Hindawi

Journal of Sensors
Volume 2021, Article ID 9931228, 13 pages
https://doi.org/10.1155/2021/9931228

Research Article
Smart eNose Food Waste Management System

Shazmina Gull , Imran Sarwar Bajwa , Waheed Anwar , and Rubina Rashid
Department of Computer Science, The Islamia University of Bahawalpur, Bahawalpur, Pakistan

Correspondence should be addressed to Imran Sarwar Bajwa; [email protected]

Received 4 March 2021; Accepted 20 June 2021; Published 22 July 2021

Academic Editor: Roberto Paolesse

Copyright © 2021 Shazmina Gull et al. This is an open access article distributed under the Creative Commons Attribution License,
which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

The modern age is an era of fast-growing technology, all thanks to the Internet of Things. The IoT becomes a prime factor of human
life. As in this running world, no one cares about the wastage of food. However, this causes environment pollution as well as loss of
many lives. A lot of researchers help in this era by introducing some great and beneficial projects. Our work is introducing a new
approach by utilizing some low-cost sensors. In this work, Arduino UNO is used as a microcontroller. We use the eNose system that
comprises MQ4 and MQ135 to detect gas emission from different food items, i.e., meat, rice, rice and meat, and bread. We collect
our data from these food items. The MQ4 sensor detects the CH4 gas while the MQ135 sensor detects CO2 and NH3 in this system.
We use a 5 kg strain gauge load cell sensor and HX711 A/D converter as a weight sensor to measure the weight of food being wasted.
To ensure the accuracy and efficiency of our system, we first calibrate our sensors as per recommendations to run in the
environment with the flow. We collect our data using cooked, uncooked, and rotten food items. To make this system a smart
system, we use a machine learning algorithm to predict the food items on the basis of gas emission. The decision tree algorithm
was used for training and testing purposes. We use 70 instances of each food item in the dataset. On the rule set, we implement
this system working to measure the weight of food wastage and to predict the food item. The Arduino UNO board fetches the
sensor data and sends it to the computer system for interpretation and analysis. Then, the machine learning algorithm works to
predict the food item. At the end, we get our data of which food item is wasted in what amount in one day. We found 92.65%
accuracy in our system. This system helps in reducing the amount of food wastage at home and restaurants as well by the daily
report of food wastage in their computer system.

1. Introduction sumes water as one apple growth consumes 125 litres of

water and one-kilogram beef needs to consume 15,400 litres
The IoT encompasses all fields of life and turns the world into [3]. And a huge amount of food waste contributes to water
a smart world. It works in hospitals, supermarkets, security waste. According to [3], 3.3 billion tons of CO2 wasted each
areas, banks, business, offices, laboratories, restaurants, edu- year, and 1 tons of food waste reduction can save approxi-
cational institutions, and home making the world smart mately 4.2 tons of CO2 [4].
and intellectual. As household and restaurant automation is To overcome this problem, IoT can help in monitoring
discussed, the main unit of both areas is the kitchen where and reducing the waste of food. There is a noteworthy
food is produced, cooked, and served to people to feed them requirement to control, monitor, and management of food
and make them healthy. But the main problem is the wastage wastage. A system is a desideratum to cover the above-
of food. Food wastage becomes a threatening problem nowa- mentioned measures. This problem can be handled to IoT,
days. Around 1.3 billion tons of food is wasted each year that as it bordered every field of life, by using some sensors, actu-
is enough to feed 3 billion hungry people each year at a cost ators, and modules. This research helps the chef as well as the
of $990 billion [1]. Just in Pakistan, around 36 million tons home and restaurants to reduce the food wastage using IoT
of food is wasted each year [2]. sensors and modules.
Greenhouse gases are emitted at food production time Electronic nose (eNose) concept comprises several het-
(which makes the 14.1% of emission) while methane gas is erogeneous electrochemical gas sensors that work according
produced at the time of food decay [1]. Food production con- to the mechanism of human nose. eNose consists of sensing,
2 Journal of Sensors

eNose system
MQ135
User
MQ4

Food item Arduino Control unit

Cloud/data server
Weight sensor

Figure 1: System architecture of smart eNose food waste management.

