Search Results (11)

The graded management of structured sensitive data has become a key challenge in data security governance, particularly amid digital transformation in sectors such as government, finance, and healthcare. The existing methods suffer from limited generalization, low efficiency, and reliance on static rules. This paper proposes PPM-SACG, a privacy preference matrix-based model for sensitive attribute classification and grading. The model adopts a three-stage architecture: (1) composite sensitivity metrics are derived by integrating information entropy and group privacy preferences; (2) domain knowledge-guided clustering and association rule mining improve classification accuracy; and (3) mutual information-based hierarchical clustering enables dynamic grouping and grading, incorporating high-sensitivity isolation. Experiments using real-world vehicle management data (50 attributes, 3000 records) and user privacy surveys verify the method’s effectiveness. Compared with existing approaches, PPM-SACG doubles computational efficiency and supports scenario-aware deployment, offering enhanced compliance and practicality for structured data governance. Full article

Due to access to the source data during the transfer phase, conventional domain adaptation works have recently raised safety and privacy concerns. More research attention thus shifts to a more practical setting known as source-data-free domain adaptation (SFDA). The new challenge is how to obtain reliable semantic supervision in the absence of source domain training data and the labels on the target domain. To that end, in this work, we introduce a novel Gradual Geometry-Guided Knowledge Distillation (G2KD) approach for SFDA. Specifically, to address the lack of supervision, we used local geometry of data to construct a more credible probability distribution over the potential categories, termed geometry-guided knowledge. Then, knowledge distillation was adopted to integrate this extra information for boosting the adaptation. More specifically, first, we constructed a neighborhood geometry for any target data using a similarity comparison on the whole target dataset. Second, based on pre-obtained semantic estimation by clustering, we mined soft semantic representations expressing the geometry-guided knowledge by semantic fusion. Third, using the soften labels, we performed knowledge distillation regulated by the new objective. Considering the unsupervised setting of SFDA, in addition to the distillation loss and student loss, we introduced a mixed entropy regulator that minimized the entropy of individual data as well as maximized the mutual entropy with augmentation data to utilize neighbor relation. Our contribution is that, through local geometry discovery with semantic representation and self-knowledge distillation, the semantic information hidden in the local structures is transformed to effective semantic self-supervision. Also, our knowledge distillation works in a gradual way that is helpful to capture the dynamic variations in the local geometry, mitigating the previous guidance degradation and deviation at the same time. Extensive experiments on five challenging benchmarks confirmed the state-of-the-art performance of our method. Full article

Nickel (Ni) resources are critical for the development of modern industry. This study investigates the knowledge structure and frontier evolution of Ni deposit research by constructing a domain-specific knowledge graph using bibliometric analysis and semantic extraction from 7090 publications (1966–2024) sourced from the Web of Science Core Collection. The results show that Ni research has three distinct phases: slow growth (1966–1990), early growth (1991–2010), and rapid expansion (2011–present). The collaborative network of institutions in which articles are published forms three regional clusters centered on China, Russia, and Australia. Keyword burst analysis identifies emerging frontiers, including sulfur isotopes, pyrite geochemistry, and LA-ICP-MS applications. Temporal keyword analysis identifies “platinum-group minerals”, “ore-forming fluids”, “isotopic analysis”, and “Eastern Tianshan” interactions as five pivotal research frontiers in nickel deposit studies. The knowledge graph framework demonstrates significant potential in mitigating data fragmentation, enhancing interdisciplinary data accessibility, and guiding future exploration strategies. This study shows the important role of knowledge maps in optimizing the study of nickel deposits. Full article

As construction projects become increasingly complex, modular integrated construction (MiC) has emerged as a pivotal solution, driving integrated development in complex projects. However, the reliance on prefabricated modules underscores the crucial role of supply chain management (SCM) in MiC, necessitating strategic planning and operational control. This study aimed to use bibliometric analysis to map the SCM knowledge domain within MiC. Through the use of keywords related to “supply chain” and “MiC”, 196 relevant papers were extracted from the Web of Science database. These papers were subjected to co-citation analysis, keyword co-occurrence analysis, and time span analysis to elucidate the historical evolution, multidisciplinary domains, and future directions in planning and control within SCM-MiC. The research identified two milestones in SCM-MiC’s historical trajectory, enhancing our understanding of its foundations. Moreover, 11 clusters were identified, illustrating the multidisciplinary nature of SCM-MiC. Dividing the literature into seven stages of the supply chain, the research outlined four research directions aligned with project complexity and technological development, highlighting current hotspots and gaps of the strategic planning and control. These directions bridge the construction management and information technology domains, guiding future SCM-MiC research within complex project management. Full article

