important application of ANNs is in the area of robotics. In particular,... more
In recent years, ANNs have been successfully used in various applications such as system identification and control, robotics, pattern recognition and vision. One important application of ANNs is in the area of robotics. In particular, ANNs have been used to compute inverse kinematic transformations of multi-link robot manipulators. The advantage of using neural approach over the conventional inverse kinematic algorithms, is that ANNs can avoid time consuming calculations. Furthermore, in a manner typical of ANNs, it would be very easy to modify the learned associations upon changes in the structure of robot manipulators. With reference to the control paradigm, ANNs have the ability to approximate arbitrary nonlinear functions which is an essential requirement in the design of controllers for nonlinear dynamic systems. Because of their learning and adaptive features, ANNs can be trained to adaptively control various nonlinear systems. On the other hand, the conventional controllers ...
Research Interests: Computer Science and IEEE
Distributed computing extends traditional computing by allowing computational components to be distributed across a heterogeneous network and seamlessly interoperating with each other to perform a task. This paper investigates three... more
Distributed computing extends traditional computing by allowing computational components to be distributed across a heterogeneous network and seamlessly interoperating with each other to perform a task. This paper investigates three Java-based approaches to distributed computing viz., Java RMI (Remote Method Invocation), Java applet-servlet communication and Java Mobile Agents (MA), using performance measurement parameters like code size, latency, response time, partial failure and concurrency, ease of development and discusses the benefits of one over others. This study is aimed at investigating the suitability of the approaches in different application scenarios using a demonstrative example to analyze the performance of these approaches to distributed computing.
Research Interests:
In this paper, a hybrid controller, consisting of a conventional proportional-integral-derivative (PID) controller and a neurocontroller, is proposed. This controller combines the learning capabilities of artificial neural network-based... more
In this paper, a hybrid controller, consisting of a conventional proportional-integral-derivative (PID) controller and a neurocontroller, is proposed. This controller combines the learning capabilities of artificial neural network-based controllers and the global asymptotic stability of conventional PID controllers to control a DC motor. This kind of controller provides better control of nonlinear plant which otherwise would have been difficult to control without the proper tuning of PID gains. Simulation results are presented for the speed control of a DC motor.
This paper makes an attempt to implement learning style theory namely Visual, Auditory/Audio and Kinesthetic in technical institutes to make learning an enjoyable experience and student centric. The students learn in different ways and... more
This paper makes an attempt to implement learning style theory namely Visual, Auditory/Audio and Kinesthetic in technical institutes to make learning an enjoyable experience and student centric. The students learn in different ways and the teacher needs to design their course to meet these requirements of the students. The purpose of this investigation is to determine the learning style of the student and of the teacher and find the correlation between them. This will provide a way to approach students' needs and deliver the course content appropriately. Here learning styles of 44 students and the teacher who is teaching one of the courses is determined. The feedback was collected from students in order to compare the effectiveness of teaching in class. The experimental results indicate that when there is similarity between teacher and student learning style, the outcome is positive. Here VAK Learning Style (VAKLS) inventory developed by Victoria Chisslet is used. The Manhattan ...
Research Interests:
In recent years, course and instructional contents have been adapting to developing and delivering E-Learning to meet the needs of education. In this paper, we discuss context-aware intelligent multi-agent environment for deployment of... more
In recent years, course and instructional contents have been adapting to developing and delivering E-Learning to meet the needs of education. In this paper, we discuss context-aware intelligent multi-agent environment for deployment of E-Learning systems. The paper also explores the usability of mobile agents in such applications that require remote information collection, retrieval, sharing, mining and processing. The paper proposes a framework of an ongoing research work in distributed E-Learning and discusses the current findings and envisaged work in future.
Research Interests:
Research Interests:
Ambiguity is always present in any realistic process. This ambiguity may arise from the interpretation of the data inputs and in the rules used to describe the relationships between the informative attributes. Fuzzy logic provides an... more
Ambiguity is always present in any realistic process. This ambiguity may arise from the interpretation of the data inputs and in the rules used to describe the relationships between the informative attributes. Fuzzy logic provides an inference structure that enables the human reasoning capabilities to be applied to artificial knowledge-based systems. For efficient working the artificial knowledge-based systems depend upon algorithms which are cumbersome to implement and require extensive computational time. On the other hand, the human brain which performs approximate reasoning employs simple information processing elements called neurons. The paradigm of artificial neural networks, developed to emulate some of the capabilities of the human brain, has demonstrated a great potential in terms of learning and adaptation for various applications such as system identification and control, pattern recognition, prediction, etc. They provide low-level computations and embodies salient features such as learning, f...
