Temporal Data Model Research Articles

ClinicalGAN: powering patient monitoring in clinical trials with patient digital twins

Conducting clinical trials is becoming increasingly challenging lately due to spiraling costs, increased time to market, and high failure rates. Patient recruitment and retention is one of the key challenges that impact 90% of the trials directly. While a lot of attention has been given to optimizing patient recruitment, limited progress has been made towards developing comprehensive clinical trial monitoring systems to determine patients at risk and potentially improve patient retention through the right intervention at the right time. Earlier research in patient retention primarily focused on using deterministic frameworks to model the inherently stochastic patient journey process. Existing generative approaches to model temporal data such as TimeGAN or CRBM , face challenges and fail to address key requirements such as personalized generation, variable patient journey, and multi-variate time-series needed to model patient digital twin. In response to these challenges, current research proposes ClinicalGAN to enable patient level generation, effectively creating a patient’s digital twin. ClinicalGAN provides capabilities for: (a) patient-level personalized generation by utilizing patient meta-data for conditional generation; (b) dynamic termination prediction to enable pro-active patient monitoring for improved patient retention; (c) multi-variate time-series training to incorporate relationship and dependencies among different tests measures captured during patient journey. The proposed solution is validated on two Alzheimer’s clinical trial datasets and the results are benchmarked across multiple dimensions of generation quality. Empirical results demonstrate that the proposed ClinicalGAN outperforms the SOTA approach by 3–4×\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\ imes $$\\end{document} on average across all the generation quality metrics. Furthermore, the proposed architecture is shown to outperform predictive methods at the task of drop-off prediction significantly (5–10% MAPE scores).

SERT: A transformer based model for multivariate temporal sensor data with missing values for environmental monitoring

Environmental monitoring is crucial to our understanding of climate change, biodiversity loss and pollution. The availability of large-scale spatio-temporal data from sources such as sensors and satellites allows us to develop sophisticated models for forecasting and understanding key drivers. However, the data collected from sensors often contain missing values due to faulty equipment or maintenance issues. The missing values rarely occur simultaneously leading to data that are multivariate misaligned sparse time series. We propose two models that are capable of performing multivariate spatio-temporal forecasting while handling missing data naturally without the need for imputation. The first model is a transformer-based model, which we name SERT (Spatio-temporal Encoder Representations from Transformers). The second is a simpler model named SST-ANN (Sparse Spatio-Temporal Artificial Neural Network) which is capable of providing interpretable results. We conduct extensive experiments on two different datasets for multivariate spatio-temporal forecasting and show that our models have competitive or superior performance to those at the state-of-the-art.

Temporal Paths in Real-World Sensor Networks

Sensor networks are used in an increasing number and variety of application areas, like traffic control or river monitoring. Sensors in these networks measure parameters of interest defined by domain experts and send these measurements to a central location for storage, viewing and analysis. Temporal graph data models, whose nodes contain time-series data reported by the sensors, have been proposed to model and analyze these networks in order to take informed and timely decisions on their operation. Temporal paths are first-class citizens in this model and some classes of them have been identified in the literature. Queries aimed at finding these paths are denoted as (temporal) path queries. In spite of these efforts, many interesting problems remain open and, in this work, we aim at answering some of them. More concretely, we characterize the classes of temporal paths that can be defined in a sensor network in terms of the well-known Allen’s temporal algebra. We also show that, out of the 8192 possible interval relations in this algebra, only 11 satisfy two desirable properties that we define: transitivity and robustness. We show how these properties and the paths that satisfy them are relevant in practice by means of a real-world use case consisting of an analysis of salinity that appears close to the Scheldt river in Flanders, Belgium, during high tides occurring in the North Sea.

