Multi-sensor Time Series Data Research Articles

Classification of faults in friction stir processed composites using a machine learning and ensemble learning approach

Abstract Aluminium alloy based surface composites with hard reinforcement particles have wide scope in aerospace and automobile manufacturing industries. In this paper, the aluminium composites, manufactured by friction stir processing (FSP) with varying parameters are investigated for the faults occurred during fabrication process. It explores a machine-learning approach to detect defects of surface hybrid composites with an Al6061 alloy matrix, reinforced with copper and graphene nano-powders, using friction stir processing and a tungsten carbide tool on a milling machine. Multi-sensor time series data (vibration, force, and current) collected during fabrication, is preprocessed and labelled with normal and defective categories (e.g., pin break, brazing break, rough surface, no composite) using visual inspection. The important time domain and frequency domain features are extracted using different libraries in python. Thenafter, various types of feature selection techniques, viz filter, wrapper and embedded methods are implemented to select most relevant features. The selected subset of features from all selection methods used, are applied to different machine learning and ensemble learning classifiers and their performances are evaluated. The optimal combinations of the type of feature selection method and classifier used, are obtained for efficient classification of surface defects in composited formed by FSP. The real time monitoring and defect detection system can be developed in future for the composites developed by FSP using the developed models.

Multi-sensor temporal-spatial graph network fusion empirical mode decomposition convolution for machine fault diagnosis

Multi-sensor time-series data at different locations contains not only temporal correlation information but also spatial correlation information which is treasure for machine fault diagnosis. Existing graph construction methods mainly apply different data analysis methods to connect nodes and edges. Few works, however, consider the location of the sensor itself and temporal correlation information of multi-sensor time-series data. To mine the relationship between spatial information and temporal information, the multi-sensor temporal-spatial graph is constructed in this paper. Hereinto, the different data points of multi-sensor are severed as different nodes which represents the spatial feature information. The temporal information is contained between different nodes of the same sensor. Moreover, an empirical mode decomposition graph convolution network (EGCN) is proposed to extract the feature. Specifically, the traditional graph convolution operator is changed to empirical mode decomposition which can decompose the input features into multiple intrinsic modal features to achieve adaptive feature extraction and improve the representation capability of the network. Finally, the different fault types can be classified by fully connected layers. Experiments from different test rigs demonstrate that the proposed method achieves a diagnostic accuracy exceeding 99 % under limited fault samples.

TimeTector: A Twin-Branch Approach for Unsupervised Anomaly Detection in Livestock Sensor Noisy Data (TT-TBAD).

Unsupervised anomaly detection in multivariate time series sensor data is a complex task with diverse applications in different domains such as livestock farming and agriculture (LF&A), the Internet of Things (IoT), and human activity recognition (HAR). Advanced machine learning techniques are necessary to detect multi-sensor time series data anomalies. The primary focus of this research is to develop state-of-the-art machine learning methods for detecting anomalies in multi-sensor data. Time series sensors frequently produce multi-sensor data with anomalies, which makes it difficult to establish standard patterns that can capture spatial and temporal correlations. Our innovative approach enables the accurate identification of normal, abnormal, and noisy patterns, thus minimizing the risk of misinterpreting models when dealing with mixed noisy data during training. This can potentially result in the model deriving incorrect conclusions. To address these challenges, we propose a novel approach called "TimeTector-Twin-Branch Shared LSTM Autoencoder" which incorporates several Multi-Head Attention mechanisms. Additionally, our system now incorporates the Twin-Branch method which facilitates the simultaneous execution of multiple tasks, such as data reconstruction and prediction error, allowing for efficient multi-task learning. We also compare our proposed model to several benchmark anomaly detection models using our dataset, and the results show less error (MSE, MAE, and RMSE) in reconstruction and higher accuracy scores (precision, recall, and F1) against the baseline models, demonstrating that our approach outperforms these existing models.

Nearest advocate: a novel event-based time delay estimation algorithm for multi-sensor time-series data synchronization

Estimating time delays in event-based time-series is a crucial task in signal processing as it affects the data quality and is a prerequisite for many subsequent analyses. In particular, data acquired from wearable devices often suffer from a low timestamp precision or clock drift. Current state-of-the-art methods such as Pearson Cross-Correlation are sensitive to typical data quality issues, e.g. misdetected events, and Dynamic Time Warping is computationally expensive. To overcome these limitations, we propose Nearest Advocate, a novel event-based time delay estimation method for multi-sensor time-series data synchronisation. We evaluate its performance using three independent datasets acquired from wearable sensor systems, demonstrating its superior precision, particularly for short, noisy time-series with missing events. Additionally, we introduce a sparse variant that balances precision and runtime. Finally, we demonstrate how Nearest Advocate can be used to solve the problem of linear as well as non-linear clock drifts. Thus, Nearest Advocate offers a promising opportunity for time delay estimation and post-hoc synchronization for challenging datasets across various applications.

