Abstract

The Food Waste Management App is designed to connect food donors with NGOs in need,
facilitating the efficient donation and distribution of surplus food. The app focuses on Database
management Systems (DBMS) domain, integrating web-based technologies for efficient handling
of NGO’s, food donor’s and admin organization.

Food waste is a significant global issue with serious economic, environmental, and social
consequences. A food waste management system is essential to addressing these challenges
effectively. Large amounts of food go to waste unnecessarily, and proper management can prevent
excessive disposal. Additionally, food waste management plays a crucial role in alleviating
hunger, as millions face food insecurity while edible food is discarded. By creating a structured
donation and redistribution system, surplus food can be efficiently redirected to those in need.

The Food Waste Management App is developed using React for frontend, Node.js for
backend, MongoDB for Database and Firebase for real-time data synchronization. This
ensures smooth working and secure connections between the blocks of Waste food managing
chain. Also this helps in real time notifications and on time delivery of food.

1
 List of Figures

Figure 1.1 Title of the figure 1

Figure 2.1 ABC technique used by XYZ et al. [5] 4

Figure 3.1 Classification of domain techniques 6

Figure 3.2 Existing system architecture used for Content-based Systems 8

Figure 3.3 Proposed system architecture (if any) 9

2
 List of Tables

Table 1.1 Title of the table 1

Table 2.1 Summary of literature survey 5

Table 3.1 Sample Dataset Used for Experiment 11

Table 3.2 Hardware details 11

Table 3.3 Software details 11

3
 Chapter 1
(18pt Font, Times New Roman, Centre)

Introduction

(18pt Font,
. Times New Roman, Centre)

1.1 Fundamentals (12pt Font, Times New Roman, Bold)

This is the first Section Heading. The text in each section will be of the following format (Times
New Roman 12, Justified, Line spacing 1.5). The same format is to be followed for all sections
and subsections.

Page number must be in the footer of the page (starting from Introduction topic to references) and
aligned to the centre of the page. The figures are centre aligned.

Fig 1.1: Title of the figure

The Figure 1.1 shows the method to add figure in the text. The description about the figure is to be
written in one or two lines or more as per the requirements.

1.2 Objectives (12pt Font, Times New Roman, Bold)

The Table 1.1 shows the method to add table in the text. The description about the figure is to be
written in one or two lines or more as per the requirements. The tables are centre aligned.

4
 Table 1.1: Title of the table
Attribute 1 Attribute 2 Attribute 3
Value 1 Value 1 Value 1
Value 2 Value 2 Value 2

The objective of Food Waste Management App is as follows:

1. To develop a digital platform that connects event organizers, restaurants, and caterers with
NGOs to facilitate the collection and redistribution of excess food to underprivileged
communities.
2. To streamline the logistics of food donation by integrating real-time tracking, automated
pickup requests, and communication channels between donors and NGOs.
3. To promote awareness and engagement by providing data-driven insights, impact reports,
and incentives for individuals and businesses to participate in reducing food waste.

1.3 Scope
The future of food waste management apps is highly promising, with advancements in real-time
tracking, enhanced security, and seamless integration with local waste management systems.
Future versions can feature an expanded database to analyze food waste patterns, helping
businesses and households optimize consumption. Stronger firewall protection and encryption will
ensure secure transactions for food donations and partnerships. Real-time collaboration with waste
authorities can streamline food redistribution, while integration with smart appliances can
automate tracking and suggest better consumption habits. Additionally, partnerships with
governments and corporations can drive widespread adoption, promoting sustainability efforts on a
larger scale. By incorporating these innovations, food waste management apps will significantly
reduce global food waste, support sustainable living, and improve food security worldwide.

1.4 Outline
The food waste management app aims to address food wastage by enabling real-time tracking,
donations, and recycling. Its main objectives are to reduce waste, promote sustainability, and
support food redistribution. Target users include households, restaurants, grocery stores, NGOs,
and waste authorities. Key features include expiry alerts, donation facilitation, and waste
management tools. The app ensures security through a robust database, firewall protection, and

5
encrypted transactions. Users can efficiently track, donate, and recycle surplus food.

