This paper presents the development and implementation of an application that recognizes American Sign Language signs with the use of deep learning algorithms based on convolutional neural network architectures. The project implementation includes the development of a training set, the preparation of a module that converts photos to a form readable by the artificial neural network, the selection of the appropriate neural network architecture and the development of the model. The neural network undergoes a learning process, and its results are verified accordingly. An internet application that allows recognition of sign language based on a sign from any photo taken by the user is implemented, and its results are analyzed. The network effectiveness ratio reaches 99% for the training set. Nevertheless, conclusions and recommendations are formulated to improve the operation of the application.
The article concerns the issue of automatic recognition of the moment of achieving the desired degree of training of an operator of devices used in precision agriculture. The aim of the research was to build a neural model that recognizes when an operator has acquired the skill of operating modern navigation on parallel strips used in precision agriculture. To conduct the test, a standard device to assist the operator in guiding the machine along given paths, eliminating overlaps, was selected. The thesis was proven that the moment of operator training (meaning driving along designated paths with an accuracy of up to eight centimeters) can be automatically recognized by a properly selected artificial neural network. This network was learned on the basis of data collected during the observation of the operator training process, using a criterion defined by experts. The data collected in the form of photos of the actual and designated route was converted into numerical data and entered into the network input. The output shows the binary evaluation of the trip. It has been shown that the developed neural model will allow the determining of the moment when operators acquire the skills to drive a vehicle along the indicated path and thus shorten the training time.
The research attempts to determine the possibility of using the phenomenon of secondary luminescence of organic matter to assess its properties, which are important from the point of view of food quality parameterization. In order to conduct the experiment, a measuring station equipped with a photomultiplier was used to identify individual photons emitted by organic matter. There was a difference in the number of photons recorded by the photon measuring system within selected groups of food products, this statement concerns the final products and components constituting their recipe. It has been observed that there is a practical possibility of differentiating organic matter in terms of the degree of photon emission.
The paper presents the interconnection of the components of the prototype station for determining the degree of ultra-low photon emission, as well as the control system created in the LabView environment. The principle of operation of the device is based on photon emission from organic matter, which is recorded in a light-tight chamber through a properly selected photomultiplier. The station allows to determine the so-called ultra-weak luminescence of a material which size is characteristic for a given object and is a differentiating feature that can be used as a tool to supplement the assessment of the quality of food products of various degrees of processing. On the created measurement station the shape of signals originating from individual photoelectrons reaching the photon counting system was analyzed using the oscilloscope. A method of eliminating disturbances resulting from the operation of the measurement system has been developed. It was found that the measurement system fulfills the assumed objective function and the method of measuring ultra-low photonic emission can be very useful in food quality assessment technologies.
The scope of work will include the timing of driver's working time (two persons) during the typical working week. Physical load will be determined based on the amount of heart contractions and its interpretation using the WRT index and on the basis of the oxygen consumption determined by lung ventilation. Polar's computer apparatus and software will be used as well as the EC-4 microprocessor energy meter. The comparative analysis will allow to distinguish between the type of activity and the degree of physical strain. In addition, the research should provide an answer to the extent to which physical fatigue affects performance in the case of selected transport tasks. The final result should be a process optimization, where the objective function will be to minimize energy expenditure while maintaining the required work efficiency.