• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.3
• /
• pp.169-175
• /
• 1996

In this paper, a new parallel neural network system that performs dynamic competitive learning is proposed. Conventional learning mehtods utilize the full dimension of the original input patterns. However, a particular attribute or dimension of the input patterns does not necessarily contribute to classification. The proposed system consists of parallel neural networks with the reduced input dimension in order to take advantage of the information in each dimension of the input patterns. Consensus schemes were developed to decide the netowrks performs a competitive learning that dynamically generates output neurons as learning proceeds. Each output neuron has it sown class threshold in the proposed dynamic competitive learning. Because the class threshold in the proposed dynamic learning phase, the proposed neural netowrk adapts properly to the input patterns distribution. Experimental results with remote sensing and speech data indicate the improved performance of the proposed method compared to the conventional learning methods.

• Proceedings of the KIEE Conference
• /
• 2003.11c
• /
• pp.429-432
• /
• 2003

In this paper, a novel neural network approach is proposed for cleaning robot to complete coverage path planning with obstacle avoidance in stationary and dynamic environments. The dynamics of each neuron in the topologically organized neural network is characterized by a shunting equation derived from Hodgkin and Huxley's membrane equation. There are only local lateral connections among neurons. The robot path is autonomously generated from the dynamic activity landscape of the neural network and the previous robot location without any prior knowledge of the dynamic environment.

• Journal of Institute of Control, Robotics and Systems
• /
• v.7 no.8
• /
• pp.647-655
• /
• 2001

In adaptive neuro-control, neural networks are used to approximate unknown plant nonlinearities. Until now, most of the studies in the field of controller design for nonlinear system using neural network considers the affine system with fixed number of neurons. This paper considers nonaffine nonlinear systems and on-line variation of the number of neurons. A control law and adaptive laws for neural network weights are established so that the whole system is stable in the sense of Lyapunov. In addition, at the expense of th input, tracking error converges to the arbitrary small neighborhood of the origin. The efficiency of the proposed scheme is shown through simulations ofa simple nonaffine nonlinear system.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.2
• /
• pp.159-167
• /
• 1996

In this paper, a new competitive learning algorithm called dynamic competitive learning (DCL) is presented. DCL is a supervised learning mehtod that dynamically generates output neuraons and nitializes weight vectors from training patterns. It introduces a new parameter called LOG (limit of garde) to decide whether or not an output neuron is created. In other words, if there exist some neurons in the province of LOG that classify the input vector correctly, then DCL adjusts the weight vector for the neuraon which has the minimum grade. Otherwise, it produces a new output neuron using the given input vector. It is largely learning is not limited only to the winner and the output neurons are dynamically generated int he trining process. In addition, the proposed algorithm has a small number of parameters. Which are easy to be determined and applied to the real problems. Experimental results for patterns recognition of remote sensing data and handwritten numeral data indicate the superiority of dCL in comparison to the conventional competitive learning methods.

• Proceedings of the KIEE Conference
• /
• 1996.07b
• /
• pp.1228-1230
• /
• 1996

A neural network(NN) mechanism is proposed to modify the gait of a biped robot that walks on sloping surface using sensory inputs. The robot starts walking on a surface with no priori knowledge of the inclination of the surface. By accumulating experience during walking, the robot improves its walking gait and finally forms a gait that is adapted to the surface inclination. A neural controller is proposed to control the gait which has 72 reciprocally inhibited and excited neurons. PI control is used for position control, and the neurons are trained by a reinforcement learning mechanism. Experiments of static gait learning and pseudo dynamic learning are performed to show the validity of the proposed reinforcement learning mechanism.

• The Korean Journal of Pain
• /
• v.11 no.1
• /
• pp.23-29
• /
• 1998

Background: The present study was conducted to investigate effects of microinjection of bicuculline, GABA-A receptor antagonist, into the brain stem nuclei on the dorsal horn neuron responsiveness in rats with an experimental peripheral neuropathy. Methods: An experimental neuropathy was induced by a unilateral ligation of L5~L6 spinal nerves of rats. After 2~3 weeks after the surgery, single-unit recording was made from wide dynamic range (WDR) neurons in the spinal cord dorsal horn. Results: Responses of WDR neurons to both noxious and innocuous mechanical stimuli applied to the somatic receptive fields were enhanced on the nerve injured side. These enhanced responsiveness of WDR neurons were suppressed by microinjection of bicuculline into periaqueductal gray(PAG) or nucleus reticularis gigantocellularis(Gi). A similar suppression was also observed when morphine was microinjected into PAG or Gi. Suppressive action by Gi-bicuculline was reversed by naloxonazine, ${\mu}$-opioid receptor antagonist, microinjected into PAG whereas PAG-bicuculline induced suppression was not affected by naloxonazine injection into Gi. Gi-bicuculline induced suppression were reversed by a transection of dorsolateral funiculus(DLF) of the spinal cord. Conclusions: The results suggest that endogenous opioids, via acting on GABAergic interneurons in PAG and Gi, may be involved in the control of neuropathic pain by activating the descending inhibitory pathways that project to the spinal dorsal horn through DLF to inhibit the responsiveness of WDR neurons.

