Laboratory Data Sets Research Articles

A Lightweight and Small Sample Bearing Fault Diagnosis Algorithm Based on Probabilistic Decoupling Knowledge Distillation and Meta-Learning.

Rolling bearings play a crucial role in industrial equipment, and their failure is highly likely to cause a series of serious consequences. Traditional deep learning-based bearing fault diagnosis algorithms rely on large amounts of training data; training and inference processes consume significant computational resources. Thus, developing a lightweight and suitable fault diagnosis algorithm for small samples is particularly crucial. In this paper, we propose a bearing fault diagnosis algorithm based on probabilistic decoupling knowledge distillation and meta-learning (MIX-MPDKD). This algorithm is lightweight and deployable, performing well in small sample scenarios and effectively solving the deployment problem of large networks in resource-constrained environments. Firstly, our model utilizes the Model-Agnostic Meta-Learning algorithm to initialize the parameters of the teacher model and conduct efficient training. Subsequently, by employing the proposed probability-based decoupled knowledge distillation approach, the outstanding performance of the teacher model was imparted to the student model, enabling the student model to converge rapidly in the context of a small sample size. Finally, the Paderborn University dataset was used for meta-training, while the bearing dataset from Case Western Reserve University, along with our laboratory dataset, was used to validate the results. The experimental results demonstrate that the algorithm achieved satisfactory accuracy performance.

From PIV to LSPIV: Harnessing deep learning for environmental flow velocimetry

The inference of velocity fields from the displacement of objects and/or fields visible within a series of consecutive images over known time intervals has been explored extensively within experimental fluid dynamics. Real image sequences of environmental hydrodynamic flows, however, pose additional challenges for velocity field inference due to factors such as lighting inhomogeneity, particle density, camera orientation and stability. Here we investigate the performance of classical and deep learning based velocity estimation methods on three experimental datasets; a hydrodynamics laboratory dataset of different flow types and two open-source datasets of aerial river footage from field campaigns. The river datasets are accompanied by observational datasets of in-situ measurements. In particular, we investigate the generalisation of deep learning based methods from ideal training conditions to real images. We consider three deep learning approaches; recurrent all-pairs-field transforms (RAFT), a physics-informed approach and an unsupervised learning approach (UnLiteFlowNet-PIV). Results indicate that RAFT, which achieves state-of-the-art performance on particle image datasets, showed good generalisation to the laboratory dataset and field imagery. The physics-informed approach performed similarly to RAFT across the laboratory dataset whilst generalisation to drone-based data proved challenging. Across the laboratory dataset, UnLiteFlowNet-PIV showed good performance within wake regions but an underestimation of channel flows and freestream regions with limited vorticity, also suffering under poor seeding density. Limited fine-tuning of UnLiteFlowNet-PIV on laboratory data, however, led to improved performance in these regions, indicating the potential of the unsupervised learning approach for environmental flows where 2D ground truth data sources are unavailable for training.

