Search Results (15)

Background/Objectives: Emergency department length of stay (ED LOS) is a key indicator reflecting emergency department crowding, patient safety, and healthcare resource efficiency. Among injured patients, ED LOS may be prolonged depending on injury severity and disposition pathways (admission and inter-hospital transfer). This nationwide study using the Korean National Emergency Department Information System (NEDIS) aimed to (1) describe the distribution and determinants of ED LOS among injured patients and (2) quantify the mediating effects of disposition (admission and transfer) on the association between injury severity measured by the International Classification of Diseases-based Injury Severity Score (ICISS) and ED LOS. Methods: We analyzed NEDIS injury-related ED visit records collected from the date of IRB approval through 12 January 2026. We conducted a retrospective observational study using NEDIS data. Of 1,048,575 injury-related ED visits, 1,035,484 visits with valid ED LOS and eligible records were included after excluding missing key variables and implausible time values. ED LOS was calculated in minutes using arrival and departure timestamps. Injury severity was assessed using ICISS (primary: based on 15 diagnoses; sensitivity: based on 20 diagnoses). Determinants of ED LOS were evaluated using gamma regression with a log link. Disposition was categorized as discharge, admission, and inter-hospital transfer; admission and transfer were modeled as binary mediators. Causal mediation analyses estimated the average causal mediation effect (ACME), average direct effect (ADE), total effect, and proportion mediated. Multiple sensitivity analyses (outlier handling, missing-data approaches, alternative log-linear modeling, and EMS arrival subgroup analyses) assessed robustness. Results: The median ED LOS was 150 min (IQR 90–260). ED LOS differed substantially by disposition: 120 min for discharged patients, 420 min for admitted patients, and 360 min for transferred patients. Overall, 17.9% of visits had an ED LOS ≥ 6 h, and prolonged stays were concentrated among admitted (≥6 h: 55.0%) and transferred (≥6 h: 45.0%) patients. In gamma regression, a 0.05 decrease in ICISS (greater severity) was associated with longer ED LOSs in the unadjusted model (Ratio 1.34) and remained significant in the fully adjusted model (Ratio 1.12, 95% CI 1.11–1.13). Admission and transfer were strong determinants of ED LOS in the final model (ratios of 2.35 and 2.05, respectively). In mediation analyses, admission mediated 36.8% of the severity–ED LOS association (ACME 0.085; ADE 0.146), and transfer mediated 14.3% (ACME 0.033; ADE 0.198). Findings were consistent across sensitivity analyses. Conclusions: In this nationwide cohort of injured patients, ED LOS showed a right-skewed distribution, with prolonged stays concentrated in admission and transfer pathways. Injury severity (ICISS) was independently associated with longer ED LOS, and a substantial proportion of this association was mediated through admission and transfer. Reducing ED LOS among severely injured patients likely requires not only streamlining diagnostic and treatment processes but also system-level interventions targeting output-stage bottlenecks, including inpatient bed operations/boarding management and transfer coordination. Full article

Inpatient deterioration, marked by ICU transfer or mortality, remains a critical challenge in hospital settings. While traditional early warning systems (EWS) have limitations, machine learning (ML) offers a promising approach for the early identification of at-risk patients. This study aimed to develop and validate multiple ML models for predicting inpatient deterioration among general medical patients using electronic health record (EHR) data. A retrospective cohort study was conducted on 524 patients admitted between January 2022 and December 2023. The dataset included demographic, clinical, and laboratory variables, with time-stamped measurements treated as distinct features. After excluding variables with >15% missing data, standard imputation was performed. The training data was balanced using the Synthetic Minority Over-sampling Technique (SMOTE), and feature selection was performed using SelectKBest. A range of models—including Logistic Regression, Random Forest, Gradient Boosting, Support Vector Machines (SVMs), and Neural Networks—were trained and evaluated using AUC, accuracy, precision, recall, and F1-score. During 5-fold cross-validation, the models demonstrated high stability, with the Random Forest achieving a mean AUC of 0.980. On the final independent test set, the optimized Random Forest model yielded the highest performance with an AUC of 0.837 and an accuracy of 85.4%. Functional status, oxygen requirements, and urea levels were identified as key predictors. ML models, particularly Random Forest, can significantly enhance the early detection of inpatient deterioration. The contribution of this work lies in its systematic comparison of multiple algorithms and its robust methodology. Future research should focus on external validation, the integration of temporal data using recurrent neural network architectures, and the application of Explainable AI (XAI) to foster clinical trust and facilitate implementation. Full article

