AU2021101744A4

AU2021101744A4 - The waste segregation method using machine learning technique

Info

Publication number: AU2021101744A4
Application number: AU2021101744A
Authority: AU
Inventors: Deepthi Bolukonda; Pawan Kumar Chaurasia; Ilyas, Md; Jay Kumar Jain; Sushma Jaiswal; Rajeev Raghuvanshi; Kamasani Chandrasekhar Reddy; Amit Kumar Sharma; Anurag SHRIVASTAVA; Ashutosh Kumar Singh; Ashwin Verma
Original assignee: Individual
Current assignee: Individual
Priority date: 2021-04-06
Filing date: 2021-04-06
Publication date: 2021-06-03
Anticipated expiration: 2029-04-06

Abstract

The waste segregation method using machine learning technique comprising an automatic waste management method based on machine learning where the waste is segregated into organic waste and inorganic waste once collected by the trash bin. Conventionally human are involved in segregation of waste which leads to several diseases also such method is not efficient. Incineration of improperly segregated waste generates gases such as carbon monoxide affecting the ozone layer. The proposed trash bin is equipped with sensor system which is able to segregate the waste in an intelligent way along with report generation of waste collected. Machine learning technique along with image recognition classified the thrash based on the input from sensors. Also the present invention comprising sensors, camera, online server dashboard, loT based connected camera, motors, Raspberry Pi camera module, Raspberry Pi Board and others supported members of the components and attachment as per the architecture of the present invention. APPLICANTS NAME:- Dr. Anurag Shrivastava ; Ashutosh kumar singh ; Dr. Sushma Jaiswal ; Dr. Jay KumarJain; Amit kumarSharma; Deepthi Bolukonda; Dr. Kamasani Chandrasekhar Reddy; Dr Pawan Kumar Chaurasia ; Md Ilyas; Dr. Rajeev Raghuvanshi Ashwin Verma ;Tulala Rajasanthosh Kumar Sheet lof 1 Waste Flap / iUd Lid opens when waste is detected -- Camera Module 1 oFlap Control Motor Biodegradable ->3- bCamera Module 2 Waste Collector Non -Biodegradable Waste Collector 10Partition Landfill Recyclable waste waste Figure 1 Dated 0 5 th April 2021.

Description

APPLICANTS NAME:- Dr. Anurag Shrivastava ; Ashutosh kumar singh ; Dr. Sushma Jaiswal ; Dr. Jay

KumarJain; Amit kumarSharma; Deepthi Bolukonda; Dr. Kamasani Chandrasekhar Reddy; Dr Pawan Kumar Chaurasia ; Md Ilyas; Dr. Rajeev Raghuvanshi

Ashwin Verma ;Tulala Rajasanthosh Kumar

Sheet lof 1

Waste

Flap / iUd Lid opens when waste is detected -- Camera Module 1

oFlap Control Motor Biodegradable bCamera Module 2 ->3- Waste Collector

Non -Biodegradable Waste Collector 10Partition

Landfill Recyclable waste waste

Figure 1

Dated 0 5 th April 2021.

EDITORIAL NOTE

2021101744

THERE ARE TWELVE PAGES OF DESCRIPTION ONLY FIELD OF THE INVENTION

The present invention related to waste separation and segregation method by using the machine learning method. The present invention more particularly relates to waste

segregation using smart bin using controlling all modules by loT as a machine learning technique, wherein biodegradable and non- biodegradable waste separation. The present

invention more particular controlled by only one easy tape and smart bin.

BACKGROUND OF THE INVENTION

Rapid increase of world's population has resulted to a serious problem of huge amount of

trash which is proportional increasing continuously. Waste management is viewed as a significant solution to solve this problem. Waste management indicates collection of waste,

transportation to non-residential places, proper disposal, recycling of useful products and monitoring of waste. Production of waste material is generally due to activity of human

beings which has to undergo segregation into biodegradable and non-biodegradable waste. A huge amount of manpower is required for the process of segregation before disposal or

recycling process.

Increase in population, progress in technological advancement, urbanisation and

development have resulted in an increase growth in consumer product. And with this progress comes a price; generation of waste. In a recent survey conducted by the World

Bank, about 1.3 billion tons of waste is generated each year. The number is expected to reach 2.2 billion by 2025. Waste management is a problem faced by a lot of societies and

communities. The amount of waste generated is far more than the waste recycled. Improper waste management has led to increase in cost of recycling and more working hours. This

leads to overcapacity of dumping grounds and landfills, littered waste around the city. These

environments act as a breeding ground for diseases.

