Questions tagged [time-series]
For questions related to time series analysis or forecasting in the context of AI and, in particular, ML.
161
questions
0
votes
0
answers
23
views
Is my 1D signal using CNN & RNN regression reasonable?
I want to know if my impact-echo signals are proper with CNN or RNN regression model.
I got some simulated signal, as following shows.
In previous research, people mostly consider frequency or even ...
- 1
0
votes
0
answers
13
views
RNN - Time To Stop extimation given non-categorical events sequence
I have a dataset which contains sequences of event of the following type:
Timestamp_s
Timestamp_e
Event_type
I've preprocessed the data to create sequences of the shape [seq_size, unique_codes_count]...
- 1
0
votes
0
answers
27
views
Backpropagation in a transformer
I have a transformer for timeseries forcasting based on this article https://arxiv.org/abs/2001.08317
Given a source containing $src=(x_{t-5},x_{t-4},x_{t-3},x_{t-2},x_{t-1})$ and a target of $tgt=(x_{...
- 101
0
votes
0
answers
5
views
Multi Output Regression but num of objects to predict vary per sample
so recently I came across a problem of predicting the positions of objects from a pulse wave. My biggest concern here is that for each data sample, the number of objects varies. I know that this ...
- 1
0
votes
0
answers
18
views
How do I find a similar RNN as a starting point?
I am new to machine learning and neural networks and I want to create a neural network for a study project.
I would like to create a RNN, that uses one (A) or several time series (with the same length,...
- 1
0
votes
0
answers
27
views
LSTM Ensemble: Combine low, mid, and high frequency time series data
I am trying to implement time series classification, but I am struggling a bit with the fact that my multivariate data has mixed frequencies. I have about 10 variables that are updated every minute, ...
- 111
0
votes
0
answers
58
views
Regarding the use of Time2Vec as positional encoding for Timeseries Transformer
Although the transformer architecture was originally designed for NLP, there exists several articles and papers that attempt to apply the same architecture for numerical timeseries classification. ...
- 21
0
votes
1
answer
24
views
How to classify positional time series data?
I am working with a data set that includes (x, y, z) coordinates and timestamps of human movement. The input data looks something like:
...
0
votes
0
answers
11
views
Can I combined the trained model between different source but same model structure?
Here I got two different deep-learning models that were trained by LSTM and time-series data.
The data is the usage percentage of CPU from two different computers.
Each computer job was the same. It ...
- 103
1
vote
0
answers
27
views
What are the most common fault prediction algorithms?
I have to predict a fault (automotive related) as much in advance as possible.
Right now I have found a solution that is somewhat satisfactory (a good number of true positives and a low number of ...
- 295
0
votes
0
answers
7
views
Early binary classification of timeseries
I'm trying to figure out how to solve this problem that I'll try to explain in the next few lines. I have a timeseries of length ~200k values and every 700 points I have a label that indicates the ...
- 1
0
votes
0
answers
20
views
How can I transform a signal into another using supervised learning?
I'm trying to transform a signal into another using supervised learning. My main goal is to create a model capable to transform a raw signal (Blue Line) into something similar to the "ideal" ...
0
votes
1
answer
272
views
Which preprocessing is the correct way to forecast time-series data using LSTM?
I just started to study time-series forecasting using RNN.
I have a few months of time series data that was an hour unit.
The data is a kind of percentage value of my little experiment and I would ...
- 103
0
votes
0
answers
16
views
How to extract body of a base-model and fine tune with that body on different shape dataset like this situation
In BERT like transformer model (I am not talking about BERT in this thread), it has 2 training objectives Masked Language Modeling and Next sentence prediction right? and BERT model is also supports ...
- 158
0
votes
0
answers
7
views
Should I downsample because of overrepresentation of geographic locations in time series data
I am in the start of working with a project where I am hoping to be able to classify activities based time series data. I have historic data; lat/long/speed/(..) as well as the activity.
The challenge ...
- 101
0
votes
0
answers
11
views
How can one incorporate spatial correlations into time series forecasting?
I am working on a project, where I am trying to predict temperatures of various streets and I have their locations recorded.
I was wondering if I could somehow train a model that could incorporate ...
1
vote
0
answers
26
views
How is batch data processed in a 1D convolution layer?
