Search

Deep Forest is a prominent machine learning algorithm known for its high accuracy in forecasting. Compared with deep neural networks, Deep Forest has almost no multiplication operations and has better performance on small datasets. However, due to the deep structure and large forest quantity, it suffers from large amounts of calculation and memory consumption. In this paper, an efficient hardware accelerator is proposed for deep forest models, which is also the first work to implement Deep Forest on FPGA. Firstly, a delicate node computing unit (NCU) is designed to improve inference speed. Secondly, based on NCU, an efficient architecture and an adaptive dataflow are proposed, in order to alleviate the problem of node computing imbalance in the classification process. Moreover, an optimized storage scheme in this design also improves hardware utilization and power efficiency. The proposed design is implemented on an FPGA board, Intel Stratix V, and it is evaluated by two typical datasets, ADULT and Face Mask Detection. The experimental results show that the proposed design can achieve around 40x speedup compared to that on a 40 cores high performance x86 CPU., 5 pages, 5 figures, conference

Background: Invasive alien insects threaten agriculture, biodiversity, and human livelihoods globally. Unfortunately, insect invasiveness still cannot be reliably predicted. Empirical policies of insect pest quarantine and inspection are mainly designed against species that are already problematic.Results: We conducted a comparative genomic analysis of 37 invasive insect species and six non-invasive insect species, showing that the gene families associated with defense, protein and nucleic acid metabolism, chemosensory function, and transcriptional regulation were significantly expanded in invasive insects, suggesting that enhanced abilities in self-protection, nutrition exploitation, and locating food or mates are intrinsic features conferring invasiveness in insects. By using these intrinsic genome features, we proposed an invasiveness index and estimated the invasiveness of 99 other insect species with genome data, classifying them as highly, moderately, or minimally invasive. Insects possessing all these aforementioned enhanced abilities are predicted to be highly invasive, and vice versa. Next, a logistic-regression classifier was trained to predict insect invasiveness, achieving 93.2% accuracy. Conclusions: We present evidence that several traits may confer invasiveness in insects and these features can be used to predict insect invasiveness accurately, and we quantify insect invasiveness with an invasiveness index.

Laminated ZrB2–SiC ultra-high temperature ceramics (UHTCs) with different layer thickness ratios and strong interfaces were fabricated by hot-pressing. Residual stresses developed on the surfaces of laminated ZrB2-SiC ceramics were evaluated by X-ray diffraction (XRD) and indentation techniques. Results showed that the characteristic XRD peaks of the ZrB2 phase on the surface of the laminated ceramics presented a shift due to the residual surface stress existence. Both XRD and indentation tested results suggested that the surface residual stress increases with the increasing layer thickness ratio confirming the theoretical analysis and calculation reported by our previous work. The presence of a compressive residual stress in the external layer of the heterogeneous material is expected to improve the mechanical properties of laminated ZrB2-SiC ceramics.

The codling moth Cydia pomonella, a major invasive pest of pome fruit, has spread around the globe in the last half century. We generated a chromosome-level scaffold assembly including the Z chromosome and a portion of the W chromosome. This assembly reveals the duplication of an olfactory receptor gene (OR3), which we demonstrate enhances the ability of C. pomonella to exploit kairomones and pheromones in locating both host plants and mates. Genome-wide association studies contrasting insecticide-resistant and susceptible strains identify hundreds of single nucleotide polymorphisms (SNPs) potentially associated with insecticide resistance, including three SNPs found in the promoter of CYP6B2. RNAi knockdown of CYP6B2 increases C. pomonella sensitivity to two insecticides, deltamethrin and azinphos methyl. The high-quality genome assembly of C. pomonella informs the genetic basis of its invasiveness, suggesting the codling moth has distinctive capabilities and adaptive potential that may explain its worldwide expansion., The codling moth, Cydia pomonella, is one of the major pests of pome fruit (apples and pears) and walnuts. Here, the authors sequence and analyze its genome, providing insights on olfactory and detoxification processes that may underlie its worldwide expansion.

Insect pests reduce yield and cause economic losses, which are major problems in agriculture. Parasitic wasps are the natural enemies of many agricultural pests and thus have been widely used as biological control agents. Plants, phytophagous insects and parasitic wasps form a tritrophic food chain. Understanding the interactions in this tritrophic system should be helpful for developing parasitic wasps for pest control and deciphering the mechanisms of parasitism. However, the genomic resources for this tritrophic system are not well organized. Here, we describe the WaspBase, a new database that contains 573 transcriptomes of 35 parasitic wasps and the genomes of 12 parasitic wasps, 5 insect hosts and 8 plants. In addition, we identified long non-coding RNA, untranslated regions and 25 widely studied gene families from the genome and transcriptome data of these species. WaspBase provides conventional web services such as Basic Local Alignment Search Tool, search and download, together with several widely used tools such as profile hidden Markov model, Multiple Alignment using Fast Fourier Transform, automated alignment trimming and JBrowse. We also present a collection of active researchers in the field of parasitic wasps, which should be useful for constructing scientific networks in this field.