A Temporal Variable-Scale Clustering Method on Feature Identification for Policy Public-Opinion Management

The development of various digital social network platforms has caused public opinion to play an increasingly important role in the policy making process. However, due to the fact that public opinion hotspots usually change rapidly (such as the phenomenon of public opinion inversion), both the behaviour feature and demand feature of netizens included in the public opinion often vary over time. Therefore, this paper focuses on the feature identification problem of public opinion simultaneously considering the multiple observation time intervals and key time points, in order to support the management of policy-focused online public opinion. According to the variable-scale data analysis theory, the temporal scale space model is established to describe candidate temporal observation scales, which are organized following the time points of relevant policy promulgation (policy time points). After proposing the multi-scale temporal data model, a temporal variable-scale clustering method (T-VSC) is put forward. Compared to the traditional numerical variable-scale clustering method, the proposed T-VSC enables to combine the subjective attention of decision-makers and objective timeliness of public opinion data together during the scale transformation process. The case study collects 48552 raw public opinion data on the double-reduction education policy from Sina Weibo platform during Jan 2023 to Nov 2023. Experimental results indicate that the proposed T-VSC method could divide netizens that participate in the dissemination of policy-focused public opinion into clusters with low behavioural granularity deviation on the satisfied observation time scales, and identify the differentiated demand feature of each netizen cluster at policy time points, which could be applied to build the timely and efficient digital public dialogue mechanism.

Diffusion Models: A Comprehensive Survey of Methods and Applications

Diffusion models have emerged as a powerful new family of deep generative models with record-breaking performance in many applications, including image synthesis, video generation, and molecule design. In this survey, we provide an overview of the rapidly expanding body of work on diffusion models, categorizing the research into three key areas: efficient sampling, improved likelihood estimation, and handling data with special structures. We also discuss the potential for combining diffusion models with other generative models for enhanced results. We further review the wide-ranging applications of diffusion models in fields spanning from computer vision, natural language processing, temporal data modeling, to interdisciplinary applications in other scientific disciplines. This survey aims to provide a contextualized, in-depth look at the state of diffusion models, identifying the key areas of focus and pointing to potential areas for further exploration. Github: https://github.com/YangLing0818/Diffusion-Models-Papers-Survey-Taxonomy

Air Quality Data Acquisition Through Temporal Data Modeling

The paper presents a novel temporal data model for acquiring air quality data. The proposed model uses the free and open-source Postgres database with tuple time stamping, resulting in rapid and effective data extraction. The conventional relational database SQL server for data extraction is used in this paper as the foundation for an air quality temporal database model. The air quality data set collected for MDU Rohtak (source: Central Control Room for Air Quality Management - All India) is utilized to test and determine the outcomes of the proposed model. Valid time is used as the time dimension for capturing data values, together with tuple timestamping. The Postgres "tsrange" datatype is used to record the timestamp. To eliminate data duplication, the dataset is cleaned up and normalized. Using the air quality temporal data model, AQI data at various time points is effectively extracted. The present model data extraction is compared with the conventional relational data model using SQL Server database. The air quality data extraction process takes a remarkably minimal amount of time, with an average of 23% lesser time than SQL server database. It takes only a few milliseconds to extract the AQI data, and the results of the experiment are ready immediately after that. The suggested model is helpful in decision-making and offers decision-makers useful information and the tool they need to enhance air quality. The results are relevant to the study of the AQI components by different pollution management agencies like central and state pollution control boards, national green tribunal and Ministry of the Environment for efficient air pollution control measures.

Analysing River Systems with Time Series Data Using Path Queries in Graph Databases

Transportation networks are used in many application areas, like traffic control or river monitoring. For this purpose, sensors are placed in strategic points in the network and they send their data to a central location for storage, viewing and analysis. Recent work proposed graph databases to represent transportation networks, since these networks can change over time, a temporal graph data model is required to keep track of these changes. In this model, time-series data are represented as properties of nodes in the network, and nodes and edges are timestamped with their validity intervals. In this paper, we show that transportation networks can be represented and queried using temporal graph databases and temporal graph query languages. Many interesting situations can be captured by the temporal paths supported by this model. To achieve the above, we extend a recently introduced temporal graph data model and its high-level query language T-GQL to support time series in the nodes of the graph, redefine temporal paths and study and implement new kinds of paths, namely Flow paths and Backwards Flow paths. Further, we analyze a real-world case, using a portion of the Yser river in the Flanders’ river system in Belgium, where some nodes are equipped with sensors while other ones are not. We model this river as a temporal graph, implement it using real data provided by the sensors, and discover interesting temporal paths based on the electric conductivity parameter, that can be used in a decision support environment, by experts for analyzing water quality across time.

