See discussions, stats, and author profiles for this publication at: https://www.researchgate.

net/publication/378520291

Leveraging Machine Learning for Career Prediction and Resume Analysis in

Career Assist

Article · February 2024

CITATIONS READS

0 349

6 authors, including:

Nupur Soni Mohit Singh

Babu Banarasi Das University Babu Banarasi Das University
27 PUBLICATIONS 61 CITATIONS 2 PUBLICATIONS 0 CITATIONS

SEE PROFILE SEE PROFILE

Shadab Ansari Ahmad Tasnim Siddiqui

Babu Banarasi Das University Sandip University
2 PUBLICATIONS 0 CITATIONS 52 PUBLICATIONS 192 CITATIONS

SEE PROFILE SEE PROFILE

All content following this page was uploaded by Syed Anas Ansar on 18 July 2024.

The user has requested enhancement of the downloaded file.

 2023 10th IEEE Uttar Pradesh Section International Conference on Electrical, Electronics and Computer Engineering (UPCON)

Leveraging Machine Learning for Career Prediction and

Resume Analysis in Career Assist
2023 10th IEEE Uttar Pradesh Section International Conference on Electrical, Electronics and Computer Engineering (UPCON) | 979-8-3503-8247-1/23/$31.00 ©2023 IEEE | DOI: 10.1109/UPCON59197.2023.10434306

1st Nupur Soni 2nd Neerav Nishant 3rd Mohit Singh

School of Computer Applications School of Engineering School of Computer Applications
Babu Banarasi Das University Babu Banarasi Das University Babu Banarasi Das University
Lucknow, India Lucknow, India Lucknow, India
[email protected] [email protected] [email protected]

4th Shadab Ansari 5th Ahmad Tasneem Siddiqui 6th Syed Anas Ansar
School of Computer Applications School of Computer Applications School of Computer Applications
Babu Banarasi Das University Babu Banarasi Das University Babu Banarasi Das University
Lucknow, India Lucknow, India Lucknow, India
[email protected] [email protected] [email protected]

Abstract— A reliable career guidance system has become worlds of big data, artificial intelligence, and cutting-edge
more crucial in this era of rapid technological advancements technologies as this Career Prediction System sets sail
and ever-evolving industries. Career Prediction Application toward a future brimming with limitless possibilities.
emerges as a trailblazer, reshaping our perception of Implementing the Career Prediction System using
professional journeys. This cutting-edge web-based platform,
meticulously crafted using Django, leverages the wonders of
Machine Learning and Django involves using the KNN
machine learning to forecast potential career options for algorithm [2-3], trained on previous data analysis to
students and professionals alike accurately. The application anticipate the most appropriate career path. The algorithm's
puts the power of a personal career advisor right at fingertips, machine learning approach ensures that the predictions are
guiding you toward the most suitable paths in the vast reliable and accurate, reducing the possibility of selecting an
landscape of opportunities. With its interactive and user- unacceptable career path. The results obtained through the
friendly interface, this system takes career planning to a whole system's implementation demonstrate encouraging accuracy
new level, making it a must-have tool in today's fast-paced and effectiveness, making it a valuable tool for students and
world. The platform boasts a plethora of powerful features, professionals.
including a cutting-edge Resume Analyzer, an extensive
Knowledge Network, and a curated collection of Courses, all
The Application's user-friendly interface is an essential
aimed at empowering users to augment their skills and excel in aspect of the Career Prediction System, offering users
their chosen careers. The centerpiece of this application lies in access to relevant information regarding their career path.
its Career Prediction module, which leverages the K-Nearest The platform provides a clear roadmap for achieving
Neighbors (KNN) algorithm, a state-of-the-art machine objectives and promoting workplace satisfaction and mental
learning technique, to scrutinize and evaluate user data prosperity. The Resume Analyzer feature is another valuable
meticulously. The resume analyzer utilizes Natural Language tool that provides users with suggestions for improving their
Processing to analyze resumes, ensuring industry-standard resumes, increasing their chances of securing a job in their
content and formatting for increased visibility and job desired career path. The Courses and Knowledge Network
prospects. Overall proposed application leverages sophisticated
algorithms and data analysis techniques to effectively match
sections `offer additional resources to help users enhance
individuals' unique aptitudes, skills, and interests with the their skills and knowledge, further increasing their chances
most suitable professions, enabling informed decision-making of success in their chosen careers. In addition, the Career
and fostering heightened career satisfaction. Prediction System using Machine Learning and Django is an
innovative career guidance and improvement solution. It
Keywords— prediction module, k-nearest neighbors (knn)
provides students and professionals with a reliable tool to
algorithm, forecast, user's career, data analysis, natural
language processing (nlp), data analysis techniques. make informed decisions about their future career paths.
The system's user-friendly interface and machine learning
I. INTRODUCTION approach offers an accurate and effective way to predict
In a transformative age propelled by awe-inspiring suitable career paths, promoting workplace satisfaction and
technological advancements and groundbreaking digital mental prosperity.
innovations, the unveiling of the Career Prediction System II. PROBLEM STATEMENT
represents a seismic shift in the realm of career guidance.
With the mighty Django framework as its foundation, this In every person's life, a pivotal decision is selecting a
system harnesses the power of advanced machine-learning career path that will have lasting implications for their future.
Opting for a career ill-suited to one's interests and skill sets
algorithms, propelling career guidance into the realm of
can cause turbulence, stunting one's career progression and
precision and foresight [1]. It is like having a tech-savvy
leading to discontent and tension. Difficulties frequently
genie by the user side, unraveling the secrets of true arise when one needs more knowledge when it comes to
vocational potential. As science and innovation shape our making career decisions, exacerbating hardships within the
world, this ingenious solution rides the waves of progress, workspace.
offering a compass to navigate the ever-changing tides of
industries. So, strap in for an exciting journey through the Due to the present education system's need for more
emphasis on unique skills and interests, students may opt for