detecting, and measuring the gas compounds, micro- and Decision tree is used as the machine algorithm in this system.
macromolecules, ion species, and volatile particles in samples The control unit analyzes and stores sensor values sent by the
and data processing and analysis systems. Arduino. The user can check the food wastage statistics
A lot of food researches have been came in the IoT era for through the system.
different FSC states, i.e., for production monitoring, quality The rest of the paper discusses the proposed system in
monitoring, waste management using RFID, temperature, more detail. “State of the Art” is all about the related research
humidity, camera, and many other sensors and modules. work. “Architecture of IoT-Based Food Waste Management”
Not any single research brings forward the idea of detecting tells about the architecture of the proposed system. “System
food items using low-cost sensors and detecting the food Implementation” contains the specifications of hardware
items while measuring food wastage. For this context, this used in this research. It contains the calibration of sensors,
research is new in its architecture and methodology. implementation of machine algorithm, and the smart eNose
This research helped in detecting, monitoring, and man- food waste management system. “Results and Discussion”
aging the food wastage in context of eNose and weight sensor contains the results of this research after the experiments
along with the Wi-Fi and Arduino modules. This research and implementation. “Conclusion” and “Future Work” con-
using gas sensors, i.e., MQ135 and MQ4, and a load cell tain the conclusion and future work of this research work,
enables the restaurants and households to monitor their food respectively.
wastage and upon statistics to reduce the amount of wastage
using some useful initiatives. Wastage of food can reduce if 2. State of the Art
monitored properly, analyzed on daily basis, and reported
to user. Detecting food items would help in attaining the This chapter discusses the related work in food department
amount of wastage of each food item and, after that, prepar- using the IoT technology. The work that is related to manag-
ing specific food item as earlier as needed by comparing the ing the food waste or casual wastage of any area using IoT
analysis report. The main objectives of this research are as technology, what researches have done on food quality in
follows: any phase of FSC (food supply chain), and IoT-based kitchen
systems that used to manage buckets and stove system in
(i) A system for real-time monitoring must have to be kitchens are describe here in detail.
ensured for food wastage reduction
2.1. Food Waste Management. Jagtap and Rahimifard [5]
(ii) A system must be capable of detecting food items reduces the wastage of meat 60.7% at the Chicken Tikka
(i.e., milk, meat, fruit, vegetable, or bread) to reduce Masala restaurant within eight months. A bin carried the
food waste wastage where a load cell weighs the wasted meat and that
(iii) A smart system is mandatory for restaurants to figures are sent to the mobile app using a Bluetooth sensor.
The data is then sent to the cloud server for analysis and stor-
detect and monitor food waste regularly to monitor
age purposes.
how much amount is being wasted and which item
Hong et al. [6–10] designed a smart garbage system that
is being wasted the most
collects food from houses, and users pay regularly according
(iv) A smart cost-effective system is needed to assist in to their waste materials. They used RFID to track the garbage
kitchen management against food wastage. collectors and weight sensors to weight the waste material.
The garbage collectors are synchronized with cloud.
The proposed system is composed of three layers/nodes: The IoT-based smart garbage and waste collection bin
sensor node, machine algorithm, and control unit. Sensor [11] used IR for level detection, weight sensor, and Wi-Fi.
node worked with the eNose system (MQ4, MQ135) and Whenever IR detects the overweight, it alarmed the system
weight sensor (HX711 and strain gauge load cell) to detect and user to free up the smart bin.
the food items and measure the weight of food waste. The A very efficient and smart restaurant waste management
machine algorithm is used here to analyze the food items. system monitored the generation (using RFID and weight
Journal of Sensors 3

Step 1: Data collection is the first step of proposed system that is used to collect the data from connected sensors.
Step 2: After data collection, the next step is data processing to organize the attribute values into a spreadsheet file for making the struc-
tured dataset.
Step 3: After data processing, the next step is data cleansing in which the data normalize each attribute value by handling the duplicate,
incomplete, and faulty values.
Step 4: In this step, we apply some validation methods for data analysis by using decision tree. Information gain and gain ratio are used
for decision tree classifier.
Step 5: In the second last step, data prediction is performed by detecting the food item either meat or any other food item (rice, rice and
meat, or bread).
Step 6: In the last step, predicted results are displayed and visualized.

