Interactive Graphics Research Articles

Narrowing the gap between machine learning scoring functions and free energy perturbation using augmented data

Machine learning offers great promise for fast and accurate binding affinity predictions. However, current models lack robust evaluation and fail on tasks encountered in (hit-to-) lead optimisation, such as ranking the binding affinity of a congeneric series of ligands, thereby limiting their application in drug discovery. Here, we address these issues by first introducing a novel attention-based graph neural network model called AEV-PLIG (atomic environment vector–protein ligand interaction graph). Second, we introduce a new and more realistic out-of-distribution test set called the OOD Test. We benchmark our model on this set, CASF-2016, and a test set used for free energy perturbation (FEP) calculations, that not only highlights the competitive performance of AEV-PLIG, but provides a realistic assessment of machine learning models with rigorous physics-based approaches. Moreover, we demonstrate how leveraging augmented data (generated using template-based modelling or molecular docking) can significantly improve binding affinity prediction correlation and ranking on the FEP benchmark (weighted mean PCC and Kendall’s τ increases from 0.41 and 0.26 to 0.59 and 0.42). These strategies together are closing the performance gap with FEP calculations (FEP+ achieves weighted mean PCC and Kendall’s τ of 0.68 and 0.49 on the FEP benchmark) while being ~400,000 times faster.

STIG-Net: a spatial–temporal interactive graph framework for recognizing violent behaviors in videos

STIG-Net: a spatial–temporal interactive graph framework for recognizing violent behaviors in videos

Patient deep spatio-temporal encoding and Medication substructure mapping for safe medication recommendation.

Medication recommendations are designed to provide physicians and patients with personalized, accurate and safe medication choices to maximize patient outcomes. Although significant progress has been made in related research, three major challenges remain: inadequate modeling of patients' multidimensional and time-series information, insufficient representation of medication substructures, and poor balance between model accuracy and drug-drug interactions. To address these issues , a safe medication recommendation model SDRBT based on patient deep spatio-temporal encoding and medication substructure mapping is proposed in this paper. SDRBT has developed a patient deep temporal and spatial coding module, which combines symptom information, disease diagnosis information, and treatment information from the patient's electronic health record data. It innovatively utilizes the Block Recurrent Transformer to model longitudinal temporal information of patients in different dimensions to obtain the horizontal representation of the patient's current visit. A dual-domain mapping module for medication substructures is designed to perform global and local mapping of medications, fully learning and aggregating medication substructure representations. Finally, a PID LOSS control unit was designed, in which we studied a drug interaction control module based on the similarity calculation between the electronic health map and the drug interaction graph. This module ensures the safety of the recommended medication combination effectively improved the recommendation efficiency and reduced the model training time . Experiments on the public MIMIC-III dataset demonstrate SDRBT's superior accuracy in medication recommendation.

Three Step Password Protection

In an era where digital security is paramount, traditional password systems remain vulnerable to sophisticated cyberattacks. This research presents a Three- Step Password Protection System aimed at significantly enhancing authentication security. The proposed model integrates three independent layers of authentication: (1) a Phrase Password, (2) Face Recognition, and (3) Graphical Authentication. Each step progressively strengthens security, ensuring that even if one layer is compromised, unauthorized access remains improbable. The system is designed to balance robust security with user convenience, addressing common vulnerabilities such as brute force, phishing, and bot attacks. By leveraging biometric verification and graphical interactions, the model reduces reliance on conventional text- based authentication while enhancing accessibility. The results suggest that this multi-layered approach provides improved resilience against unauthorized access, making it a viable solution for sensitive and high-security environments.

Spatiotemporal interactive learning dynamic adaptive graph convolutional network for traffic forecasting

Spatiotemporal interactive learning dynamic adaptive graph convolutional network for traffic forecasting

Interactive sequential generative models for team sports

Understanding spatiotemporal coordination of players in team sports is key to movement models, pattern detection, and computational tactics. Existing generative models propose to capture all stochasticity by a single latent variable and may suffer from entangled representations, or aim to uncover interaction structures of players but then do not focus on their generative ability. As a remedy, we propose a hierarchical latent variable model for predicting trajectories of multiple players. In the generative model, both, discrete role assignments and a latent interaction graph are sampled to allow for different models in subsequent node updates and message passing operations between nodes, where standard Gaussian latent variables are employed per agent and timestep. We cast our approach as a variational autoencoder that provides a disentangled latent space to capture variability in team sport movements and propose a neural architecture for its optimization. We empirically evaluate our approach on tracking data from basketball and soccer and observe that our contribution outperforms the state-of-art in all experiments.

