Optimal feature subset selection for neuron spike sorting using the genetic algorithm

It is crucial for a neuron spike sorting algorithm to cluster data from different neurons efficiently. In this study, the search capability of the Genetic Algorithm (GA) is exploited for identifying the optimal feature subset for neuron spike sorting with a clustering algorithm. Two important objectives of the optimization process are considered: to reduce the number of features and increase the clustering performance. Specifically, we employ a binary GA with the silhouette evaluation criterion as the fitness function for neuron spike sorting using the Super-Paramagnetic Clustering (SPC) algorithm. The clustering results of SPC with and without the GA-based feature selector are evaluated using benchmark synthetic neuron spike data sets. The outcome indicates the usefulness of the GA in identifying a smaller feature set with improved clustering performance.

Factors affecting peritoneal dialysis selection in Taiwanese patients with chronic kidney disease

BACKGROUND: Taiwan has the highest incidence and prevalence of end-stage renal disease (ESRD) in the world with 55,499 ESRD patients on long-term dialysis. Nevertheless, 90.96% of these patients are managed on maintenance haemodialysis (HD), with only 9.03% enrolled in a peritoneal dialysis (PD) programme. AIM: The study aim was to identify the factors affecting Taiwanese patient's selection of PD in preference to HD for chronic kidney disease. METHODS: A cross-sectional research design was utilized with 130 chronic renal failure (CRF) patients purposively selected from outpatient nephrology clinics at four separate Taiwan hospitals. Logistic regression was used to identify the main factors affecting the patient's choice of dialysis type. RESULTS: Single-factor logistic regression found significant differences in opinion related to age, education level, occupation type, disease characteristics, lifestyle modifications, self-care ability, know-how of dialysis modality, security considerations and findings related to the decisions made by medical personnel (P < 0.05). Moreover, multinomial logistic regression after adjustment for interfering variables found that self-care ability and dialysis modality know-how were the two main factors affecting the person's selection of dialysis type. CONCLUSIONS: Self-care ability and the person's knowledge of the different types of dialysis modality and how they function were the major determinants for selection of dialysis type in Taiwan based on the results from this study. The results indicate that the education of CRF patients about the types of dialysis available is essential to enable them to understand the benefits or limitations of both types of dialysis.

Enhanced Twitter sentiment analysis by using feature selection and combination

Tweet sentiment analysis is an important research topic. An accurate and timely analysis report could give good indications on the general public's opinions. After reviewing the current research, we identify the need of effective and efficient methods to conduct tweet sentiment analysis. This paper aims to achieve a high level of performance for classifying tweets with sentiment information. We propose a feasible solution which improves the level of accuracy with good time efficiency. Specifically, we develop a novel feature combination scheme which utilizes the sentiment lexicons and the extracted tweet unigrams of high information gain. We evaluate the performance of six popular machine learning classifiers among which the Naive Bayes Multinomial (NBM) classifier achieves the accuracy rate of 84.60% and takes a few minutes to complete classifying thousands of tweets.

Multi-layer attribute selection and classification algorithm for the diagnosis of cardiac autonomic neuropathy based on HRV attributes

Cardiac autonomic neuropathy (CAN) poses an important clinical problem, which often remains undetected due difficulty of conducting the current tests and their lack of sensitivity. CAN has been associated with growth in the risk of unexpected death in cardiac patients with diabetes mellitus. Heart rate variability (HRV) attributes have been actively investigated, since they are important for diagnostics in diabetes, Parkinson's disease, cardiac and renal disease. Due to the adverse effects of CAN it is important to obtain a robust and highly accurate diagnostic tool for identification of early CAN, when treatment has the best outcome. Use of HRV attributes to enhance the effectiveness of diagnosis of CAN progression may provide such a tool. In the present paper we propose a new machine learning algorithm, the Multi-Layer Attribute Selection and Classification (MLASC), for the diagnosis of CAN progression based on HRV attributes. It incorporates our new automated attribute selection procedure, Double Wrapper Subset Evaluator with Particle Swarm Optimization (DWSE-PSO). We present the results of experiments, which compare MLASC with other simpler versions and counterpart methods. The experiments used our large and well-known diabetes complications database. The results of experiments demonstrate that MLASC has significantly outperformed other simpler techniques.

Microencapsulation of omega-3 fatty acids: a review of microencapsulation and characterization methods

To improve consumption of omega-3 fatty acids, foods can be enriched with omega-3 rich oils. Microencapsulation of omega-3 oils minimizes oxidative deterioration and allows their use in stable and easy-to-handle form. Microencapsulation of omega-3 fatty acids can be achieved by using a variety of methods, with the two most commonly used commercial processes being complex coacervation and spray dried emulsions. A variety of other methods are in development including spray chilling, extrusion coating and liposome entrapment. The key parameter in any of these processes is the selection of wall material. For spray dried emulsions and complex coacervates protein or polysaccharides are primarily used as shell material, although complex coacervation is currently commercially limited to gelatin. Here we review the need for microencapsulation of omega-3 oils, methods of microencapsulation and analysis, and the selection of shell material components. In particular, we discuss the method of complex coacervation, including its benefits and limitations. This review highlights the need for research on the fundamentals of interfacial and complexation behaviour of various proteins, gums and polyphenols to encapsulate and deliver omega-3 fatty acids, particularly with regard to broadening the range of shell materials that can be used in complex coacervation of omega-3 rich oils.