Simple Time Series Research Articles

Long Short-Term Memory Algorithm for Personalized Tacrolimus Dosing: A Simple and Effective Time Series Forecasting Approach Post-Lung Transplantation.

Management of tacrolimus trough levels influences morbidity and mortality after lung transplantation. Several studies have explored pharmacokinetic and artificial intelligence models to monitor tacrolimus levels. However, many models depend on a wide range of variables, some of which, like genetic polymorphisms, are not commonly tested for in regular clinical practice. This study aimed to verify the efficacy of a novel approach simply utilizing time series data of tacrolimus dosing, with the objective of accurately predicting trough levels in the variety of clinical settings. Data encompassing 36 clinical variables for each patient were gathered, and a multivariate long short-term memory algorithm was applied to forecast subsequent tacrolimus trough levels based on the selected clinical variables. The tool was developed using a dataset of 87,112 data points from 117 patients and its efficacy was confirmed using six additional cases. Shapley Additive exPlanations revealed a significant correlation between trough levels and prior dose-concentration data. By using simple trend learning of dose, administration route, and previous trough levels of tacrolimus, we could predict values within 30% of the actual values for 88.5% of time points, which facilitated the creation of a tool for simulating tacrolimus trough levels in response to dosage adjustments. The tool exhibited the potential for rectifying clinical misjudgments in a simulation cohort. Utilizing our time series forecasting tool, precise prediction of trough levels is attainable independently of other clinical variables, through the analysis of historical tacrolimus dose-concentration trends alone.

Using ARIMA and ETS models for forecasting water level changes for sustainable environmental management

It is vital to provide useful hydrological forecasts for urban and agricultural water management, hydropower generation, flood protection and management, drought mitigation and alleviation, and river basin planning and management, among other things. This paper introduces a simple and flexible hydrological time series forecasting framework. Predicting water levels is crucial, given the need for sustainable environmental management. The prognosis should be reasonable to persuade individuals to take proper precautions. While many methods have been developed to predict water levels, here the effectiveness of two approaches to predicting river water levels was assessed. For this purpose, nine years of data were used, which were divided into input data (2014–2021) and validation data (2022), on water levels in the Morava e Binçës river for the Vitia station, in the form of monthly time series records, to identify the best model among those used and to identify the information necessary for water resource management and hazard control. Models Autoregressive Integrated Moving Average(ARIMA) and Error Trend and Seasonality, or Exponential Smoothing (ETS), were examined using the R package to determine the most accurate. The results indicate the applicability of both models, as evidenced by the Root Mean Square Error (RMSE) and the Mean Absolute Error (MAE). The predictive analysis based on historical water levels allowed the identification of distinct periods characterized by high and low water levels between 2022 and 2024, which is important for the area in question due to the numerous flood events occurring here.

Wavelet Transform-Based Inertial Neural Network for Spatial Positioning Using Inertial Measurement Units

As the demand for spatial positioning continues to grow, positioning methods based on inertial measurement units (IMUs) are emerging as a promising research topic due to their low cost and robustness against environmental interference. These methods are particularly well suited for global navigation satellite system (GNSS)-denied environments and challenging visual scenarios. While existing algorithms for position estimation using IMUs have demonstrated some effectiveness, there is still significant room for improvement in terms of estimation accuracy. Current approaches primarily treat IMU data as simple time series, neglecting the frequency-domain characteristics of IMU signals. This paper emphasizes the importance of frequency-domain information in IMU signals and proposes a novel neural network, WINNet (Wavelet Inertial Neural Network), which integrates time- and frequency-domain signals using a wavelet transform for spatial positioning with inertial sensors. Additionally, we collected ground-truth data using a LiDAR setup and combined it with the TLIO dataset to form a new IMU spatial positioning dataset. The experimental results demonstrate that our proposed method outperforms the current state-of-the-art inertial neural network algorithms in terms of the ATE, RTE, and drift error metrics overall.

