More Like this

1. Convolutional neural network learning for generic data classification

   Han, Huimei; Li, Ying; Zhu, Xingquan (March 2019, Information sciences)

   Convolutional Neural Network (CNN) uses convolutional layers to explore spatial/temporal adjacency to construct new feature representations. So, CNN is commonly used for data with strong temporal/spatial correlations, but cannot be directly applied to generic learning tasks. In this paper, we propose to enable CNN for learning from generic data to improve classification accuracy. To take the full advantage of CNN’s feature learning power, we propose to convert each instance of the original dataset into a synthetic matrix/image format. To maximize the correlation in the constructed matrix/image, we use 0/1 optimization to reorder features and ensure that the ones with strong correlations are adjacent to each other. By using a feature reordering matrix, we are able to create a synthetic image to represent each instance. Because the constructed synthetic image preserves the original feature values and correlation, CNN can be applied to learn effective features for classification. Experiments and comparisons, on 22 benchmark datasets, demonstrate clear performance gain of applying CNN to generic datasets, compared to conventional machine learning methods. Furthermore, our method consistently outperforms approaches which directly apply CNN to generic datasets in naive ways. This research allows deep learning to be broadly applied to generic datasets. 

   more » « less
2. Interactive AI Tutors for Training the Workforce of the Future

   Qian, Peizhu (April 2025, Rice University)

   Unhelkar, Vaibhav (Ed.)

   The need to train new workers effectively and upskill the existing workforce is a challenge faced by almost every industry across the globe. The healthcare industry, in particular, is confronting a crisis. The World Health Organization (WHO) projects a shortage of 10 million healthcare workers by 2030. However, according to the Future of Jobs Report by the World Economic Forum, only half of the workers have access to training and learning opportunities. To sustain a resilient workforce and to protect the health of the world’s population, my thesis looks at using AI and robots to accelerate human learners’ acquisition of workforce skills. Specifically, I develop novel Explainable AI (XAI) algorithms to automate training to enable workers to collaborate with autonomous robots - a trend that is fast-growing. I also use statistical models to model human learner cognitive processes to create Human-Robot Interaction (HRI) systems to generate effective instructions tailored to individual learners. In addition to driving technical advances, my research is having a positive societal impact. I collaborate with Houston Methodist Hospital to create a first-of-its-kind robotic tutor for clinical nursing education to reduce healthcare-associated infections. 

   more » « less
3. Cuttlefish exert self-control in a delay of gratification task

   https://doi.org/10.1098/rspb.2020.3161  

   Schnell, Alexandra K.; Boeckle, Markus; Rivera, Micaela; Clayton, Nicola S.; Hanlon, Roger T. (March 2021, Proceedings of the Royal Society B: Biological Sciences)

   The ability to exert self-control varies within and across taxa. Some species can exert self-control for several seconds whereas others, such as large-brained vertebrates, can tolerate delays of up to several minutes. Advanced self-control has been linked to better performance in cognitive tasks and has been hypothesized to evolve in response to specific socio-ecological pressures. These pressures are difficult to uncouple because previously studied species face similar socio-ecological challenges. Here, we investigate self-control and learning performance in cuttlefish, an invertebrate that is thought to have evolved under partially different pressures to previously studied vertebrates. To test self-control, cuttlefish were presented with a delay maintenance task, which measures an individual's ability to forgo immediate gratification and sustain a delay for a better but delayed reward. Cuttlefish maintained delay durations for up to 50–130 s. To test learning performance, we used a reversal-learning task, whereby cuttlefish were required to learn to associate the reward with one of two stimuli and then subsequently learn to associate the reward with the alternative stimulus. Cuttlefish that delayed gratification for longer had better learning performance. Our results demonstrate that cuttlefish can tolerate delays to obtain food of higher quality comparable to that of some large-brained vertebrates. 

   more » « less
4. Geometrical Relations between Slab Dip and the Location of Volcanic Arcs and Back-arc Spreading Centers

   https://doi.org/10.5281/zenodo.7636704  

   Ha, Goeun; Montési, Laurent G.; Zhu, Wenlu (January 2023, Zenodo)