MVideoRec: Micro Video Recommendations Through Modality Decomposition and Contrastive Learning

Personalized micro video recommendation aims to recommend the micro videos tailored to user preference based on the user’s interaction history with the micro videos, which has drawn increasing attention from both the academic and industrial communities. Existing solutions primarily concentrate on video-level interactions between users and micro videos to model their preferences, and cannot distinguish the finer-grained users’ interactions with various modalities. Ignoring modality-level interactions prevents the full understanding of the user’s true and subtle preferences on micro videos. To this end, in this paper, we propose a Contrastive Multimodal Interaction Graph Learning ( MVideoRec ) model to automatically and explicitly learn the modality-level interaction between users and micro videos for recommendations. Specifically, we designed a graph structure learning module with a sparsification strategy to infer modality-level interaction graph, which will be dynamically and iteratively updated based on the node representations obtained from the node representation learning module. Furthermore, to address the lack of ground truth labels, we propose to generate teacher view from video-level interaction graph and student view from modality-level interaction graph, as well as construct intra-modality and inter-modality contrastive pairwise instances to provide self-supervised signals. Extensive experiments on three real-world micro video datasets validate the effectiveness of MVideoRec.

Attention-Based Interpretable Multiscale Graph Neural Network for MOFs.

Metal-organic frameworks (MOFs) hold great potential in gas separation and storage. Graph neural networks (GNNs) have proven effective in exploring structure-property relationships and discovering new MOF structures. Unlike molecular graphs, crystal graphs must consider the periodicity and patterns. MOFs' specific features at different scales, such as covalent bonds, functional groups, and global structures, influenced by interatomic interactions, exert varying degrees of impact on gas adsorption or selectivity. Moreover, redundant interatomic interactions hinder training accuracy, leading to overfitting. This research introduces a construction method for multiscale crystal graphs, which considers specific features at different scales by decomposing the crystal graph into multiple subgraphs based on interatomic interactions within varying distance ranges. Additionally, it takes into account the global structure of the crystal by encoding the periodic patterns of the unit cells. We propose MSAIGNN, a multiscale atomic interaction graph neural network with self-attention-based graph pooling mechanism, which incorporates three-body bond angle information, accounts for structural features at different scales, and minimizes interference from redundant interactions. Compared with traditional methods, MSAIGNN demonstrates higher prediction accuracy in assessing single-component adsorption, gas separation, and structural features. Visualization of attention scores confirms effective learning of structural features at different scales, highlighting MSAIGNN's interpretability. Overall, MSAIGNN offers a novel, efficient, multilayered, and interpretable approach for property prediction of complex porous crystal structures like MOFs using deep learning.

LGS-KT: Integrating logical and grammatical skills for effective programming knowledge tracing.

Knowledge tracing (KT) estimates students' mastery of knowledge concepts or skills by analyzing their historical interactions. Although general KT methods have effectively assessed students' knowledge states, specific measurements of students' programming skills remain insufficient. Existing studies mainly rely on exercise outcomes and do not fully utilize behavioral data during the programming process. Therefore, we integrate a Logical and Grammar Skills Knowledge Tracing (LGS-KT) model to enhance programming education. This model integrates static analysis and dynamic monitoring (such as CPU and memory consumption) to evaluate code elements, providing a thorough assessment of code quality. By analyzing students' multiple iterations on the same programming problem, we constructed a reweighted logical skill evolution graph to assess the development of students' logical skills. Additionally, to enhance the interactions among representations with similar grammatical skills, we developed a grammatical skills interaction graph based on the similarity of knowledge concepts. This approach significantly improves the accuracy of inferring students' programming grammatical skill states. The LGS-KT model has demonstrated superior performance in predicting student outcomes. Our research highlights the potential application of a KT model that integrates logical and grammatical skills in programming exercises. To support reproducible research, we have published the data and code at https://github.com/xinjiesun-ustc/LGS-KT, encouraging further innovation in this field.

Zero-Shot Traffic Identification with Attribute and Graph-Based Representations for Edge Computing.

With the proliferation of mobile terminals and the rapid growth of network applications, fine-grained traffic identification has become increasingly challenging. Methods based on machine learning and deep learning have achieved remarkable results, but they heavily rely on the distribution of training data, which makes them ineffective in handling unseen samples. In this paper, we propose AG-ZSL, a zero-shot learning framework based on traffic behavior and attribute representations for general encrypted traffic classification. AG-ZSL primarily learns two mapping functions: one that captures traffic behavior embeddings from burst-based traffic interaction graphs, and the other that learns attribute embeddings from traffic attribute descriptions. Then, the framework minimizes the distance between these embeddings within the shared feature space. The gradient rejection algorithm and K-Nearest Neighbors are introduced to implement a two-stage method for general traffic classification. Experimental results on IoT datasets demonstrate that AG-ZSL achieves exceptional performance in classifying both known and unknown traffic, highlighting its potential for enhancing secure and efficient traffic management at the network edge.

