Search Results (144)

This comprehensive review maps the fast-evolving landscape in which artificial intelligence (AI) and deep-learning (DL) techniques converge with the Internet of Things (IoT) to manage energy, comfort, and sustainability across smart environments. A PRISMA-guided search of four databases retrieved 1358 records; after applying inclusion criteria, 143 peer-reviewed studies published between January 2019 and April 2025 were analyzed. This review shows that AI-driven controllers—especially deep-reinforcement-learning agents—deliver median energy savings of 18–35% for HVAC and other major loads, consistently outperforming rule-based and model-predictive baselines. The evidence further reveals a rapid diversification of methods: graph-neural-network models now capture spatial interdependencies in dense sensor grids, federated-learning pilots address data-privacy constraints, and early integrations of large language models hint at natural-language analytics and control interfaces for heterogeneous IoT devices. Yet large-scale deployment remains hindered by fragmented and proprietary datasets, unresolved privacy and cybersecurity risks associated with continuous IoT telemetry, the growing carbon and compute footprints of ever-larger models, and poor interoperability among legacy equipment and modern edge nodes. The authors of researches therefore converges on several priorities: open, high-fidelity benchmarks that marry multivariate IoT sensor data with standardized metadata and occupant feedback; energy-aware, edge-optimized architectures that lower latency and power draw; privacy-centric learning frameworks that satisfy tightening regulations; hybrid physics-informed and explainable models that shorten commissioning time; and digital-twin platforms enriched by language-model reasoning to translate raw telemetry into actionable insights for facility managers and end users. Addressing these gaps will be pivotal to transforming isolated pilots into ubiquitous, trustworthy, and human-centered IoT ecosystems capable of delivering measurable gains in efficiency, resilience, and occupant wellbeing at scale. Full article

Phishing attacks pose significant risks to security, drawing considerable attention from both security professionals and customers. Despite extensive research, the current phishing website detection mechanisms often fail to efficiently diagnose unknown attacks due to their poor performances in the feature selection stage. Many techniques suffer from overfitting when working with huge datasets. To address this issue, we propose a feature selection strategy based on a convolutional graph network, which utilizes a dataset containing both labels and features, along with hyperparameters for a Support Vector Machine (SVM) and a graph neural network (GNN). Our technique consists of three main stages: (1) preprocessing the data by dividing them into testing and training sets, (2) constructing a graph from pairwise feature distances using the Manhattan distance and adding self-loops to nodes, and (3) implementing a GraphSAGE model with node embeddings and training the GNN by updating the node embeddings through message passing from neighbors, calculating the hinge loss, applying the softmax function, and updating weights via backpropagation. Additionally, we compute the neighborhood random walk (NRW) distance using a random walk with restart to create an adjacency matrix that captures the node relationships. The node features are ranked based on gradient significance to select the top k features, and the SVM is trained using the selected features, with the hyperparameters tuned through cross-validation. We evaluated our model on a test set, calculating the performance metrics and validating the effectiveness of the PhishGNN dataset. Our model achieved a precision of 90.78%, an F1-score of 93.79%, a recall of 97%, and an accuracy of 93.53%, outperforming the existing techniques. Full article

This study investigates the mechanisms underlying the diffusion of risk information about genetically modified organisms (GMOs) on the Chinese social media platform Weibo. Drawing upon social contagion theory, we examine how endogenous and exogenous mechanisms shape users’ information-sharing behaviors. An analysis of 388,722 reposts from 2444 original GMO risk-related texts enabled the construction of a comprehensive sharing network, with computational text-mining techniques employed to detect users’ attitudes toward GMOs. To bridge the gap between descriptive and inferential network analysis, we employ a Shannon entropy-based approach to quantify the uncertainty and concentration of attitudinal differences and similarities among sharing and non-sharing dyads, providing an information-theoretic foundation for understanding positional and differential homophily. The entropy-based analysis reveals that information-sharing ties are characterized by lower entropy in attitude differences, indicating greater attitudinal alignment among sharing users, especially among GMO opponents. Building on these findings, the Exponential Random Graph Model (ERGM) further demonstrates that both endogenous network mechanisms (reciprocity, preferential attachment, and triadic closure) and positional homophily influence GMO risk information sharing and dissemination. A key finding is the presence of a differential homophily effect, where GMO opponents exhibit stronger homophilic tendencies than non-opponents. Despite the prevalence of homophily, this paper uncovers substantial cross-attitude interactions, challenging simplistic notions of echo chambers in GMO risk communication. By integrating entropy and ERGM analyses, this study advances a more nuanced, information-theoretic understanding of how digital platforms mediate public perceptions and debates surrounding controversial socio-scientific issues, offering valuable implications for developing effective risk communication strategies in increasingly polarized online spaces. Full article

