As per Cognitive Market Research's latest published report, the Global Time Series Databases Software market size will be $993.24 Million by 2028. Time Series Databases Software Industry's Compound Annual Growth Rate will be 18.36% from 2023 to 2030. Factors Affecting Time Series Databases Software market growth

Rise in automation in industry

Industrial sensors are a key part of factory automation and Industry 4.0. Motion, environmental, and vibration sensors are used to monitor the health of equipment, from linear or angular positioning, tilt sensing, leveling, shock, or fall detection. A Sensor is a device that identifies the progressions in electrical or physical or other quantities and in a way delivers a yield as an affirmation of progress in the quantity.

In simple terms, Industrial Automation Sensors are input devices that provide an output (signal) with respect to a specific physical quantity (input). In industrial automation, sensors play a vital part to make the products intellectual and exceptionally automatic. These permit one to detect, analyze, measure, and process a variety of transformations like alteration in position, length, height, exterior, and dislocation that occurs in the Industrial manufacturing sites. These sensors also play a pivotal role in predicting and preventing numerous potential proceedings, thus, catering to the requirements of many sensing applications. This sensor generally works on time series as the readings are taken after equal intervals of time.

The increase in the use of sensor to monitor the industrial activities and in production factories is fueling the growth of the time series database software market. Also manufacturing in pharmaceutical industry requires proper monitoring due to which there is increase in demand for sensors and time series database, this fuels the demand for time series database software market.

Market Dynamics of

Time Series Databases Software Market

Key Drivers of

Time Series Databases Software Market

Increasing Adoption of IoT Devices : The rise of IoT devices is producing vast amounts of time-stamped data. Time Series Databases (TSDBs) are specifically engineered to manage this data effectively, facilitating real-time monitoring, analytics, and forecasting—rendering them crucial for sectors such as manufacturing, energy, and smart cities.

Rising Demand for Real-Time Analytics : Companies are progressively emphasizing real-time data processing to enable quicker, data-informed decisions. TSDBs accommodate rapid data ingestion and querying, allowing for real-time analysis across various sectors including finance, IT infrastructure, and logistics, significantly enhancing their market adoption.

Growth of Cloud Infrastructure : As cloud computing becomes ubiquitous, cloud-native TSDB solutions are gaining popularity. These platforms provide scalability, ease of deployment, and lower operational expenses. The need for adaptable and on-demand database solutions fosters the expansion of TSDBs within contemporary IT environments.

Key Restraints in

Time Series Databases Software Market

High Implementation and Maintenance Costs : The deployment and upkeep of Time Series Database (TSDB) systems can necessitate a considerable financial commitment, particularly for small to medium-sized businesses. The costs encompass infrastructure establishment, the hiring of skilled personnel, and the integration with current systems, which may discourage market adoption in environments sensitive to costs.

Complexity in Data Management : Managing large volumes of time-stamped data demands a robust system architecture. As the amount of data increases, difficulties in indexing, querying, and efficient storage can adversely affect performance and user experience, thereby restricting usability for organizations that lack strong technical support.

Competition from Traditional Databases : In spite of their benefits, TSDBs encounter competition from advanced traditional databases such as relational and NoSQL systems. Many of these databases now offer time-series functionalities, leading organizations to be reluctant to invest in new TSDB software when existing solutions can be enhanced.

Key Trends of

Time Series Databases Software Market

Integration with AI and Machine Learning Tools : TSDBs are progressively being integrated with AI/ML platfo...