A centralized system with the involvement of technology is demanded to replace human intervention in this segregation process as it also leads to several health hazards to the work

force. Environment is impacted with serious consequences such as water pollution, spreading of diseases, air pollution, local flooding and global warming due to waste mismanagement. Human health is affected by adverse effects due to improper disposal of hazardous waste. Hence in this invention, we propose automatic waste management system which avoids human intervention in waste segregation based on machine learning technique.

US 20200257573 Al disclosed the Fast modern interconnects may be exploited to control

when garbage collection is performed on the nodes (e.g., virtual machines, such as JVMs) of

a distributed system in which the individual processes communicate with each other and in which the heap memory is not shared. A garbage collection coordination mechanism (a

coordinator implemented by a dedicated process on a single node or distributed across the nodes) may obtain or receive state information from each of the nodes and apply one of

multiple supported garbage collection coordination policies to reduce the impact of garbage collection pauses, dependent on that information. For example, if the information indicates

that a node is about to collect, the coordinator may trigger a collection on all of the other

nodes (e.g., synchronizing collection pauses for batch-mode applications where throughput is important) or may steer requests to other nodes (e.g., for interactive applications where

request latencies are important).

US 10310507 B2 method of operating a mobile robot includes generating a segmentation map defining respective regions of a surface based on occupancy data that is collected by a

mobile robot responsive to navigation of the surface, identifying sub-regions of at least one of the respective regions as non-clutter and clutter areas, and computing a coverage pattern

based on identification of the sub-regions. The coverage pattern indicates a sequence for navigation of the non-clutter and clutter areas, and is provided to the mobile robot.

Responsive to the coverage pattern, the mobile robot sequentially navigates the non-clutter and clutter areas of the at least one of the respective regions of the surface in the sequence

indicated by the coverage pattern. Related methods, computing devices, and computer

program products are also discussed.

EP 2818258 A2 disclosed the machinery (1) for collecting and treating waste, in particular solid urban waste, comprises an outer containing casing (2), which houses a processing

chamber (3), in which the disposed waste is treated to produce two fractions and separate them from each other; and a holding chamber (4), connected to the processing chamber (3) and which receives and separately accumulates the two produced fractions; the processing chamber (3) comprises at least one waste separation part (9) provided with separation means (17), configured so as to separate the waste into an organic wet fraction and into a residual dry fraction directly in the machinery (1) and to accumulate the two fractions in respective compartments (21, 22) of the holding chamber (4).

US 9650650 B2 disclosed the Solid waste that includes a mixture of wet organic material and dry organic material can be are separated using mechanical separation to produce a wet

organic stream enriched in wet organics and a dry organic stream enriched in dry organics. The separated wet organic stream and dry organic stream are separately converted to

renewable or recyclable products using different conversion techniques particularly suited for the separated wet and dry organic streams.

US 20190249090 Al disclosed the approach is provided for processing mixed solid waste using an integrated bioenergy complex. The approach, for instance, involves receiving the

mixed solid waste at the integrated bioenergy complex, the integrated bioenergy complex including an organic conversion processing center and an inorganic conversion processing

center. The approach also involves separating the mixed solid waste into recyclables, an organic waste stream, and an inorganic waste stream. The approach further involves feeding

the organic waste stream to the organic conversion processing center to produce organic conversion products and an organic residual, and feeding the organic residual and the

inorganic waste stream to the inorganic conversion processing center to produce inorganic conversion products, electric power, and a residual waste. The electric power is used to

partially or fully power the organic conversion processing center, and residual waste is less than a target percentage of the received mixed solid waste.

SUMMARY OF THE INVENTION

The main aspect of the present invention comprising Integration of technology has found solution to several issues in this digital age. In this invention machine learning technique

along with loT (Internet of Things) is integrated for waste management providing promising solution for e-environments such as smart cities. This system involves sensors along with a monitoring platform where the sensors collect information about the garbage which is in turn used by the data analyzing technique for interpretation of type of waste leading to automatic waste segregation and its monitoring system. The proposed system uses two computers where monitoring will be done using LinkIt ONE and waste segregation based on image recognition will be done using Raspberry Pi 3.

One of the aspect of the present invention comprising a camera is installed at the top of the bin that detects a human presence and opens the lid. The image processing algorithm used

in the bin can detect and process the waste and carefully signal the bins to open the compartment where the waste belong. The dataset used for the model is mostly of all the

generic waste produced in the household. This grass-root segregation of waste will enable faster way to recycle the waste and save time and resources.

