Turn On Your Future @ UWTSD's School of Applied Computing & Electronics

Posts tagged ‘artificial-intelligence’

Guest Lecture: Emerging Trends & Digitisation of Society

Many thanks to David Jones (Consultant) and Geraint Williams (Director of Mission Control) from Fujitsu for recently visiting the University and speaking with our students.

Geraint Williams (right) & David Jones (left)

The talk titled ‘Digital Trends‘ covered the incredible rapid innovation and evolution of Technology that has brought about an incredible transformation and digitization of society. Highlighting significant historical and current innovations, positive impacts, and emerging trends & technologies, challenges and future impacts. A whistle stop tour of the digital landscape: past, present and future. A fascinating talk enjoyed by all, staff and students alike.

“Our Digital Trends talk, delved into the multifaceted impact of digitalisation on society, business, and daily life. It highlights key themes such as the integration of technology into everyday activities, the challenges of digital transformation, lifestyle shifts driven by digital innovation, and future trends including Robotics, AI, and Quantum Computing. Additionally, it introduces the concept of Human Centric Design and describes a workshop where participants tackle the ethical integration of Generative AI in organisations, focusing on creating value while mitigating risks such as misinformation and bias”. – David Jones (Guest Speaker from Fujitsu)

David went on to explain that the Digital Trends talk explored the ongoing digital transformation shaping society, business, and daily life. And that it’s purpose is to inform and inspire audiences about the profound impact of digitalisation, the benefits and challenges it brings, and the emerging trends that will define the future.

Key Themes Covered:

  • Digitalisation of Society: Examines how technology is blending virtual and physical environments, transforming commerce, education, finance, health, and communication. Highlighting the benefits of efficiency, global connectivity, economic growth, and access to information, while also addressing the importance of security and trust in digital systems.
  • Challenges of Digital Transformation: Discusses digital inequality, job displacement, ethical considerations (such as AI bias and privacy), cybersecurity threats, and the need for robust digital infrastructure. The content emphasizes the importance of inclusivity, ethical technology use, and collaboration among stakeholders to address these challenges.
  • Digital Living – Lifestyle Shifts: Explores how digital technologies have revolutionized the way we interact, work, consume, and manage our lives, from remote work and smart homes to online communities, e-learning, and digital entertainment.
  • Future Trends: Looks ahead to transformative innovations such as Robotics and AI, Quantum Computing, Cashless Societies, Extended Reality, Bionics & Cybernetics, and Regenerative approaches to society and energy and risks associated with these advancements, including ethical, economic, and societal implications.
  • Human Centric Design: Introduces a unique design thinking methodology focused on aligning business challenges with human needs, fostering creativity, and developing rapid, actionable solutions.

The Human Centric Design workshop provided students with a Challenge Statement: How can organisations harness Generative AI to create value for customers while preventing misinformation, bias, and intellectual property risks. It gave the students an opportunity to consider the introduction of AI into a company’s ecosystem and how they can work together to ideate and reach a consensus on what the key features and challenges are for ethical AI solutions.

“It was a pleasure to return to the place where it all began for me and give something back. I genuinely enjoyed the preparations, creation and delivery of both the talk and workshop and it was good to see the next generation of industry experts beginning their journey, there is much ahead of them, change is accelerating at a pace like we have never seen…” – David Jones

“Great to be back at the University of Wales Trinity Saint David (UWTSD) today speaking with first year Computing students. As a former student of the university, it’s special to return to the place that set me up for success and share the lessons I’ve learned along the way e.g. stay curious, build your network, and keep evolving/adapting – the technology industry never stands still!” – Geraint Williams

The Academic staff at UWTSD’s School of Applied Computing would like to thank David & Geraint for taking the time to come back to the University and share their invaluable experience, industry knowledge and insights. Diolch yn fawr iawn.

~

Category:

Uncategorized

Tagged with:

UWTSD Host Workshop on Robots & Digital Healthcare

The University of Wales Trinity Saint David (UWTSD) hosted a pioneering workshop, titled ‘Soft Exoskeleton Robots and Digital Healthcare,’ bringing together experts from across disciplines to explore the future of rehabilitation technologies.