Transfer Learning from Synthetic Data for SOH Estimation

Public data on battery cell and battery pack aging, especially accessible from outside the automotive industry, is scarce. Scaling up from cell to pack level is not straightforward, as it requires an understanding of the underlying inhomogeneities and degradation patterns. Within the automotive industry, comprehensive time-series data on battery pack or battery electric vehicle aging is also limited due to high costs and data privacy concerns related to customer fleet data. Moreover, it is nearly impossible to capture the vast array of possible aging trajectories in controlled experiments. Such datasets, however, are essential for diagnosis and forecast of battery pack aging in the field, as well as for developing data-driven methods for state estimation.In this work, we introduce a fast, publicly available, battery pack aging data simulation toolbox based on pristine half-cell potential measurements at various C-rates. This toolbox enables the generation of constant-current charging events at different C-rates and can simulate any conceivable aging path. The modular framework allows users to adjust individual cell parameters, including state of charge (SOC), state of health (SOH), and degradation modes.Utilizing pristine half-cell potential measurements from a modern automotive lithium-ion battery, we create an initial cell model. This model, founded on the ‘alawa-toolbox [1], is validated with experimental data from a laboratory dataset. As Figure 1 illustrates, we construct a battery pack model by serially and parallelly connecting multiple cell models, incorporating intermediate resistances. This pack model reflects the configuration of a physical battery pack and permits modifications to SOC, SOH, degradation modes, and lead resistances.We collect time-series data from partial charging events of development vehicles at various aging states and use this data to calibrate our model by minimizing the discrepancy between simulated and measured voltage curves. Our model allows users to simulate and analyze the evolution of battery pack asymmetries, creating a digital twin to monitor aging impacts and identify the "weakest" cell for early damage detection and intervention.Giving every user the opportunity to generate big data from our toolbox expedites the development of data-driven SOH estimation or open-circuit voltage (OCV) reconstruction models. Future research will explore the use of synthetic data to develop state estimation algorithms applicable to various chemistries and configurations, including the analysis and validation against real customer fleet data, their battery pack aging and asymmetry patterns.Our work represents a significant advancement in facilitating access to battery and battery electric vehicle aging data, thereby reducing barriers in this research field. We anticipate that our contribution will hasten the development of data-driven methods at the battery pack level.[1] M. Dubarry, C. Truchot, B. Y. Liaw, Synthesize battery degradation modes via a diagnostic and prognostic model, Journal of Power Sources 219 (2012) 204-216, https://doi.org/10.1016/j.jpowsour.2012.07.016. Figure 1

Data-driven mechanical behavior modeling of granular biomass materials

Significant equipment downtime, mainly caused by the variable attributes and complex mechanical behavior of granular biomass materials, has challenged the great potential of biofuel generation. Expensive and time-consuming lab experiments are not affordable in fully characterizing material behavior for samples with all possible attributes. In this paper, we present data-driven modeling of the cyclic axial compression and ring-shear stress–strain behavior for granular biomass materials with different moisture contents and mean particle sizes. Laboratory characterization data of milled pine samples, with a mean particle size of 2, 4, and 6 mm and a moisture content of 0%, 20%, and 40%, were employed to train two machine learning (ML) models independently. The sequential model takes a sequence of loading history into Gated Recurrent Units (GRU) and predicts the next step of strain/stress with a feed-forward neural network. In contrast, the incremental model takes only the current state to predict the stiffness/compliance coefficient and compute the stress/strain increment. Both models account for material variations in particle sizes and moisture content. After training, both models demonstrate their high efficiency and accuracy in predicting the mechanical behavior of samples with a diverse set of unseen material properties, augmenting the existing laboratory data set. They also effectively capture the underlying physics, which involves increased compressibility as moisture content rises and a linear relationship between applied compression and shear strength. This effort established the foundation for comprehensive data-driven constitutive modeling tailored for unconventional granular materials.

Advanced Bearing-Fault Diagnosis and Classification Using Mel-Scalograms and FOX-Optimized ANN.

Accurate and reliable bearing-fault diagnosis is important for ensuring the efficiency and safety of industrial machinery. This paper presents a novel method for bearing-fault diagnosis using Mel-transformed scalograms obtained from vibrational signals (VS). The signals are windowed and pass through a Mel filter bank, converting them into a Mel spectrum. These scalograms are subsequently fed into an autoencoder comprising convolutional and pooling layers to extract robust features. The classification is performed using an artificial neural network (ANN) optimized with the FOX optimizer, which replaces traditional backpropagation. The FOX optimizer enhances synaptic weight adjustments, leading to superior classification accuracy, minimal loss, improved generalization, and increased interpretability. The proposed model was validated on a laboratory dataset obtained from a bearing testbed with multiple fault conditions. Experimental results demonstrate that the model achieves perfect precision, recall, F1-scores, and an AUC of 1.00 across all fault categories, significantly outperforming comparison models. The t-SNE plots illustrate clear separability between different fault classes, confirming the model's robustness and reliability. This approach offers an efficient and highly accurate solution for real-time predictive maintenance in industrial applications.

