Time series

A recent study [1] alerts on the limitations of evaluating anomaly detection algorithms on popular time-series datasets such as Yahoo, Numenta, or NASA, among others. In particular, these datasets are noted to suffer from known flaws suchas trivial anomalies, unrealistic anomaly density, mislabeled ground truth, and run-to-failure bias. The TELCO dataset corresponds to twelve different time-series, with a temporal granularity of five minutes per sample, collected and manually labeled for a period of seven months between January 1 and July 31, 2021.


This dataset includes real-world Channel Quality Indicator (CQI) values from UEs connected to real commercial LTE networks in Greece. Channel Quality Indicator (CQI) is a metric posted by the UEs to the base station (BS). It is linked with the allocation of the UE’s modulation and coding schemes and ranges from 0 to 15 in values. This is from no to 64 QAM modulation, from zero to 0.93 code rate, from zero to 5.6 bits per symbol, from less than 1.25 to 20.31 SINR (dB) and from zero to 3840 Transport Block Size bits.


This dataset includes the relevant data for the journal article titled 'A Novel LSTM Pipeline to Detect Anomalies in Manufacturing Production'. In this paper, we present a novel anomaly detection method using a semi-supervised LSTM forecasting approach to highlight process anomalies in a complex, real-world dataset in an automotive manufacturing setting. This data includes two time-series subsets, each with 5000 labeled observations.



Europe is covered by distinct climatic zones which include semiarid, the Mediterranean, humid subtropical, marine,

humid continental, subarctic, and highland climates. Land use and land cover change have been well documented in the

past 200 years across Europe1where land cover grassland and cropland together make up 39%2. In recent years, the

agricultural sector has been affected by abnormal weather events. Climate change will continue to change weather


The dataset is composed of digital signals obtained from a capacitive sensor electrodes that are immersed in water or in oil. Each signal, stored in one row, is composed of 10 consecutive intensity values and a label in the last column. The label is +1 for a water-immersed sensor electrode and -1 for an oil-immersed sensor electrode. This dataset should be used to train a classifier to infer the type of material in which an electrode is immersed in (water or oil), given a sample signal composed of 10 consecutive values.


This dataset consists of sensory data of digits, i.e., from 0 to 9. The dataset is collected from 20 volunteers by using a 9−axis Inertial Measurement Unit (IMU) equipped marker pen. The objective of this dataset is to design classification algorithms for recognizing a handwritten digit in real-time.


The CREATE database is composed of 14 hours of multimodal recordings from a mobile robotic platform based on the iRobot Create.