Collaborative Counseling to Build a Social Construct to Overcome Alcoholic Addiction

Alcohol consumption by teenagers is influenced by environmental factors. To overcome alcohol addiction among teenagers, a social construction needs to be built. So efforts are needed to overcome alcohol addiction, namely through collaborative counseling. In Collaborative Counseling the relationships and conversations create something different bringing together the collection, application, innovation and expansion of ideas involving working professionals from various disciplines, contexts and cultures, by detailing what they actually do every day for individuals, couples, families and groups . This research uses a Mixed Method with the Triangular Design type, namely collecting quantitative and qualitative data simultaneously. Quantitative research was conducted to answer the first research question, how addicted the sample was to alcohol during the research. By using Time-series Design with a simple interrupted Time Series approach with a sample size of 8 people. The qualitative research used in this research is a phenomenological approach, namely research that answers what certain phenomena are about. This research will also be used to interpret meaning in context. From the results obtained in this research, it was found that Collaborative Counseling was successful in eliminating addiction in the research sample.

Fast, Simple, and Accurate Time Series Analysis with Large Language Models: An Example of Mean-motion Resonances Identification

Classical machine learning has been actively utilized in astronomy to address various challenges, including predicting orbital stability, classifying asteroids, galaxies, and other objects, and analyzing images. However, the emerging trend in artificial intelligence involves the use of large language models such as GPT-4 and ChatGPT. These models are trained on a large corpus of text and can perform a wide range of natural language processing tasks, including text generation, translation, summarization, and classification. Surprisingly, these capabilities present significant potential for application in astronomy. This paper demonstrates how the new model gpt-4-vision-preview can analyze visual patterns and accurately classify asteroids as resonant or nonresonant with high accuracy. This process requires no training, fine-tuning, or coding beyond writing the appropriate prompt in natural language. Moreover, this approach can be extended to other common problems within astronomy.

Long-term impact of COVID-19 pandemic on antibiotic use in primary care: lessons to optimize antimicrobial use

ABSTRACT Background Lockdowns due to the COVID-19 pandemic was associated with changes in the pattern of use of antimicrobials, but persistence of changes after lockdowns has not been described. The objective was to describe the number of patients with dispensed antibiotic treatment and consumption of antibiotics in outpatients from primary care in Catalonia 18 months after the end of the emergency period. Research design and methods Data for the COVID-19 pandemic period was obtained from March 2020 to December 2021. Four high transmission rate (Rt > 100) periods were established. To compare data, a simple Bayesian structural time series model was used. Results The observed number of patients with dispensed antibiotics decreased respect to the estimated, especially during the four high transmission rate periods: April–May 2020 (lockdown period) (−42.57% and −42.68%); December 2020-February 2021 (−41.65%, −49.97% and −43.64%); October 2021 (−16.23%), and December 2021 (−20.16%). Overall antibiotic consumption was reduced by 23.37% (p = 0.002). These differences were mainly observed in those ≤ 15 years. Conclusions We describe the reduction in the number of patients with dispensed antibiotics and antibiotic consumption after the COVID-19 lockdown persisted in a period of recovery of healthcare accessibility. This information may help to improve antimicrobial use at the primary care level.

Tourism, Inequality and Segregation in The North Lombok Regency

The aim of this research is to look at the effects of tourism spatially and examine its impact on the aggregate welfare of the population. Therefore, the author asks two fundamental questions in this research. First, is the rapid demand for tourism capable of creating new regional growth poles spatially? Second, is increasing tourism receipts able to create welfare effects. The method used in this research is simple time series correlation and regression. The findings in this research are that the dependent variables tend to have a strong influence on education and employment indicators. Tourism seems to only have a false effect on economic activity in North Lombok Regency. It is proven that since this district was expanded, there have been no significant growth poles in this region. Regional and economic segregation is still clearly visible today.

Using responsive feedback from routine monitoring data to guide course corrections for a family planning intervention in Nigeria.

