An Intelligent Parkinson's Disease Diagnostic System Based on a Chaotic Bacterial Foraging Optimization Enhanced Fuzzy KNN Approach.

Parkinson's disease (PD) is a common neurodegenerative disease, which has attracted more and more attention. Many artificial intelligence methods have been used for the diagnosis of PD. In this study, an enhanced fuzzy k-nearest neighbor (FKNN) method for the early detection of PD based upon vocal measurements was developed. The proposed method, an evolutionary instance-based learning approach termed CBFO-FKNN, was developed by coupling the chaotic bacterial foraging optimization with Gauss mutation (CBFO) approach with FKNN. The integration of the CBFO technique efficiently resolved the parameter tuning issues of the FKNN. The effectiveness of the proposed CBFO-FKNN was rigorously compared to those of the PD datasets in terms of classification accuracy, sensitivity, specificity, and AUC (area under the receiver operating characteristic curve). The simulation results indicated the proposed approach outperformed the other five FKNN models based on BFO, particle swarm optimization, Genetic algorithms, fruit fly optimization, and firefly algorithm, as well as three advanced machine learning methods including support vector machine (SVM), SVM with local learning-based feature selection, and kernel extreme learning machine in a 10-fold cross-validation scheme. The method presented in this paper has a very good prospect, which will bring great convenience to the clinicians to make a better decision in the clinical diagnosis.

An Enhanced Grey Wolf Optimization Based Feature Selection Wrapped Kernel Extreme Learning Machine for Medical Diagnosis.

In this study, a new predictive framework is proposed by integrating an improved grey wolf optimization (IGWO) and kernel extreme learning machine (KELM), termed as IGWO-KELM, for medical diagnosis. The proposed IGWO feature selection approach is used for the purpose of finding the optimal feature subset for medical data. In the proposed approach, genetic algorithm (GA) was firstly adopted to generate the diversified initial positions, and then grey wolf optimization (GWO) was used to update the current positions of population in the discrete searching space, thus getting the optimal feature subset for the better classification purpose based on KELM. The proposed approach is compared against the original GA and GWO on the two common disease diagnosis problems in terms of a set of performance metrics, including classification accuracy, sensitivity, specificity, precision, G-mean, F-measure, and the size of selected features. The simulation results have proven the superiority of the proposed method over the other two competitive counterparts.

A Framework for Bus Trajectory Extraction and Missing Data Recovery for Data Sampled from the Internet.

This paper presents a novel framework for trajectories' extraction and missing data recovery for bus traveling data sampled from the Internet. The trajectory extraction procedure is composed of three main parts: trajectory clustering, trajectory cleaning and trajectory connecting. In the clustering procedure, we focus on feature construction and parameter selection for the fuzzy C-means clustering method. Following the clustering procedure, the trajectory cleaning algorithm is implemented based on a new introduced fuzzy connecting matrix, which evaluates the possibility of data belonging to the same trajectory and helps detect the anomalies in a ranked context-related order. Finally, the trajectory connecting algorithm is proposed to solve the issue that occurs in some cases when a route trajectory is incorrectly partitioned into several clusters. In the missing data recovery procedure, we developed the contextual linear interpolation for the cases of missing data occurring inside the trajectory and the median value interpolation for the cases of missing data outside the trajectory. Extensive experiments are conducted to demonstrate that the proposed framework offers a powerful ability to extract and recovery bus trajectories sampled from the Internet.

An intelligent prognostic system for analyzing patients with paraquat poisoning using arterial blood gas indexes.

The arterial blood gas (ABG) test is used to assess gas exchange in the lung, and the acid-base level in the blood. However, it is still unclear whether or not ABG test indexes correlate with paraquat (PQ) poisoning. This study investigates the predictive value of ABG tests in prognosing patients with PQ poisoning; it also identifies the most significant indexes of the ABG test. An intelligent machine learning-based system was established to effectively give prognostic analysis of patients with PQ poisoning based on ABG indexes. In the proposed system, an enhanced support vector machine combined with a feature selection strategy was developed to predict the risk status from a pool of 103 patients (56 males and 47 females); of these, 52 subjects were deceased and 51 patients were alive. The proposed method was rigorously evaluated against the real-life dataset in terms of accuracy, sensitivity, and specificity. Additionally, the feature selection was investigated to identify correlating factors for the risk status. The results demonstrated that there were significant differences in ABG indexes between deceased and alive subjects (p-value <0.01). According to the feature selection, we found that the most important correlated indexes were associated with partial pressure of carbon dioxide (PCO2). This study discovered the relationship between ABG test and poisoning degree to provide a new avenue for prognosing PQ poisoning.