Perkembangan Model Data Temporal serta Implementasinya pada Database Management Systems

This essay examines how temporal data models are created and how they are integrated into database management systems. The well-known Relational Data Model’s extension, the Temporal Relational Data Model, is discussed. The application of this temporal data model in database management systems is also researched. The Historical Relational Data Model adds timestamps to attributes, and the Temporal Relational Model adds timestamps to tuples. These two approaches make up the temporal data model. It has become apparent via the implementation of this temporal data model that not all temporal data ideas are applicable to database management systems. IBM DB2 has explicitly integrated the idea of time stamps, but not the idea of PERIOD data type. While Teradata has implemented the PERIOD data type, but has not yet implemented the concept of explicit timestamps.

Memorization and prediction capability of the interacting phase oscillators

Nonlinear dynamical systems, such as well-tuned recurrent neural networks, have proved a powerful tool for modeling temporal data. However, tuning such models to achieve optimal performance remains an outstanding challenge, not least because of the complex behaviors that emerge from interacting microscopic constituents. Here, we consider a minimal model of two interacting phase oscillators coupled to a thermal bath and driven by a common signal. We quantify the memory and predictive capability of the system with the mutual information between the phases of oscillators and the signals at different times. We show that the interaction between oscillators can increase the information between the system and the movement. We attribute this behavior to an increase in the effective signal-to-noise ratio, resulting from a stronger correlation between the oscillators. We also demonstrate that heterogeneity in the natural frequencies of the oscillators can further increase the mutual information though more efficient uses of oscillator states.Our work offers the first step toward a systematic approach to optimizing interacting nonlinear dynamical systems for memorizing and predicting temporal patterns.

An efficient implementation for spatial–temporal Gaussian process regression and its applications

Spatial–temporal Gaussian process regression is a popular method for spatial–temporal data modeling. Its state-of-art implementation is based on the state-space model realization of the spatial–temporal Gaussian process and its corresponding Kalman filter and smoother, and has computational complexity O(NM3), where N and M are the number of time instants and spatial input locations, respectively, and thus can only be applied to data with large N but relatively small M. In this paper, our primary goal is to show that by exploring the Kronecker structure of the state-space model realization of the spatial–temporal Gaussian process, it is possible to further reduce the computational complexity to O(M3+NM2) and thus the proposed implementation can be applied to data with large N and moderately large M. The proposed implementation is illustrated over applications in weather data prediction and spatially-distributed system identification. Our secondary goal is to design a kernel for both the Colorado precipitation data and the GHCN temperature data, such that while having more efficient implementation, better prediction performance can also be achieved than the state-of-art result.

Effectiveness of the use of algorithms and methods of artificial technologies for sign language recognition for people with disabilities

According to WHO, the number of people with disabilities in the world has exceeded 1 billion. At the same time, 80 percent of all people with disabilities live in developing countries. In this regard, the demand for the use of applications for people with disabilities is growing every day. The paper deals with neural network methods like MediaPipe Holistic and the LSTM module for determining the sign language of people with disabilities. MediaPipe has demonstrated unprecedented low latency and high tracking accuracy in real-world scenarios thanks to built-in monitoring solutions. Therefore, MediaPipe Holistic was used in this work, which combines pose, hand, and face control with detailed levels. The main purpose of this paper is to show the effectiveness of the HAR algorithm for recognizing human actions, based on the architecture of in-depth learning for classifying actions into seven different classes. The main problem of this paper is the high level of recognition of the sign language of people with disabilities when implementing their work in cross-platform applications, web applications, social networks that facilitate the daily life of people with disabilities and interact with society. To solve this problem, an algorithm was used that combines the architecture of a convolutional neural network (CNN) and long short-term memory (LSTM) to study spatial and temporal capabilities from three-dimensional skeletal data taken only from a Microsoft Kinect camera. This combination allows you to take advantage of LSTM when modeling temporal data and CNN when modeling spatial data. The results obtained based on calculations carried out by adding a new layer to the existing model showed higher accuracy than calculations carried out on the existing model.

