A Comparative Study of Linear, Random Forest and AdaBoost Regressions for Modeling Non-Traditional Machining

Non-traditional machining (NTM) has gained significant attention in the last decade due to its ability to machine conventionally hard-to-machine materials. However, NTMs suffer from several disadvantages such as higher initial cost, lower material removal rate, more power consumption, etc. NTMs involve several process parameters, the appropriate tweaking of which is necessary to obtain economical and suitable results. However, the costly and time-consuming nature of the NTMs makes it a tedious and expensive task to manually investigate the appropriate process parameters. The NTM process parameters and responses are often not linearly related and thus, conventional statistical tools might not be enough to derive functional knowledge. Thus, in this paper, three popular machine learning (ML) methods (viz. linear regression, random forest regression and AdaBoost regression) are employed to develop predictive models for NTM processes. By considering two high-fidelity datasets from the literature on electro-discharge machining and wire electro-discharge machining, case studies are shown in the paper for the effectiveness of the ML methods. Linear regression is observed to be insufficient in accurately mapping the complex relationship between the process parameters and responses. Both random forest regression and AdaBoost regression are found to be suitable for predictive modelling of NTMs. However, AdaBoost regression is recommended as it is found to be insensitive to the number of regressors and thus is more readily deployable.

MIA3 Splice Defect in Cane Corso Dogs with Dental-Skeletal-Retinal Anomaly (DSRA)

We investigated a hereditary syndrome in Cane Corso dogs. Affected dogs developed dental-skeletal-retinal anomaly (DSRA), clinically characterized by brittle, discolored, translucent teeth, disproportionate growth and progressive retinal degeneration resulting in vision loss. Combined linkage and homozygosity mapping delineated a 5.8 Mb critical interval. The comparison of whole genome sequence data of an affected dog to 789 control genomes revealed a private homozygous splice region variant in the critical interval. It affected the MIA3 gene encoding the MIA SH3 domain ER export factor 3, which has an essential role in the export of collagen and other secreted proteins. The identified variant, XM_005640835.3:c.3822+3_3822+4del, leads to skipping of two exons from the wild type transcript, XM_005640835.3:r.3712_3822del. Genotypes at the variant were consistent with monogenic autosomal recessive mode of inheritance in a complete family and showed perfect genotype-phenotype association in 18 affected and 22 unaffected Cane Corso dogs. MIA3 variants had previously been shown to cause related phenotypes in humans and mice. Our data in dogs together with the existing functional knowledge of MIA3 variants in other mammalian species suggest the MIA3 splice defect and a near complete loss of gene function as causative molecular pathomechanism for the DSRA phenotype in the investigated dogs.

Digital Image Denoising Techniques Based on Multi-Resolution Wavelet Domain with Spatial Filters: A Review

Recently, with the explosion in the number of digital images captured every day in all life aspects, there is a growing demand for more detailed and visually attractive images. However, the images taken by current sensors are inevitably degraded by noise in various fields, such as medical, astrophysics, weather forecasting, etc., which contributes to impaired visual image quality. Therefore, work is needed to reduce noise by preserving the textural, information, and structural features of the image. So far, there are different techniques for reducing noise that various researchers have done. Each technique has its advantages and disadvantages. In this paper, a review of some significant work in the field of image denoising based on that the denoising methods is presented. These methods can be classified as wavelet domain, spatial domain, or both methods can combine to obtain the advantage them. After a brief discussion, the classification of image denoising techniques is explained. A comparative analysis of various image denoising methods is also performed to help researchers in the image denoising area. Besides, standard measurement parameters have been used to compute the results and to evaluate the performance of the used denoising techniques. This review paper aims to provide functional knowledge of image denoising methods in a nutshell for applications using images to provide ease for selecting the ideal strategy according to the necessity.

FINER: enhancing the prediction of tissue-specific functions of isoforms by refining isoform interaction networks

Annotating the functions of gene products is a mainstay in biology. A variety of databases have been established to record functional knowledge at the gene level. However, functional annotations at the isoform resolution are in great demand in many biological applications. Although critical information in biological processes such as protein–protein interactions (PPIs) is often used to study gene functions, it does not directly help differentiate the functions of isoforms, as the ‘proteins’ in the existing PPIs generally refer to ‘genes’. On the other hand, the prediction of isoform functions and prediction of isoform–isoform interactions, though inherently intertwined, have so far been treated as independent computational problems in the literature. Here, we present FINER, a unified framework to jointly predict isoform functions and refine PPIs from the gene level to the isoform level, enabling both tasks to benefit from each other. Extensive computational experiments on human tissue-specific data demonstrate that FINER is able to gain at least 5.16% in AUC and 15.1% in AUPRC for functional prediction across multiple tissues by refining noisy PPIs, resulting in significant improvement over the state-of-the-art methods. Some in-depth analyses reveal consistency between FINER’s predictions and the tissue specificity as well as subcellular localization of isoforms.

