Data Distribution Research Articles

Distribution of air quality data across stratified areas of Port Harcourt metropolis

Distribution of Air Quality Data across seven stratified areas of Port Harcourt Metropolis was carried out. The study utilized a total of 18 parameters from four different air quality datasets obtained from 24 sampling points during field data collection. The sampling points were structured and stratified into residential, industrial, commercial, recreational, transport, dumpsite and abattoir areas. Air quality data were acquired using a multi-digital potable tool, Aerosol Gas Monitor and TESTO Gas Analyser for meteorological data, particulate matters (PM), gaseous emissions and heavy metals. Results showed that the concentrations of air quality data were not evenly distributed across the seven stratified areas, an indication of the influence of location-based activities on the distribution of air quality parameters. The minimum and maximum values of wind speed, temperature and relative humidity were obtained within Residential and Transport Areas, Abattoir and Dumpsite Areas, and, Industrial and Recreational Areas with numerical values of 1.1ms-1 and 3.7ms-1, 27.20C and 350C, and, 67.8% and 923% for wind speed, temperature and relative humidity respectively. The values of TSP, PM2.5 and PM10 ranged from 53 to 255 μg/m3, 13 to 90 μg/m3 and 40 to 169μg/m3 for TSP, PM2.5 and PM10 respectively with the lowest and highest values obtained within Residential and Dumpsite Areas respectively. The concentrations of NO2 and SO2 exceeded the standards of WHO, NAAQS and FMEnv in Industrial, Dumpsite and Abattoir Areas. Lead ( Pb) showed very high values within Dumpsite Area (0.954mg/kg), Industrial Area (0.372mg/kg) and Transport Area (0.077mg/kg).

Detection of Novel Classes in Dynamic Data Streams

Every second, a huge volume of multi-dimensional data is generated in fields such as Social Networking, Industrial Internet of Things, Stock market and E-commerce applications. Knowledge and pattern extraction are a challenging task in the evolving nature of data stream. Major issues are (i) ‘concept drift’ occurs as a result of pattern changes in the data distribution and (ii) ‘concept evolution’ occurs when a new class evolves in the data stream. These issues degrade the performance of learning models. In this paper, we focus on detection of concept evolution and enhance the performance of classifiers. For this, we propose a new model to identify novel classes, namely, Detection of Novel Classes (DNC). The proposed method adopts long short term memory to continuously observe the streaming data in order to detect emerging classes. The continuous monitoring allows the model to distinguish between existing classes and the novel classes which save time and memory. Also, the proposed method is demonstrated for identifying more than one novel class. The experiments are performed over seven different datasets. The results confirm the efficiency is increased ranging from 6% to 34% by the proposed method in identifying new concepts in the evolving data stream than the existing methods available in the literature.

Clustering by detecting skeletal structure and identifying density fluctuation

Clustering is one of the most important techniques for unsupervised learning, it tries to divide points into different clusters without any priori knowledge of data. Therefore, several criterions for clustering algorithm are as follows: 1. Handling clusters with arbitrary shape and various density; 2. Finding cluster centers automatically; 3. Low parameter sensitivity and computational complexity. In this context, a novel algorithm namely clustering by detecting skeletal structure and identifying density fluctuation (CSSDF) was presented. In CSSDF, an efficient strategy based on density and local information of neighborhood is firstly proposed to detect the skeletal structure, which can collect the local information and identify the rough distribution of data. With the identified distribution information, a method takes expanded neighborhood and density fluctuation into consideration is proposed to further collect global information of data, which can assign all skeleton points and find cluster centers. To sum up, CSSDF can not only discover the underlying structure of data regardless of its’ distribution, but also ensure the correct assignment of all skeleton points and thus lead to a satisfying clustering performance. In addition, the computational complexity of the proposed approach is O(nlogn), which makes it possible to deal with some large clustering problem.

