Dataset Description





Standard Postgraduate Regulations


Your studies will be governed by the BCU Academic Regulations on Assessment, Progression and Awards. Copies of regulations can be found at


For courses accredited by professional bodies such as the IET (Institution of Engineering and Technology) there are some derogations from the standard regulations and these are detailed in your Programme Handbook


Cheating and Plagiarism


Both cheating and plagiarism are totally unacceptable and the University maintains a strict policy against them. It is YOUR responsibility to be aware of this policy and to act accordingly. Please refer to the Academic Registry Guidance at


The basic principles are:


• Don’t pass off anyone else’s work as your own, including work from “essay banks”. This is


plagiarism and is viewed extremely seriously by the University.


• Don’t submit a piece of work in whole or in part that has already been submitted for


assessment elsewhere. This is called duplication and, like plagiarism, is viewed extremely


seriously by the University.


• Always acknowledge all of the sources that you have used in your coursework assignment


or project.


• If you are using the exact words of another person, always put them in quotation marks.


• Check that you know whether the coursework is to be produced individually or whether you


can work with others.


• If you are doing group work, be sure about what you are supposed to do on your own.


• Never make up or falsify data to prove your point.


• Never allow others to copy your work.


• Never lend disks, memory sticks or copies of your coursework to any other student in the


University; this may lead you being accused of collusion.


By submitting coursework, either physically or electronically, you are confirming that it is your own work (or, in the case of a group submission, that it is the result of joint work undertaken by members of the group that you represent) and that you have read and understand the University’s guidance on plagiarism and cheating.


You should be aware that coursework may be submitted to an electronic detection system in order to help ascertain if any plagiarized material is present. You may check your own work prior to submission using Turnitin at the Formative Moodle Site. If you have queries about what constitutes plagiarism, please speak to your module tutor or the Centre for Academic Success.




Electronic Submission of Work


It is your responsibility to ensure that work submitted in electronic format can be opened on a faculty computer and to check that any electronic submissions have been successfully uploaded. If it cannot be opened it will not be marked. Any required file formats will be specified in the assignment brief and failure to comply with these submission requirements will result in work not being marked. You must retain a copy of all electronic work you have submitted and re-submit if requested.


Learning Outcomes to be Assessed:


1. Select and explain appropriate AI applications to deal with the complex data processing issues along with the justification of the appropriateness.


2. Synthesise data and information from a range of AI artefacts, determining the links between principles and applications


3. Identify and evaluate machine learning schemes to quantify a range of performance metrics related to emerging data processing challenges


Assessment Details:


Title: Research Essay – Machine Learning Applications


Theme: Networks, Cybersecurity, or Smart Systems (depending on the enrolled course)


Style: Individual report






In an era marked by a rapid surge in technological capabilities, machine learning stands as a cornerstone in shaping our digital future. Its paramount importance lies in its ability to revolutionize information processing, decision-making, and the fabric of intelligent systems. Beyond its roots in computer science, machine learning has become an indispensable tool across diverse domains, including networking, cybersecurity, and smart systems. Its usage extends from enhancing efficiency in data analysis to fortifying cybersecurity protocols and optimizing the functionality of smart technologies. The scope of machine learning is expansive, offering transformative possibilities in automating tasks, predicting patterns, and extracting insights from vast datasets. As we navigate an increasingly complex digital landscape, the importance of understanding and harnessing the capabilities of machine learning becomes ever more crucial for individuals and industries alike.


Recognizing the interdisciplinary nature of machine learning, the assessment aims to equip students with essential knowledge and investigation skills specific to their respective fields. By focusing on exploratory data analysis and domain-specific applications, the coursework seeks to foster a deep understanding of machine learning’s practical implications, empowering students to harness its benefits while emphasizing the importance of originality and academic integrity in their research endeavors.


Description of the Tasks Required:


This is an individual assessment that requires you to submit a research essay on the analysis of machine learning applications in your respective course (networks, cybersecurity, or smart systems).


• As a first step, you must select a topic after studying the related research papers andidentify your title, problem statement and research questions.• Then, for the purpose of literature review and study comparisons, you are required toselect at least five research articles (journal articles are highly recommended thanconference papers) related to your research questions for comparison. You mustproperly cite the papers you read in their entirety to compose a very compact andtechnical paper draft. Create a table in the following format for all cited papers in theliterature review section,Reference Year Dataset Method Metric Accuracy Platform
Huang et al., 2017 2017 NSL-KDD CNN, SVM, Random Forest Accuracy, precision, recall, fscore Accuracy=98%, precision=96.25%, recall=92.36%, fscore = 93% Weka, Tensorflow, keras