Dual intent view contrastive learning for knowledge aware recommender systems

Knowledge-aware recommendation systems often face challenges owing to sparse supervision signals and redundant entity relations, which can diminish the advantages of utilizing knowledge graphs for enhancing recommendation performance. To tackle these challenges, we propose a novel recommendation model named Dual-Intent-View Contrastive Learning network (DIVCL), inspired by recent advancements in contrastive and intent learning. DIVCL employs a dual-view representation learning approach using Graph Neural Networks (GNNs), consisting of two distinct views: a local view based on the user-item interaction graph and a global view based on the user-item-entity knowledge graph. To further enhance learning, a set of intents are integrated into each user-item interaction as a separate class of nodes, fulfilling three crucial roles in the GNN learning process: (1) providing fine-grained representations of user-item interaction features, (2) acting as evaluators for filtering relevant relations in the knowledge graph, and (3) participating in contrastive learning to strengthen the model’s ability to handle sparse signals and redundant relations. Experimental results on three benchmark datasets demonstrate that DIVCL outperforms state-of-the-art models, showcasing its superior performance. The implementation is available at: https://github.com/yzxx667/DIVCL.

Educators’ intention to use tangible and graphical experimentation with Arduino and Micro:bit

Nowadays, the educational process is enriched with technological tools such as Arduino and Micro:bit. These tools offer both tangible and graphical interaction, however, widespread adoption by educators faces limitations. Many educators hesitate to utilize them, primarily due to lacking training. Therefore, this study examines educators’ behavioral intentions to use Arduino and Micro:bit to enhance teaching and learning. Sixty-one primary and secondary school educators participated without prior knowledge of electronic circuits or programming. The examination aimed to assess: (a) educators’ preferences between tangible and virtual experimentation, and (b) factors influencing educators’ behavioral intention to use Arduino and Micro:bit. The statistical analysis encompassed a range of methods, including factor analysis, and linear regression. The findings indicated a preference among educators for implementing Arduino circuits through simulation, while no preference differences were observed between simulation and a real board for the Micro:bit. Additionally, linear regressions revealed that Arduino and Micro:bit follow different paths leading to the behavioral intention to use. Specifically, with Arduino, the intention to use is primarily influenced by users’ perceived usefulness. Conversely, in the case of Micro:bit, the intention to use is mainly driven by users’ attitudes towards its use. Hence, enhancing educators’ perceived usefulness and ease of use of Arduino Uno and Micro:bit is essential for fostering their intention to integrate these tools into their teaching practices.

The Use of Modern Robust Regression Analysis with Graphics: An Example from Marketing

Routine least squares regression analyses may sometimes miss important aspects of data. To exemplify this point we analyse a set of 1171 observations from a questionnaire intended to illuminate the relationship between customer loyalty and perceptions of such factors as price and community outreach. Our analysis makes much use of graphics and data monitoring to provide a paradigmatic example of the use of modern robust statistical tools based on graphical interaction with data. We start with regression. We perform such an analysis and find significant regression on all factors. However, a variety of plots show that there are some unexplained features, which are not eliminated by response transformation. Accordingly, we turn to robust analyses, intended to give answers unaffected by the presence of data contamination. A robust analysis using a non-parametric model leads to the increased significance of transformations of the explanatory variables. These transformations provide improved insight into consumer behaviour. We provide suggestions for a structured approach to modern robust regression and give links to the software used for our data analyses.

SemSI-GAT: Semantic Similarity-based Interaction Graph Attention Network for Knowledge Graph Completion

SemSI-GAT: Semantic Similarity-based Interaction Graph Attention Network for Knowledge Graph Completion

Cross-Skeleton Interaction Graph Aggregation Network for Representation Learning of Mouse Social Behavior

Cross-Skeleton Interaction Graph Aggregation Network for Representation Learning of Mouse Social Behavior

Building a taxonomy for evidence-based medical eXtended Reality (MXR) applications: identifying best practices for design innovation and global collaboration

Aims: This article aims to create a taxonomy of evidence-based medical eXtended Reality (MXR) applications, including Virtual Reality (VR), Augmented Reality (AR), Mixed Reality (MR), and 360-degree photo/video technologies, to identify best practices for designing and evaluating user experiences and interfaces (UX/UI). The goal is to assist researchers, developers, and practitioners in comparing and extrapolating the best solutions for high-precision MXR tools in medical and wellness contexts. Methods: To develop the taxonomy, a review of medical and MXR publications was conducted, followed by three systematic mapping studies. Applications were categorized by end-users and purposes. The first mapping cross-referenced digital health technology classifications. The second validated the structure by incorporating over 350 evidence-based MXR apps, with input from twenty XR-HCI researchers. The third, ongoing mapping adds emerging apps, refining the taxonomy further. Results: The taxonomy is presented in a dynamic database and 3D interactive graph, allowing international researchers to visualize and discuss developed evidence-based medical and wellness XR applications. This formalizes prior efforts to distinguish validated MXR solutions from speculative ones. Conclusion: The taxonomy focuses solely on evidence-based applications, highlighting areas where VR, AR, and MR have been successfully implemented. It serves as a tool for stakeholders to analyze and understand best practices in MXR design, promoting the development of safe, effective, and user-friendly medical and wellness applications.

