Questions tagged [time-series]
Time series are data observed over time (either in continuous time or at discrete time periods).
0
votes
0answers
7 views
One sided time series alignment with dynamic time warping - reference constraint
I want to align multiple time series sequences $T:=\lbrace t_1,\ldots,t_N\rbrace$ of varied length in time using Dynamic Time Warping (DTW), such that all vectors in $T_{warped}$ will have the same ...
0
votes
0answers
10 views
Loss function returns nan on time series dataset using tensorflow
This was the follow up question of Prediction on timeseries data using tensorflow.
I have an input and output of below format.
...
0
votes
0answers
6 views
Looking for freely available labelled time series data sets for automated feature extraction and selection
I am looking for recommendations of big, labelled time series datasets that are freely available on the net.
My aim is to apply and evaluate methods of automatic feature generation and selection, ...
0
votes
0answers
4 views
Truncating RNN due to limited resources
I am currently working with time series data and am able to fit it to a RNN in Keras. However, I am continually getting new data and it becomes computationally more expensive to train on all of the ...
0
votes
0answers
6 views
How to denormalize data used to train a RNN?
I am running the code defined in the "usage" section of this repo.
I get the same output :
Before training and testing, the data is normalized with the following code :
...
0
votes
1answer
18 views
Why does my LSTM perform better when randomizing training subset vs. standard batch training?
I am training a simple LSTM network using Keras to predict time series values. It is a simple 2-layer LSTM.
I get the best performance when I train on subsets of the training set that start at random ...
0
votes
0answers
11 views
Online learning of time series signatures [closed]
What's the current best in class method for one shot or online learning of signatures or repeating patterns in a continuously valued time series? I'm especially interested in methods applied to real-...
0
votes
1answer
19 views
Generating a set of different scenarios based on some initial observations
I have a in my hands 3 different time series which model 3 different scenarios (base, downside, upside). Every of this time-series depends on a set of 11 different attributes, which take values for ...
1
vote
1answer
45 views
Prediction on timeseries data using tensorflow
I have an input and output of below format.
(X) = [[ 0 1 2]
[ 1 2 3]]
y = [ 3 4 ]
Its a timeseries data. The task is to predict the next ...
-1
votes
0answers
20 views
Machine Learning Model [closed]
I have a dataframe with columns as Month,Number of Demand, SkillsList,Location,Experience Grade,Practice , Skill Group and Demand Source.
I want to predict the Number of demand by month.
Which is the ...
2
votes
2answers
48 views
0
votes
1answer
22 views
Cumulative sum of increase/decrease over time [closed]
I am looking for an efficient way to handle a calculation. I have lots of timestamped events, representing loading and unloading of trucks. I need to construct the filling rate of these trucks over ...
1
vote
0answers
18 views
Time-series clustering Quality Measures
I am clustering time-series datasets which are not labeled (No Ground truth) and I want to measure the quality of the clusters.
Could you please suggest any Clustering performance evaluation methods ...
1
vote
0answers
28 views
What kind of algorithm should I use to build ML model that can predict just next reoccurence of an event in the future (at irregular time interval)?
I'm quite new to machine learning and statistics.
I've a dataset from some ecommerce sale's history. It's almost 2k instances, and features include personId (string), productCategory (string/...
0
votes
1answer
17 views
which forecasting models could be chosen?
I'm new for data analysis. I got some data from the regional environmental center.
Measurements:
Datetime, PointID, SubstanceID, Value (substances concentrations in air), MeteoID ,NextValue
...
-1
votes
0answers
20 views
How to use K-Means to detect users anomaly in Access Control
I'm currently working on access control project, Smart Lock to be more spesific.
Like the other smart lock system, the system required user's authentication to open the door. I'm using RFID as ...
1
vote
0answers
23 views
Any tool that can help on manually label a time series data please?
i am working with a 10 years weekly financial time series data set, which has the standard format date open high low close volume.
i would like to manually label (classify) the data set with label/...
1
vote
0answers
9 views
Using by statement in proc esm
I was using proc een in SAS, for time series forecasting. I want to include two variables in by statement.
My data contains four columns:
Shop_id
Item_id
...
0
votes
0answers
24 views
Input shape for forecasting time series with Keras LSTM
For the last few days I have been trying to get familar with time series forecasting using LSTM in Keras. I have been mostly following tutorials on https://machinelearningmastery.com. Overall the ...
0
votes
0answers
10 views
Generate captions for time series data trends
I am trying to generate captions for time series data based on increasing/decreasing values.
I have a column with values which change gradually over time (time horizon is irrelevant for now). When we ...
-1
votes
0answers
34 views
Clustering Multivariate Time Series
I have 1000 time series data from different stations each has 8760 rows (point) and 13 columns (variables). A sample time series is as follows:
...
0
votes
0answers
11 views
Inserting a feature in the training set made of a target variable
I have a timeseries that contain the daily price of items based on the stores , the manufacturers , and other attributes. Other than what we know about not including a signal from target variable in ...
1
vote
0answers
20 views
Am I missing something about LSTM?
I have imbalanced data that I pass through a LSTM network.
Here is part of my code :
...
1
vote
0answers
26 views
How to compare slope of two time series
Suppose we have the 2 sets of time series data L1,M1 sampled at the same 1000 points of time t[t1,t2,...t1000]. Lets assume before hand that that the L1 can be given as
L1 = tX+a where X is the slope ...
1
vote
1answer
8 views
Fully endogenous models for predicting multivariate time series
I have a formal social science background but I am new to data science. My interest is in building predictive models for applications in the social sciences, mostly (but not only) in economics.
I am ...