Another aspect of the present invention having waste will be segregated into biodegradable

and non-biodegradable such that organic waste, paper, cardboard are categorized as

biodegradable section whereas aluminum cans, plastic bags, shattered glass, plastic utensils and glass bottles are categorized as non-biodegradable waste. Machine learning model is

trained for the segregating the waste based on the training images collected in the dataset involving both the image of biodegradable and non-biodegradable images. Level of filling is

thrash-bin is monitored using ultrasonic sensors indicating levels in percentage of multiples of 10. Segregation is possible when waste is thrown one by one hence this system is

implemented at the level of thrash-bin itself.

Other aspect of the present invention comprising waste segregator has been successfully implemented for segregation of waste into biodegradable and non- biodegradable waste at

a domestic level.

One of the aspect of the present invention having noise level and embodiment, wherein it

can be eliminated from the sensor modules to increase the accuracy and efficiency of the system. It can segregate only one type of waste at a time since having different types of

wastes at once can create problems in effectively segregating. Thus, improvements can be made to segregate mixed type of waste by the use of buffer spaces.

Other aspect of the present invention involves two important modules namely automatic waste segregator and automatic waste monitoring system, where the automatic waste

segregator is utilized for classifying the trash thrown into the trash-bin such that trash is segregated properly into two compartments by tilting.

Another aspect of the present invention comprising waste monitoring system continuously monitors the level of trash in the two separate departments whose report is recorded to

avoid overflow.

One of the aspect of the present invention comprising overall system involves several sub modules namely image recognition module, monitoring module, data reporting module,

Raspberry pi 3, Raspberry Pi camera V2, GPS module, Servo motor for tilting, LinkIt One and

sensors such as ultrasonic, IR collision, temperature and humidity sensor.

Other aspect of the present invention comprising monitoring module is used for the detection of fill level in trash-bin along with temperature and humidity using sensors which

also monitors suspicious material thrown in bin thereby generates alert to authenticated persons.

Another aspect of the present invention comprising Data reporting module generates report

based on the data collected by the sensors which can be viewed from remote locations using website developed.

One of the aspect of the present invention comprising machine learning technique, in which it is able to segregate the trash accurately as it is trained by huge set of images stored in the

database. Every time a trash is thrown in the trash bin, its image is captured and sent for

classification through loT. It is then classified by machine learning technique based on which the servo motor fitted to the bin is tilted to dispose the trash into biodegradable and non

biodegradable waste.

These and other objects, features, advantages and alternative aspects of the present invention will become apparent to those skilled in the art from a consideration of the following detailed description taken in combination with the accompanying drawings.

It will be apparent to persons of skill in the art that various of the foregoing aspects and/or

objects, and various other aspects and/or objects disclosed herein, can be incorporated and/or achieved separately or combined in a single device, method, system, composition,

article of manufacture, and/or improvement thereof, thus obtaining the benefit of more

than one aspect and/or object, and that an embodiment may encompass none, one, or more than one but less than all of the aspects, objects, or features enumerated in the

foregoing summary or otherwise disclosed herein. The disclosure hereof extends to all such combinations. In addition to the illustrative aspects, embodiments, objects, and features

described above, further aspects, embodiments, objects, and features will become apparent by reference to the drawing figures and detailed description. Also disclosed herein are

various embodiments of related methods, devices, apparatus, compositions, systems,

articles of manufacture, and/or improvements thereof. The foregoing summary is intended to provide a brief introduction to the subject matter of this disclosure and does not in any

way limit or circumscribe the scope of the invention(s) disclosed herein, which scope is defined by the claims currently appended or as they may be amended, and as interpreted by

a skilled artisan in the light of the entire disclosure. !0

BRIEF DESCRIPTION OF DRAWINGS

The summary, as well as the following detailed description, is further understood when read in conjunction with the appended drawings. For the purpose of illustrating the invention,

there are shown in the drawing's exemplary embodiments of the invention; however, the

invention is not limited to the specific methods, compositions, and devices disclosed. In addition, the drawings are not necessarily drawn to scale. In the drawings:

The detailed description is set forth with reference to the accompanying drawings. The

drawings are provided for purposes of illustration only and merely depict example embodiments of the disclosure. The drawings are provided to facilitate understanding of the disclosure and shall not be deemed to limit the breadth, scope, or applicability of the disclosure. The use of the same reference numerals indicates similar, but not necessarily the same or identical components. However, different reference numerals may be used to identify similar components as well. Various embodiments may utilize elements or components other than those illustrated in the drawings, and some elements and/or components may not be present in various embodiments. The use of singular terminology to describe a component or element may, depending on the context, encompass a plural number of such components or elements and vice versa.

