Filter by keyword, subject, or both. Updates live as new model answers are added to our portal.
500 words
Reflective Account – Data Collection Practices
This individual assessment requires students to complete practical data collection exercises and write a 400–500 word reflective account based on their experience. The assessment is designed to develop understanding of different data collection methods and encourage students to connect the practical exercises completed in the laboratory with research methods and concepts covered during lectures. Students are required to complete two main types of data collection practice. The first involves questionnaire tests, which students attend during their allocated practical sessions. The second involves a series of recorded interaction exercises involving ChatGPT and human participants. Students must follow the supplied study instructions, use the specified prompts where required, record the requested activities using a camera such as a phone, and upload the relevant files to a designated OneDrive folder. The briefing also requires students to complete and sign the participant consent form and submit it with their collected data. The reflective account should summarise the methods learned during the module lectures and the methods exercised during the laboratory sessions. Students should demonstrate their overall understanding of how data collection works, why data collection is important in research, and how knowledge of data collection methods can be improved through practical experience. The reflection must address several key research and methodological questions. Students should explain how they would design a research question based on the collected data and identify the PICO elements relevant to the research. They should discuss what type of research could be conducted using the data and define an example of a machine learning problem that could be investigated. The reflection should also consider the participant experience by identifying areas of the data collection process that could be improved. Students are additionally asked to consider how they would design a similar data collection project themselves and whether they would make any changes to the methods, procedures or participant experience. The assessment therefore combines practical experience with critical reflection on research design, data collection, research questions, PICO, machine learning applications and methodological improvement. The final reflective account is a Canvas submission and should remain within the specified 400–500 word range. The assessment briefing states that students are marked based on the submitted report, making the reflective account the primary assessed component of the activity.
Read Model Answer →
Identifying Psychological States of Human Subjects via Machine Learning Algorithms
This research project investigates the application of artificial intelligence and machine learning techniques to the identification of human psychological states. The study collects multimodal information from participants during structured conversational interactions and combines these data with established psychological and demographic measures. The research explores whether machine learning algorithms can identify patterns associated with psychological states using behavioural, physiological and conversational information. Participants take part in structured conversations involving both artificial intelligence and another human participant. The conversational activities include emotional reflection, cognitive challenges and open-ended discussion. During the emotional reflection activity, participants discuss experiences such as happiness, stress and coping strategies. The cognitive component includes memory tasks, riddles, planning questions and problem-solving or moral-dilemma questions. The final component involves an open conversation around topics such as travel, artificial intelligence, books or films. The ChatGPT interaction is designed to provide a consistent conversational structure while allowing participants to respond naturally. The study collects several forms of multimodal data. These include voice recordings, video recordings showing participants' facial expressions, spoken conversation transcripts and EEG data. Additional demographic and lifestyle information may also be collected. The research materials describe factors such as age, marital status, weight, height, disability, smoking, drinking, academic performance, family income, family size and physical exercise. Established questionnaires are also used to obtain information about participants' experiences and psychological states. Machine learning techniques are subsequently applied to the collected datasets to identify patterns that may be associated with psychological states. The research materials describe potential applications of AI in psychological assessment, predictive analytics, emotion recognition, monitoring and prevention, personalised treatment and AI-assisted mental health support. The broader objective is to investigate whether computational approaches can contribute to earlier identification of psychological difficulties and support more accessible and personalised approaches to mental health assessment. The project also places emphasis on participant welfare, informed consent, confidentiality and secure handling of research data. Participants are informed that they can withdraw their data up to completion of the study and are provided with support information if participation raises concerns or emotional discomfort. The consent documentation confirms that participants are informed about voice, video and photographic recording, data handling and access arrangements. The supplied materials also contain separate instructions for a conversational AI study in which participants interact with ChatGPT for at least ten minutes. The interaction is recorded and the resulting conversation transcript is retained for research purposes. The project therefore provides a multimodal research setting for examining human psychological states through conversational, behavioural and machine-learning approaches.