Algorithm 1: Working algorithm of IoT-based food waste management.

Start

Sensors

Sensor data input

Control unit

Generate excel sheet of data

Data cleansing/
Normalization

Generate dataset

Find gain ratio &

information gain

Choose best one attribute for root

Split data

Training Testing
dataset dataset

Apply decision
Tree

Decision tree generate

Apply model

Trained decision tree generate

Check accuracy
& performance

Final result

Visualization

Graphs/plots

End

Figure 2: Flowchart of smart eNose food waste management system.

4 Journal of Sensors

sensor bin at each restaurant), collection (through smart

wastage collection truck enabled with RFID, weight, video
surveillance cameras, and GPS/GIS monitoring), transporta-
tion (using truck with real-time video monitoring), and
disposal (by measuring the weight of wastage using RFID)
of food waste at restaurants. This system worked well, effi-
ciently, and with low error rate. [12]
Ostojić et al. [13, 14] measured the temperature and
humidity of supplied food items and alert the user when
the parameter values increased. RFID tag is used to detect
each food item. They used Wi-Fi to sync with the server
and cloud.
Figure 3: MQ135 sensor.
The food waste management system [15] for a university
mess is designed using a sharp IR sensor to count people,
using the mess-meal-cards in a box, weighting sensor, and
Hx711-IC to measure the weight of wastage of the food.
The sensed value is displayed on LED, and the LED sends
data to IC every 3 seconds. The resultant data is also
uploaded to web portal to monitor the food wastage.
Elhassan et al. [16] proposed a smart garbage bin for
massive areas that contains five sections for different waste
materials (paper, plastic, metal, glass, and food, respectively).
The authors used a capacitive proximity sensor for detecting
paper and plastic, metal sensor for metal detection, infrared
sensor for glass detection, humidity sensor to validate
whether the trash is wet or not, ultrasonic sensor to detect Figure 4: MQ4 sensor.
the trash bin level, and servomotor and solar cell for power
consumption. The sensed values are sent to the control unit
using radio frequency signals. As bin is filled with wastage
or the humidity level increased, the system alerts the user.
Sofia et al. detect and analyze the presence of mycotoxins
in different food items using UV, spectrometer, biosensors,
and electrical nose and proved that the mycotoxins destroy
food in any stage of food production, preservation, and har-
vesting [17].
A food waste management-recycling system [18] used
RFID and weight and level sensor to detect the bin tag
and location and to measure the waste weight and the level
detection (3 levels) of trash in trash bin. The trash bin is
collected by a smart truck, and all the collected food wast-
age is recycled in fertilizer for planting using FWDM
(designed using motor vehicle parts and IOT modules).
The overall result and data capture through sensors can Figure 5: Weight sensor: HX711 and 5 kg load cell.
be seen on LCDs.
A smart bin system is created for recycling and managing
the wastage. The RFID and Wi-Fi module is used in this pro- Minaam et al. [23] designed a system that used a led indi-
ject. A user via a web service calls for a smart bin and places cator and AVR burning tool, for indicating the cooking time
the wastage in to the bin by specifying the waste type. If the of a meal. The chef can set a timer for different cooking food
waste is recyclable, this wastage is sent to the company items at the same time using a 4 × 4 keypad.
(waste-collector-vendor) for recycling; otherwise, it would An AI system for smart refrigerator worked with image
be wasted/discarded. Each type of wastage is weighted by processing to detect food items and their freshness status;
the wastage-based billing system. The user has to pay the bill after that, the NLP analysis helped to analyze which food is
using RFID [19]. going to rot, and an alarming message is sent to the user
via a mobile phone to prevent food spoilage and to manage
2.2. IoT-Based Kitchen. Chatterjee et al. [20–22] worked on the food wastage [24].
kitchen air quality by measuring temperature, humidity, gas Chopade and Nighot [25–27] worked on kitchen pantry
leakage, and water flow using respective sensors. Whenever systems that detect the level of food stored on shelves and
these parameters crossed the threshold, the system alerts alert the user whenever it reduced and suggest the nearby
the user. stores from where the user can purchase that food item.
Journal of Sensors 5

MQ–4
10

Rs/Ro
1

0.1
100 1000 10000
LPG Al cohol
CH4 Smoke
H2 Air
C0

Figure 6: MQ4-CH4 measurement-circuit gas concentration graph.

