Review on time series databases and recent research trends in Time Series Mining

Garima, .; Rani, Sangeeta

doi:10.1109/confluence.2014.6949290

Cited by 8 publications

(4 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are many frequently used activation functions, including sigmoid function, tanh function (hyperbolic tangent function), relu function (Rectified Linear Unit), etc. The relu function can solve the problem of gradient disappearance, and its calculation speed and convergence speed are faster than sigmoid function and tanh function, which is defined as equation (9).…”

Section: The Hybrid Cnn-lstm Modelmentioning

confidence: 99%

“…This air quality data is closely related to time, which means it belongs to time series data [8], and has obvious periodicity. Because of the timeliness of data, time series prediction has become a hot topic [9]. Time series analysis plays an important role in a large variety of application fields, such as economics, medicine, astronomy, geology, etc.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Hybrid CNN-LSTM Model for Forecasting Particulate Matter (PM2.5)

2020

View full text Add to dashboard Cite

PM2.5 is one of the most important pollutants related to air quality, and the increase of its concentration will aggravate the threat to people's health. Therefore, the prediction of surface PM2.5 concentration is of great significance to human health protection. In this study, A hybrid CNN-LSTM model is developed by combining the convolutional neural network (CNN) with the long short-term memory (LSTM) neural network for forecasting the next 24h PM2.5 concentration in Beijing, which makes full use of their advantages that CNN can effectively extract the features related to air quality and the LSTM can reflect the long term historical process of input time series data. The air quality data of the last 7days and the PM2.5 concentration of the next day are first set as the input and output of the model due to the periodicity, respectively. Subsequently four models namely univariate LSTM model, multivariate LSTM model, univariate CNN-LSTM model and multivariate CNN-LSTM model, are established for PM2.5 concentration prediction. Finally, mean absolute error (MAE) and root mean square error (RMSE) are employed to evaluate the performance of these models and results show that the proposed multivariate CNN-LSTM model performs the best results due to low error and short training time.

show abstract

Section: The Hybrid Cnn-lstm Modelmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Hybrid CNN-LSTM Model for Forecasting Particulate Matter (PM2.5)

2020

View full text Add to dashboard Cite

show abstract

“…This approach that provides fine-granular and high-frequency data about network states and other measurement statistics plays an important role in monitoring network events, performance, and security metrics. In order to increase the speed of the systems, it is more important how data are modeled and parsed rather than how data are transported [31]. Thus, we customized a collector to collect measurement data in an encoding mechanism that is commonly used in the literature for many purposes but is new in anomaly detection and mitigation.…”

Section: Telemetry Modulementioning

confidence: 99%

Real-time anomaly detection and mitigation using streaming telemetry in SDN

Kurt¹,

Erdem²

2020

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

Measurement and monitoring are crucial for various network tasks such as traffic engineering, anomaly detection, and intrusion prevention. The success of critical capabilities such as anomaly detection and prevention depends on whether the utilized network measurement method is able to provide granular, near real-time, low-overhead measurement data or not. In addition to the measurement method, the anomaly detection and mitigation algorithm is also essential for recognizing normal and abnormal traffic patterns in such a huge amount of measured data with high accuracy and low latency. Software-defined networking is an emerging concept to enable programmable and efficient measurement functions for these kinds of challenging requirements. In this paper, we present a new, real-time, modeldriven anomaly detection and mitigation platform. Model-driven streaming telemetry and exponential smoothing are the underlying approaches of the platform. A customized collector is proposed to gather streaming telemetry metrics, and Holt's prediction algorithm is improved to handle real-time streaming data and decrease false positives. The developed system is tested on a campus network and the success rate of the system is calculated as 92%.

show abstract

“…This information on air quality has a clear periodicity and is tightly tied to time, making it a time series data [13]. The timely nature of the data has made time series prediction a popular subject [14].…”

Section: Introductionmentioning

confidence: 99%

Time Series Analysis Based Air Pollution Level Prediction Using Long Short Term Memory Recurrent Neural Network with Attention Mechanism

K. Azhahudurai, V. Veeramanikandan

2023

tjjpt

View full text Add to dashboard Cite

Air pollution has grown significantly as a threat to the environment during the past few decades. It has had a profound effect on the ecosystem, public health, and safety. For government agencies to design plans for pollution prevention, predicting the extent of air pollution becomes essential for maintaining the environment and environmental protection. One of the efficient approaches to solving the problem of predicting the level of air pollutants is time series analysis. The drawbacks of conventional machine learning algorithms in time series analysis are solved by employing deep learning algorithms in a variety of ways. Deep Learning models learn features and dynamics exclusively and directly from the data, in contrast to Machine Learning models, such as autoregressive models (AR) or exponential smoothing, where feature engineering is conducted manually and frequently certain parameters are adjusted while taking domain expertise into account. To forecast the level of pollution in the following hour using the current hour's weather and pollution levels, a Recurrent Neural Network (RNN) model based on Long Short Term Memory (LSTM) units has been trained, tested, and optimized. The predictive model has been developed with both uni-variate, which takes into account only one feature, and multi-variate, which takes into account many features. To improve the performance of the model on long input sequences attention mechanism has been implemented.

show abstract

Review on time series databases and recent research trends in Time Series Mining

Cited by 8 publications

References 26 publications

A Hybrid CNN-LSTM Model for Forecasting Particulate Matter (PM2.5)

A Hybrid CNN-LSTM Model for Forecasting Particulate Matter (PM2.5)

Real-time anomaly detection and mitigation using streaming telemetry in SDN

Time Series Analysis Based Air Pollution Level Prediction Using Long Short Term Memory Recurrent Neural Network with Attention Mechanism

Contact Info

Product

Resources

About