The formation of economic yield and fruit quality of Roxburgh rose (Rosa roxburghii Tratt.) depends essentially on its source-sink interaction. Thus, a pruning experiment was conducted to assess the effects of source-sink regulation on photosynthetic physiology and fruit yield of Roxburgh rose, which was of great significance to production. Cutting off vegetative branches reduced physiological fruit loss and malformed fruits but increased single fruit quality and yield. Results revealed that the stomatal characteristics, the composition of mesophyll tissue, and photosynthesis of leaves on reproductive branches were significantly affected by the ratio of the vegetative and reproductive shoots. Our data indicated that the source-sink ratio could reflect the balance between vegetative growth and reproductive growth of the tree during the whole fruit period. Fruit tree pruning had guiding significance for improving the fruit yield of Roxburgh rose.
An efficient training and pruning method based on the HY filtering algorithm is proposed for feedforward neural networks (FNN). A FNN's weight importance measure linking up prediction error sensitivity obtained from the HY filtering training, and then a weight salience based pruning algorithm is derived. Moreover, based on the monotonicity property of the HY filtering Riccati equation and the initial value of the error covariance matrix, performance of the HY filtering training algorithm will also be investigated. The simulation results show that our approach is an effective training and pruning method for neural networks.
Each national language is described by specific grammatical rules. But rule-based knowledge representations alone cannot be used for the natural flow of speech.
In this paper, optimisation of the naturalness of speech, i.e. the optimal choice of phonetic and phonologic parameters for prosody modelling is sought. We will try to find relevant features (speech parameters) having the basic influence on the fundamental frequency and duration of speech units. If the prosody of the synthesizer is controlled by an artificial neural network (ANN), optimisation of the ANN topology is necessary.
The topology of the ANN is also dependent on the number of input neurons which represent the most important speech parameters. The pruning of the ANN based on the several approaches (GUHA method, sensitivities of the synaptic weights, etc.) is a suitable tool for reducing the ANN structure.