Search for: All records

Games and competitions enhance student engagement and help improve hands-on learning of computing concepts. Focusing on targeted goals, competitions provide a sense of community and accomplishment among students, fostering peer-learning opportunities. Despite these benefits of motivating and enhancing student learning, the impact of competitions on curricular learning outcomes has not been sufficiently studied. For institutional or program accreditation, understanding the extent to which students achieve course or program learning outcomes is essential, and helps in establishing continuous improvement processes for the program curriculum. Utilizing the Collegiate Cyber Defense Competition (CCDC), a curricular assessment was conducted for an undergraduate cybersecurity program at a US institution. This archetypal competition was selected as it provides an effective platform for broader program learning outcomes, as students need to: (1) function in a team and communicate effectively (teamwork and communication skills); (2) articulate technical information to non-technical audiences (communication skills); (3) apply excellent technical and non-technical knowledge (design and analysis skills applied to problem-solving); and (4) function well under adversity (real-world problem-solving skills). Using data for both students who competed and who did not, student progress was tracked over five years. Preliminary analysis showed that these competitions made marginally-interested students become deeply engaged with the curriculum; broadened participation among women who became vital to team success by showcasing their technical and management skills; and pushed students to become self-driven, improving their academic performance and career placements. This experience report also reflects on what was learned and outlines the next steps for this work. 

Electron microscopy images of carbon nanotube (CNT) forests are difficult to segment due to the long and thin nature of the CNTs; density of the CNT forests resulting in CNTs touching, crossing, and occluding each other; and low signal-to-noise ratio electron microscopy imagery. In addition, due to image complexity, it is not feasible to prepare training segmentation masks. In this paper, we propose CNTSegNet, a dual loss, orientation-guided, self-supervised, deep learning network for CNT forest segmentation in scanning electron microscopy (SEM) images. Our training labels consist of weak segmentation labels produced by intensity thresholding of the raw SEM images and self labels produced by estimating orientation distribution of CNTs in these raw images. The proposed network extends a U-net-like encoder-decoder architecture with a novel two-component loss function. The first component is dice loss computed between the predicted segmentation maps and the weak segmentation labels. The second component is mean squared error (MSE) loss measuring the difference between the orientation histogram of the predicted segmentation map and the original raw image. Weighted sum of these two loss functions is used to train the proposed CNTSegNet network. The dice loss forces the network to perform background-foreground segmentation using local intensity features. The MSE loss guides the network with global orientation features and leads to refined segmentation results. The proposed system needs only a few-shot dataset for training. Thanks to it’s self-supervised nature, it can easily be adapted to new datasets. 

Carbon nanotube (CNT) forests are imaged using scanning electron microscopes (SEMs) that project their multilayered 3D structure into a single 2D image. Image analytics, particularly instance segmentation is needed to quantify structural characteristics and to predict correlations between structural morphology and physical properties. The inherent complexity of individual CNT structures is further increased in CNT forests due to density of CNTs, interactions between CNTs, occlusions, and lack of 3D information to resolve correspondences when multiple CNTs from different depths appear to cross in 2D. In this paper, we propose CNT-NeRF, a generative adversarial network (GAN) for simultaneous depth layer decomposition and segmentation of CNT forests in SEM images. The proposed network is trained using a multi-layer, photo-realistic synthetic dataset obtained by transferring the style of real CNT images to physics-based simulation data. Experiments show promising depth layer decomposition and accurate CNT segmentation results not only for the front layer but also for the partially occluded middle and back layers. This achievement is a significant step towards automated, image-based CNT forest structure characterization and physical property prediction.