An integrated deep neural network model combining 1D CNN and LSTM for structural health monitoring utilizing multisensor time-series data

Introducing deep learning algorithms into the field of structural health monitoring (SHM) has contributed to the automatic extraction of damage-sensitive features, but the type and architecture of these algorithms are still in dispute. This paper proposes a hybrid deep learning framework entitled time-distributed one-dimensional convolutional neural network (1D CNN) long short-term memory (LSTM) model, which utilizes raw multisensor time histories to detect structural damages. Using a sliding window that moves along the temporal dimension, the multisensor data are first segmented into subsequences. The 1D CNN layers are simultaneously applied to each subsequence to extract damage-sensitive features from row data samples. These features are then fed into the LSTM layers to extract temporal features between subsequences. As the final step, these extracted features are classified using fully connected layers. In order to assess the performance of this model, a numerical model of a high-rise frame with nonlinear members is used. This hybrid model is assumed to identify the location of damages to this frame. In order to assess the proposed model with a real-world structure, a well-known benchmark building is employed to identify damage patterns by this deep hybrid neural network. A set of metrics related to the performance of the model is measured and evaluated. It is found that the model has an average accuracy of above 96.6% in localizing damage in the numerical structure and above 99.6% in detecting each damage pattern in the experimental building. The results indicate that the proposed model can be applied effectively to the SHM of different structural systems with different damage patterns.

Data Fusion and Pattern Classification in Dynamical Systems Via Symbolic Time Series Analysis

Abstract Symbolic time series analysis (STSA) plays an important role in the investigation of continuously evolving dynamical systems, where the capability to interpret the joint effects of multiple sensor signals is essential for adequate representation of the embedded knowledge. This technical brief develops and validates, by simulation, an STSA-based algorithm to make timely decisions on dynamical systems for information fusion and pattern classification from ensembles of multisensor time series data. In this context, one of the most commonly used methods has been neural networks (NN) in their various configurations; however, these NN-based methods may require large-volume data and prolonged computational time for training. An alternative feasible method is the STSA-based probabilistic finite state automata (PFSA), which has been shown in recent literature to require significantly less training data and to be much faster than NN for training and, to some extent, for testing. This technical brief reports a modification of the current PFSA methods to accommodate (possibly heterogeneous and not necessarily tightly synchronized) multisensor data fusion and (supervised learning-based) pattern classification in real-time. Efficacy of the proposed method is demonstrated by fusion of time series of position and velocity sensor data, generated from a simulation model of the forced Duffing equation.

A multimode structured prediction model based on dynamic attribution graph attention network for complex industrial processes

Complex industrial processes with dynamic and time-varying characteristics, as well as diverse operating conditions, pose challenges in developing accurate real-time online prediction models for the key performance indicator (KPI). To address these challenges, a KPI prediction framework is proposed in this study, which utilizes a multimode structured prediction model based on a dynamic-attribution graph attention network (DAGAT). First, a multimode clustering method based on a Gaussian mixture model is designed to divide and locate industrial multimode operational data. Second, to address the limitations of traditional deep network models in accurately capturing the complex relationships between process variables and KPI, a graph structure is used to model multi-sensor time series data. Subsequently, a novel DAGAT is proposed to improve node prediction performance and interpretation of industrial graph data. Considering the cumulative effect of large-scale equipment, the DAGAT incorporates knowledge of the industrial process, enabling it to capture the influence of chemical-reaction variables. Simultaneously, the Huber loss function is used to further optimize the prediction results. Moreover, the model can calculate in real-time the contribution of each individual process variable to KPI, providing guidance for optimal control. Finally, the effectiveness and superiority of the proposed method are validated through an industrial case.