Held at the University’s IQ Building at its SA1 Swansea Waterfront campus, the event marked a significant moment in cross-sector collaboration aimed at co-designing innovative, patient-focused solutions. 

Led by Dr Seena Joseph and Dr Tim Bashford from UWTSD, the workshop was part of the Soft Exoskeleton Robotics Project, a collaborative effort funded by the Wales Innovation Network (WIN). The project brings together partners from Cardiff Met ( Dr Wai Keung Fu), University of South Wales (Dr Leshan Uggalla) and Institute of Robotics, Bulgaria (Dr Tony Punnoose), all working together to advance rehabilitation technologies.

The full-day workshop convened leaders from robotics and engineering, healthcare and clinical practice, academia, and industry, sparking multidisciplinary dialogue on the development and real-world application of soft exoskeleton robots for rehabilitation. Attendees included academics, researchers, clinicians, innovators, and policy influencers, all united by a common goal: to shape more effective, accessible, and human-centred healthcare technologies.

Dr Kapilan Radhakrishan, UWTSD’s Academic Director (Applied Computing), delivered the welcome address and provided an overview of the project. He described the workshop as a valuable platform to introduce the project and set the stage of exploring new research ideas and to ignite meaningful collaborations with experts across disciplines in soft robotic and digital health. 

Dr Mark Cocks, Dean of the University’s Wales Institute of Science and Art who opened the event said: “Collaboration is the buzzword, and it is more important than ever. In today’s complex and fast-changing landscape, working together across disciplines and sectors is essential to drive innovation and achieve meaningful outcomes. This workshop perfectly exemplifies how bringing experts from academic, industry and healthcare together can spark new ideas. We are proud to host such an impactful and forward-thinking event.”

Highlights included:

The workshop featured a series of compelling talks and a live demonstration of the prototype of soft exoskeleton robot for stroke rehabilitation developed by Dr Tony Punnoose (Institute of Robotics, Bulgaria), one of the team members. 

Dr Fatma Layas and Dr Yajie Zhang (ATiC) presenting human-centred product evaluation approaches in healthcare.

“A Digital Healthcare Overview” was presented by Dr. Tim Bashford, one of the workshop organisers. His presentation provided a broad perspective on the evolving role of digital technologies in healthcare, setting the scene for the day’s discussions and highlighting opportunities for innovation and collaboration.

Dr Wai Keung Fung (Cardiff Metropolitan University) one of the co-organisers outlining core design principles of Soft Exoskeletons 

Dr Gokul Kandaswamy (NHS Wales) delivered an exciting talk on how robotic technologies are transforming patient care, sparking meaningful discussions, and inspiring ideas for future collaborations

Dr Udayanga Galappaththi  an  industry partner from Far UK Ltd exploring the integration of sustainable materials in robotic hand exoskeletons.

Dr Seena Joseph delivered an presentation on “Recent Trends in Soft Robotic Exoskeletons: Insights from a Systematic Literature Review,” offering a comprehensive overview of global research developments, emerging technologies, and future directions in the field.

Additional highlights included the presentation from several experts: Prof Eggbeer, Dominic from Cardiff Met discussed the impact of lead users and 3D printing on advancing adaptive sports technology, while Dr Rajan Prasad, from Khalifa University, Abu Dhabi shared innovative simulation-based designs for cable-driven exoskeletons aiding post stroke gait recovery. 

A live prototype demonstration by Dr Tony Punnoose (Institute of Robotics, Bulgaria), showcasing a bilateral soft exoskeleton robot for stroke rehabilitation. He underscored the importance of shifting research efforts toward developing small-scale, user-friendly parallel robotic systems that patients can take home, enabling more consistent, accessible, and effective rehabilitation beyond the clinical setting. 

The event culminated in an energetic panel discussion, moderated by Dr Fung, with panellists diving into practical applications, ethical considerations, and future research directions for soft robotic solutions in health contexts. Looking back on the event, he said: 

“Moderating the panel discussion reminded me that the future of rehabilitation isn’t just about smarter machines, it’s about deeper collaboration between engineers, clinicians, and users to co-create technologies that truly empower.”

