Dosage planning for type 2 diabetes mellitus patients using Indexing HDMR

Diabetes mellitus type 2 (T2DM), is also named as non-insulin dependent diabetes mellitus (NIDDM) or adult-onset diabetes, is a metabolic disease characterized by high blood glucose. Deficient insulin production or insulin resistance of the body are the causes of T2DM. Drug treatment has a very important role as well as exercise and diet. To keep the body sugar level stable within the accepted range values, drug dosage planning is a part of combinational treatment. In this study, Indexing HDMR method which is a multivariate data partitioning method is used to produce a polynomial based rule structure to manage the drug dosage planning process. For this purpose, 142 diabetic assays, 96 of which as training data and 46 of which as testing data, were used in this study. The Indexing HDMR method worked well in modeling drug dosages and it is obvious that the method is reliable for the purpose.     

A patient network-based machine learning model for disease prediction: The case of type 2 diabetes mellitus

Applied Intelligence - In recent years, the prevalence of chronic diseases such as type 2 diabetes mellitus (T2DM) has increased, bringing a heavy burden to healthcare systems. While regular...     

Enhancing security of cookie-based sessions in mobile networks using sparse caching

The exponential growth in the use of mobile phones and tablets to gain wireless access to the Internet has been accompanied by a similar growth in cyber attacks over wireless links to steal session cookies and compromise private users’ accounts. The popular one-way hash chain authentication technique in its conventional format is not optimal for mobile phones and other handheld devices due to its high computational overhead. In this paper, we propose and evaluate the use of sparse caching techniques to reduce the overhead of one-way hash chain authentication. Sparse caching schemes with uniform spacing, non-uniform spacing and geometric spacing are designed and analyzed. A Weighted Overhead formula is used to obtain insight into the suitable cache size for different classes of mobile devices. Additionally, the scheme is evaluated from an energy consumption perspective. We show that sparse caching can also be effective in the case of uncertainty in the number of transactions per user session. Our extensive performance tests have shown the significant improvement achieved by the sparse caching schemes.     

Analysis of computational intelligence techniques for diabetes mellitus prediction

Diabetes as a chronic disease is becoming a foremost community health concern worldwide. In developing countries, the diabetic patients are increasing rapidly due to lack of sentience and bad eating habits. So, there is a need of a framework that can effectively diagnose thousands of patients using clinical specifics. This work uses six computational intelligence techniques for diabetes mellitus prediction namely classification tree, support vector machine, logistic regression, naïve Bayes, and artificial neural network. The performance of these techniques was evaluated on eight different classification performance measurements. Moreover, these techniques were appraised on a receiver operative characteristic curve. Classification accuracy of 77 and 78% was achieved by artificial neural network and logistic regression, respectively, with F 1 measure of 0.83 and 0.84.

     

Comparison of interval and Monte Carlo simulation for the prediction of postprandial glucose under uncertainty in type 1 diabetes mellitus

In this paper, the problem of tackling uncertainty in the prediction of postprandial blood glucose is analyzed. Two simulation approaches, Monte Carlo and interval models, are studied and compared. Interval simulation is carried out using modal interval analysis. Simulation of a glucoregulatory model with uncertainty in insulin sensitivities, glucose absorption and food intake is carried out using both methods. Interval simulation is superior in predicting all severe and mild hyper- and hypoglycemia episodes. Furthermore, much less computational time is required for interval simulation than for Monte Carlo simulation.     

Inferring hybrid transportation modes from sparse GPS data using a moving window SVM classification

Understanding travel behaviour and travel demand is of constant importance to transportation communities and agencies in every country. Nowadays, attempts have been made to automatically infer transportation modes from positional data, such as the data collected by using GPS devices so that the cost in time and budget of conventional travel diary survey could be significantly reduced. Some limitations, however, exist in the literature, in aspects of data collection (sample size selected, duration of study, granularity of data), selection of variables (or combination of variables), and method of inference (the number of transportation modes to be used in the learning). This paper therefore, attempts to fully understand these aspects in the process of inference. We aim to solve a classification problem of GPS data into different transportation modes (car, walk, cycle, underground, train and bus). We first study the variables that could contribute positively to this classification, and statistically quantify their discriminatory power. We then introduce a novel approach to carry out this inference using a framework based on Support Vector Machines (SVMs) classification. The framework was tested using coarse-grained GPS data, which has been avoided in previous studies, achieving a promising accuracy of 88% with a Kappa statistic reflecting almost perfect agreement.     