Long short term memory networks for predicting resilient Modulus of stabilized base material subject to wet-dry cycles

The resilient modulus (MR) of different pavement materials is one of the most important input parameters for the mechanistic-empirical pavement design approach. The dynamic triaxial test is the most often used method for evaluating the MR, although it is expensive, time-consuming, and requires specialized lab facilities. The purpose of this study is to establish a new model based on Long Short-Term Memory (LSTM) networks for predicting the MR of stabilized base materials with various additives during wet-dry cycles (WDC). A laboratory dataset of 704 records has been used using input parameters, including WDC, ratio of calcium oxide to silica, alumina, and ferric oxide compound, Maximum dry density to the optimal moisture content ratio (DMR), deviator stress (σd), and confining stress (σ3). The results demonstrate that the LSTM technique is very accurate, with coefficients of determination of 0.995 and 0.980 for the training and testing datasets, respectively. The LSTM model outperforms other developed models, such as support vector regression and least squares approaches, in the literature. A sensitivity analysis study has determined that the DMR parameter is the most significant factor, while the σd parameter is the least significant factor in predicting the MR of the stabilized base material under WDC. Furthermore, the SHapley Additive exPlanations approach is employed to elucidate the optimal model and examine the impact of its features on the final result.

Biofilm Growth in Porous Media Well Approximated by Fractal Multirate Mass Transfer With Advective‐Diffusive Solute Exchange

AbstractBiofilm growth in porous media changes not only the hydrodynamic properties of the medium (reduction in porosity and permeability, and increase in dispersivity), but also the transport itself (breakthrough curves display increasingly fast first arrivals and long tails). These features are well reproduced by multicontinuum models (Multi‐Rate Mass Transfer, MRMT) which can be used to describe reactive transport in heterogeneous porous media and facilitate the simulation of reactions that are localized within biofilms. Here, we present a conceptual and numerical model of biochemical reactive transport with dynamic biofilm growth based on MRMT formulations. Mass exchange between mobile water and immobile biofilm aggregates is represented by a memory function, which simplifies definition of MRMT parameters. We successfully tested this model on two sets of laboratory data and found that (a) a basic model based on the growth of uniformly sized biofilm aggregates fails to reproduce laboratory tracer tests and rate of biofilm growth, while a fractal growth model, which we obtain by integrating the memory functions of biofilm aggregates with a power law distribution, does; (b) the biofilm memory function evolves as the biofilm grows; and (c) the early time portion of eluted volume tracer breakthrough curves are independent of flow rate, whereas the tail becomes heavier when the flow rate is decreased, which implies that both advection controlled and diffusion controlled mass exchange coexist in biofilms. These findings imply that porous media biofilms are essentially different from those developing in human tissues or open spaces.

LIBS plasma diagnostics with SuperCam on Mars: Implications for quantification of elemental abundances

The Perseverance rover landed in Jezero Crater, Mars, in 2021 to explore an ancient delta for signs of past life and collect samples for a future Mars Sample Return Mission. SuperCam, onboard Perseverance, uses Laser Induced Breakdown Spectroscopy (LIBS) to quantify the elements in the rocks/soils encountered along the rover's traverse. LIBS is desirable for planetary science missions because of its effectiveness at a distance and with different target types (rock, soil, etc). However, decreased laser irradiance with distance and changing coupling efficiency in different targets could cause the physical conditions of the plasma plume to vary, with important implications for SuperCam's elemental calibration. This study examines the characteristics of laser-induced plasmas on Mars by estimating apparent temperature via the multiline Boltzmann plot method and electron density using Stark broadening of the H-α line. We find that apparent plasma temperatures do not decrease with distance or vary systematically with target type (rock vs soil). The variability in plasma temperatures seen on Mars is fully represented in the laboratory dataset used for SuperCam's elemental calibration, which suggests that our elemental calibration is likely robust against observed changes in apparent plasma temperature. These results imply that SuperCam can make reliable LIBS observations to at least 8 m. Estimated electron density is 1.4× higher in soils than rock targets, which is likely related to the dependence of the H-α line on topographic relief, a poorly understood mechanism which contributes to the difficulty of quantifying hydrogen abundance in Mars spectra.

