Classification of Parkinson's disease using feature weighting method on the basis of fuzzy C-means clustering

This study presents the application of fuzzy c-means (FCM) clustering-based feature weighting (FCMFW) for the detection of Parkinson's disease (PD). In the classification of PD dataset taken from University of California – Irvine machine learning database, practical values of the existing traditional and non-standard measures for distinguishing healthy people from people with PD by detecting dysphonia were applied to the input of FCMFW. The main aims of FCM clustering algorithm are both to transform from a linearly non-separable dataset to a linearly separable one and to increase the distinguishing performance between classes. The weighted PD dataset is presented to k-nearest neighbour (k-NN) classifier system. In the classification of PD, the various k-values in k-NN classifier were used and compared with each other. Also, the effects of k-values in k-NN classifier on the classification of Parkinson disease datasets have been investigated and the best k-value found. The experimental results have demonstrated that the combination of the proposed weighting method called FCMFW and k-NN classifier has obtained very promising results on the classification of PD.     

A survey of routing protocols for smart grid communications

With the recent initiatives to upgrade the existing power grid to the Smart Grid (SG), there has been a significant interest in the design and development of an efficient communications infrastructure for connecting different components of the SG. In addition to the currently used underlying networks and protocols, new wired/wireless approaches are being planned for deployment for different components/applications of the SG. Based on the data requirements of the applications, new challenges have arisen at the network layer of the protocol stack with respect to routing and data forwarding. In this paper, we focus on the routing issues in the SG communications infrastructure which consists of different network components, such as Home Area Networks (HANs), Neighborhood Area Networks (NANs) and Wide Area Networks (WANs). We provide a comprehensive survey of the existing routing research and analyze the advantages and disadvantages of the proposed protocols with respect different applications areas. We also identify the future research issues that are yet to be addressed with respect to the applications and network components. This survey is the first to identify routing design issues for the SG and categorize the proposed routing protocols from the SG applications perspective. We believe that this work will be valuable for the utilities and other energy companies whose target is to develop and deploy a specific SG application that may span different network components. In addition, this work will provide valuable insights for the newcomers who would like to pursue routing related research in the SG domain.     

Automatic detection of respiratory arrests in OSA patients using PPG and machine learning techniques

Obstructive sleep apnea is a syndrome which is characterized by the decrease in air flow or respiratory arrest depending on upper respiratory tract obstructions recurring during sleep and often observed with the decrease in the oxygen saturation. The aim of this study was to determine the connection between the respiratory arrests and the photoplethysmography (PPG) signal in obstructive sleep apnea patients. Determination of this connection is important for the suggestion of using a new signal in diagnosis of the disease. Thirty-four time-domain features were extracted from the PPG signal in the study. The relation between these features and respiratory arrests was statistically investigated. The Mann–Whitney U test was applied to reveal whether this relation was incidental or statistically significant, and 32 out of 34 features were found statistically significant. After this stage, the features of the PPG signal were classified with k-nearest neighbors classification algorithm, radial basis function neural network, probabilistic neural network, multilayer feedforward neural network (MLFFNN) and ensemble classification method. The output of the classifiers was considered as apnea and control (normal). When the classifier results were compared, the best performance was obtained with MLFFNN. Test accuracy rate is 97.07 % and kappa value is 0.93 for MLFFNN. It has been concluded with the results obtained that respiratory arrests can be recognized through the PPG signal and the PPG signal can be used for the diagnosis of OSA.

     

Subtractive clustering attribute weighting (SCAW) to discriminate the traffic accidents on Konya-Afyonkarahisar highway in Turkey with the help of GIS: A case study