Multivariate Time-Series (MTS) are ubiquitous, and are generated in areas as disparate as sensor recordings in aerospace systems, music and video streams, medical monitoring, and financial systems. Domain experts are often interested in searching for interesting multivariate patterns from these MTS databases which can contain up to several gigabytes of data. Surprisingly, research on MTS search is very limited. Most existing work only supports queries with the same length of data, or queries on a fixed set of variables. In this paper, we propose an efficient and flexible subsequence search framework for massive MTS databases, that, for the first time, enables querying on any subset of variables with arbitrary time delays between them. We propose two provably correct algorithms to solve this problem — (1) an R-tree Based Search (RBS) which uses Minimum Bounding Rectangles (MBR) to organize the subsequences, and (2) a List Based Search (LBS) algorithm which uses sorted lists for indexing. We demonstrate the performance of these algorithms using two large MTS databases from the aviation domain, each containing several millions of observations. Both these tests show that our algorithms have very high prune rates (>95%) thus needing actual disk access for only less than 5% of the observations. To the best of our knowledge, this is the first flexible MTS search algorithm capable of subsequence search on any subset of variables. Moreover, MTS subsequence search has never been attempted on datasets of the size we have used in this paper.

Multivariate Time-Series (MTS) are ubiquitous, and are generated in areas as disparate as sensor recordings in aerospace systems, music and video streams, medical monitoring, and financial systems. Domain experts are often interested in searching for interesting multivariate patterns from these MTS databases which can contain up to several gigabytes of data. Surprisingly, research on MTS search is very limited. Most existing work only supports queries with the same length of data, or queries on a fixed set of variables. In this paper, we propose an efficient and flexible subsequence search framework for massive MTS databases, that, for the first time, enables querying on any subset of variables with arbitrary time delays between them. We propose two provably correct algorithms to solve this problem — (1) an R-tree Based Search (RBS) which uses Minimum Bounding Rectangles (MBR) to organize the subsequences, and (2) a List Based Search (LBS) algorithm which uses sorted lists for indexing. We demonstrate the performance of these algorithms using two large MTS databases from the aviation domain, each containing several millions of observations. Both these tests show that our algorithms have very high prune rates (>95%) thus needing actual disk access for only less than 5% of the observations. To the best of our knowledge, this is the first flexible MTS search algorithm capable of subsequence search on any subset of variables. Moreover, MTS subsequence search has never been attempted on datasets of the size we have used in this paper.

This lesson was adapted from educational material written by Dr. Kateri Salk for her Fall 2019 Hydrologic Data Analysis course at Duke University. This is the first part of a two-part exercise focusing on time series analysis.

Introduction

Time series are a special class of dataset, where a response variable is tracked over time. The frequency of measurement and the timespan of the dataset can vary widely. At its most simple, a time series model includes an explanatory time component and a response variable. Mixed models can include additional explanatory variables (check out the nlme and lme4 R packages). We will be covering a few simple applications of time series analysis in these lessons.

Opportunities

Analysis of time series presents several opportunities. In aquatic sciences, some of the most common questions we can answer with time series modeling are:

• Has there been an increasing or decreasing trend in the response variable over time?

• Can we forecast conditions in the future?

  Challenges

Time series datasets come with several caveats, which need to be addressed in order to effectively model the system. A few common challenges that arise (and can occur together within a single dataset) are:

• Autocorrelation: Data points are not independent from one another (i.e., the measurement at a given time point is dependent on previous time point(s)).

• Data gaps: Data are not collected at regular intervals, necessitating interpolation between measurements. There are often gaps between monitoring periods. For many time series analyses, we need equally spaced points.

• Seasonality: Cyclic patterns in variables occur at regular intervals, impeding clear interpretation of a monotonic (unidirectional) trend. Ex. We can assume that summer temperatures are higher.

• Heteroscedasticity: The variance of the time series is not constant over time.

• Covariance: the covariance of the time series is not constant over time. Many of these models assume that the variance and covariance are similar over the time-->heteroschedasticity.

  Learning Objectives

After successfully completing this notebook, you will be able to:

1. Choose appropriate time series analyses for trend detection and forecasting

2. Discuss the influence of seasonality on time series analysis

3. Interpret and communicate results of time series analyses

1) Data Introduction • The Air Properties Time Series Dataset is a tabular time series dataset collected for air conditioning (HVAC) environment monitoring. It includes key air quality indicators such as dew point temperature, temperature, humidity, air flow, and power consumption of supply and return air at each time interval.

2) Data Utilization (1) Characteristics of the Air Properties Time Series Dataset: • By integrating real-time air quality, temperature and humidity, dew point, and other environmental indicators, this dataset is well-suited for practical applications such as industrial cleanroom environment control and facility management.