Predicting strain energy causing soil liquefaction

Liquefaction, which typically occurs in saturated sandy soil deposits, is one of the destructive phenomena that can occur during an earthquake. When the soil reaches liquefied state, it loses a significant amount of resistance and stiffness, which often results in widespread catastrophic damages. Therefore, accurate evaluating the potential of soil liquefaction occurrence is of great importance in earthquake geotechnical designs in regions prone to this phenomenon. The strain energy-based approach is a novel robustness technique to evaluate liquefaction potential. In the current research, 165 laboratory data sets from cyclic experiments were collected and analyzed. A predictive model using gene expression programming (GEP) was proposed to assess strain energy needed for occurrence of soil liquefaction. Assessing physical behavior of developed GEP-based model was conducted through sensitivity analysis. Performance of GEP-based was validated by comparing with a series of centrifuge experiments and cyclic triaxial tests results. Subsequently, after experimental verification of numerical modeling, the strain energy required for soil liquefaction under cyclic loading at different conditions were numerically evaluated and compared with the strain energy calculated by proposed model. Finally, the developed GEP-based model was compared with established strain energy-based relationships. The results indicated high precision of proposed GEP-based model in determination of strain energy required for soil liquefaction triggering.

An attention fused sequence -to-sequence convolutional neural network for accurate solar irradiance forecasting and prediction using sky images

The challenge of accurately forecasting ultra-short-term solar irradiance for photovoltaic systems is complicated by rapidly changing weather, and while ground-based sky images offer potential improvements, effectively extracting spatiotemporal data from these images remains a significant hurdle for current computer vision models. A new hybrid model, "An Attention Fused Sequence-to-Sequence Convolutional Neural Network," is being developed to address this challenge. The model predicts intra-hour GHI, DNI, and DHI with a 10-min lead time by combining a Convolutional Neural Network (for spatial feature extraction from sky images), an attention mechanism (to focus on relevant regions), and a sequence-to-sequence model (for temporal feature extraction from time-series data). The proposed Model is trained using the NREL Solar Radiation Research Laboratory Dataset while evaluating the model with the Mean Bias Error, Mean Absolute Error, Root Mean Squared Error, R Squared, and forecasting skill score. The 10-min and sequence length 2 interval is considered to be the best performing across most of the evaluation metrics with an MBE value is 2.321 W/m2, MAE value of 39.490 W/m2, RMSE value of 62.086 W/m2, R2 value is 0.909 W/m2, FSS value of 23.589 W/m2 and an MBE of 4.876 W/m2, MAE of 56.887 W/m2, RMSE of 85.346 W/m2, R2 of 0.834 and FSS of 24.881 W/m2 respectively. Furthermore, the sensitivity analysis reveals that the proposed model's performance is influenced by both the sequence length and the lead time. The proposed framework outperforms other techniques for ultra-short-term PV generation forecasting, demonstrating its potential for practical deployment in PV systems to improve grid reliability and energy management.

NPM1 Minimal Residual Disease Detection at Any Time by Clinical Next Generation Sequencing Predicts Poor Survival in Acute Myeloid Leukemia

Abstract Introduction/Objective Acute Myeloid Leukemia (AML) is a deadly disease that accounts for 80% of adult leukemia cases and carries a 5-year survival rate of only 31.7%. Historically, prognosis hinged heavily on cytogenetic stratification, but more recently minimal residual disease (MRD) has emerged as a crucial prognostic marker. Flow cytometry, PCR, and NGS can all be employed for MRD detection, but each carries its own limitations. Though technically challenging, NGS has the advantage being able to simultaneously assay multiple mutations, thus providing for broader applicability. NPM1 is the most prevalently mutated gene in AML (25-35%). In this study, one of the largest of its kind, we investigate the feasibility and impact of NPM1 MRD detection by clinical NGS. Methods/Case Report IRB approval was obtained. We reviewed the medical record and clinical laboratory data sets from AML patients treated at Moffitt Cancer Center who had NPM1 status assessed by clinical NGS, Testing was performed at LabPMM (San Diego, CA). DNA was extracted, and NPM1 exon 12 was amplified. PCR products were sequenced on an Illumina MiSeq. The clinically reportable assay sensitivity was 5 x 10-5 though lower levels were detected on review of raw data. Kaplan-Meier analysis was conducted for overall survival assessment. Since patients often had multiple tests, we divide patients into those with NPM1+ at any time and NPM1 always negative. Results (if a Case Study enter NA) There was a total of 140 patients. Overall, 346 tests were conducted, with an average of 2.5 tests/patient. There were 85 patients (60%) who underwent serial testing. MRD+ patients (n=80) had a mean age of 66 years, while MRD- patients (n=60) had a mean age of 58 years. MRD+ patients exhibited a mean overall survival of 29.3 months versus 43.6 months for MRD- patients (p=0.005.) Conclusion Through our study encompassing a large patient cohort of 140 patients and nearly 350 testing data points, we confirm the feasibility and clinical utility of NPM1 MRD evaluation by NGS. The significantly poorer survival in patients who were MRD+ at any time during their disease provides a scientific rationale for serial NGS testing to enable risk stratification of NPM1+ AML patients.

