All Questions
Tagged with neural-networks time-series
419 questions
1
vote
0
answers
27
views
Preprocessing and model selection strategies
I am working on a fault detection problem where each sample is a time series labeled with a specific type of fault. I am using a CNN model and a validation set for hyperparameter tuning. Currently, I ...
- 77
0
votes
0
answers
16
views
Embeddings in time series prediction
Increasingly, I’ve noted that embeddings are used in pure prediction ML tasks. For example, instead of predicting whether user i will purchase item i and thereby adding thousands or millions of inputs ...
- 3,520
2
votes
1
answer
34
views
Is it possible to train Neural networks for time series forecasting using elastic distances (such as dtw) as a loss function?
Normally, elastic distances are used as ways to tell how similar two time series are. Examples of these are dynamic time warping and move-split-merge and many more. And I read some researches such as ...
0
votes
0
answers
31
views
Hyperparameter Tuning for Multiple Time Series
I am developing a time-series model utilizing NeuralProphet for forecasting the demand of products by day. I have grouped the products into a number of clusters by features such as average demand, ...
1
vote
1
answer
62
views
Should classical/traditional ML techniques such as polynomial regression/decision trees/random forests SIGNIFICANTLY outperform RNN in timeseries? [closed]
I have a dataset of numerous years of buoy wave height measurements including features such as measured significant wave height, numerical model predictions, peak wave period, mean wave period, and ...
- 11
0
votes
0
answers
23
views
Detect paterns over time in multivariate dataset
I have a dataset representing the stock of a shop over several days. For each day, I have hourly inventories of the objects in the shop. Some products are sold, and others might temporarily disappear (...
0
votes
0
answers
18
views
multivariate time series forecasting
I have a dataset of 200,000 rows. Each row contains the song ID, the number of streams today (day_0), the number of streams yesterday (day_1), etc. up to the number of streams 21 days ago (day_21). My ...
1
vote
0
answers
30
views
Use latest data in training a timeseries model
I am training a global timeseries deep learning model.
I have split the data for training, validation(to select the best hyperparameters), and test(to test on out of sample data).
There are only 3 ...
- 11
0
votes
0
answers
9
views
How to Improve performance of deep learning timeseries forecasting model like LSTM? [duplicate]
I have historical data of 5 years (June 2019- June 2024). Data is in daily & csv file format. I have 4 features: Data, AQI, Raw Concentration, NowCast Concentration. I am trying to forecast only ...
0
votes
0
answers
28
views
Why Do AR-NN Models Have Tighter Confidence Intervals Compared to Linear AR Models?
I have conducted a forecast for the following data series using different autoregressive models: Intercept-only, AR1, AR2, ARIMA BIC, ARIMA AIC, and AR-NN. Using the point forecasts, the AR1 model is ...
- 363
0
votes
0
answers
19
views
How does highly imbalanced test data in certain splits of k-fold time-series cross-validation affect model performance?
I am working on a time-series classification (TSC) problem using k-fold time-series cross-validation (TSCV) to evaluate the performance of my models. My training data for each split is fairly balanced,...
0
votes
0
answers
33
views
How can I integrate time in my Implicit Feedback dataset?
I'm working on a recommendation system based on Collaborative Filtering. Specifically, I've been looking at models such as NCF (Neural Collaborative Filtering) and SAR (Simple Algorithm for ...
- 1
0
votes
0
answers
33
views
EWMA formula for SGD with momentum different than generic EWMA formula
I am currently trying to understand how SGD with momentum works, what I understand is it uses the Exponential Weighted Moving Average concept to make the updates smoother. We take weighted average of ...
- 275
0
votes
0
answers
18
views
Can anyone explain me what does ACF and PCF tells from this figure?
I want to know what does it mean? Is my data stationary or not because the p value tells its stationary and what should be the order ARIMA model(p,1,q) is it (p,d,0) or (0,d,q)
9
votes
1
answer
468
views
What is a good approach to split 3 years of hourly data in a train, validation and test set for an electricity price forecasting neural network?
I would like to train a simple neural network to forecast electricity prices in a certain region. However, I only have a 'limited' amount of data available (3 sequential years of the historical price, ...
- 93
1
vote
0
answers
11
views
Classification of intervals in time series data of multiple instances
I have a problem that I am trying to frame. I have signal data from ECG (a classic signal over time data). A close example here: https://github.com/jjongjjong/ECG_segmentation_1DUnet
I am basically ...
