Mehmet Fatih Akay

Support vector machines combined with feature selection for breast cancer diagnosis

Breast cancer is the second largest cause of cancer deaths among women. At the same time, it is also among the most curable cancer types if it can be diagnosed early. Research efforts have reported with increasing confirmation that the support vector machines (SVM) have greater accurate diagnosis ability. In this paper, breast cancer diagnosis based on a SVM-based method combined with feature selection has been proposed. Experiments have been conducted on different training-test partitions of the Wisconsin breast cancer dataset (WBCD), which is commonly used among researchers who use machine learning methods for breast cancer diagnosis. The performance of the method is evaluated using classification accuracy, sensitivity, specificity, positive and negative predictive values, receiver operating characteristic (ROC) curves and confusion matrix. The results show that the highest classification accuracy (99.51%) is obtained for the SVM model that contains five features, and this is very promising compared to the previously reported results.

Measurement and monitoring of microwave reflection and transmission properties of cement-based specimens

The results of measurement and monitoring of reflection and transmission properties of cement-based specimens (blocks of mortar, concrete) during long time of their service lives, including hydration process, and different curing conditions at microwave frequencies (X-band) are presented. A simple and inexpensive measurement system that utilizes the nondestructive and contactless free space method is used. Dependencies of the reflection and transmission coefficients on water-to-cement ratio, preparing and curing conditions of the specimens are demonstrated. It is shown that the reflection coefficient is approximately stable after hydration process while the transmission coefficient changes during long time of the specimens service life. The complex dielectric permittivity of the cement-based materials is calculated by a new method using only the amplitudes of the reflection and transmission coefficients. The expected applications of the results are discussed.

Performance improvement of parallel programs on a broadcast-based distributed shared memory multiprocessor by simulation

Abstract Due to advances in fiber optics and VLSI technology, interconnection networks that allow simultaneous broadcasts are becoming feasible. Distributed shared memory (DSM) implementations on such networks promise high performance even for small applications with small granularity. This paper, after summarizing the architecture of one such implementation called the Simultaneous Multiprocessor Optical Exchange Bus (SOME-Bus), presents simple algorithms for improving the performance of parallel programs running on the SOME-Bus multiprocessor implementing cache-coherent DSM. The algorithms are based on run-time data redistribution via dynamic page migration protocol. They use memory access references together with the information of average channel utilization, average channel waiting time, number of messages in the channel queue or short-term average channel waiting time reported by each node and gathered by hardware monitors to make correct decisions related to the placement of shared data. Simulations with four parallel codes on a 64-processor SOME-Bus show that the algorithms yield significant performance improvements such as reduction in the execution times, number of remote memory accesses, average channel waiting times, average network latencies and increase in average channel utilizations.

Support vector regression and multilayer feed forward neural networks for non-exercise prediction of VO2max

The purpose of this study is to develop non-exercise (N-Ex) VO2max prediction models by using support vector regression (SVR) and multilayer feed forward neural networks (MFFNN). VO2max values of 100 subjects (50 males and 50 females) are measured using a maximal graded exercise test. The variables; gender, age, body mass index (BMI), perceived functional ability (PFA) to walk, jog or run given distances and current physical activity rating (PA-R) are used to build two N-Ex prediction models. Using 10-fold cross validation on the dataset, standard error of estimates (SEE) and multiple correlation coefficients (R) of both models are calculated. The MFFNN-based model yields lower SEE (3.23mlkg-1min-1) whereas the SVR-based model yields higher R (0.93). Compared with the results of the other N-Ex prediction models in literature that are developed using multiple linear regression analysis, the reported values of SEE and R in this study are considerably more accurate. Therefore, the results suggest that SVR-based and MFFNN-based N-Ex prediction models can be valid predictors of VO2max for heterogeneous samples.

A new congestion control algorithm for improving the performance of a broadcast-based multiprocessor architecture

Congestion occurring in the input queues of broadcast-based multiprocessor architectures can severely limit their overall performance. The existing congestion control algorithms estimate congestion based on a nodes output channel parameters such as the number of free virtual channels or the number of packets waiting at the channel queue. In this paper, we have proposed a new congestion control algorithm to prevent congestion on broadcast-based multiprocessor architectures with multiple input queues. Our algorithm performs congestion control at the packet level and takes into account the next input queue number which will be accessed by the processor, which form the fundamental differences between our algorithm and the algorithms based on the idea of virtual channel congestion control. The performance of the algorithm is evaluated by OPNET Modeler with various synthetic traffic patterns on a 64-node Simultaneous Optical Multiprocessor Exchange Bus (SOME-Bus) architecture employing the message passing protocol. Performance measures such as average input waiting time, average network response time and average processor utilization have been collected before and after applying the algorithm. The results show that the proposed algorithm is able to decrease the average input waiting time by 13.99% to 20.39%, average network response time by 8.76% to 20.36% and increase average processor utilization by 1.92% to 6.63%. The performance of the algorithm is compared with that of the other congestion control algorithms and it is observed that our algorithm performs better under all traffic patterns. Also, theoretical analysis of the proposed method is carried out by using queuing networks.