A case study including the discrimination of traffic accidents as accident free and accident cases on Konya-Afyonkarahisar highway in Turkey using the proposed hybrid method based on combining of a new data preprocessing method called subtractive clustering attribute weighting (SCAW) and classifier algorithms with the help of Geographical Information System (GIS) technology has been conducted. In order to improve the discrimination of classifier algorithms including artificial neural network (ANN), adaptive network based fuzzy inference system (ANFIS), support vector machine, and decision tree, using data preprocessing need in solution of these kinds of problems (traffic accident case study). So, we have proposed a novel data preprocessing method called subtractive clustering attribute weighting (SCAW) and combined with classifier algorithms. In this study, the experimental data has been obtained by means of using GIS. The obtained GIS attributes are day, temperature, humidity, weather conditions, and month of occurred accident. To evaluate the performance of the proposed hybrid method, the classification accuracy, sensitivity and specificity values have been used. The experimental obtained results are 53.93%, 52.25%, and 38.76% classification successes using alone ANN, ANFIS, and SVM with RBF kernel type, respectively. As for the proposed hybrid method, the classification accuracies of 67.98%, 70.22%, and 61.24% have been obtained using the combination of SCAW with ANN, the combination of SCAW with SVM (radial basis function (RBF) kernel type), and the combination of SCAW with ANFIS, respectively. The proposed SCAW method with the combination of classifier algorithms has been achieved the very promising results in the discrimination of traffic accidents.     

A hybrid expert system approach for telemonitoring of vocal fold pathology

Acoustical parameters extracted from the recorded voice samples are actively pursued for accurate detection of vocal fold pathology. Most of the system for detection of vocal fold pathology uses high quality voice samples. This paper proposes a hybrid expert system approach to detect vocal fold pathology using the compressed/low quality voice samples which includes feature extraction using wavelet packet transform, clustering based feature weighting and classification. In order to improve the robustness and discrimination ability of the wavelet packet transform based features (raw features), we propose clustering based feature weighting methods including k-means clustering (KMC), fuzzy c-means (FCM) clustering and subtractive clustering (SBC). We have investigated the effectiveness of raw and weighted features (obtained after applying feature weighting methods) using four different classifiers: Least Square Support Vector Machine (LS-SVM) with radial basis kernel, k-means nearest neighbor (kNN) classifier, probabilistic neural network (PNN) and classification and regression tree (CART). The proposed hybrid expert system approach gives a promising classification accuracy of 100% using the feature weighting methods and also it has potential application in remote detection of vocal fold pathology.     

The free vibration analysis and optimal design of an adhesively bonded functionally graded single lap joint

In this study, three-dimensional free vibration and stress analyses of an adhesively bonded functionally graded single lap joint were carried. The effects of the adhesive material properties, such as modulus of elasticity, Poisson's ratio and density were found to be negligible on the first ten natural frequencies and mode shapes of the adhesive joint. Both the finite element method and the back-propagation artificial neural network (ANN) method were used to investigate the effects of the geometrical parameters, such as overlap length, plate thickness and adhesive thickness; and the material composition variation through the plate thickness on the natural frequencies, mode shapes and modal strain energy of the adhesive joint. The suitable ANN models were trained successfully using a series of free vibration and stress analyses for various random geometrical parameters and compositional gradient exponents. The ANN models showed that the support length, the plate thickness and the compositional gradient exponent played important role on the natural frequencies, mode shapes and modal strain energies of the adhesive joint whereas the adhesive thickness had a minor effect. In addition, the optimal joint dimensions and compositional gradient exponent were determined using genetic algorithm and ANN models so that the maximum natural frequency and the minimum modal strain energy conditions are satisfied for each natural frequency of the adhesively bonded functionally graded single lap joint.     

Cathodic polarization of commercially pure aluminium

Cathodic corrosion, particularly alkaline pitting and repassivation, of 1S aluminium has been investigated by potential-controlled methods in unbuffered chloride media. The results are mainly for de-aerated solutions; the influence of dissolved oxygen and stirring, which are likely to be present in a practical situation, are also discussed. The metal undergoes stable pitting and then uniform etching as the applied potential is decreased below ? 1.35 V(SCE). At potentials more positive than this threshold value, metal dissolution still occurs possibly near the cathodic impurities on the surface due to local alkalinization resulting from hydrogen evolution; but, the surface repassivates slowly as the cathodic sites are covered up by the oxide film. The polarization behaviour of the partially passive surface is studied by fast-scan potential measurements and is associated with hydrogen evolution kinetics. The measured current decays exponentially with time during repassivation at constant potential. This is explained in terms of a model based on film growth controlled by metal dissolution.     

