Microarray contains a large matrix of information and has been widely used by biologists and bio data scientist for monitoring combinations of genes in different organisms. The coherent patterns in all continuous columns are mined in gene microarray data matrices. It is investigated, in this study, the coherent patterns in all continuous columns in gene microarray data matrix by developing the time series similarity measure for the coherent patterns in all continuous columns, as well as the evaluation function for verifying the proposed algorithm and the corresponding biclusters. The continuous time changes are taken into account in the coherent patterns in all continuous columns, and co-expression patterns in time series are searched. In order to use all the common information between sequences, a similarity measure for the coherent patterns in continuous columns is defined in this paper. To validate the efficiency of the similarity measure to mine biological information at continuous time points, an evaluation function is defined to measure biclusters and an effective algorithm is proposed to mine the biclusters. Simulation experiments are conducted to verify the biological significance of the biclusters, which include synthetic datasets and real gene microarray datasets. The performance of the algorithm is analyzed and the results show that the algorithm is highly efficient.

No abstract

No abstract

The reinforcement learning-based routing, modulation, and spectrum assignment has been regarded as an emerging paradigm for resource allocation in the elastic optical networks. One limitation is that the learning process is highly dependent on the training environment, such as the traffic pattern or the optical network topology. Therefore, re-training is required in case of network topology or traffic pattern variations, which consumes a great amount of computation power and time. To ease the requirement of re-training, we propose a policy distillation scheme, which distills knowledge from a well-trained teacher model and then transfers the knowledge to the to-be-trained student model, so that the training of the latter can be accelerated. Specifically, the teacher model is trained for one training environment (e.g., the topology and traffic pattern) and the student model is for another training environment. The simulation results indicate that our proposed method can effectively speed up the training process of the student model, and it even leads to a lower blocking probability, compared with the case that the student model is trained without knowledge distillation.

No abstract