21448 research outputs found
Sort by
A heterogeneous graph-based semi-supervised learning framework for access control decision-making
Get PDFFor modern information systems, robust access control mechanisms are vital in safeguarding data integrity and ensuring the entire system’s security. This paper proposes a novel semi-supervised learning framework that leverages heterogeneous graph neural network-based embedding to encapsulate both the intricate relationships within the organizational structure and interactions between users and resources. Unlike existing methods focusing solely on individual user and resource attributes, our approach embeds organizational and operational interrelationships into the hidden layer node embeddings. These embeddings are learned from a self-supervised link prediction task based on a constructed access control heterogeneous graph via a heterogeneous graph neural network. Subsequently, the learned node embeddings, along with the original node features, serve as inputs for a supervised access control decision-making task, facilitating the construction of a machine-learning access control model. Experimental results on the open-sourced Amazon access control dataset demonstrate that our proposed framework outperforms models using original or manually extracted graph-based features from previous works. The prepossessed data and codes are available on GitHub,facilitating reproducibility and further research endeavors
Hierarchical adaptive evolution framework for privacy-preserving data publishing
Get PDFThe growing need for data publication and the escalating concerns regarding data privacy have led to a surge in interest in Privacy-Preserving Data Publishing (PPDP) across research, industry, and government sectors. Despite its significance, PPDP remains a challenging NP-hard problem, particularly when dealing with complex datasets, often rendering traditional traversal search methods inefficient. Evolutionary Algorithms (EAs) have emerged as a promising approach in response to this challenge, but their effectiveness, efficiency, and robustness in PPDP applications still need to be improved. This paper presents a novel Hierarchical Adaptive Evolution Framework (HAEF) that aims to optimize t-closeness anonymization through attribute generalization and record suppression using Genetic Algorithm (GA) and Differential Evolution (DE). To balance GA and DE, the first hierarchy of HAEF employs a GA-prioritized adaptive strategy enhancing exploration search. This combination aims to strike a balance between exploration and exploitation. The second hierarchy employs a random-prioritized adaptive strategy to select distinct mutation strategies, thus leveraging the advantages of various mutation strategies. Performance bencmark tests demonstrate the effectiveness and efficiency of the proposed technique. In 16 test instances, HAEF significantly outperforms traditional depth-first traversal search and exceeds the performance of previous state-of-the-art EAs on most datasets. In terms of overall performance, under the three privacy constraints tested, HAEF outperforms the conventional DFS search by an average of 47.78%, the state-of-the-art GA-based ID-DGA method by an average of 37.38%, and the hybrid GA-DE method by an average of 8.35% in TLEF. Furthermore, ablation experiments confirm the effectiveness of the various strategies within the framework. These findings enhance the efficiency of the data publishing process, ensuring privacy and security and maximizing data availability
HoopTransformer: Advancing NBA Offensive Play Recognition with Self-Supervised Learning from Player Trajectories
No full textBackground and Objective: Understanding and recognizing basketball offensive set plays, which involve intricate interactions between players, have always been regarded as challenging tasks for untrained humans, not to mention machines. In this study, our objective is to propose an artificial intelligence model that can automatically recognize offensive plays using a novel self-supervised learning approach. Methods: The dataset was collected by SportVU from 632 games during the 2015–2016 season of the National Basketball Association (NBA), with a total of 90,524 possessions. A multi-agent motion prediction pretraining model was built on the basis of axial-attention transformer and trained with different masking strategies: motion prediction (MP), motion reconstruction (MR), and MP + MR joint strategy. A downstream play-level classification task and similarity search were used to evaluate the models’ performance. Results: The results showed that the MP + MR joint masking strategy maximized the ability of the model compared with individual masking strategies. For the classification task, the joint strategy achieved a top-1 accuracy of 81.5% and top-3 accuracy of 97.5%. In the similarity search evaluation, the joint strategy attained a top-5 accuracy of 76% and top-10 accuracy of 59%. Additionally, with the same MP + MR joint masking strategy, our HoopTransformer model outperformed the two baseline models in the classification task and similarity search. Conclusion: This study presents a self-supervised learning model and demonstrates the effectiveness and potential of the model in accurately comprehending and capturing player movements and complex interactions during offensive plays
Disruption and Improvisation: Experiences of Loneliness for People With Chronic Illness
Get PDFChronic illness can disrupt many aspects of life, including identity, social relationships, and anticipated life trajectories. Despite significant scholarship on chronic illness, we know less about the ways in which chronic illness impacts feelings of loneliness and how people with chronic illness deal with loneliness. Drawing on concepts of biographical disruption and liminality and data from walking and photo-elicitation interviews with 14 people, we aimed to explore how people with chronic illness experience loneliness in their everyday lives. Tracing how past and present illness experiences are implicated in the lived experience of loneliness and the strategies people use to manage loneliness, our findings illustrated that being caught in a liminal state where participants struggled to maintain and adapt to a new normality in life with chronic illness was a central thread woven throughout their experience of loneliness. Although participants drew on their personal agency and adopted strategies to account for, manage, and limit disruptions from chronic illness and loneliness, they found that their strategies were not completely effective or satisfactory. Chronic illness and loneliness continue to be largely considered as an individual’s problem, limiting opportunities for people with chronic illness who experience loneliness to seek support and social connection. Our research highlighted that chronic illness and loneliness need to be acknowledged as both a personal and collective problem, with multi-level responses that involve individuals, communities, and society
Something for the young and old: A natural experiment to evaluate the impact of park improvements
Get PDFGiven the significant time and financial investment required to improve parks, evaluations of the effectiveness of park improvements are crucial to inform future investment and design to benefit people of all ages. This natural experiment study examined the impact of park improvements on park visitation and park-based physical activity (PA) in two suburban parks (Park A and Park B) compared to a control park with no improvements. Park A underwent substantial improvements with wide range of facilities, including an all-abilities large adventure-style playground, outdoor fitness area designed for older adults, walking paths and other amenities. Park B received relatively minor improvements that included a playground for young children, outdoor fitness equipment for older adults, and a picnic area. Direct observations were conducted using the System for Observing Play and Recreation in Communities at three timepoints; before (T1–2020) and after (T2–2021, and T3–2022) the improvements. At Park A, there was a significant increase in the total number of park visitors at both timepoints, and those engaged in moderate-to-vigorous physical activity (MVPA) from T1 to T3, relative to the control park. There were also significant increases in active park visits among children, adults, and older adults. At Park B, there were no significant changes in the total number of park visitors or those engaged in MVPA at either timepoint relative to the control park. These findings suggest the extent of improvements and the diversity of facilities included can influence the success of the intervention. The study highlights that including challenging and diverse play equipment suitable for various age groups and abilities, as well as other recreational features such as walking paths and outdoor fitness equipment can increase park visitation and physical activity across different age groups. The findings can inform future park management and planning decisions
The impacts of 2D graphene oxide on selective and substrate layer of TFC membrane: A critical review on fabrication techniques and performance in water treatment
No full text