Support vector machines for aerobic fitness prediction of athletes

Support vector machine is a statistical learning classifier, based on the principle of structural risk minimization, which performs well when applied to data outside the training set. This paper presents a new approach based on support vector machines to predict whether an athlete is aerobically fit or not. The input data set contains physical properties of athletes as well as their cardiopulmonary exercise testing results which were obtained at Cukurova University Sports Physiology Laboratory. According to the exercise test protocol, speed and grade of the treadmill were increased at certain times and the input variables of time, speed and grade of the treadmill, and oxygen uptake, carbon dioxide output, minute ventilation and heart rate of athletes were recorded. The average of the exercise test data was taken over certain time intervals and a curve fitting algorithm was applied to remove the spikes in the data and make it more suitable to use with support vector machines. Experiments with several different training and test data show that curve-fitted data has better performance measures, such as higher prediction rate, sensitivity, specificity, and shorter training time.

Predicting the performance measures of a message-passing multiprocessor architecture using artificial neural networks

In this paper, we develop multi-layer feed-forward artificial neural network (MFANN) models for predicting the performance measures of a message-passing multiprocessor architecture interconnected by the simultaneous optical multiprocessor exchange bus (SOME-Bus), which is a fiber-optic interconnection network. OPNET Modeler is used to simulate the SOME-Bus multiprocessor architecture and to create the training and testing datasets. The performance of the MFANN prediction models is evaluated using standard error of estimate (SEE) and multiple correlation coefficient (R). Also, the results of the MFANN models are compared with the ones obtained by generalized regression neural network (GRNN), support vector regression (SVR), and multiple linear regression (MLR). It is shown that MFANN models perform better (i.e., lower SEE and higher R) than GRNN-based, SVR-based, and MLR-based models for predicting the performance measures of a message-passing multiprocessor architecture.

An automated amplitudes-only measurement system for permittivity determination using free-space method

An automated PC based free-space system for determining the permittivity of high-loss materials is proposed. The main feature of the system is to measure only the amplitudes of transmission and reflection coefficients using free-space method and determine the permittivity dynamically using a computer. Firstly, the expressions for the reflection and transmission coefficients involving the permittivity of the high-loss material are derived. Then these equations are solved together by using the halving method. In order to measure the amplitudes of reflection and transmission coefficients, a simple and inexpensive microwave measurement system is established. The parallel port is used as an interface between the computer and the designed control circuit. A software program is developed for the treatment of the measured signal amplitudes and determination the permittivity of high-loss materials.

Machine learning and statistical methods for the prediction of maximal oxygen uptake: recent advances.

Maximal oxygen uptake (VO2max) indicates how many milliliters of oxygen the body can consume in a state of intense exercise per minute. VO2max plays an important role in both sport and medical sciences for different purposes, such as indicating the endurance capacity of athletes or serving as a metric in estimating the disease risk of a person. In general, the direct measurement of VO2max provides the most accurate assessment of aerobic power. However, despite a high level of accuracy, practical limitations associated with the direct measurement of VO2max, such as the requirement of expensive and sophisticated laboratory equipment or trained staff, have led to the development of various regression models for predicting VO2max. Consequently, a lot of studies have been conducted in the last years to predict VO2max of various target audiences, ranging from soccer athletes, nonexpert swimmers, cross-country skiers to healthy-fit adults, teenagers, and children. Numerous prediction models have been developed using different sets of predictor variables and a variety of machine learning and statistical methods, including support vector machine, multilayer perceptron, general regression neural network, and multiple linear regression. The purpose of this study is to give a detailed overview about the data-driven modeling studies for the prediction of VO2max conducted in recent years and to compare the performance of various VO2max prediction models reported in related literature in terms of two well-known metrics, namely, multiple correlation coefficient (R) and standard error of estimate. The survey results reveal that with respect to regression methods used to develop prediction models, support vector machine, in general, shows better performance than other methods, whereas multiple linear regression exhibits the worst performance.

Support vector machines for predicting the admission decision of a candidate to the School of Physical Education and Sports at Cukurova University

The School of Physical Education and Sports at Cukurova University, Adana, Turkey conducts physical ability test to select students for admission to the School. A candidates performance in the physical ability test as well as his scores in the National Selection and Placement Examination and graduation grade point average (GPA) at high school are the main factors (along with some other criteria) that determine whether he will be admitted or not. In this paper, we use support vector machines (SVM) to predict in advance whether or not a candidate will be admitted to the School once he knows (or somehow has) his scores from the physical ability test. Experiments have been conducted on two different datasets, which are actual test results of candidates who applied to the School in 2006 and 2007, respectively. Results are presented also for the case when the 2006 dataset is used for training and the 2007 dataset is used for testing. The results (classification accuracies of 97.17% and 90.51% in 2006 and 2007, respectively) show that SVM-based classification is a promising tool for this application domain.