Condition monitoring of bearings is an open issue. The use of the stator current to monitor induction motors has been validated as a very advantageous and practical way to detect several types of faults. Nevertheless, for bearing faults the use of vibrations or sound generally offers better results in the accuracy of the detection although with some disadvantages related to the sensors used for monitoring. To improve the performance of bearing monitoring, it is proposed to take advantage of more information available in the current spectra, beyond the usually employed, incorporating the amplitude of a significant number of sidebands around the first eleven harmonics, growing exponentially the number of fault signatures. This is especially interesting for inverter-fed motors. But, in turn, this leads to the problem of overfitting when applying a classifier to perform the fault diagnosis. To overcome this problem, and still exploit all the useful information available in the spectra, it is proposed to use shrinkage methods, which have been lately proposed in machine learning to solve the overfitting issue when the problem has much more variables than examples to classify. A case study with a motor is shown to prove the validity of the proposal

Background, Leucoptera coffeella (Guerin-Meneville, 1842) is a moth species (Lyonetiidae, Lepidoptera) pest that causes severe losses to coffee crops. Further information about its genomic data is required to allow molecular strategies for the development of sustainable pesticides and to gain in-depth knowledge on phylogenetics. However, the closest complete genome available is within the superfamily level (Yponomeutoidea). Here we report the generation of the first long-read genome, transcriptome and proteome results of L. coffeella and the in silico analysis performed in these molecular levels to investigate genes involved in the siRNA processing. Results, PACBio and paired-end Illumina combined DNA sequencing from pupae samples resulted in more than 436 Gb subreads and 31Mb reads with N50 read length of 15,512 nt, mean read length 13.8 Kb and max read length 420.7 Kb. Additionally, 20Gb data of short DNA sequencing was combined to produce 1,984 contigs comprising 397 Mb in total. The longest and shortest scaffold sizes are 10,809,567 nt and 15,247 nt, respectively (mean size 200,178 nt). The N50 scaffold was 275,598 nt and the GC content was 36.10%. Predicted coding DNA sequences counted 39.930 gene models. Searching of 5286 BUSCO groups revealed 91.7 percent of completeness (single and duplicated genes combined) compared to lepidoptera genomes (lepidoptera_odb10). Flow cytometry showed the 1C DNA content is approximately 295 Mb. RNA-Seq from seven development stages resulted in 28294 identified transcripts. Additionally, proteomics from immature stages resulted in 2045 proteins matching the gene models. Conclusions, This first nuclear genome of the Lyonetiidae family brings valuable molecular resources to study Lepidoptera genomes. Genome, transcriptome and proteome sequencing to raise genome annotation precision may resolve uncovered taxonomic issues. In addition, these combined approaches provide insights into plant-insect interaction players, as horizontally transferred genes (HGT) and endosymbionts. Put together, the generated data enables the development of molecular tools towards sustainable biotechnology solutions for lepidopteran pest control.