(2) Applications of theAir Properties Time Series Dataset: • Development of AHU Operating Status Prediction Models: The dataset can be used to develop machine learning models that predict the operating status (ON/OFF) of air handling units (AHU) using various environmental variables and time information. • Air Conditioning Environment Monitoring and Anomaly Detection: By analyzing the time series patterns of key indicators such as temperature, humidity, and dew point, the dataset can be utilized for real-time environment monitoring and anomaly detection in air conditioning systems.

This dataset is designed to support research and development in digital smart grid systems, focusing on asset identification, fault detection, and automated grid reconfiguration. It simulates time-series data collected from smart meters and sensors distributed across low-voltage distribution substations. The dataset reflects realistic power system behaviors, including fluctuations in voltage, current, power, and energy usage.

📊 Features Column Name Description Timestamp Minute-level timestamp of sensor reading Substation_ID Unique identifier for each substation Asset_ID Unique identifier for the monitored asset (e.g., transformer, switch) Voltage_V Voltage reading in volts Current_A Current reading in amperes Power_kW Calculated real power consumption in kilowatts Frequency_Hz Electrical frequency (normally ~50 Hz) Energy_Consumed_kWh Energy consumed in kilowatt-hours over the minute interval Load_Type Type of load (Residential, Industrial, or Commercial) Fault_Event Event indicator (e.g., None, Overload, Outage, UnderVoltage) Reconfig_Action Automatic control action taken (e.g., Load_Balance, Switching, or None) Asset_Type Target column indicating asset class for classification tasks

This dataset comprises 524 recordings of 6-dimensional time series data, capturing forces in three directions and torques in three directions during the assembly of small car model wheels. The data was collected using an equidistant sampling method with a sampling period of 0.004 seconds. Each time series represents the process of assembling one wheel, specifically the placement of a tire onto a rim, and includes a label indicating whether the assembly was successful (OK). The wheels were assembled in batches of four, and the recordings were obtained over six different days. The labels of recordings from two (days 3 and 4) of the six days are invalid as described in [1]. The labels presented in this data set are only binary (they do not describe the reason of the failure). The labels of recordings from days 5 and 6 are created by human while the other labels came from a convolutional neural network based computer vision classifier and can be inaccurate as described in section 5.4 of [1].

Dataset Structure:

File: ForceTorqueTimeSeries.csv

Columns:

idx (1-524): Index of the recording corresponding to the assembly of one wheel.

label (true/false): Indicates whether the assembly was successful (TRUE = product is OK).

meas_id (1-6): Identifier for the day on which the recording was made (refer to Table 2.1 in [1]).

force_x: X-component of the force measured by the sensor mounted on the delta robot's end effector.

force_y: Y-component of the force.

force_z: Z-component of the force.

torque_x: X-component of the torque.

torque_y: Y-component of the torque.

torque_z: Z-component of the torque.

Additional Files:

IMG_3351.MOV: A video demonstrating the assembly process for one batch of four wheels.

F3-BP-2024-Trna-Ales-Ales Trna - 2024 - Anomaly detection in robotic assembly process using force and torque sensors.pdf: Bachelor thesis [1] detailing the dataset and preliminary experiments on fault detection.

F3-BP-2024-Hanzlik-Vojtech-Anomaly_Detection_Bachelors_Thesis.pdf: Bachelor thesis [2] describing the data acquisition process.

References:

Trna, A. (2024). Anomaly detection in robotic assembly process using force and torque sensors [Bachelor’s thesis, Czech Technical University in Prague].

Hanzlik, V. (2024). Edge AI integration for anomaly detection in assembly using Delta robot [Bachelor’s thesis, Czech Technical University in Prague].