Evaluating the effectiveness of quantitative pupillometry in assessing dynamic aerobic training intensity

Sports injuries often arise from improper scheduling of exercise loads, and timely assessment of these loads is essential for minimizing injury risk. This article investigates the validity of using changes in pupillary light reflex (PLR) during dynamic aerobic training as a novel approach to evaluating exercise load. Dynamic aerobic training was conducted on a power bicycle for 15 min. With a 3-minute interval as the demarcation line, PLR measurement was performed before training and heart rate was recorded throughout the process. The Rating of Perceived Exertion (RPE) scale invented by Borg was used for scoring before training and after training. The normal distribution of data was confirmed through the Shapiro-Wilk test. Pearson correlation analysis was used to quantify the correlation between variables. The Receiver Operating Characteristic (ROC) curve and the area under the curve (AUC) analysis were used to determine the indicators of exercise load. The optimal threshold of the indicators was calculated through the Youden index to evaluate sensitivity and specificity. Thirty male second-tier athletes with a mean age of 23.66 ± 2.21 years, a mean height of 175.3 ± 6.5 cm, and a mean weight of 68.99 ± 10.35 kg participated in this study. Based on the RPE scale results, it was confirmed that the 15-minute dynamic aerobic exercise successfully elicited varying levels of perceived exertion among the athletes. The findings of this study indicate significant changes in PLR and heart rate (HR) with increasing exercise duration and external load. There were strong correlations between RPE and maximum constriction velocity (MCV) (|r| = 0.8309, p < 0.001, negative correlation), maximum diameter (INIT) (r = 0.7641, p < 0.001, positive correlation), time to reach 75% recovery (T75) (|r| = 0.7289, p < 0.001, negative correlation), and HR (r = 0.8170, p < 0.001, positive correlation). Additionally, the results suggest that MCV is the most significant potential indicator for detecting internal load, exhibiting high specificity and sensitivity (AUC = 0.8509, p < 0.001). Further analysis using the Youden index identified 5.07 mm/s as the optimal cutoff value for MCV, indicating that when MCV ≤ 5.07 mm/s, the athletes’ internal load has reached an “Intense” state. PLR may be a potential indicator for assessing internal load Further investigation could involve developing a non-invasive exercise load detection system based on pupillary variable indicators, providing a valuable new approach for accurately measuring exercise load.

Data Delivery Indicators in EIDA: Designing a Consistent Metrics System in a Distributed Services Environment

The European Integrated Data Archive (EIDA) is a data service within Observatories and Research Facilities for European Seismology (ORFEUS) which distributes seismological waveform data across, presently, 12 federated data centres, so-called EIDA nodes. EIDA is also integrated into the European Research Infrastructure EPOS (European Plate Observing System). The increasing need of quantifying the scientific impact of such Research Infrastructures at all levels of operations has led EIDA to develop a unified system able to provide global indicators for data delivery across all EIDA nodes. To achieve this goal, EIDA implemented a system where the numbers are collected and aggregated by each EIDA node and ingested in a centralised database, accessible through an online API. The successful implementation of the system stems from carefully identifying the relevant indicators for well-defined groups of users. The implementation combines simplicity and robustness whilst respecting the distributed design of EIDA. The architecture and implementation choices may be of interest to other multi-site data distribution research infrastructures that face the challenge of providing meaningful key performance indicators.

Tabular Federated Learning to detect cyber faults in smart buildings

By incorporating artificial intelligence into applications, everyone in the current circumstance has become intelligent, thereby reducing the burden of incessant interruption or human control. In today’s environment, most of the hardware infrastructure in buildings is connected to the internet, transforming the building infrastructure into a smart building infrastructure. In a similar vein, it should be noted that intelligent building infrastructure is susceptible to cyber-induced defects, and the issue of data privacy is a significant worry within the realm of collaborative learning. The primary objective of this study is to devise and implement an Attentive Interpretable Tabular-based Federated Learning methodology for safeguarding data privacy while detecting cyber-induced problems in the infrastructure of intelligent buildings. In this paper, Federated Learning ecosystem-based deep learning models are used to find and describe cyber-induced faults and vulnerabilities. The suggested system will be evaluated using various measures, including accuracy, precision, recall, and losses. Additionally, the built ecosystem is examined using various data distributions to determine whether the outcomes are stable.