MQ–135
10
Rs/Ro

0.1
10 100 1000
ppm

Air NH4
CO2 1/4⁎
CO +
3/4 AE

Figure 7: MQ135-CO2+NH4 measurement-circuit gas concentration graph.

3. Architecture of IoT-Based Food the weight of the wasted food item. The record is then saved
Waste Management into the database for further precautionary measures to
reduce the food wastage. Architecture of smart eNose food
This smart system consists of combination of different sen- waste management is shown in Figure 1, in which we
sors and modules. The user has to put wasted food item on depicted all components, their interaction, and working
the acrylic disc of the weight sensor. The weight sensor mea- strategy.
sures the weight of the wasted food, and the eNose system
detects the gas emission from food items. The sensed values
are then sent to the control unit by digitizing the analog 3.1. Used Algorithm. We designed the detailed working algo-
sensed values using Arduino. Arduino IDE is used to inter- rithm of IoT-based smart eNose food waste management
pret the sensed information. The control unit analyzes the based on entropy and information from decision tree. The
sensor information through the machine algorithm and proposed algorithm steps are described in Algorithm 1, and
comes up to a result which food item is being wasted and flow chart is given in Figure 2.
6 Journal of Sensors

Name Type Missing Statistics

Label Least Most Values

Class Polynominal 0 Rice&Meat (70) Bread (70) Bread (70), Meat (70), ...[2 more]

Min Max Average

NH3 Real 0 3.320 6.460 5.222

Min Max Average

CO2 Real 0 272.090 1031.870 687.768

Min Max Average

CH4 Real 0 1.750 7.190 4.549

Figure 8: Statistics of full dataset.

Table 1: Information gain of full dataset. Table 3: Gain ratio of training dataset.

Attribute Weight Attribute Weight

NH3 0.813 NH3 0.886
CO2 0.813 CH4 0.908
CH4 0.813 CO2 0.917

Table 2: Gain ratio of full dataset. used for detecting the NH3 and CO2 in food waste. MQ135
gas sensor is shown in Figure 3.
Attribute Weight
The MQ4 sensor is used to detect CH4, cigarette smoke,
CH4 0.815 natural gas LNG, cooking fumes, and alcohol. It is highly sen-
NH3 0.864 sitive to CH4 and LNG yet low sensitive to smoke and alco-
CO2 0.881 hol. In our system, it is used to detect CH4 in food waste.
The MQ4 gas sensor is shown in Figure 4.
Weight sensor consists of HX711 (A/D converter) and 5
3.2. Machine Algorithm for Smart eNose Food Waste kg load cell (weight gauge) sensor that is used to measure the
Management. After sensing, retrieving, and constructing weight of food wasted. HX711 is a high-precision 24-bit
the dataset, classification and regression are done using the analog-to-digital converter. HX711 is specially designed for
decision tree. We use RapidMiner for applying machine industries and weighing scales. It can be directly interfaced
learning algorithm: decision tree. with the bridge sensor. It supports two analog-input chan-
The decision tree algorithm is a supervised learning algo- nels. Weight sensor is shown in Figure 5.
rithm that is used for classification and regression. The deci-
sion tree algorithm generates a training model (trained 4.2. Sensor Calibration. In this proposed model, MQ135,
decision tree and rule set) to predict the desired attribute’s MQ4, and load cell sensors are mainly used for detection
(class in our dataset) values. We used the C4.5 decision tree and measurement purposes. These sensors are used in a pro-
algorithm model (advanced ID3) in this project. totype model after calibration. Before their actual usage, the
We used the information gain and gain ratio. We gas sensors (MQ135, MQ4) are put to preheat for 24 hours
calculate the information gain and gain ratio using the for each gas detection and were made sure to use 10 kΩ or
RapidMiner tool before splitting the dataset. The highest above with gas sensors (MQ135, MQ4) for RL . For calibra-
information gain is chosen by the decision tree algorithm to tion, RO has to be calculated firstly in fresh air, and after that,
construct/split the decision tree. We used the gain ratio for it never changes in fresh air. The calculated value of RO is
splitting our dataset to construct the decision tree. Gain ratio used to calculate the RS that is changeable with the gas con-
is used to remove the biasness over attributes. centration or presence in specific gas.
The general formula to calculate PPM of a gas is
4. System Implementation PPM = 10∧½flog ðratioÞ − b/mg: ð1Þ
4.1. Used Hardware. We designed the sensor node of the
smart eNose food waste management by using multiple sen- The measurement gas concentration graph for MQ4 and
sors MQ135, MQ4, and weight sensor. A microcontroller MQ135 is given in Figures 6 and 7, respectively.
Arduino UNO is used for embedding these sensors. Detail The gas concentration graph is on log-log scale/linear
of hardware components used in data collection is as follows: scale. So, the line formula is used to find the log-log scale
MQ135 is an air-quality highly sensitive sensor/module. gas concentration ratio.
This sensor used to detect the smoke, NH3, alcohol, NOx,
benzene, and CO2. In our proposed system, this sensor is y = mx + b: ð2Þ
Journal of Sensors 7