Health condition monitoring of machines based on long short-term memory convolutional autoencoder

Machine health assessment is crucial to prognostics and health management (PHM), which can increase reliability of machines while reducing operation cost. However, the data collected from machines in real-world cases are noised and high-dimensional, so that it is very difficult to detect the early defects of machines. Moreover, it is still a challenging problem to capture sequential information from multi-sensor signals for machine health assessment. This paper proposes a novel autoencoder (AE), called long short-term memory convolutional autoencoder (LSTMCAE), where LSTM and convolutional units are embedded in this specific network for feature learning from sensor signals based on unsupervised-learning. A long short-term memory (LSTM) unit in LSTMCAE is utilized to capture sequential information from multi-sensor time series data. A convolutional and deconvolutional unit is further embedded after the LSTM unit to filter noise and extract features corresponding to health state of machines. Residual learning is employed to reduce the training difficulty and improve the feature learning performance of LSTMCAE. Multivariate Gaussian distribution (MGD) is adopted to generate health index (HI) based on reconstruction errors of LSTMCAE for quantifying machines health state. A contribution analysis-based feature selection method is proposed to select effective features for machinery health assessment. Experimental results on turbofan engines demonstrate the effectiveness of LSTMCAE for machine health assessment. Compared with other unsupervised learning methods, the HIs generated by LSTMCAE show better tendency. LSTMCAE can detect earlier slight degradation than LSTM-AE. Moreover, contribution analysis results indicate that the sensitive variables can be selected for machine health monitoring. Residual learning significantly improves the feature learning performance of LSTMCAE. Thus, LSTMCAE can well quantify the degradation trend of machines. The experimental results on engines show that the proposed method will be an effective tool for machine health assessment.

Unsupervised Deep Anomaly Detection for Multi-Sensor Time-Series Signals

Nowadays, multi-sensor technologies are applied in many fields, e.g., Health Care (HC) and Human Activity Recognition (HAR). These sensors can generate a substantial amount of multivariate time-series data. Unsupervised anomaly detection on multi-sensor time-series data has been proven critical in machine learning researches. The key challenge is to discover generalized normal patterns by capturing spatial-temporal correlation in time series. Beyond this challenge, noisy data is often intertwined with training data, which is likely to mislead the model by making it hard to distinguish between normal, abnormal, and noisy data. Few of previous researches can jointly address these two challenges. In this paper, we propose a novel deep learning-based anomaly detection algorithm called Deep Convolutional Autoencoding Memory network (CAE-M). We first build a Deep Convolutional Autoencoder to characterize spatial dependence of high-dimensional data with a Maximum Mean Discrepancy (MMD) to better distinguish between the noisy, normal, and abnormal data. Then, we construct a Memory Network consisting of linear (Autoregressive Model) and non-linear predictions (Bidirectional LSTM with Attention) to capture temporal dependence from time-series data. Finally, CAE-M jointly optimizes these two subnetworks. We compare the proposed approach with several state-of-the-art anomaly detection methods on HAR and HC datasets. Experimental results demonstrate that our proposed model outperforms these existing method

Degradation-Aware Remaining Useful Life Prediction With LSTM Autoencoder

The remaining useful life (RUL) prediction plays a pivotal role in the predictive maintenance of industrial manufacturing systems. However, one major problem with the existing RUL estimation algorithms is the assumption of a single health degradation trend for different machine health stages. To improve the RUL prediction accuracy with various degradation trends, this article proposes an algorithm dubbed degradation-aware long short-term memory (LSTM) autoencoder (AE) (DELTA). First, the Hilbert transform is adopted to evaluate the degradation stage and factor with the real-time sensory signal. Second, we adopt LSTM AE to predict RUL based on multisensor time-series data and the degradation factor. Distinct from the existing studies, the proposed framework is able to dynamically model the degradation factor and explore latent variables to improve RUL prediction accuracy. The performance of DELTA is evaluated with the open-source FEMTO bearing data set. Compared with the existing algorithms, DELTA achieves appreciable improvements in the RUL prediction accuracy.

Data-driven Prognostics with Predictive Uncertainty Estimation using Ensemble of Deep Ordinal Regression Models