Intelligent fault diagnosis of hoisting systems under complex working conditions using deep graph convolutional generative adversarial networks with limited data

Owing to the difficulty of collecting adequate fault data from hoisting systems under complex working conditions, data-driven diagnostic methods suffer from decreased accuracy due to inadequate fault information. To deal with this problem, we introduce an intelligent few-shot fault diagnosis approach using a deep graph convolutional generative adversarial networks (DGCGANs) algorithm. The goal of the proposed method is to acquire a more comprehensive few-shot fault feature information, thus facilitating the generation and augmentation of scarce data. Results of two cases including laboratory and real-world industrial datasets demonstrate the viability and efficacy of our approach for diagnosing few-shot faults. Specifically, the proposed DGCGAN method outperforms existing advanced diagnostics, thereby offering superior accuracy in identifying hoisting system faults with limited data. Finally, the practicality and adaptability of the proposed DGCGAN-based fault diagnosis method are further substantiated through comprehensive ablation studies.

A series of regression models to predict the weathering index of tropical granite rock mass

In the recent past, several weathering indicators have been developed to describe its state of weathering. The state of rock weathering is a useful indicator to estimate the integrity of tropically weathered rock material and mass which weatherability plays an important role in a tropical region. Through a ground assessment tool, the strength and durability of the rock mass could be estimated and complex or adopted to simplify the early prediction of the complex engineering parameter. This paper presents several models of the Weathering Index (WI) using selected significant parameters using statistical analysis. For this purpose, several sites have been chosen to represent granitic rock mass. Forty (40) numbers of samples were collected and tested comprising from four (4) sites in Malaysia. Several laboratory tests have been conducted such as Point Load Index (Is(50)), dry density, Slake Durability 1 (SD1), Slake Durability 2 (SD2) and moisture content. The field and laboratory data sets are used to determine the WI by using simple regression and MLR analysis Significant parameters found to be useful in determining the WI are selected namely SD1, dry density, Is(50), and block volume. These parameters were selected based on stepwise analysis using Statistical Package for the Social Sciences (SPSS). Following the models’ implementation, the models were evaluated and the best prediction model was selected after considering statistical coefficients, such as coefficient of determination (R2), variance account for (VAF), and root mean squared error (RMSE), as well as utilizing a straightforward ranking approach. The findings of this study could contribute to the more accurate prediction of WI using a more simplistic field and laboratory parameters. Therefore, the WI is useful during the initial stages and planning of rock excavation work and provides a good description of weathering grade and rock mass properties, which will affect excavatability in granitic areas.

Tumor Board Visualization: Integrating Clinical and Laboratory Insights.

We present a data visualization tool for tumor boards, merging clinical with molecular and multi-omics data to refine precision oncology decisions. The tool offers a holistic patient perspective, facilitating personalized treatment strategies. By integrating clinical and laboratory datasets, it enables intuitive navigation through complex information. Clinicians are supported in their decision-making by user-friendly visualizations. Future studies are needed to evaluate its real-world impact and usability in precision oncology settings.

EEG-Based Feature Classification Combining 3D-Convolutional Neural Networks with Generative Adversarial Networks for Motor Imagery.

