Internet of Things

We will use standard weather and news information from weather.com and NEW API websites.

and as well, will use implanted IOT sensors to capture vision, density, temperature, moisture, sound and activities. Sensors

density / vision

Capturing crowd density varies case by case. For example, In case of, organized gatherings like Theme parks, concerts etc. number of people attending the event can be predicted in advance.

However, at the same, number of people entering, leaving and present at a given time is very important. Most of the chaos, happens when too many people appear at a place at the same time. for example, people entering / leaving premises.

Sensors Sensors

Reference

other option is, Density will calculated using vision AI, captured through a motion camera / CCTV footage.

Sensors

visibility

Brightness

Sensors

temperature

Outside temperature

Sensors

##############################################
# outdoorTemp
##############################################
using DataFrames, CSV, Dates, Distributions
sampleSize = 365
weatherDF = DataFrame(
    cityid = 1:1:sampleSize,
    state = rand(["LA","LA","FL"], sampleSize),
    indoorTemp = rand(64:1:94, sampleSize),
    outdoorTemp = rand(54:1:104, sampleSize),
    wind = rand(5:1:30, sampleSize),
    humidity = rand(30:1:70, sampleSize),
    precipitation = rand(0:1:5, sampleSize)
    )
first(weatherDF[:, [:cityid, :state, :outdoorTemp]], 10)

10 rows × 3 columns

	cityid	state	outdoorTemp
	Int64	String	Int64
1	1	LA	94
2	2	FL	101
3	3	LA	87
4	4	LA	98
5	5	LA	85
6	6	LA	62
7	7	LA	70
8	8	FL	74
9	9	LA	102
10	10	FL	103

Inside temperature

Sensors

##############################################
# outdoorTemp
##############################################
using DataFrames, CSV, Dates, Distributions
sampleSize = 365
weatherDF = DataFrame(
    cityid = 1:1:sampleSize,
    state = rand(["LA","LA","FL"], sampleSize),
    indoorTemp = rand(64:1:94, sampleSize),
    outdoorTemp = rand(54:1:104, sampleSize),
    wind = rand(5:1:30, sampleSize),
    humidity = rand(30:1:70, sampleSize),
    precipitation = rand(0:1:5, sampleSize)
    )
first(weatherDF[:, [:cityid, :state, :indoorTemp]], 10)

10 rows × 3 columns

	cityid	state	indoorTemp
	Int64	String	Int64
1	1	FL	67
2	2	LA	82
3	3	LA	78
4	4	FL	93
5	5	LA	94
6	6	FL	76
7	7	FL	81
8	8	LA	79
9	9	LA	70
10	10	FL	94

moisture

Sensors

##############################################
# moisture
##############################################
using DataFrames, CSV, Dates, Distributions
sampleSize = 365
weatherDF = DataFrame(
    cityid = 1:1:sampleSize,
    state = rand(["LA","LA","FL"], sampleSize),
    indoorTemp = rand(64:1:94, sampleSize),
    outdoorTemp = rand(54:1:104, sampleSize),
    wind = rand(5:1:30, sampleSize),
    humidity = rand(30:1:70, sampleSize),
    precipitation = rand(0:1:5, sampleSize)
    )
first(weatherDF[:,[:cityid, :state, :humidity]], 10)

10 rows × 3 columns

	cityid	state	humidity
	Int64	String	Int64
1	1	LA	33
2	2	LA	59
3	3	LA	68
4	4	LA	47
5	5	LA	49
6	6	LA	40
7	7	LA	32
8	8	LA	55
9	9	LA	33
10	10	LA	31

sound

Sensors

##############################################
# Noise / sound
##############################################
using DataFrames, CSV, Dates, Distributions
sampleSize = 365
weatherDF = DataFrame(
    cityid = 1:1:sampleSize,
    state = rand(["LA","LA","FL"], sampleSize),
    indoorTemp = rand(64:1:94, sampleSize),
    sound = rand(54:1:104, sampleSize),
    wind = rand(5:1:30, sampleSize),
    humidity = rand(30:1:70, sampleSize),
    precipitation = rand(0:1:5, sampleSize)
    )
first(weatherDF[:,[:cityid, :state, :sound]], 10)

10 rows × 3 columns

	cityid	state	sound
	Int64	String	Int64
1	1	FL	86
2	2	LA	76
3	3	LA	90
4	4	FL	69
5	5	FL	83
6	6	LA	103
7	7	LA	63
8	8	FL	59
9	9	LA	59
10	10	LA	69

activities

motion activities

Sensors

##############################################
# motion activities
##############################################
using DataFrames, CSV, Dates, Distributions
sampleSize = 365
weatherDF = DataFrame(
    cityid = 1:1:sampleSize,
    state = rand(["LA","LA","FL"], sampleSize),
    indoorTemp = rand(64:1:94, sampleSize),
    sound = rand(54:1:104, sampleSize),
    shadows = rand(5:1:30, sampleSize),
    humidity = rand(30:1:70, sampleSize),
    precipitation = rand(0:1:5, sampleSize)
    )
first(weatherDF[:,[:cityid, :state, :shadows]], 10)

10 rows × 3 columns

	cityid	state	shadows
	Int64	String	Int64
1	1	FL	29
2	2	LA	8
3	3	LA	8
4	4	LA	29
5	5	LA	28
6	6	LA	29
7	7	FL	11
8	8	LA	24
9	9	FL	19
10	10	LA	14