Surface water systems face unprecedented stress due to climate variability, urbanization, land-use change, and growing water demand—prompting a shift from traditional hydrological modeling to intelligent, adaptive systems. This review critically explores the integration of Artificial Intelligence (AI) in surface flow management, encompassing applications in streamflow forecasting, sediment transport, flood prediction, water quality monitoring, and infrastructure operations such as dam and irrigation control. Drawing from over two decades of interdisciplinary literature, this study synthesizes recent advances in machine learning (ML), deep learning (DL), the Internet of Things (IoT), remote sensing, and hybrid AI–physics models. Unlike earlier reviews focusing on single aspects, this paper presents a systems-level perspective that links AI technologies to their operational, ethical, and governance dimensions. It highlights key AI techniques—including Long Short-Term Memory (LSTM), Convolutional Neural Networks (CNNs), Graph Neural Networks (GNNs), Transformer models, and Reinforcement Learning—and discusses their strengths, limitations, and implementation challenges, particularly in data-scarce and climate-uncertain regions. Novel insights are provided on Explainable AI (XAI), algorithmic bias, cybersecurity risks, and institutional readiness, positioning this paper as a roadmap for equitable and resilient AI adoption. By combining methodological analysis, conceptual frameworks, and future directions, this review offers a comprehensive guide for researchers, engineers, and policy-makers navigating the next generation of intelligent surface flow management. Full article

The significance of searching for edge crossings in graph theory lies inter alia in enhancing the clarity and readability of graph representations, which is essential for various applications such as network visualization, circuit design, and data representation. This paper focuses on exploring the crossing number of the join product $G^{*}+D_n$, where $G^{*}$ is a graph isomorphic to the path on four vertices $P_4$ with an additional two vertices adjacent to two inner vertices of $P_4$, and $D_n$ is a discrete graph composed of n isolated vertices. The proof is based on exact crossing-number values for join products involving particular subgraphs $H_k$ of $G^{*}$ with discrete graphs $D_n$ combined with the symmetrical properties of graphs. This approach could also be adapted to determine the unknown crossing numbers of two other 6-vertices graphs obtained by adding one or two additional edges to the graph $G^{*}$. Full article

Knee osteoarthritis (KOA) is a highly prevalent muscoloskeletal joint disorder affecting a significant portion of the population worldwide. Accurate predictions of KOA progression can assist clinicians in drawing preventive strategies for patients. In this paper, we present an integrated approach based on hypergraph convolutional networks (HGCNs) for longitudinal predictions of KOA grades and progressions from MRI images. We propose two novel models, namely, the C_Shape.Net and the predictor network. The C_Shape.Net operates on a hypergraph of volumetric nodes, especially designed to represent the surface and volumetric features of the cartilage. It encompasses deep HGCN convolutions, graph pooling, and readout operations in a hierarchy of layers, providing, at the output, expressive 3D shape descriptors of the cartilage volume. The predictor is a spatio-temporal HGCN network (ST_HGCN), following the sequence-to-sequence learning scheme. Concretely, it transforms sequences of knee representations at the historical stage into sequences of KOA predictions at the prediction stage. The predictor includes spatial HGCN convolutions, attention-based temporal fusion of feature embeddings at multiple layers, and a transformer module that generates longitudinal predictions at follow-up times. We present comprehensive experiments on the Osteoarthritis Initiative (OAI) cohort to evaluate the performance of our methodology for various tasks, including node classification, longitudinal KL grading, and progression. The basic finding of the experiments is that the larger the depth of the historical stage, the higher the accuracy of the obtained predictions in all tasks. For the maximum historic depth of four years, our method yielded an average balanced accuracy (BA) of 85.94% in KOA grading, and accuracies of 91.89% (+1), 88.11% (+2), 84.35% (+3), and 79.41% (+4) for the four consecutive follow-up visits. Under the same setting, we also achieved an average value of Area Under Curve (AUC) of 0.94 for the prediction of progression incidence, and follow-up AUC values of 0.81 (+1), 0.77 (+2), 0.73 (+3), and 0.68 (+4), respectively. Full article