One of the main limitations of traditional neural-network-based classifiers is the assumption that all query data are well represented within their training set. Unfortunately, in real-life scenarios, this is often not the case, and unknown class data may appear during testing, which drastically weakens the robustness of the algorithms. For this type of problem, open-set recognition (OSR) proposes a new approach where it is assumed that the world knowledge of algorithms is incomplete, so they must be prepared to detect and reject objects of unknown classes. However, the goal of this approach does not include the detection of new classes hidden within the rejected instances, which would be beneficial to increase the model’s knowledge and classification capability, even after training. This paper proposes an OSR strategy with an extension for new class discovery aimed at vehicle make and model recognition. We use a neuroevolution technique and the contrastive loss function to design a domain-specific CNN that generates a consistent distribution of feature vectors belonging to the same class within the embedded space in terms of cosine similarity, maintaining this behavior in unknown classes, which serves as the main guide for a probabilistic model and a clustering algorithm to simultaneously detect objects of new classes and discover their classes. The results show that the presented strategy works effectively to address the VMMR problem as an OSR problem and furthermore is able to simultaneously recognize the new classes hidden within the rejected objects. OSR is focused on demonstrating its effectiveness with benchmark databases that are not domain-specific. VMMR is focused on improving its classification accuracy; however, since it is a real-world recognition problem, it should have strategies to deal with unknown data, which has not been extensively addressed and, to the best of our knowledge, has never been considered from an OSR perspective, so this work also contributes as a benchmark for future domain-specific OSR. Full article

In the current challenging and competitive dynamic business world today, automotive companies have been rapidly developing and promoting autonomous vehicles (AVs), which aim to reduce crashes, energy consumption, pollution, and congestion and increase transport accessibility. To ensure the successful adoption of AVs, an increasing number of studies have been conducted to understand public acceptance. This paper used the bibliometric technique to understand the distribution, emerging trend, and the research cluster in the context of AV technology acceptance through knowledge mapping. The Web of Science database was used to retrieve 401 scientific articles from 2000 to June 2022. The findings reported that the previous studies mainly focused on the research clusters related to the domains of attitude, trust, technology, impact, and models. Finally, this study added to the existing body of literature by providing the current knowledge landscape to guide the future research. Full article

To solve the problem of inadequate feature extraction by the model due to factors such as occlusion and illumination in person re-identification tasks, this paper proposed a model with a joint cross-consistency learning and multi-feature fusion person re-identification. The attention mechanism and the mixed pooling module were first embedded in the residual network so that the model adaptively focuses on the more valid information in the person images. Secondly, the dataset was randomly divided into two categories according to the camera perspective, and a feature classifier was trained for the two types of datasets respectively. Then, two classifiers with specific knowledge were used to guide the model to extract features unrelated to the camera perspective for the two types of datasets so that the obtained image features were endowed with domain invariance by the model, and the differences in the perspective, attitude, background, and other related information of different images were alleviated. Then, the multi-level features were fused through the feature pyramid to concern the more critical information of the image. Finally, a combination of Cosine Softmax loss, triplet loss, and cluster center loss was proposed to train the model to address the differences of multiple losses in the optimization space. The first accuracy of the proposed model reached 95.9% and 89.7% on the datasets Market-1501 and DukeMTMC-reID, respectively. The results indicated that the proposed model has good feature extraction capability. Full article