This paper aims to promote the use of simple interrupted time series (ITS) analyses of routine data as a responsive feedback tool to improve public health programs. Although advanced ITS techniques exist, their use is often not feasible due to limitations in funding or research capacity. We propose an Excel-based analysis that requires minimal resources or statistical expertise, and illustrate it by measuring the effect of a radio campaign to promote a family planning call center in Nigeria on the demand for family planning information. We used a single group interrupted time series design (ITS) as a responsive feedback mechanism to determine whether the radio campaign influenced use of the Honey&Banana call center. ITS is ideal when there is no control group. ITS uses the pre-intervention trend to predict what would have happened if the intervention were absent. After conducting ITS analyses, the results show that the number of calls requesting family planning information increased throughout the campaign period, with a gain of about 500 additional calls per month, and then decreased after the campaign ended. However, the number of calls gained from the campaign was substantially lower than anticipated. While end-of-project impact evaluations are necessary, there should be regular feedback system to provide program implementers with information about the status of the project, such as failures, successes, and areas of improvements. This would allow implementers to make necessary adjustments as needed throughout the intervention period. The finding that the radio campaign was not living up to expectations helped Honey&Banana program implementers to end the campaign prematurely and re-allocate resources to a more promising activity. Our research shows that basic Excel-based ITS analysis of routine data can be a useful tool for receiving regular feedback to guide programming improvements for organizations that have limited resources and/or research capacity.

Dynamic Modelling for Cancer-Associated Venous Thromboembolism

Background: Cancer-associated venous thromboembolism (VTE) is an important source of morbidity and mortality. Current risk prediction models for thrombosis are handicapped by static applicability (i.e. one-time evaluation prior to the first cycle of chemotherapy). We hypothesized that event forecasting using time series modelling could account for important changes in clinical state, variations in treatment and aspects of cancer progression over time. Methods: The cohort consisted of adult patients with a solid tumor enrolled in the MSK-IMPACT study between 2014 and 2019. VTE was defined as any symptomatic or asymptomatic pulmonary embolus or lower extremity deep vein thrombosis. We derived time series mixed-effects logistic regression models in order to predict cancer-associated VTE events using baseline patient characteristics (cancer type, time from diagnosis and age) along with time-dependent covariates including total white blood cell count, hemoglobin, platelet count, albumin, creatinine and parenteral chemotherapy type. Time-periods of one month were used and models were fitted to predict the presence or absence of a VTE episode in the following period (time = t+1) based on predictor values in the current period (time = t). The laboratory test result ascribed to a given period could be either the last value in the interval or the mean of all interval-specific values (both approaches tested). Missing laboratory results were imputed using the previously known value when available. Differences in laboratory values between periods t-1 and t were included as predictors in the initial model along with indicators of missingness (see Figure for flow of information between time-period cells). We hypothesized that absence of laboratory testing for a time-period would be a marker of stable medical state and hence associated with a lower risk of VTE. A previously defined training set comprising 80% of the cohort was used and different modelling approaches were evaluated using 5-fold cross-validation. The final selected model was evaluated in a separate dedicated validation set including the remaining 20% of the cohort. Results: The original cohort included 35,391 patients, from which 26,075 individuals with no cancer-associated VTE episode before observation start and sufficient laboratory test information could be included in the analysis, comprising 276,579 months of observation and 1,463 VTE events. The initial logistic regression model including all available predictors was fitted on the training set, revealing associations between predictors and VTE risk largely consistent with data reported by other groups (see Table). After adjusting for multiple comparisons, significant predictors of cancer-associated VTE identified included albumin, cell count result missingness (decreased risk for missing value), treatment with a platinum analogue (increased risk), hemoglobin, white blood cell count, breast cancer (decreased risk) and high-grade glioma (increased risk). Based on model metrics and prior knowledge from published literature, the set of covariates selected for inclusion in the final model consisted of cell counts along with the corresponding missingness indicator, platelet count change over time, albumin and chemotherapy types. The c-index for the final model using 5-fold cross-validation in the training set was 0.77 (95% CI = 0.75-0.80), compared to 0.77 (95% CI = 0.74-0.79) in the validation set. The latter corresponded to a specificity of 0.83 (95% CI = 0.79-0.86) when fixing sensitivity at 50%. Conclusions: A simple mixed-effects logistic regression time series model demonstrated promising potential to estimate the risk of cancer-associated VTE on a dynamic basis using routine laboratory test results and chemotherapy prescription data widely available in most electronic health record systems. Validation of this dynamic VTE risk model has the potential to optimize outpatient thromboprophylaxis during periods of high thrombotic risk.