SCALABLE TIME SERIES CHANGE DETECTION FOR BIOMASS MONITORING USING GAUSSIAN PROCESS VARUN CHANDOLA AND RANGA RAJU VATSAVAI Abstract. Biomass monitoring, specifically, detecting changes in the biomass or vegetation of a geographical region, is vital for studying the carbon cycle of the system and has significant implications in the context of understanding climate change and its impacts. Recently, several time series change detection methods have been proposed to identify land cover changes in temporal profiles (time series) of vegetation collected using remote sensing instruments. In this paper, we adapt Gaussian process regression to detect changes in such time series in an online fashion. While Gaussian process (GP) has been widely used as a kernel based learning method for regression and classification, their applicability to massive spatio-temporal data sets, such as remote sensing data, has been limited owing to the high computational costs involved. In our previous work we proposed an efficient Toeplitz matrix based solution for scalable GP parameter estimation. In this paper we apply these solutions to a GP based change detection algorithm. The proposed change detection algorithm requires a memory footprint which is linear in the length of the input time series and runs in time which is quadratic to the length of the input time series. Experimental results show that both serial and parallel implementations of our proposed method achieve significant speedups over the serial implementation. Finally, we demonstrate the effectiveness of the proposed change detection method in identifying changes in Normalized Difference Vegetation Index (NDVI) data.

Time Series Databases Software Market size was valued at USD 359.37 USD Million in 2024 and is projected to reach USD 773.71 Million by 2031, growing at a CAGR of 10.06% from 2024 to 2031.

Time Series Databases Software Market Drivers

Growing Data Volume: The exponential growth of data generated by various sources, including IoT devices, financial transactions, and digital services, necessitates efficient management and analysis of time-stamped data. Time series databases are optimized for handling large volumes of time-stamped data, driving their adoption.

Rise of IoT and Connected Devices: The proliferation of IoT devices in industries such as manufacturing, healthcare, and smart cities generates massive amounts of time-series data. Time series databases are crucial for storing, querying, and analyzing this continuous stream of data efficiently.

Increasing Importance of Real-Time Analytics: Businesses require real-time insights to make informed decisions and maintain competitive advantage. Time series databases support real-time analytics by efficiently processing and analyzing time-stamped data, which is critical for applications like monitoring, forecasting, and anomaly detection.

This dataset is for the paper "First onset of unrest captured at Socompa: A Recent Geodetic Survey at Central Andean volcanoes in Northern Chile" which is published in GRL: https://doi.org/10.1029/2022GL102480.

InSAR Data:

The folder of InSAR_149A.rar stores the InSAR time series analysis dataset on ascending track 149.

The 'Imagedate' folder stores the empty *.rslc files to indicate the date of each SLCs.

Data_Asc.mat stores the main InSAR time series data, which includes the UTC time of the acquisition (for accurate time calculation), the length of perpendicular baselines (unit is meter), the number of days counting from the first epoch, the unwrapped time series data (ifg), the unwrapped time series data with GACOS correction (ifg_aps), the look angles (la, unit is rad), and lat&lon.

parms.mat stores the parameters used during the data processing by StaMPS.

semi_fit.mat stores the results of the semi-variogram fitting of each interferogram on time series. It provides two versions for the original dataset (semi) and the GACOS-corrected dataset (semi_aps). This file is mainly used to weight the data during the time series fitting.

runTSA.m, the main function to run the InSAR time series fitting. See more details in the Code part.

The folder of InSAR_156D.rar stores the same content as the InSAR_149A.rar but for descending track 156.

Code:

This folder contains the codes of the InSAR time series fitting for this dataset, and the GBIS software.

TSA_findref.m, this function is used to search the reference point of the InSAR data.

TSA_EQ_fit.m, is the main function to perform InSAR time series fitting.

rb_pixel_fit.m, is the robust way to fit the linear model.

TSA_EQ_pixel.m, is the function used to plot the results.

To perform the InSAR time series fitting, you need to put these four functions under your Matlab path, and then run the runTSA.m function in the data folder.

The GBIS folder stores the updated version of the GBIS software, which allows you to perform the pCDM, CDM, and pECM. The core functions of these models are provided by Dr. Mehdi Nikkhoo, and you could find them here: https://www.volcanodeformation.com/software

GBIS_Modelling_Results:

This folder stores the data of InSAR and GPS joint inversion for Socompa Uplift.