979-8-3503-8247-1/23/$31.00 ©2023 IEEE 1009

Authorized licensed use limited to: Thapar Institute of Engineering & Technology. Downloaded on February 28,2024 at 06:00:58 UTC from IEEE Xplore. Restrictions apply.
 2023 10th IEEE Uttar Pradesh Section International Conference on Electrical, Electronics and Computer Engineering (UPCON)

careers that differ from their abilities or personal interests. Unveiling the Array of Career With various skillsets and
Additionally, they may need to gain knowledge about certain focuses, there is a vast array of career possibilities within
career paths and the necessary skills to be successful in them. computer and information technology. Applying
Indecisiveness and confusion can arise when personalized mathematical concepts to achieve specific objectives is the
career recommendations are lacking, resulting in job cornerstone of careers in computer science. The field covers
dissatisfaction and burnout due to a mismatch between one's several areas: software development, artificial intelligence,
skills and interests and their current profession. A guidance cybersecurity, and database management [12]. For success in
and awareness system could prevent such issues for students this branch, it's critical to possess robust math skills,
and working professionals. programming knowledge, and problem-solving abilities [11].
As a result, there is a pressing need for a comprehensive, Installation, improvement, and maintenance of computer
interactive system that employs machine learning to provide systems, networks, and databases are abilities included in
individuals with accurate and personalized career guidance. information technology (IT) professions. Professionals in this
The system should take into account the interests, talents, field will ensure that technology efficiently supports business
and educational background of the individual to create a activities. Different jobs included in this career path are IT
concise plan for achieving their career goals. The proposed consultant, systems analyst, network administrator, and
system is intended to recommend career paths to individuals database administrator. Those who practice IT careers must
that are personalized based on their individual needs; this possess technical know-how, issue-solving skills, and
would allow them to make informed decisions regarding various software and hardware mastery [13, 14].
their career paths, which may lead to increased work
satisfaction and mental health. To solve business problems, individuals pursuing
Computer Information Systems (CIS) careers apply
III. LITERATURE REVIEW technology. Their responsibilities include developing,
designing, and implementing information systems that align
This part examines the major computer categories and with organizational objectives. Some areas of focus within
thoroughly analyzes the work that has already been done to CIS include project management, data analysis, and system
forecast students' suitable career prospects. Information administration. In addition to understanding information
technology, computer science, and computer information systems and technology, individuals employed in CIS careers
systems offer various career paths in the computing industry. require communication skills and business savvy.
The review encompasses different prediction techniques and
evaluates the models and algorithms employed. A crucial aspect of selecting a profession in computing is
taking into account individual aptitudes, proficiencies, and
"Student Future Prediction Using Machine Learning" by passions. Investigating the various career possibilities and
Dileep Chaudhary et al. [4,5] provides an overview of the corresponding qualifications and expertise demanded by
existing systems that aim to predict students' suitable career each job is indispensable [11]. Figure 1 shows Career Paths
paths. The authors note that most of these systems solely rely in Computer and Information Technology, illustrating the
on personality traits or interests, which may result in diverse range of professions and specializations available
inconsistent results. In contrast, the study by Janet E. Hurn within the industry.
and Beth Dietz-Uhler [6,7] emphasises the value of learning
analytics in predicting and improving student performance
while emphasising the impact of students' interests, skills,
and strengths on their success. In another study by Lokesh
Katore, Bhakti Ratnaparkhi, and Jayant Umale [8], the
authors utilize 12 attributes of students and various
classifiers to predict career paths. Additionally, Roshani Ade
and P.R. Deshmukh [9] offer an incremental ensemble of
classifiers that tests hypotheses from many classifiers and
uses a majority voting procedure to determine the final
outcome, yielding an accuracy of 90.8%. The investigation
by Mustafa Agaoglu examines the precision of several
classifiers and emphasises the significance of numerous
criteria in assessing faculty performance [10]. However, it is
worth noting that these systems often provide generalized
recommendations not specific to a particular university or
country/state. It is possible for students to need clarification
on some systems' recommendations for groups of courses
belonging to different fields. These limitations highlight the
need for more comprehensive approaches that consider
multiple factors beyond personality traits or interests to
Fig. 1. Wong & Kemp Classification of Computing Careers
accurately predict suitable career paths for students [4].
Numerous prediction models have been investigated; In India, there are numerous career options available in
however, a Nave Bayes and Random Forest model analysis the field of research and technology. Within computing,
reveals a research gap in the reliable and successful individuals can pursue various roles or career paths, such as
prediction of careers [11]. This study aims to discover how to data scientist, UI developer, business process analyst,
use the KNN algorithm to create a more precise and database administrator, software testing, network analyst,
dependable career prediction model.