The event also included a productive networking session, facilitated by Dr Leshan Uggalla (University of South Wales) from the project team. This session gave attendees a valuable opportunity to connect, exchange ideas, and foster potential collaborations in a relaxed and engaging environment.

The workshop not only reinforced UWTSD’s commitment to fostering interdisciplinary research and real-world innovation but also underscored its ambition to serve as a hub for cutting-edge dialogue that shapes the future of care and rehabilitation.

Adapted from original post & source here: https://www.uwtsd.ac.uk/news/uwtsd-hosts-workshop-soft-exoskeleton-robots-and-digital-healthcare

Category:

Uncategorized

Tagged with:

MSc Project: Fusion neural network

Name: Ze Wu

Q. Course: MSc Software Engineering and Artificial Intelligence

Q. Project title: Detection of fusarium head blight on wheat spikelets using a multi-scale feature fusion CNN model.

Q. Introduction/rationale: The motivation for choosing this project stems from the significant impact of fusarium head blight (FHB) on wheat production, which poses a threat to global food security. By leveraging advanced artificial intelligence techniques, this project aims to develop a robust detection system that can assist farmers in early identification of FHB, ultimately contributing to better crop management and yield optimization.

Q. Overview of the practical implementation:

  • Data Collection: Acquiring a dataset of wheat spikelet images, both healthy and affected by FHB.

Figure 1: Dataset Samples

  • Model Development: Designing a multi-scale feature fusion convolutional neural network (CNN) to analyze the images. Built on the advanced YOLOv9 framework, the model incorporates a Multi-Scale Feature Enhancement and Fusion (MSFEF) module, which plays a critical role in extracting and dynamically enhancing features from various scales. To enhance computational efficiency, as shown in Figure 2, optimized convolutional layers such as RepNCSPELAN and DWConv are used, reducing the overall computational load while maintaining high detection performance.

Figure 2: Proposed network overview

  • Training and Testing: The model was trained on the dataset using techniques like data augmentation (Mosaic) to enhance its robustness. Testing was conducted to evaluate accuracy and performance.

Figure 3: Training batch samples

  • Deployment: The final model can be integrated into a user-friendly application for real-time detection, offering researchers and farmers an efficient tool for early disease detection and management.

Figure 4: Model predictions

Q. Overview of outcome/conclusion:

The project successfully demonstrated that the proposed multi-scale feature fusion CNN model can accurately detect fusarium head blight in wheat spikelets, achieving an accuracy of over 90%, which highlights the potential of AI-driven solutions in agriculture, paving the way for future advancements in plant disease management and crop monitoring.

Q. What Career and job role are you hoping to move into after graduation?

After graduation, I aspire to work as a machine learning engineer, focusing on applying AI in agricultural technology. My goal is to contribute to innovations that enhance food security and sustainability through smart farming practices.

Q. Please share a top tip/advice for students who are interested in completing a University Degree?

One essential piece of advice is to stay curious and actively engage with your coursework beyond the classroom. Seek out projects, internships, and collaborative opportunities that apply your knowledge in real-world contexts. Building a strong network and gaining practical experience will significantly enhance learning and career prospects.

For further information about Computing courses at UWTSD, please click-here.

Category:

Uncategorized

Tagged with:

MSc Project: LSTM Networks

Project title: Development of Stock Price Prediction Model using LSTM Networks

Course: MSc / Master of Science in Data and Artificial Intelligence

Student name: Mohammed Talha Sajidhusein Vasanwala

Rationale: What was the reason/motivation for choosing the project?

The volatility of stock markets presents a major challenge in financial forecasting. Traditional methods, while effective in some cases, struggle to capture the inherent complexities of financial data, such as time dependencies, trends, and market shocks. Tesla’s stock prices, which are known for their rapid fluctuations, piqued my interest for this project. The motivation behind choosing this project was twofold:

  1. To explore how Long Short-Term Memory (LSTM) networks can be optimized to capture and predict the volatile patterns in stock price data.
  2. To address the limitations of traditional models and highlight the potential of LSTM models for accurate financial forecasting, especially in dynamic environments like stock trading.