CO2

> 542.425 > 542.425

Rice
NH3

> 5.030 ≤ 5.030

CH4 CH4

> 3.770 ≤ 3.770 > 3.175 ≤ 3.175

Rice & Meat Meat Bread Meat

Figure 9: Trained decision tree.

Figure 10: Implementation of smart eNose food waste management system.

Here, y is the X value, x is X value, m is the slope of line, PLX-DAQ. In this current system, four classes are used to
and b is y intercept. discriminate between food items based on gas emission (see
For log-log scale, convert (2) into following: Figure 8).
The information gain for our dataset is given in Table 1.
log ðyÞ = m × log ðxÞ + b: ð3Þ As shown in Table 1, information gain for all of the attri-
butes and the number of instances used for each class item
Here, the log base is 10. are of equal size.
The value of RO found by the MQ4 and MQ135 sensors The calculated gain ratio for our dataset is given in
in our system is 4.78. Table 2.
The weight sensor contains a strain gauge load cell and a We also calculate the gain ratio of the training dataset for
HX711 A/D converter. For its calibration, the known weight accuracy (see Table 3).
has to be placed on the load cell, and the calibration factor to The both calculated gain ratios give the highest ratio of
set the scale was found. After that, that calibration factor was CO2, so we choose the CO2 attribute as root or construc-
used to measure the weight of an unknown object. In this tion/split in the decision tree.
research, the method used for calibration is taken from the The rule model for this current system is as follows:
HX711_ADC library. The calibration value of weight sensor If CO2 > 542:425, NH3 > 5:030, and CH4 > 3:770, then
found using our load cell is 456.0. rice and meat is (52/0/0/0).
If CO2 > 542:425, NH3 > 5:030, and CH4 ≤ 3:770, then
4.3. Implementation of Decision Tree Algorithm. The dataset meat is (0/49/0/0).
is collected by two sensors, MQ4 (CH4 detection) and If CO2 > 542:425, NH3 ≤ 5:030, and CH4 > 3:175, then
MQ135 (CO2 and NH3 detection), using Arduino IDE and bread is (1/0/1/53).
8 Journal of Sensors

Time 5:00:00 AM PKT 5:00:00 AM PKT

281.838
251.189
223.872
199.526
177.828
158.489
141.254
125.893
Weight

112.202
100
89.125
79.433
70.795
63.096
56.234
50.119

Rice Bread Meat Rice & Meat

Food_Class

Figure 11: Food wastage in one day at home.

Table 4: Performance vector of algorithm.

according to the need and likes of consumers. This system
Accuracy: 92.65% requires no human interception as the literature research
Confusion matrix: work needs human to enter the food type or weight of food
True Rice and meat Meat Rice Bread wastage.
Rice and meat 14 0 0 1 We implement our system at home. The food wastage in
one day at home can be found easily using graphs. These
Meat 0 17 0 0
graphs are made by using RapidMiner. One of these graph
Rice 1 0 17 1 records is given in Figure 11.
Bread 2 0 0 15 In Figure 11, the weight is measured in grams.