Research Interests:
Over the last two decades several advances have been made in the areas of fuzzy logic and artificial neural networks. It is interesting to note that fuzzy logic and neural networks complement each other, and their fusion provides the... more
Over the last two decades several advances have been made in the areas of fuzzy logic and artificial neural networks. It is interesting to note that fuzzy logic and neural networks complement each other, and their fusion provides the benefits of both the technologies. Neural networks can deal with imprecise data and ill-defined activities; thus, they offer low-level computational features. On the other hand, fuzzy logic provides higher-level cognitive features as it can deal with issues such as approximate reasoning and natural language processing. The merging of these two fields results in an emerging paradigm called ‘neuro-fuzzy systems’. These are believed to have considerable potential in the areas of robotics, expert systems, medical diagnosis, control systems, pattern recognition and system modeling. The intent of this paper is to describe a Neuro-Fuzzy System (NFS) for on-line computation of inverse kinematic transformations of a robot manipulator. The NFS is comprised of a conventional fuzzy logic...
Research Interests:
This paper describes an intelligent computational scheme to obtain feasible solutions to the problem of inverse kinematics in robotics. The proposed scheme consists of a recurrent neural network and a knowledge-based (KB) system. The... more
This paper describes an intelligent computational scheme to obtain feasible solutions to the problem of inverse kinematics in robotics. The proposed scheme consists of a recurrent neural network and a knowledge-based (KB) system. The latter, based on the requirements and specifications of the robot task-space provided by the user, determines the neural network configuration and checks the robot link angles during the process of computation against the physical constraints. On the other hand, a recurrent neural network provides low-level computational features such as functional approximation, parallelism, learning and adaptation capabilities. The inverse kinematics problem in robotics involves the determination of joint variables for a desired end-effector position in the robot task-space. This problem is difficult in the sense that for a given end-effector position there can be many solutions, and some of these solutions may not be practically feasible due to the physical limitations imposed by the robot...
Research Interests:
Research Interests:
The use of dynamic neural networks to model and control dynamic systems is of great importance in the control paradigm. The intent of this paper is to use one such dynamic neural structure, namely the recurrent neural network, to drive... more
The use of dynamic neural networks to model and control dynamic systems is of great importance in the control paradigm. The intent of this paper is to use one such dynamic neural structure, namely the recurrent neural network, to drive unknown nonlinear systems to follow the desired trajectories. The learning scheme employed for this task consists of a conventional proportional-plus-derivative
Research Interests:
Machine vision (MV) is the technology which provides camera based analysis of images for various applications such as automatic quality inspection, pattern recognition, process flow control and pattern classification. The machine vision... more
Machine vision (MV) is the technology which provides camera based analysis of images for various applications such as automatic quality inspection, pattern recognition, process flow control and pattern classification. The machine vision system is expensive as it contains high resolution camera and lenses. The paper proposes an algorithm to develop a low cost web camera based vision system for screw thread inspection. The Bayesian super-resolution method is used to super-resolute the images captured using low resolution web cameras. The parameters such as major, minor and pitch diameters, depth and thread angles are measured by using the proposed dimension measurement method. The results of web camera based automatic inspection of major diameter, minor diameter, pitch diameter, thread and depth of hex lag screw thread shows an error of range 0.000 to 0.310 mm. The comprehensive experimental results reveal that the proposed approach is suitable for real-time high speed quality analysis in various industries.
Research Interests:
A neural structure which is comprised of dynamic neural units with time-varying sigmoidal functions is proposed. The effect of sigmoidal gain on nonlinear dynamic systems is discussed. The learning and adaptive algorithm to determine the... more
A neural structure which is comprised of dynamic neural units with time-varying sigmoidal functions is proposed. The effect of sigmoidal gain on nonlinear dynamic systems is discussed. The learning and adaptive algorithm to determine the optimum sigmoidal gain, which results in selftuning of the neuron, is derived. The effectiveness of the proposed neural network is demonstrated through computer simulation studies.<<ETX>>
Research Interests: Computer Science and IEEE
The authors describe a neural model, called the dynamic neural processor (DNP), which functionally mimics the subpopulation of neurons in a neural population. The DNP consists of two dynamic neural units which are coupled to function as... more
The authors describe a neural model, called the dynamic neural processor (DNP), which functionally mimics the subpopulation of neurons in a neural population. The DNP consists of two dynamic neural units which are coupled to function as excitatory and inhibitory neurons. The parallel architecture of the proposed neural model makes it very advantageous to apply to multi-variable control systems. The DNP is effectively implemented to coordinate different subsystems, both linear and nonlinear. The mathematical model and the learning and adaptive algorithm of the proposed neural model are described. A number of computer simulation studies are presented to demonstrate the effectiveness of the proposed model.<<ETX>>
Research Interests: Computer Science and IEEE
Many neurophysiologists believe that one of the important circuits in the entire central nervous system (CNS) is the reverberating (oscillatory) circuit. Such positive feedback within the neuronal pool. One such circuit is a central... more
Many neurophysiologists believe that one of the important circuits in the entire central nervous system (CNS) is the reverberating (oscillatory) circuit. Such positive feedback within the neuronal pool. One such circuit is a central pattern generator (CPG) which generates rhythmic motion actions such as locomotion and respiration. Here, the authors use a recurrent neural network (RNN) to model the CPG. By appropriately modifying the weights of the RNN using a learning algorithm, the RNN can be programmed to function as an adaptive oscillator which in turn models the CPG. The CPG model is potentially applicable for improved understanding of animal locomotion, and for its application in legged robots. Computer simulations are provided to demonstrate the efficacy of the proposed CPG model using the RNN.