Sign prediction in sparse social networks using clustering and collaborative filtering

Today, social networks have created a wide variety of relationships between users. Friendships on Facebook and trust in the Epinions network are examples of these relationships. Most social media research has often focused on positive interpersonal relationships, such as friendships. However, in many real-world applications, there are also networks of negative relationships whose communication between users is either distrustful or hostile in nature. Such networks are called signed networks. In this work, sign prediction is made based on existing links between nodes. However, in real signed networks, links between nodes are usually sparse and sometimes absent. Therefore, existing methods are not appropriate to address the challenges of accurate sign prediction. To address the sparsity problem, this work aims to propose a method to predict the sign of positive and negative links based on clustering and collaborative filtering methods. Network clustering is done in such a way that the number of negative links between the clusters and the number of positive links within the clusters are as large as possible. As a result, the clusters are as close as possible to social balance. The main contribution of this work is using clustering and collaborative filtering methods, as well as proposing a new similarity criterion, to overcome the data sparseness problem and predict the unknown sign of links. Evaluations on the Epinions network have shown that the prediction accuracy of the proposed method has improved by 8% compared to previous studies.

     

Development of a multi-parametric model predictive control algorithm for insulin delivery in type 1 diabetes mellitus using clinical parameters

A multi-parametric model predictive control (mpMPC) algorithm for subcutaneous insulin delivery for individuals with type 1 diabetes mellitus (T1DM) that is computationally efficient, robust to variations in insulin sensitivity, and involves minimal burden for the user is proposed. System identification was achieved through impulse response tests feasible for ambulatory conditions on the UVa/Padova simulator adult subjects with T1DM. An alternative means of system identification using readily available clinical parameters was also investigated. A safety constraint was included explicitly in the algorithm formulation using clinical parameters typical of those available to an attending physician. Closed-loop simulations were carried out with daily consumption of 200 g carbohydrate. Controller robustness was assessed by subject/model mismatch scenarios addressing daily, simultaneous variation in insulin sensitivity and meal size with the addition of Gaussian white noise with a standard deviation of 10%. A second-order-plus-time-delay transfer function model fit the validation data with a mean (coefficient of variation) root-mean-square-error (RMSE) of 26 mg/dL (19%) for a 3 h prediction horizon. The resulting control law maintained a low risk Low Blood Glucose Index without any information about carbohydrate consumption for 90% of the subjects. Low-order linear models with clinically meaningful parameters thus provided sufficient information for a model predictive control algorithm to control glycemia. The use of clinical knowledge as a safety constraint can reduce hypoglycemic events, and this same knowledge can further improve glycemic control when used explicitly as the controller model. The resulting mpMPC algorithm was sufficiently compact to be implemented on a simple electronic device.     

Enhancing SVM performance in intrusion detection using optimal feature subset selection based on genetic principal components

Intrusion detection is very serious issue in these days because the prevention of intrusions depends on detection. Therefore, accurate detection of intrusion is very essential to secure information in computer and network systems of any organization such as private, public, and government. Several intrusion detection approaches are available but the main problem is their performance, which can be enhanced by increasing the detection rates and reducing false positives. This issue of the existing techniques is the focus of research in this paper. The poor performance of such techniques is due to raw dataset which confuse the classifier and results inaccurate detection due to redundant features. The recent approaches used principal component analysis (PCA) for feature subset selection which is based on highest eigenvalues, but the features corresponding to the highest eigenvalues may not have the optimal sensitivity for the classifier due to ignoring many sensitive features. Instead of using traditional approach of selecting features with the highest eigenvalues such as PCA, this research applied a genetic algorithm to search the genetic principal components that offers a subset of features with optimal sensitivity and the highest discriminatory power. The support vector machine (SVM) is used for classification purpose. This research work used the knowledge discovery and data mining cup dataset for experimentation. The performance of this approach was analyzed and compared with existing approaches. The results show that proposed method enhances SVM performance in intrusion detection that outperforms the existing approaches and has the capability to minimize the number of features and maximize the detection rates.     