Figure 1:- The Architecture system of the present system.

Repeat use of reference characters in the present specification and drawings is intended to

represent the same or analogous features or elements of the present invention.

!0

DETAILED DESCRIPTION OF THE INVENTION

Embodiments, of the present disclosure, will now be described with reference to the accompanying drawings.

Embodiments are provided so as to thoroughly and fully convey the scope of the present

disclosure to the person skilled in the art. Numerous details are set forth, relating to specific

components, and methods, to provide a complete understanding of embodiments of the present disclosure. It will be apparent to the person skilled in the art that the details

provided in the embodiments should not be construed to limit the scope of the present disclosure. In some embodiments, well-known processes, well-known apparatus structures,

and well-known techniques are not described in detail.

The terminology used, in the present disclosure, is only for the purpose of explaining a

particular embodiment and such terminology shall not be considered to limit the scope of the present disclosure. As used in the present disclosure, the forms "a," "an," and "the" may

be intended to include the plural forms as well, unless the context clearly suggests otherwise. The terms "comprises," "comprising," "including," and "having," are open

ended transitional phrases and therefore specify the presence of stated features, integers,

steps, operations, elements, modules, units and/or components, but do not forbid the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. The particular order of steps disclosed in the method and process of the present disclosure is not to be construed as necessarily requiring

their performance as described or illustrated. It is also to be understood that additional or alternative steps may be employed.

The main embodiment of the present invention comprising camera, in which is installed at the top of the bin that detects a human presence and opens the lid. The image processing

algorithm used in the bin can detect and process the waste and carefully signal the bins to open the compartment where the waste belong. The dataset used for the model is mostly of

all the generic waste produced in the household. This grass-root segregation of waste will enable faster way to recycle the waste and save time and resources.

Another embodiment of the present invention the Raspberry Pi board , wherein Raspberry

Pi board is a series of single-board computers having a System On Chip (SoC). It has a multicore processor, GPU, ROM, 1/O Peripherals, DDR RAM memory, Ethernet port, USB

host and micro HDMI on it. The Raspberry Pi board is very efficient as it can help in various automation projects, smart agriculture and we will be using it in our system for smart

segregation of waste. We will be using the Raspberry Pi 4 board for the smart bin.

Other embodiment of the present invention comprising ultrasonic sensor, in which is to

detect any object nearing the dustbin. This will, in turn, open the lid of the bin and the trash can be discarded. We are planning to use the HC-SRO4 module which is quite streamlined.

One of the embodiment of the present invention having Raspberry Pi camera module

, wherein this Raspberry Pi camera module V2 is the apt camera module for this purpose of

waste segregation. It has a fixed focus lens on board with an 8 megapixel native resolution sensor-capable of 3280 x 2464 pixel static images. These images will be used as input for the

machine learning model which will determine the type of waste.

Another embodiment of the present invention comprising capacitive plates, wherein these

plates will be used for finding if the disposed waste is a wet waste or dry waste. This sensor will be connected to the collapsible flap, which in turn is controlled by a servo motor. These

plates measure the moisture by finding out the dielectric constant of the water, which is unique to every substance.

Other embodiment of the present invention having servo motors, wherein these motors are

small devices with the shaft attached and controlled by the Raspberry Pi board. It receives a certain amount of pulse, with which it turns clockwise or anticlockwise. It can turn from 0 to

180 degrees, as it has a gearbox and potentiometer, with which we can position the shaft.

One of the embodiment of the present invention having infrared sensors, in which these sensors emit infrared light, which is absorbed by the body to which is projected, and is later

received by the receiver. The amount of absorptivity is measured or calculated and can be used to segregate waste like plastic, which might be a challenge for the machine learning

model. This, however, is an alternative in case the plastic doesn't get identified and segregated in the apt bin.

Other embodiment of the present invention comprising temperature and humidity sensor

for measuring the temperature and humidity inside the bin. GPS module is fitted along with the system for providing current GPS location including longitude and latitude position of

the trash-bin such that waste collection is facilitated.

Another embodiment of the present invention comprising machine learning technique, in

which it is able to segregate the trash accurately as it is trained by huge set of images stored in the database. Every time a trash is thrown in the trash bin, its image is captured and sent

for classification through loT. It is then classified by machine learning technique based on which the servo motor fitted to the bin is tilted to dispose the trash into biodegradable and non-biodegradable waste.

