Antimicrobial resistance (AMR) is a global health problem that poses a threat for now and poses an even greater threat for the future. Since the discovery of the first antibiotics, pathogens have developed different mechanisms of resistance against antibiotics. Today, the technology to understand the mechanisms of AMR and their genomics is more competent than ever. This paper provides a wide range of information about using genomic data combined with machine learning for predicting antibiotic resistance and proposes a multi-model approach ASAP (Antibiotic Susceptibility and Antibiogram Prediction) for creating antibiograms. In this work, 10 different machine learning models, including Convolutional Neural Network, Nearest Neighbor, Random Forest, XGBoost, CatBoost, Naive Bayes, Support Vector Machines, Light Gradient Boosting Machine, Gradient Boost, and Logistic Regression, have been tested, evaluated, and compared for their predictive capabilities. For data preprocessing, different methods of feature extraction through n-gram encoding have been tested. For the evaluation of the models, accuracy, recall, precision, and F1 scores are used. Experiments show that models can predict the antibiotic resistance of a given pathogen sequence with up to 0.99 accuracy and 0.90+ macro average recall. The best performing model for this work has been XGBoost with 0.99 accuracy, and the least predictive model has been Naive Bayes with 0.89 accuracy. Our proposed method results shows that machine learning with gene sequences are promising tools to improve the current manual antibiogram creation, maintenance process and can provide healthcare professionals with valuable insights for less empirical antibiotic prescribing.

Abstract Automatic detection of emotions in textual data masses provides priceless opportunities for researchers and also it is inevitable for practitioners. The unfavorable factors involved in text data cause ambiguity and adversely affect the performances of emotion classifiers. Although deep learning approaches spark off significantly successive results, the obtained performances of the classifiers in the literature are commonly evaluated as the overall accuracy. This incomplete evaluation ignores inner class performance and overall accuracy can behave as a hopeful evaluator. In this study, we employed deep learning and meta‐heuristic optimization methods together in order to resolve the ambiguity issue. Moreover, the decision mechanism of a conventional deep learning model is equipped with optimal emotion vectors obtained by optimization processes for each emotion class. Experimental results show that the proposed approach improves the inner class performance by maintaining the overall accuracy scores.

Abstract This paper proposes four novel term evaluation metrics to represent documents in the text categorization where class distribution is imbalanced. These metrics are achieved from the revision of the four common term evaluation metrics:chi-square,information gain,odds ratio, andrelevance frequency. While the common metrics require a balanced class distribution, our proposed metrics evaluate the document terms under an imbalanced distribution. They calculate the degree of relatedness of terms with respect to minor and major classes by considering their imbalanced distribution. Using these metrics in the document representation makes a better distinction between the documents of the minor and major classes and improves the performance of machine learning algorithms. The proposed metrics are assessed over three popular benchmarks (two subsets of Reuters-21578 and WebKB) by using four classification algorithms: support vector machines, naive Bayes, decision trees, and centroid-based classifiers. Our empirical results indicate that the proposed metrics outperform the common metrics in the imbalanced text categorization.

Automatic rule generation of fuzzy systems is a extensively studied topic which is generally handled by using a labeled dataset. This paper presents a new method for this problem which does not rely on training data. It only requests a tiny information which can be roughly acquired from any data and/or domain expert. By using this information, it selects single or multiple influencing factor(s) to determine the consequent part of rules. The experiments were performed on software fault prediction problem, and the resulting rules are compared with the rules obtained from 3 existing rule generation methods which are data-based, expert-based and partially data-based solutions. Results shows that, the proposed method is able to outperform its counterparts in most of the cases.

Abstract In a competent crowd navigation system, it is very important for the agents in the system to plan their movements being aware of the other agents. In this study, we propose the use of machine learning methods to create time‐based global path plans by utilizing the information as to when and where the other agents would be at a future time. The application of a machine learning method in the traditional manner for the global path planning problem is not a straightforward task due to the complexity of data collection; therefore, this study proposes a novel method to apply machine learning methods for global path planning. This enables us to create a context‐free model. We organize experiments to compare our method to a recent and competitive approach that is referred to as the potential‐based method (PBM). We employed three different machine learning methods, namely, artificial neural networks, polynomial regression, and support vector regression. The results of the mass scenario tests and a corridor scenario indicate that the versions with polynomial regression and support vector regression outperform the PBM. This encourages further investigations on the use of machine learning methods for global path planning in crowd navigation.

Hierarchical Fuzzy System (HFS) is a popular approach for handling curse of dimensionality problem occurred in complex fuzzy rule-based systems with various and numerous inputs. However, the processes of modeling and reasoning of HFS have some critical issues to be considered. In this study, the effect of these issues on the accuracy and stability of the resulting system has been investigated, and an end-to-end HFS framework has been proposed. The proposed framework has three main steps such as single system modeling, rule partitioning and HFS reasoning. It is fully automated, generic, almost independent from data, and applicable for any kind of inference problem. In addition, the proposed framework preserves accuracy and stability during the HFS reasoning. These judgments have been ensured by a number of experimental studies on several datasets about software faulty prediction (SFP) problem with a large feature space. The main contributions of this paper are as follows: (i) it provides the entire HFS implementation from problem definition to calculation of final output, (ii) it increases the accuracy of recently proposed rule generation scheme in the literature, (iii) it presents the only possible fuzzy system solution for SFP problem containing a large feature space with reasonable accuracy.

This paper presents the results of the neuro-fuzzy model using remote-sensing data and geographic information system for landslide susceptibility analysis in a part of the Cameron Highlands areas in Malaysia. Landslide locations in the study area were identified by interpreting aerial photographs and satellite images, supported by extensive field surveys. Landsat TM satellite imagery was used to map the vegetation index. Maps of the topography, lineaments, Normalized Difference Vegetation Index (NDVI), and land cover were constructed from the spatial data sets. Eight landslide conditioning factors such as altitude, slope gradient, curvature, distance from the drainage, distance from the road, lithology, distance from the faults, and NDVI were extracted from the spatial database. These factors were analyzed using a neuro-fuzzy model adaptive neuro-fuzzy inference system to produce the landslide susceptibility maps. During the model development works, a total of five landslide susceptibility models were constructed. For verification, the results of the analyses were then compared with the field-verified landslide locations. Additionally, the receiver operating characteristic curves for all landslide susceptibility models were drawn, and the area under curve values were calculated. Landslide locations were used to validate the results of the landslide susceptibility map, and the verification results showed a 97% accuracy for model 5, employing all parameters produced in the present study as the landslide conditioning factors. The validation results showed a sufficient agreement between the obtained susceptibility map and the existing data on the landslide areas. Qualitatively, the model yields reasonable results, which can be used for preliminary land-use planning purposes.