Band 17, Heft 3

Objectives Helping patients suffering from serious neurological diseases that lead to hindering the independent movement is of high social importance and an interdisciplinary challenge for engineers. Brain–computer interface (BCI) interfaces based on the electroencephalography (EEG) signal are not easy to use as they require time consuming multiple electrodes montage. We aimed to contribute in bringing BCI systems outside the laboratories so that it could be more accessible to patients, by designing a wheelchair fully controlled by an algorithm using alpha waves and only a few electrodes. Methods The set of eight binary words are designed, that allow to move forward, backward, turn right and left, rotate 45° as well as to increase and decrease the speed of the wheelchair. Our project includes: development of a mobile application which is used as a graphical user interface, real-time signal processing of the EEG signal, development of electric wheelchair engines control system and mechanical construction. Results The average sensitivity, without training, was 79.58% and specificity 97.08%, on persons who had no previous contact with BCI. Conclusions The proposed system can be helpful for people suffering from incurable diseases that make them closed in their bodies and for whom communication with the surrounding world is almost impossible.

Objectives The key test in Content-Based Medical Image Retrieval (CBMIR) frameworks for MRI (Magnetic Resonance Imaging) pictures is the semantic hole between the low-level visual data caught by the MRI machine and the elevated level data seen by the human evaluator. Methods The conventional component extraction strategies centre just on low-level or significant level highlights and utilize some handmade highlights to diminish this hole. It is important to plan an element extraction structure to diminish this hole without utilizing handmade highlights by encoding/consolidating low-level and elevated level highlights. The Fleecy gathering is another packing technique, which is applied in plan depiction here and SVM (Support Vector Machine) is applied. Remembering the predefinition of bunching amount and enlistment cross-section is until now a significant theme, a new predefinition advance is extended in this paper, in like manner, and another CBMIR procedure is suggested and endorsed. It is essential to design a part extraction framework to diminish this opening without using painstakingly gathered features by encoding/joining low-level and critical level features. Results SVM and FCM (Fuzzy C Means) are applied to the power structures. Consequently, the incorporate vector contains all the objectives of the image. Recuperation of the image relies upon the detachment among request and database pictures called closeness measure. Conclusions Tests are performed on the 200 Image Database. Finally, exploratory results are evaluated by the audit and precision.

Objectives This paper focuses on developing a regularization-based feature selection approach to select the most effective attributes from the Parkinson’s speech dataset. Parkinson’s disease is a medical condition that progresses as the dopamine-producing nerve cells are affected. Early diagnosis often reduces the effect on the individuals, minimizes the advancement over time. In recent times, intelligent computational models are used in many complex cases to diagnose a clinical condition with high precision. These models are intended to find meaningful representation from the data to diagnose the disease. Machine learning acts as a tool, gears up the model learning process through a mathematical baseline. But, not in all cases, machine learning will be demanded to perform optimally. It comes with a few constraints, mainly the representation of the data. The learning models expect a clean, noise-free input, which in-turns produces better discriminative patterns over different categories of classes. Methods The proposed model identified five candidate features as predictors. This feature subset is trained with different varieties of supervised classifiers to trace out the best-performing model. Results The results are validated through accuracy, precision, recall, and receiver’s operational characteristic curves. The proposed regularization- based feature selection model outperformed the benchmark algorithms by attaining 100% accuracy on most of the classifiers, other than linear discriminant analysis (99.90%) and naïve Bayes (99.51%). Conclusions This paper exhibits the need for intelligent models to analyze complex data patterns to assist medical practitioners in better disease diagnosis. The results exhibit that the regularization methods find the best features based on their importance score, which improved the model performance over other feature selection methods.

Objectives Purpose of this research was to find the best blue-emitting fluorescent substance for plastic scintillator used for gamma radiation dosimetry. Scintillator should convert gamma radiation into blue light with high efficiency. Methods Plastic scintillators with fixed concentration of various fluorescent additives, called wavelength shifters, absorbing ultraviolet light and emitting blue light were manufactured by radical bulk polymerization of styrene. Light output were measured and compared to the light output of commercial plastic scintillator. Results Performed measurements of charge Compton spectra confirmed usefulness of majority of researched substances as wavelength shifters in plastic scintillators with emission maximum at blue range of visible light. Conclusions Plastic scintillation dosimeter may be constructed from manufactured polystyrene-based scintillators. Performance of synthesized scintillators is close to commercial polystyrene scintillators.