Chapter 2
Literature Survey

In this chapter the relevant techniques in literature are reviewed. It describes various techniques
used in the work. Identify the current literature on related domain problems. Identify the
techniques that have been developed and present the various advantages and limitations of these
methods used extensively in literature.

Write the advantages and disadvantages of this method. The summary of the literature presented at
the end of this Chapter.

A literature review is an objective, critical summary of published research literature relevant to a

topic under consideration for research. Its purpose is to create familiarity with current thinking and
research on a particular topic, and may justify future research into a previously overlooked or
understudied area.

A typical literature review consists of the following components:

1. Introduction
2. Main Body
3. Conclusion
4. References

2.1 Technique Category One

The techniques in this category are adapted to the individual needs, interests and preferences of
user or society. They are tools for suggesting items to users in this domain. Various techniques in
this category are listed here. These techniques have various advantages and are used extensively in
literature.

2.1.1 Technique One

6
This technique is used by Author One [2] for XYZ purpose. It presents the state of the Art and
discusses the main issues related to this domain problem. It discusses various techniques starting
from simple techniques for representing structured data, to more complex techniques coming from
the unstructured data. Write the advantages and disadvantages of this method. This work is divided
into three parts. Discuss each part here.

2.1.2 Technique Two

It was developed by Author Two et al. [3]. It presents the survey and experiments the two domain
related techniques. These techniques show the complementary advantages and disadvantages. It
compares the various techniques and shows which techniques are better based on the evaluation
metrics. This fact has provided incentive for research in this domain for improved performance. It
proposes various hybrid approaches that give better results.

2.2 Technique Category Two

The techniques in this category are adapted to the individual needs, interests and preferences of the
user or society. They are tools for suggesting items to users in this domain. Various techniques in
this category are listed here. These techniques have various advantages. Write the advantages and
disadvantages of this method.

2.2.1 Technique Three

Author Three et al. [4] applied similar techniques on different datasets. It introduces the flow of
the domain system and the specific realization procedures of data input, data preprocessing, and
other related steps. Results show that this technique in this domain has shown great performance.

2.2.2 Hybrid Approach One

Author Four has presented a hybrid approach [5] for ABC domain technique for XYZ purposes.
The architecture is shown in Figure 2.1 It explores a new hybrid approach for solving the problem
of finding the solutions based on user inputs. The proposed technique provides improvements in
addressing two major challenges of this domain system: LMN and OPQ.

7
 Fig. 2.1 ABC technique used by XYZ et al. [5]

The evaluation of the system shows superiority of the solution compared to stand-alone user-based
ABC techniques. It shows that the hybrid approach improves the various problems.

2.3 Literature Summary

A literature review is an objective, critical summary of published research literature relevant to a
topic under consideration for research. The summary is presented here.

Table 2.1 Summary of literature survey

SN Paper Advantages and Disadvantages
1. Author One [2] Advantages: Learning a profile is easy.
Quality improves over time. Consider implicit feedback.
Disadvantages: Does not completely overcome the problem of abc and
xyz.
2. Author Two et Advantages: The web site based on this has shown great performance.
al. [3] Disadvantages: It does not recommend quality content to the users. Does
not consider the new user ABC problem. Not very efficient in terms of
performance.
3. Author Three et Advantages: The survey shows combine techniques for improved
al. [4] performance. It improves the user preferences for suggesting items to
users.

8
4. Author Four [5] Advantages: It solves the problem of finding xyz. It improves lmn
problem.
Disadvantage: It does not consider the abc features which would give
better results and solve the abc problem.

9
 Chapter 3
Proposed System

3.1 Overview
The system overview is presented in this Section. The classification of various techniques the
domain is given in Figure 3.1

Fig. 3.1 Classification of domain techniques

This system helps users to find information by providing them with personalized suggestions.
Based on the above problems of researchers, recommendation techniques will have great influence
in all aspects of our life.

Personalized Recommendation: The personalization is concerned with adapting to the individual

needs, interests and preferences of each user. It includes recommending, filtering and predicting
techniques. From a business perspective, it is viewed as part of Customer Relationship
Management (CRM) . These techniques are content based recommendation system, collaborative
filtering and knowledge based recommendation.