Source apportionment of particle number size distribution at the street canyon and urban background sites

Abstract. Particle size is one of the key factors influencing how aerosol particles affect their climate and health effects. Therefore, a better understanding of particle size distributions from various sources is crucial. In urban environments, aerosols are produced in a large number of varying processes and conditions. This study intended to develop the source apportionment of urban aerosols by utilising a novel approach to positive matrix factorisation (PMF). The particle source profiles were detected in particle number size distribution data measured simultaneously in a street canyon and at a nearby urban background station between February 2015 and June 2019 in Helsinki, southern Finland. The novelty of the method is combining the data from both sites and finding profiles for the unified data. Five aerosol sources were found. Four of them were detected at both of the stations: slightly aged traffic (TRA2), secondary combustion aerosol (SCA), secondary aerosol (SecA), and long-range-transported aerosol (LRT). One of the sources, fresh traffic (TRA1) was only detected at a street canyon. The factors were identified based on available auxiliary data. Additionally, the trends of the found factors were studied, and statistically significant decreasing trends were found for TRA1 and SecA. A statistically significant increasing trend was found for TRA2. This work implies that traffic-related aerosols remain important in urban environments and that aerosol sources can be detected using only particle number size distribution data as input in the PMF method.

Estimation of Longwave Radiation Intensity Emitted from Urban Obstacles in Each Direction Using Drone-Based Photogrammetry

Longwave radiation is a crucial factor affecting human thermal comfort and thermal stress, especially in outdoor spaces in summer, owing to the vast effect of longwave radiation emitted from high-heated asphalt roads, building walls, and automobiles. Although controlling the longwave radiation environment to improve thermal comfort in summer is crucial, the prediction of the longwave radiation environment is frequently conducted only at the assessment stage of the final proposal because of the high computational cost of radiation calculations and unsteady heat balance analysis considering multiple reflections. This is a significant constraint for the design of urban and architectural environments. A previous study proposed a method to rapidly estimate the longwave radiation environment based on a point-by-point method with longwave radiation intensity distributions of the heat sources. To use this method, 3D models of the geographical objects in urban areas, such as buildings and trees, must be accurately generated, and these models should have information on the longwave radiation emitted in each direction from each object. However, no specific examples of a 3D model and longwave radiation intensity distribution have been presented. In this study, a 3D modeling method for geographical objects in urban areas with longwave radiation information based on drones and photogrammetric techniques was utilized. Moreover, a 3D model of a small-scale building was generated. A longwave radiation intensity distribution was produced for the building. Based on the distribution data, the directional characteristics of longwave radiation were discussed, and the availability of the proposed method was assessed.

×Gymnigritella suaveolens (Orchidaceae), a New Natural Hybrid to the Flora of Serbia

×Gymnigritella suaveolens (Orchidaceae), a natural hybrid between Gymnadenia conopsea and Nigritella rhellicani, was found at Mt Kopaonik for the first time in Serbia, representing its single known locality in the Central Balkans. Morphological characteristics, distribution data, habitat and ecological preferences are indicated. The hybrid was found at 1552 m a.s.l., on sericite schists, as a member of the Festuco-Deschampsietum flexuosae grassland community. Two hybrid specimens were recorded at the site where the two parental species grow in sympatry, and where the population size of G. conopsea was larger than the population size of N. rhellicani.