Non-linear elastic stresses in a thin hard coating/an elastic substrate system subjected to a surface pressure distribution

A hard ceramic coating on elastic steel substrates has been increasingly used in the tribological applications in order to reduce wear rates and friction. In case a surface pressure is applied to the coating surface of a coating–substrate system, the stress and deformation states inside the coating and at the edges of the coating–substrate interface play important role in service life of the coating. In this study, the geometrically non-linear stress analysis of a thin hard coating–elastic substrate system subjected to a surface pressure was carried out using the incremental finite element method (IFEM) based on the small strain–large displacement theory (SSLD). The pressure distribution was considered for plane-strain and axisymmetric cases. The comparison of the stress distributions of an uncoated substrate determined analytically with the results of both the SSLD analysis and the small strain–small displacement (SSSD) analysis showed a good agreement. In addition, the stress analysis of a thin coating/substrate system was carried out based on the SSLD and SSSD theories. The stress distributions along the coating surface, coating–substrate interface and across the coating and substrate were investigated in detail. Both theories showed that the normal and shear stresses became critical in the coating and on the coating–substrate interface regions corresponding to the centre and ends of the surface pressure distribution. These stresses are a probable reason of the coating–substrate detachment encountered in practice. However, the SSSD theory can not predict accurately lower stress and strain variations arising at the edges of the coating and the coating–substrate interface since the SSSD theory neglects the effects of the large displacements whereas the SSLD theory found that the normal and shear stresses and strains at these critical locations had also non-linear variations as the applied load is increased. Increasing the coating modulus resulted in higher stresses in the coating and at the edges of the coating–substrate interface. In case of a thin coating, these critical stresses occurred in the substrate whereas they spread completely inside coating regions neighboring the coating–substrate interface for relatively thicker coatings. The SSLD analysis also predicted lower and non-linear normal, shear stress and strain variations at the critical locations in the coating and on the coating–substrate interface for different modulus ratios and coating thicknesses. Since the peak stresses arising along the coating surface and the coating–substrate interface were dependent on both the coating thickness and modulus it was not possible to determine an optimum coating thickness and modulus ratio reducing all stress components causing the coating failure. However, optimum coating thickness and modulus can be searched in a large solution space using the optimization techniques.     

Antifungal Activity of Olive Oil and Ozonated Olive Oil Against Candida Spp. and Saprochaete Spp.

Ozonated olive oil was investigated for their capacity to inhibit growth of 38 yeast strains of Candida albicans, Candida glabrata, Candida krusei, Candida parapsilosis, and Saprochaete capitata. Two different ozonated olive oil (OZO1, OZO2) and two different olive oil (OL1, OL2) samples having different biochemical parameters were assessed in terms of their antifungal ability and comparison was made. Fluconazole was chosen as control antifungal agent. Each sample’s antifungal activity decreased in the following order: OZO1 > OZO2 > OL1 ≥ OL2. This study demonstrated that ozonated olive oil may help to control some fluconazole-resistant and dose-dependent sensitive fungal strains.     

Cash-back rewards versus equity-based electronic loyalty programs in e-commerce

Loyalty is a crucial part of today’s business because retaining a customer is generally less expensive than attracting a new one. This relationship also holds true in e-commerce. Most of the e-loyalty programs available on the Internet utilize cash-back rewards. A new type of e-loyalty program in which customers are offered a fraction of merchant firm’s equity is emerging recently. The profitability of this approach versus cash-back reward programs is still an open question. In this paper, we first survey current e-loyalty programs, and then develop a two-period duopoly model in which one of the firms gives customers a small fraction of its equity and the other offers cash-back reward for a purchase. We derive analytical conditions to compare the total profits generated through each loyalty program. In particular, we find that equity-based e-loyalty programs provide higher total profits than those of cash-back programs in markets where it is difficult for customers to switch between firms. We are grateful for the valuable comments and suggestions by the participants of the AMCIS 2004 Doctoral Consortium, New York City; the Big Ten IS Research Consortium 2004 at the Michigan State University; EURO/INFORMS 2003, Istanbul, Turkey; WISE 2002, Barcelona, Spain; and ICTEC 2002, Montreal, Canada. We are also indebted to the faculty at the Krannert Graduate School of Management for their indispensable inputs.