   The dataset includes the measurements of individual subduction zones defined in the convergence-parallel, trench-perpendicular, and spreading-parallel direction. </p>  </p> Table S3. Location of each trench, arc, and back-arc defined in a direction parallel to the convergence, and the corresponding distance from the trench to the arc (D_TA), subarc slab depth (H), and from the trench to the back-arc spreading center (D_TB). The slab dip is measured at 50km (Dip50), 100km (Dip100), and 200km (Dip200) and averaged from 0 to 50 km (Dip050), 0 to 100km (Dip0100), 0 to 200km (Dip0200), and 50 to 200km (Dip50200). </p> Table S4. Location of each trench, arc, and back-arc defined in a direction perpendicular to the trench, and the corresponding distance from the trench to the arc (D_TA), subarc slab depth (H), and from the trench to the back-arc spreading center (D_TB). The slab dip is measured at 50km (Dip50), 100km (Dip100), and 200km (Dip200) and averaged from 0 to 50 km (Dip050), 0 to 100km (Dip0100), 0 to 200km (Dip0200), and 50 to 200km (Dip50200). </p> Table S5. Location of each trench, arc, and back-arc defined in a direction parallel to the spreading direction, and the corresponding distance from the trench to the arc (D_TA), subarc slab depth (H), and from the trench to the back-arc spreading center (D_TB). The slab dip is measured at 50km (Dip50), 100km (Dip100), and 200km (Dip200) and averaged from 0 to 50 km (Dip050), 0 to 100km (Dip0100), 0 to 200km (Dip0200), and 50 to 200km (Dip50200). </p>  </p> 

   more » « less
5. Molecular docking with Python in Jupyter Notebooks: Towards the development of accessible docking procedures

   Schoneman, Lee; Craig, Paul A (April 2025, ASBMB)

   Molecular docking is a computational technique used to predict ligand binding potential, conformation, and location for a given receptor, and is regarded as an attractive method to use in drug design due to its relatively low computational and monetary cost. However, molecular docking programs tend not to be accessible to novice users. Most docking programs require at least a basic knowledge of command line and computer programming to install and configure the program. Additionally, tutorials for the most commonly used programs tend to be inflexible, requiring a specific molecule or set of molecules to be bound to a specific receptor, and need the installation and usage of other programs or websites to download and prepare structures. To increase general access to molecular docking, basil_dock utilizes a series of easy-to-use Jupyter notebooks that do not assume user familiarity with molecular docking procedures and concepts, requiring little command line usage and software installation. The series includes four notebooks that were created to reflect the different steps in the molecular docking process: (1) the preparation of ligand and protein files prior to docking, (2) the docking of ligands to a protein receptor, (3) analyzing the resulting data and determining how different functional groups in the ligand can affect protein-ligand binding, and (4) identifying essential locations for binding within the ligand and protein. The notebooks enable novice users flexibility and customization in exploring docking procedures and systems, as well as teaching users the basis behind molecular docking without having to leave the environment to obtain information and materials from other applications. The first version of basil_dock allows users to choose from receptors uploaded to the Protein Data Bank and to add additional ligands as desired. Users can then select between the Vina and Smina docking engines and change ligand functional groups to see how the substitution of atom groups affects binding affinity and ligand conformation. The data can then be analyzed to determine residues in the receptor and atom groups in the ligand that are likely to be integral to forming the ligand-protein complex and to discern which ligands are likely to be orally bioactive based on Lipinski’s Rule of Five. From this work, a package of python scripts has been created to streamline the generating, splitting, and writing of ligand files, greatly reducing the number of errors arising from attempting to split a comprehensive ligand file manually. Libraries used in basil_dock include Vina, Smina, RDKit, openbabel, and MDAnalysis. While the package has been designed based off the needs of basil_dock, it has been created to be extensible. Support for this project was provided by NSF 2142033 

   more » « less