NPIPVis:A visualization system involving NBA visual analysis and integrated learning model prediction

Background Data-driven event analysis has gradually become the backbone of modern competitive sports analysis. Competitive sports data analysis tasks increasingly use computer vision and machine-learning models for intelligent data analysis. Existing sports visualization systems focus on the player–team data visualization, which is not intuitive enough for team season win–loss data and game time-series data visualization and neglects the prediction of all-star players. Methods This study used an interactive visualization system designed with parallel aggregated ordered hypergraph dynamic hypergraphs, Calliope visualization data story technology,and i Storyline narrative visualization technology to visualize the regular statistics and game time data of players and teams. NPIPVis includes dynamic hypergraphs of a team’s wins and losses and game plot narrative visualization components. In addition, an integrated learning-based all-star player prediction model, SRR-voting, which starts from the existing minority and majority samples, was proposed using the synthetic minority oversampling technique and Random Under Sampler methods to generate and eliminate samples of a certain size to balance the number of allstar and average players in the datasets. Next, a random forest algorithm was introduced to extract and construct the features of players and combined with the voting integrated model to predict the all-star players, using GridSearch CV, to optimize the hyperparameters of each model in integrated learning and then combined with five-fold cross-validation to improve the generalization ability of the model. Finally, the SHapley Additive ex Planations(SHAP) model was introduced to enhance the interpretability of the model. Results The experimental results of comparing the SRR-voting model with six common models show that the accuracy, F1-score, and recall metrics are significantly improved, which verifies the effectiveness and practicality of the SRR-voting model. Conclusions This study combines data visualization and machine learning to design a National Basketball Association data visualization system to help the general audience visualize game data and predict all-star players;this can also be extended to other sports events or related fields.

Electrostatic and hydrophobic interaction cooperative nanochaperone regulates protein folding

Natural molecular chaperones utilize spatially ordered multiple molecular forces to effectively regulate protein folding.However,synthesis of such molecules is a big challenge.The concept of“aggregate science”provides insights to construct chemical entities(aggregates)beyond molecular levels to mimic both the structure and function of natural chaperone.Inspired by this concept,herein we fabricate a novel multi-interaction(i.e.,electrostatic and hydrophobic interaction)cooperative nanochaperone(multi-co-nChap)to regulating protein folding.This multi-co-nChap is fabricated by rationally introducing electrostatic interactions to the surface(corona)and confined hydrophobic microdomains(shell)of traditional single-hydrophobic interaction nanochaperone.We demonstrate that the corona electrostatic attraction facilitates the diffusion of clients into the hydrophobic microdomains,while the shell electrostatic interaction balances the capture and release of clients.By finely synergizing corona electrostatic attraction with shell electrostatic repulsion and hydrophobic interaction,the optimized multi-co-nChap effectively facilitated de novo folding of nascent polypeptides.Moreover,the synergy between corona electrostatic attraction,shell electrostatic attraction and shell hydrophobic interaction significantly enhanced the capability of multi-co-nChap to protect native proteins from denaturation at harsh temperatures.This work provides important insights for understanding and design of nanochaperone,which is a kind of ordered aggregate with chaperone-like activity that beyond the level of single molecule.

ORDERED WEIGHTED AVERAGING AGGREGATION METHOD FOR PORTFOLIO SELECTION

Portfolio management is a typical decision making problem under incomplete,sometimes unknown, information. This paper considers the portfolio selection problemsunder a general setting of uncertain states without probability. The investor's preferenceis based on his optimum degree about the nature, and his attitude can be described by anOrdered Weighted Averaging Aggregation function. We construct the OWA portfolio selection model, which is a nonlinear programming problem. The problem can be equivalentlytransformed into a mixed integer linear programming. A numerical example is given andthe solutions imply that the investor's strategies depend not only on his optimum degreebut also on his preference weight vector. The general game-theoretical portfolio selectionmethod, max-min method and competitive ratio method are all the special settings of thismodel.