THE ODD LOMAX TOPP LEONE DISTRIBUTION: PROPERTIES AND APPLICATION

Lifetime distributions are parametric models used in statistical analyses of time-to-event data. Several probability distributions have been very used in literature to model lifetime data sets which have been useful in the analysis of lifetime data, but in most cases, they are not flexible enough to analyze some complex lifetime data in practice. Due to the importance of these lifetime distributions in modeling real lifetime data, there has several modifications and generalization of lifetime distributions, particularly the Lomax distribution to develop more flexible distributions to address the drawback presented by some classical lifetime distributions including the Lomax distribution. Several attempts have been made by researchers to generalize classical lifetime distributions which offer more flexibility in modeling lifetime data. Our interest in this study is to introduce a new extension of Lomax distribution called the “The odd lomax Topp-Leone distribution” which is bounded on a unit interval data such that its flexibility can accommodate increasing, decreasing, right skewed, left skewed, symmetric and u-shaped data sets. An application to a real lifetime data set clearly shows that the proposed extension of the Lomax distribution is a better alternative to some existing distributions bounded on a unit interval.

USING RETROSPECTIVE DATA TO ASSESS THE UNCERTAINTY OF INDICATORS OF BIOLOGICAL SAFETY OF FOOD AND FEED RAW MATERIALS

The results of the analysis of the advantages and disadvantages of the use of retrospective data for the implementation of the evaluation of uncertainty in the measurement of indicators of biological safety of food and feed raw materials are given. The model measurement procedure used quantitative determination of genetically modified organisms by means of polymerase chain reaction in real time 250 measurement results of certified reference material with a content of 0.1% genetically modified soybean line obtained under conditions of intra-laboratory reproducibility and 10 results of relevant inter-laboratory comparisons with the participation accredited provider. The suitability of retrospective data was assessed by the Shapiro-Wilk criterion and statistical controllability analysis using standardized score charts and modified Shewhart charts, uncertainty by 4 methods described in general and branch international guidelines and regulations. The results of using a combination of modified Shewhart maps demonstrate the acceptability of this approach for establishing the suitability of retrospective measurement results as input data for uncertainty assessment. By integrating additional "fitness limits" to a set of standardized control limits, this analysis acquires the ability to simultaneously establish not only stability, through the interpretation of geometric patterns, but also compliance with specific criteria. Using this approach, objective evidence of the suitability of retrospective data for estimating measurement uncertainty was obtained. The distribution of retrospective data obtained under conditions of intralaboratory reproducibility is assumed to be normal. As a result of the assessment of statistical controllability and compliance with the established criteria, objective evidence of the suitability of the data for uncertainty assessment was obtained. Analysis of uncertainty intervals of subgroups with the volume of 25 measurements, using 4 assessment methods, demonstrated significant variability in the results of measuring biological safety indicators. The uncertainty interval could narrow or widen by almost 100% of the value within fifty measurements. Median values obtained using different uncertainty estimation methods were 2.69%, 22.69%, 39.23, and 43.08%. This variability is due to the limited coverage of sources of uncertainty, which is inherent in each of the analyzed methods. The most optimal method is the evaluation based on the routine measurement of the certified reference material. Retrospective results of routine measurement of certified reference material and interlaboratory comparisons are an effective source of input data for assessing the uncertainty of the results of measuring biological safety indicators of agricultural raw materials. There is a need for further research to establish an assessment model that will provide an opportunity to take into account the optimal number of influential sources of uncertainty that are inherent in biological systems and cannot be simultaneously taken into account using existing approaches offered by standard assessment methods.

Multi-step reconstruction of radio-interferometric images

The large aperture arrays for the currently under construction SKA Observatory (SKAO) will allow for observations of the universe in the radio spectrum at unprecedented resolution and sensitivity. However, these telescopes will produce data on the scale of exabytes, introducing a slew of hardware and software design challenges. This paper proposes a multi-step image reconstruction framework that allows for partitioning of visibility data by baseline length. This enables more flexible data distribution and parallelization, aiding in processing radio-astronomical observations within given constraints. Additionally, as each step of the framework only relies on a subset of the total visibilities, one can perform reconstruction progressively, with the initial step performed on the SKAO Science Data Processors and the second on local clusters. The multi-step reconstruction is separated into two steps. First a low-resolution image is reconstructed with only short-baseline visibilities, and then using this image together with the long-baseline visibilities, the full-resolution image is reconstructed. The proposed method only operates in the minor cycle, and it can be easily integrated into existing imaging pipelines. We show that our proposed method allows for partitioning of visibilities by baseline without introducing significant additional drawbacks, reconstructing images of similar quality within similar numbers of major cycles compared to a single-step all-baselines approach that uses the same reconstruction method as well as compared to multi-scale CLEAN.

