Activity recognition is the problem of predicting the current action of a person through the motion sensors worn on the body. The problem is usually approached as a supervised classification task where a discriminative model is learned from known samples and a new query is assigned to a known activity label using learned model. The challenging issue here is how to feed this classifier with a fixed number of features where the real input is a raw signal of varying length. In this study, we consider three possible feature sets, namely time-domain, frequency domain and wavelet-domain statistics, and their combinations to represent motion signal obtained from accelerometer reads worn in chest through a mobile phone. In addition to a systematic comparison of these feature sets, we also provide a comprehensive evaluation of some preprocessing steps such as filtering and feature selection. The results determine that feeding a random forest classifier with an ensemble selection of most relevant time-domain and frequency-domain features extracted from raw data can provide the highest accuracy in a real dataset

Neurodegenerative diseases occur because of degeneration in brain cells but can manifest as impairment of motor functions. One of the side effects of this impairment is an abnormality in walking. With the development of sensor technologies and artificial intelligence applications in recent years, the disease severity of patients can be estimated using their gait data. In this way, decision support applications for grading the severity of the disease that the patient suffers in the clinic can be developed. Thus, patients can have treatment methods more suitable for the severity of the disease. The presented research proposes a deep learning-based approach using gait data represented by a Quick Response code to develop an effective and reliable disease severity grading system for neurodegenerative diseases such as amyotrophic lateral sclerosis, Huntington’s disease, and Parkinson’s disease. The two-dimensional Quick Response data set was created by converting each one-dimensional gait data of the subjects with a novel representation approach to a Quick Response code. This data set was regressed with the convolutional neural network deep learning method, and a solution was sought for the problem of grading disease severity. Further, to demonstrate the success of the results obtained with the novel approach, native machine learning approaches such as Multilayer Perceptron, Random Forest, Extremely Randomized Trees, and K-Nearest Neighbours, and ensemble machine learning methods, such as voting and stacking, were applied on one-dimensional data. Finally, the results obtained on the prediction of disease severity by testing one-dimensional gait data with a convolutional neural network architecture that operates on one-dimensional data were included. The results showed that, in most cases, the two-dimensional convolutional neural network approach performed the best among all methods.

Eye diseases are one of the serious health problems affecting human life. Cataract, diabetic retinopathy and glaucoma eye diseases cause visual impairment and cause irreversible eye defects. Throughout human life; genetic, age and environmental factors affect people's eye health. Detection of the disease plays a critical role in order to apply the right diagnosis and therefore increase the quality of life of the patient. With the developing technology, artificial intelligence can detect eye defects and therefore whether there is a disease or not. This study aims to develop solutions for detecting an important health problem such as eye health by using deep learning models. In the related study, Convolutional Neural Networks models, one of the deep learning types are used. The data set used for disease detection includes a total of 2748 Retinal Fundus images taken from 1374 normal individuals and 1374 different disease groups. In order to compare the classification performances and to achieve better performance, a solution to the disease detection problem was sought by using a total of 5 different Convolutional Neural Networks architectures. These are DenseNet, EfficientNet, Xception, VGG, Resnet. For the validity of the approach, it was tested using the 10-fold cross-validation technique. Accuracy, Recall, Precision, F1-Score, and Matthews’s coefficient correlation metrics were used as performance evaluation criteria. When the classification performances were examined, the results obtained with the EfficientNet architecture were measured as 94.88%, 94.88%, 95.02%, 94.88%, 89.89% for Accuracy, Recall, Precision, F1-Score, and Matthews’s coefficient correlation metrics. In this context, the best classification performance was obtained with the EfficientNet architecture.