1
Machine Learning: Virtual Assistant for Personalized Physical
Activity and Diet Meal Plan for Weight Loss
and Muscle Growth
In Partial Fulfillment of The Requirements for the course
FUNDAMENTALS OF RESEARCH
By:
Ahon, Ernieco Jay
Esguerra, Ulyssa Marie T.
Lorezo, Kent Charlies
2021
2
Dedication
This study is dedicated to our beloved families. A special feeling of gratitude to our loving
parents who have been our source of strength and supported us physically, morally, emotionally,
and financially all throughout the completion of this paper.
To our siblings, friends and classmates, who also gave a hand and shared in this study their
words of guidance and encouragement. Time and effort are greatly appreciated.
Above all, we devote this study to the All-Powerful God. Thank you for protecting and
encouraging to finish this research. We give you all of these.
Acknowledgements
The completion of this paper is a result of collaborative help and support of various people
whose names may not be all enumerated. Their contributions are sincerely appreciated and greatly
acknowledge. However, the researchers would like to express their deep appreciation and
indebtedness particularly to the following:
Professor Jeffrey Aceron, who is our professor during this course Fundamentals of
Research, thank you for your guidance and constant supervision as well as for imparting your
knowledge and expertise in this study.
To all classmates, relatives and closest friends who in one way or another express their
support, either morally, financially, and physically. Thank you.
Above all, to the Great Almighty, the author of knowledge and wisdom, for His countless
love.
3
Abstract
Poor diets and physical inactivity may result in lower immunity, greater disease
susceptibility, physical and mental development impairment and reduced productivity. In the
everyday activities of people including managerial schedules, appointments and wake-up calls,
virtual assistants are involved. They have a conversational service and make their daily life
manageable for 24 hours a day. Many renowned businesses have introduced virtual assistants that
handle their everyday routine activities with this new trend. The advances in machine learning
technology provide enormous opportunities to create virtual assistants that can provide customized
physical activity and dietary meals intended for weight loss and muscle growth. This research will
provide greater understanding by addressing the effectiveness and benefits of these virtual
assistants using machine learning techniques and show the interaction between people and
machinery within the context of a health nutrition recommendation. The result may be useful to
inform future researcher of virtual assistants and promote the personalization of user’s health care.
Keywords: Machine learning, virtual assistants, physical activity
4
CONTENTS
1. INTRODUCTION…………………………………………………………………………………………………. 5
1.1 Background of the Study……………………………………………………………………………… 6
1.2 Objective of the Study ………………………………………………………………………………… 7
1.3 Statement of the Problem…………………………………………………………………………….. 8
1.4 Significance of the Study…………………………………………………………………………….. 8
2. REVIEW AND LITERATURE………………………………………………………………………………8
2.1 Historical Backgroud………………………………………………………………………………….. 8
2.2 Logistics…………………………………………………………………………………………………… 10
2.3 Issues and Challenges….…………………………………………………………………………… 12
2.4 Actions…………………………………………………………………………………………………….. 16
2.5 Discussions and Conclusions………………………………………………………………………. 22
2.6 References………………………………………………………………………………………………. 22
2.7 Appendices……………………………………………………………………………………………….. 22
5
CHAPTER ONE
1. Introduction
A new generation of attentive customized systems called virtual assistants allowed for the
confluence of many new technologies. Virtual Assistants help users effectively complete their
regular routine assignments. Many virtual assistants use artificial intelligence to provide users with
customized assistance in the form of calendar management, smart environment monitoring,
navigation, appointment making, wake-up calls, and many other items. Many apps already have
their own integrated virtual assistants from various realms, such as televisions, mobile devices,
cars, and the Internet of Things. Humans behind the scenes are vital for helping virtual assistants
to learn how to interact with people as if they were real people themselves. At the moment, one of
the main things holding adoption of virtual assistants back is the public’s discomfort with
communicating machines using their own voice.
