SafeChemNet
A Smart Social Platform for Safer Chemical Workplaces.
-
{What}
Design & Development
-
{Industry}
Healthcare IT
-
{How long}
7 month
-
{Team}
8 members
-
{Where}
Germany
A mobile-first corporate social network built specifically for employees in the chemical industry. It empowers workers to report incidents, share observations, and communicate in real time—all while helping management track workplace safety indicators like air quality or liquid spills. With image recognition tools, smart reporting, and real-time alerts, SafeChemNet creates a more connected and informed workforce, ensuring better safety decisions and faster reactions to potential hazards. Think of it as part social network, part safety command center.
- Mobile: Kotlin (Android) / Swift (iOS)
- Backend: Python (Django)
- Database: PostgreSQL
- Image Recognition: TensorFlow Lite
- Push Notifications: Firebase Cloud Messaging / APNS
- Authentication: OAuth 2.0 / SSO
- Hosting/Infrastructure: AWS
-
Incident Reporting
Allows employees to quickly report safety incidents with attached photos, descriptions, and severity levels.
-
Internal Social Feed
A dedicated space for posts, safety updates, alerts, and peer communication—like LinkedIn meets a safety dashboard.
-
Real-Time Chat
Secure in-app messaging to enable fast coordination between workers and supervisors.
-
Image Recognition for Hazards
Users can snap photos of unknown materials or objects, which the app helps identify as potential dangers using machine learning.
-
Environmental Monitoring Input
App connects to sensors or allows manual reporting of air pollution, chemical leaks, or other safety-critical environmental data.
-
User Profile & Activity Logs
Each user has a profile with their training records, participation stats, and safety history for managerial oversight.
-
Admin Dashboard for Management
Backend tools give plant managers access to incident trends, safety stats, and employee reports in real time.
-
Data-Driven Alerts & Suggestions
Automatically generated alerts and recommendations based on user input and historical patterns to guide better safety practices.