The article presents a blockchain-based architecture for decentralized electricity trading that tokenizes energy delivery rights and cash-flows. Energy Attribute Certificates (EACs) are implemented as NFTs, while buy/sell orders are encoded as ERC-1155 tokens whose tokenId packs a time slot and price, enabling precise matching across hours. A clearing smart contract (Matcher) burns filled orders, mints an NFT option, and issues two ERC-20 assets: PT, the right to consume kWh within a specified interval, and YT, the producer’s claim on revenue. We propose a simple, linearly increasing discounted buyback for YT within the slot and introduce an aggregating token, IndexYT, which accumulates YTs across slots, redeems them at par at maturity, and gradually builds on-chain reserves—turning IndexYT into a liquid, yield-bearing instrument. We outline the PT/YY lifecycle, oracle-driven policy controls for DSO (e.g., transfer/splitting constraints), and discuss transparency, resilience, and capital efficiency. The contribution is a Pendle-inspired split of electricity into Principal/Yield tokens combined with a time-stamped on-chain order book and IndexYT, forming a programmable market for short-term delivery rights and yield derivatives with deterministic settlement. Full article

This study addresses the persistence of avoidable failures and efficiency losses in HVAC plants by introducing a field-validated predictive maintenance (PdM) framework that estimates component-level RUL from multiyear BMS telemetry and translates forecasts into schedule-aware maintenance actions. The objective was to determine whether an LSTM ensemble with mode-aware segmentation and isotonic calibration could yield decision-quality RUL forecasts that reduce unplanned outages, downtime, and electricity use in a large Riyadh office building. Two years of 1 min BMS data from chillers, primary pumps, and AHU fans were cleaned, standardized, and segmented by operating mode; RUL labels were derived from time-stamped work orders and failure confirmations; the LSTM produced per-minute RUL estimates trained with a Huber loss, calibrated to lower quantiles, and converted to sustained triggers compared against a fixed-interval program. On the held-out test set, the model achieved a weighted MAE of 19.8 ± 2.1 h and RMSE of 29.1 ± 3.3 h, with quantile calibration error (QCE) $\le 0.06$ and lead-time accuracy (LTA; fraction of triggers whose calibrated lower-quantile RUL is $\ge$ the planning threshold) of 0.79 at a 10-day threshold. When deployed in counterfactual evaluation, triggers reduced unplanned outages by 47.6% (paired bootstrap p = 0.008) and total downtime by 41.3% (p = 0.012), and yielded a 10.6% reduction in HVAC electricity (95% CI: 7.7–13.2%) and a 9.7% decrease in total operating cost. The findings indicate that calibrated sequence models coupled to simple sustained triggers can convert routine BMS data into reliable maintenance schedules with quantifiable reliability and energy benefits. Practically, conservative calibration (q approximately 0.25) with thresholds of 10–12 days provided stable lead windows; future work should assess transferability across climates and facility types using transfer learning and integrate uncertainty-aware triggering with MPC for joint operational and maintenance optimization. Full article

Accurate time-series forecasting plays a vital role in sensor-driven applications such as energy monitoring, traffic flow prediction, and environmental sensing. While most existing approaches focus on extracting local patterns from historical observations, they often overlook the global temporal information embedded in timestamps. However, this information represents a valuable yet underutilized aspect of sensor-based data that can significantly enhance forecasting performance. In this paper, we propose a novel timestamp-guided knowledge distillation framework (TKDF), which integrates both historical and timestamp information through mutual learning between heterogeneous prediction branches to improve forecasting robustness. The framework comprises two complementary branches: a Backbone Model that captures local dependencies from historical sequences, and a Timestamp Mapper that learns global temporal patterns encoded in timestamp features. To enhance information transfer and reduce representational redundancy, a self-distillation mechanism is introduced within the Timestamp Mapper. Extensive experiments on multiple real-world sensor datasets—covering electricity consumption, traffic flow, and meteorological measurements—demonstrate that the TKDF consistently improves the performance of mainstream forecasting models. Full article

The text classification method is one of the most frequently used approaches in text mining studies. Text classification requires a model generation using a predefined dataset, and this model aims to assign uncategorized data to a correct category. In line with this purpose, this study used machine learning algorithms, deep learning algorithms, word embedding algorithms, and transfer-learning algorithms to classify Turkish texts using three diverse datasets, one of which is new, to analyze text classification performances for the Turkish language. The preparation process of the newly added dataset involved the variations in Turkish word usage patterns over the years, since it consisted of timestamp-enabled data. The study also developed a novel method named LSRM to increase the text classification performance for agglutinative languages such as Turkish. After testing the new method on datasets, the statistical ANOVA method revealed that applying the proposed LSRM method increased the classification performance. Full article