10
Non personalized recommendation: Non-personalized recommender systems are the simplest
type of recommender systems. As the name suggests, these types of recommender systems do not
take into account the personal preferences of the users. The recommendations produced by these
systems are identical for each customer. For example, if we go to amazon.com as an anonymous
user it shows items that are currently viewed by other members. These systems recommend items
to consumers based on what other consumers have said about the items or rated them on an
average. Non-personalized recommender systems mainly use two types of algorithms: Aggregated
opinion recommender and Basic product association recommender.

Aggregated opinion recommender: It displays the recommendations with a score which is an

average of the ratings given to that specific thing by other customers. This score is basically a
measure of how good the restaurant is. Its scores generally range from 0 to 5. The average score
calculated for most of such guides is as given in Equation 1.

Score = round (MEAN (ratings)*10) or simply as Score =MEAN (ratings*10) (3.1)

Averages are useful for an overall sense of what the population feels. However these averages lack
context during recommendations. In above examples one bad rating or review has a lot of weight
and can pull down an otherwise excellent rating. To tackle this issue, some websites tallied the
percentage of people who rated a particular item “good” or “bad. This leads us to the concept of
product association recommender.

Content Based Recommender Systems: Systems implementing a content based recommendation

approach analyze a set of documents and/or descriptions of items previously rated by a user, and
build a model or profile of user interests based on the features of the objects rated by that user. The
profile is a structured representation of user interests, adopted to recommend new interesting
items. The recommendation process basically consists in matching up the attributes of the user
profile against the attributes of a content object. The result is a relevance judgment that represents
the user’s level of interest in that object. If a profile accurately reflects user preferences, it is of
tremendous advantage for the effectiveness of an information access process. For instance, it could
be used to filter search results by deciding whether a user is interested in a specific Web page or

11
not and, in the negative case, preventing it from being displayed.

3.1.1 Existing System Architecture

The Content Based Information Filtering (IF) systems need proper techniques for representing the
items and producing the user profile, and some strategies for comparing the user profile with the
item representation.

Fig. 3.2 Existing system architecture used for Content Based Systems [2]

The high level architecture of a content based recommender system is depicted in Figure 3.2. The
recommendation process is performed in three steps, each of which is handled by a separate
component:
● Content Analyzer: When information has no structure (e.g. text), some kind of pre-
processing step is needed to extract structured relevant information. The main responsibility
of the component is to represent the content of items (e.g. documents, Web pages, news,
product descriptions, etc.) coming from information sources in a form suitable for the next
processing steps.
● Profile Learner: This module collects data representative of the user preferences and tries

12
 to generalize this data, in order to construct the user profile. Usually, the generalization
strategy is realized through machine learning techniques, which are able to infer a model
of user interests starting from items liked or disliked in the past. For instance, the profile
learner of a Web page recommender can implement a relevance feedback method in which
the learning technique combines vectors of positive and negative examples into a
prototype vector representing the user profile.
● Filtering Component: This module exploits the user profile to suggest relevant items by
matching the profile representation against that of items to be recommended. The result is
a binary or continuous relevance judgment (computed using some similarity metrics), the
latter case resulting in a ranked list of potentially interesting items.

3.1.2 Proposed System Architecture

The previous sections discussed the strengths and weaknesses of existing system. In order to
achieve better domain results, researchers combined both techniques to build Hybrid domain
systems, which seek to inherit vantages and eliminate disadvantages.

In general, hybrid recommenders are systems that combine multiple recommendation techniques
together to achieve a synergy between them. Although there exist a number of recommendation
approaches that are practical to merge (i.e. Collaborative, Content-based, Demographic and
Knowledge-based Recommender), our work will mainly focus on the combination of CF and CBF
techniques. The proposed architecture is shown in Figure 3.3

Fig. 3.3 Proposed system architecture (if any)

