FSHDA: a Framework for Smart Home Dataset Analysis

Description
This framework is designed to analyze the smart home datasets in order to reflect their diverse dimensions in uniform format. FSHDA analyzes the time duration, activity count, activity type, sensor count, sensor type, sensor location, activity occurrence, activity sensor events, activity time, parallel activity count, parallel activity type, and sequences of parallel activities. These dimensions can provide detailed views regarding differences in environments, residents, and activities and provide similar information about every dataset so that researchers can choose datasets according to algorithm requirements and application domains. Dataset folder contains 14 datasets from three smart home projects. Dataset folder contains three subfolders one for each smart homes project. 

Installation Steps

Step 1: Install Matlab compiler MCRInstaller

Step 2: Open Command prompt, give the complete path for FSHDA.exe

Step 3:
[1] Press 1 for .dat file data loading
[2] Press 2 for .mat file data loading

Step 4: (If choice is 1)
.dat File Path= write full path along with file name

Step 4: (If choice is 2)
.mat Folder Path= write full path for .mat folder
[1] for MIT Data format
[2] for ISL Data format

Step 5:
Output will be generated in excel file with four sheets. The descriptions of the sheets are as follows:

Sheet 1: FSHDA Computed Statistics includes ActivityID, Activity Type, Activity Count, Activity Time, Activity Sensor Events

Sheet 2: FSHDA Parallel Activities includes two types of information. Statistics about overall dataset such as Activity count, Sensor Count, Duration, Idle Activity Time, and Idle Sensor Events. For Parallel activities statistics are represented in a form of Activity 1, Activity 2, Start First, End First, and Activity Count

Sheet 3: FSHDA Dataset Time Duration includes unique Year, Month, day

Sheet 4: FSHDA Dataset Activity Details includes ActivityID, ActivityStartTime, ActivityEndTime, SensorEvents for each activity