- 125
1
vote
0
answers
13
views
Why does GAP at the end of FCN for MTSC work?
I have a binary MTSC (Multivariate Time Series Classification) problem where i train a CNN, namely a FCN (or Fully Convolutional Network) to predict class 0 or class 1 based on a multivariate time ...
- 11
0
votes
0
answers
58
views
Forecasting RNN and LSTM without X_test
Dear StackExchange Community,
My data is composed of only 1 time series variable (Stock prices of an asset)
I have splitted it to train and test subsets.
I have tarined an RNN and LSTM models with ...
0
votes
0
answers
29
views
Large Scale Missing Data & Imputation of Time Series Data in Neural Networks [duplicate]
I know there has already been a lot of discussion about this topic, but I have reasons to believe it still remains unanswered and lacks several justifications.
Suppose we have an time series feature ...
- 101
0
votes
0
answers
31
views
Normalization of time-series data with time-varying variance
I'm building a neural network (CNN) model for a regression problem with time-series data. Both input and output are multi-variate zero-mean timeseries data with time-varying variance. Currently, I am ...
- 111
0
votes
0
answers
192
views
Transformer with just one input vector
I have a problem where I am mapping from 1D input sequences of length L to 1D output sequences, also of length L. These sequences contain numerical data. The input sequence is the time evolution of a ...
1
vote
0
answers
29
views
Is using aggregated usage data more efficient than using flattened usage data to build a ML model in anomaly detection? [closed]
We're tracking users' hourly usage on our cloud service and have a risk model that uses aggregated usage data plus other signals to identify potential fraudsters. Basically, it's an anomaly detection ...
- 151
1
vote
0
answers
72
views
Multilayer Perceptron vs. Recurrent Neural Network for Time Series Forecasting: Utilizing Multiple Lagged Values
I am currently analyzing daily sales data for a product sold across multiple stores using a Multilayer Perceptron (MLP) model. For simplicity, let's assume it consists of a single layer, structured as ...
- 63
0
votes
0
answers
11
views
Classification based on frequency decomposition of timeseries
I'm working on a classification problem where the dataset comprises a quote-unquote frequency profile from a timeseries. My dataset looks like this:
...
0
votes
0
answers
13
views
Question on a paper which talks about stacking several fully connected layers of 2 neural networks
So to preface, my knowledge on neural networks is very limited, and I've had a very difficult time trying to comprehend the details of this paper.
My background is in maths, and I've created a ...
- 101
0
votes
0
answers
7
views
How to Assess Predictive Potential in Time Series Analysis, Especially with Deep Learning? [duplicate]
In the realm of time series forecasting, how can one assess the predictive potential of a given time series? While traditional methods involve checking for stationarity and white noise characteristics,...
- 1
1
vote
0
answers
44
views
Time series normalization
I'm not an expert yet in the field and I have some questions. I have some data of birds and drones taken from a radar. I want to create a classifier that differentiates them. At first I'm trying and ...
- 11
0
votes
0
answers
16
views
Error metrics for the up-down time series curves
I have a time series prediction! here is a graph of that. This shows the consumption of gas for a city! So, I want to define some metrics for it. However, I dont want to use the smape or mae or other ...
- 133
0
votes
1
answer
66
views
Event prediction using Statistical or Black box approach
I just came across a problem related to Event prediction in timeseries data.
So there is a timeseries data having timestamp and event occurred at that time, and I need to predict the next set of ...
- 33
2
votes
0
answers
210
views
How to format exogenous variables when forecasting multiple related time series using n-hits or n-beats neural network forecasting models
Motivation:
I would like to forecast Canadian Inflation Index using N-HITS or N-BEATS model (I have considered both pytorch forecasting package and neuralforecast python packages).
I hope to use ...
- 31
2
votes
1
answer
149
views
How to handle hyperparameter tuning for LSTM with early stopping?
I am looking for advice on the best practice to determine hyperparameters for my LSTM model. I have time series data that I have divided into train and test sets. I was planning to use an expanding ...
- 255
0
votes
1
answer
39
views
Deep learning classification with multiple temporal data
I'm working on a project to predict the category of music segments in an audio file (represented in pianoroll format with an additional column for the corresponding class). Each row represents the ...
- 1
1
vote
0
answers
361
views
What loss function should one use when using an RNN to to predict a time series of binary values which are not necessarily independent?