Is deeper always better? Evaluating deep learning models for yield forecasting with small data

Predicting crop yields, and especially anomalously low yields, is of special importance for food insecure countries. In this study, we investigate a flexible deep learning approach to forecast crop yield at the provincial administrative level based on deep 1D and 2D convolutional neural networks using limited data. This approach meets the operational requirements—public and global records of satellite data in an application ready format with near real time updates—and can be transferred to any country with reliable yield statistics. Three-dimensional histograms of normalized difference vegetation index (NDVI) and climate data are used as input to the 2D model, while simple administrative-level time series averages of NDVI and climate data to the 1D model. The best model architecture is automatically identified during efficient and extensive hyperparameter optimization. To demonstrate the relevance of this approach, we hindcast (2002–2018) the yields of Algeria’s three main crops (barley, durum and soft wheat) and contrast the model’s performance with machine learning algorithms and conventional benchmark models used in a previous study. Simple benchmarks such as peak NDVI remained challenging to outperform while machine learning models were superior to deep learning models for all forecasting months and all tested crops. We attribute the poor performance of deep learning to the small size of the dataset available.

Selective Imputation for Multivariate Time Series Datasets With Missing Values

Multivariate time series often contain missing values for reasons such as failures in data collection mechanisms. Since these missing values can complicate the analysis of time series data, imputation techniques are typically used to deal with this issue. However, the quality of the imputation directly affects the performance of downstream tasks. In this paper, we propose a selective imputation method that identifies a subset of timesteps with missing values to impute in a multivariate time series dataset. This selection, which will result in shorter and simpler time series, is based on both reducing the uncertainty of the imputations and representing the original time series as good as possible. In particular, the method uses multi-objective optimization techniques to select the optimal set of points, and in this selection process, we leverage the beneficial properties of the Multi-task Gaussian Process (MGP). The method is applied to different datasets to analyze the quality of the imputations and the performance obtained in downstream tasks, such as classification or anomaly detection. The results show that much shorter and simpler time series are able to maintain or even improve both the quality of the imputations and the performance of the downstream tasks.

A data science approach for multi-sensor marine observatory data monitoring cold water corals (Paragorgia arborea) in two campaigns.

Fixed underwater observatories (FUO), equipped with digital cameras and other sensors, become more commonly used to record different kinds of time series data for marine habitat monitoring. With increasing numbers of campaigns, numbers of sensors and campaign time, the volume and heterogeneity of the data, ranging from simple temperature time series to series of HD images or video call for new data science approaches to analyze the data. While some works have been published on the analysis of data from one campaign, we address the problem of analyzing time series data from two consecutive monitoring campaigns (starting late 2017 and late 2018) in the same habitat. While the data from campaigns in two separate years provide an interesting basis for marine biology research, it also presents new data science challenges, like the the marine image analysis in data form more than one campaign. In this paper, we analyze the polyp activity of two Paragorgia arborea cold water coral (CWC) colonies using FUO data collected from November 2017 to June 2018 and from December 2018 to April 2019. We successfully apply convolutional neural networks (CNN) for the segmentation and classification of the coral and the polyp activities. The result polyp activity data alone showed interesting temporal patterns with differences and similarities between the two time periods. A one month "sleeping" period in spring with almost no activity was observed in both coral colonies, but with a shift of approximately one month. A time series prediction experiment allowed us to predict the polyp activity from the non-image sensor data using recurrent neural networks (RNN). The results pave a way to a new multi-sensor monitoring strategy for Paragorgia arborea behaviour.