Modeling Groundwater Levels in California's Central Valley by Hierarchical Gaussian Process and Neural Network Regression

AbstractModeling groundwater levels continuously across California's Central Valley (CV) hydrological system is challenging due to low‐quality well data which is sparsely and noisily sampled across time and space. The lack of consistent well data makes it difficult to evaluate the impact of 2017 and 2019 wet years on CV groundwater following a severe drought during 2012–2015. A novel machine learning method is formulated for modeling groundwater levels by learning from a 3D lithological texture model of the CV aquifer. The proposed formulation performs multivariate regression by combining Gaussian processes (GP) and deep neural networks (DNN). The hierarchical modeling approach constitutes training the DNN to learn a lithologically informed latent space where non‐parametric regression with GP is performed. We demonstrate the efficacy of GP‐DNN regression for modeling non‐stationary features in the well data with fast and reliable uncertainty quantification, as validated to be statistically consistent with the empirical data distribution from 90 blind wells across CV. We show how the model predictions may be used to supplement hydrological understanding of aquifer responses in basins with irregular well data. Our results indicate that on average the 2017 and 2019 wet years in California were largely ineffective in replenishing the groundwater loss caused during previous drought years.

Comparison of Machine Learning Models and Feature Importance Investigation of Intelligent Fault Diagnosis Methods for Robots Based on Datasets Across Various Distributions

Intelligent fault detection is an important component of the industrial and automation fields. However, conventional research on intelligent fault detection mainly focuses on industrial production equipment, while there is little research on intelligent fault detection scenarios for robots. Based on a hexapod robot joints dataset, this paper investigates intelligent fault diagnosis tasks in the field of robotics. Firstly, the dataset is clustered into two new datasets with different distributions through k-means method, which is used to simulate the practicality of imbalanced distribution between healthy and fault data. Afterwards, several multioutput machine learning classification models were established to predict robot joints with faults. In two datasets with different distributions, the larger one is used as the training set and the smaller one is used as the testing set. The article compares the performance of these models with prediction accuracy as the main indicator. And based on the results, the paper selects the model with the highest accuracy for further exploration of feature importance. Finally, the article explains the significance of the results and analyzes possible reasons. The experimental results show that the random forest model better overcomes the problem of data distribution differences and has the highest accuracy. In the random forest model, the importance of position data representing position error is higher than that of slope with respect to the axis data representing angle error. This result may be related to the distribution of feature values and the fact that position data contains more crucial information.

A review on adversarial–based deep transfer learning mechanical fault diagnosis

Mechanical equipment is a vital foundational support for promoting national economic development and is widely utilized in key sectors such as aerospace, shipping, construction machinery, energy, petrochemicals, and robotics. With the advancement of artificial intelligence and industrial intelligence, industrial big data and its intelligent analysis provide robust support for fault prediction and health management of equipment. Building on existing research, intelligent diagnostics for mechanical equipment based on deep learning have gained significant attention and application. However, the success of big data relies on comprehensive fault data, which is challenging to obtain in practical applications where continuous equipment operation is essential. Moreover, mechanical equipment often operates under varying conditions, leading to different data distributions for training and testing. This discrepancy can result in low diagnostic accuracy or even failure of deep learning methods. Deep Transfer Learning (DTL) is an emerging machine learning paradigm that not only leverages the advantages of deep learning (DL) in feature representation but also harnesses the strengths of transfer learning (TL) in knowledge transfer. Consequently, DTL techniques can make deep learning-based fault diagnosis methods more reliable, robust, and applicable, leading to extensive development and research in the field of intelligent fault diagnosis. This paper primarily introduces adversarial-based deep transfer learning (ADTL) models, which are fundamentally based on Generative Adversarial Network (GAN). We provide a detailed discussion of the main applications of ADTL and its recent developments in intelligent fault diagnosis, along with some future challenges and prospects.

