Update README.md

README.md

-# Smart HVAC Energy Optimization with Occupancy Analytics
-
-
-
-## Festlegung der Raumbelegung)
-
-A Python toolkit to determine room occupancy from environmental sensor data.  
-It includes data integrity checks and a hybrid (model-based + rule-based) algorithm to infer occupancy in (near) real time.
-
-
----
-
-## Key Features
-- Data integrity checks before analytics
-- Hybrid algorithm: model-based + rule-based
-- Works with motion, CO₂, temperature, humidity
-- Classifies occupancy levels (e.g., empty / sparse / full)
-- Designed for efficient, accurate analysis
-
----
-
-## Resource
-Here is the link to Original Repository:
-```bash
-https://gitlab.rz.hft-stuttgart.de/11akmi1bif/raumbelegung-messung-bplaced.git
-
-```
-
-## Prerequisites
-- Python **3.x** (recommended: 3.10+)
-- `pip` (Python package manager)
-
----
-
-## Installation
-Clone the repository and install dependencies:
-
-```bash
-pip install -r requirements.txt
-
-## Project Task
-- Rule based algorithm: rulebased_occupied_label.py 
-The algorithm already parses sensor data (csv files) and assigns labels to the datasets. However, the rules should be adjusted:  
-
-## expected output
-
-## judging criteria 
-
-
+# Occupancy with Energy Optimization
+
+## Overview
+Develop a system that analyzes sensor data to detect room occupancy and optimize energy usage. The system should evaluate multiple parameters, accumulate occupancy trends over at least two months, and generate heating plans that balance comfort with efficiency.
+
+## Targets
+- Occupancy detection algorithm using multiple sensor parameters.  
+- Historical occupancy accumulation across two months or more.  
+- Energy optimization model to plan heating schedules based on occupancy trends.  
+- Dashboard or API to visualize occupancy data and optimized heating plans.  
+
+## Data Needs
+- Sensor data (motion, CO₂, temperature, humidity).  
+- Room metadata (capacity, function, floor plan).  
+- Historical occupancy logs (2+ months).  
+- Energy usage/cost data for validation (if available).  
+
+## Acceptance Criteria
+- Can occupancy be reliably detected from sensor data?  
+- Are occupancy patterns accumulated and visualized clearly over time?  
+- Does the system suggest heating plans that reduce energy while ensuring comfort?  
+- Is the optimization reproducible with new data?  
+
+## Environment Setup
+- **Languages:** Python (data processing, algorithms), JavaScript (dashboard).  
+- **Frameworks:** Pandas, NumPy, scikit-learn (analysis), Flask/Django (backend), Plotly/Dash or React (visualization).  
+- **Tools:** Jupyter Notebook for prototyping.  
+- **OS:** Mac / Windows / Linux.