Extreme Learning Machine (ELM) has proved to be well suited to different kinds of classification and regression problems. However, failing to seek deep representation of raw data completely brought ...by shallow architecture has made a plenty of research work stagnant, when ELM was chosen as the basic model. Recent years, deep ELM models like Hierarchical ELM (H-ELM), deep representations learning via ELM (Dr-ELM) have been proposed to be applied in multiple applications in machine learning. In this paper, a novel double deep ELMs ensemble system (DD-ELMs-ES) is proposed to focus on the problem of time series forecasting. In the proposed system, besides H-ELM and Dr-ELM are utilized as the basic models, a novel Constrained H-ELM (CH-ELM) is presented and serves as another basic model as well. CH-ELM intends to constrain the hidden neurons’ input connection weights, so that they could be consistent with the directions of sample vectors. Whats more, a self-adaptive ReTSP-Trend pruning technique is proposed to implement ensemble pruning in DD-ELMs-ES. Benefited from the merits of combining deep learning scheme with ensemble pruning paradigm, in the empirical results, DD-ELMs-ES demonstrates better generalization performance than the basic deep ELM models and some other state-of-the-art algorithms in tackling with time series forecasting tasks.
In a series of high performance diverted discharges on DIII-D, we demonstrate that strong negative triangularity (NT) shaping robustly suppresses all edge-localized mode (ELM) activity over a wide ...range of plasma conditions: ⟨n⟩ = 0.1 − 1.5 × 1020 m−3, Paux = 0 − 15 MW and |Bt| = 1 − 2.2 T, corresponding to Ploss/PLH08 ∼ 8. The full dataset is consistent with the theoretical prediction that magnetic shear in the NT edge inhibits access to ELMing H-mode regimes; all experimental pressure profiles are found to be at or below the infinite-n ballooning stability limit. Our present dataset also features edge pressure gradients in strong NT that are closer to an H–mode than a typical L-mode plasma, supporting the consideration of NT for reactor design.
Sign language is one of the most important communication tools for hearing impaired people. In this study, the recognition of two-handed dynamic words in Turkish Sign Language (TSL) was studied using ...the LMC device. As a result of the repetition of 26 dynamic words, which were determined by considering the similarities and differences between them, by 6 participants, two data sets were obtained by extracting two types of feature sets. By applying a three-stage strategy to these feature sets, word recognition performances are presented by considering many aspects. These stages are data regularization, feature selection and dimension reduction. By performing these stages, new datasets with less dimension were obtained. The recognition performance was tested with six different ELM networks and the results were compared. Five-fold cross-validation was used to test the validity of the proposed system and accuracy of the obtained results. According to the results obtained with a comprehensive analysis, it has been seen that the Meta-ELM classifier maintains its performance rate and gives the highest performance. At the same time it has been observed that the Meta-ELM classifier has a stable structure that offers less user intervention.
The study aims to examine the factors influencing the long-term educators' motivation to use ELMS. The study was conducted at School of Big Data and Computer Science, Hechi University, China. The ...research methodology consisted of the author's developed online questionnaire, which was designed to determine the motives for using ELMS in the educator's work. The sample is represented by 214 respondents, most of whom are men (64.1%), the bulk of the participants (46.1%) are 35-50 years old, 38.8% have 5-10 years of work experience in educational institutions, 29.4% are associate professors. It follows from the results that teachers have significant intentions to use ELMS in their future professional activities (overall mean = 3.99). Creation by the administration and government of favorable conditions for the introduction and use of technology did not receive high support (overall mean = 2.82). The results obtained can be used to build mathematical models in educational institutions that will help determine the intentions of the long-term use of ELMS by the teaching staff. Adjusted R-squared (0.428) of the model indicates a good level of predictive power.
•Full-length transcriptomes obtained for four Ulmus species.•There are significant differences in the genetic features between different elms.•The divergence time of four Ulmus species was in the ...period of extreme climate change.•In this study, 22 genes were found, which were affected by positive selection pressure during the evolution of elms.
Ulmus spp. have a wide distribution, strong adaptability, and high application value. However, due to the outbreak of Dutch elm disease and a lack of nuclear genome data, studies on Ulmus spp. are lacking. In this study, we obtained full-length transcriptomes from four elm species, with an average of 64,529 transcripts per species. Among these transcripts, an average of 6410 long noncoding RNAs were obtained per species. We performed SSR site detection and primer design and obtained an average of 20,650 SSR primer pairs per elm species. Fisher’s exact test revealed a large difference in the enrichment of functional genes shared between Ulmus parvifolia and three other elms, which represented 31 Gene Ontology terms, four Kyoto Encyclopedia of Genes and Genomes pathways, and two transcription factors. Phylogenetic evolution and divergence time analyses indicated that U. parvifolia diverged from the three other elms ca. 13.98 Mya; the divergence time of Ulmus macrocarpa, Ulmus davidiana, and Ulmus pumila was ca. 10.84–7.25 Mya. Furthermore, we identified 22 genes that were positively selected, and transcriptional profiling analysis showed that the expression levels of those genes showed marked changes under high temperature. These positively selected genes are widely involved in the ubiquitin system, nucleotide excision repair, protein modification, circadian rhythm regulation, light stimulus response, abiotic stimulus response, MAPK signaling, and plant pathogenicity interactions; they may play an important role in the adaptation of elms to environmental changes. This study provides a basis for the study of adaptive evolution, genetic diversity and functional gene development in Ulmus spp.