• The Korean Journal of Physiology and Pharmacology
• /
• v.1 no.3
• /
• pp.263-273
• /
• 1997

The purpose of this study was to evaluate the effects of electrical stimulation on vestibular compensation following ULX in rats. Electrical stimulation (ES) with square pulse ($100{\sim}300uA$, 1.0 ms, 100 Hz) was applied to ampullary portion bilaterally for 6 and 24 hours in rats receiving ULX. After ES, animals that showed the recovery of vestibular symptoms by counting and comparing the number of spontaneous nystagmus were selected for recording resting activity of type I, II neurons in the medial vestibular nuclei (MVN) of the lesioned side. And then the dynamic neuronal activities were recorded during sinusoidal rotation at a frequency of 0.1 Hz and 0.2 Hz. The number of spontaneous nystagmus was significantly different 24 hours (p<0.01, n=10), but not 6 hours after ULX+ES. As reported by others, the great reduction of resting activity only in the type I neurons ipsilateral to lesioned side was observed 6, 24 hours after ULX compared to that of intact labyrinthine animal. However, the significant elevation (p<0.01) of type I and reduction (p<0.01) of type II neuronal activity were seen 24 hours after ULX+ES. Interestingly, gain, expressed as maximum neuronal activity(spikes/sec)/maximum rotational velocity(deg/sec), was increased in type I cells and decreased in type II cells 24 hours after ULX+ES in response to sinusoidal rotation at frequencies of both 0.1 Hz and 0.2 Hz. This result suggests that accompanying the behavioral recovery, the electrical stimulation after ULX has beneficial effects on vestibular compensation, especially static symptoms (spontaneous nystagmus), by enhancing resting activity of type I neurons and reducing that of type II neurons.

• The Korean Journal of Physiology
• /
• v.23 no.1
• /
• pp.151-167
• /
• 1989

The present study was undertaken to investigate modification in electrophysiological characteristics of cat dorsal horn cells resulting from carrageenin-induced inflammation. The followings were studied; 1) the time-course of changes in responses of the WDR (wide dynamic range) cell 1-3h after subcutaneous injection of carrageenin in its receptive field; 2) the responses of the same dorsal hern cells before and after induction of inflammation; 3) the effect of inflammation on the responsiveness of dorsal horn neurons to algogens (bradykinin & potassium); and 4) the effect of inflammation on the activity of WDR cell following administration of indomethacin and clonidine. Though responses of WDR neuron were increased dramatically during first 1h, the maximal enhancement was observed 3h after induction of inflammation especially by repetitive light tactile stimulus. Following carrageenin injection the majority of WDR neurons (10/15 units) showed enhanced responses to all the mechanical stimuli while in 3 cases responsiveness were intensified during activation by one tactile stimulus (brush or pressure). One cell was unaffected by inflammation and in another case the response was enhanced only to noxious stimulus. Five of 9 cells that could initially be driven by noxious stimulus were activated more strongly by same stimulus and even by tactile stimulus (pressure) following inflammation. In 2 cases neurons were sensitized only to noxious stimulus whereas in another 2 cells that did not show enhanced responses to noxious stimulus responses to light tactile stimulus (pressure) appeared after inflammation. Of 16 LT cells tested 6 responded to squeeze while 4 showed the characteristics of WDR cell following inflammation. No modification in responsiveness was recognized in 3 cells whereas response to only brush was enhanced in another 3 neurons. Following carrageenin injection responses of LT cell to bradykinin or $K^{+}$ were not altered whereas those of WOR neurons to bradykinin or $K^{+}$ were suppressed in 22.2% and 33.3% of cases, respectively. In two of 8 activity of HT cells were inhibited by bradykinin while in five of 8 responsiveness to $K^{+}$ were rather enhanced by inflammation. In the rest inflammation was ineffective. In inflammation-induced animal the receptive field of LT cell was not changed whereas those of WDR cell and HT cell were tremendously expanded. The enhanced responses of WDR neurons to mechanical stimuli resulted from inflammation were suppressed by intravenously injected indomethacin and clonidine suggesting that postaglandin is involved in inflammation-induced sensitization of these cells. The involvement of peripheral and central mechanisms in the modification in responsiveness of dorsal horn cells in the carrageenin-induced inflammation was discussed.

• Journal of Institute of Control, Robotics and Systems
• /
• v.11 no.9
• /
• pp.781-788
• /
• 2005

This paper proposes an identification method using a self recurrent wavelet neural network (SRWNN) for dynamic systems. The architecture of the proposed SRWNN is a modified model of the wavelet neural network (WNN). But, unlike the WNN, since a mother wavelet layer of the SRWNN is composed of self-feedback neurons, the SRWNN has the ability to store the past information of the wavelet. Thus, in the proposed identification architecture, the SRWNN is used for identifying nonlinear dynamic systems. The gradient descent method with adaptive teaming rates (ALRs) is applied to 1.am the parameters of the SRWNN identifier (SRWNNI). The ALRs are derived from the discrete Lyapunov stability theorem, which are used to guarantee the convergence of an SRWNNI. Finally, through computer simulations, we demonstrate the effectiveness of the proposed SRWNNI.

• Proceedings of the KIEE Conference
• /
• 1995.11a
• /
• pp.157-160
• /
• 1995

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 very slow learning. In order to emulate some, dynamic functions, such as learning and adaption, and to better reflect the dynamics of biological neurons, M.M.Gupta and D.H.Rao have developed a 'dynamic neural model'(DNU). Proposed neural unit model is to introduce some dynamics to the neuron transfer function, such that the neuron activity depends on internal states. Numerical examples are presented for a model system. Those case studies showed that the proposed DNU is so useful in practical sense.