Q. Brief Overview of the Practical Implementation (Text Description and a Few Images)

The practical implementation of this project involved multiple stages, including data preprocessing, building and testing LSTM models, and evaluating the models’ predictive performance. Here’s a breakdown of the key steps:

Data Preprocessing:

  • Tesla’s historical stock data (specifically ‘Close’ prices) was collected and cleaned.
  • The data was normalized using MinMaxScaler, which is crucial for speeding up the LSTM training process.
  • The dataset was then split into training and testing sets, ensuring proper chronological order for the time-series data.

Model Building:

  • Thirty different LSTM configurations were tested, focusing on adjusting layers, units, activation functions, and learning rates.
  • The final best-performing model consisted of three LSTM layers, each with 64 units and ‘tanh’ activation functions. The model also used the ReduceLROnPlateau and EarlyStopping callbacks to optimize training and prevent overfitting.

Training and Evaluation:

  • The models were trained with RMSE, MAE, MSE, and R² score as key evaluation metrics.
  • The best model achieved an RMSE of 0.0456 and an R² score of 0.944, demonstrating its high accuracy.

Q. Overview of Outcomes/Conclusions

The project successfully developed an optimized LSTM model that significantly outperformed traditional forecasting methods. The model was able to capture the temporal dependencies in Tesla’s stock price data and deliver highly accurate predictions. Some key outcomes include:

High predictive accuracy: The final model achieved a strong RMSE of 0.0456 and an R² score of 0.944, reflecting its superior performance in predicting Tesla’s stock prices.

Overcoming common challenges: Issues such as overfitting were effectively addressed using advanced regularization techniques and dynamic learning rate adjustments.

Despite the success, the study recognized the limitation of relying solely on historical data. Incorporating real-time data such as news sentiment and company-specific updates could further improve the model’s performance in capturing sudden market changes.

Q. Top Tips/Advice for Students Interested in completing a University BSc/MSc Degree:

Start Early: Begin your project as soon as possible, especially right after submitting your research proposal. This will give you ample time to explore different ideas, refine your methods, and address unexpected challenges along the way.

Be Proactive in Securing Data: Data accessibility can sometimes be a bottleneck. Make sure you identify and secure the necessary datasets early in your project, even if they require permissions or payments.

Iterate and Experiment: Machine learning projects, especially those involving deep learning models like LSTMs, benefit greatly from iterative experimentation. Small changes in hyperparameters can have a significant impact on model performance, so don’t hesitate to test various configurations.

Understand your Tools: Take time to thoroughly understand the libraries and tools you’re using. In my case, libraries like Keras and TensorFlow were vital for building LSTM models. Understanding how to efficiently use these tools sped up my development process.

Consult your Supervisor Regularly: Keep in close contact with your supervisor. Their feedback is invaluable, especially when it comes to refining your methodology and solving challenges related to your project. Stay Resilient: Research can be unpredictable. You might face challenges like overfitting, lack of data, or even model failure. The key is persistence and a willingness to adjust your approach as needed.

For further information about Computing courses at UWTSD, please click-here.

Category:

Uncategorized

Tagged with:

MSc Project: Machine Learning (ML)

Student name: Sriskantharaja Mithushan

Course: MSc in Data Science and Analytics

Project title: A Comparative Evaluation of Machine Learning Techniques for Sales Forecasting

/\ Sriskantharaja Mithushan

Rationale: What was the reason/motivation for choosing the project?

The motivation behind choosing this project stemmed from the increasing importance of accurate sales forecasting in business decision-making. Companies rely heavily on predictive models to optimize inventory management, plan marketing strategies, and drive revenue growth. I was particularly interested in how different machine learning techniques could enhance the accuracy of these predictions, compared to traditional forecasting methods. My goal was to explore and compare the effectiveness of various machine learning models in improving sales forecasts, which could have a significant impact on business operations and profitability.

Machine learning (ML) is a branch of artificial intelligence (AI) and computer science that focuses on using data and algorithms to enable machines to learn from experience, much like humans do. In analyzing data, the ML algorithm, processes data multiple times to learn / adjust itself to improve accuracy.