Other embodiment of the present invention comprising monitoring of trash level is done

using LinkIt One which is operated using sensors usable immediately using its Grove Shied. IR sensor in it is able to detect the distance of trash from the bin lid. HC-SRO4 is the

ultrasonic sensor utilized for measuring the object distance for monitoring the trash level in

the bin. It alerts even if the trash is not properly thrown inside.

The architecture of the present invention comprising when trash is brought near the lid of the smart bin, an ultrasonic sensor detects the trash and opens the lid so that it can be

placed on the first collapsible flap below the lid. The user is only expected to place the trash on the first collapsible flap of the smart bin, all segregation is taken care of by the bin. No

other user interaction is necessary. The trash is then segregated into biodegradable or non

biodegradable trash with the help of the Raspberry Pi camera module, infrared sensor, and moisture sensor. This segregation is done using object detection and convolutional neural

network algorithms. To further increase the accuracy of the classification, moisture sensor or capacitive plates are used to distinguish between wet and dry trash. When the

classification is done, a pulse is then sent to the servo motors which control the first collapsible flap. Depending on the pulse, the first collapsible flap tilts clockwise or

anticlockwise accordingly so that the trash falls into its correct category. If the trash is classified as biodegradable there is no more classification and segregation is complete. On

the other hand, if the trash is classified as non- biodegradable, it then falls onto the second collapsible flap. This trash on the second collapsible flap is then further classified into landfill

or recyclable trash. This is done by using object detection on the non-biodegradable trash. When the classification is done, a pulse is sent to the servo motors controlling the second

collapsible flap. Again depending on the pulse, the servo motors tilt the flap clockwise or

anticlockwise. The trash then falls into its rightful category and then segregation is complete.

The Wi-Fi is connected to the monitoring system such that data is published every 5 minutes

to the AWS MQTT which lessens the amount of data unchanged in user records.

The present invention consists of machine learning and other controlling server based by

AWS loT core is used for interacting with loT device. PHP is utilized for along with HTML5 for developing a web application in order to view the interpreted data. Data storage is done

using MYSQL database.

In the following detailed description section, the specific embodiments of the present

techniques are described in connection with preferred embodiments. However, to the extent that the following description is specific to a particular embodiment or a particular

use of the present techniques, this is intended to be for exemplary purposes only and simply provides a concise description of the exemplary embodiments. Moreover, to the extent that

a particular feature or aspect of the present systems and methods are described in connection with a particular embodiment or implementation, such features and/or aspects

may similarly be included or used in connection with other embodiments or implementations described herein or otherwise within the scope of the invention claimed in

this or related applications. Accordingly, the invention is not limited to the specific

embodiments described below, but rather, it includes all alternatives, modifications, and equivalents falling within the true scope of the appended claims.

!0

Throughout this specification the word "comprises", or variations such as "comprises" or "comprising", will be understood to imply the inclusion of a stated element, step, or group

of elements, steps, but not the exclusion of any other element, step, or group of elements, or steps.

While considerable emphasis has been placed herein on the components and component

parts of the preferred embodiments, it will be appreciated that many embodiments can be

made and that many changes can be made in the preferred embodiments without departing from the principles of the disclosure. These and other changes in the preferred embodiment

as well as other embodiments of the disclosure will be apparent to those skilled in the art from the disclosure herein, whereby it is to be distinctly understood that the foregoing

descriptive matter is to be interpreted merely as illustrative of the disclosure and not as a limitation.

Modifications to embodiments of the invention described in the foregoing are possible without departing from the scope of the invention as defined by the accompanying claims. Expressions such as "including", "comprising", "incorporating", "consisting of", "have", "is" used to describe and claim the present invention are intended to be construed in a non exclusive manner, namely allowing for items, components or elements not explicitly described also to be present. Reference to the singular is also to be construed to relate to the plural. Numerals included within parentheses in the accompanying claims are intended to assist understanding of the claims and should not be construed in any way to limit subject matter claimed by these claims.

Although embodiments have been described in language specific to structural features and/or methodological acts, it is to be understood that the disclosure is not necessarily limited to the specific features or acts described. Rather, the specific features and acts are disclosed as illustrative forms of implementing the embodiments. Conditional language, such as, among others, "can," "could," "might," or "may," unless specifically stated otherwise, or otherwise understood within the context as used, is generally intended to convey that certain embodiments could include, while other embodiments do not include, certain features, elements, and/or steps. Thus, such conditional language is not generally intended to imply that features, elements, and/or steps are in any way required for one or more embodiments or that one or more embodiments necessarily include logic for deciding, with or without user input or prompting, whether these features, elements, and/or steps are included or are to be performed in any particular embodiment.