. . . . . . .. . . . . . .
• For the purpose of the analysis, you have to identify 1 research paper published inreliable journal publishers from 2010 onwards.o Examples of publishers: IEEE, ACM, Elsevier, Springer, Wileyo Scimago JR ( can be used to determine thereliability of the publishers.• You will carry out the critical analysis of the machine learning applications in theselected research article. The analysis shall consist of contextual machine learningapplication, dataset description and exploratory analysis, working principles of aspecific machine learning technique, justification of its use in the correspondingapplication, and effectiveness of the technique with recommendation for improvement.• In the process of developing a machine learning model based on the selected researcharticle, several key steps are involved. First, the relevant dataset is collected, ensuringalignment with the contextual machine learning application discussed in the article.Subsequently, data preprocessing activities address issues such as missing values,outliers, and feature scaling. Feature engineering is then undertaken to enhance themodel’s predictive capabilities through the creation or transformation of features.Following this, a specific machine learning technique is chosen, and its workingprinciples are understood. The justification for the technique’s selection is establishedbased on its suitability for the given application. Implementation involves training atleast two algorithms on the dataset, and results are evaluated using appropriatemetrics. The comparative analysis of algorithm performance informs insights into theirstrengths and weaknesses. Finally, recommendations for improvement are provided,guiding potential adjustments to hyperparameters or data collection strategies toenhance the model’s efficacy in addressing the specific machine learning application.• You need to document the outcomes of your critical analysis into a research essayformat of 3500 words (+/- 10%) with the structure given below.

Recommended Essay Structure:


The essay structure shall include:


Title page – this must consist of:


o The essay title. This should reflect a specific analysis carried by yourself and be


different from the title of your selected paper. o The Module Code and title o The


student’s name and ID o Essay word count


Table of Contents


Literature Review o The related work identified should be presented here. o Provide a


short brief of each paper you have selected. o A brief description of the dataset the


selected papers have used.


o The comparison table for the selected papers (at least 5)






o Key points of the entire essay that includes: 1) the overall purpose of a specific


machine learning technique in the domain-specific context; 2) your


interpretations and understanding of the justification of this technique and its


effectiveness in solving issues in the domain-specific context.


o Please limit your Summary to be within 150 – 200 words maximum.


Context of the Machine Learning Application o This presents the context of the


application scenario(s) in which machine learning techniques are applied to solve


domain-specific issues. It will include current understanding and background information


about the topic as well as the problem statement. This section will also provide the


argument from the study and research reading to what extent machine learning is


generally relevant for the context of the scenario(s), drawing upon the pros and cons of


such an approach.


Dataset Description and Exploratory Analysis o This will explain what type of dataset


was proposed or used in the selected paper. Provide more details on what


preprocessing was performed on the datasets. Building upon this, exploratory data


analysis will be anticipated to reveal key patterns, which can link to the specific selection


of machine learning technique.


Machine Learning Principles o Using your own interpretations from the study and


research reading, this section will provide in-depth explanation of a selected machine


learning technique used in the paper to solve the domain-specific issues. If there are


multiple techniques available in the paper, you will need to select one of them, arguing


the importance of this selection.


Justification of Machine Learning Application o Using your own interpretations from


the study and research reading, this section will expand the principles in the previous


section by providing the justification of the use of a selected machine learning technique


in the corresponding domain-specific context. Qualitative comparison with other


techniques could be drawn to provide research-informed arguments.


Effectiveness of the Machine Learning Technique o Drawing upon


Analysis/Results/Discussions/Findings section in the selected paper, this section will


critically review the performance of the selected machine learning technique. The


synthesis and explanation shall identify the gaps or deficiency in the performance and


possible methods for improvement. Whilst experimental testing is not required in this


coursework, improvement methods should build upon suitable valid machine learning




Conclusion o The conclusion should highlight the importance of your overall analysis.


It combines the key points that are delivered by the essay.


References o It provides all the sources you have used in your essay using Harvard


referencing style.


o This part is excluded from the word limit of the essay.




Additional information:


Submission requirement: Upload the final written report in a PDF or MS Word format


using the upload link in the assessment section of Moodle website.


Examples of web links to find a research paper:


o IEEE: o ACM:


o Elsevier: o Springer: o Wiley:


o Google Scholar


Examples of methods for finding datasets linked to papers:


o o o


A guide on Harvard referencing style from BCU Library:




o For advice on writing style, referencing and academic skills,


please make use of the Centre for Academic Success: success


Workload:This assessment is equivalent to 3500 words and a typical student would be expected to take 30 hours to pass this assessment.
Transferable skills:• Process analysis• Applied machine learning research• Research-informed knowledge acquisition• Academic writing• Planning and time-management• Critical analysis




