# Data collection and pre-processing techniques

Source: [https://docs.qualcomm.com/doc/80-63442-4/topic/data-collection-and-pre-processing-techniques.html](https://docs.qualcomm.com/doc/80-63442-4/topic/data-collection-and-pre-processing-techniques.html)

Preparing data for use in machine learning models and deep learning

Whether they are new to deep learning or looking for a refresher, mobile app developers
            find that QDN blog posts are a good introduction to AI and machine learning (ML). Posts
            like [Mobile AI Through Machine Learning Algorithms](https://www.qualcomm.com/developer/blog/2019/02/mobile-ai-through-machine-learning-algorithms)
            and [AI Machine Learning Algorithms – How a Neural Network
                Works](https://www.qualcomm.com/developer/blog/2019/04/ai-machine-learning-algorithms-how-neural-network-works) set the stage for using the [Qualcomm® Neural Processing SDK for AI](https://www.qualcomm.com/developer/software/neural-processing-sdk-for-ai). You
            can find all the latest blogs on our [Artificial Intelligence Get Started page](https://www.qualcomm.com/products/technology/artificial-intelligence).

The entry point to the development cycle of any ML project is the data preparation
            stage.

As shown in the primitive ML development pipeline below, data preparation precedes the
            training and learning stage, known as feature extraction, of any ML model. Hence, the
            importance of executing this stage correctly from the outset.  
![](data:image/png;base64,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)

Within the data preparation stage are the data collection and data pre-processing
            stages.

## Data collection

Collecting data for training the ML model is the basic step in the machine learning
                pipeline. The predictions made by ML systems can only be as good as the data on
                which they have been trained. Following are some of the problems that can arise in
                data collection:

- Inaccurate data. The collected data could be unrelated to the problem
                    statement.
- Missing data. Sub-data could be missing. That could take the form of empty
                    values in columns or missing images for some class of prediction.
- Data imbalance. Some classes or categories in the data may have a
                    disproportionately high or low number of corresponding samples. As a result,
                    they risk being under-represented in the model.
- Data bias. Depending on how the data, subjects and labels themselves are chosen,
                    the model could propagate inherent biases on gender, politics, age or region,
                    for example. Data bias is difficult to detect and remove.

Several techniques can be applied to address those problems:

- Pre-cleaned, freely available datasets. If the problem statement (for example,
                    image classification, object recognition) aligns with a clean, pre-existing,
                    properly formulated dataset, then take advantage of existing, open-source
                    expertise.
- Web crawling and scraping. Automated tools, bots and headless browsers can crawl
                    and scrape websites for data.
- Private data. ML engineers can create their own data. This is helpful when the
                    amount of data required to train the model is small and the problem statement is
                    too specific to generalize over an open-source dataset.
- Custom data. Agencies can create or crowdsource the data for a fee.

## Data pre-processing

Real-world raw data and images are often incomplete, inconsistent and lacking in
                certain behaviors or trends. They are also likely to contain many errors. So, once
                collected, they are pre-processed into a format the machine learning algorithm can
                use for the model.

Pre-processing includes a number of techniques and actions:

- Data cleaning. These techniques, manual and automated, remove data incorrectly
                    added or classified.
- Data imputations. Most ML frameworks include methods and APIs for balancing or
                    filling in missing data. Techniques generally include imputing missing values
                    with standard deviation, mean, median and k-nearest neighbors (k-NN) of the data
                    in the given field.
- Oversampling. Bias or imbalance in the dataset can be corrected by generating
                    more observations/samples with methods like repetition, bootstrapping or [Synthetic Minority Over-Sampling Technique
                        (SMOTE)](https://towardsdatascience.com/a-deep-dive-into-imbalanced-data-over-sampling-f1167ed74b5), and then adding them to the under-represented classes.
- Data integration. Combining multiple datasets to get a large corpus can overcome
                    incompleteness in a single dataset.
- Data normalization. The size of a dataset affects the memory and processing
                    required for iterations during training. Normalization reduces the size by
                    reducing the order and magnitude of data.

Those techniques point to the [Types of machine learning](https://docs.qualcomm.com/doc/80-63442-4/topic/types-of-machine-learning.html) available
                to mobile app developers.

**Parent Topic:** [Artificial Intelligence, Machine Learning, Android and the Qualcomm Neural Processing SDK for AI](https://docs.qualcomm.com/doc/80-63442-4/topic/artificial-qualcomm-neural-processing-sdk.html)

Last Published: Jun 24, 2024

[Previous Topic
Types of machine learning](https://docs.qualcomm.com/bundle/publicresource/80-63442-4/topics/types-of-machine-learning.md) [Next Topic
Introduction to the Qualcomm Neural Processing SDK for AI and its components](https://docs.qualcomm.com/bundle/publicresource/80-63442-4/topics/introduction-to-qualcomm-neural-processing-sdk.md)