Research Interests:
Research Interests:
ABSTRACT Over the last decade or so, significant advances have been made in two distinct areas: fuzzy logic and computational neural networks. The theory of fuzzy logic provides mathematical strength to compare the uncertainties... more
ABSTRACT Over the last decade or so, significant advances have been made in two distinct areas: fuzzy logic and computational neural networks. The theory of fuzzy logic provides mathematical strength to compare the uncertainties associated with human cognitive processes, such as thinking and reasoning. Also, it provides a mathematical morphology to emulate certain perceptual and linguistic attributes associated with human cognition. On the other hand, the computational neural network paradigm has evolved in the process of understanding the incredible learning and adaptability of biological neural mechanisms. Neural networks replicate, on a small scale, some of the computational operations observed in biological learning and adaptation. The integration of these two fields, fuzzy logic and neural networks, has given birth to an emerging paradigm--the fuzzy neural networks. The fuzzy neural networks have the potential to capture the benefits of the two fascinating fields, fuzzy logic and neural networks, into a single capsule. The intent of this paper is to provide an introductory look at this emerging research field of fuzzy neural networks.
Research Interests:
Research Interests:
ABSTRACT This paper proposes a pseudo random number generator using Elman neural network. The proposed neural network is a recurrent neural network able to generate pseudo-random numbers from the weight matrices obtained from the layer... more
ABSTRACT This paper proposes a pseudo random number generator using Elman neural network. The proposed neural network is a recurrent neural network able to generate pseudo-random numbers from the weight matrices obtained from the layer weights of the Elman network. The proposed method is not computationally demanding and is easy to implement for varying bit sequences. The random numbers generated using our method have been subjected to frequency test and ENT test program. The results show that recurrent neural networks can be used as a pseudo random number generator(prng).
Research Interests: Computer Science and IEEE
Hash functions have been used to generate hash codes for data authentication. Traditionally these functions are generated using byte oriented algorithms like MD5 and others. In our paper we propose a new method of generating hash code for... more
Hash functions have been used to generate hash codes for data authentication. Traditionally these functions are generated using byte oriented algorithms like MD5 and others. In our paper we propose a new method of generating hash code for images using neural networks. Three sample images namely, fingerprint, lena and football image have been considered and their hash values calculated using two neural network structures namely, 1) structure without feedback 2) structure with feedback. The original images are then subjected to bit modification,Gaussian noise and rotational noise. The hash values are recalculated for the modified images. Sensitivity and hit collision are calculated and are found to be comparable with that of MD5 algorithm.
Research Interests:
As is known, many of the attributes of intelligent control in a biological process are due to the interactions of billions of neurons. Changing the weights of neurons alter the behavior of the entire neural network. Learning in a neutral... more
As is known, many of the attributes of intelligent control in a biological process are due to the interactions of billions of neurons. Changing the weights of neurons alter the behavior of the entire neural network. Learning in a neutral network is accomplished by adjusting the weights, typically to minimize some objective function, and storing these weights as the actual
Research Interests:
This paper proposes a pseudo random number generator using Layers-Recurrent network. The proposed dynamic network is a recurrent neural network able to generate pseudo-random numbers from the weight matrices obtained from the layer... more
This paper proposes a pseudo random number generator using Layers-Recurrent network. The proposed dynamic network is a recurrent neural network able to generate pseudo-random numbers from the weight matrices obtained from the layer weights of the Layer Recurrent network. A pseudorandom number generator (PRNG) is a deterministic algorithm that on input of a short random seed outputs a (typically much) longer sequence that is computationally in-distinguishable from a uniformly chosen random sequence. The random numbers generated using our method has been subjected to frequency test and ENT test and NIST test program. The results show that layer recurrent neural networks can generate pseudo random numbers effectively as standard generators.