Estimation of Height Changes of Continuous GNSS Stations in the Eastern Anatolia Region during the Seasonal Variation

Estimating the height component of Global Navigation Satellite System (GNSS) stations is widely known to be more challenging than estimating the horizontal position. In this study, we utilized height time series data from 37 continuous GNSS stations that were part of the Turkish RTK CORS Network called TUSAGA-Active (Turkish National Permanent GNSS Network Active). The data covered the period from 2014 to 2019, and the selection of stations focused on the Eastern Anatolia region of Turkey due to its topographic characteristics and the pronounced influence of seasonal changes, which facilitated the interpretation of the effects on the height component. The daily coordinates of the GNSS stations were derived using the GAMIT/GLOBK software solution. We identified statistically significant trends, periodic variations, and stochastic components associated with the stations by applying time series analysis to these daily coordinate values. As a result, the vertical velocities of the GNSS stations were determined, along with their corresponding standard deviations. Furthermore, examining the height components of the continuous GNSS stations revealed seasonal effects. We aimed to investigate the potential relationship between these height components and meteorological parameters. The study provides evidence of the interconnectedness between the height components of continuous GNSS stations and various meteorological parameters. Simple linear regression analysis and ARMA time series modeling were utilized to establish this relationship.

Overview of Logistics Demand Forecasting Methods

Accurate forecasting of logistics demand is of great theoretical significance and practical application value for the formulation of national policies and the satisfaction of actual demand in the logistics industry. From the modeling form, the existing logistics demand forecasting methods are divided into four categories: single traditional forecasting method, single intelligent forecasting method, combined forecasting method and mixed forecasting method. Among them, single traditional forecasting methods mainly include simple time series method, regression analysis, mathematical and statistical methods, etc.; single intelligent forecasting methods mainly involve gray forecasting method, neural network, support vector machine and their improved forms; combined forecasting methods are mainly summarized into three combined forms: linear combination of single forecasting results, nonlinear combination of single forecasting results, modified single forecasting results; mixed forecasting methods are mainly summarized into three hybrid forms: hybrid intelligent optimization algorithms with single prediction methods, hybrid data dimensionality reduction techniques with intelligent prediction methods, and hybrid data mining techniques with intelligent prediction methods. The four major types of forecasting methods are reviewed, and each forecasting model in the four major types of methods is evaluated in terms of modeling principles, advantages and disadvantages, and applicability, in order to find forecasting methods suitable for different logistics demand forecasting tasks for logistics demand researchers.

Using deep learning–derived image features in radiologic time series to make personalised predictions: proof of concept in colonic transit data

ObjectivesSiamese neural networks (SNN) were used to classify the presence of radiopaque beads as part of a colonic transit time study (CTS). The SNN output was then used as a feature in a time series model to predict progression through a CTS.MethodsThis retrospective study included all patients undergoing a CTS in a single institution from 2010 to 2020. Data were partitioned in an 80/20 Train/Test split. Deep learning models based on a SNN architecture were trained and tested to classify images according to the presence, absence, and number of radiopaque beads and to output the Euclidean distance between the feature representations of the input images. Time series models were used to predict the total duration of the study.ResultsIn total, 568 images of 229 patients (143, 62% female, mean age 57) patients were included. For the classification of the presence of beads, the best performing model (Siamese DenseNET trained with a contrastive loss with unfrozen weights) achieved an accuracy, precision, and recall of 0.988, 0.986, and 1. A Gaussian process regressor (GPR) trained on the outputs of the SNN outperformed both GPR using only the number of beads and basic statistical exponential curve fitting with MAE of 0.9 days compared to 2.3 and 6.3 days (p < 0.05) respectively.ConclusionsSNNs perform well at the identification of radiopaque beads in CTS. For time series prediction our methods were superior at identifying progression through the time series compared to statistical models, enabling more accurate personalised predictions.Clinical relevance statementOur radiologic time series model has potential clinical application in use cases where change assessment is critical (e.g. nodule surveillance, cancer treatment response, and screening programmes) by quantifying change and using it to make more personalised predictions.Key Points• Time series methods have improved but application to radiology lags behind computer vision. Colonic transit studies are a simple radiologic time series measuring function through serial radiographs.• We successfully employed a Siamese neural network (SNN) to compare between radiographs at different points in time and then used the output of SNN as a feature in a Gaussian process regression model to predict progression through the time series.• This novel use of features derived from a neural network on medical imaging data to predict progression has potential clinical application in more complex use cases where change assessment is critical such as in oncologic imaging, monitoring for treatment response, and screening programmes.

