In virtual reality (VR), interaction techniques significantly influence user experience and performance. In this study, we explore the effect of the onset position of ray casting in VR through a target selection task. We designed the pointing task (i.e., Fitts’ law task) for data collection with various onset positions. We then analyzed data to explore how different onset positions affect the individuals’ performance for 3D interaction in terms of pointing and selection. Results showed significant effects for each participant yet no generalized impact was found across all participants. Results highlight the complexity of human-computer interaction in ray casting and suggest that a one-size-fits-all approach may not be effective. For future research and practical applications, our findings advocate a personalized approach that takes into account the specific preferences and responses of individual users. This tailored strategy could potentially improve the effectiveness and usability of interactive systems using ray cast techniques.

Microscopic image-based analysis has been intensively performed for pathological studies and diagnosis of diseases. However, mis-authentication of cell lines due to misjudgments by pathologists has been recognized as a serious problem. To address this problem, we propose a deep-learning-based approach for the automatic taxonomy of cancer cell types. A total of 889 bright-field microscopic images of four cancer cell lines were acquired using a benchtop microscope. Individual cells were further segmented and augmented to increase the image dataset. Afterward, deep transfer learning was adopted to accelerate the classification of cancer types. Experiments revealed that the deep-learning-based methods outperformed traditional machine-learning-based methods. Moreover, the Wilcoxon signed-rank test showed that deep ensemble approaches outperformed individual deep-learning-based models (p < 0.001) and were in effect to achieve the classification accuracy up to 97.735%. Additional investigation with the Wilcoxon signed-rank test was conducted to consider various network design choices, such as the type of optimizer, type of learning rate scheduler, degree of fine-tuning, and use of data augmentation. Finally, it was found that the using data augmentation and updating all the weights of a network during fine-tuning improve the overall performance of individual convolutional neural network models.