This work proposes an approach to address the problem of improving content selection in automatic text summarization by using some statistical tools. This approach is a trainable summarizer, which takes into account several features, for each sentence to generate summaries. First, we investigate the effect of each sentence feature on the summarization task. Then we use all features in combination to train cellular automata (CA), genetic programming approach and fuzzy approach in order to construct a text summarizer for each model. Furthermore, we use trained models to test summarization performance. The proposed approach performance is measured at several compression rates on a data corpus composed of 17 English scientific articles. This article shows that some features are more important to construct models rather than other.
Features such as severe resource limitations, wireless communication media, network variable topology along with other IoT constraints, have led to increased faults and needs for fault tolerance guarantee in order to network correct performance. Accordingly, many studies have tried to improve this basic field by focusing on different techniques. But past methods are inefficient in stability guarantee and data exchange accuracy with the occurrence of error. In this paper, a method called FTRTA based on the development of RPL protocol and data distribution techniques has been introduced. Distribution techniques are effective in improving the balance of the network traffic load and fault tolerance. FTRTA has designed based on this technique and three operational steps. In the first step, the situation of network nodes is evaluated and analyzed in the same way as in the process of sending DIO messages. In the second step, the network communication graph is formed. Finally in the third step, data transmission is based on distribution technique with the aim of ensuring fault tolerance. The results of simulation using the Cooja software indicate high FTRTA performance in improving factors such as data delivery ratio and network throughput compared to similar studies.
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.