1
vote
1answer
15 views
Using sensor data and a know reference point infer the position of a moving robot
Say, the robot is starting at a known position and I've data coming off of the robot as it traverses the grid layout. Exploiting the nuances captured in the data - like the implication of unequal rpm ...
1
vote
0answers
15 views
Applicable method for the clustering of time-series consisting of multiple events
I'm currently dealing with a time-series clustering problem at work and I need help with picking/suggesting the right methodology. The problem is similar to clustering of users on a website based on ...
1
vote
0answers
36 views
Reconciling time-based data when data source clock drifts
How can I reconcile time-based data when the clock on the data source tends to drift and the data may be infrequently retrieved?
I measured the clock to be about 30 minutes behind after 15 hours. ...
2
votes
0answers
20 views
ACF (Autocorrelation) estimation
I have two signals "Signal A" and Signal B" and I plot the autocorrelation for each signal with itself as shown below. How I can determine which signal has a stronger correlation with itself.
To ...
0
votes
0answers
22 views
methods to find causality between 1000 time series
I have an eco-system of 100 applications which each are monitored by let's say 100 metrics publishing every 5 minutes. So my dataset has 10,000 time series. I want to build/learn the dependency graph ...
2
votes
1answer
65 views
LSTM for time series - which window size to use
I have a LSTM based network which inputs a n-sized sequence of length (n x 300) and outputs the next single step (1 x 300).
The "raw" data consists of a few thousand semi-processed sequences of ...
2
votes
2answers
39 views
Is it acceptable for a forecasting model to predict moving averaged version of the data?
I'm working on a project in which I'm developing a precipitation forecasting model.
When I try to predict the original data, the model (LSTM neural network) is not able to predict the peaks.
This ...
1
vote
1answer
17 views
Time series on syslogs
Is time series model suitable for network syslogs considering the fact the messages are sequential and the messages are outputted as a result of dependency between themselves which can range from ...
0
votes
1answer
16 views
Higher frequency of time series benefits
We are setting up an experiment for a model that is able to predict the evolution of a time series in different horizons. One of the parameters to decide is the granularity of frequency of our samples ...
1
vote
1answer
55 views
LSTM future steps prediction with shifted y_train relatively to X_train
I'm trying to predict simple one feature time series data with shifted train data. The source looks like this:
...
1
vote
0answers
25 views
Transposing a dataframe (time-series)
I'm working on event-forecasting problem for a supermarket, and the data frame I have looks like (sorry for formatting):
...
1
vote
0answers
8 views
Classification on time series items - choose not constant threshold
I'm dealing with a classification problem on a time series {time: t, value: y(t)} where, for each time t,
my classification algorithm gives as ouput the probability that the y(t) belongs to class 0 or ...
2
votes
2answers
27 views
Multiple-output vs single-output NNs
I'm trying to build a 5 input-5 output model using LSTM, where all the outputs are the same features as the inputs, predicted in the future.
My question is: is it better to build 5 models, each with ...
1
vote
1answer
18 views
predicition for a specific month
I am attempting to build a predictive model based on the past historical data. I have details of specific machine failure based on the past year data. I have data from some months of 2016 and from ...
1
vote
0answers
21 views
Dataset containing spatial and temporal features (built on a CNN model)
A dataset contains spatial and temporal features.
It contains the time series data (2 min intervals) of the sections of a map.
It is 320*480 (320 map sections and 480-time intervals). Each row ...
4
votes
1answer
25 views
Training network with variable frame rate?
I would like to train a temporal network, but the video data available are in different frame rates(ex 7,12,15,30). How should I train this network, without down-sampling higher frame rate videos.
I ...
1
vote
0answers
19 views
Can ARIMA be applied on a dataset of few months?
I have dataset of a few months of (time series) electrical load usage of multiple users. Can/Should ARIMA be applied for load forecasting considering that its not much data?
3
votes
0answers
25 views
RNN-based Predictions of Sine Waves with Frequency Different From Training Data
I am wondering if I can generate a sine wave with a frequency different from training data using RNN. For example,
Using two training data of two time series, say 0[sec] ~ 10[sec] each:
sin(t) and ...
1
vote
1answer
39 views
Timestamps in Ridge Regression Scikit Learn
I am trying to transform data for use in regression, most likely the Ridge or Lasso technique implemented in sklearn.linear_model.
My training data contains time ...
2
votes
1answer
38 views
VAR model ValueError: x already contains a constant
I'm using VAR model for multivariate time series. The structure is that although each variable is a linear function of past lags of itself and past lags of the other variables, one and/or two of the ...
2
votes
3answers
58 views
Small dataset in Time series
I have soccer data with a time series index. 30 seconds interval. So, 194 rows for 90+ minutes per game. I have 1500 games.
The dataframe has the following information.
Home/Away:
• Goal Total.
• ...
1
vote
0answers
35 views
Multi-class time series data in LSTM
I have a data set that includes the individual performance of a number of "actors" over some period of time.
For a less-than-ideal contrived example (I'm not able to share the actual use case), you ...
2
votes
2answers
83 views
Time-series decomposition to a base level and an effect of another feature
I've got a time-series data (let's denote it as y) and some feature (let's denote it as x). y...
0
votes
0answers
12 views
Exponential smoothing trend curve frequency
I want to predict week by week the numbers of orders.
Data : all the year for 2013 to 2017 (52 weeks) and 25 weeks in 2018
Time serie plot :
...
0
votes
0answers
13 views
Predicting both - classification and regression with time series random forest
so
I'm developing a sports book betting system. So my goal is to choose appropriate ML approach to predict client's next bet based on the history of other clients' bets.
Its regression and ...