Applying minirhizotrons to observe spatiotemporal variations in rooting depth and distribution in agroecosystems to improve the performance of hydrological models

AbstractTo understand and explain soil moisture dynamics, the role of the vegetation is crucial. Hydrological processes in agricultural soils are strongly affected by rooting depth and root distribution. We present a new approach to monitor and model root dynamics and its influence on soil moisture using minirhizotrons combined with phenological observations. Field setups consist of a portable root scanner and acrylic glass tubes installed in the soil at the start of the growing season. 360° scans of soil and roots are taken regularly at different depths in the tubes. Root traits are identified automatically for each soil layer and complemented by observations of aboveground plant phenology. Results from minirhizotron data collected at an agrometeorological observatory in Germany show for both cereal and rapeseed (Brassica napus L.) crops a higher root density in deeper soil layers and a lower density near the soil surface when compared to literature data. An opposite picture emerged for maize (Zea mays L.) and potato (Solanum tuberosum L.), whereas vertical root distribution in sugar beet (Beta vulgaris subsp. vulgaris) had a different seasonal course than expected from literature. Applying the new root distribution data in calculations of the soil water balance resulted in differences of more than 3% in absolute volumetric soil water content. A comparison with in situ measurements of volumetric soil moisture at 20‐ and 50‐cm depth revealed a significant improvement of the model results due to the new parameterization. Thus, we argue that minirhizotrons constitute a useful supplement to hydrological observatories and can help understand and predict soil moisture dynamics in the critical zone.

Enhanced fish species classification using dynamic multilayer perceptron and transformer encoders with extra distribution data

Enhanced fish species classification using dynamic multilayer perceptron and transformer encoders with extra distribution data

Effect of sacubitril/valsartan and dapagliflozin on athletic performance; can the popular cardiac medications of recent years be used as doping agents?

Abstract Background/Introduction Recent guidelines have highlighted the positive impacts of sacubitril/valsartan and dapagliflozin on heart failure management [1]. Given their potential misuse as doping agents in professional sports, this study evaluates their effects on athletic performance. Purpose To investigate the effects of sacubitril/valsartan and dapagliflozin on athletic performance and cardiac functions in a rodent model. Methods The study had a randomized double-blind design. 24 Sprague-Dawley male rats aged 4 months, divided into control, sacubitril/valsartan, and dapagliflozin groups. The rats were weighed at the start of the experiment. The medications (dapagliflozin 1,5 mg/kg/1 ml/once a day, sacubitril/valsartan 60 mg/kg/1 ml/once a day to their respective groups, and normal saline for control group) were administered via gastric gavage for 30 days. The rats were weighed, examined with transthoracic echocardiography and put on rotarod at the start of the experiment, and on 15th and 30th days. The rats were put on forced swimming tests for 20 days. Exhaustion, loss of coordinated movements and failure to surface for 3 seconds after submersion in the water were defined as indications for ending the test as per the guidelines regarding rat exercise testing [2]. M-mode and Doppler measurements, forced swimming test durations, rotarod durations and weight were recorded on 0th, 15th and 30th days. Results Initial performance metrics, including echocardiography, weight, and rotarod tests, showed no significant differences among the groups at baseline. The distributions in data were non-normal. Over the course of the study, median swimming times significantly differed from the 9th session, with dapagliflozin-treated rats exhibiting a substantial increase in endurance. Specifically, dapagliflozin group's swimming times increased to a median of 3580 seconds by the 20th session, compared to 2382 seconds in the control group and 2591 seconds in the sacubitril/valsartan group, indicating a pronounced improvement in exercise capacity (P&amp;lt;0.0001)(Figure-1). Echocardiographic assessments revealed enhanced cardiac output and ejection fraction, particularly in the sacubitril/valsartan group, suggesting increased cardiac efficiency and potential athletic performance enhancement. Conclusion(s) The study demonstrates a significant improvement in athletic performance with dapagliflozin compared to sacubitril/valsartan. These findings suggest a potential for misuse in sports doping, emphasizing the need for stringent regulation and monitoring within competitive athletics.Figure-1

A New Natural Language Processing-Inspired Methodology (Detection, Initial Characterization, and Semantic Characterization) to Investigate Temporal Shifts (Drifts) in Health Care Data: Quantitative Study.

