Search

The recognition of stomatological disorders and the classification of dental caries are important areas of biomedicine that can hugely benefit from machine learning tools for the construction of relevant mathematical models. This paper explores the possibility of using reflectivity data to distinguish between healthy tissues and caries by deep learning and multilayer convolutional neural networks. The experimental data set includes more than 700 observations recorded in the stomatology laboratory. For rigor, the results obtained from the deep learning systems are compared with those evaluated for selected sets of features estimated for each observation and classified by a decision tree, support vector machine (SVM), k-nearest neighbor, Bayesian methods, and two-layer neural networks. The classification accuracy obtained for the deep learning systems was 98.1% and 94.4% for data in the signal and spectral domains, respectively, in comparison with an accuracy of 97.2% and 87.2% evaluated by the SVM method. The proposed method conclusively demonstrates how the artificial intelligence and deep learning methodology can contribute to improved diagnosis of dental problem in stomatology. [ABSTRACT FROM AUTHOR]

The monitoring of physical activities and recognition of motion disorders belong to important diagnostical tools in neurology and rehabilitation. The goal of the present paper is in the contribution to this topic by (1) analysis of accelerometric signals recorded by wearable sensors located at specific body positions and by (2) implementation of deep learning methods to classify signal features. This paper uses the general methodology to analysis of accelerometric signals acquired during cycling at different routes followed by the global positioning system. The experimental dataset includes 850 observations that were recorded by a mobile device in the spine area (L3 verterbra) for cycling routes with the different slope. The proposed methodology includes the use of deep learning convolutional neural networks with five layers applied to signal values transformed into the frequency domain without specification of any signal features. The accuracy of discrimination between different motion patterns for the uphill and downhill cycling and recognition of 4 classes associated with different route slopes was 96.6% with the loss criterion of 0.275 for sigmoidal activation functions. These results were compared with those evaluated for selected sets of features estimated for each observation and classified by the support vector machine, Bayesian methods, and the two-layer neural network. The best cross-validation error of 0.361 was achieved for the two-layer neural network model with the sigmoidal and softmax transfer functions. Our methodology suggests that deep learning neural networks are efficient in the assessment of motion activities for automated data processing and have a wide range of applications, including rehabilitation, early diagnosis of neurological problems, and possible use in engineering as well. [ABSTRACT FROM AUTHOR]

The recognition of motion patterns belongs to very important research areas related to neurology, rehabilitation, and robotics. It is based on modern sensor technologies and general mathematical methods, multidimensional signal processing, and machine learning. The present paper is devoted to the detection of features associated with accelerometric data acquired by 31 time-synchronized sensors located at different parts of the body. Experimental data sets were acquired from 25 individuals diagnosed as healthy controls and ataxic patients. The proposed method includes the application of the discrete Fourier transform for the estimation of the mean power in selected frequency bands and the use of these features for data segments classification. The study includes a comparison of results obtained from signals recorded at different positions. Evaluations are based on classification accuracy and cross-validation errors estimated by support vector machine, Bayesian, nearest neighbours (k-NN], and neural network (NN) methods. Results show that highest accuracies of 77.1%, 78.9%, 89.9%, 98.0%, and 98.5% were achieved by NN method for signals acquired from the sensors on the feet, legs, uplegs, shoulders, and head/spine, respectively, recorded in 201 signal segments. The entire study is based on observations in the clinical environment and suggests the importance of augmented reality to decisions and diagnosis in neurology. [ABSTRACT FROM AUTHOR]

This paper presents a novel method of gait recognition that uses the image and depth sensors of the Microsoft (MS) Kinect to track the skeleton of a moving body and allows for simple human-machine interaction. While video sequences acquired by complex camera systems enable very precise data analyses and motion detection, much simpler technical devices can be used to analyze video frames with sufficient accuracy in many cases. The experimental part of this paper is devoted to gait data acquisition from 18 individuals with Parkinson's disease and 18 healthy age-matched controls via the proposed MS Kinect graphical user interface. The methods designed for video frame data processing include the selection of gait segments and data filtering for the estimation of chosen gait characteristics. The proposed computational algorithms for the processing of the matrices acquired by the image and depth sensors were then used for spatial modeling of the moving bodies and the estimation of selected gait features. Normalized mean stride lengths were evaluated for the individuals with Parkinson's disease and those in the control group and were determined to be 0.38 and 0.53 m, respectively. These mean stride lengths were then used as features for classification. The achieved accuracy was >90 %, which suggests the potential of the use of the image and depth sensors of the MS Kinect for these applications. Further potential increases in classification accuracy via additional biosensors and body features are also discussed. [ABSTRACT FROM AUTHOR]

In needle electromyography, general mathematical methods of pattern recognition and signal analysis can be used to detect motor unit potentials and to classify various types of muscle diseases. The goal of the paper is to contribute to various methods enabling discrimination of individuals with axonal neuropathy (a positive set) from normal cases (a control set) using signals acquired from muscle activities. Data from a control set of 104 individuals and a set of 76 patients were used to validate selected methods of their separation and classification. Different features in both the time and frequency domains were studied to obtain the most reliable results . This novel approach involves comparison of individual features based on adaptive signal thresholding, as well as their combination, using supervised sigmoidal neural networks for their classification. Specificity, sensitivity and accuracy of the features used to detect individuals with axonal neuropathy was analysed using the receiver operating characteristic curves and confusion analysis. An accuracy higher than 93 % was achieved for the given sets of individuals and the optimal criterion values. The proposed modified Willison amplitude together with statistical and spectral properties of signal components classified individuals into sets of healthy and neuropathic patients by artificial neural networks with sensitivity 96.1 % and sufficient accuracy in the wide range of criterion values. [ABSTRACT FROM AUTHOR]