The folder Socompa stores the modelling results using the models of Okada(D), pECM(E), Mogi(M), pCDM(N), and Yang(Y), respectively.

GPS_data.txt stores the cumulative displacements and the uncertainties of the SOCM station in three directions.

Socompa.inp is the configuration file for GBIS running.

Vol_asc.mat and Vol_asc_ds.mat stores the original and the downsampled ascending data, while Vol_dsc.mat and Vol_dsc_ds.mat store those of descending.

Many thanks for using our dataset and please let me know if you have any further questions!

Weather Long-term Time Series Forecasting (2020)

https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F8734253%2F832430253683be01796f74de8f532b34%2Fweather%20forecasting.png?generation=1730602999355141&alt=media" alt="">

Dataset Description

Weather is recorded every 10 minutes throughout the entire year of 2020, comprising 20 meteorological indicators measured at a Max Planck Institute weather station. The dataset provides comprehensive atmospheric measurements including air temperature, humidity, wind patterns, radiation, and precipitation. With over 52,560 data points per variable (365 days × 24 hours × 6 measurements per hour), this high-frequency sampling offers detailed insights into weather patterns and atmospheric conditions. The measurements include both basic weather parameters and derived quantities such as vapor pressure deficit and potential temperature, making it suitable for both meteorological research and practical applications. You can find some initial analysis using this dataset here: "Weather Long-term Time Series Forecasting Analysis".

File Structure

The dataset is provided in a CSV format with the following columns:

Potential Use Cases

This high-resolution meteorological dataset enables applications across multiple domains. For weather forecasting, the frequent measurements support development of prediction models, while climate researchers can study microclimate variations and seasonal patterns. In agriculture, temperature and vapor pressure deficit data aids crop modeling and irrigation planning. The wind and radiation measurements benefit renewable energy planning, while the comprehensive atmospheric data supports environmental monitoring. The dataset's detailed nature makes it particularly suitable for machine learning applications and educational purposes in meteorology and data science.

Credits

• This data was provided by the Max Planck Institute, and acc...

Time series electromagnetic-induction log (TSEMIL) datasets are collected from PVC cased or uncased monitoring wells to evaluate changes in water conductivity over time. TSEMIL datasets consist of a series of individual electromagnetic-induction logs collected at a frequency of months or years that have been compiled into a dataset by eliminating small uniform offsets in bulk conductivity between logs likely caused by minor variations in calibration. At depths where water conductivity is not changing through time, each log is typically within about ±15 mS/m of the median of the dataset at any given depth, which is within the stated resolution, repeatability, and accuracy specifications of the probe. Though the offsets between logs are small (±15 mS/m), they obscure the ability to identify small but real changes in bulk conductivity resulting from changes in aquifer salinity. These offsets are removed by selecting a depth at which no changes are apparent from year to year, and by adjusting individual logs to the median of all logs at the selected depth. Generally, these depths are within the freshwater saturated part of the aquifer, well below the water table. Once the offsets have been removed there is generally only about ±2 mS/m of completely irregular variation between successive logs that cannot be removed. Even if perfect numerical alignment is achieved at one or two depths, the ±2 mS/m of random variation remains at other depths. Given these corrections, however, changes from year to year caused by saltwater intrusion are easier to identify. Detailed descriptions of how these corrections are applied are described in Prinos and others (2014) and Prinos and Valderrama (2015). TSEMIL datasets can be used to monitor changes in water conductivity throughout the full thickness of an aquifer, without the need for long open-interval wells, which have, in some instances, allowed vertical water flow within the well bore that has biased water conductivity profiles (Prinos and Valderrama, 2015). Although TSEMIL datasets are most commonly used to evaluate saltwater intrusion some other observed changes evident in TSEMIL datasets are: (1) variations in bulk conductivity near the water table where water saturation of pore spaces may vary, and water temperature may be more variable, (2) dissipation of conductive water in high porosity rock layers, which may have entered these layers during drilling.