Modelling temporal data in knowledge graphs: a systematic review protocol.

Background: The benefits of having high-quality healthcare data are well established. However, high-dimensionality and irregularity of healthcare data pose challenges in their management. Knowledge graphs have gained increasing popularity in many domains, as a method for representing data to overcome such challenges. However, little is known about their suitability for use with healthcare data. One important factor in representing data is "time". Data with time related attributes are considered, temporal data. Temporal data are frequently observed in healthcare and the management of rapidly changing patient data is an ongoing challenge. Traditionally, data models have focused on presenting static data and do not account for temporal data. Temporal data models ensure time consistency in data models and assist analysing the history of data and predicting the future trends in data. Knowledge graphs can include temporal data models and are therefore of interest to the field of healthcare data management. As such, the herein aim is to outline a protocol for an inter-disciplinary systematic review of approaches, applications and challenges in modelling temporal data in knowledge graphs so that we can inform the application of knowledge graphs to healthcare data. Method: The research questions is, what are the existing approaches in modelling temporal data in RDF based knowledge graphs. Two sub-questions on applications, and challenges will also be evaluated. ACM digital library, IEEE Xplore and Scopus will be searched for this review. The search will be limited to peer-reviewed literature referring to knowledge graphs based on Resource Description Framework (RDF). A narrative synthesis of the papers will be conducted. Conclusion: The findings of this systematic review will be useful for data engineers to better represent data and perform analytics through temporal data modelling. They can be applied in the context of healthcare data and the current challenges faced in managing rapidly changing patient data.

A Temporal JSON Data Model and Its Query Languages

As a ubiquitous form of data in the natural world, time has been widely used in many domains such as the military, finance, medical treatment, and environment. Temporal data models that are used to model the dynamic development process of data are constantly proposed, such as temporal database and temporal XML. With the rapid development and popularization of the Web, the requirement of dealing with diverse data efficiently is becoming more important. As a new generation of data exchange language, JSON (JavaScript Object Notation) has been widely used because it is lightweight, has fast parsing, and has high transmission efficiency. In this paper, we propose a novel temporal JSON data model. Based on the proposed temporal JSON data model, we further propose two temporal JSON query languages, t-JSONPath, and t-JSONiq, which are the temporal extensions to JSONPath and JSONiq, respectively. With the proposed temporal JSON data model, we demonstrate our temporal JSON query languages with typical temporal query examples and evaluate their query response times.

Fuzzy relational representation, modeling and interpretation of temporal data

In virtue of omnipresence of temporal data (time series), a quest for efficient and interpretable models of such data becomes of paramount relevance. The accuracy-interpretable dilemma becomes more visible in light of the current trend of producing accurate, yet comprehensible models supporting users in making sound and highly actionable conclusions. This study is positioned in the realm of human-centric granular representation of temporal data (time series) where the logic settings of relational calculus is realized at the level of information granules. We establish modeling pursuits and resulting constructs at a certain level of abstraction delivered by information granules expressed as fuzzy sets. While have been some studies involving a framework of granular computing applied to granular models of time series, in this study we advocate a unified and original environment of logic blueprint of relational dependencies among information granules articulated by means of weighted logic expressions where both the components of the expressions as well as their associations are quantified (calibrated) in the presence of available experimental data. An overall processing scheme is structured as the following sequence of main functional modules: granulation (encoding) – relational computing – logic interpretation – numeric characterization of results (produced through decoding). Relational computing engages a suite of architectures that capture temporal dependencies describing predictions at the level of granular amplitudes and granular trends. The quality of the relational model is quantified at the level of information granules (which emphasizes the interpretability aspect) as well as. A series of experiments is reported to demonstrate the performance of the relational models and their performance impacted by the parameters of the relational architectures.