5.1. System Accuracy and Efficiency. The smart eNose food

waste management system is accurate, efficient, and highly
If CO2 > 542:425, NH3 ≤ 5:030, and CH4 ≤ 3:175, then performed. These features are achieved after training and
meat is (0/3/0/0). testing the dataset on different food items. The proposed sys-
If CO2 ≤ 542:425, then rice is (0/1/52/0). tem offers a class precision for meat, rice, rice and meat, and
The trained decision tree for this proposed system is bread of 100%, 89.47%, 93.33%, and 88.24%, respectively; the
given in Figure 9, and the implementation of proposed sys- class recall of meat, rice, rice and meat, and bread is 100%,
tem is given in Figure 10. 100%, 82.35%, and 88.24%, respectively, and 92.65% accu-
racy and weighted-mean recall. The accuracy and perfor-
5. Results and Discussion mance vectors description are given in Table 4:
The scatter plots, retrieved after making the decision tree
The smart eNose food waste management System is opera- of given dataset, are given in Figure 12.
ble in homes and restaurants as well. This proposed system To describe the frequency of different attributes over food
is efficient, real-time, accurate, and cost-effective. The pro- items, color-histogram graph is used in this proposed system
posed system detects the food items with the collaboration (see Figure 13).
of sensors and actuators and measures the weight of waste The proposed system has also some negative points as
food. The sensed information is then analyzed using the there is a 7.35% classification error in implementing the deci-
decision tree. This system helps to reduce the food wastage sion tree using the dataset generated from the sensors
by checking the previous records. A chef can also cook (Table 5; classification error: 7.35%).
Journal of Sensors 9

CH4 CH4

NH3 CO2

(a) (b)
CO2 NH3

NH3 CO2

(c) (d)
NH3

CH4

(e)

Figure 12: (a–e) Scatter plots of multiple attributes where blue denotes rice and meat, red denotes bread, sea-green denotes meat, and light-
green denotes rice.
10 Journal of Sensors

4.00
3.75
3.50
3.25
3.00
2.75
2.50
Frequency

2.25
2.00
1.75
1.50
1.25
1.00
0.75
0.50
0.25
0.00
2.75 3.00 3.25 3.50 3.75 4.00 4.25 4.50 4.75 5.00 5.25 5.50 5.75 6.00 6.25 6.50 6.75 7.00

CH4

Rice and Meat Rice

Meat Bread
(a)

4.00
3.75
3.50
3.25
3.00
2.75
2.50
Frequency

2.25
2.00
1.75
1.50
1.25
1.00
0.75
0.50
0.25
0.00
300 350 400 450 500 550 600 650 700 750 800 850 900 950 1,000

CO2
Rice and Meat Rice
Meat Bread
(b)

Figure 13: Continued.

Journal of Sensors 11

4.00
3.75
3.50
3.25
3.00
2.75
2.50
Frequency

2.25
2.00
1.75
1.50
1.25
1.00
0.75
0.50
0.25
0.00
3.50 3.75 4.00 4.25 4.50 4.75 5.00 5.25 5.50 5.75 6.00 6.25 6.50

NH3
Rice and Meat Rice
Meat Bread
(c)

Figure 13: Color-histogram frequency graphs. (a) CH4 frequency over class. (b) CO2 frequency over class. (c) NH3 frequency over class.

Table 5: Classification error.

True rice and meat True meat True rice True bread Class precision
Pred. rice and meat 14 0 0 1 93.33%
Pred. meat 0 17 0 0 100.00%
Pred. rice 1 0 17 1 89.47%
Pred. bread 2 0 0 15 88.24%
Class recall 82.35% 100.00% 100.00% 88.24%