Abstract Prognostics solutions for mission critical systems require a comprehensive methodology for proactively detecting and isolating failures, recommending and guiding condition-based maintenance actions, and estimating in real time the remaining useful life of critical components and associated subsystems. A major challenge has been to extend the benefits of prognostics to include computer servers and other electronic components. The key enabler for prognostics capabilities is monitoring time series signals relating to the health of executing components and subsystems. Time series signals are processed in real time using pattern recognition for proactive anomaly detection and for remaining useful life estimation. Examples will be presented of the use of pattern recognition techniques for early detection of a number of mechanisms that are known to cause failures in electronic systems, including: environmental issues; software aging; degraded or failed sensors; degradation of hardware components; degradation of mechanical, electronic, and optical interconnects. Prognostics pattern classification is helping to substantially increase component reliability margins and system availability goals while reducing costly sources of "no trouble found" events that have become a significant warranty-cost issue. Bios Aleksey Urmanov is a research scientist at Sun Microsystems. He earned his doctoral degree in Nuclear Engineering at the University of Tennessee in 2002. Dr. Urmanov's research activities are centered around his interest in pattern recognition, statistical learning theory and ill-posed problems in engineering. His most recent activities at Sun focus on developing health monitoring and prognostics methods for EP-enabled computer servers. He is a founder and an Editor of the Journal of Pattern Recognition Research. Anton Bougaev holds a M.S. and a Ph.D. degrees in Nuclear Engineering from Purdue University. Before joining Sun Microsystems Inc. in 2007, he was a lecturer in Nuclear Engineering Department and a member of Applied Intelligent Systems Laboratory (AISL), of Purdue University, West Lafayette, USA. Dr. Bougaev is a founder and the Editor-in-Chief of the Journal of Pattern Recognition Research. His current focus is in reliability physics with emphasis on complex system analysis and the physics of failures which are based on the data driven pattern recognition techniques.

Data and code to reproduce the results in Weix D., Cath T. Y., and Hering A. S. “Monitoring Covariance in Multivariate Time Series: Comparing Machine Learning and Statistical Approaches”. Under Review with Quality and Reliability Engineering International

This dataset provides high-frequency, time-stamped vital sign measurements for anonymized patients, including heart rate, blood pressure, respiratory rate, oxygen saturation, body temperature, and consciousness level. Designed for health monitoring and early warning system development, it supports longitudinal patient analysis and real-time clinical decision support. Device and location metadata enable context-aware analytics and integration with hospital systems.

Anomaly detection in time series data is essential for fraud detection and intrusion monitoring applications. However, it poses challenges due to data complexity and high dimensionality. Industrial applications struggle to process high-dimensional, complex data streams in real time despite existing solutions. This study introduces deep ensemble models to improve traditional time series analysis and anomaly detection methods. Recurrent Neural Networks (RNNs) and Long Short-Term Memory (LSTM) networks effectively handle variable-length sequences and capture long-term relationships. Convolutional Neural Networks (CNNs) are also investigated, especially for univariate or multivariate time series forecasting. The Transformer, an architecture based on Artificial Neural Networks (ANN), has demonstrated promising results in various applications, including time series prediction and anomaly detection. Graph Neural Networks (GNNs) identify time series anomalies by capturing temporal connections and interdependencies between periods, leveraging the underlying graph structure of time series data. A novel feature selection approach is proposed to address challenges posed by high-dimensional data, improving anomaly detection by selecting different or more critical features from the data. This approach outperforms previous techniques in several aspects. Overall, this research introduces state-of-the-art algorithms for anomaly detection in time series data, offering advancements in real-time processing and decision-making across various industrial sectors.

Time Series Analytics for Financial Services Market Outlook

According to our latest research, the global Time Series Analytics for Financial Services market size reached USD 6.8 billion in 2024, with a robust compound annual growth rate (CAGR) of 13.2% observed over the recent period. This market is being propelled by the increasing adoption of advanced analytics and machine learning technologies within the financial sector. By 2033, the market is forecasted to achieve a value of USD 20.7 billion, driven by the growing need for real-time analytics, risk mitigation, and predictive insights across banking, insurance, and asset management domains. The upsurge in digital transformation initiatives and the critical demand for accurate forecasting and fraud detection are among the primary growth factors shaping the industry’s trajectory.