Q. Brief overview of the practical implementation? 

The project was conducted in several stages, starting with data gathering, followed by preprocessing, model execution, and evaluation. A rich dataset was collected from various retail and e-commerce platforms, containing sales records, customer demographics, product categories, and revenue figures. This data was cleaned and transformed to handle missing values, normalize scales, and ensure proper formatting for model training.

Five machine learning models were implemented:

  • Random Forest
  • Support Vector Regression (SVR)
  • LightGBM
  • XGBoost
  • Gated Recurrent Unit (GRU) Neural Network

Each model was trained on the prepared dataset using Python, with libraries such as Scikit-learn, LightGBM, XGBoost, and TensorFlow.

After training, predictions from each model were compared to the actual sales data. Visualization tools like Matplotlib and Seaborn were used to graphically depict the performance of each model, with side-by-side comparisons of RMSE and MAPE metrics. These visualizations helped to highlight the strengths and weaknesses of the various models.

The Profit Over Time graph below, tracks monthly profit trends, providing a clear view of how profitability fluctuates over time. Key insights include: Seasonality and Profit Growth or Decline. For example Seasonality highlights periods of increased or decreased profits, often aligned with sales cycles or specific marketing efforts. This helps in identifying high-profit months and adjusting strategies for low-profit periods.

This visualization is crucial for understanding financial performance, aiding in strategic decision-making, and optimizing resource allocation for long-term profitability.

/\ Profit Over Time: Illustrates monthly profit trends.

This pairplot chart below, simultaneously shows the distributions (diagonal plots) and relationships (scatter plots) between the key variables: Sales, Quantity, Discount, and Profit. For example the scatter shows a strong positive relationship, confirming that higher sales lead to greater profits. A weak negative trend suggests that offering larger discounts may slightly lower profits. This pair plot provides a comprehensive overview of how these variables relate to each other and how each is distributed, helping in identifying trends, correlations, and potential outliers.

/\ Pairplot: Distributions and Relationships Between Sales, Quantity, Discount, and Profit.

The chart below is a Heat-map. The Heatmap shows the correlations between the key business metrics of Sales, Quantity, Discount, and Profit. The color intensity represents the strength and direction of the relationships, with darker colors indicating stronger correlations. For example, a deep hue between Sales and Profit highlights that as sales increase, profits rise significantly. This visual tool helps identify how these variables interact and guide strategic decisions on pricing, sales, and profit optimization.

/\ Correlation Matrix Heatmap: Sales, Quantity, Discount, and Profit

Q. Overview of outcomes/conclusions?

The project concluded with Random Forest emerging as the top-performing model in terms of prediction accuracy.

The research delved into the use of machine learning techniques for sales forecasting in the retail and e-commerce sectors, with the goal of identifying which models provide the most accurate predictions. The study examined five machine learning algorithms: Random Forest, Support Vector Regression (SVR), LightGBM, XGBoost, and Gated Recurrent Unit (GRU) neural networks. The models were evaluated using metrics such as Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE).

This study contributes to the understanding of how machine learning can be applied to sales forecasting in retail and e-commerce. It shows that tree-based ensemble methods, particularly Random Forest, are among the most effective techniques. However, deep learning models like GRU also show potential, particularly for capturing temporal dependencies. A balanced approach, combining multiple models and fine-tuning hyperparameters, can lead to more accurate sales predictions. By acting on these insights, retail and e-commerce companies can improve their forecasting accuracy, optimize inventory management, and ultimately enhance customer satisfaction and profitability. 

Q. Please share some top tips/advice for students?

Completing a Bachelor of Science (BSc) or a Master of Science (MSc) at a university like the University of Wales Trinity Saint David (UWTSD) can be a rewarding and challenging journey.

The University offers a variety of Computing courses. Ensure you choose a program that aligns with your interests and career goals. During both BSc and MSc, you’ll often have the flexibility to choose elective modules. Select modules that allow you to develop key skills that are in-demand in your field, or that attract your personal interest. Balancing lectures, labs, independent study, and personal commitments is crucial. Use digital tools to organize deadlines, assignment dates, and exam preparation to stay on track. The University also offer career services to help students prepare for employment. Take advantage of these CV workshops, interview practice, and employability training.

For further information about Computing courses at UWTSD, please click-here.

~

Category:

Uncategorized

Tagged with: