Search Results (284)

Automatic sleep staging technology based on wearable photoplethysmography can provide a non-invasive and continuous solution for large-scale sleep health monitoring. This study accordingly developed a novel cross-scale dynamically coupled extended long short-term memory network (SleepXLSTM) to realize automatic sleep staging based on heart rate signals collected by wearable devices. SleepXLSTM models the relationship between heart rate fluctuations and sleep stage labels by correlating physiological features with clinical semantics using a knowledge graph neural network. Furthermore, an excitation–inhibition dual-effect regulator is applied in an improved multiplicative long short-term memory network along with memory mixing in a scalar long short-term memory network to extract and strengthen the key heart rate timing features while filtering out noise produced by motion artifacts, thereby facilitating subsequent high-precision sleep staging. The benefits and functions of this comprehensive heart rate feature extraction were demonstrated using sleep staging prediction and ablation experiments. The proposed model exhibited a superior accuracy of 91.25% and Cohen’s kappa coefficient of 0.876 compared to an extant state-of-the-art neural network sleep staging model with an accuracy of 69.80% and kappa coefficient of 0.040. On the ISRUC-Sleep dataset, the model achieved an accuracy of 87.51% and F1 score of 0.8760. The dynamic coupling strategy employed by SleepXLSTM for automatic sleep staging using the heterogeneous temporal representation of heart rate data can promote the development of smart wearable devices to provide early warning of sleep disorders and realize cost-effective technical support for sleep health management. Full article

Unsafe behaviors at construction sites often originate from cognitive failures such as lapses in memory and attention. This study proposes a novel, hybrid framework to systematically identify and predict the key contributors of cognitive failures among construction workers. First, a detailed literature review was conducted to identify 30 candidate factors related to cognitive failures and unsafe behaviors at construction sites. Thereafter, 10 construction safety experts ranked these factors to prioritize the most influential variables. A questionnaire was then developed and field surveys were conducted across various construction sites. A total of 500 valid responses were collected from construction workers involved in residential, highway, and dam projects in Pakistan. The collected data was first analyzed using conventional statistical analysis techniques like correlation analysis followed by multiple linear and binary logistic regression to estimate factor effects on cognitive failure outcomes. Thereafter, machine-learning models (including support vector machine, random forest, and gradient boosting) were implemented to enable a more robust prediction of cognitive failures. The findings consistently identified fatigue and stress as the strongest predictors of cognitive failures. These results extend unsafe behavior frameworks by highlighting the significant factors influencing cognitive failures. Moreover, the findings also imply the importance of targeted interventions, including fatigue management, structured training, and evidence-based stress reduction, to improve safety conditions at construction sites. Full article

The energy transition, driven by the global shift toward renewable and electrification, necessitates accurate and efficient prediction of electrical load profiles to quantify energy consumption. Therefore, the systematic literature review (SLR), followed by PRISMA guidelines, synthesizes hybrid architectures for sequential electrical load profiles, aiming to span statistical techniques, machine learning (ML), and deep learning (DL) strategies for optimizing performance and practical viability. The findings reveal a dominant trend towards complex hybrid models leveraging the combined strengths of DL architectures such as long short-term memory (LSTM) and optimization algorithms such as genetic algorithm and Particle Swarm Optimization (PSO) to capture non-linear relationships. Thus, hybrid models achieve superior performance by synergistically integrating components such as Convolutional Neural Network (CNN) for feature extraction and LSTMs for temporal modeling with feature selection algorithms, which collectively capture local trends, cross-correlations, and long-term dependencies in the data. A crucial challenge identified is the lack of an established framework to manage adaptable output lengths in dynamic neural network forecasting. Addressing this, we propose the first explicit idea of decoupling output length predictions from the core signal prediction task. A key finding is that while models, particularly optimization-tuned hybrid architectures, have demonstrated quantitative superiority over conventional shallow methods, their performance assessment relies heavily on statistical measures like Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Mean Absolute Percentage Error (MAPE). However, for comprehensive performance assessment, there is a crucial need for developing tailored, application-based metrics that integrate system economics and major planning aspects to ensure reliable domain-specific validation. Full article

As distributed energy resources and nonlinear loads are integrated into power grids on a large scale, power quality issues have grown increasingly prominent, triggering a substantial rise in distribution transformer losses. Traditional approaches struggle to accurately forecast transformer losses under complex power quality conditions and lack quantitative analysis of the influence of various power quality indicators on losses. This study presents a data-driven methodology for transformer loss prediction and sensitivity analysis in such environments. First, an experimental platform is designed and built to measure transformer losses under composite power quality conditions, enabling the collection of actual measurement data when multi-source disturbances exist. Second, a high-precision loss prediction model—dubbed Newton-Raphson-Based Optimizer-Transformer-Bidirectional Long Short-Term Memory (NRBO-Transformer-BiLSTM)—is developed on the basis of an enhanced deep neural network. Finally, global sensitivity analysis methods are utilized to quantitatively evaluate the impact of different power quality indicators on transformer losses. Experimental results reveal that the proposed prediction model achieves an average error rate of less than 0.18% and a similarity coefficient of over 0.9989. Among all power quality indicators, voltage deviation has the most significant impact on transformer losses (with a sensitivity of 0.3268), followed by three-phase unbalance (sensitivity: 0.0109) and third harmonics (sensitivity: 0.0075). This research offers a theoretical foundation and technical support for enhancing the energy efficiency of distribution transformers and implementing effective power quality management. Full article

Interventions on Heritage Buildings (HBs) involve significant challenges due to their tangible (embodied in the material, architectural, physical and technical integrity of the cultural asset), and intangible values (linked to socio-historical–cultural and collective identity, memory, customs and symbols meanings), which must be preserved while also adapting to current sustainability and circular economy goals. However, current conservation and management practices often lack systematic tools to trace, assess, and organise material and component information, hindering the implementation of circular strategies. In line with the European Union’s objectives for climate neutrality and resource efficiency and sufficiency, Material and Product Passports (MPPs) have emerged as digital tools that enhance data traceability, interoperability and transparency throughout a building’s lifecycle. This paper examines the potential of MPPs to support circular management of HBs by analysing the structure of MPPs and outlining the information flows generated by rehabilitation, maintenance and adaptive reuse strategies. A mixed methods approach, combining literature review and data structure analysis, is adopted to identify how the different categories of data produced during maintenance, rehabilitation and adaptive reuse processes can be integrated into MPP modules. The research highlights the conceptual opportunities of MPPs to document and interlink historical, cultural, and technical data, thereby improving decision-making and transparency across intervention stages. The analysis suggests that adapting MPPs to the specificities of historic contexts, such as authenticity preservation, reversibility, and contextual sensitivity, can foster innovative, sustainable, and circular practices in the conservation and management of HBs. Full article

For the Simeulue community, trauma does not remain a source of fear or psychological burden. Instead, it becomes a guideline for their survival. This study explores how societies reconstruct themselves through memory by examining smong, the local knowledge of the Simeulue community in Indonesia, as a cultural mechanism that transforms disaster experience into social resilience. Using a qualitative ethnographic approach, the research utilizes interviews, nandong and song lyrics, field notes, and historical documentation. The findings indicate that smong operates through interconnected layers of communicative and cultural memory: it is preserved in family stories, bedtime stories, artistic expressions, commemorative practices, and symbolic markers such as monuments and grave inscriptions. Through these processes, traumatic experiences are reframed as moral instructions and actionable knowledge that guide rapid evacuation, mutual aid, and collective vigilance during earthquakes and tsunamis. This study demonstrates that the reconstruction of the Simeulue community is driven not by a formal disaster management system but by practices rooted in culture. Past disaster experiences are continuously reinterpreted and integrated into everyday life. This highlights the importance of memory-based strategies for strengthening community resilience and offers directions for future research on intergenerational knowledge transmission, cultural adaptation, and disaster preparedness in oral societies. Full article

The conventional reactive cooling strategy, which relies on static thresholds, has become inadequate for managing dynamically changing heat loads, often resulting in energy inefficiency and increased risk of local hot spots. In this study, we develop a data center cooling optimization system that integrates distributed sensor arrays for predictive analysis. By deploying high-density temperature and humidity sensors both inside and outside server racks, a real-time, high-fidelity three-dimensional digital twin of the data center’s thermal environment is constructed. Time-series analysis combined with Long Short-Term Memory algorithms is employed to forecast temperature and humidity based on the extensive environmental data collected, achieving high predictive accuracy with a root mean square error of 0.25 and an R² value of 0.985. Building on these predictions, a proactive cooling control strategy is formulated to dynamically adjust fan speeds and the opening degree of chilled-water valves in computer room air conditioning units, changing the cooling approach from passive to preemptive prevention of overheating. Compared with conventional proportional–integral–differential control, the developed system significantly reduces overall energy consumption and maintains all equipment within safe operating temperatures. Specifically, the framework has reduced the energy consumption of the cooling system by 37.5%, lowered the overall power usage effectiveness of the data center by 12% (1.48 to 1.30), and suppressed the cumulative hotspot duration (temperature 27 °C) by nearly 96% (from 48 to 2 h). Full article

Accurate prediction of soil texture is essential for effective soil management, precision agriculture, and hydrological modeling. This study proposes a novel, data-driven approach for estimating soil texture without the need for laboratory-based analysis. High-frequency in situ soil moisture measurements from EnviroSCAN (Sentek Technologies, Stepney, Australia) sensors and satellite-derived vegetation indices (NDVI) from Sentinel-2 were collected across 25 sites in Hungary. Temporal soil moisture dynamics were encoded using a Long Short-Term Memory (LSTM) neural network, designed to capture soil-specific hydrological response behavior from time-series data. The resulting latent embeddings were subsequently used within an ordinal regression framework to predict ordered soil texture classes, explicitly enforcing physical consistency between classes. Model performance was evaluated using leave-one-soil-out cross-validation, achieving an overall classification accuracy of 0.54 and a mean absolute error (MAE) of 0.50, indicating predominantly adjacent-class errors. The proposed approach demonstrates that soil texture can be inferred from dynamic environmental responses alone, offering a transferable alternative to fraction-based regression models and supporting scalable sensor calibration and digital soil mapping in data-scarce regions. Full article

Community gardening has become an important urban sustainability initiative that integrates ecological restoration with social participation. However, little is known about the psychological and social mechanisms that drive citizens’ willingness to engage in such activities, particularly in densely populated cities with limited green space. This study develops and empirically tests an integrative behavioral model combining environmental psychology, social cognitive theory, and environmental identity theory to explain citizens’ participation in community gardening in Tehran, Iran. Using survey data from 416 residents and analyzing results through structural equation modeling, the study evaluates the effects of six key predictors, including childhood nature experience, connectedness to nature, self-efficacy, outcome expectancy, psychological restoration, and collective environmental responsibility, on willingness to participate. The model explained 54% of the variance in participation, indicating high explanatory power. Five predictors significantly influenced willingness to participate: childhood nature experience, connectedness to nature, outcome expectancy, psychological restoration, and collective environmental responsibility, while self-efficacy was not significant. The findings reveal that engagement in community gardening is shaped more by emotional, restorative, and moral motivations than by perceived capability alone. Theoretically, this research advances understanding of pro-environmental participation by integrating memory-based, affective, and normative dimensions of behavior. Practically, it provides actionable insights for urban planners and policymakers to design inclusive, emotionally restorative, and collectively managed green initiatives that strengthen citizen participation and enhance urban resilience. Full article

Accurate monitoring of chlorophyll-a (Chl-a) is essential for managing coastal aquaculture, as Chl-a indicates phytoplankton biomass and water quality. This study developed a hybrid deep learning model integrating convolutional neural networks (CNN), bidirectional long short-term memory (BiLSTM), and an attention mechanism (Attention) to classify Chl-a using hourly, water quality datasets collected from the GOT001 station in Si Racha Bay, Eastern Gulf of Thailand (2020–2024). A random forest (RF) identified sea surface temperature (SEATEMP), dew point temperature (DEWPOINT), and turbidity (TURB) as the most influential variables, accounting for over 90% of the accuracy. Chl-a concentrations were categorized into ecological groups (low, medium, and high) using quantile-based binning and K-means clustering to support operational classification. Model performance comparison showed that the CNN–BiLSTM model achieved the highest classification accuracy (81.3%), outperforming the CNN–LSTM model (59.7%). However, the addition of the Attention did not enhance predictive performance, likely due to the limited number of key predictive variables and their already high explanatory power. This study highlights the potential of CNN–BiLSTM as a near-real-time classification tool for Chl-a levels in highly variable coastal ecosystems, supporting aquaculture management, early warning of algal blooms or red tides, and water quality risk assessment in the Gulf of Thailand and comparable coastal regions. Full article

Accurate Prognostics and Health Management (PHM) of cutting tools in Computer Numerical Control (CNC) milling machines is essential for minimizing downtime, improving product quality, and reducing maintenance costs. Previous studies have frequently applied deep learning, particularly Long Short-Term Memory (LSTM) neural networks, for tool wear prediction and Remaining Useful Life (RUL) prediction. However, they often rely on simplified datasets or single architectures limiting industrial relevance. This study proposes a novel ensemble-LSTM framework that combines LSTM, BiLSTM, Stacked LSTM, and Stacked BiLSTM architectures using a GRU-based meta-learner to exploit their complementary strengths. The framework is evaluated using the publicly available PHM’2010 milling dataset, a well-established industrial benchmark comprising comprehensive time-series sensor measurements collected under variable loads and realistic machining conditions. Experimental results show that the ensemble-LSTM outperforms individual LSTM models, achieving an RMSE of 2.4018 and an MAE of 1.9969, accurately capturing progressive tool wear trends and adapting to unseen operating conditions. The approach provides a robust, reliable solution for real-time predictive maintenance and demonstrates strong potential for industrial tool condition monitoring. Full article

Considering the significant role that emergency infrastructure projects (EIPs) play globally in responding to emergency events, public sentiment towards EIPs has become an increasingly important factor to consider. However, limited studies have analysed the public’s sentiment specifically towards EIPs in emergency and urgent circumstances. This study analyses public sentiment characteristics by collecting objective big data from popular posts and comments related to EIPs on Sina Weibo. Sentiment information was extracted using text mining methods, and sentiment was measured using a long short-term memory (LSTM) model. Findings indicate that (1) Positive sentiment predominates in the data. (2) Public sentiment of temporary EIPs remains relatively stable, while long-term adaptive EIPs earn more pronounced sentiment fluctuation. (3) There are regional differences in public sentiment; Hebei, Shandong and Shanghai exhibit slightly lower stability with positive sentiment being slightly lower than or equal to neutral sentiment. The findings contribute to the literature by focusing innovatively on the public perspective of EIPs under urgent circumstances by exploring public sentiment characteristics and evolution and are of particular significance for related government departments and project managers in decision-making and construction management. Full article

To address the limitations of sensor deployment and high maintenance costs in smart swine barns, this study proposes a digital twin (DT)-based virtual sensor prediction and visualization method. Spatial constraints and harsh barn environments often cause sensor blackout zones, hindering precise environmental monitoring. To overcome these challenges, a virtual sensor was defined at the central position between Zone 1 and Zone 2, and its data were generated using a hybrid model that combines inverse distance weighting (IDW)-based spatial interpolation with long short-term memory (LSTM)-based time-series prediction. The proposed method was evaluated using 34,992 datasets collected from January to August 2025. Performance analysis demonstrated that the hybrid model achieved high prediction accuracy, particularly for variables with strong spatial heterogeneity, such as carbon dioxide (CO₂) and ammonia (NH₃), with overall coefficients of determination (R²) exceeding 0.95. Furthermore, a Web-based graphics library (WebGL) digital twin visualization environment was developed to intuitively observe spatiotemporal changes in sensor data. The system integrates sensor placement, risk-level assessment, and time-series graphs, thereby supporting users in real-time environmental monitoring and decision-making. This approach improves the precision and reliability of smart barn management and contributes to the stabilization of farm income. Full article

Sleep is increasingly acknowledged as a cornerstone of public health, with chronic sleep loss implicated in preventable injury and deaths. Obstructive sleep apnea (OSA) affects over one billion people worldwide but remains widely under-diagnosed due to dependence on polysomnography (PSG), an overnight, hospital-based intrusive procedure. As an adjunct to the clinical diagnosis of OSA, this paper presents a low-cost, smartphone-based Generative AI agent framework for sleep apnea detection and sleep coaching at the bedside. Powered by an on=device Generative AI model, the four agents of this framework include a classifier, an analyser, a visualiser, and a sleep coach. The key agent activities performed are sleep apnea detection, sleep data management, data analysis, and natural language sleep coaching. The framework was empirically evaluated on a subject-independent hold-out set drawn from a dataset of 500 clinician annotated clips collected from 10 clinically diagnosed OSA patients. Sleep apnea detection achieved an accuracy of 0.89, precision of 0.91, and recall of 0.88, with nightly Apnea–Hypopnea Index (AHI) estimates strongly correlated with PSG-based clinical scores. The framework was further assessed on the performance metrics of computation, latency, memory, and energy usage. The results of these experiments confirm the feasibility of the proposed framework for large-scale, low-cost OSA screening, with pathways for future work in federated learning, noise robustness, and broad clinical validation. Full article

Solid-State Drives (SSDs) have become the dominant storage medium in performance-sensitive systems due to their high throughput, reliability, and energy efficiency. However, inherent constraints in NAND flash memory—such as out-of-place writes, block-level erase operations, and data fragmentation—necessitate frequent garbage collection (GC), which can significantly degrade user I/O performance when not properly managed. This paper presents a channel-aware GC control mechanism for multi-channel SSD architectures that limits GC concurrency based on real-time storage utilization. Unlike conventional controllers that allow GC to proceed simultaneously across all channels—often leading to complete I/O stalls—our approach adaptively throttles the number of GC-active channels to preserve user responsiveness. The control logic uses a dynamic thresholding function that increases GC aggressiveness only as the SSD approaches full capacity, allowing the system to balance space reclamation with quality-of-service guarantees. We implement the proposed mechanism in an SSD simulator and evaluate its performance under a range of real-world workloads. Experimental results show that the proposed adaptive GC control significantly improves SSD responsiveness across various workloads. Across all workloads, the proposed adaptive GC control achieved an average latency improvement factor of 4.86×, demonstrating its effectiveness in mitigating GC-induced interference. Even when excluding extreme outlier cases, the method maintained an average improvement of 1.55×, with a standard deviation of 1.17, confirming its consistency and robustness across diverse workload patterns. Full article