Daylighting systems make daylight illuminance possible, and the development of prototype daylighting systems can provide more efficient daylight illuminance. The purpose of this article is to review the development and performance of prototype daylighting systems in the last decade. The passive and active daylighting systems are listed separately and divided into the four categories by the presence and absence of hybrid. Each prototype daylighting system was evaluated in terms of cost and daylight performance and as well as their novel optical design. We evaluated the architecture and daylighting principles of each system by reviewing individual prototype daylighting systems. The cost of prototype systems still poses a challenge to development. How to use passive or active systems in different environments and whether or not electrical lighting assistance is needed is a controversial issue. However, active daylighting systems equipped with solar tracking systems are still mainstream. This research is a valuable resource for daylight researchers and newcomers. It is helpful to understand the advantages of various prototype daylighting systems and commercial daylighting systems that have been developed for many years; moreover, it is also possible to know the research directions suggested by the prototype daylighting systems. These will be of further use in developing innovative and better daylighting systems and designs.

No abstract

The size of one’s pupil can indicate one’s physical condition and mental state. When we search related papers about AI and the pupil, most studies focused on eye-tracking. This paper proposes an algorithm that can calculate pupil size based on a convolution neural network (CNN). Usually, the shape of the pupil is not round, and 50% of pupils can be calculated using ellipses as the best fitting shapes. This paper uses the major and minor axes of an ellipse to represent the size of pupils and uses the two parameters as the output of the network. Regarding the input of the network, the dataset is in video format (continuous frames). Taking each frame from the videos and using these to train the CNN model may cause overfitting since the images are too similar. This study used data augmentation and calculated the structural similarity to ensure that the images had a certain degree of difference to avoid this problem. For optimizing the network structure, this study compared the mean error with changes in the depth of the network and the field of view (FOV) of the convolution filter. The result shows that both deepening the network and widening the FOV of the convolution filter can reduce the mean error. According to the results, the mean error of the pupil length is 5.437% and the pupil area is 10.57%. It can operate in low-cost mobile embedded systems at 35 frames per second, demonstrating that low-cost designs can be used for pupil size prediction.

No abstract

No abstract