This study analyses empirically how built environment affects school travel with a focus on independence from adults and travel mode. Students in three elementary schools—Chinan, Jingmei and Xinhwa—in Taipei’s Wenshan District are analysed after questionnaire surveys. The survey data are analysed using nested logit models at two decision levels. Analytical results indicate that high shade-tree density and high sidewalk coverage encourage children to walk to school independently, while large block sizes and increased intersection numbers discourage children from walking to school independently. Furthermore, although high building density, high vehicle density and diversified mode option encourage children to travel home after school by walking, bus or vanpool, block size and road width discourage children from so doing. These results are mostly similar to the findings of previous studies, although they also have some differences. Based on the empirical evidence presented in this study, three strategies are recommended for reshaping the built environment in Taipei: compact structure, pedestrian-friendly design and frequent bus services.
In this paper a new model of self-organizing neural networks is proposed. An algorithm called "double self-organizing feature map" (DSOM) algorithm is developed to train the novel model. By the DSOM algorithm the network will adaptively adjust its network structure during the learning phase so as to make neurons responding to similar stimulus have similar weight vectors and spatially move nearer to each other at the same time. The final network structure allows us to visualize high-dimensional data as a two dimensional scatter plot. The resulting representations allow a straightforward analysis of the inherent structure of clusters within the input data. One high-dimensional data set is used to test the effectiveness of the proposed neural networks.
We present an efficient approach to forming feature maps. The method involves three stages. In the first stage, we use the K-means algorithm to select N2 (i.e., the size of the feature map to be formed) cluster centers from a data set. Then a heuristic assignment strategy is employed to organize the N2 selected data points into an N x N neural array so as to form an initial feature map. If the initial map is not good enough, then it will be fine-tuned by the traditional Kohonen self-organizing feature map (SOM) algorithm under a fast cooling regime in the third stage. By our three-stage method, a topologically ordered feature map would be formed very quickly instead of requiring a huge amount of iterations to fine-tune the weights toward the density distribution of the data points, which usually happened in the conventional SOM algorithm. Three data sets are utilized to illustrate the proposed method.
yste-c epartment of Electrica .c.A system for the recognition of static hand gestures is developed. Applications of hand gesture recognition range @om teleoperated control, to hand diagnostic and rehabilitation or to speaking aids for the deaJ We use two EMI-Gloves connected to an IBM compatible PC via HyperRectangular Composite Neural Networks flRCNNs) to implement a gesture recognition system. Using the supervised decision-directed learning (SDDL) algorithm, the HRCNNs can quickly leam the complex mapping of measurements of ten $fingers' jlex angles to corresponding categories. In addition, the values of the synaptic weights of the trained HRCNNs were utilized to extract a set of crisp IF-THEN classipcation rules. In order to increase tolerance on variations of measurements corrupted by noise or some other factors we propose a special scheme to fuzzifi these crisp rules. The System is evaluated for the classification of 51 static hand gestures @om 4 "speakers'! The recognition accuracy for the testing set were 93.9%Hand gestures involve relative flexure of the user's fingers and consist of information that is often too abstract to be interpreted by a machine. Applications of hand gesture recognition widely range from teleoperated control to medicine or to e n t e~~e n t[I], [2]. For instance, transform of human hand motion for telemanipulation is especially impo environments [3]. To motivate a patient to take hand rehabilitation exercise an appealing idea is to customize the hand rehabilitation procedure and then package the exercise into a video game format [4]. Another important application of hand gesture recognition is to improve the quality of life of the deaf or non-vocal persons through a hand-gesture to speech system. Due to congenital malfunction, disease, head injuries, or virus infections, deaf or non-vocal individuals are unable to communicate with hearing people through speech. Deaf or non-vocal rsons use sign language or hand gestures to express themselves. However, most hearing people do not have the special sign language expertise. This is a major barrier between these two groups in daily communication. How to overcome this barrier to help the former persons to integrate into society is a very challenging research area.s i m~~i~~~ is that the resulting recogmion accuracy is not very high. The reason is that measurement data is usually corrupted by disturbance (e.g. sensor noise, glove slipping 0-7803-3645-3/96 $5.0001996 IEEE
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.