Pilot Study on Analysis of Electroencephalography Signals from Children with FASD with the Implementation of Naive Bayesian Classifiers

In this paper Naive Bayesian classifiers were applied for the purpose of differentiation between the EEG signals recorded from children with Fetal Alcohol Syndrome Disorders (FASD) and healthy ones. This work also provides a brief introduction to the FASD itself, explaining the social, economic and genetic reasons for the FASD occurrence. The obtained results were good and promising and indicate that EEG recordings can be a helpful tool for potential diagnostics of FASDs children affected with it, in particular those with invisible physical signs of these spectrum disorders.

Bayesian approximations to the theory of visual attention (TVA) in a foraging task

Foraging as a natural visual search for multiple targets has increasingly been studied in humans in recent years. Here, we aimed to model the differences in foraging strategies between feature and conjunction foraging tasks found by Kristjánsson et al. (2014). Bundesen (1990) proposed the Theory of Visual Attention (TVA) as a computational model of attentional function that divides the selection process into filtering and pigeonholing. The theory describes a mechanism by which the strength of sensory evidence serves to categorize elements. We combined these ideas to train augmented Naïve Bayesian classifiers using data from Kristjánsson et al. (2014) as input. Specifically, we attempted to answer whether it is possible to predict how frequently observers switch between different target types during consecutive selections (switch rates) during feature and conjunction foraging using Bayesian classifiers. We formulated eleven new parameters that represent key sensory and bias information that could be used for each selection during the foraging task and tested them with multiple Bayesian models. Separate Bayesian networks were trained on feature and conjunction foraging data, and parameters that had no impact on the model's predictability were pruned away. We report high accuracy for switch prediction in both tasks from the classifiers, although the model for conjunction foraging was more accurate. We also report our Bayesian parameters in terms of their theoretical associations to TVA parameters, π_j (denoting the pertinence value) and β_i (denoting the decision-making bias).

Classifying Drug Ratings Using User Reviews with Transformer-Based Language Models

Social web contains a large amount of information with user sentiment and opinions across different fields. For example, drugs.com provides users' textual review and numeric ratings of drugs. However, text reviews may not always be consistent with the numeric ratings. In this project, we built different classification models to classify user ratings of drugs with their textual review. Multiple supervised machine learning models including Random Forest and Naive Bayesian classifiers were built with drug reviews using TF-IDF features as input. Also, transformer-based neural network models including BERT, BioBERT, RoBERTa, XLNet, ELECTRA, and ALBERT were built for classification using the raw text as input. Overall, BioBERT model outperformed the other models with the overall accuracy of 87%. This research demonstrated that transformer-based classification models can be used to classify drug reviews and identify reviews that are inconsistent with the ratings.

Taxonomical evaluation of plant genetic markers by Bayesian Classifier

DNA barcodes are standardized sequences that range between 400-800 bp, vary at different taxonomic levels, and make it possible to identify individuals of species that have been previously assigned taxonomically. Several barcodes have been identified in different groups in the tree of life. However, there are groups that lack an accurate DNA marker, and even more so, accurate strategies that enable verification of their taxonomic affiliation. Several DNA barcodes have been postulated for plants, nonetheless, their classification potential has not been evaluated for metabarcoding, and as a result, it would appear as no one of them excels above the others in this area. One tool that has recently gained traction is Naïve Bayesian Classifiers; this type of classifier is based on the independence of attributes and the allocation of categories in each context. The present study aims at evaluating the classification power of several plant genetic markers that have been proposed as barcodes (trnL, rpoB, rbcL, matK, psbA-trnH and psbK) using a Naïve Bayesian Classifier, in order to determine the markers with higher performance at different taxonomic levels for metabarcoding analysis and to identify problematic genera at the time of species assignment. We propose matK and trnL as potential candidates up to the genus assignment. Some problematic genera (Aegilops, Gueldenstaedtia, Helianthus, Oryza, Shorea, Thysananthus and Triticum) within certain families in a sample could lead to misclassification no matter which marker is used. Finally, we propose recommendations when performing taxonomic identification analysis of plants in samples with multiple individuals.

Probabilistic Contextual and Structural Dependencies Learning in Grammar-Based Genetic Programming

Genetic Programming is a method to automatically create computer programs based on the principles of evolution. The problem of deceptiveness caused by complex dependencies among components of programs is challenging. It is important because it can misguide Genetic Programming to create sub-optimal programs. Besides, a minor modification in the programs may lead to a notable change in the program behaviours and affect the final outputs. This paper presents Grammar-based Genetic Programming with Bayesian Classifiers (GBGPBC) in which the probabilistic dependencies among components of programs are captured using a set of Bayesian network classifiers. Our system was evaluated using a set of benchmark problems (the deceptive maximum problems, the royal tree problems, and the bipolar asymmetric royal tree problems). It was shown to be often more robust and more efficient in searching the best programs than other related Genetic Programming approaches in terms of the total number of fitness evaluation. We studied what factors affect the performance of GBGPBC and discovered that robust variants of GBGPBC were consistently weakly correlated with some complexity measures. Furthermore, our approach has been applied to learn a ranking program on a set of customers in direct marketing. Our suggested solutions help companies to earn significantly more when compared with other solutions produced by several well-known machine learning algorithms, such as neural networks, logistic regression, and Bayesian networks.