Electromyography (EMG) data gives information about the electrical activity related to muscles. EMG data obtained from arm through sensors helps to understand hand gestures. For this work, hand gesture data were taken from UCI2019 EMG dataset obtained from MYO thalmic armband were classied with six dierent machine learning algorithms. Articial Neural Network (ANN), Support Vector Machine (SVM), k-Nearest Neighbor (k-NN), Naive Bayes (NB), Decision Tree (DT) and Random Forest (RF) methods were preferred for comparison based on several performance metrics which are accuracy, precision, sensitivity, specicity, classication error, kappa, root mean squared error (RMSE) and correlation. The data belongs to seven hand gestures. 700 samples from 7 classes (100 samples per group) were used in the experiments. The splitting ratio in the classication was 0.8-0.2, i.e. 80% of the samples were used in training and 20% of data were used in testing phase of the classier. NB was found to be the best among other methods because of high accuracy (96.43%) and sensitivity (96.43%) and the lowest RMSE (0.189). Considering the results of the performance parameters, it can be said that this study recognizes and classies seven hand gestures successfully in comparison with the literature.
31 May 2016 in El-Cezeri Fen ve Mühendislik Dergisi
Dünya Sağlık Örgütü’nün verilerine göre, hem gelişmiş hem de gelişmekte olan ülkelerde, göğüs kanseri kadınlar arasındaki en yaygın kanser türüdür. Kentleşme ve batılı hayat tarzına uyum sağlamanın gelişen dünyada bu kanser türünü tetiklediği düşünülmektedir. Çoğu kanser vakası hastalığın son evrelerinde teşhis edilebilmekte ve tedaviler bu evreden sonra çoğu zaman cevap verememekte ve hasta kayıpları yaşanmaktadır. Bu sebeple, diğer kanser türlerinde olduğu gibi, göğüs kanserinin de erken tanısı hayati önem taşımaktadır. Bu çalışmada, göğüs kanserinin erken tanısına katkıda bulunabilmek amaçlanmıştır. Hastalara belirtileri doğrultusunda göğüs kanseri olup olmadıklarına dair teşhis konulmuştur. Bu amaçla, veritabanında mevcut olan, önceden teşhisi konulmuş vakaların verileri kullanılarak, henüz teşhisi belli olmayan örneklere tahmin yoluyla teşhis konulmuştur. Tahmin işi, tasarlanan bir yapay sinir ağına yaptırılmış ve doğruluk oranı %77 olarak bulunmuştur.
1 June 2022 in Biomedical Engineering / Biomedizinische Technik
Parkinson’s disease (PD), a slow-progressing neurological disease, affects a large percentage of the world’s elderly population, and this population is expected to grow over the next decade. As a result, early detection is crucial for community health and the future of the globe in order to take proper safeguards and have a less arduous treatment procedure. Recent research has begun to focus on the motor system deficits caused by PD. Because practically most of the PD patients suffer from voice abnormalities, researchers working on automated diagnostic systems investigate vocal impairments. In this paper, we undertake extensive experiments with features extracted from voice signals. We propose a layer Recurrent Neural Network (RNN) based diagnosis for PD. To prove the efficiency of the model, different network models are compared. To the best of our knowledge, several neural network topologies, namely RNN, Cascade Forward Neural Networks (CFNN), and Feed Forward Neural Networks (FFNN), are used and compared for voice-based PD detection for the first time. In addition, the impacts of data normalization and feature selection (FS) are thoroughly examined. The findings reveal that normalization increases classifier performance and Laplacian-based FS outperforms. The proposed RNN model with 300 voice features achieves 99.74% accuracy.
1 April 2020 in Sakarya University Journal of Science
Machine learning methods have been frequently used for the diagnosis of several diseases recently because of its reliability and convenience. In this paper, a comprehensive overview of the literature related to diabetes and diabetic retinopathy has been done and diagnosis of diabetic retinopathy disease is investigated. Artificial Neural Networks (ANN) method has been applied to the problem using Rapid Miner, a data mining tool. Some other methods have also adapted to the problem, but ANN based detection approach gave the best results. 88.52% sensitivity has been obtained using the features of Messidor dataset. Besides showing the success of ANN in diabetic retinopathy detection, this study also proved that Rapid Miner can be used effectively for the analysis of diabetic retinopathy.
30 April 2020 in Düzce Üniversitesi Bilim ve Teknoloji Dergisi
Mesothelioma is pleura cancer that cause death in about one year after diagnosis. The disease causes pain and shortness of breath. Patients have a CT (Computed Tomography)-scan and lung x-ray traditionally, but the exact method is biopsy. There are also different biopsy methods for its diagnosis. Its prevalence is one or two in a million around the world, but for Turkey it is disastrous. Five hundred people are diagnosed as mesothelioma every year in Turkey. This serious rate makes early diagnosis systems crucial for mesothelioma. In this paper, a machine learning based early detection system has been proposed for this fatal disease. An open database is used for the experiments and different methods have been applied to the problem of diagnosing mesothelioma disease. Accuracy and sensitivity performance metrics were used for the evaluation of the methods. The results show the diagnostic performance of different machine learning methods and present a successful early diagnosis system.