One of the foremost growth drivers for the Time Series Analytics for Financial Services market is the exponential increase in data generation within the sector. Financial institutions are witnessing a surge in the volume, velocity, and variety of transactional and market data, necessitating advanced analytics solutions to derive actionable insights. Time series analytics, which focuses on analyzing sequential data points indexed in time order, enables organizations to detect trends, seasonality, and anomalies in financial data streams. This capability is instrumental in enhancing decision-making processes, optimizing trading strategies, and improving customer experiences. Furthermore, the integration of artificial intelligence and machine learning algorithms with time series analytics tools has significantly amplified the precision and efficiency of analytics outcomes, thus fueling market expansion.

Another critical factor driving market growth is the heightened regulatory scrutiny and compliance requirements in the financial services industry. Financial institutions are mandated to maintain rigorous risk management frameworks to comply with international and regional regulations such as Basel III, MiFID II, and Dodd-Frank. Time series analytics provides the tools necessary for real-time risk assessment, stress testing, and scenario analysis, enabling organizations to proactively identify and mitigate potential risks. The ability to automate compliance reporting and monitor financial transactions in real-time has become indispensable, especially as regulatory environments continue to evolve. This trend is compelling financial entities to invest heavily in advanced analytics platforms, thereby contributing to sustained market growth.

The proliferation of digital banking, mobile payments, and fintech innovations has also played a pivotal role in shaping the Time Series Analytics for Financial Services market. The rise of digital-first financial services has led to a dramatic increase in online transactions, which, in turn, has amplified the need for sophisticated fraud detection and prevention mechanisms. Time series analytics enables continuous monitoring of transactional patterns, allowing for the early identification of fraudulent activities and abnormal behaviors. Additionally, the competitive landscape in financial services is intensifying, with traditional banks and fintech startups vying for market share. This has accelerated the adoption of analytics-driven decision-making to enhance product offerings, personalize customer experiences, and optimize operational efficiencies, further propelling the market forward.

From a regional perspective, North America continues to dominate the global Time Series Analytics for Financial Services market, accounting for the largest revenue share in 2024. The region’s leadership can be attributed to the presence of major financial institutions, advanced technological infrastructure, and a strong focus on innovation. Europe follows closely, driven by stringent regulatory frameworks and a mature banking sector. Meanwhile, the Asia Pacific region is experiencing the fastest growth, fueled by rapid digitalization, expanding fintech ecosystems, and increasing investments in analytics technologies. Latin America and the Middle East & Africa are also witnessing steady adoption, albeit at a slower pace, as financial institutions in these regions gradually embrace digital transformation and analytics-driven solutions.

The agricultural WSN (wireless sensor network) has the characteristics of long operation cycle and wide coverage area. In order to cover as much area as possible, farms usually deploy multiple monitoring devices in different locations of the same area. Due to different types of equipment, monitoring data will vary greatly, and too many monitoring nodes also reduce the efficiency of the network. Although there have been some studies on data fusion algorithms, they have problems such as ignoring the dynamic changes of time series, weak anti-interference ability, and poor processing of data fluctuations. So in this study, a data fusion algorithm for optimal node tracking in agricultural wireless sensor networks is designed. By introducing the dynamic bending distance in the dynamic time warping algorithm to replace the absolute distance in the fuzzy association algorithm and combine the sensor’s own reliability and association degree as the weighted fusion weight, which improved the fuzzy association algorithm. Finally, another three algorithm were tested for multi-temperature sensor data fusion. Compare with the kalman filter, arithmetic mean and fuzzy association algorithm, the average value of the improved data fusion algorithm is 29.5703, which is close to the average value of the other three algorithms, indicating that the data distribution is more even. Its extremely bad value is 8.9767, which is 10.04%, 1.14% and 9.85% smaller than the other three algorithms, indicating that it is more robust when dealing with outliers. Its variance is 2.6438, which is 2.82%, 0.65% and 0.27% smaller than the other three algorithms, indicating that it is more stable and has less data volatility. The results show that the algorithm proposed in this study has higher fusion accuracy and better robustness, which can obtain the fusion value that truly feedbacks the agricultural environment conditions. It reduces production costs by reducing redundant monitoring devices, the energy consumption and improves the data collection efficiency in wireless sensor networks.