Suppose I have a time series data written in a matrix $\mathbf{X} \in \mathbb{R}^{N \times d}$. The sequence length is $N$ and $d$ is the number of features (I have $d$ series). Say I have a batch of $...
- 23
0
votes
1
answer
27
views
Feature Extraction for timeseries temperature signal [closed]
i have two temperature signals from which one is sensitive toward a specific event. I would like to know what other features can be useful to extract apart from:
Angles (between the two).
Slopes ( ...
- 61
1
vote
1
answer
52
views
Creating a Dataset from Time Series Data
Context
I'd like to build a regression model for this data to predict a user's test scores given their study habits.
Basically, the variables are in two separate csv tables similar to the ones below. ...
- 113
0
votes
1
answer
24
views
Regression Model diverging after adding a new feature with higher variance and magnitude
In a time series regression problem I'm predicting "change" rather than the actual intended value i.e
Instead of:
...
2
votes
1
answer
64
views
How to fine tune model on dataset which is having different shape compared to dataset model is trained on
I am having 2 questions as follows:
I am using normal CNN model for time series classification, Where my dataset1 is of shape (28,9,1) and I trained my CNN model on dataset1, where now the input ...
- 158
1
vote
1
answer
51
views
Transfer Learning for Solar Energy Production Forecasting with LSTM: Generalized vs. Specialized Models
I am working on a solar energy production forecasting problem using LSTM multi-step models to predict 1/4/8h ahead of solar energy production for different solar installations. Our goal is to help ...
0
votes
1
answer
365
views
Difference between sequence length and hidden size in LSTM
It does not come clear to me how the seq_length is not the exact same as the hidden_size in LSTMs.
For example, in the next ...
- 31
0
votes
0
answers
23
views
Missing Value Imputation for Time Series
I am working on a Stock Price Forecasting project, the data of which consists of 5306 instance & 12 columns. Of these, 2 columns contain about 500 instances of missing values (the starting 500 ...
0
votes
0
answers
19
views
Preventing Overfitting While Cross Validating Time Series Models
I have some time series data (e.g. daily rainfall for 10 years) and I am interested in fitting a time series model to this data and record the error.
I want to use the "rolling window cross ...
- 269
0
votes
0
answers
17
views
Healthcare alerting system based on weather data?
I have a database containing time series information about the temperature, pressure, humidity, wind speed and the number of people visiting my hospital each day. I want to design a system that ...
-1
votes
1
answer
53
views
Are there public examples of AI models that predicted short-term price well?
This question is inspired by Is there any AI model that predicts short-term stock price well?.
As answered, game theoretically either nobody would reveal such a model or it would have been alread ...
- 1,131
0
votes
1
answer
39
views
What reinforcement learning algorithm should I use for the following problem?
Environment
I have a static timeseries environment meaning the environment is the same.
This problem is a multi armed bandit problem.
Time
t0
t1
t2
State
s0
s1
s2
Score
10
0.1
0.2
Class
1
0
0
...
- 1
0
votes
1
answer
96
views
Is there any AI model that predicts short-term stock price well?
One simple way of predicating short-term stock price is to simply take the average price of the previous few days.
I wonder if there is some AI model/methods which can do better than this using only ...
- 261
0
votes
0
answers
15
views
Regressing parameters that map between two curves machine learning
I am wondering if anyone has experience in regressing out parameters that map one curve to another. For example, I have two curves that look like this. I used some non-linear equation to map orange to ...
1
vote
1
answer
34
views
Many To One LSTM - Can I Use the Same Sequence as Input from Previous Timesteps?
I'm new to LSTMs, and I'm trying to do a basic timeseries prediction using stock prices. However, I'm a bit confused as to how the LSTM is supposed to remember outputs from previous timesteps when it ...
- 111
1
vote
0
answers
19
views
SCINet: how does interactive learning work?
i'm having some trouble understanding how does the basic building block of a SCINet works. In the paper the author describes the SCI-block with the following figure:
In which $\phi$, $\theta$, $\eta$ ...
0
votes
0
answers
9
views
Is it recommend to perform a time series analysis with a fixed set of validation data?
I'm currently working on a project in material science and the data to evaluate is very limited. I work with about 60 datasets, each with about 10.000 relevant lines.