The virtual assistant is also known as a chatbot, dialogue manager, virtual agent, interactive
assistant, or conversational agent. Many well-known companies including Apple (Siri), Google
(Assistant), Samsung (Bixby) and Amazon (Alexa) introduced their own virtual assistants. Their
accuracy, speed, and contextual abilities are all because of Machine Learning algorithms and
servers owned by their developing companies. The main distinction exists in their protocols and
data protection intricacies, and they all function in a similar way. When a user makes a request,
the request is instantly packed and submitted for a response to the server of their respective
businesses, i.e. why internet access is one of the fundamental criteria for proper functioning of
Virtual Assistants. After the package is sent to the server the words and tone of your request are
analyzed by a set of algorithms, which are then matched with a command that it thinks you asked.
Not all the information is processed with the help of the server, only the complicated ones.
Over the past two decades, developments in natural language processing and deep learning
have contributed to the development of more sophisticated artificial intelligence technologies,
many of which employ conversational functions. These virtual assistants provide an interactive
user interface – text, speech, or both, that have the ability to understand requests, handle complex
tasks, and generate an appropriate response using the machine learning model.
6
The field of research into virtual health assistants is expanding rapidly. In 2020 alone,
virtual assistants have been tested for pain-self management amongst adults with chronic pain,
promoting fertility awareness among child-bearing women, for life skill promotion amongst
adolescents, and to promote physical activity amongst office workers. Other recently tested virtual
assistants include Tess to support adolescents with pre-diabetes and Woebot to support adolescents
with depression and anxiety. There are fewer examples of virtual assistants with a focus on
physical activity and diet. Bickmore et al. tested a virtual assistant for improving physical activity
and fruit and vegetable intake, as well as physical activity in older adults]. Reflection Companian
was used to promote physical activity amongst adults based on FitBit data. All of these studies
were pilot in nature, often of short duration (2–12 weeks) and small sample size. While all showed
at least some improved outcomes for those exposed to the virtual assistant, most had limited
process evaluation, if any.
1.1. Background of the Study
Virtual assistants focused on machine learning have also enabled the treatment of
unhealthy lifestyles, in the health care sector. Our current times see the advent of an epidemic of
lifestyle-related behavioral problems. In 2013, the Word Health Organization reported that obesity,
worldwide, has more than doubled since 1980. It found that 1.4 billion adults were overweight, of
which 500 million were obese, and 42 million children under the age of five were overweight;
overall more than 10% of the world’s adult population was obese Overweight and obesity are risk
factors for a number of diseases, such as cardiovascular troubles, diabetes, musculoskeletal
disorders, some cancers and can be prevented by diet and exercise. Moreover, unhealthy lifestyles
lead to increased premature mortality and are a risk factor for sustaining non-communicable
diseases (NCDs) such as cardiovascular diseases, cancers, chronic respiratory diseases, and
diabetes. NCDs caused 63% of all deaths that occurred globally in 2008. There are four behavioral
factors that have a significant influence on the prevention of NDCs: healthy nutrition, not
smoking, maintaining a healthy body weight, and sufficient physical activity.
Insufficient physical activity is one of the leading risk factors for the major NCDs and not
meeting the recommended level of physical activity is associated with approximately 5.3 million
deaths that occurred globally in symptom. A high amount of sedentary time without sufficient
daily physical activity leads to a higher rate of all-cause mortality. Besides the increased risk of
premature mortality in the long term, the short-term quality of life, being able to work, and social
participation is also threatened by insufficient physical activity.
Despite the overwhelming benefits of healthy food and physical activity, it is enormously
difficult to make and maintain lifestyle improvements. Health practitioners, such as dietitians and
exercise physiologists or physiotherapists, may offer specialist training to help people improve
their lifestyle. However, health systems’ finite budgets typically limit access to such services to
specific patient populations, such as those with established chronic disease. Consequently, many
people with unfavorable lifestyle patterns, who in time will go on to develop chronic disease, do
not have access to health professional support to help them modify their lifestyle and prevent
disease.
Fortunately, these risks are eliminated when this sedentary time is compensated for with
sufficient physical activity of moderate intensity. With the help of a machine learning, we can
