Mastitis is one of the most frequently encountered diseases in dairy cattle, negatively affecting animal welfare and milk production. For this reason, contributions to understanding its genomic architecture are of great interest. Genome-wide association studies (GWAS) have identified multiple loci associated with somatic cell score (SCS) and mastitis in cattle. However, most of the studies have been conducted in different parts of the world on various breeds, and none of the investigations have studied the genetic architecture of mastitis in Romanian dairy cattle breeds up to this point in time. In this study, we report the first GWAS for SCS in dairy cattle breeds from Romania. For GWAS, we used an Axiom Bovine v3 SNP-chip (>63,000 Single Nucleotide Polymorphism -SNPs) and 33,330 records from 690 cows belonging to Romanian Spotted (RS) and Romanian Brown (RB) cattle. The results found one SNP significantly associated with SCS in the RS breed and 40 suggestive SNPs with −log₁₀ (p) from 4 to 4.9 for RS and from 4 to 5.4 in RB. From these, 14 markers were located near 12 known genes (AKAP8, CLHC1, MEGF10, SATB2, GATA6, SPATA6, COL12A1, EPS8, LUZP2, RAMAC, IL12A and ANKRD55) in RB cattle, 3 markers were close to ZDHHC19, DAPK1 and MMP7 genes, while one SNP overlapped the HERC3 gene in RS cattle. Four genes (HERC3, LUZP2, AKAP8 and MEGF10) associated with SCS in this study were previously reported in different studies. The most significant SNP (rs110749552) associated with SCS was located within the HERC3 gene. In both breeds, the SNPs and position of association signals were distinct among the three parities, denoting that mastitis is controlled by different genes that are dependent according to parity. The current results contribute to an expansion in the body of knowledge regarding the proportion of genetic variability explained by SNPs for SCS in dairy cattle.

Hate speech is an important problem in the management of user-generated content. To remove offensive content or ban misbehaving users, content moderators need reliable hate speech detectors. Recently, deep neural networks based on the transformer architecture, such as the (multilingual) BERT model, have achieved superior performance in many natural language classification tasks, including hate speech detection. So far, these methods have not been able to quantify their output in terms of reliability. We propose a Bayesian method using Monte Carlo dropout within the attention layers of the transformer models to provide well-calibrated reliability estimates. We evaluate and visualize the results of the proposed approach on hate speech detection problems in several languages. Additionally, we test whether affective dimensions can enhance the information extracted by the BERT model in hate speech classification. Our experiments show that Monte Carlo dropout provides a viable mechanism for reliability estimation in transformer networks. Used within the BERT model, it offers state-of-the-art classification performance and can detect less trusted predictions.

We argue that results produced by a heuristic optimisation algorithm cannot be considered reproducible unless the algorithm fully specifies what should be done with solutions generated outside the domain, even in the case of simple bound constraints. Currently, in the field of heuristic optimisation, such specification is rarely mentioned or investigated due to the assumed triviality or insignificance of this question. Here, we demonstrate that, at least in algorithms based on Differential Evolution, this choice induces notably different behaviours in terms of performance, disruptiveness, and population diversity. This is shown theoretically (where possible) for standard Differential Evolution in the absence of selection pressure and experimentally for the standard and state-of-the-art Differential Evolution variants, on a special test function and the BBOB benchmarking suite, respectively. Moreover, we demonstrate that the importance of this choice quickly grows with problem dimensionality. Differential Evolution is not at all special in this regard—there is no reason to presume that other heuristic optimisers are not equally affected by the aforementioned algorithmic choice. Thus, we urge the heuristic optimisation community to formalise and adopt the idea of a new algorithmic component in heuristic optimisers, which we refer to as the strategy of dealing with infeasible solutions. This component needs to be consistently: (a) specified in algorithmic descriptions to guarantee reproducibility of results, (b) studied to better understand its impact on an algorithm's performance in a wider sense (i.e., convergence time, robustness, etc.), and (c) included in the (automatic) design of algorithms. All of these should be done even for problems with bound constraints.

Recently a new Grid-based software platform was developed to allow remote sensing image processing for preventing disasters like river floods and forest fires. While several innovative components were presented in research papers in the last year, this paper presents a state-of-the-art of the whole platform and exposes the novelty elements that distinguish it from other similar approaches.