Percussion-based concrete fiber content recognition using homologous heterogeneous data fusion and denoising deep learning network

With the development of materials science, fiber-reinforced concrete (FRC) has attracted much attention in building engineering areas and gradually alternated the traditional regular concrete in recent years. Since the fiber content significantly affects the performance of FRC material, it is of great importance to detect the fiber content in practical applications. Thus, this research proposes a novel percussion-based recognition method to evaluate the fiber content in FRC material, which contains a simple but effective time series data fusion approach and an adroitly integrated one-dimensional denoising autoencoder-enhanced convolutional neural network (1D-DAECNN). Particularly, compared with most current existing percussion-based recognition methods, which utilize single acoustic signals, the proposed method simultaneously adopts the homologous heterogeneous data obtained respectively from the microphone and embedded piezoceramic transducer after one-time percussion. Then, the homologous heterogeneous data are processed by the presented time series data fusion approach to achieve time domain waveform features fusion, which aims to improve the convergence speed of deep learning networks. After that, the 1D-DAECNN is constructed to identify the fiber content in FRC material. Via the front-end denoising autoencoder (DAE) and the back-end one-dimensional convolutional neural network (1D-CNN) in the integrated network, the noise suppression capability of the 1D-DAECNN can be improved, and the manual feature extraction can be avoided during the training process. Finally, the effectiveness of the proposed method is demonstrated via laboratory tests on five FRC specimens. The results indicate that, compared with the conventional percussion-based method, the convergence speed and recognition precision of the proposed method is significantly improved even under noise conditions.

Upaya Penguatan Perekonomian Masyarakat Pasca Tambang Karst

Karst mines in the Mount Kromong area cannot be separated from the historical aspects of local communities in utilizing karst resources as a support for their necessities of life. Historically the use of karst in the area of Mount Kromong has been going on since 1700 and has been passed down from generation to generation. However, the change in control of the karst mining area resulted in various significant changes to people's lives so that various alternative economic sectors emerged that needed to be strengthened through empowerment efforts. This study aims to examine how the post-mining Cikeusal Village community's economy has changed and how the Village Government's efforts to strengthen community alternative economic sectors after the mining sector has become exclusive. So, the questions that will be formulated by researchers in this study are (1) What is the history of karst mining management in Cikeusal Village?; and (2) How is the post-karst mining economic empowerment process in Cikeusal Village? Researchers used qualitative research methods with a case study approach. Data collection techniques used by researchers are observation, interviews and documentation while data analysis techniques used by researchers are simple time series analysis. In this research, the researcher outlines the data obtained in the field during the time the research took place chronologically as well as a description of the dynamics of the post-mining community economic empowerment process in Cikeusal Village.

Analysis of Amazon Stock Using Simple Linear Regression and Time Series ARIMA Model

The rate of daily return of a stock is one of the important indicators for investors to anticipate benefits or losses from historical data. This paper will focus on the stock of Amazon, which is a popular choice for stock traders and contains data from August 25, 2017, to August 24, 2022. By using regression models such as a simple linear regression model and an autoregressive integrated moving average (ARIMA), the recent daily return value is predicted based on data during these 5 years. The simple linear regression can show the trend of stock price and the predicted response rate of daily return using the linear model. Furthermore, ARIMA is a more advanced time series model to provide a more accurate rate of daily return with confidence intervals. The predicted trend and rate of daily return are useful for investors to make decisions to buy or sell a stock recently. The trend can tell investors whether the stock price would go up and the daily return can indicate how many benefits can they earn if they choose to invest in this stock.