However I want to predict a ...
- 11
0
votes
0
answers
16
views
Idea for generating time series with irregular time-intervals with GANs
I want to model time-series with irregular time-intervals using GANs. Think of the following (short) data sample
...
- 1,898
0
votes
0
answers
32
views
How to output a function given a time series data as an input using supervised learning?
I have a spreadsheet with time series data collected from two sensors, one measuring temperature and the other measuring humidity. And I also collected data from an experiment that I conducted, the ...
- 1
0
votes
2
answers
227
views
Should I use multi-armed-bandits or RL for a financial time-series problem?
If we take simple financial timeseries data(stock/commodity/currency prices), State(t+1) does not depend on the action that we choose to take at State(t) as in Maze or Chess problem.
Simple example: ...
- 3
0
votes
1
answer
36
views
Should we always use the usual no leakage train-val-test splt in time series?
Some of you may be familiar with the unusual split scheme used for time-series data. In short, there is a saying that one should only consider a split where the training set comes prior to the testing ...
- 371
0
votes
0
answers
30
views
What are the inputs of a neural network when learning a difference equation?
The time series y[n] is the solution of the difference equation
...
- 11
0
votes
0
answers
10
views
Referencing features by name instead of index when feeding inputs
Traditionally the inputs of a model is a matrix of N dimensions.
This works well with inputs that are position-sensitive (For example in CV the placement of the pixels relative to each other can be ...
0
votes
0
answers
24
views
RNN Time-series forecasting hidden state
I'm starting with RNNs for time series forecasting and can't seem to understand how RNN/LSTM/GRU predict future values in time series data.
Assuming one sample per batch consisting of a sequence of ...
- 1
1
vote
1
answer
58
views
What type of neural network architecture allows filtering out of unwanted sounds?
I have a use case where I will be inputting audio to a model, and the output of the model will be the same audio except with certain sounds removed (volume set to zero). The dataset is generated by ...
- 111
0
votes
0
answers
30
views
LSTM with time-series data transform
I have a time series data which has distinct time steps. For example, one time series data was recorded with the 1/30(min) time step, but some other data may have 1/15(min), 1/6(min), 1/5(min) time ...
- 101
-1
votes
1
answer
110
views
Generating synthetic time series data with limited data
I would like some opinions on my current situation.
I have a set of time series data that I want to forecast. The data however is not very long (around 500 rows) so I was looking into generating many ...
- 13
0
votes
0
answers
8
views
How to perform prescriptive analysis with timeseries models (ARIMA / Prophet)?
We have recently come across a problem of applying prescriptive modeling techniques to time series models in a business analytics context. For the HR domain, we are using employees demographic data , ...
0
votes
0
answers
23
views
Generalize and optimize a model for multiple time series
I have a physics equation that takes so much time to be solved computationally.
So the idea is to optimize this computational time with Machine Learning techniques. I've already generated data ...
- 21
0
votes
1
answer
106
views
Can i train xgboost on multiple time series csv files at the same time?
I built an xgboost model to predict stock it now trains on 1 stock at a time its a csv file I use pandas to load it.
Is there a way to train the model on multiple stocks at the same time? What would ...
- 1
0
votes
0
answers
70
views
How to evaluate the embeddings of a model?
If you have a task of extracting embeddings from a model (such as penultimate layer - pre-last layer of the model), would you train the model on a benchmark similar dataset (if there were) or train on ...
0
votes
0
answers
18
views
Very high ACC (ca. 95%) with 1DConvNet for Time Series
Does this sound legit, for people working with CNN and Time Series?
I have a Framework that applies Dynamic Tim Warping (DTW) on time series, using the DTW distance matrix, I cluster my data and ...
- 51
0
votes
1
answer
110
views
How to encode categorical data for a convolutional model?
Is there a way to encode categorical nominal (no ordered) data to be used in CNN models?
Let's say I need to create a 1D CNN model for categorization of time series but the values are not measurements,...
- 1,240
0
votes
4
answers
85
views
How to discover/approximate the causations/correlations between multiple time-series and related open source libraries?
I have the following time-series data with two value columns.
(t: time, v1: time-series values 1, v2: time-series values 2)
...