The Internet’s expansion has changed how the services accessed and businesses operate. Blockchain is an innovative technology that emerged after the rise of the Internet. In addition, it maintains transactions on encrypted databases that are distributed among many computer networks, much like digital ledgers for online transactions. This technology has the potential to establish a decentralized marketplace for Internet retailers. Sensitive information, like customer data and financial statements, should be routinely transferred via e-commerce. As a result, the system becomes a prime target for cybercriminals seeking illegal access to data. As e-commerce increases, so does the frequency of hacker attacks that raise concerns about the safety of e-commerce platforms’ databases. Owing to the sensitivity of customer data, employee records, and customer records, organizations must ensure their protection. A data breach not only affects an enterprise’s financial performance but also erodes clients’ confidence in the platform. Currently, e-commerce businesses face numerous challenges, including the security of the e-commerce system, transparency and trust in its effectiveness. A solution to these issues is the application of blockchain technology in the e-commerce industry. Blockchain technology simplifies fraud detection and investigation by recording transactions and accompanying data. Blockchain technology enables transaction tracking by creating a detailed record of all the related data, which can assist in identifying and preventing fraud in the future. Using blockchain cryptocurrency will record the sender’s address, recipient’s address, amount transferred, and timestamp, which creates an immutable and transparent ledger of all transaction data. Full article

Temporal knowledge graphs play an increasingly prominent role in scenarios such as social networks, finance, and smart cities. As such, research on temporal knowledge graphs continues to deepen. In particular, research on temporal knowledge graph reasoning holds great significance, as it can provide abundant knowledge for downstream tasks such as question answering and recommendation systems. Current reasoning research focuses primarily on interpolation and extrapolation. Extrapolation research aims to predict the likelihood of events occurring in future timestamps. Historical events are crucial for predicting future events. However, existing models struggle to fully capture the evolutionary characteristics of historical knowledge graphs. This paper proposes a multi-scale evolutionary network (MSEN) model that leverages Hierarchical Transfer aware Graph Neural Network (HT-GNN) in a local memory encoder to aggregate rich structural semantics from each timestamp’s knowledge graph. It also utilizes Time Related Graph Neural Network (TR-GNN) in a global memory encoder to model temporal-semantic dependencies of entities across the global knowledge graph, mining global evolutionary patterns. The model integrates information from both encoders to generate entity embeddings for predicting future events. The proposed MSEN model demonstrates strong performance compared to several baselines on typical benchmark datasets. Results show MSEN achieves the highest prediction accuracy. Full article

Attractants used with sticky traps for monitoring navel orangeworm include artificial pheromone lures, ovipositional bait (ovibait) bags, and phenyl propionate; however, the sticky traps have the limitations of potentially becoming ineffective because of full or dirty glue surfaces and of having access to data dependent on increasingly expensive labor. A study comparing detection with a commercially available pseudo-acoustic optical sensor (hereafter, sensor) connected to a server through a cellular gateway found similar naval orangeworm activity profiles between the sensor and pheromone traps, and the timestamps of events in the sensors was consistent with the behavior of navel orangeworm males orienting to pheromone. Sensors used with ovibait detected navel orangeworm activity when no navel orangeworm were captured in sticky traps with ovibait, and the timestamps for this activity were inconsistent with oviposition times for navel orangeworm in previous studies. When phenyl propionate was the attractant, sensors and sticky traps were more highly correlated than for pheromone traps on a micro-level (individual replicates and monitoring intervals), but there was high variation and week-to-week profiles differed. These results indicate that these sensors represent a promising alternative to sticky traps for use with pheromone as an attractant, but more research is needed to develop the use of sensors with other attractants. These results will guide developers and industry in transfer of this promising technology. Full article

We present a case study of a Structural Health Monitoring (SHM) hybrid system based on Brillouin Distributed Fiber Optic Sensors (D-FOS), Vibrating Wire (VW) extensometers and temperature probes for an existing historical water penstock bridge positioned in a mountain valley in Valle d’Aosta Region, Northwestern Italy. We assessed Brillouin D-FOS performances for this kind of infrastructure, characterized by a complex structural layout and located in a harsh environment. A comparison with the more traditional strain monitoring technology offered by VW strain gauges was performed. The D-FOS strain cable has been bonded to the concrete members using a polyurethane-base adhesive, ensuring a rigid strain transfer. The raw data from all sensors are interpolated on a unique general timestamp with hourly resolution. Strain data from D-FOS and VW strain gauges are then corrected from temperature effects and compared. Considering the inherent differences between the two monitoring technologies, results show a good overall matching between strain time series collected by D-FOS and VW sensors. Brillouin D-FOS proves to be a good solution in terms of performance and economic investment for SHM systems on complex infrastructures such as hydropower plants, which involve extensive geometry combined with the need for detailed and continuous strain monitoring. Full article