The adoption of convolutional neural networks (CNNs) for decoding electroencephalogram (EEG)-based motor imagery (MI) in brain-computer interfaces has significantly increased recently. The effective extraction of motor imagery features is vital due to the variability among individuals and temporal states. This study introduces a novel network architecture, 3D-convolutional neural network-generative adversarial network (3D-CNN-GAN), for decoding both within-session and cross-session motor imagery. Initially, EEG signals were extracted over various time intervals using a sliding window technique, capturing temporal, frequency, and phase features to construct a temporal-frequency-phase feature (TFPF) three-dimensional feature map. Generative adversarial networks (GANs) were then employed to synthesize artificial data, which, when combined with the original datasets, expanded the data capacity and enhanced functional connectivity. Moreover, GANs proved capable of learning and amplifying the brain connectivity patterns present in the existing data, generating more distinctive brain network features. A compact, two-layer 3D-CNN model was subsequently developed to efficiently decode these TFPF features. Taking into account session and individual differences in EEG data, tests were conducted on both the public GigaDB dataset and the SHU laboratory dataset. On the GigaDB dataset, our 3D-CNN and 3D-CNN-GAN models achieved two-class within-session motor imagery accuracies of 76.49% and 77.03%, respectively, demonstrating the algorithm's effectiveness and the improvement provided by data augmentation. Furthermore, on the SHU dataset, the 3D-CNN and 3D-CNN-GAN models yielded two-class within-session motor imagery accuracies of 67.64% and 71.63%, and cross-session motor imagery accuracies of 58.06% and 63.04%, respectively. The 3D-CNN-GAN algorithm significantly enhances the generalizability of EEG-based motor imagery brain-computer interfaces (BCIs). Additionally, this research offers valuable insights into the potential applications of motor imagery BCIs.

Co-estimation and definition for states of health and charge of lithium-ion batteries using expansion

Accurate and efficient estimation of state of charge (SOC) and state of health (SOH) is crucial for the safe and stable operation of lithium-ion batteries (LIBs). However, achieving accurate SOC–SOH co-estimation remains a challenging task. Meanwhile, the states are primarily defined by capacity, which cannot be directly measured and requires extensive calculations. Hence, a SOH–SOC co-estimation method based on multi-time scale long short-term memory (LSTM) is proposed, which utilizes the expansion characteristics. Additionally, definitions of SOH and SOC are presented based on expansion for the first time, which can obtain the LIBs’ states by direct measurement. To evaluate the necessity of expansion measurements for battery state estimation and definition, the University of Michigan Battery Laboratory (UMBL) dataset is utilized. Then, the relationships between expansion characteristics and SOH/SOC are deeply analyzed. The experimental results demonstrate that the proposed co-estimation method estimates SOC and SOH with high accuracy. The root mean square error (RMSE) and mean absolute error (MAE) are within 0.68 % and 0.51 %, respectively. Moreover, compared with the traditional definitions based on capacity, the MAE/RMSE of new definitions for SOH and SOC are 0.59 %/0.78 % and 5.2 %/6.6 %, respectively.

Herpes simplex virus in infancy: Evaluation of national surveillance case capture.

As herpes simplex virus (HSV) in infancy is not a mandatory notifiable condition in Australia, completeness of ascertainment by the Australian Paediatric Surveillance Unit (APSU) has been difficult to evaluate to date. We evaluated case capture in Queensland (QLD) and Western Australia (WA) using statewide laboratory and clinical data and complementary surveillance data collected via the APSU. HSV polymerase chain reaction positive results in infants (0-3 months) from 2007 to 2017 were obtained from statewide public pathology providers in QLD and WA. Clinical data were extracted from patient records and compared to APSU reported cases. A total of 94 cases of HSV disease in infancy (70 QLD; 24 WA) were identified from laboratory data sets, compared to 36 cases (26 QLD; 10 WA) reported to the APSU. In total there was 102 unique cases identified; 28 cases were common to both data sets (seven skin eye mouth (SEM) disease, 13 central nervous system (CNS)disease and eight disseminated disease). Active surveillance captured 35% (36/102) of cases overall including 74% (14/19) of CNS, 71% (10/14) of disseminated and 17% (12/69) of SEM disease cases, respectively. Surveillance reported cases had a higher case-fatality rate compared to those not reported (14% vs. 3%, P = 0.038). Neurological sequelae at discharge were comparable between the groups. Active surveillance captures one third of hospitalised HSV cases in QLD and WA, including the majority with severe disease. However, morbidity and mortality remain high. Future studies on HSV will rely on observational studies. Enhanced case ascertainment through combined laboratory and surveillance data is essential for better understanding and improving outcomes.

