Adding noise
Adding noise (English: noise addition) adds random “noise” (or random variation) to the data to hide exact values while preserving the statistical properties and regularities of the dataset. Initially, it is necessary to choose how much “noise” to add, and then add or subtract a random value within the “noise” for each record (for each value of the selected identifier).
Example
Original data
| ID | Age | City | Diagnosis |
|---|---|---|---|
| 101 | 35 | Sigulda | Hypertension |
| 102 | 28 | Ape | Diabetes |
| 103 | 40 | Dobele | Migraine |
| 104 | 32 | Suntaži | Multiple sclerosis |
| 105 | 22 | Riga | Asthma |
| 106 | 44 | Liepaja | Hypertension |
Anonymised dataset after adding "noise" to the age of respondents (+/-2 years)
| ID | Age | City | Diagnosis |
|---|---|---|---|
| 101 | 33 | Sigulda | Hypertension |
| 102 | 30 | Ape | Diabetes |
| 103 | 42 | Dobele | Migraine |
| 104 | 34 | Suntaži | Multiple sclerosis |
| 105 | 20 | Riga | Asthma |
| 106 | 46 | Liepaja | Hypertension |
Adding noise
Adding noise (English: noise addition) adds random “noise” (or random variation) to the data to hide exact values while preserving the statistical properties and regularities of the dataset. Initially, it is necessary to choose how much “noise” to add, and then add or subtract a random value within the “noise” for each record (for each value of the selected identifier).
Example
Original data
| ID | Age | City | Diagnosis |
|---|---|---|---|
| 101 | 35 | Sigulda | Hypertension |
| 102 | 28 | Ape | Diabetes |
| 103 | 40 | Dobele | Migraine |
| 104 | 32 | Suntaži | Multiple sclerosis |
| 105 | 22 | Riga | Asthma |
| 106 | 44 | Liepaja | Hypertension |
Anonymised dataset after adding "noise" to the age of respondents (+/-2 years)
| ID | Age | City | Diagnosis |
|---|---|---|---|
| 101 | 33 | Sigulda | Hypertension |
| 102 | 30 | Ape | Diabetes |
| 103 | 42 | Dobele | Migraine |
| 104 | 34 | Suntaži | Multiple sclerosis |
| 105 | 20 | Riga | Asthma |
| 106 | 46 | Liepaja | Hypertension |