13
Depending on the domain and data characteristics, different types of combinations might produce
dissimilar outputs. The following list describes several hybridization techniques that come into
consideration to merge CF and CBF recommenders
● Weighted hybrid: This hybrid combines scores from each component using linear formula.
Therefore, components must be able to produce its recommendation score which can be
linearly combinable. Also, the components have to be consistent relative accuracy across the
product space and to perform uniformly.
● Switching hybrid: The issue of this hybrid is selecting one recommender among candidates.
This selection is made according to the situation it is experiencing. The criterion for the
selection like confidence value or external criteria should exist and the components might
have different performance with different situations.
● Mixed hybrid: This is a hybrid which is based on the merging and presentation of multiple
ranked lists into one. Each component of this hybrid should be able to produce
recommendation lists with ranks and the core algorithm of the mixed hybrid merges them into
a single ranked list.
● Feature combination hybrid: There exist two very different recommendation components
for this hybrid, contributing and actual recommender. The actual recommender works with
data modified by the contributing one. The contributing one injects features of one source to
the source of the other component.
● Feature augmentation hybrid: This is similar to the feature combination hybrids but
different in that the contributor generates new features. It is more flexible and adds a smaller
dimension than the feature combination method.
● Cascade hybrid: This one is a tie breaker. The secondary recommender is just a tie breaker
and does refinements.
● Meta-level hybrid: For this one, contributing and actual recommenders exist but the former
one completely replaces the data for the latter one, not just part of i

Hybrid models discussed two techniques that have merged in four different ways. Write about it.

3.2 Implementation Details

The implementation detail is given in this section.

14
3.2.1 Technique ABC
Explain the techniques to be implemented with examples. The procedure in detail is given in this
Section. An algorithm shouldn't have computer code. Instead, the algorithm should be written in
such a way that it can be used in similar programming languages. Algorithms are a way to
communicate about your problem/solution with other people. Also it is a possible way to solve a
given problem.

3.2.2 Use Case Diagram / Activity Diagram

Explain the diagram if any. Explain each block in at least one line with possible examples. The
procedure is given as follows. Give steps.

3.2.3 Sample Dataset Used

An experiment is conducted in order to identify the input/output behavior of the system. Identify
inputs. Specify the sample inputs that would be used in the experiments. The sample dataset used
in the experiment are identified and given in Table 3.1

Table 3.1 Sample Dataset Used for Experiment

Dataset Users Items Interactions Type

Filmtipset 81,282 64,747 19,812,490 Information

Last.fm 10, 681 359, 349 160, 154 3, 778, 552, 887 Personalized radio

Movielens 71, 567 10,681 10, 000, 054 Information

3.2.4 Hardware and Software Specifications

The experiment setup is carried out on a computer system which has the different hardware and
software specifications as given in Table 3.2 and Table 3.3 respectively.

15
 Table 3.2 Hardware details

Processor 2 GHz Intel

HDD 180 GB

RAM 2 GB

Table 3.3 Software details

Operating System Windows XP Professional With Service pack 2

Programming Language JDK 1.8

Database Oracle 9

3.3 Evaluation Metrics

The quality of a domain system can be evaluated by comparing recommendations to a test set of
known user ratings. These systems are typically measured using precision and recall [6].

Precision: A measure of exactness, determines the fraction of relevant items retrieved out of all
items retrieved. Precision (P) It is given in Equation 3.1. It is the proportion of recommended
movies that are actually good.

(3.1)
Recall: a measure of completeness, determines the fraction of relevant items retrieved out of all
relevant items. Recall (R) is given in Equation 3.2. It is the proportion of all good movies
recommended.

(3.2)

16
 Chapter 4

Applications

There are various applications of this domain system. The application is listed here.

4.1 Broadcast News Audio

Broadcasting news is considered as an important and interesting application field of content based
audio classification systems. Since this system is used for segmenting audio streams into
expressive regions, it has received special attention. For detection of particular events or file audio
classification is used. The aim of using audio classification in news broadcasting is classifying
recorded sound into pure speech and the other specified classes. So, the news can be smoothly
broadcasted without any interruption.

4.2 Information Retrieval

The semantic retrieval of information is one of the applications in this field. The content based
information retrieval has been developed using standards e.g. MPEG-7 [9]. For retrieving the data
from the database, it is necessary to classify the data into similar types. So, it can be easily
retrieved by the user. It is an easy task for users who might not have the knowledge about how the
information is stored in the database.

4.3 Video Indexing

The audio classification system can be used in video indexing. The video is classified into
different classes containing distinct features or properties with the help of a classifier. So, the user
can access the particular video by using the index or class of that video.