.
6. Conclusion lect data, 70 instances of each, of four food items, i.e.,
meat, rice, rice and meat, and bread. We use 5 kg strain
Food wastage becomes a renowned issue of these days. In this gauge load cell and HX711 as the weight sensor to mea-
modern computer age, there is a need to control human sure the weight of food wastage.
chores using computers. To fulfill this purpose of IoT and For ensuring the accuracy and performance of our sys-
to reduce the amount of food wastage, we designed a system tem, we calibrate the sensors as per recommendations. We
that is suitable in this situation and do not need human col- use the decision tree algorithm with contrast to the informa-
laboration to control and monitor it manually. tion gain and gain ratio to make this system an intelligent and
We proposed a smart eNose food waste management smart system. The generated rule model is applied in actual
system that is capable of describing a food item and in implementation of the current system software. We imple-
which amount is wasted in a day. For this accomplish- ment our system in home and find out the food wastage in
ment, we use sensors and microcontroller collaboration one day. The current system is accurate, efficient, cost-effec-
with the great contribution of decision tree. We detect tive, and durable in its performance. This system appeals
food items through their gas emission. The smart eNose high accuracy of 92.65%. There is a least classification error
system helps us to detect food items which contain MQ4 found, 7.35%.
and MQ135 sensors. MQ4 is used to detect CH4 (emitted The proposed system is new in its technology and fills the
from rice). MQ135 is used to detect CO2 (emitted from gap in the food waste management industry with its high
bread and meat) and NH3 (emitted from meat). We col- accuracy and cost-efficiency.
12 Journal of Sensors