Objectives: This study aimed to visualize the evidence in the global research on health education to better improve the nation’s health literacy and to guide future research. Method: We searched the Web of Science (Core Collection) electronic databases. The search strategies: topic: (“Health Education” OR “Education, Health” OR “Community Health Education” OR “Education, Community Health” OR “Health Education, Community”) AND document: (Article) AND language:(English). Articles of evidence from January 2011 to December 2021 with those words in the title or abstract or keywords will be included in this review. We used the Citespace 5.6.R5 (64-bit) to investigate and determine the thematic patterns, and emerging trends of the knowledge domain, and presented a narrative account of the findings. Result: We analyzed 10,273 eligible articles. It showed that BMC Public Health displays the most prolific journals. Author MARCO PAHOR is highlighted in health education. The University of Sydney has published the most studies about health education. The USA plays an important role in these studies. Specifically, the visualization shows several hotspots: disease prevalence surveys and a specific population of knowledge, attitude and practice surveys, health intervention, chronic and non-communicable management, youth-health action, sexual and reproductive health, and physical activity promotion. Furthermore, document co-citation analysis indicated that there are 10 main clusters, which means the research front in health education. Meanwhile, by the citation detected, COVID-19, has achieved universal health coverage in related studies, however, public health education and the health workforce might be more popular in the coming years. Conclusion: Health education is an effective measure to shift the concept of public health and improve healthy living standards. The present study facilitates an extensive understanding of the basic knowledge and research frontiers that are pivotal for the developmental process of health education and allows scholars to visualize the identification modes and tendencies. Full article

Human activity recognition plays a prominent role in numerous applications like smart homes, elderly healthcare and ambient intelligence. The complexity of human behavior leads to the difficulty of developing an accurate activity recognizer, especially in situations where different activities have similar sensor readings. Accordingly, how to measure the relationships among activities and construct an activity recognizer for better distinguishing the confusing activities remains critical. To this end, we in this study propose a clustering guided hierarchical framework to discriminate on-going human activities. Specifically, we first introduce a clustering-based activity confusion index and exploit it to automatically and quantitatively measure the confusion between activities in a data-driven way instead of relying on the prior domain knowledge. Afterwards, we design a hierarchical activity recognition framework under the guidance of the confusion relationships to reduce the recognition errors between similar activities. Finally, the simulations on the benchmark datasets are evaluated and results show the superiority of the proposed model over its competitors. In addition, we experimentally evaluate the key components of the framework comprehensively, which indicates its flexibility and stability. Full article

The understanding of water quality and its underlying processes is important for the protection of aquatic environments. With the rare opportunity of access to a domain expert, an explainable AI (XAI) framework is proposed that is applicable to multivariate time series. The XAI provides explanations that are interpretable by domain experts. In three steps, it combines a data-driven choice of a distance measure with supervised decision trees guided by projection-based clustering. The multivariate time series consists of water quality measurements, including nitrate, electrical conductivity, and twelve other environmental parameters. The relationships between water quality and the environmental parameters are investigated by identifying similar days within a cluster and dissimilar days between clusters. The framework, called DDS-XAI, does not depend on prior knowledge about data structure, and its explanations are tendentially contrastive. The relationships in the data can be visualized by a topographic map representing high-dimensional structures. Two state of the art XAIs called eUD3.5 and iterative mistake minimization (IMM) were unable to provide meaningful and relevant explanations from the three multivariate time series data. The DDS-XAI framework can be swiftly applied to new data. Open-source code in R for all steps of the XAI framework is provided and the steps are structured application-oriented. Full article

Graphs emerge naturally in many domains, such as social science, neuroscience, transportation engineering, and more. In many cases, such graphs have millions or billions of nodes and edges, and their sizes increase daily at a fast pace. How can researchers from various domains explore large graphs interactively and efficiently to find out what is ‘important’? How can multiple researchers explore a new graph dataset collectively and “help” each other with their findings? In this article, we present Perseus-Hub, a large-scale graph mining tool that computes a set of graph properties in a distributed manner, performs ensemble, multi-view anomaly detection to highlight regions that are worth investigating, and provides users with uncluttered visualization and easy interaction with complex graph statistics. Perseus-Hub uses a Spark cluster to calculate various statistics of large-scale graphs efficiently, and aggregates the results in a summary on the master node to support interactive user exploration. In Perseus-Hub, the visualized distributions of graph statistics provide preliminary analysis to understand a graph. To perform a deeper analysis, users with little prior knowledge can leverage patterns (e.g., spikes in the power-law degree distribution) marked by other users or experts. Moreover, Perseus-Hub guides users to regions of interest by highlighting anomalous nodes and helps users establish a more comprehensive understanding about the graph at hand. We demonstrate our system through the case study on real, large-scale networks. Full article