Prognostics or Remaining Useful Life (RUL) Estimation from multi-sensor time series data is useful to enable condition-based maintenance and ensure high operational availability of equipment. We propose a novel deep learning based approach for Prognostics with Uncertainty Quantification that is useful in scenarios where: (i) access to labeled failure data is scarce due to rarity of failures (ii) inherent noise ispresent in the sensor readings. The two scenarios mentioned are unavoidable sources of uncertainty in the RUL estimation process, often resulting in unreliable RUL estimates. To address (i), we formulate RUL estimation as an Ordinal Regression (OR) problem and propose LSTM-OR: deep Long Short Term Memory (LSTM) network-based approach to learn the OR function. We show that LSTM-OR naturally allows for the incorporation of censored operational instances in training along with the failed instances, leading to more robust learning. To address (ii), we propose a simple yet effectiveapproach to quantify predictive uncertainty in the RUL estimation models by training an ensemble of LSTM-OR models. Through empirical evaluation on the publicly available turbofan engine benchmark datasets, we demonstrate that LSTMOR is at par with commonly used deep metric regressionbased approaches for RUL estimation when sufficient failed instances are available for training. Importantly, LSTM-OR outperforms these metric regression-based approaches in the practical scenario where failed training instances are scarce, but sufficient operational (censored) instances are additionally available. Furthermore, our uncertainty quantification approach yields high-quality predictive uncertainty estimateswhile also leading to improved RUL estimates compared to single best LSTM-OR models.

Landslide mapping from multi-sensor data through improved change detection-based Markov random field

Accurate landslide inventory mapping is essential for quantitative hazard and risk assessment. Although multi-temporal change detection techniques have contributed greatly to landslide inventory preparation, it is still challenging to generate quality change detection images (CDIs) for accurate landslide mapping. The recently proposed change detection-based Markov random field (CDMRF) provides an effective approach for rapid mapping of landslides with minimum user interventions. However, when CDI is generated by change vector analysis (CVA) alone, the CDMRF method may suffer from noise especially when the pre- and post-event remote sensing images are acquired under different atmospheric, illumination, and phenological conditions. This paper improved such CDMRF approach by integrating normalized difference vegetation index (NDVI), principal component analysis (PCA), and independent component analysis (ICA) generated CDIs with MRF for landslide inventory mapping from multi-sensor data. To justify the effectiveness and applicability, the improved methods were applied to map rainfall-, typhoon-, and earthquake-triggered landslides from the pre- and post-event satellite images acquired by very high resolution QuickBird, high resolution FORMOSAT-2, and moderate resolution Sentinel-2. Moreover, they were tested on pre-event Landsat-8 and post-event Sentinel-2 datasets, indicating that they are operational for landslide inventory mapping from combined multi-temporal and multi-sensor data. The results demonstrate that the improved δNDVI-, PCA-, and ICA-based approaches perform much better than CVA-based CDMRF in terms of completeness, correctness, Kappa coefficient, and F-measures. To the best of our knowledge, it is the first time that NDVI, PCA, and ICA are integrated with MRF for landslide inventory mapping from multi-sensor data. It is anticipated that this research can be a starting point for developing new change detection techniques that can readily generate quality CDI and for applying advanced machine learning algorithms (e.g., deep learning) to automatic detection of natural hazards from multi-sensor time series data.

On Practical Aspects of Using RNNs for Fault Detection in Sparsely-labeled Multi-sensor Time Series

In this work, we attempt to address two practical limitations when using Recurrent Neural Networks (RNNs) as classifiers for fault detection using multi-sensor time series data: Firstly, there is a need to understand the classification decisions of RNNs. It is difficult for engineers to diagnose the faults when multiple sensors are being monitored at once. The faults detected by RNNs can be better understood if the sensors carrying the faulty signature are known. To achieve this, we propose a sensor relevance scoring (SRS) approach that scores each sensor based on its contribution to the classification decision by leveraging the hidden layer activations of RNNs. Secondly, lack of labeled training data due to infrequent faults (or otherwise) makes it difficult to train RNNs in a supervised manner. We pre-train an RNN on large unlabeled data via an autoencoder in an unsupervised manner, and then finetune the RNN for the fault detection task using small amount of labeled training data. Through experiments on a public gasoil heating loop dataset and a proprietary pump dataset, we demonstrate the efficacy of the proposed solutions, and show that i) SRS can help point to the sensors relevant for a fault, ii) large unlabeled data can be used to pre-train an RNNbased fault detector in an unsupervised manner in sparselylabeled scenarios, and iii) a purely unsupervised approach for fault detection (e.g. based on RNN-autoencoders) may not suffice when the number of sensors being monitored is large while the signature for fault is present in only a small subset of sensors.

