In this paper, a simple method is proposed to evolve artificial neural networks(ANNs) using augmenting weight matrix method(AWMM). ANNs' architecture and connection weights can be evolved simultaneously by AWMM, a...
In this paper, a simple method is proposed to evolve artificial neural networks(ANNs) using augmenting weight matrix method(AWMM). ANNs' architecture and connection weights can be evolved simultaneously by AWMM, and their structures incrementally are growing up from minimal structure. It is a non-mating method. It employs 5 mutation operators: add connection, add node, delete connection, delete node, and new initial weight. And the connection weight is trained by the simplified alopex method, which is a correlation based method for solving optimization problem. In AWMM, structural information is encoded to weighting matrix, and the matrix is augmenting as the hidden nodes are added.
In this paper, we proposed an analog neural controller (ANC) that is similar to physical modeling of the nervous system. ANC is composed of sensory neurons, motor neurons, synapses and dendrites. The functions of sens...
详细信息
ISBN:
(纸本)9812835768
In this paper, we proposed an analog neural controller (ANC) that is similar to physical modeling of the nervous system. ANC is composed of sensory neurons, motor neurons, synapses and dendrites. The functions of sensory neurons generate CPG signals and motor neurons change the sensory neuron signal for driving actuators. Synapses connect between neurons and the weigh to be given. Dendrites can accept external signal from the sensor. Because of parallel structure which is one of main characteristic of ANC, it is possible to walk by generating new pattern even though one of the neuron is out of working.
Lane detection is an essential component of autonomous mobile robot applications. Any lane detection method has to deal with the varying conditions of the lane and surrounding that the robot would encounter while movi...
详细信息
Lane detection is an essential component of autonomous mobile robot applications. Any lane detection method has to deal with the varying conditions of the lane and surrounding that the robot would encounter while moving. Lane detection procedure can provide estimates for the position and orientation of the robot within the lane and also can provide a reference system for locating other obstacles in the path of the robot. In this paper we present a method for lane detection in video frames of a camera mounted on top of the mobile robot. Given video input from the camera, the gradient of the current lane in the near field of view are automatically detected. Randomized Hough Transform is used for extracting parametric curves from the images acquired. A priori knowledge of the lane position is assumed for better accuracy of lane detection.
In this paper, a method of estimating both the position and the rotation angle of an object on a measurement stage was proposed. The system utilizes the radio communication technology and the directivity of an antenna...
In this paper, a method of estimating both the position and the rotation angle of an object on a measurement stage was proposed. The system utilizes the radio communication technology and the directivity of an antenna. As a prototype system, a measurement stage (a circle 240mm in diameter) with 36 antennas that placed in each 10 degrees was developed. Two transmitter antennas are settled in a right angle on the stage as the target object, and the position and the rotation angle is estimated by measuring efficiency of the radio communication of each 36 antennas. The experimental result revealed that even when the estimated location is not so accurate (about a 30 mm error), the rotation angle is accurately estimated (about 2.33 degree error on average). The result suggests that the proposed method will be useful for estimating the location and the direction of an object.
In this paper, a handle-electrode system is proposed for obtaining the heart rate of a user while riding a bicycle. The system was designed to measure the user's heart rate by only gripping the handle of a bicycle...
In this paper, a handle-electrode system is proposed for obtaining the heart rate of a user while riding a bicycle. The system was designed to measure the user's heart rate by only gripping the handle of a bicycle. Three electrodes made from conductive cloth were adhered to the handle. A method detecting heart-rate from the obtained electrocardiogram was also proposed. To assess the applicability of the proposed system, a simple experiment was performed. The experiment was performed in four conditions of road surfaces; lawn, asphalt, a tiled, and an uneven road. Experimental result suggests that the proposed system can be useful for obtaining R waves while riding a bicycle.
Active appearance model (AAM) has been widely used in face tracking and recognition. However, accuracy and efficiency are always two main challenges with the AAM search. The paper therefore proposed a fast appearance-...
详细信息
ISBN:
(纸本)9781424422944
Active appearance model (AAM) has been widely used in face tracking and recognition. However, accuracy and efficiency are always two main challenges with the AAM search. The paper therefore proposed a fast appearance-model based 3D face tracking algorithm to track a face appearance with significant translation, rotation, and scaling activities by using stochastic meta-descent (SMD) optimization scheme to accelerate the appearance model search and to improve the tracking efficiency and accuracy. The proposed algorithm constructs an active face appearance model by using several semantic landmark points extracted from each frame and then processes the appearance model search to approximate the model translating, rotating, and scaling by using the SMD filter to minimize the appearance difference between the current model and the new observation. We compared the results with both a conventional AAM and a Camshift filter and found that our algorithm outperforms both two in terms of efficiency and accuracy in tracking a fast moving, rotating, and scaling face object in a video sequence.
Density functional theory can accurately predict chemical and mechanical properties of nanostructures, although at a high computational cost. A quasicontinuum-like framework is proposed to substantially increase the s...
详细信息
The objective of this study is to propose a model for planning course registration by using a data mining technique: Bayesian network. The proposed model can be used to predict the sequences of courses to be registere...
详细信息
ISBN:
(纸本)9781424414895
The objective of this study is to propose a model for planning course registration by using a data mining technique: Bayesian network. The proposed model can be used to predict the sequences of courses to be registered by undergraduate students whose majors are computerscience or engineering. The data set was obtained from student enrollments and include GPA and grades in each subject for first and second year students from a private university in Thailand. Evaluations show that the predictive power of this model is acceptable. The implications from this studypsilas findings suggest that the model can be applied for advising students in planning courses to be registered in each semester. Further, the model appears to be useful for improving curriculum development in order to fit both studentspsila and university requirements.
Since the appearance in 1993, first approaching the Shannon limit, the turbo codes gave a new direction for the channel encoding field, especially since they were adopted for multiple norms of telecommunications, such...
详细信息
Since the appearance in 1993, first approaching the Shannon limit, the turbo codes gave a new direction for the channel encoding field, especially since they were adopted for multiple norms of telecommunications, such as deeper communication. To obtain an excellent performance, it is necessary to design robust turbo code interleaver. In this research, we investigated genetic algorithms as a promising optimization method to find good performing interleavers for large frame sizes. In this paper, we present our work, compare with several previous approaches and present experimental results.
Recently, particle filters have been applying to many robotic problems including the simultaneous localization and mapping (SLAM). Specifically, SLAM approaches employing Rao-Blackwellized particle filter (RBPF) have ...
详细信息
Recently, particle filters have been applying to many robotic problems including the simultaneous localization and mapping (SLAM). Specifically, SLAM approaches employing Rao-Blackwellized particle filter (RBPF) have shown good results. However, no research is conducted to analyze representation of the results of particle filtering. After finishing the particle filtering, the results such as a map and a path are stored in the separate particles. In most cases, the result of the particle that has the highest importance weight is represented as the result. However, this approach does not give the best result all the time. Thus, We provide the analysis of final representation of particle filtering. In this paper, we compares several methods to derive the final representation of the result after finishing RBPF-SLAM. According to the result, combining data of each particle provides the better result with high probability than using just data of a particle such as the highest weighted particle representation.
暂无评论