Marking Criteria: Table of Assessment Criteria and Associated Grading Criteria
LearningObjectivesAssessment CriteriaWeighting: Grading Criteria0 – 24%24 – 49% 50 – 59% 60 – 69% 70 – 79% LO1 – Select and explain appropriate AI applications to deal with the complex data processing issues along with the justification of the appropriateness.1. Summary,literature review andcontext of machinelearning application2. Dataset explanation and exploratory analysis15% 20% No submission or major shortcomings in identifying applicationNo submission or major shortcomings in acquiring dataset and performing exploratory analysisInadequate selection of paperInsufficient feature explanationA lack of appropriate application for domainspecific contextA lack of exploratory analysisAdequate selection of paper with average qualityAdequate feature explanationUtilising existing concepts, but insufficient concept appraisalEvidence of preliminary exploratory analysisSelection of paper with good qualityAdapting existing concepts with appropriate justificationA good level of feature explanationExploratory analysis at a good standard, revealing several data patterns.Selection of paper with very good qualityAdapting existing concepts with clearly undertaken syntheses; Very good appraisal demonstratedVery good demonstration in presenting the argument within the word limit.A very good level of feature explanationExploratory analysis at a very good standard, combining different patterns to inform the rationale of machine learning development LO2 – Synthesise data and information from a range of AI artefacts, determining the links between principles and applications.3. Machine learning principles and application alignment/justification40% No or major limitation of evidence for linking principles and applicationInaccurate explanation of principlesInadequate alignment of principles and application purposeMeaningful explanation of principles apparent in several parts of essayAdequate alignment shown, but the links are rather weakClear synthesis of concepts and results that align principles and applicationInclude consideration of benefits and drawbacksCoherent and very clearsynthesis of several concepts and results to determine the principlesapplication linksExpanding benefits and drawbacks discussion with research-informed argument within the word limit. LO3 – Identify and evaluate machine learning schemes to quantify a range of performance metrics related to emerging data processing challenges.3. Effectiveness of machine learning technique and conclusion25%No or major limitation of applying performance metrics to measure effectivenessConfused discussion on performance metricsLimited evaluationSatisfactory discussion on performance metricsConsidered evaluation with a few metrics; Some gaps in appraising the roles of the different metricsGood discussion on performance metricsClear argument of combining different performance metrics to provide holistic evaluationVery good discussion on performance metricsCoherent and very clear argument of combining different performance metric to provide holistic evaluation




80 – 89% Selection of paper with excellent quality


Adaptation of existing concepts with very clear synthesis


Excellent demonstration in presenting the argument within the word limit


An excellent level of feature explanation


Exploratory analysis at an excellent standard with effective use of textual and visual objects


Coherent and very clear synthesis of a wide range of concepts and results to determine the principlesapplication




A wide range of benefits and drawbacks discussion backed-up by state-of-the-art researchinformed argument within the word limit.


Excellent discussion on performance metrics


Excellent level of innovation in combining different performance metric to reveal insights from evaluation


90 – 100% In addition to the criteria in the 80-89 bracket.


Selection of paper with outstanding quality


Excellent synthesis and appraisal, showing originality of thought to context analysis


In addition to the criteria in the 80-89 bracket.


Outstanding feature explanation


Demonstration of exploratory analysis with professional uses of textual and visual objects.


In addition to the criteria in the 80-89 bracket.


Outstanding synthesis from holistic principlesapplication assessment


Strong novelty apparent from assessing benefits and drawbacks, showing originality of thought.


In addition to the criteria in the 80- 89 bracket.


Exceptionally well-structured discussion on performance metrics with innovative use of combining performance metrics that results in novel ideas


Submission Details:


Format: Upload the final written report in a PDF or MS Word format using the upload link in the assessment section of Moodle website
Regulations:The minimum pass mark for a module is 50%Re-sit marks are capped at 50%Full academic regulations are available for download using the link provided above in the IMPORTANT STATEMENTS sectionLate PenaltiesIf you submit an assessment late at the first attempt, then you will be subject to one of the following penalties:if the submission is made between 1 and 24 hours after the published deadline theoriginal mark awarded will be reduced by 5%. For example, a mark of 60% will be reducedby 3% so that the mark that the student will receive is 57%. ;if the submission is made between 24 hours and one week (5 working days) after thepublished deadline the original mark awarded will be reduced by 10%. For example, amark of 60% will be reduced by 6% so that the mark the student will receive is 54%.




• •


if the submission is made after 5 days following the deadline, your work will be


deemed as a fail and returned to you unmarked.


The reduction in the mark will not be applied in the following two cases:


the mark is below the pass mark for the assessment. In this case the mark achieved by the student will stand


where a deduction will reduce the mark from a pass to a fail. In this case the mark awarded will be the threshold (i.e., 50%) Please note:


If you submit a re-assessment late, then it will be deemed as a fail and returned to


you unmarked.


Formative verbal feedback will be provided in the weekly sessions.Marks and Feedback on your work will normally be provided within 20 working days of its submission deadline via Moodle.Written feedback on the final submitted essay will be provided via the submission point on Moodle website.

Where to get help:


Students can get additional support from the library for searching for information and finding academic sources. See their iCity page for more information:


The Centre for Academic Success offers 1:1 advice and feedback on academic writing, referencing, study skills and maths/statistics/computing. See their iCity page for more information:


Additional assignment advice can be found here:




Fit to Submit:


Are you ready to submit your assignment – review this assignment brief and consider whether you have met the criteria. Use any checklists provided to ensure that you have done everything needed.




Assignment Tip Sheet


Assignment Checklist


Run through this simple tick list before submitting your work!




Well prepared materials make your work look more professional and easy to understand.


Item Action Done?

Referencing and Originality


Your work will be subjected to checks to ensure it is not derivative of other works. Works found to be derivative may leave you subject to penalties, including in extreme cases, expulsion from the University.


Item Action Done?



Is your work complete? Have you included all the required elements?


Item Action Done?