Extra-forebrain impact of antipsychotics indicated by c-Fos or FosB/ΔFosB expression: A minireview

It is apparent that the c-Fos and FosB/ΔFosB immunohistochemistry has generally become a useful tool for determining the different antipsychotic (AP) drugs activities in the brain. It is also noteworthy that there are no spatial limits, while to the extent of their identification over the whole brain axis. In addition, they can be in a parallel manner utilized in the unmasking of the brain cell phenotype character activated by APs and by this way also to identify the possible brain circuits underwent to the APs action. However, up to date, the number of APs involved in the extra-striatal studies is still limited, what prevents the possibility to fully understand their extra-striatal effects as a complex as well as differentiate their extra-striatal impact in qualitative and quantitative dimensions. Actually, it is very believable that more and more anatomical/functional knowledge might bring new insights into the APs extra-striatal actions by identifying new region-specific activities of APs as well as novel cellular targets affected by APs, which might reveal more details of their possible side effects of the extra-striatal origin.

THE INFLUENCE OF DIFFERENTIATED MATHEMATICAL TASKS ON STUDENTS' LOGICAL-COMBINATORIAL THINKING IN ELEMENTARY MATHEMATICS TEACHING

The aim of this research was to examine the influence of differentiated tasks on the development of logical-combinatorial thinking abilities of the first grade of primary school students, using the experimental-research method. The research was conducted on the sample (N=60) chosen from the population of first-grade students of primary school "Nikola Tesla" in Novi Sad. Obtained research results showed the high influence of differentiated mathematical problems on students' logical-combinatorial thinking and functional knowledge in elementary mathematics education. The results' practical implication mirrors the possibility of their application in the domain of the improvement of students' cognitive abilities and functional knowledge from the very beginning of the educational journey.

Data-driven biological network alignment that uses topological, sequence, and functional information

Background Network alignment (NA) can transfer functional knowledge between species’ conserved biological network regions. Traditional NA assumes that it is topological similarity (isomorphic-like matching) between network regions that corresponds to the regions’ functional relatedness. However, we recently found that functionally unrelated proteins are as topologically similar as functionally related proteins. So, we redefined NA as a data-driven method called TARA, which learns from network and protein functional data what kind of topological relatedness (rather than similarity) between proteins corresponds to their functional relatedness. TARA used topological information (within each network) but not sequence information (between proteins across networks). Yet, TARA yielded higher protein functional prediction accuracy than existing NA methods, even those that used both topological and sequence information. Results Here, we propose TARA++ that is also data-driven, like TARA and unlike other existing methods, but that uses across-network sequence information on top of within-network topological information, unlike TARA. To deal with the within-and-across-network analysis, we adapt social network embedding to the problem of biological NA. TARA++ outperforms protein functional prediction accuracy of existing methods. Conclusions As such, combining research knowledge from different domains is promising. Overall, improvements in protein functional prediction have biomedical implications, for example allowing researchers to better understand how cancer progresses or how humans age.

Barriers to implementation of distance learning during the COVID-19 outbreak: Teacher perspective

Since the outbreak of the COVID-19 pandemic in early 2020, distance learning has become one of the main educational issues globally. With the transition of all instruction to the online environment, teachers in Serbia have faced a number of challenges and barriers that have affected the quality of their work. In this paper, we wanted to analyse the barriers that teachers faced during the first months of distance learning. The research was conducted combining quantitative and qualitative analysis of data collected on a sample of 122 high school teachers from the Southeast Serbia (Nis, Leskovac). The results show that teachers recognise evaluation barriers as the predominant ones, followed by organisational-administrative ones, while the least represented were material-technical barriers to distance learning. The findings also confirm that material and technical barriers are most common among teachers with the longest work experience, as well as that organisational-administrative and socio-emotional barriers are the least common among teachers of vocational subjects. Although the focus of the paper was on the barriers in the implementation of distance learning, it can be concluded that teachers recognise certain benefits of this type of instruction and indicate that it can be used as a supplement to regular instruction. The main pedagogical implications of the paper refer to the empowerment of teachers through professional development in the field of distance learning, but also to the need to create new professional development programmes in this field which will enable the development of functional knowledge and relevant competencies for the immediate situational context of modern instruction.

Ortoepija u programima za mlađe razrede osnovne škole

We point out the importance of working on the correct articulation of sounds and analyze the representation of orthoepy in the curricular contents for the subject Serbian Language in the lower grades of primary school. The results of the content analysis show that the importance of a continuous work on the correct articulation of sounds has not been recognized in the new curricula. The work on the pronunciation of sounds is included only in the curriculum for the first grade. A comparative analysis of the old (2004, 2005, 2006) and new curricula (2017, 2018, 2019) has shown that the reform rejected all the contents that continuously extended the work on the pronunciation of sounds until the fourth grade. The state of the pronunciation norm in practice, confirmed by the research results, indicates numerous problems of atypical articulation that is not organic in nature. Therefore, the pedagogical implications are that the changes of and/or additions to the content of orthoepy related to the pronunciation of sounds should be included in the mother tongue curricula for the lower grades of primary school and made operational through outcomes as the functional knowledge of the pronunciation norm. These are the contents that were represented in the curricula before the reform, and they refer to the pronunciation of affricates (č, ć, dž, đ) and fricatives (h) in the third and fourth grades. This would enable continuity in the work of the practitioners which is necessary to correct the mistakes in the pronunciation of sounds that are not organic in nature and to strengthen the correct articulation.