1010
Authorized licensed use limited to: Thapar Institute of Engineering & Technology. Downloaded on February 28,2024 at 06:00:58 UTC from IEEE Xplore. Restrictions apply.
 2023 10th IEEE Uttar Pradesh Section International Conference on Electrical, Electronics and Computer Engineering (UPCON)

network manager, and more. Each role requires fundamental Additionally, the system calculates the probability of the
knowledge of the respective fields [11,15]. prediction and presents the top careers with a probability
Business innovation and technology are constantly greater than 0.05. These top careers are displayed to the user
evolving, creating an increased demand for qualified IT in descending order of probability, offering further
professionals seeking careers in a variety of computer career information and suggestions. In summary, this module
fields. Many computing programs prepare future utilizes a KNN classification model trained on 17 skills
professionals to enter the workplace and maintain their shown in Figure 4 to predict career roles. Figure 5
productivity, such as computer science, information showcases a user form specifically designed for gathering
technology, software engineering, information systems, and input data to generate accurate predictions.
management information systems degrees. Graduates of
computing programs exhibit diverse practical skills and
comprehensive knowledge across multiple computer and
information technology domains. Moreover, information
technology greatly impacts commercial processes and setups,
requiring knowledge of business and non-technical skills.
IV. PROPOSED SYSTEM
Our proposed system, shown in Figure 2, is designed to
provide a comprehensive solution for career prediction,
course recommendations, knowledge network access, and
resume analysis. It consists of four modules: Career
Prediction, Courses, Knowledge Network, and Resume
Analyzer. Each module serves a specific purpose in assisting
individuals with their career development and job search.

Fig. 3. Proposed Computing Career Classification System Architecture

Fig. 2. Proposed System Architecture

A. Career Prediction
The Career Prediction module incorporates a K-nearest
neighbor (KNN) [2] classifier with k=5 neighbors to predict
career roles based on the user's skills [16]. The system
implements this prediction algorithm using Python code.
Fig. 4. Different Career Fields and User Options
Firstly, the code trains the KNN model using the available
training data, whose steps are shown in Figure 2. As part of
the metrics module, the accuracy_score function is used to
compare predicted and actual career roles for the test data.
As part of the training process, the accuracy score is
calculated and stored in a dictionary, with k=5 representing
the number of neighbors considered in classification. The
trained model is then saved to a pickle file named 'career
counselling.pkl', utilizing the 'pickle' module. To predict the
user's career based on their skills, the system loads the pre-
trained model from the "career counselling.pkl" file using the
'pickle' module. The input data, consisting of the user's skills,
is passed to the model, and the model generates the predicted
career. The predicted career is used to index into a dictionary
containing various careers' names. The name of the predicted
career is displayed to the user, providing them with insights Fig. 5. Form of User Input
into their potential career path.