During the training phase of the supervised learning, it is not feasible to collect all the datasets of labelled data in an outdoor environment for the localization problem. The semi-supervised transfer learning is consequently used to pre-train a small number of labelled data from the source domain to generate a kernel knowledge for the target domain. The kernel knowledge is transferred to a target domain to transfer some unlabelled data into the virtual labelled data. In this paper, we have proposed a new outdoor localization scheme using a semi-supervised transfer learning for LoRaWANs. In the proposed localization algorithm, a grid segmentation concept is proposed so as to generate a number of virtual labelled data through learning by constructing the relationship of labelled and unlabelled data. The labelled-unlabelled data relationship is repeatedly fine-tuned by correctly adding some more virtual labelled data. Basically, the more the virtual labelled data are added, the higher the location accuracy will be obtained. In the real implementation, three types of signal features, RSSI, SNR, and timestamps, are used for training to improve the location accuracy. The experimental results illustrate that the proposed scheme can improve the location accuracy and reduce the localization error as opposed to the existing outdoor localization schemes. Full article

When computer systems are increasingly important for our daily activities, cybercrime has created challenges for the criminal justice system. Data can be hidden in ADS (Alternate Data Stream) without hindering performance. This feature has been exploited by malware authors, criminals, terrorists, and intelligence agents to erase, tamper, or conceal secrets. However, ADS problems are much ignored in digital forensics. Rare researches illustrated the contact artifacts of ADS timestamps. This paper performs a sequence of experiments from an inherited variety and provides an in-depth overview of timestamp transfer on data hiding operations. It utilizes files or folders as original media and uses the timestamp rules as an investigative approach for the forensic exchange analysis of file sets. This paper also explores timestamp rules using case examples, which allow practical applications of crime scene reconstruction to real-world contexts. The experiment results demonstrate the effectiveness of temporal attributes, help digital forensic practitioners to uncover hidden relations, and trace the contact artifacts among crime scenes, victims, and suspects/criminals. Full article

Snoring, a form of sleep-disordered breathing, interferes with sleep quality and quantity, both for the person who snores and often for the person who sleeps with the snorer. Poor sleep caused by snoring can create significant physical, mental, and economic problems. A simple and natural solution for snoring is to sleep on the side, instead of sleeping on the back. In this project, a deep learning model for snoring detection is developed and the model is transferred to an embedded system—referred to as the listener module—to automatically detect snoring. A novel wearable gadget is developed to apply a vibration notification on the upper arm until the snorer sleeps on the side. The gadget is rechargeable, and it is wirelessly connected to the listener module using low energy Bluetooth. A smartphone app—connected to the listener module using home Wi-Fi—is developed to log the snoring events with timestamps, and the data can be transferred to a physician for treating and monitoring diseases such as sleep apnea. The snoring detection deep learning model has an accuracy of 96%. A prototype system consisting of the listener module, the wearable gadget, and a smartphone app has been developed and tested successfully. Full article

As the use of unmanned aerial vehicles (UAVs) for industrial use increases, so are the demands for highly accurate navigation solutions, and with the high dynamics that UAVs offer, the accuracy of a measurement does not only depend on the value of the measurement, but also the accuracy of the associated timestamp. Sensor timing using dedicated hardware is the de-facto method to achieve optimal sensor performance, but the solutions available today have limited flexibility and requires much effort when changing sensors. This article presents requirements and suggestions for a highly accurate, reconfigurable sensor timing system that simplifies integration of sensor systems and navigation systems for UAVs. Both typical avionics sensors, like GNSS receivers and IMUs, and more complex sensors, such as cameras, are supported. To verify the design, an implementation named the SenTiBoard was created, along with a software support package and a baseline sensor-suite. With the solution presented in this paper we get a measurement resolution of 10 nanoseconds and we can transfer up to 7.6 megabytes per second. If the sensor suite includes a GNSS receiver with a pulse-per-second (PPS) reference, the sensor measurements can be related to an absolute time reference (UTC) with a clock drift of 1.9 microseconds per second RMS. An experiment was carried out, using a Mini Cruiser fixed-wing UAV, where errors in georeferencing infrared images were reduced with a factor of 4 when compared to a software synchronization method. Full article

Smartphone-based sensing is becoming a convenient way to collect data in science, especially in environmental research. Recent studies that use smartphone sensing methods focus predominantly on single sensors that provide quantitative measurements. However, interdisciplinary projects call for study designs that connect both, quantitative and qualitative data gathered by smartphone sensors. Therefore, we present a novel open-source task automation solution and its evaluation in a personal exposure study with cyclists. We designed an automation script that advances the sensing process with regard to data collection, management and storage of acoustic noise, geolocation, light level, timestamp, and qualitative user perception. The benefits of this approach are highlighted based on data visualization and user handling evaluation. Even though the automation script is limited by the technical features of the smartphone and the quality of the sensor data, we conclude that task automation is a reliable and smart solution to integrate passive and active smartphone sensing methods that involve data processing and transfer. Such an application is a smart tool gathering data in population studies. Full article