Data to diagnosis in global health: a 3P approach

BackgroundWith connected medical devices fast becoming ubiquitous in healthcare monitoring there is a deluge of data coming from multiple body-attached sensors. Transforming this flood of data into effective and efficient diagnosis is a major challenge.MethodsTo address this challenge, we present a 3P approach: personalized patient monitoring, precision diagnostics, and preventive criticality alerts. In a collaborative work with doctors, we present the design, development, and testing of a healthcare data analytics and communication framework that we call RASPRO (Rapid Active Summarization for effective PROgnosis). The heart of RASPRO is Physician Assist Filters (PAF) that transform unwieldy multi-sensor time series data into summarized patient/disease specific trends in steps of progressive precision as demanded by the doctor for patient’s personalized condition at hand and help in identifying and subsequently predictively alerting the onset of critical conditions. The output of PAFs is a clinically useful, yet extremely succinct summary of a patient’s medical condition, represented as a motif, which could be sent to remote doctors even over SMS, reducing the need for data bandwidths. We evaluate the clinical validity of these techniques using SVM machine learning models measuring both the predictive power and its ability to classify disease condition. We used more than 16,000 min of patient data (N=70) from the openly available MIMIC II database for conducting these experiments. Furthermore, we also report the clinical utility of the system through doctor feedback from a large super-speciality hospital in India.ResultsThe results show that the RASPRO motifs perform as well as (and in many cases better than) raw time series data. In addition, we also see improvement in diagnostic performance using optimized sensor severity threshold ranges set using the personalization PAF severity quantizer.ConclusionThe RASPRO-PAF system and the associated techniques are found to be useful in many healthcare applications, especially in remote patient monitoring. The personalization, precision, and prevention PAFs presented in the paper successfully shows remarkable performance in satisfying the goals of 3Ps, thereby providing the advantages of three A’s: availability, affordability, and accessibility in the global health scenario.

A Time-Distributed Spatiotemporal Feature Learning Method for Machine Health Monitoring with Multi-Sensor Time Series.

Data-driven methods with multi-sensor time series data are the most promising approaches for monitoring machine health. Extracting fault-sensitive features from multi-sensor time series is a daunting task for both traditional data-driven methods and current deep learning models. A novel hybrid end-to-end deep learning framework named Time-distributed ConvLSTM model (TDConvLSTM) is proposed in the paper for machine health monitoring, which works directly on raw multi-sensor time series. In TDConvLSTM, the normalized multi-sensor data is first segmented into a collection of subsequences by a sliding window along the temporal dimension. Time-distributed local feature extractors are simultaneously applied to each subsequence to extract local spatiotemporal features. Then a holistic ConvLSTM layer is designed to extract holistic spatiotemporal features between subsequences. At last, a fully-connected layer and a supervised learning layer are stacked on the top of the model to obtain the target. TDConvLSTM can extract spatiotemporal features on different time scales without any handcrafted feature engineering. The proposed model can achieve better performance in both time series classification tasks and regression prediction tasks than some state-of-the-art models, which has been verified in the gearbox fault diagnosis experiment and the tool wear prediction experiment.

Using SAR satellite data time series for regional glacier mapping

Abstract. With dense SAR satellite data time series it is possible to map surface and subsurface glacier properties that vary in time. On Sentinel-1A and RADARSAT-2 backscatter time series images over mainland Norway and Svalbard, we outline how to map glaciers using descriptive methods. We present five application scenarios. The first shows potential for tracking transient snow lines with SAR backscatter time series and correlates with both optical satellite images (Sentinel-2A and Landsat 8) and equilibrium line altitudes derived from in situ surface mass balance data. In the second application scenario, time series representation of glacier facies corresponding to SAR glacier zones shows potential for a more accurate delineation of the zones and how they change in time. The third application scenario investigates the firn evolution using dense SAR backscatter time series together with a coupled energy balance and multilayer firn model. We find strong correlation between backscatter signals with both the modeled firn air content and modeled wetness in the firn. In the fourth application scenario, we highlight how winter rain events can be detected in SAR time series, revealing important information about the area extent of internal accumulation. In the last application scenario, averaged summer SAR images were found to have potential in assisting the process of mapping glaciers outlines, especially in the presence of seasonal snow. Altogether we present examples of how to map glaciers and to further understand glaciological processes using the existing and future massive amount of multi-sensor time series data.

