| Idea Name: |
AP Model |
| Slogan: |
You Can Trust Us |
| Supervisor Name: |
Dr. Deedar Nabi |
| Supervisor Designation: |
Assistant Professor |
| Supervisor School: |
School of Civil and Environmental Engineering (Scee) |
| Supervisor Department: |
Institute of Environmental Science and Engineering (IESE) |
| Contact number: |
03325565751 |
| Email ID: |
[email protected] |
| Abstract: |
| Toxic volatile organic compounds (VOCs) are atmospheric pollutants representing a threat to human health requiring assessment how they are distributed in the body using blood:air parition coefficient. |
| What is the unmet need in society that your idea will fulfill ? |
| Our project is to simulate the occupational exposure of VOCs through development of an inexpensive and efficient computational model that will take only two parameters compare to other estimation model which uses six parameters and are costly to find partition coefficient. |
| Who needs it ? How many would benefit ? |
| Model can be of added value in chemical risk assessment procedures for agencies and chemical industry that requires assessing thousands of chemicals in market. To achieve this, risk assessment should focus more on groups of chemicals and move away from labor-intensive and animal consuming approach. |
| How will the solution works |
| The model outcome will be blood:air partition coefficient for any VOC, calculated on the basis of Octanol to Water (Kow) and Air to Water (Kaw) partition coefficient of that chemical. This will assist agencies to evaluate degree of hazard posed by the chemical in occupational exposure and to devise its limit to avoid long-term diseases and ensure public health. |
| Who are your competitors ? How is your solution different |
| The major competitors are methods not agencies. This model is substantially cheaper compared to available methods. Our model uses Machine Learning algorithms to predict results. ASM Model involves extensive laboratory testing for concluding result which is expensive and very time intensive. |
| Status: |
new |
| Entry Date & Time: |
2020-12-20 (1457) |