1011
Authorized licensed use limited to: Thapar Institute of Engineering & Technology. Downloaded on February 28,2024 at 06:00:58 UTC from IEEE Xplore. Restrictions apply.
 2023 10th IEEE Uttar Pradesh Section International Conference on Electrical, Electronics and Computer Engineering (UPCON)

1) Result: After taking input from the user in the form information extracted includes the candidate's name, email
shown in Figure 5, the system generates the top three career address, social profiles, years of work experience,
results, as shown in Figure 6. The predicted career with its educational background, publications, certificates, volunteer
corresponding probability is displayed to the user, providing experiences, relevant keywords, and the resume's cluster.
insights into their potential career path. The system also After this information is collected, it is stored in a database
presents the top careers with a probability greater than 0.05, like SQLite for later use. A resume may have some structure,
offering further information and suggestions. This but the information can vary according to type, order,
functionality enables users to explore and consider potential format, writing style, and format type (e.g., text, pdf). The
career paths based on their skills and interests. Additionally, model must be independent of the order or type of data to
the system incorporates the Knowledge Network module to parse such data effectively and efficiently from different
types of resumes. The Resume Analysis process is
further enhance the user's understanding of the predicted
illustrated in Figure 7, which illustrates the various steps
career.
involved in evaluating and extracting relevant information
from resumes [17].

Fig. 7. Architecture of the Resume Analysis System

1) Text preprocessing: Text preprocessing, a crucial

Fig. 6. Obtained Results from the Proposed System step in natural language processing (NLP), involves the
cleaning and preparation of text data for subsequent analysis
B. Courses or modeling. Python libraries like NLTK (Natural Language
The Courses module offers a wide range of computer Toolkit) and re (regular expressions) are commonly used to
science courses available on the Internet. It assists users in handle various text preprocessing tasks. These tasks aim to
selecting courses relevant to their interests and career goals. transform the text data into a standardized and more
Each course is accompanied by a detailed description and a manageable format, enabling efficient processing and
skill map highlighting the skills that can be acquired by analysis in NLP applications [18].
completing the course. The module incorporates
personalized learning, allowing students to learn at their a) Sentence Segmentation: “Artificial intelligence has
own pace and focus on areas of improvement. Interactive made significant advancements in various fields in recent
learning tools, such as quizzes, assignments, and projects, years. Machine learning algorithms have revolutionized the
are provided to enhance the learning experience. Users can way we process and analyze vast amounts of data. Natural
obtain certifications upon course completion to showcase language processing techniques have improved language
their skills to potential employers. understanding and automated text generation. These
C. Knowledge Network advancements have led to exciting applications such as
intelligent virtual assistants, chatbots, and recommendation
The Knowledge Network module is a comprehensive
systems” [15,20 ]. As the first step in the NLP pipeline,
collection of various job roles in the IT field, along with the
sentence segmentation involves dividing the paragraph into
skills required for each role. It provides detailed role
individual sentences; “In recent years, artificial intelligence
descriptions and skill maps, helping users understand the
has made significant advancements in various fields.”
skills they need to excel in specific jobs. The module also
offers career guidance, assisting users in exploring different "Machine learning algorithms have revolutionized the
career paths within the IT industry. Users can gain industry way we process and analyze vast amounts of data."
insights, including emerging trends and in-demand skills, to "Natural language processing techniques have
make informed decisions about their career development. improved language understanding and automated text
generation." These advancements have led to exciting
D. Resume Analyzer applications such as intelligent virtual assistants, chatbots,
The processing of a large volume of resumes on a daily and recommendation systems.
basis poses a considerable challenge for corporate entities b) Tokenization: Tokenization involves dividing a
and recruitment agencies. In order to handle this task given character sequence or a detailed document unit into
efficiently, humans would have to spend a tremendous smaller units called tokens by removing certain characters,
amount of time. It is necessary to develop an automated such as punctuation. It can be illustrated as following Figure
intelligent system to extract crucial information from 8.
unstructured resumes and convert it into a standardized
format for ranking candidates for specific jobs. The essential