Proper analysis and interpretation of health care data can significantly improve patient outcomes by enhancing services and revealing the impacts of new technologies and treatments. Understanding the substantial impact of temporal shifts in these data is crucial. For example, COVID-19 vaccination initially lowered the mean age of at-risk patients and later changed the characteristics of those who died. This highlights the importance of understanding these shifts for assessing factors that affect patient outcomes. This study aims to propose detection, initial characterization, and semantic characterization (DIS), a new methodology for analyzingchanges in health outcomes and variables over time while discovering contextual changes for outcomes in large volumes of data. The DIS methodology involves 3 steps: detection, initial characterization, and semantic characterization. Detection uses metrics such as Jensen-Shannon divergence to identify significant data drifts. Initial characterization offers a global analysis of changes in data distribution and predictive feature significance over time. Semantic characterization uses natural language processing-inspired techniques to understand the local context of these changes, helping identify factors driving changes in patient outcomes. By integrating the outcomes from these 3 steps, our results can identify specific factors (eg, interventions and modifications in health care practices) that drive changes in patient outcomes. DIS was applied to the Brazilian COVID-19 Registry and the Medical Information Mart for Intensive Care, version IV (MIMIC-IV) data sets. Our approach allowed us to (1) identify drifts effectively, especially using metrics such as the Jensen-Shannon divergence, and (2) uncover reasons for the decline in overall mortality in both the COVID-19 and MIMIC-IV data sets, as well as changes in the cooccurrence between different diseases and this particular outcome. Factors such as vaccination during the COVID-19 pandemic and reduced iatrogenic events and cancer-related deaths in MIMIC-IV were highlighted. The methodology also pinpointed shifts in patient demographics and disease patterns, providing insights into the evolving health care landscape during the study period. We developed a novel methodology combining machine learningand natural language processing techniques to detect, characterize, and understand temporal shifts in health care data. This understanding can enhance predictive algorithms, improve patient outcomes, and optimize health care resource allocation, ultimatelyimproving the effectiveness of machine learning predictive algorithms applied to health care data. Our methodology can be applied to a variety of scenarios beyond those discussed in this paper.

Lifelong QoT prediction: an adaptation to real-world optical networks

Predicting the quality of transmission (QoT) is a critical task in the management and optimization of modern fiber-optic networks. Traditional machine learning (ML) QoT prediction models, typically trained on pre-collected datasets, are designed to make long-term predictions once deployed. However, this static training strategy often falls short in the face of time-dependent network evolution and variations. We identify the root cause of these shortcomings as shifts in data distribution, which are not accounted for in conventional static models. In response to these challenges, we propose an online continual learning pipeline that is specifically designed for stable QoT prediction in optical networks. This pipeline directly addresses the problem of distribution shifts by continuously updating the prediction model in response to real-time network data. We explore and compare various strategies within this framework and demonstrate that the integration of the adaptive retraining strategy and the regularized online continual learning algorithm (OCL-REG) significantly enhances the QoT prediction stability while optimizing the resource efficiency. OCL-REG demonstrates superior adaptability and stability, achieving an average cumulative mean squared error (C-MSE) of 0.19 on a testbench with a data distribution shift sequence containing 1000 batches. Moreover, the OCL-REG model requires fewer samples for adaptation, averaging around 107 samples, compared to the conventional retraining strategy, which requires an average of 253 samples. Our approach presents a paradigm shift in QoT prediction, moving from a static to a dynamic, lifelong learning model that is more attuned to the evolving realities of real fiber-optic networks.