Predicting daily emergency department visits using machine learning could increase accuracy

ObjectiveAdministrators and clinicians alike have attempted to predict emergency department visits for many years. The ability to predict or “forecast” ED visit volume can allow for more efficient resource allocation, including up-staffing or down-staffing, changing OR schedules, and predicting the need for significant resources. The goal of this study is to examine combinations of variables via machine learning to increase prediction accuracy and determine the factors that are most predictive of overall ED visits. As compared to a simple univariate time series model, we hypothesize that machine learning models will predict St. Joseph Mercy Ann Arbor's patient visit load for the emergency department (ED) with higher accuracy than a simple univariate time series model. MethodsUnivariate time series models for daily ED visits, including ARIMA, Exponential Smoothing (ETS), and Facebook Inc.'s prophet algorithm were estimated as a baseline comparison. Machine learning models, including random forests and gradient boosted machines (GBM), were trained using data from 2017 to 2018. After final models were created, they were applied to the 2019 data to determine how well these models predicted actual ED patient volumes in data not utilized during the model fitting process. The accuracy of the machine learning and time series models were assessed based on out-of-sample predictive accuracy, compared using root mean squared error (RMSE). ResultsUsing root mean squared error (RMSE) to assess out-of-sample predictive accuracy of the models, the results showed that the random forest model was the most accurate at predicting daily ED visits in the 2019 test set, followed by the GBM model. These performed only slightly better than the simple exponential smoothing model predictions. The ARIMA model performed poorly in comparison. The day of the week (likely capturing differences between weekdays and weekends) was found to be the most important predictor of patient volumes. Weather-related features such as maximum temperature and SFC pressure appeared to capture some of the seasonality trends related to changes in patient volumes. ConclusionsMachine learning models perform better at predicting daily patient volumes as compared to simple univariate time series models, though not by a substantial amount. Further research can help confirm these limited initial results. Gathering more training data and additional feature engineering could also be beneficial to training the models and potentially improving predictive accuracy.

Adversarial training of LSTM-ED based anomaly detection for complex time-series in cyber-physical-social systems

• Solving the time-series anomaly detection problem in CPSSs by deep learning approach. • Combining the advantages of LSTM and reconstruction models for time- series anomaly detection problems. • Proposing the adversarial training method to improve the robustness of Encoder-Decoder model. • Avoiding the heavy workload of traditional methods for a priori knowledge and quality labeling. • Conducting the extensive experiments to prove the validity of the method in this paper. With the development and maturity of smart cities, more and more Cyber-Physical-Social Systems (CPSSs) need to monitor a variety of time-series data from sensors and network transmissions to ensure the quality and reliability of the Cyber-Physical-Social Services. Time-series anomaly detection is a common search problem in the field of pattern recognition. Existing approaches and models of anomaly detection have solved the problem of simple smooth time-series and perform ideal recognition performance. However, in real scenarios, complex time-series with non-Gaussian noise and complex data distributions are prevalent. Compared to smooth and simple time-series, complex time-series occur more frequently in real-world settings and are difficult to model and label. To address these challenges, this paper proposes an unsupervised anomaly detection algorithm based on Long Short-Term Memory Encoder-Decoder (LSTM-ED) via an adversarial training method for complex time-series in cyber-physical-social systems with high performance. This is a novel method that incorporates adversarial learning to improve the robustness of encoder-decoder architecture, enabling it to obtain good anomaly detection results for complex time-series. In addition, LSTM is employed as the network unit of encoder-decoder architecture, which is also able to extract temporal correlation in time-series to a greater extent. We have conducted extensive experiments on four datasets from real scenarios and the results show that the accuracy of the proposed adversarial training of LSTM-ED is significantly better than that of the state-of-the-art methods, including other unsupervised methods and traditional supervised methods.