1012
Authorized licensed use limited to: Thapar Institute of Engineering & Technology. Downloaded on February 28,2024 at 06:00:58 UTC from IEEE Xplore. Restrictions apply.
 2023 10th IEEE Uttar Pradesh Section International Conference on Electrical, Electronics and Computer Engineering (UPCON)

words are represented by directed edges, indicating the

dependency or grammatical connections. By analyzing the
dependency parse tree, we gain insights into the syntactic
structure and dependencies present within the sentence.
g) Part-of-speech (POS): Part-of-speech (POS)
Fig. 8. Tokenization tagging is a process in natural language processing that
assigns specific grammatical categories or tags to each word
c) Stemming: Stemming is a crucial step in natural in a sentence. These tags indicate the word's syntactic role
language processing, which involves reducing words to their and help determine its grammatical function and meaning
root or base form, as illustrated in Figure 9. This is done to within the sentence. POS tagging is essential in various NLP
facilitate analysis and improve search results. The process of tasks, including information extraction, sentiment analysis,
stemming involves removing prefixes and suffixes from machine translation, and text generation, as it provides
words so that variations of the same word are mapped to the valuable insights into the text's syntactic structure and
same root word. However, it is important to note that the semantic understanding [19].
stem may not always correspond to the actual root of the
word. Various algorithms have been developed to perform
stemming, dating back to the 1960s. The goal of stemming 2) Implementation
is to improve the efficiency and accuracy of search engines a) Resume information extraction: The first key
by expanding the number of results that match a given query. feature of your resume analyzer is the ability to extract
This is accomplished by treating words with the same stem important information from the uploaded resume. This
as synonyms, a process known as conflation [17]. includes the name and contact details of the applicant, as
well as any skills or technologies mentioned in the resume.
This feature is crucial in order to automate the process of
screening and shortlisting candidates.
b) Job field recommendation: Once the information
has been extracted from the resume, the next step is to
provide a set of recommendations regarding which job fields
the applicant should apply for based on their skills and
experience. This feature is particularly useful for candidates
Fig. 9. Stemming who may not be sure about which field they are best suited
for or looking to explore new opportunities [23].
d) Lemmatization: Lemmatization is a text
c) Course recommendation: In addition to job field
preprocessing technique that removes inflectional endings
recommendations, your resume analyzer also provides a
from words and returns their canonical or base form, known
method to recommend courses that the applicant should
as the lemma. While similar to stemming, lemmatization
enroll in. These courses may be specific to the job field they
ensures that the resulting lemma is a valid word in the
are interested in or general courses to help them build their
language. Consider the words "playing" and "plays."
skills and knowledge. This feature is particularly useful for
Through lemmatization, these words are reduced to their
candidates looking to upskill or reskill to be more
common base form, "play." Unlike stemming, which might
competitive in the job market.
yield a non-word like "intelligent," lemmatization
guarantees that the resulting lemma is a valid and d) Key skills suggestions: Finally, your resume
recognizable word [19]. Lemmatization enhances text analyzer also suggests some key skills the candidate may
analysis by providing linguistically meaningful lemmas, want to develop to enhance their employability. These skills
allowing for improved language understanding, information may be related to the job field they are interested in or more
retrieval, and other natural language processing tasks. general, skills in high demand in the current job market.
e) Stop word analysis: The subsequent step involves Our resume analyzer provides a comprehensive
assessing the significance of individual words within a given solution to help job seekers identify their strengths and
sentence. In the English language, certain words, such as weaknesses, explore new job opportunities, and develop
"is," "a," "the," and "and," tend to occur frequently. These their skills and knowledge to enhance their employability.
commonly occurring words are referred to as stop words in V. CONCLUSION AND FUTURE SCOPE
the NLP pipeline. By identifying them, they can be filtered
out from the analysis, allowing the focus to be placed on The Career Prediction Application is an innovative and
words that carry more importance or convey meaningful practical solution for individuals seeking accurate career
information [21]. guidance and improvement. The platform's user-friendly
interface and various features, such as Resume Analyzer,
f) Dependency parsing: It is crucial to determine the
Knowledge Network, and Courses, make it accessible to a
relationships between words within a sentence. It allows us
broad range of users. The Career Prediction module, which
to understand how each word depends on or relates to other
utilizes the K-Nearest Neighbors (KNN) algorithm, is the
words. This process involves constructing a tree structure,
central feature of the application and provides accurate
where a single word is assigned as the parent and other
career recommendations based on the user's skills and
words as its dependents.[22]
interests. However, the potential for career counseling apps
In the dependency parse tree, the main verb in the on the web is limitless, and there are several areas for future
sentence serves as the root node. The relationships between

