Deep-learning workflows of microscopic image analysis are sufficient for handling the contextual variations because they employ biological samples and have numerous tasks. The use of well-defined annotated images is important for the workflow. Cancer stem cells (CSCs) are identified by specific cell markers. These CSCs were extensively characterized by the stem cell (SC)-like gene expression and proliferation mechanisms for the development of tumors. In contrast, the morphological characterization remains elusive. This study aims to investigate the segmentation of CSCs in phase contrast imaging using conditional generative adversarial networks (CGAN). Artificial intelligence (AI) was trained using fluorescence images of the Nanog-Green fluorescence protein, the expression of which was maintained in CSCs, and the phase contrast images. The AI model segmented the CSC region in the phase contrast image of the CSC cultures and tumor model. By selecting images for training, several values for measuring segmentation quality increased. Moreover, nucleus fluorescence overlaid-phase contrast was effective for increasing the values. We show the possibility of mapping CSC morphology to the condition of undifferentiation using deep-learning CGAN workflows.

The growing prominence of e-learning in education has led to the need for a comprehensive understanding of the factors influencing learning outcomes. This study aims to investigate the combined effects of e-learning orientation, Moodle usage, and learning planning on learning outcomes in the context of on-demand lectures. A sample of participants from the Department of Information Science and Engineering in the Faculty of Engineering completed questionnaires related to e-learning orientation, while Moodle usage data and learning planning information were collected. Correlation, principal component, cluster, and multiple regression analysis were conducted to examine the relationships between variables and their impact on learning outcomes. The results suggest that e-learning orientation did not exert a significant influence on learning outcomes. However, Moodle usage and learning planning emerged as crucial factors. Increased engagement with Moodle, as indicated by higher clicks and utilization of its learning functionalities, was associated with improved learning outcomes. Additionally, effective learning planning, characterized by adherence to schedules and timely submissions, positively influenced learning outcomes. The results emphasize the importance of considering multiple factors, not just a single factor, for successful online learning. These findings provide valuable insights for optimizing learning outcomes in on-demand lectures.

The number of elements in two stereo-surfaces parallelly overlapped in depth is overestimated compared to that in a single flat surface, even when both have the same number of elements. Using stereoscopic pairs of elements, we evaluated two hypotheses on the overestimation: one that a higher-order process, forming a background surface, increases the number of perceived elements, and the other that the number of elements potentially occluded by the elements on a front surface is taken accounted for. The data from four experiments showed that (a) when binocular disparity between (or among) stereoscopic elements was small, the overestimation occurred for the stimuli we used—a two-surface-overlapping stimulus, where the likelihood for the process to operate was manipulated by changing the averaged luminance of each surface, a volumetric stimulus, where the likelihood for the background surface to be formed would decrease, and a two-non-overlapping-surface stimulus, where the surfaces in depth were not overlapped—, and (b) when binocular disparity was large, the overestimation occurred for the two-surfaces-overlapping stimulus, when the averaged luminance of the two surfaces were the same, and for the volumetric stimulus, but diminished for the surface-overlapping stimulus, when the averaged luminance differed between the surfaces and for the surfaces-non-overlapping stimulus. These results cannot be explained either hypothesis only. We explain the results by postulating that the sensory system processing disparities of elements interferes with that estimating the number of elements, resulting in an overestimation of the elements in a stereo-stimulus, and the disparity range within which the interference occurs may depend on the stimulus depth structure.

Samawa language is one of living languages with more than 500K native speakers in Sumbawa island, Indonesia. There are, however, extremely small amounts of available resources and efforts to develop tools in the Natural Language Processing (NLP) discipline area. In this paper, we observe and evaluate three models of probabilistic approach which are Unigram, Hidden Markov Model (HMM) and Trigram’n’Tags (TnT) models for part of speech tagging problem, which is a process to label either word or punctuation in a sentence. We used k-fold cross-validation (with k = 5 and 10) and tagged corpus around 20K tokens with 24 tags. TnT model gives the best performance reached 96.18% compared with the other models. This result shows that TnT model could be considered and used to extend Samawa corpora and help some NLP tasks in the future.