Learning Generative RNN-ODE for Collaborative Time-Series and Event Sequence Forecasting

Time-series and event sequences are widely collected data types in real-world applications. Modeling and forecasting of such temporal data play an important role in an informed decision-making process. A major limitation of previous methods is that they either focus on time-series or events, rather than the combination of the two worlds. In fact, the two types of data often provide complementary information, emphasizing the necessity of jointly modeling the both. In this paper, we propose the RNN-ODE collaborative model for joint modeling and forecasting of heterogeneous time-series and event sequence data, which combines several useful techniques from both Bayesian and deep learning for its interpretability. Specifically, we devise a tailored encoder to combine the advances in deep temporal point processes models and variational recurrent neural networks. To predict the probability of event occurrence over an arbitrary continuous-time horizon, we base our model on the mathematical foundation of Neural Ordinary Differential Equations (NODE). Extensive experimental results on simulations and real data sets show that compared with existing methods, our integrated approach can achieve more competitive forecasting performance of both time-series and event sequences.

Timo: In‐memory temporal query processing for big temporal data

AbstractToday's internet applications generate massive temporal data anywhere and anytime. Although some disk‐based temporal systems are currently available, they suffer from poor I/O performance, especially when applied in intelligent applications deployed in the cloud and edge environments. Therefore, how to process temporal operations with low latency and high throughput becomes a crucial problem for efficient data processing. This paper proposes Timo, a distributed in‐memory temporal query and analytic model for big temporal data. Firstly, a space‐efficient temporal index is proposed to support more efficiently query performance with less memory space than the state‐of‐art methods. Secondly, based on the temporal locality feature of temporal queries, Timo proposes a partitioner mechanism, which utilizes forward scan algorithm, to improve query throughput. Thirdly, some optimal strategies are proposed to improve the execution process of temporal query and analysis, which reduce intermediate result data size and improve the throughput much further. Lastly, we implement the Timo system on the Apache Spark platform, which extends Spark dataset API with temporal query and analysis API functions for users. Extensive experimental results show that the Timo system outperforms other Spark‐based temporal systems in terms of both query latency and throughput.

Prediction of heart conditions by consensusK-nearest neighbor algorithm and convolution neural network

In recent days, health problems are becoming more prevalent because of changes in lifestyles and inherited factors. Heart disease (HD), in particular, has become increasingly widespread in recent years, putting people’s lives in jeopardy. Blood pressure, cholesterol, and pulse rate are all varied for each person. Normal blood pressure should be 120/90, cholesterol should be 100–129[Formula: see text]mg/dL, pulse rate should be 72, fasting blood sugar level should be 100[Formula: see text]mg/dL, heart rate should be 60–100[Formula: see text]bpm, and ECG should be normal, according to medically established data. The aorta is 25[Formula: see text]mm (1 inch) wide, whereas capillaries are only 8[Formula: see text][Formula: see text]m wide, which signifies HD. This paper is based on a public health dataset that also contains a cardiac dataset. In our previous work, a new conventional neural network (CNN) architecture was used to extract and categorize histopathological images using the [Formula: see text]-means consensus clustering. We achieved good results with the cardiac dataset compared to the existing results. The outcome of the proposed work achieves a precision rate of 97%. In this paper, a novel conventional neural network (CNN) architecture was utilized to identify and characterize histopathology pictures with the help of using the consensus [Formula: see text]-nearest neighbor algorithm (CKNN). The usage of a deep neural network, as well as the selection and recovery of functionality, is an essential step until the dataset is classified. As a result, the training process has pre-formed the dataset. The system evaluates the person’s symptoms as input and provides the disease’s possibility as an output. The suggested approach is linked to temporal data modeling and makes use of a prior HD CNN prediction. In comparison to previous outcomes, we had good outcomes with the current cardiac dataset. The proposed model’s conclusion has brought out accuracy of 99.1%.

