A prediction-aided routing algorithm based on ant colony optimization mode(PRACO)to achieve energy-aware data-gathering routing structure in wireless sensor networks(WSN)is presented.We adopt autoregressive moving average model(ARMA)to predict dynamic tendency in data traffic and deduce the construction of load factor,which can help to reveal the future energy status of sensor in WSN.By checking the load factor in heuristic factor and guided by novel pheromone updating rule,multi-agent,i.e.,artificial ants,can adaptively foresee the local energy state of networks and the corresponding actions could be taken to enhance the energy efficiency in routing construction.Compared with some classic energy-saving routing schemes,the simulation results show that the proposed routing building scheme can ① effectively reinforce the robustness of routing structure by mining the temporal associability and introducing multi-agent optimization to balance the total energy cost for data transmission,② minimize the total communication consumption,and ③ prolong the lifetime of networks.
Tone model (TM) integration is an important task for mandarin speech recognition.It has been proved to be effective to use discriminatively trained scaling factors when integrating TM scores into multi-pass speech recognition.Moreover,context-dependent (CD) scaling can be applied for better interpolation between the models.One limitation of this approach is a large number of parameters will be introduced,which makes the technique prone to overtraining.In this paper,we propose to induce context-dependent model weights by using automatically derived phonetic decision trees.Question at each tree node is chosen tominimize the expected recognition error on the training data.First order approximation of theminimum phone error (MPE) objective function is used for question pruning to make tree building efficient.Experimental results on continuous mandarin speech recognition show the method is capable of inducing the most crucial phonetic contexts and obtains significant error reduction with far fewer parameters,compared with that obtained by using manually designed context-dependent scaling parameters.