1013
Authorized licensed use limited to: Thapar Institute of Engineering & Technology. Downloaded on February 28,2024 at 06:00:58 UTC from IEEE Xplore. Restrictions apply.
 2023 10th IEEE Uttar Pradesh Section International Conference on Electrical, Electronics and Computer Engineering (UPCON)

development. Expanding the scope of career guidance web [9] L. S. Katore, B. S. Ratnaparkhi and J. S. Umale, "Novel professional
career prediction and recommendation method for individual through
applications to cover all fields can enable students from analytics on personal traits using C4.5 algorithm," 2015 Global
different backgrounds to receive personalized career advice. Conference on Communication Technologies (GCCT), Thuckalay,
Adding machine learning and NLP techniques can India, 2015, pp. 503-506, doi: 10.1109/GCCT.2015.7342798.
significantly enhance the Resume Analyzer's accuracy and [10] R. Ade and P. R. Deshmukh, "An incremental ensemble of classifiers
incorporate a recommendation engine to suggest jobs as a technique for prediction of student's career choice," 2014 First
International Conference on Networks & Soft Computing
matching a student's skills, interests, and education level. (ICNSC2014), Guntur, India, 2014, pp. 384-387, doi:
Furthermore, integrating psychometric tests can help 10.1109/CNSC.2014.6906655.
identify the student's personality traits, strengths, [11] M. Agaoglu, "Predicting Instructor Performance Using Data Mining
weaknesses, and interests, guiding them to choose the right Techniques in Higher Education," in IEEE Access, vol. 4, pp. 2379-
2387, 2016, doi: 10.1109/ACCESS.2016.2568756.
career path according to their personal characteristics.
Overall, the Career Prediction Application is a valuable tool [12] S. Nai, "Career Prediction Model for Computing College Students in
Kenya," Scholarly Project, University of Nairobi Digital, Repository,
for professionals and students, providing accurate career 2022. Available: http://erepository.uonbi.ac.ke/handle/11295/161620.
guidance and recommendations to enable users to make [13] S.A. Ansar, S.P. Srivastava, J. Yadav, M. Khan, A. Yadav, and R.A.
informed decisions about their future. By incorporating new Khan, “Estimation of Software Security Risks through CVSS: A
technologies and expanding the platform's features, Design Phase Perspective,” Turkish Online Journal of Qualitative
Inquiry, vol. 12, no.4, 2021
individuals can take control of their careers and work
[14] Chandra, P., Agarwal, D. and Shukla, P.K., 2020. A review on the
towards achieving their professional goals. The future scope interval type-2 fuzzy systems. International Journal of Intelligent
of career counseling apps on the web is vast, and the Systems Design and Computing, 3(2), pp.117-132.
incorporation of new features such as expanding the scope [15] S.A. Ansar, S. Aggarwal, S. Arya, M.A. Haq, V. Mittal, and F. Gared,
of fields, enhancing the accuracy of the Resume Analyzer, “An intuitionistic approach for the predictability of anti-angiogenic
incorporating a recommendation engine, and integrating inhibitors in cancer diagnosis,” Scientific Reports, vol.13, no.1,
pp.7051, 2023.
psychometric tests can provide more accurate and
[16] S.A. Oloruntoba1 and J.L.Akinode (2017), “Student Academic
personalized career advice to students from different Performance Prediction Using Support Vector Machine,”
backgrounds. International Journal Of Engineering Sciences & Research
Technology, pp. 588-598
REFERENCES [17] S.A. Ansar, S. Arya, S.K. Dwivedi, N. Soni, A. Yadav, and P.C.
[1] The mean power (MNP) of all the three muscles were Pathak,” Data Mining: An Incipient Approach to World Security,” In