AcTBeCalf Dataset Description

The AcTBeCalf dataset is a comprehensive dataset designed to support the classification of pre-weaned calf behaviors from accelerometer data. It contains detailed accelerometer readings aligned with annotated behaviors, providing a valuable resource for research in multivariate time-series classification and animal behavior analysis. The dataset includes accelerometer data collected from 30 pre-weaned Holstein Friesian and Jersey calves, housed in group pens at the Teagasc Moorepark Research Farm, Ireland. Each calf was equipped with a 3D accelerometer sensor (AX3, Axivity Ltd, Newcastle, UK) sampling at 25 Hz and attached to a neck collar from one week of birth over 13 weeks.

This dataset encompasses 27.4 hours of accelerometer data aligned with calf behaviors, including both prominent behaviors like lying, standing, and running, as well as less frequent behaviors such as grooming, social interaction, and abnormal behaviors.

The dataset consists of a single CSV file with the following columns:

• dateTime: Timestamp of the accelerometer reading, sampled at 25 Hz.
• calfid: Identification number of the calf (1-30).
• accX: Accelerometer reading for the X axis (top-bottom direction)*.
• accY: Accelerometer reading for the Y axis (backward-forward direction)*.
• accZ: Accelerometer reading for the Z axis (left-right direction)*.
• behavior: Annotated behavior based on an ethogram of 23 behaviors.
• segId: Segment identification number associated with each accelerometer reading/row, representing all readings of the same behavior segment.

* the directions are mentioned in relation to the position of the accelerometer sensor on the calf.

Code Files Description

The dataset is accompanied by several code files to facilitate the preprocessing and analysis of the accelerometer data and to support the development and evaluation of machine learning models. The main code files included in the dataset repository are:

1. accelerometer_time_correction.ipynb: This script corrects the accelerometer time drift, ensuring the alignment of the accelerometer data with the reference time.
2. shake_pattern_detector.py: This script includes an algorithm to detect shake patterns in the accelerometer signal for aligning the accelerometer time series with reference times.
3. aligning_accelerometer_data_with_annotations.ipynb: This notebook aligns the accelerometer time series with the annotated behaviors based on timestamps.
4. manual_inspection_ts_validation.ipynb: This notebook provides a manual inspection process for ensuring the accurate alignment of the accelerometer data with the annotated behaviors.
5. additional_ts_generation.ipynb: This notebook generates additional time-series data from the original X, Y, and Z accelerometer readings, including Magnitude, ODBA (Overall Dynamic Body Acceleration), VeDBA (Vectorial Dynamic Body Acceleration), pitch, and roll.
6. genSplit.py: This script provides the logic used for the generalized subject separation for machine learning model training, validation and testing.
7. active_inactive_classification.ipynb: This notebook details the process of classifying behaviors into active and inactive categories using a RandomForest model, achieving a balanced accuracy of 92%.
8. four_behv_classification.ipynb: This notebook employs the mini-ROCKET feature derivation mechanism and a RidgeClassifierCV to classify behaviors into four categories: drinking milk, lying, running, and other, achieving a balanced accuracy of 84%.

Kindly cite one of the following papers when using this data:

Dissanayake, O., McPherson, S. E., Allyndrée, J., Kennedy, E., Cunningham, P., & Riaboff, L. (2024). Evaluating ROCKET and Catch22 features for calf behaviour classification from accelerometer data using Machine Learning models. arXiv preprint arXiv:2404.18159.

Dissanayake, O., McPherson, S. E., Allyndrée, J., Kennedy, E., Cunningham, P., & Riaboff, L. (2024). Development of a digital tool for monitoring the behaviour of pre-weaned calves using accelerometer neck-collars. arXiv preprint arXiv:2406.17352