4.4 Content Analysis

Content based classification systems can be used for analysis of audio/video content. Audio
classification is also used in speaker identification for analysis of content [10]. In video/audio
content, the number of speakers is undefined. So, in order to identify the particular speaker in the
given content audio classification is used. Also it is applied to analyze the content whether noise is
present in content.

17
4.5 Dubbing of audio
The content based audio classification system can be used in dubbing of audio. While dubbing it is
necessary to classify it, because an audio contains different types of sound. So in order to identify
the sound of a particular class, audio classification is used.

4.6 Multimedia Content Retrieval

The classification is a widely used concept for multimedia retrieval. Multimedia data consists of
images, texts, audios, and videos. It is necessary to arrange these classes in the form of clusters of
the same type. So, the user can easily retrieve the multimedia data according to his/her choice. The
multimedia data has been stored in the database, so the user can easily access that data.

4.7 Searching for Particular Sound

Searching for particular sound is the most commonly used application of content based audio
classification. The audio data is classified into different classes or sound. So, the user can easily
search for a particular sound or class. It can also be used to identify different sounds like barking
of dogs, laughing etc.

18
 Chapter 5

Summary

In this report, the study of different domain techniques is presented. The different techniques such
as ABC, XYZ, content based, and collaborative filtering is explained with examples. The different
hybrid approaches are also described. The comparative study of various techniques mentioned
above is presented in this report. The hybrid approach is proposed with xyz modification. The
performance measures like precision and recall are described in this report. The different standard
datasets or variable inputs are defined that may be used in experiment for this domain system. The
two datasets identified for experiments are CDEF and JKLM. The applications of this domain are
identified and presented.

19
 References

(The following text shall be 12pt Font, Times New Roman, Justified, 1.5 line spacing)
(All papers/theses/articles/letters/reports/urls used for writing project synopsis has to be mentioned in the
Reference Section (here) and must to be cited in the report text wherever referred. For more details refer
the url https://www.ieee.org/documents/ieeecitationref.pdf )
[1] Pamela Fry (Thompson Rivers University). Literature Review Template [Online]. Available
FTP: https://www.tru.ca/__shared/assets/Literature_Review_Template30564.pdf

[2] J. K. Author, “Name of paper,” Abbrev. Title of Periodical, vol. x, no. x, pp. xxx-xxx, Abbrev.
Month, year.

[3] R. E. Kalman, “New results in linear filtering and prediction theory,” J. Basic Eng., ser. D, vol.
83, pp. 95-108, Mar. 1961.

[4] A. B. Author. (year). Title (edition) [Type of medium]. Available FTP: Directory: File:

[5] R. J. Vidmar. (1994). On the use of atmospheric plasmas as electromagnetic reflectors

[Online]. Available FTP: atmnext.usc.edu Directory: pub/etext/1994 File: atmosplasma.txt.

[6] A. B. Author, “Title of paper,” in Unabbreviated Name of Conf., City of Conf., Abbrev. State
(if given), year, pp. xxx-xxx.

20
 Acknowledgement
(The following text shall be 12pt Font, Times New Roman, Justified, 1.5 line spacing)

We would like to extend our heartfelt thanks to our principal, Dr. Joshi sir , for granting us the
opportunity to work on this project and for fostering a learning atmosphere that promotes
academic excellence. Their constant support and leadership have been truly inspiring.

We are also grateful to our Head of Department (HOD), Dr. Monika Mam, for providing the
necessary resources and a conducive environment for completing this project. Their motivation
and insightful suggestions have played a crucial role in shaping the direction of our research.

We would like to express our sincere gratitude to our Guide, Prof. Anup vange sir, for his
invaluable support, guidance, and encouragement throughout this project. His expert advice and
constructive feedback have helped us enhance our understanding and improve our work
significantly.

Lastly, we would like to express our appreciation to our friends, classmates, and family for their
unwavering support, encouragement, and motivation. Their help and positive reinforcement have
been instrumental in the successful completion of this project.

Jidnyasa Kalaskar, 620

Yash Pandey,
Atharva Naik,
Mrunal Deshpande,

21