How can I help?
How can I help?

Dr Gopal Jamnal

Senior Lecturer

Dr Gopal Jamnal holds a PhD in IoT machine learning from Edinburgh Napier University and currently serves as a Senior Lecturer in data science and AI. His current research interest are health informatics, explainable AI, financial risk management and visual analytics.

Orcid Logo 0000-0001-7516-6214
Dr Gopal Jamnal staff profile image

About

Dr Gopal Jamnal holds a PhD in IoT machine learning from Edinburgh Napier University and currently serves as a Senior Lecturer in data science and AI. His current research interest are health informatics, explainable AI, financial risk management and visual analytics.

Dr Gopal Jamnal holds a PhD in IoT Machine Learning from Edinburgh Napier University and currently serves as a Senior Lecturer in data science ad AI. With over a decade of experience spanning industry and academia, Dr Jamnal has established himself as a distinguished data scientist and software engineer, working across Europe, the UK, and the Asia-Pacific region. His extensive industrial collaborations with renowned organizations such as Adidas Group, LIST, Goodyear, and PwC have significantly shaped his expertise in developing data-driven AI solutions and conducting research in explainable AI systems. His commitment to advancing the field of AI through practical applications and academic research interest are diverse and impactful.

Academic positions

  • Senior Lecturer
    Leeds Beckett University, Leeds Beckett University, Leeds, United Kingdom | 01 January 2021 - present

Degrees

  • PhD
    Edinburgh Napier University, Edinburgh, United Kingdom

Research interests

Specialisms
  • Health Informatics
  • Explainable AI
  • RAG -LLM- Knowledge Graph
  • Financial Risk Management
  • Visual Analytics
  • DevOps Engineering
Innovate UK

KTP funding worth £260k over 30 months.

The KTP project is with a distributor of high precision bearings called Quality Bearings Online (QBOL) based in Leeds. The project creates a unique, expert system - the Intelligent System for the NetZero Era (IS-NeZE) which will enable QBOL to deliver high-quality services and products whilst evolving its business model for the net zero era. The project is a collaboration with the Business School with a total project value £260k over 30 months.

Publications (7)

Sort By:

Thesis or dissertation

A Cognitive IoE (Internet of Everything) Approach to Ambient-Intelligent Smart Space

Featured 01 July 2018
Conference Proceeding (with ISSN)

Home automation:HMM based fuzzy rule engine for Ambient intelligent smart space

Featured 05 July 2017 The 29th International Conference on Software Engineering and Knowledge Engineering International Conferences on Software Engineering and Knowledge Engineering Pittsburgh, Pennsylvania, USA KSI Research Inc. and Knowledge Systems Institute Graduate School
AuthorsJamnal GS, Liu X, Fan L

In this paper, we proposed a new type of decision making system to achieve the intelligent goal for automated smart environments. The artificial intelligence techniques, used as building blocks to understand inhabitant activity patterns. The collected information fused to a central inference engine based on Hidden Markov model and Fuzzy rules for taking appropriate actions to communicate and control various home appliances. We proposed a novel CASH (cognitive automated smart home) architecture, based on the Hidden Markov Model and the fuzzy rule based system. The Hidden Markov Model and fuzzy rules are well equipped to address the spatio-temporal activity pattern recognition problem and to trigger appropriate task execution rules.

Conference Proceeding (with ISSN)

A Cognitive-IoE Approach to Ambient-intelligent Smart Home

Featured 2017 2nd International Conference on Internet of Things, Big Data and Security Proceedings of the 2nd International Conference on Internet of Things, Big Data and Security Porto, Portugal SCITEPRESS - Science and Technology Publications
AuthorsJamnal G, Liu X

In today’s world, we are living in busy metropolitan cities and want our homes to be ambient intelligent enough towards our cognitive requirements for assisted living in smart space environment and an excellent smart home control system should not rely on the users' instructions. Cognitive IoE is a new state-of-art computing paradigm for interconnecting and controlling network objects in context-aware perception-action cycle for our cognitive needs. The interconnected objects (sensors, RFID, network objects etc.) behave as agents to learn, think and adapt situations according to dynamic contextual environment with no or minimum human intervention. One most important recent research problem is “how to recognize inhabitant activity patterns from the observed sensors data”. In this paper, we proposed a two level classification model named as ACM (Ambient Cognition Model) for inhabitant’s activities pattern recognition, using Hidden Markov Model based probabilistic model and sub tractive clustering classification method. While subtractive clustering separates similar activity states from non-similar activity state, a HMM works as the top layer to train systems for temporal-sequential activities to learn and predict inhabitant activity pattern proactively. The proposed ACM framework play, a significant role to identify user activity intention in more proactive manner such as routine, location, social activity intentions in smart home scenario. The experimental results have been performed on Matlab simulation to evaluate the efficiency and accuracy of proposed ACM model.

