This study presents an integrated finite-element–machine-learning framework for predicting early-age stress evolution in concrete materials/structures by combining an enhanced thermo-chemo-mechanical (TCM) model, deep sequential learning (DSL), and active learning (AL). The proposed TCM model incorporates experimentally informed viscoelasticity, a stable exponential creep–relaxation conversion, and an efficient exponential algorithm for the Maxwell-chain formulation in finite element analysis, which is further validated by a temperature stress testing machine. This model generates high-fidelity stress–time data across diverse mixtures, temperatures, and structural configurations. These simulations are used to train a Gated Recurrent Unit with Monte Carlo Dropout (GRU-MCD) model, whose predictive performance surpasses conventional point-wise approaches such as Light Gradient Boosting Machine and Gaussian Process Regression, yielding higher accuracy with reduced overfitting. The AL strategy further enhances efficiency by enabling the GRU-MCD model to achieve the accuracy of ∼900 Latin Hypercube samples using only ∼200 samples selected by active learning. Although demonstrated on a wall–base structure, the proposed framework is general and applicable to other cementitious material or structural systems, providing an effective tool for cracking-risk evaluation, reliability analysis, and the design of low-carbon concrete structures.

Graph Alignment (GA) is an NP-hard combinatorial challenge. The existing methods usually work on small-scale graphs because their computational complexity grows as the square of the number of nodes. Recent techniques relied on alignment labels to divide the large source and target graphs into small ones respectively, which are then aligned separately. However, the alignment labels in expansive real-world graphs are often scarce, which makes GA even more challenging. To address these issues, we propose a novel self-supervised learning framework that is able to work on the graphs of million nodes without any alignment labels, where the existing methods usually fail to output an answer within a reasonable time. Our method also falls in the divide-and-conquer paradigm. We do not cluster the source and target graph separately by the existing graph clustering algorithms, because it is difficult to pair and then align the cluster-induced source and target subgraphs in the absence of alignment labels. We devise an Alignment-Aware Clustering (AAC) method to partition the source and target nodes jointly and keep the ought-to-be-aligned pairs of nodes within the same cluster as much as possible. Furthermore, we develop a Topology-Aware Repartition (TAR) that leverages pseudo-alignment labels as anchors for re-clustering, preserving detailed structural information within clusters. This enables graph neural networks to effectively enhance the graph representation learning for node alignments which are self-supervised by a graph-matching solver. Extensive experiments have demonstrated that our method greatly reduces computational demands and sustains high alignment accuracies in large-scale graph applications.

Deep learning methods have demonstrated promising performance on the NP-hard Graph Matching (GM) problems. However, the state-of-the-art methods usually require the ground-truth labels, which may take extensive human efforts or be impractical to collect. In this paper, we present a robust self-supervised bidirectional learning method (IA-SSGM) to tackle GM in an unsupervised manner. It involves an affinity learning component and a classic GM solver. Specifically, we adopt the Hungarian solver to generate pseudo correspondence labels for the simple probabilistic relaxation of the affinity matrix. In addition, a bidirectional recycling consistency module is proposed to generate pseudo samples by recycling the pseudo correspondence back to permute the input. It imposes a consistency constraint between the pseudo affinity and the original one, which is theoretically supported to help reduce the matching error. Our method further develops a graph contrastive learning jointly with the affinity learning to enhance its robustness against the noise and outliers in real applications. Experiments deliver superior performance over the previous state-of-the-arts on five real-world benchmarks, especially under the more difficult outlier scenarios, demon- strating the effectiveness of our method.

ZigBee-Wireless Mesh Networks (ZigBee-WMNs) are recognized as a cost-effective and flexible solution for building automation and control systems (BACs). They have the potential to unify the methods of data communication for sensors, actuators, appliances, and asset-tracking devices in BACs. They offer a means to build a reliable but affordable network backbone to facilitate building control. ZigBee operates primarily in the license-free 2.4 GHz ISM (Industrial, Scientific and Medical) band. This feature makes the technology easily applicable, but also potentially vulnerable to interference by other electronic systems working in the same band such as WLAN-systems of IEEE 802.11 and microwave ovens. This paper reports the experimental results to quantify the impact of different interferers on ZigBee-WMNs. They show that, among different interferers, interference from microwave oven is indeed a major problem. In particular, it results in bigger drop rate and retrial rate compared to the impact of WiFi on WMN. It is expected that the results can provide a quantitative basis for designing reliable ZigBee-WMNs.

Interference from collocated networks operating over the same frequency range becomes an increasingly severe problem as the number of networks overlapping geographically increases within commercial and residential buildings. This paper aims to highlight the issues affecting co-existence of IEEE 802.15.4 (ZigBee) systems in the presence of interference. ZigBee uses the IEEE 802.15.4 PHY and MAC layer standards to handle devices. The practical performance of ZigBee systems are established with reference to supporting empirical and simulated data. Our experiments show that, among different interferers, interference from microwave ovens is indeed a major problem. Guidelines are provided for installing sensors inside buildings.

Wireless Mesh technology has emerged as a new one for next-generation wireless networking to provide a wide variety of applications that cannot be supported directly by other wireless networks. With the recent emergence of standards, wireless solutions are ready to be deployed in building automation networks. For both new and old structures, wireless networking is expected to improve the existing applications and open up new ones. Wireless Mesh Networks (WMNs) deployed in building automation systems is at an early stage; however, as more and more building functions and applications are controlled electronically and wirelessly, the use of WMNs will offer distinctive advantages in the field of commercial and residential buildings. This paper surveys the developments and applications of WMNs in building automation and control systems and sketches the contours of the directions to achieve our goal towards highly energy-efficient buildings while maintaining a healthy, productive, and safe indoor environment.

This paper reviews thermal comfort based control strategies for modern commercial buildings with heating, ventilating, and air-conditioning (HVAC) systems. In order to make HVAC systems more energy-efficient, better system operations and control algorithms for HVAC systems are demanded. Research conducted predominately within the last decade suggests that commercial building HVAC significantly influences the health, satisfaction, and productivity of the building occupants. This paper also projects the use of wireless sensor networks (WSNs) to enhance energy efficiency of HVAC systems as well as provides comfortable environment to assure occupants' productivities.