The Application of Biological Feedback in the Rehabilitation of Patients after Ischemic Stroke.

Balance disorders are the main concern for patients after an ischemic stroke. They are caused by an abnormal force on the affected side or paresis, which causes uneven loading and visuospatial disorders. Minimizing the effects of stroke is possible through properly conducted rehabilitation. One of the known ways to achieve this objective is biological feedback. The lack of proper muscle tone on one side of the body is manifested by the uneven pressure of the lower extremities on the ground. The study and control groups were composed of two equal groups of 92 people each, in which the same set of kinesiotherapeutic exercises were applied. Patients in the study group, in addition to standard medical procedures, exercised five days a week on a Balance Trainer for four weeks. The examination and training with the device were recorded on the first day of rehabilitation, as well as after two and four weeks of training. The assessment was performed using the following functional tests and scales: Brunnström, Rankin, Barthel, Ashworth, and VAS. Patients in the control group started exercising on the Balance Trainer two weeks after the first day of rehabilitation using traditional methods. The study results reveal statistically significant reductions in the time the body's center of gravity (COG) spent in the tacks, outside the tracks and in the COG distance, lower COG excursions in all directions. Post-stroke patients that received biofeedback training presented significantly better results than patients that did not receive such training.

Flame Image Processing and Classification Using a Pre-Trained VGG16 Model in Combustion Diagnosis.

Nowadays, despite a negative impact on the natural environment, coal combustion is still a significant energy source. One way to minimize the adverse side effects is sophisticated combustion technologies, such as, e.g., staged combustion, co-combustion with biomass, and oxy-combustion. Maintaining the combustion process at its optimal state, considering the emission of harmful substances, safe operation, and costs requires immediate information about the process. Flame image is a primary source of data which proper processing make keeping the combustion at desired conditions, possible. The paper presents a method combining flame image processing with a deep convolutional neural network (DCNN) that ensures high accuracy of identifying undesired combustion states. The method is based on the adaptive selection of the gamma correction coefficient (G) in the flame segmentation process. It uses the empirically determined relationship between the G coefficient and the average intensity of the R image component. The pre-trained VGG16 model for classification was used. It provided accuracy in detecting particular combustion states on the ranging from 82 to 98%. High accuracy and fast processing time make the proposed method possible to apply in the real systems.