Activity-on-arc (AoA) and activity-on-node (AoN) project network representations have been used in construction scheduling for many decades. But due to the primary information that they emphasize—the activities themselves in the AoA graphs, and the precedence relationship structure in the AoN graphs—they also have significant limitations. In this paper, we develop a hybrid representation approach named Activity-on-Arcs-and-Nodes (AoAaN). This novel network representation transforms all project activities into arcs (as in the AoA representation) but retains all precedence relationships between activities (as in AoN). To develop this alternative network representation, first, we establish its theoretical drawing principles, which mostly involve how to deal with different precedence relationship types (FS, SS, SF, FF) in basic networks. Then, we proceed with the calculation and analysis of more realistic project examples with a larger number of activities. Advantages of the new AoAaN is that it allows a simpler and more fine-grained determination of the critical path, while facilitating computer calculation via a Dependency Structure Matrix (DSM) that purely contains numerical information. Additionally, the proposed AoAaN allows handling coupled (interdependent) activities, a type of relationship that had previously hampered analysis of networks. Due to its flexible modeling capabilities and calculation simplicity, we suggest the AoAaN representation be added to project management courses as well as be used by project schedulers as a more capable alternative to the traditional AoA and AoN representations. Full article

Hierarchy analysis of the knowledge graphs aims to discover the latent structure inherent in knowledge base data. Drawing inspiration from topic modeling, which identifies latent themes and content patterns in text corpora, our research seeks to adapt these analytical frameworks to the hierarchical exploration of knowledge graphs. Specifically, we adopt a non-parametric probabilistic model, the nested hierarchical Dirichlet process, to the field of knowledge graphs. This model discovers latent subject-specific distributions along paths within the tree. Consequently, the global tree can be viewed as a collection of local subtrees for each subject, allowing us to represent subtrees for each subject and reveal cross-thematic topics. We assess the efficacy of this model in analyzing the topics and word distributions that form the hierarchical structure of complex knowledge graphs. We quantitatively evaluate our model using four common datasets: Freebase, Wikidata, DBpedia, and WebRED, demonstrating that it outperforms the latest neural hierarchical clustering techniques such as TraCo, SawETM, and HyperMiner. Additionally, we provide a qualitative assessment of the induced subtree for a single subject. Full article

Graphs are an excellent tool with applications in various branches of engineering. Graph layouts have emerged as a cornerstone in the visual representation and analysis of complex systems. They are indispensable in reducing complexity, optimizing designs, improving communication, and enhancing problem-solving capabilities. They transform abstract concepts and data into visual formats that are easier to interpret, analyze, and apply in real-world engineering challenges. Therefore, many graph layouts are designed for various purposes. It is not easy to choose the most appropriate one. There are a number of surveys on this subject, but they are descriptive ones. In this paper, we focus on the two most versatile—and therefore most widely used—layouts, namely Fruchterman–Reingold and ForceAtlas2, and show their possibilities in a visual way. We compare how the drawings appear while using various settings of the available options. This helps to choose an appropriate set of settings in practice. Full article

