Building the Project
Step 1: Connecting LM35 to Bolt
Step 2: Configure Bolt IoT
Step 3: Visualization
Step 4: Anomaly Detection with Z- Score analysis and Notification

Published February 27, 2019

Monitoring of Temperature and Its Alert

The device which notifies via email or SMS for any sudden change in temperature or if it goes out of the defined threshold.

IntermediateFull instructions provided2 hours2,766

Things used in this project

Hardware components

Bolt IoT Bolt WiFi Module

Awesome Wifi Module by Bolt IoT

Temperature Sensor

LM35 series are precision integrated-circuit temperature sensors.

Jumper wires (generic)

Jumper wires are simply wires that have connector pins at each end, allowing them to be used to connect two points to each other without soldering.

Software apps and online services

Bolt IoT Bolt Cloud

Bolt Cloud platform for connecting and managing Bolt IoT devices

Bolt IoT Android App

Link your Bolt devices to your Bolt Cloud account.

Twilio SMS Messaging API

Cloud communications platform for building SMS, Voice & Messaging applications

Mailgun

Cloud communications platform for sending the Emails

Oracle VM Virtual Box Or Digital Occean

Story

Hi there !!

This project is about the pharmaceutical companies which use a cooling chamber to keep the tablets and maintain the temperature in the required limits. So making a device which notifies via Email or SMS for any sudden change in temperature or if it goes out of the defined threshold.

Instead of Cooling chamber, we use a regular refrigerator at home for this project.

Video of the Final result of this project :

Video of this Project

Building the Project

For Setting the Bolt WiFi Module click on link https://docs.boltiot.com/docs.

Step 1: Connecting LM35 to Bolt

Connect the GND pin of LM35 to GND pin of the Bolt device.
Connect the analog output pin of LM35 to A0 (analog input) pin of the Bolt device.
Connect VCC pin of the LM35 is connected to 5v of the Bolt device.

Step 2: Configure Bolt IoT

To create a Product for this project, firstly login into BOLT CLOUD

Click on the Products tab and then create a product

For this Project

select the Input Devices option and GPIO to collect the data

Click on Configure this product to configure the product

Click on the "A0" pin of the Bolt and name the variable

now click on Code tab and write down the code

Step 3: Visualization

Now for Making Prediction Graph, we write code on JavaScript in the Bolt Cloud by using Google Chart

setChartLibrary('google-chart');
setChartTitle('Temperature Prediction For Pharmaceuticals');
setChartType('predictionGraph');
setAxisName('Time','Temperature');
mul(0.0977);
plotChart('time_stamp','temp');

Now view the visualization

count data for every 5 minute so wait for 20-25 mins.

Note :- Now you can also use your BOLT IOT android app and ios app for Visualization by just clicking the Bolt Device Name

Step 4: Anomaly Detection with Z- Score analysis and Notification

For this project, I used Oracle VM Virtual Box, you can also use Digital Ocean. Now make conf.py which has the information of Twilio (Login and you use API) and Bolt Cloud account such as

SSID = "You can find SSID in your Twilio Dashboard "
AUTH_TOKEN = "You can find  on your Twilio Dashboard"
FROM_NUMBER = "This is the no. generated by Twilio. You can find this on your Twilio Dashboard"
TO_NUMBER = "This is your number. Make sure you are adding +91 in beginning"
API_KEY = "This is your Bolt Cloud account API key"
DEVICE_ID = "This is the ID of your Bolt device"
FRAME_SIZE = 10
MUL_FACTOR = 6

Similarly for Mailgun Email, make email_conf.py

MAILGUN_API_KEY = "your Mailgun private API"
SANDBOX_URL = "your sandbox url"
SENDER_EMAIL = "test@your sandbox url"
RECIPIENT_EMAIL = "your mail id"
API_KEY = "Bolt API key"
DEVICE_ID = "Your Device ID"
FRAME_SIZE = 10
MUL_FACTOR = 6

Make anomaly_detection.py in which we write a python code to use z-score analysis for anomaly detection and run it using

python3 anaomaly_detection.py

Python code is attached below

In case the anomaly occurs or temperature crosses the threshold, an SMS & mail alert is sent out using the Twilio and Mailgun.

The Screenshots of Twilio's Sms and Mailgun's Email

and Screenshot of display

Thank you

Code

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


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

    if len(history_data) > frame_size :
        del history_data[0:len(history_data)-frame_size]
    Mn = statistics.mean(history_data)
    Variance = 0
    for data in history_data:
        Variance += math.pow((data-Mn), 2)
    Zn = factor * math.sqrt(Variance / frame_size)
    High_bound = history_data[frame_size-1]+Zn
    Low_Bound = history_data[frame_size-1]-Zn
    return [High_bound,Low_Bound]


minimum_limit = 7 #can be change
maximum_limit = 40 #can be change

mybolt = Bolt(email_conf.API_KEY, email_conf.DEVICE_ID)
mailer = Email(email_conf.MAILGUN_API_KEY, email_conf.SANDBOX_URL, email_conf.SENDER_EMAIL, email_conf.RECIPIENT_EMAIL)
sms = Sms(conf.SSID, conf.AUTH_TOKEN, conf.TO_NUMBER, conf.FROM_NUMBER)

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("The sensor value is"+(data['value']))
    sensor_value = 0
    try:
        sensor_value = int(data['value'])
    except Exception as e:
        print("There was an error while parsing the response:", e)
        continue
    bound = compute_bounds(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 > maximum_limit or sensor_value < minimum_limit:
            response = mailer.send_email("Alert", "The Current temperature is beyond the threshold ")
        if sensor_value > bound[0]:
            print("The temperature increased suddenly.Sending Sms.")
            response = sms.send_sms("Someone opened the chamber")
            print("This is the response", response)
        elif sensor_value < bound[1]:
            print("The temperature decreased suddenly. Sending an email.")
            response = mailer.send_email("Someone opened the chamber")
            print("This is the response", response)
        history_data.append(sensor_value)
    except Exception as e:
        print("Error", e)
    time.sleep(10)

Credits

Tarun Singh Negi

2 projects • 5 followers

a student and want to learn a lot of things

Monitoring of Temperature and Its Alert

Things used in this project

Hardware components

Software apps and online services

Story

Building the Project

Step 1: Connecting LM35 to Bolt

Step 2: Configure Bolt IoT

Step 3: Visualization

Step 4: Anomaly Detection with Z- Score analysis and Notification

Schematics

LM35 connection to Bolt

Code

anomaly_detection.py

conf.py

email_conf.py

Credits

Tarun Singh Negi

Comments

Embed the widget on your own site

Monitoring of Temperature and Its Alert

Monitoring of Temperature and Its Alert

Things used in this project

Hardware components

Software apps and online services

Story

Building the Project

Step 1: Connecting LM35 to Bolt

Step 2: Configure Bolt IoT

Step 3: Visualization

Step 4: Anomaly Detection with Z- Score analysis and Notification

Schematics

LM35 connection to Bolt

Code

anomaly_detection.py

conf.py

email_conf.py

Credits

Tarun Singh Negi

Comments

Related channels and tags