I'm trying to use an RNN to predict a time series {$y_t$}, where $y_t \in {0,1} \forall 1 \leq t \leq T$ given an input time series {$x_t$}. The elements of the target sequence are not necessarily ...
- 1,617
1
vote
0
answers
21
views
auto.hd.type = "cv" in mlp() function in nnfor package
In running mlp() function of the nnfor package, you can allow the model to choose the number of hidden nodes through cross validation.
...
- 41
1
vote
0
answers
37
views
Input Time Series Transformation
This question is regarding applying power transformations on input time series.
In literature the idea behind applying transformations to input time series is to stabilize variance. But I have seen ...
1
vote
0
answers
32
views
Which metric for neural network should I try for time series data with sudden peaks?
I am doing time series forecasting with neural network (feedforward for now, but I will test also RNNs) and my problem is that, even though the network learned general patterns, it doesn't forecast ...
- 115
0
votes
0
answers
27
views
Regression from multiple time-series
I wish to build a deep neural network that takes multiple time-series as input and outputs a single scalar value. The length of each time-series is constant, but the number of time-series can change ...
- 1
1
vote
0
answers
75
views
Linear positional encoding for Transformers with fixed sequence length
I am trying to use Transformers for a Time-series task (with fixed sequence length).
Since it's sequence length is always the same, can I use a linear positional encoding? I read some articles about ...
- 113
1
vote
0
answers
157
views
Why LSTM predicts very poorly with loss curves showing no indication of overfitting or underfitting?
I am training a LSTM model for load demand prediction with:
Training Data: 18288 samples with 9 features
Validation Data: 0.05% of Training Data (about 915 samples)
Data Scaling: MinMax Scaler(0,1)---&...
- 11
2
votes
1
answer
350
views
Time series as one of several inputs to ML Model
I have what seems to be a relatively simple question that I haven't been able to find a satisfactory answer to despite searching for quite a long time:
The classic way to analyze time series data ...
- 143
0
votes
1
answer
230
views
Input Tensor Shape for CNN Binary Classification of Time Series Data
I want to predict whether a machine will fail based on the most recent set of measurements taken by on-board sensors. I have several dozen machines, each with a sensor that takes a measurement at ...
- 21
0
votes
1
answer
335
views
What degree of difference does validation and training loss need to have to be called good fit?
I am conducting a multi-variate time series forecasting using an LSTM model. The model architecture and other details are given below:
Dataset split: (80/10/10 split)
Training Data Points: 367640
...
- 11
0
votes
0
answers
178
views
Is time series regression closer to forecasting or classification?
I'm working on multivariate time series regression task.
The literature for it seems quite light compared to the problems of Time series classification (using algorithm like rocket for example) and ...
- 133
1
vote
1
answer
998
views
How predictions are made in time-varying survival analysis?
I am using Deep Recurrent Survival Machines (RDSM) model from auton-survival library for survival analysis with time-varying covariates. I am using a longitudinal survey dataset (Health and Retirement ...
1
vote
0
answers
160
views
Kernel Filter size and sampling frequency
I was wondering if I could understand the relationship between kernel size and sampling frequency. I was reading this paper and on Pg 6-7 ("In block-1" section), I read that kernel size of ...
- 113
1
vote
0
answers
32
views
Predict Time of an RNN Model Output?
I have an RNN based neural network that models a 1-1 relationship for inputs over time.
The model output is sigmoid activated, and the process I’m modeling is always monotonically increasing, so the ...
- 11
3
votes
1
answer
2k
views
What exactly is a "persistent/persistence model"?
I'm new to time series forecasting and only got previous experience with image processing in therms of neural networks. My goal is to do create an ML forecasting model for time series data. Currently ...
- 43
2
votes
1
answer
159
views
Turning point of Adam optimizer for LSTM
I'm training a two-layer LSTM with Adam optimizer for time-series data. I encountered several times that there was a "turning point" of the MAE vs. epochs plot. Is this a normal behavior?
- 226
19
votes
2
answers
3k
views
Showing machine learning results are statistically irrelevant
This is a question as part of a paper review which was already published. The authors of the paper publish $R^2$ and RMSE in training but only RMSE in validation. Utilizing the published code, $R^2$ ...
- 315
1
vote
0
answers
372
views
Why using logarithmic scale for time series forecasting? [closed]
Recently, I built some models (LSTM, XGBOOST, etc) for time series forecasting. I've tested those models in synthetic and real data. In some obscure forum, I've read that it would be better to ...
- 1,008