The teaching of environmental education must change to promote critical, sustainable, and reflective engagement with environmental problems. This study introduces a social-science question for primary education focused on pharmaceuticals in surface water. The aims of the paper are to evaluate the level of students’ performance in arguing their answers in relation to the reference answer; their use and interpretation of provided materials from which they draw the evidence to justify their arguments; and the type of solutions they propose in the framework of sustainability. This is carried out by analyzing the content of their written reports and the discourse during their group discussions. Statistical tests are also used to compare their individual and group performance. The results show that students perform at an intermediate level. They use text and video effectively but struggle with graphs and maps. Their proposed solutions are contextually appropriate and consider multiple perspectives. Notably, their performance is similar whether working individually or in groups. All in all, this pedagogical intervention in the framework of scientific practices and transformative environmental education supports the development of scientific thinking and sheds light on how students process information when addressing socio-environmental issues. Full article

IPv6 over Low-Power Wireless Personal Area Networks (6LoWPAN) are specifically designed for applications that require lower data rates and reduced power consumption in wireless internet connectivity. In the context of 6LoWPAN, Internet of Things (IoT) devices with limited resources can now seamlessly connect to the network using IPv6. This study focuses on examining the performance and power consumption of routing protocols in the context of 6LoWPAN, drawing insights from prior research and utilizing simulation techniques. The simulation involves the application of routing protocols, namely Routing Protocol for Low-power and Lossy (RPL) Networks, Ad hoc On-demand Distance Vector (AODV), Lightweight On-demand Ad hoc Distance-vector Next Generation (LOADng), implemented through the Cooja simulator. The simulation also runs in different network topologies to gain an insight into the performance of the protocols in the specific topology including random, linear, and eclipse topology. The raw data gathered from the tools including Powertrace and Collect-View were then analyzed with Python code to transfer into useful information and visualize the graph. The results demonstrate that the power consumption, specifically CPU power, Listen Power, and Total Consumption Power, will increase with the incremental of motes. The result also shows that RPL is the most power-efficient protocol among the scenarios compared to LOADng and AODV. The result is helpful because it brings insights into the performance, specifically power consumption in the 6LoWPAN network. This result is valuable to further implement these protocols in the testbed as well as provide an idea of the algorithmic enhancements. Full article

With the development of algorithms for autonomous decision-making in the field of structural engineering, the design of precast concrete segment (PCS) box girder bridges faces new challenges. This paper proposes using a multi-objective optimization method based on genetic algorithms for the rapid design of PCS box girder bridges with small and medium spans. By considering 20 design parameters such as the physical dimensions of the box girder cross-section, material properties, and prestressing parameters, the paper formulates and quantifies three objective functions: cost, safety, and structural performance. The multi-objective optimization was conducted using four optimization algorithms (NSGA-II, NSGA-III, GDE3, and PSO). An optimization evaluation index ($\phi \left[F\right(x\left)\right]$) was established and weights were assigned to different optimization objectives. A specific design case based on the general diagram of a 3 × 25 m-long continuous PCS box girder bridge was carried out. The results indicate that genetic algorithms performed exceptionally well on this problem, with the NSGA-III algorithm achieving the best $\phi \left[F\right(x\left)\right]$ value of 0.2789 among all algorithms. A performance analysis was conducted on various optimization models using box plots and sensitivity studies. Scatter plots and surface plots of the Pareto front of the optimized solutions were generated, and corresponding cross-sectional design drawings were created based on the two proposed solutions. Compared with the general graph, the design cases provided by the NSGA-III algorithm model have a change rate of 8.03%, −0.29%, and 75.49% in the three optimization objectives, respectively, indicating a significant improvement effect. The research content of this paper provides a reasonable direction for future studies on intelligent bridge design methodologies. Full article