7. Future Work [12] Z. Wen, S. Hu, D. De Clercq et al., “Design, implementation,

and evaluation of an internet of things (IoT) network system
In the future, we want to increase our accuracy and perfor- for restaurant food waste management,” Waste Management,
mance using more sensors, i.e., pH sensor for food items vol. 73, pp. 26–38, 2018.
and ethylene sensor to work with fruits and vegetables. As [13] G. Ostojić, S. Stankovski, S. Tegeltija, N. Đukić, and B. Tejić,
this, the today world is incomplete without smart phones. “Implementation of IoT for food wastage minimisation,” in
So, we want to make our system mobilize for every user to XVII International Scientific Conference on Industrial Systems,
interact with the system using their mobile phones at any Novi Sad, Serbia, October 2017.
place at any time. This would help in increasing the accuracy, [14] Z. Li, G. Liu, L. Liu, X. Lai, and G. Xu, “IoT-based tracking and
durability, reliability, and efficiency of the proposed system. tracing platform for prepackaged food supply chain,” Indus-
trial Management & Data Systems, vol. 117, no. 9, pp. 1906–
1916, 2017.
Data Availability
[15] V. Jain, “eBin: an automated food wastage tracking system for
Data related to this research will be available if needed. dormitory student's mess,” in 2016 International Conference
on Internet of Things and Applications (IOTA), Pune, India,
January 2016.
Conflicts of Interest [16] R. Elhassan, M. A. Ahmed, and R. AbdAlhalem, “Smart waste
The authors declare that they have no conflicts of interest. management system for crowded area: Makkah and holy sites
as a model,” in 2019 4th MEC International Conference on Big
Data and Smart City (ICBDSC), Muscat, Oman, January 2019.
References [17] S. Agriopoulou, E. Stamatelopoulou, and T. Varzakas,
“Advances in analysis and detection of major mycotoxins in
[1] The World Bank, “What a WAste 2.0, a global snapshot of
foods,” Foods, vol. 9, no. 4, p. 518, 2020.
solid waste management to 2050,” May 2020, http://
datatopics.worldbank.org/what-a-waste/global_food_loss_ [18] K. Jayalakshmi, S. Pavithra, and C. Aarthi, “Waste to
and_waste.html. wealth—a novel approach for food waste management,” in
[2] F. H. Mughal, Food Waste and its Consequences, Dawn, 2018. 2017 IEEE International Conference on Electrical, Instrumen-
tation and Communication Engineering (ICEICE), Karur,
[3] trvst, “Why is food waste a global issue,” 2019, May 2020,
India, April 2017.
https://www.trvst.world/inspiration/why-is-food-waste-a-
global-issue/. [19] M. Kaur and K. S. Saini, “A framework for recyclable house-
hold waste management system in smart home using IoT,”
[4] The World Counts, “Global challenges,” May 2020, https://
in Computing and Network Sustainability, H. Vishwakarma
www.theworldcounts.com/challenges/consumption/foods-
and S. Akashe, Eds., vol. 12 of Lecture Notes in Networks
and-beverages/food-waste-facts.
and Systems, pp. 213–223, Springer, Singapore, 2017.
[5] S. Jagtap and S. Rahimifard, “The digitisation of food
manufacturing to reduce waste - case study of a ready meal fac- [20] J. M. Chatterjee, R. Kumar, M. Khari, D. T. Hung, and D.-
tory,” Waste Management, vol. 87, pp. 387–397, 2019. N. Le, “Internet of Things based system for smart kitchen,”
International Journal of Engineering and Manufacturing, Mod-
[6] I. Hong, S. Park, B. Lee, J. Lee, D. Jeong, and S. Park, “IoT-
ern Education and Computer Science Press, vol. 8, no. 4, p. 29,
based smart garbage system for efficient food waste manage-
2019.
ment,” The Scientific World Journal, vol. 2014, Article ID
646953, 13 pages, 2014. [21] M. Sundarapandiyan, S. Karthik, and M. J. A. Daniel, “IoT
based smart kitchen,” International Journal of Computer Sci-
[7] M. V. Patil and S. M. Gajbhiye, “A review on internet of things
ence Trends and Technology (IJCST), vol. 7, no. 2, 2019.
based garbage bins detection systems,” International Journal of
Science and Research, vol. 6, no. 4, pp. 1699–1702, 2017. [22] F. Nugroho and A. Pantjawati, “Automation and monitoring
[8] P. S. I. Shirke, S. Ithape, S. Lungase, and M. Mohare, “Automa- smart kitchen based on Internet of Things (IoT),” in IOP Con-
tion of smart waste management using IoT,” International ference Series: Materials Science and Engineering, Volume 384,
Research Journal of Engineering and Technology, vol. 6, no. 6, International Symposium on Materials and Electrical Engineer-
pp. 414–419, 2019. ing (ISMEE) 2017, Bandung, Indonesia, November 2017.
[9] E. D. Likotiko, D. Nyambo, and J. Mwangoka, “Multi-agent [23] D. S. A. Minaam, M. Abd-ELfattah, and M. A. Ali, “Design of
based IoT smart waste monitoring and collection architec- an Internet of Things (IoT) network system for kitchen food
ture,” International Journal of Computer Science, Engineering waste management,” International Journal of Computer Sci-
and Information Technology (IJCSEIT), vol. 7, no. 5, pp. 1– ence and Network Security, vol. 18, no. 5, pp. 130–138, 2018.
14, 2017. [24] T. Nagaraju and B. R. Shubhamangala, “Artificial intelligence
[10] M. Giacobbe, C. Puliafito, and M. Scarpa, “The big bucket: an powered smart refrigerator to arrest food wastage,” in 3rd
IoT cloud solution for smart waste management in smart cit- International Conference on Innovative Computing and Com-
ies,” in Advances in Service-Oriented and Cloud Computing. munication (ICICC-2020), Delhi, India, April 2020.
ESOCC 2016. Communications in Computer and Information [25] S. Dilip Chopade and M. K. Nighot, “Smart kitchen manage-
Science, vol 707, A. Lazovik and S. Schulte, Eds., Springer, ment using IOT technology,” International Journal of
Cham, 2016. Advanced Research in Computer Engineering & Technology,
[11] S. Navghane, M. Killedar, and V. Rohokale, “IoT based smart vol. 8, no. 7, pp. 269–271, 2019.
garbage and waste collection bin,” International Journal of [26] S. Rezwan, W. Ahmed, M. A. Mahia, and M. R. Islam, “IoT
Advanced Research in Electronics and Communication Engi- based smart inventory management system for kitchen using
neering, vol. 5, no. 5, pp. 1576–1578, 2016. weight sensors, LDR, LED, Arduino Mega and NodeMCU
Journal of Sensors 13

(ESP8266) Wi-Fi module with website and app,” in 2018

Fourth International Conference on Advances in Computing,
Communication & Automation (ICACCA), Subang Jaya,
Malaysia, October 2018.
[27] N. Korde and A. Thakare, “Smart shelve management system
using IoT-a novel approach,” in 2018 3rd International Con-
ference for Convergence in Technology (I2CT), Pune, India,
April 2018.