Component description
Bolt Wi-Fi Module
LDR
Hardware Connections
Prediction graph
Algorithm
Z-score Analysis
Results:
Project screenshots
Reference:

Published September 28, 2019 © GPL3+

Room Light Monitoring

This project helps to maintain the intensity in the defined range and alerts us if an anomaly is detected.

BeginnerShowcase (no instructions)5 hours450

Things used in this project

Hardware components

Bolt IoT Bolt WiFi Module

LDR, 5 Mohm

Resistor 10k ohm

Jumper wires (generic)

Solderless Breadboard Half Size

Software apps and online services

Bolt IoT Bolt Cloud

Bolt IoT Android App

Ubuntu terminal

Mailgun

Story

Objective:- This project is just a small protocol. It will be useful in bigger projects like monitoring sunlight falling on plants.

Component description:

Bolt Wi-Fi Module:

An IoT platform that lets you control or monitor things over the internet. It collects and visualizes the necessary data for monitoring different sensors. It can be operated remotely as well. It connects to the Bolt Cloud through an android application, Bolt IoT.

LDR

An LDR is a light-controlled variable resistor. The resistance of an LDR decreases with increasing incident light intensity(photoconductivity). The voltage developed across it depends directly on its resistor using the voltage divider rule. The Bolt module measure the voltage change through its analog input pin, A0. The measured value is then converted into a digital value by the Bolt module. The Bolt module sends this value to the Bolt Cloud.

Hardware Connections:

1. Connect one pin of LDR to 3.3V pin and the other one to the analog pin,A0, of the bolt module.

2. Connect one pin of the resistor to the ground pin and another one to the analog pin,A0.

To avoid cross-connection, use breadboard and jumper wires. At last, power on the module via adapter.

Prediction graph:

The data collected from the module is plotted instantly on the cloud. Using polynomial regression, we can predict the data and manage to take early actions.

Polynomial regression formula:

Algorithm:

1) Fetch the latest sensor value from the Bolt device.

2) Check if the sensor value is in the defined range.

3) If it is not in range, send an email.

4) Store the sensor value in a list that will be used for computing z-score.

5) Compute the z-score and upper and lower threshold bounds for normal and anomalous readings.

6) Check if the sensor reading is within the range for normal readings.

7) Alert through email if an anomaly is detected.

8) Wait for 10 seconds.

9) Repeat from step 1.

Z-score Analysis:

It is a technique used for anomaly detection. The formula for z-score analysis is

Results:-

Project screenshots

Reference:-

Bolt IoT Training
Wikipedia

import email_conf
import json, time, math, statistics
from boltiot import Email, Bolt

min_limit = -51

def compute(history_data,frame_size,factor):
    if len(history_data)<int(frame_size) :
        return None

    if len(history_data)>frame_size :
        del history_data[0:len(history_data)-frame_size]
    Mn=statistics.mean(history_data)
    Var=0
    for data in history_data :
        Var += math.pow((data-Mn),2)
    Zn = factor * math.sqrt(Var / frame_size)
    High_bound = history_data[frame_size-1]+Zn
    Low_bound = history_data[frame_size-1]-Zn
    return [High_bound,Low_bound]
    
    
mybolt = Bolt(email_conf.API, email_conf.DEVICE_ID)
mailer = Email(email_conf.MAILGUN, email_conf.SANDBOX, email_conf.SENDER_EMAIL, email_conf.RECIPIENT_EMAIL)
history_data=[]

while True:
    response = mybolt.analogRead('A0')
    data = json.loads(response)
    if data['success'] != 1:
        print("There was an error while retriving the data.")
        print ("This is the error:"+data['value'])
        time.sleep(10)
        continue

    print("This is the value "+data['value'])
    sensor_value=0
    try:
        sensor_value = int(data['value'])
        if sensor_value<min_limit:
          response = mailer.send_email("Alert","Light intensity decreased below the minimum limit. The current value is " +str(sensor_value))   
    except e:
        print("There was an error while parsing the response: ", e)
        time.sleep(10)
        continue     

    bound = compute(history_data,email_conf.FRAME_SIZE,email_conf.MUL_FACTOR)
    if not bound:
        required_data_count=email_conf.FRAME_SIZE-len(history_data)
        print("Not enough data to compute Z-score. Need ",required_data_count," more data points")
        history_data.append(int(data['value']))
        time.sleep(10)
        continue
    try:
        if sensor_value<bound[0] :
             print ("The light level decreased suddenly. Sending an Email.")
             response = mailer.send_email("Alert","Someone turned off the lights. The current value is " +str(sensor_value))
             print("This is the response ",response)
        history_data.append(sensor_value);
    except Exception as e:
          print ("Error occured",e)
    time.sleep(10)

Credits

Nikita Shehra

1 project • 0 followers

Room Light Monitoring