Fabrication drawings are essential for design evaluation, lean manufacturing, and quality detection of precast concrete (PC) components. Due to the complicated shape of PC components, the fabrication drawing needs to be customized to determine manufacturing dimensions and relevant assembly connections. However, the traditional manual drawing method is time-consuming, labor-intensive, and error-prone. This paper presents a BIM-based framework to automatically generate the readable drawing of PC components using building information modeling (BIM) and multi-agent reinforcement learning (MARL). Firstly, an automated generation method is developed to transform BIM model to view block. Secondly, a graph-based representation method is used to create the relationship between blocks, and a reward mechanism is established according to the drawing readability criterion. Subsequently, the block layout is modeled as a layout optimization problem, and the internal spacing and position of functional category blocks are regarded as agents. Finally, the agents collaborate and interact with the environment to find the optimal layout with the guidance of a reward mechanism. Two different algorithms are utilized to validate the efficiency of the proposed method (MADQN). The proposed framework is applied to PC stairs and a double-sided shear wall to demonstrate its practicability. Full article

To achieve optimal controllability in a dual steering tractor (a four-wheel, iso-diametric tractor equipped with a dual-hydraulic steering system), this study proposes a coordinated approach that combines experimental testing (using a special agricultural tractor) with numerical analysis of the entire vehicle, developed in Bond Graph-3D. For certain crops, a dual steering vehicle is used to meet the needs of professionals who require easy maneuverability in narrow spaces and/or reduced steering time. This study aims to explore the reasons behind the need for dual steering tractors, highlighting the advantages and disadvantages of these two different configurations and ultimately focusing on the combined benefits of both. Based on an extensive review of the literature and drawing from previous studies, this paper analyzes aspects such as the variation in noise levels (or comfort level) experienced at the steering wheel when switching from Ackermann steering to a dual steering system. After outlining the theoretical methodology used to describe the model, both experimental and numerical analyses of a vineyard tractor in operation are presented. The goal of this work is to provide guidance on design methods and, through the Bond Graph-3D model, suggest the best control algorithms to minimize steering noise and enhance driving comfort. This research aims to pave the way for future control strategies in electrohydraulic steering systems. Full article

Background: Repetitive intramuscular injections of botulinum neurotoxin (BoNT) have become the treatment of choice for a variety of disease entities. But with the onset of BoNT therapy, the natural course of a disease is obscured. Nevertheless, the present study tries to analyze patients’ “suspected” course of disease severity under the assumption that no BoNT therapy had been performed and compares that with the “experienced” improvement during BoNT treatment. Methods: For this cross-sectional study, all 112 BoNT long-term treated patients in a botulinum toxin out-patient department were recruited who did not interrupt their BoNT/A therapy for more than two injection cycles during the last ten years. Patients had to assess the remaining severity of their disease as a percentage of the severity at onset of BoNT therapy and to draw three different graphs: (i) the CoDB-graph showing the course of severity of patient’s disease from onset of symptoms to onset of BoNT/A therapy, (ii) the CoDA-graph illustrating the course of severity from onset of BoNT/A therapy until recruitment, and (iii) the CoDS-graph visualizing the suspected development of disease severity from onset of BoNT/A therapy until recruitment under the assumption that no BoNT/A therapy had been performed. Three different types of graphs were distinguished: the R-type indicated a rapid manifestation or improvement, the C-type a continuous worsening or improvement, and the D-type a delayed manifestation or response to BoNT therapy. Four patient subgroups (cervical dystonia, other cranial dystonia, hemifacial spasm, and the migraine subgroup) comprised 91 patients who produced a complete set of graphs which were further analyzed. The “experienced” improvement and “suspected” worsening of disease severity since the onset of BoNT/A therapy were compared and correlated with demographical and treatment related data. Results: Improvement was significant (p < 0.05) and varied between 45 and 70% in all four patient subgroups, the “suspected” worsening was also significantly (p < 0.05) larger than 0, except in the migraine patients and varied between 10 and 70%. The “total benefit” (sum of improvement and prevented “suspected” worsening) was the highest in the other cranial dystonia group and the lowest in the migraine subgroup. The distributions of R-,C-,D-type graphs across CoDB-, CoDS-, and CoDB-graphs and across the four patient subgroups were significantly different. Conclusions: (i) Most BoNT long-term treated patients have the opinion that their disease would have further progressed and worsened if no BoNT/A therapy had been performed, (ii) The type of response to BoNT/A is different across different subgroups of BoNT/A long-term treated patients. Full article