Structural health monitoring of a footbridge using Echo State Networks and NARMAX

Echo State Networks (ESNs) and a Nonlinear Auto-Regressive Moving Average model with eXogenous inputs (NARMAX) have been applied to multi-sensor time-series data arising from a test footbridge which has been subjected to multiple potentially damaging interventions. The aim of the work was to automatically classify known potentially damaging events, while also allowing engineers to observe and localise any long term damage trends. The techniques reported here used data from ten temperature sensors as inputs and were tasked with predicting the output signal from eight tilt sensors embedded at various points over the bridge. Initially, interventions were identified by both ESNs and NARMAX. In addition, training ESNs using data up to the first event, and determining the ESNs’ subsequent predictions, allowed inferences to be made not only about when and where the interventions occurred, but also the level of damage caused, without requiring any prior data pre-processing or extrapolation. Finally, ESNs were successfully used as classifiers to characterise various different types of intervention that had taken place.

Derivation of long-term spatiotemporal landslide activity—A multi-sensor time series approach

Abstract This paper presents a remote sensing-based method to efficiently derive multi-temporal landslide inventories over large areas, which allows for the spatiotemporal analysis of landslide activity, which is an important prerequisite in systematic regional landslide hazard and risk assessment. The developed method uses globally archived satellite remote sensing data for a retrospective systematic assessment of past multi-temporal landslide activity. Landslides are automatically identified as spatially explicit objects based on landslide-specific vegetation cover changes using temporal NDVI-trajectories and complementary relief-oriented parameters. To enable the long-term analysis of large areas with highest possible temporal resolution, the developed method facilitates the use of a large amount of optical multi-sensor time series data. The database of this study consists of 212 datasets that comprise freely available Landsat TM & ETM + data and SPOT 1 & 5, IRS1-C LISSIII, ASTER, and RapidEye data. These data were acquired between 1986 and 2013 and cover a landslide-prone area of 2500 km 2 in southern Kyrgyzstan. We identified 1583 landslide objects ranging in size between 50 m 2 and 2.8 km 2 . Spatiotemporal analysis of the landslides that were detected during these 27 years reveals continuous landslide activity of varying intensity. The highest overall landslide rates occurred in 2003 and 2004, exceeding the long-term annual average rate of 57 landslides per year by more than a factor of five. The areas of highest landslide activity are also determined, whereas most of these areas were persistent over time.

Robust Automated Image Co-Registration of Optical Multi-Sensor Time Series Data: Database Generation for Multi-Temporal Landslide Detection

Reliable multi-temporal landslide detection over longer periods of time requires multi-sensor time series data characterized by high internal geometric stability, as well as high relative and absolute accuracy. For this purpose, a new methodology for fully automated co-registration has been developed allowing efficient and robust spatial alignment of standard orthorectified data products originating from a multitude of optical satellite remote sensing data of varying spatial resolution. Correlation-based co-registration uses world-wide available terrain corrected Landsat Level 1T time series data as the spatial reference, ensuring global applicability. The developed approach has been applied to a multi-sensor time series of 592 remote sensing datasets covering an approximately 12,000 km2 area in Southern Kyrgyzstan (Central Asia) strongly affected by landslides. The database contains images acquired during the last 26 years by Landsat (E)TM, ASTER, SPOT and RapidEye sensors. Analysis of the spatial shifts obtained from co-registration has revealed sensor-specific alignments ranging between 5 m and more than 400 m. Overall accuracy assessment of these alignments has resulted in a high relative image-to-image accuracy of 17 m (RMSE) and a high absolute accuracy of 23 m (RMSE) for the whole co-registered database, making it suitable for multi-temporal landslide detection at a regional scale in Southern Kyrgyzstan.

A Proposal for Classification of Multisensor Time Series Data based on Time Delay Embedding

Abstract Multisensor time series data is common in many ap- plications of process industry, medical and health care, biometrics etc.Analysis of multisensor time series data requires analysis of multidimensional time series(MTS) which is challenging as they constitute a huge volume of data of dynamic nature. Traditional machine learning algorithms for classification and clustering developed for static data can not be applied directly to MTS data. Various techniques have been developed to represent MTS data in a suitable manner for analysis by popular machine learning algorithms. Though a plethora of different approaches have been developed so far, 1NN classifier based on dynamic time warping (DTW) has been found to be the most popular due to its simplicity. In this work, an approach for time series classification is proposed based on multidimensional delay vector representation of time series. Multivariate time series is considered here as a group of single time series and each time series is processed separately to be represented by a multidimensional delay vector (MDV). A simple simulation experiment with online handwritten signature data has been done with a similarity measure based on the MDV representation and classification performance is compared with DTW based classifier. The simulation results show that classification accuracy of the proposed approach is satisfactory while computational cost is lower than DTW method.