simultaneousoly studied during the entire muscle-activity. The graphs Computer Vision and Robotics: Proceedings of CVR 2022, pp. 541-
below show that TA muscle is least functional in the entire cycle of 550, Singapore: Springer Nature Singapore, 2023.
both FAST and PRESS phase. The S muscle is extensively active [18] Sroison, Pornphat; Chan, Jonathan H. (2021). Resume Parser with
during the PRESS phase while the GA and S are equally active during Natural Language Processing. TechRxiv. Preprint.
the fast cycle. https://doi.org/10.36227/techrxiv.17641604.v1.
[2] Django.[Online]. Available at: https://www.djangoproject.com/. [Last [19] Codecademy, "NLP Text Preprocessing Cheatsheet," Codecademy
Accessed: May. 8, 2023]. [Online] Available at: https://www.codecademy.com/learn/dsnlp-text-
[3] T. Srivastava, “A Complete Guide to K-Nearest Neighbors (Updated preprocessing/modules/nlp-text-preprocessing/cheatsheet.
2023),” Analytics Vidhya, Apr. 2023, [Online]. Available at: [20] Turing (2022) Natural Language Processing Functionality in AI
https://www.analyticsvidhya.com/blog/2018/03/introduction-k- [Online]. Available at: https://www.turing.com/kb/natural-language-
neighbours-algorithm-clustering/, [Last Accessed: April. 28, 2023]. processing-function-in-ai (Last Accessed: 24 April 2023).
[4] S. Saxena, N Soni, A. K. Bhasker and A. Mishra “Using PCA and t- [21] Chandra, P., Agarwal, D., Shukla, P.K. (2019). MOBI-CLASS: A
SNE to support HCV Patient Prediction and Data Analysis” 2021 Fuzzy Knowledge-Based System for Mobile Handset Classification.
Journal of Xi’an Shiyou University, Natural Science Edition, vol 16, In: Bansal, J., Das, K., Nagar, A., Deep, K., Ojha, A. (eds) Soft
pp. 259-265. Computing for Problem Solving. Advances in Intelligent Systems and
[5] D. Chaudhary, H. Prajapati, R. Rathod, P. Patel and R. K. Gurjwar Computing, vol 817. Springer, Singapore.
‘Student Future Prediction Using Machine Learning, 2019 [22] S.A. Ansar, S. Arya, S. Aggrawal, J. Yadav, and P.C. Pathak,
International Journal of Scientific Research in Computer Science, “Bitcoin-Blockchain Technology: Security Perspective,” In 2022 3rd
Engineering and Information Technology, Technoscience Academy, International Conference on Intelligent Engineering and Management
Apr. 2019, pp. 1104–1108, https://doi.org10.32628/cseit1952300. (ICIEM), IEEE, pp. 291-296, 2022.
[6] S. A. Ansar, K. Jaiswal, S. Aggarwal, S. Shukla, J. Yadav and N. [23] S.A. Ansar, A. Singh, S. Aggrawal, A. Yadav, P.C. Pathak, and R.A.
Soni, "Smart Home Personal Assistants: Fueled by Natural Language Khan, “Modernizing CPS with Blockchain: Applications, Challenges
Processor and Blockchain Technology," 2022 Second International & Future Directions,” In 2022 Second International Conference on
Conference on Interdisciplinary Cyber-Physical Systems (ICPS), Interdisciplinary Cyber Physical Systems (ICPS), pp. 124-129, IEEE,
Chennai, India, 2022, pp. 113-117, doi: 2022.
10.1109/ICPS55917.2022.00029. [24] Smart_Resume_Analyser_App," GitHub. [Online]. Available at:
[7] U.D. Beth and H.E. Janet, "Using Learning Analytics to Predict (and https://github.com/Spidy20/Smart_Resume_Analyser_App.
Improve) Student Success: A Faculty Perspective," Journal of
Interactive Online Learning, vol. 12, pp. 17-26, 2013.
[8] W. Greller, and H. Drachslrer (2012). Translating learning into
numbers: A generic framework for learning analytics. Educational
Technology & Society, 15(3), 42-57.

1014
Authorized licensed use limited to: Thapar Institute of Engineering & Technology. Downloaded on February 28,2024 at 06:00:58 UTC from IEEE Xplore. Restrictions apply.

View publication stats