While the present disclosure has been described with respect to a limited number of embodiments, those skilled in the art, having benefit of this disclosure, will appreciate that other embodiments may be devised which do not depart from the scope of the disclosure as described herein. Accordingly, the scope of the present disclosure should be limited only by the attached claims.

EDITORIAL NOTE

2021101744

THERE ARE THREE PAGES OF CLAIMS ONLY

Claims

CLAIMS,

We Claims,

[CLAIM 1] A waste segregation method using machine learning technique comprising sensors, camera, online server dashboard, loT based connected camera,

motors, Raspberry Pi camera module, Raspberry Pi Board and others

components wherein process comprising of :

a) a camera is installed at the top of the bin that detects a human presence and opens the lid. The image processing algorithm used in

the bin can detect and process the waste and carefully signal the bins to open the compartment where the waste belong. The dataset used

for the model is mostly of all the generic waste produced in the household. This grass-root segregation of waste will enable faster

way to recycle the waste and save time and resources;

b) involves several sub modules namely image recognition module, monitoring module, data reporting module, Raspberry pi 3, Raspberry Pi camera V2, GPS module, Servo motor for tilting, LinkIt One and sensors such as ultrasonic, IR collision, temperature and

humidity sensor.
[CLAIM 2] The waste segregation method using machine learning technique as claimed in claim 1, wherein method flow using machine learning technique, in which

it is able to segregate the trash accurately as it is trained by huge set of images stored in the database. Every time a trash is thrown in the trash bin,

its image is captured and sent for classification through loT. It is then

classified by machine learning technique based on which the servo motor fitted to the bin is tilted to dispose the trash into biodegradable and non

biodegradable waste.
[CLAIM 3] The waste segregation method using machine learning technique as claimed in claim 1, wherein involves two important modules namely automatic waste segregator and automatic waste monitoring system, where the automatic waste segregator is utilized for classifying the trash thrown into the trash-bin such that trash is segregated properly into two compartments by tilting.
[CLAIM 4] The waste segregation method using machine learning technique as claimed in claim 1, wherein Wi-Fi is connected to the monitoring system such that

data is published every 5 minutes to the AWS MQTT which lessens the amount of data unchanged in user records.
[CLAIM 5] The waste segregation method using machine learning technique as claimed

in claim 1, wherein the architecture of the present invention comprising when trash is brought near the lid of the smart bin, an ultrasonic sensor

detects the trash and opens the lid so that it can be placed on the first

collapsible flap below the lid;

a) the user is only expected to place the trash on the first collapsible flap of the smart bin, all segregation is taken care of by the bin. No

other user interaction is necessary. The trash is then segregated into biodegradable or non-biodegradable trash with the help of the

Raspberry Pi camera module, infrared sensor, and moisture sensor. This segregation is done using object detection and convolutional

neural network algorithms;

b) to further increase the accuracy of the classification, moisture sensor

or capacitive plates are used to distinguish between wet and dry trash. When the classification is done, a pulse is then sent to the

servo motors which control the first collapsible flap; c) depending on the pulse, the first collapsible flap tilts clockwise or

anticlockwise accordingly so that the trash falls into its correct category. If the trash is classified as biodegradable there is no more classification and segregation is complete; d) on the other hand, if the trash is classified as non- biodegradable, it then falls onto the second collapsible flap. This trash on the second collapsible flap is then further classified into landfill or recyclable trash. This is done by using object detection on the non biodegradable trash; e) when the classification is done, a pulse is sent to the servo motors controlling the second collapsible flap. Again depending on the pulse, the servo motors tilt the flap clockwise or anticlockwise. The trash then falls into its rightful category and then segregation is complete.

Dated 05th April 2021.

APPLICANTS NAME:- Dr. Anurag Shrivastava ; Ashutosh kumar singh ; Dr. Sushma Jaiswal ; Dr. Jay 06 Apr 2021

Kumar Jain ; Amit kumar Sharma ; Deepthi Bolukonda ; Dr. Kamasani Chandrasekhar Reddy ; Dr Pawan Kumar Chaurasia ; Md Ilyas ; Dr. Rajeev Raghuvanshi Ashwin Verma ; Tulala Rajasanthosh Kumar

Sheet 1of 1 2021101744

Figure 1

Dated 05th April 2021.