Modified binary PSO for feature selection using SVM applied to mortality prediction of septic patients

This paper proposes a modified binary particle swarm optimization (MBPSO) method for feature selection with the simultaneous optimization of SVM kernel parameter setting, applied to mortality prediction in septic patients. An enhanced version of binary particle swarm optimization, designed to cope with premature convergence of the BPSO algorithm is proposed. MBPSO control the swarm variability using the velocity and the similarity between best swarm solutions. This paper uses support vector machines in a wrapper approach, where the kernel parameters are optimized at the same time. The approach is applied to predict the outcome (survived or deceased) of patients with septic shock. Further, MBPSO is tested in several benchmark datasets and is compared with other PSO based algorithms and genetic algorithms (GA). The experimental results showed that the proposed approach can correctly select the discriminating input features and also achieve high classification accuracy, specially when compared to other PSO based algorithms. When compared to GA, MBPSO is similar in terms of accuracy, but the subset solutions have less selected features.     

Applications of evolutionary SVM to prediction of membrane alpha-helices

This paper is in the area of membrane proteins. Membrane proteins make up about 75% of possible targets for novel drugs discovery. However, membrane proteins are one of the most understudied groups of proteins in biochemical research because of technical difficulties of attaining structural information about transmembrane regions or domains. Structural determination of TM regions is an important priority in pharmaceutical industry, as it paves the way for structure based drug design.This research presents a novel evolutionary support vector machine (SVM) based alpha-helix transmembrane region prediction algorithm to solve the membrane helices in amino acid sequences. The SVM-genetic algorithm (GA) methodology is based on the optimisation of sliding window size, evolutionary encoding selection and SVM parameter optimisation. In this research average hydrophobicity and propensity based on skew statistics are used to encode the one letter representation of amino acid sequences datasets.The computer simulation results demonstrate that the proposed SVM-GA methodology performs better than most conventional techniques producing an accuracy of 86.71% for cross-validation and 86.43% for jack-knife for randomly selected proteins containing single and multiple transmembrane regions. Furthermore, for the amino acid sequence 3LVG, the proposed SVM-GA produces better alpha-helix region identification than PRED-TMR2, MEMSATSVM/MEMSAT3 and PSIPRED V3.0.     

C-peptide microheterogeneity in type 2 diabetes populations

Purpose: The purpose of this study was to investigate naturally occurring C‐peptide microheterogeneity in healthy and type 2 diabetes (T2D) populations. Experimental design: MS immunoassays capable of simultaneously detecting intact C‐peptide and variant forms were applied to plasma samples from 48 healthy individuals and 48 individuals diagnosed with T2D. Results: Common throughout the entire sample set were three previously unreported variations of C‐peptide. The relative contribution of one variant, subsequently identified as C‐peptide (3‐31), was found to be more abundant in the T2D population as compared to the healthy population. Dipeptidyl peptidase IV is suspected to be responsible for this particular cleavage product, which is consistent with the pathophysiology of T2D. Conclusions and clinical relevance: C‐peptide does not exist in the human body as a single molecular species. It is qualitatively more heterogeneous than previously thought. These results lay a foundation for future studies devoted to a comprehensive understanding of C‐peptide and its variants in healthy and diabetic populations.     

A feedforward–feedback glucose control strategy for type 1 diabetes mellitus

As the “artificial pancreas” becomes closer to reality, automated insulin delivery based on real-time glucose measurements becomes feasible for people with diabetes. This paper is concerned with the development of novel feedforward–feedback control strategies for real-time glucose control and type 1 diabetes. Improved post-meal responses can be achieved by a pre-prandial snack or bolus, or by reducing the glucose setpoint prior to the meal. Several feedforward–feedback control strategies provide attractive alternatives to the standard meal insulin bolus and are evaluated in simulations using a physiological model.     

Bankruptcy prediction using SVM models with a new approach to combine features selection and parameter optimisation

Due to the economic significance of bankruptcy prediction of companies for financial institutions, investors and governments, many quantitative methods have been used to develop effective prediction models. Support vector machine (SVM), a powerful classification method, has been used for this task; however, the performance of SVM is sensitive to model form, parameter setting and features selection. In this study, a new approach based on direct search and features ranking technology is proposed to optimise features selection and parameter setting for 1-norm and least-squares SVM models for bankruptcy prediction. This approach is also compared to the SVM models with parameter optimisation and features selection by the popular genetic algorithm technique. The experimental results on a data set with 2010 instances show that the proposed models are good alternatives for bankruptcy prediction.     

SVM与神经网络模型在股票预测中的应用研究

介绍了SVM、BP神经网络和小波神经网络模型在股票预测中的应用研究。通过输入历史股票价格走势数据进行模型训练,并分别进行三个模型预测输出,最后通过均方误差、走势方向准确率和总盈利率三个指标分析比较三个模型,从而了解模型在股票预测领域的应用效果,为后续研究做参考。