H2LWRF-PDR: An efficient indoor positioning algorithm using a single Wi-Fi access point and Pedestrian Dead Reckoning

Indoor localization is challenging in densely populated urban areas due to the multipath effect, attenuation, noise, and difficulty finding reliable Wi-Fi access points. In urban flats, multiple access points are not easily available or require infrastructure setup, which increases cost. To address the above issues, the article proposes a new algorithm called ‘H2LWRF-PDR’ based on Wi-Fi fingerprinting using a single access point with extended features. This algorithm is designed for static and moving objects. The proposed algorithm first converts the received signal strengths from a single access point into five statistical features used as fingerprints. Then, hierarchical clustering is applied to remove outliers from the fingerprints. Then, a random forest classifier is used to predict the cluster values. Finally, the lowess filters are used to smoothen the output values from the classifier. Furthermore, these outputs are combined with the proposed Pedestrian Dead Reckoning (PDR) algorithm. In the end, a Savitzky–Golay filter is utilized to remove the fluctuations in the trajectories. The proposed approach has been validated in urban flat and laboratory environments and compared with state-of-the-art localization algorithms. The proposed algorithm ‘H2LWRF-PDR’ showed 50% improvements in an urban flat dataset and at least 30% in the laboratory dataset.

Enhanced drift self-calibration of low-cost sensor networks based on cluster and advanced statistical tools

The escalating use of low-cost sensors in environmental monitoring demands effective management of sensor drift and errors. To tackle this challenge, lightweight calibration techniques are essential for accurate sensor readings. This paper presents a novel calibration method for low-cost sensors, prioritizing the detection and correction of sensor drifts. The approach incorporates clustering for efficient task distribution and leverages Inverse Distance Weighting (IDW) for calibration precision. Also, advanced statistical tools, including the Two-Sample Kolmogorov–Smirnov test (TSKS test) and Exponential Moving Average (EMA), assess and enhance sensor data stability based on historical measurements. Additionally, the Root Update Estimator (RUE) is utilized to adjust predicted values and improve the model’s adaptability to changes in the underlying data distribution. Extensive simulation experiments using an Intel Berkeley Research Laboratory (IBRL) dataset affirm the method’s effectiveness in swiftly addressing sensor drifts. These findings advance low-cost sensor calibration, boosting reliability and precision in environmental monitoring.

Augmenting maternal clinical cohort data with administrative laboratory dataset linkages: a validation study.

The use of big data and large language models in healthcare can play a key role in improving patient treatment and healthcare management, especially when applied to large-scale administrative data. A major challenge to achieving this is ensuring that patient confidentiality and personal information is protected. One way to overcome this is by augmenting clinical data with administrative laboratory dataset linkages in order to avoid the use of demographic information. We explored an alternative method to examine patient files from a large administrative dataset in South Africa (the National Health Laboratory Services, or NHLS), by linking external data to the NHLS database using specimen barcodes associated with laboratory tests. This offers us with a deterministic way of performing data linkages without accessing demographic information. In this paper, we quantify the performance metrics of this approach. The linkage of the large NHLS data to external hospital data using specimen barcodes achieved a 95% success. Out of the 1200 records in the validation sample, 87% were exact matches and 9% were matches with typographic correction. The remaining 5% were either complete mismatches or were due to duplicates in the administrative data. The high success rate indicates the reliability of using barcodes for linking data without demographic identifiers. Specimen barcodes are an effective tool for deterministic linking in health data, and may provide a method of creating large, linked data sets without compromising patient confidentiality.