SocialJGCF: Social Recommendation with Jacobi Polynomial-Based Graph Collaborative Filtering

With the flourishing of social media platforms, data in social networks, especially user-generated content, are growing rapidly, which makes it hard for users to select relevant content from the overloaded data. Recommender systems are thus developed to filter user-relevant content for better user experiences and also the commercial needs of social platform providers. Graph neural networks have been widely applied in recommender systems for better recommendation based on past interactions between users and corresponding items due to the graph structure of social data. Users might also be influenced by their social connections, which is the focus of social recommendation. Most works on recommendation systems try to obtain better representations of user embeddings and item embeddings. Compared with recommendation systems only focusing on interaction graphs, social recommendation has an additional task of combining user embedding from the social graph and interaction graph. This paper proposes a new method called SocialJGCF to address these problems, which applies Jacobi-Polynomial-Based Graph Collaborative Filtering (JGCF) to the propagation of the interaction graph and social graph, and a graph fusion is used to combine the user embeddings from the interaction graph and social graph. Experiments are conducted on two real-world datasets, epinions and LastFM. The result shows that SocialJGCF has great potential in social recommendation, especially for cold-start problems.

Tally Tracking System

In today’s fast-paced world, effectively managing personal expenses is crucial for maintaining financial stability and achieving long-term goals. However, many existing systems lack a user-friendly interface to efficiently track and categorize expenses. Users often struggle to enter expense details manually and visualize their spending trends over time. These limitations can make it difficult to identify spending patterns and create effective financial plans. Without proper categorization and reporting features, users may fail to track their expenses accurately, which leads to poor financial decisions. To overcome these drawbacks, the new system features a modern, user-friendly website built using Python and Flask. This system allows users to easily enter their expense details, including the category of the expense, such as food, entertainment, transportation, or utilities. The website is designed to ensure that users can quickly input their daily expenses, making it more accessible and intuitive. With Flask as the backend framework, the system ensures efficient processing of user data and seamless integration of the front-The end interface provides a smooth experience for users who are not necessarily tech-savvy. One of the key features of the proposed system is its ability to visualize the entered data in various formats, allowing users to view their expenses on a day-by- day, month-by-month, or year-by-year basis. The system uses interactive graphs and charts to display data, making it easy for users to track their spending patterns over time. In addition, users can generate detailed reports based on their selected timeframe, which provides insights into their financial habits and helps facilitate better decision-making. This solution empowers users to take control of their finances by providing a clear, graphic representation of their expenses and an easy way to generate periodic reports, thereby enhancingoth their financial planning and awareness.

Knowledge interaction graph guided prompting for event causality identification

Event causality identification (ECI) aims to identify causality between event pairs in a text, and is commonly approached as a supervised classification task using pre-trained language models (PLMs). However, limitations in implicit causality identification and insufficient event-knowledge interaction pose significant challenges to ECI. To address these issues, we propose a novel Knowledge Interaction Graph guided Prompt Tuning (KIGP), which leverages prompt tuning and knowledge interaction to fully exploit the potential of PLMs for ECI by integrating external knowledge. Specifically, to accurately capture implicit causality, we design the guidance mechanism and construct event-knowledge interaction graphs that enable external knowledge to enhance event representations through deep interaction between events and knowledge. Experimental results on two benchmark datasets demonstrate that our model outperforms existing approaches significantly.Graphical abstract

Educational interactive graphics tool for teaching the Cross process

The program demonstrates to students in the Structural Analysis discipline of the Civil Engineering course how the Cross Process (Moment Distribution Method) works for continuous beams, visually showing the physical interpretation of the method associated with the calculations in the same way as they are done in calculation memory. In addition to the calculations, the program shows the structural model with the loads (uniformly distributed forces across each span), its deformation, and its bending moment diagram. The program, with open source code, was implemented in the Java language, based on the Object Oriented Programming paradigm – OOP.The program for calculating continuous beams using the Cross Process has four canvases. It is on these canvases that the structural models, their diagrams, and their results will be drawn. The user can interact using the mouse to model the continuous beam, create new internal supports, remove internal supports, modify the dimensions of the spans, or modify the load values. The student can track the results by following the incremental analysis of the method step by step. Furthermore, the student can interfere in the iterative solution process by forcing the bending moment balance of any internal node in any order. All these procedures help the student to understand the analysis process. Well-documented source code is also an essential component for learning the method.