Figure S1. Flow cytometry estimation of the genome size for the M. cingulum. Figure S2. The distribution of 17-mer frequency in M. cingulum genome sequencing reads. Figure S3. Distribution of GC content, CpG Obs/ExpRatios of M. cingulum(Mcin), N. vitripennis(Nvit) and A. mellifera(Amel). Figure S4. COG function classification of the OGS in M. cingulum. Figure S5. KEGG pathway analysis of the OGS in M. cingulum. Figure S6. GO classification of the OGS in M. cingulum. Figure S7. Venn diagram of the homologous protein-coding genes among three wasps (M. cingulum, C. solmsi, N. vitripennis) and fruit fly (D. melanogaster). Figure S8. Phylogenetic relationship of CSP proteins from A. mellifera, C. floridanum, C. solmsi, M. cingulum, N.vitripennis, S.invicta. Figure S9. Phylogenetic relationship of GR proteins from A. mellifera, C. floridanum, C. solmsi, M. cingulum, N.vitripennis, S.invicta. Figure S10. Phylogenetic relationship of IR proteins from A. mellifera, C. floridanum, C. solmsi, M. cingulum, N.vitripennis, S.invicta. Figure S11. Phylogenetic relationship of OR proteins from C. floridanum, D. melanogaster and M. cingulum. Figure S12. Phylogenetic relationship of OBP proteins from A. mellifera, C. floridanum, C. solmsi, M. cingulum, N.vitripennis, S.invicta. Figure S13. Phylogenetic relationship of SNMP proteins from A.mellifera, C. floridanum, C. solmsi, M. cingulum, N.vitripennis, S.invicta. Figure S14. Phylogenetic relationship of GST proteins from A. mellifera, C. floridanum, C. solmsi, M. cingulum, N.vitripennis, S.invicta. Figure S15. Phylogenetic relationship of P450 proteins from N. vitripennis, D. melanogaster and M. cingulum. Figure S16. Phylogenetic relationship of ABC proteins from M. cingulum and D. melanogaster. Figure S17. Different expression levels of miR-14b in different developmental stages of M. cingulum.Table S1. Genome sequencing data of M. cingulum. Table S2. Estimation of M. cingulum genome size using K-mer analysis. Table S3. Summary of the M. cingulum genome assembly. Table S4. The published insect genomes. Table S5. The genome assembly assessment on different insects. Table S6. Classification of repeat sequences identified in the M. cingulum genome. Table S7. Genome features of the M. cingulum, N. vitripennis and A. mellifera. Table S8. Gene features of M. cingulum, N. vitripennis and A. mellifera. Table S9. The insects with OGSs in InsectBase. Table S10. Hemomucin genes in eight wasps. Table S11. The different gene expression of embryo and pseudogerm transcriptomes in KEGG pathway. Table S12. The differently expressed miRNAs in embryo and mixed embryo transcriptomes. Table S13. Comparison of gene numbers for chemoreception in A.mellifera, C. floridanum, C. solmsi, M. cingulum, N. vitripennis and S. invicta. Table S14. Comparison of gene numbers for Gene families associated with insecticide resistance and detoxification in D. melanogaster, A. mellifera, C. floridanum, C. solmsi, M. cingulum, N. vitripennis and S. invicta. Table S15. Comparison of gene numbers of insect immune in A. mellifera, C. floridanum, C. solmsi, M. cingulum, N. vitripennis and S. invicta. Table S16. The PCR primer for target genes of mci-miR-14b. (PDF 6076 kb)

The multi-axial forging (MAF) process was introduced into the strain induced metal activation (SIMA) process to replace conventional forging. Microstructure evolution of MAF formed AZ80 magnesium alloy during partial remelting was investigated. Furthermore, the tensile mechanical properties for AZ80 magnesium alloy thixoextruded from the starting materials treated by MAF were determined. For comparison, as-cast AZ80 magnesium alloy was also thixoextruded. The results show that the SIMA route produced ideal, fine semi-solid microstructure, in which almost completely spheroidal primary solid grains had a little amount of entrapped liquid. The microstructure of the as-cast alloy in the semi-solid state is less spheroidized compared with the MAF alloy under the similar isothermal holding conditions. With prolonged holding time, the size of the solid grain increases and the degree of spheroidization is improved in the MAF formed alloys. However, the solid grain size of the as-cast alloys decreases initially, and then increases with further increasing temperature. The tensile mechanical properties for AZ80 magnesium alloy thixoextruded from the starting material produced by MAF are better than those of AZ80 magnesium alloy thixoextruded from the starting material produced by casting. The ultimate tensile strength, yield strength and elongation of the alloy thixoextruded from the starting material produced by MAF are 314 MPa, 238 MPa and 14%, respectively.

The NCBI accession numbers of insect ace-1 and ace-2 genes

The SRA accession numbers of 971 RNA-Seq data used for detecting mutations