Feature selection has become interest to many research areas which deal with machine learning and data mining, because it provides the classifiers be fast, cost-effective, more accurate. In this paper effect of feature on accuracy NaïveBayes, Artificial Neural Network as Multilayer Perceptron, J48 decision tree is presented. These are compared fifteen real datasets pre-processed methods. Up 15.55% improvement in classification observed, Perceptron appears most sensitive classifier selection.

Cardiotocography is one of the most widely used technique for recording changes in fetal heart rate (FHR) and uterine contractions. Assessing cardiotocography crucial that it leads to iden- tifying fetuses which suffer from lack oxygen, i.e. hypoxia. This situation defined as dis- tress requires intervention order prevent fetus death or other neurological disease caused by In this study a computer-based approach analyzing cardiotocogram in- cluding diagnostic features discriminating...

Emphysema is a chronic lung disease that causes breathlessness. HRCT the reliable way of visual demonstration emphysema in patients. The fact dangerous and widespread nature require immediate attention doctor with good degree specialized anatomical knowledge. This necessitates development computer-based automatic identification system. study aims to investigate deep learning solution for discriminating subtypes by using raw pixels input images lung. Convolutional Neural Network (CNN) used as...

An evaluation of the performance artificial networks (ANNs) to estimate weights blue crab (Callinectes sapidus) catches in Yumurtalık Cove (Iskenderun Bay) that uses measured predictor variables is presented, including carapace width (CW), sex (male, female and with eggs), sampling month. Blue crabs (n=410) were collected each month between 15 September 1996 May 1998. Sex, CW, used specified input layer network. The utilized output A multi-layer perception architecture model was calibrated...

Nowadays, datasets are growing daily to obtain knowledge from big dataset. Extraction operation of useful information the dataset is called data mining that one major techniques get diagnostic results especially in medical care fields as breast cancer. Breast cancer widespread cancers among women if matched with all other tumors over world. Classification widely used most important and necessary tasks real life applications fields. This technique has ability detecting very...

Coronary Artery Disease (CAD) is very common among the major types of cardiovascular diseases, and there are several studies created with different features including data that collected from patients for timely diagnosis CAD. In this study, a dataset 21 have been used, risk score prediction system has proposed. The were divided into four groups. To determine effective CAD dataset; t-test Relief-f methods on Logistic Regression Analysis (LRA); Neural Network (NN) feature selection utilized....

Electrical energy forecasting is crucial for efficient, reliable, and economic operations of hospitals due to serving 365 days a year, 24/7, they require round-the-clock energy.An accurate prediction consumption particularly required management, maintenance scheduling, future renewable investment planning large facilities.The main objective this study forecast electrical demand by performing comparing well-known techniques, which are frequently applied short-term problem in the literature,...

Abstract Breast cancer and breast imaging diagnostic procedures are typically carried out using a variety of modalities, including mammography, MRI, ultrasound. However, ultrasound mammography have limitations MRI is recognized as better than other procedures. Recent computational approaches, such radiomics, applied to image analysis shown remarkable progress in lowering difficulties. This research analysed the robustness tumour classification with feature extraction (radiomics) featureless...

This paper reviews the energy sector in Rwanda with an accent on Renewable Energy. In Rwanda, plays a vital role supporting socio-economic evolution and has close connection to growth of other economic sectors. The country both renewable non-renewable sources. Energy policies give special attention use modern, clean efficient technologies. Most Electricity comes from sources: total currently installed electricity capacity is 160 MW (March 2015), which approximately more than 60% hydrological...

Among various medical diagnostic tests performed to identify osteoarthritis in the knee, most of them are invasive and expensive. Therefore, this study, another methodology for diagnosing knee a more qwick, non-invasive cheap manner was proposed. For that purpose, surface electromyography signals recorded from four muscles surrounding recording flexion degree pattern recognition algorithms were used. The datasets experiment comprised 22 subjects among whom 11 had normal other Subjects an...

In the field of orthopaedics, treatment extremity deformities can be realised by means external fixators. However, control such biomedical system is very difficult. Some different mathematical models have been developed to improve quality this service. Most parameters, which are used in these models, obtained from two orthogonal X-ray images: one anteroposterior, AP, direction and other a lateral, L, direction. The results model dependent on accuracy input parameters. Measuring parameters...

Image classification is a very easy task for humans. Even three years old child can classify an image instantly and without any doubt. However, teaching computers classifying images has been working area researchers long time because of the intrinsic difficulties computers. With rise deep learning, it possible to get better performance than before. In this work, we evaluated convolutional neural network combined with support vector machine aerial based on presence vehicle.

External fixators are widely used in the area of orthopedics to manage deformities and fractures. The historical trend obtaining a mechanical infrastructure has shifted from simple devices like pins, rods, hinges more sophisticated frames involving parallel manipulators. Despite advantages such robotic especially removing stiffness issues, there still problems associated with reliable deployment these modern devices. Problems singularity, possibilities guiding fragments along many different...

This paper proposes the use of artificial neural networks (ANN) to perfectly predict critical buckling loads cylindrical isotropic helical spring with fixed ends and circular sections, large pitch angles. The equations springs loaded axially consist a set twelve linear differential equations. As finding solution in an analytical manner is too difficult, numerical exact based on transfer-matrix method collect consistent dimensionless data for training process used. In this way almost perfect...

Bu çalışmada atık kömür katkılı modifiye bitüm kullanılarak Marshall tasarımı ile hazırlanmış asfalt betonu numunelerinin performans karakteristikleri deneysel tasarım yöntemlerinden Merkezi Kompozit Tasarım (MKT) ve Geri Yayılımlı Yapay Sinir Ağı (YSA) modeli tahmin edilmiştir. Her iki modelin ettiği değerleri karşılaştırılmıştır. MKT yönteminin optimum olarak belirlediği koşullarda doğrulama deneyleri gerçekleştirilmiştir. Ayrıca deney koşulları YSA giriş parametresi tanımlanmış ağın...