Conference Proceeding (with ISSN)

Instils Trust in Random Forest Predictions

Featured 01 January 2023 2023 IEEE 10th International Conference on Data Science and Advanced Analytics (DSAA) 2023 IEEE 10th International Conference on Data Science and Advanced Analytics, DSAA 2023 - Proceedings IEEE

This paper addresses the interpretability and transparency behind the random forest model predictions. Random forest is an ensemble of bootstrapped independent decision trees that are trained on subsets of input data to make predictions. Although random forest is a robust model that can overcome bias, its inherent complexity, and poor interpretability can make it challenging to apply in many application domains that require transparency and explainability in the model's predictions. This lack of transparency in the decision-making process can prevent users from analyzing what makes the model arrive at a specific prediction. The paper presents a visual analytic application to overcome transparency challenges by providing a clear structure of individual decision trees and hierarchical relationships between features. This allows users to analyze latent information and instils trust in the random forest model. Additionally, statistical analysis of feature ranking agreement and prediction popularity reduces mental burden of the user. The paper includes two case studies to evaluate model's uncertainty, bias, and variances in predictions with explainability at local and global scales of decision paths. The visual analytics application provides a coordinated multiple-view system to instil trust in random forest models.

Chapter

Cognitive Internet of Everything (CIoE): State of the Art and Approaches

Featured 01 January 2019 Securing the Internet of Things Concepts Methodologies Tools and Applications
AuthorsJamnal GS, Liu X, Fan L, Ramachandran M

In today’s world, we are living in busy metropolitan cities and want our homes to be ambient intelligent enough towards our cognitive requirements for assisted living in smart space environment and an excellent smart home control system should not rely on the users’ instructions (Wanglei, 2015). The ambient intelligence is a sensational new information technology paradigm in which people are empowered for assisted living through multiple IoTs sensors environment that are aware of inhabitant presence and context and highly sensitive, adaptive and responsive to their needs. A noble ambient intelligent environment are characterized by their ubiquity, transparency and intelligence which seamlessly integrated into the background and invisible to surrounded users/inhabitant. Cognitive IoE (Internet of Everything) is a new type of pervasive computing. As the ambient smart home is into research only from a couple of years, many research outcomes are lacking potentials in ambient intelligence and need to be more dug around for better outcomes. As a result, an effective architecture of CIoE for ambient intelligent space is missing in other researcher’s work. An unsupervised and supervised methods of machine learning can be applied in order to classify the varied and complex user activities. In the first step, by using fuzzy set theory, the input dataset value can be fuzzified to obtain degree of membership for context from the physical layer. In the second step, using K-pattern clustering algorithms to discover pattern clusters and make dynamic rules based on identified patterns. This chapter provides an overview, critical evaluation of approaches and research directions to CIoE.

Chapter

Cognitive Internet of Everything (CIoE)

Featured 2017 Advances in Wireless Technologies and Telecommunication IGI Global
AuthorsJamnal GS, Liu X, Fan L, Ramachandran M

In today's world, we are living in busy metropolitan cities and want our homes to be ambient intelligent enough towards our cognitive requirements for assisted living in smart space environment and an excellent smart home control system should not rely on the users' instructions (Wanglei, 2015). The ambient intelligence is a sensational new information technology paradigm in which people are empowered for assisted living through multiple IoTs sensors environment that are aware of inhabitant presence and context and highly sensitive, adaptive and responsive to their needs. A noble ambient intelligent environment are characterized by their ubiquity, transparency and intelligence which seamlessly integrated into the background and invisible to surrounded users/inhabitant. Cognitive IoE (Internet of Everything) is a new type of pervasive computing. As the ambient smart home is into research only from a couple of years, many research outcomes are lacking potentials in ambient intelligence and need to be more dug around for better outcomes. As a result, an effective architecture of CIoE for ambient intelligent space is missing in other researcher's work. An unsupervised and supervised methods of machine learning can be applied in order to classify the varied and complex user activities. In the first step, by using fuzzy set theory, the input dataset value can be fuzzified to obtain degree of membership for context from the physical layer. In the second step, using K-pattern clustering algorithms to discover pattern clusters and make dynamic rules based on identified patterns. This chapter provides an overview, critical evaluation of approaches and research directions to CIoE.

Conference Proceeding (with ISSN)
Developing reusable.NET software components
Featured 01 January 2014 2014 Science and Information Conference (SAI) Proceedings of 2014 Science and Information Conference, SAI 2014 IEEE
AuthorsRamachandran M, Jamnal GS

© 2014 The Science and Information (SAI) Organization. Software Development with reuse and for reuse is the foundation of CBSE (Component based software engineering) which allow faster development at lower cost and better usability. A reusable software component works as a plug and play device, which abstract the software complexity and increase performance. Software reuse guidelines have been addressing the issue of capturing best practices, for a long while software industry has collected the enormous wealth of knowledge, experience, domain expertise, design principals & heuristics, hypothesis, algorithms, and experimental results. However, there is no rock solid and mature software component development guidelines defined for the current technologies such as.NET. This paper presents reuse guidelines based framework (known as.NET Reuse Guider) for guidelines based component development for reuse in.NET family. We have demonstrated our approach by designing a binary component as part of development for reuse based on our own.NET Reuse Guider framework. This paper also provides a number reuse analysis and metrics and a prototype component guider tool which sits on top of the.NET architecture with built-in software development & reuse knowledge.

Current teaching

  • Advanced Machine Learning (BSc)
  • Intelligent Systems and Machine Learning (MSc)
  • Programming for Data Science (BSc)
  • Team Project Data Science (BSc)
  • Machine Learning Techniques (BSc)
  • Data Analytics and Visualization (MSc)
  • MSc Supervision Dissertation/Projects
  • BSc Supervision Production Projects