Read Model Answer →
Research Methods / Project Management / Computer and Information Sciences
3,000 words
Critical Literature Review in Research Methods and Project Management
This Research Methods and Project Management assessment develops students’ ability to search for, evaluate, critically analyse and synthesise academic literature within a computing or information-science research area. Students work within an allocated group to conduct a structured literature search and critically evaluate research papers relevant to an assigned theme, before using the combined group literature corpus to produce an individual literature review. KF7028 - Assessment 1 - Semeste… Each group member must identify and critically analyse a minimum of five academic papers using the supplied Critical Paper Summary template. These individual summaries are then combined into a single group document and shared so that all team members can use the collective body of research. The quality of this component depends on the relevance and academic quality of the selected papers and the depth of critical evaluation rather than simple description. KF7028 - Assessment 1 - Semeste… The main individual component is a 3,000-word critical literature review, worth 60% of the assessment. Students must use the literature identified and summarised through the group activity and critically discuss the research associated with their allocated topic. The review should synthesise the literature into a coherent discussion rather than presenting disconnected paper summaries, demonstrating criticality, clear structure and effective academic writing. KF7028 - Assessment 1 - Semeste… A further 20% is awarded for an individual research and meeting log, maintained through Blackboard. Students are expected to record their research progress, contribution to the group, approach to collaboration and reflections on the literature-review process. Stronger logs demonstrate detailed evidence of active participation, reflective insight and professional collaboration rather than merely listing completed tasks. KF7028 - Assessment 1 - Semeste… KF7028 - Assessment 1 - Semeste… The assessment directly evaluates the ability to apply project-management principles to a computing-related research activity and to search, evaluate and develop a critical literature review. Wider module outcomes also emphasise research techniques, data and information analysis, professional research practice, ethics, risk, legal issues, societal considerations and sustainability. KF7028 - Assessment 1 - Semeste… The marking structure allocates 20% to the combined critical paper analysis, 20% to the research/meeting log and 60% to the individual literature review. Higher-performing work is expected to use high-quality and directly relevant academic sources, demonstrate strong critical analysis, synthesise evidence across the research theme, maintain a professional academic structure and apply accurate Harvard referencing throughout. KF7028 - Assessment 1 - Semeste… KF7028 - Assessment 1 - Semeste… Important for the public Reference Library: the brief states that ChatGPT or other AI tools must not be used to generate text or fill in assessment-template sections. Any AI use that supports the work or thinking must be declared, referenced and accompanied by a prompt log in an appendix. Therefore, this entry should be used only as a high-level public description of the assessment rather than as directly submissible student content. KF7028 - Assessment 1 - Semeste…
Read Model Answer →
Cybersecurity / Information Security Auditing
3,000 words
Physical Security Audit of University Computing Facilities Using ISO/IEC 27002:2022
This postgraduate information-security coursework requires students to act as an IT Security Auditor working for CyberSAFE Auditors and conduct a professional physical-security audit of computing resources used by students at the University of Greenwich. The audit focuses on public student-study and open computing areas within the Dreadnought and Stephen Lawrence Buildings, with findings evaluated against relevant physical-security controls from ISO/IEC 27002:2022 Section 7. 202526 SL-COMP1431 CWK 2026-am … The project begins with planning and project-control activities. Students must define their audit tasks, plan the work independently and document progress through two Work-in-Progress reports, one produced near the beginning of the project and another approximately halfway through. Each WIP report is limited to 250 words and records completed activities, encountered or anticipated problems, planned next steps and potential risk areas. 202526 SL-COMP1431 CWK 2026-am … The second phase involves practical fieldwork. Students must visit the specified university buildings and decide on suitable audit methods, timetable and evidence-gathering procedures. The audit is restricted to public student areas and must not include staff rooms, seminar rooms or utility areas. Students must also comply with client-imposed constraints, including not communicating with university staff and approaching the audit from the perspective of an ordinary student rather than conducting highly technical operating-system or server-level investigation. 202526 SL-COMP1431 CWK 2026-am … 202526 SL-COMP1431 CWK 2026-am … The final professional audit report evaluates secure areas and equipment security, including physical security perimeters, entry controls, protection of rooms and facilities, working in secure areas, equipment siting, supporting utilities and cabling security. Findings should distinguish between expected controls and observed controls, identify gaps and provide justified recommendations for immediate and future management action. 202526 SL-COMP1431 CWK 2026-am … 202526 SL-COMP1431 CWK 2026-am … Assessment places particular emphasis on practical audit methodology, secure-area analysis, equipment security, audit conclusions, gap analysis, professional reporting and the two WIP reports. 202526 SL-COMP1431 CWK 2026-am … Overview word count: approximately 355 words. AI-use note: the brief states that this coursework does not lend itself to reliance on AI-based applications such as ChatGPT and emphasises original analysis, fieldwork and proper attribution of sources. 202526 SL-COMP1431 CWK 2026-am …
Read Model Answer →
Machine Learning and Deep Learning
2,000 words
Development and Evaluation of Deep Learning Models for Healthcare Classification
This individual technical assessment focuses on the design, development, analysis and evaluation of a deep learning solution for a healthcare-related classification problem. Students select one of two provided scenarios: Polycystic Ovary Syndrome (PCOS) detection using ultrasound images or heartbeat classification using electrocardiogram (ECG) signals. The objective is to develop an appropriate deep learning approach and demonstrate critical understanding of the complete machine learning workflow, from initial data exploration through to model evaluation and reflection. Students may either design and train a deep learning model from scratch or customise and fine-tune an existing pre-trained architecture. The complete work is presented through a single Jupyter Notebook integrating Python code, technical discussion, results and visualisations. The notebook must clearly define the selected healthcare problem, explain its significance, justify methodological and architectural choices, and critically evaluate the resulting solution. The first stage involves exploratory data analysis and preprocessing, including investigation of class distributions, data imbalance and relevant patterns. Students prepare the data through techniques such as normalisation, augmentation, train-validation-test splitting and appropriate handling of class imbalance. This is followed by model design, training, validation and hyperparameter tuning, with the architecture selected according to the characteristics of the data and classification task. Model performance must then be evaluated using appropriate classification measures, including precision, recall, F1-score, ROC curves and area under the curve (AUC). The developed model should also be compared against suitable benchmark approaches, which may include traditional machine learning algorithms or alternative deep learning architectures. This comparison should identify the relative strengths and limitations of the proposed solution. The final component requires clear visual presentation and critical reflection on the complete modelling process, including limitations, challenges and opportunities for improvement. Importantly, grading prioritises methodological rigour, analytical depth and critical evaluation rather than simply achieving the highest predictive accuracy. Overview word count: approximately 330 words. AI restriction: this brief only permits automated AI tools for spelling and grammar checking. It explicitly prohibits tools such as ChatGPT, Gemini or Copilot from authoring assessment text or code; any permitted AI use must also be acknowledged.
Read Model Answer →