Real-Time Human Action Recognition Using Deep Learning Architecture

In this work, efficient human activity recognition (HAR) algorithm based on deep learning architecture is proposed to classify activities into seven different classes. In order to learn spatial and temporal features from only 3D skeleton data captured from a “Microsoft Kinect” camera, the proposed algorithm combines both convolution neural network (CNN) and long short-term memory (LSTM) architectures. This combination allows taking advantage of LSTM in modeling temporal data and of CNN in modeling spatial data. The captured skeleton sequences are used to create a specific dataset of interactive activities; these data are then transformed according to a view invariant and a symmetry criterion. To demonstrate the effectiveness of the developed algorithm, it has been tested on several public datasets and it has achieved and sometimes has overcome state-of-the-art performance. In order to verify the uncertainty of the proposed algorithm, some tools are provided and discussed to ensure its efficiency for continuous human action recognition in real time.

Modelling temporal data in knowledge graphs: a systematic review protocol

Background: The benefits of having high-quality healthcare data are well established. However, high-dimensionality and irregularity of healthcare data pose challenges in their management. Knowledge graphs have gained increasing popularity in many domains, as a method for representing data to overcome such challenges. However, little is known about their suitability for use with healthcare data. One important factor in representing data is “time”.Data with time related attributes are considered, temporal data. Temporal data are frequently observed in healthcare and the management of rapidly changing patient data is an ongoing challenge. Traditionally, data models have focused on presenting static data and do not account for temporal data. Temporal data models ensure time consistency in data models and assist analysing the history of data and predicting the future trends in data. Knowledge graphs can include temporal data models and are therefore of interest to the field of healthcare data management. As such, the herein aim is to outline a protocol for an inter-disciplinary systematic review of approaches, applications and challenges in modelling temporal data in knowledge graphs so that we can inform the application of knowledge graphs to healthcare data. Method: The research questions is, what are the existing approaches in modelling temporal data in knowledge graphs. Two sub-questions on applications, and challenges will also be evaluated. ACM digital library, IEEEXplore and ScienceDirect will be searched for this review. The search will be limited to peer-reviewed literature referring to knowledge graphs based on Resource Description Framework (RDF). A narrative synthesis of the papers will be conducted. Conclusion: The findings of this systematic review will be useful for data engineers to better represent data and perform analytics through temporal data modelling. They can be applied in the context of healthcare data and the current challenges faced in managing rapidly changing patient data.

A semiparametric latent factor model for large scale temporal data with heteroscedasticity

Large scale temporal data have flourished in a vast array of applications, and their sophisticated structures, especially the heteroscedasticity among subjects with inter- and intra-temporal dependence, have fueled a great demand for new statistical models. In this paper, with covariate information, we consider a flexible model for large scale temporal data with subject-specific heteroscedasticity. Formally, the model employs latent semiparametric factors to simultaneously account for the subject-specific heteroscedasticity and the contemporaneous and/or serial correlations. The subject-specific heteroscedasticity is modeled as the product of the unobserved factor process and subject’s covariate effect, which is further characterized via additive models. For estimation, we propose a two-step procedure. First, the latent factor process and nonparametric loading are recovered through projection-based methods, and following, we estimate the regression components by approaches motivated from the generalized least squares. By scrupulously examining the non-asymptotic rates for recovering the factor process and its loading, we show the consistency and efficiency of estimated regression coefficients in the absence of prior knowledge of latent factor process and subject’s covariate effect. The statistical guarantees remain valid even for finite time points that makes our method particularly appealing when the subjects significantly outnumber the observation time points. Using comprehensive simulations, we demonstrate the finite sample performance of our method, which corroborates the theoretical findings. Finally, we apply our method to a data set of air quality and energy consumption collected at 129 monitoring sites in the United States in 2015.