Tatiana Kalganova

Ayman Elhalwagy, Tatiana Kalganova

Deep learning techniques have recently shown promise in the field of anomaly detection, providing a flexible and effective method of modelling systems in comparison to traditional statistical modelling and signal processing-based methods. However, there are a few well publicised issues Neural Networks (NN)s face such as generalisation ability, requiring large volumes of labelled data to be able to train effectively and understanding spatial context in data. This paper introduces a novel NN architecture which hybridises the Long-Short-Term-Memory (LSTM) and Capsule Networks into a single network in a branched input Autoencoder architecture for use on multivariate time series data. The proposed method uses an unsupervised learning technique to overcome the issues with finding large volumes of labelled training data. Experimental results show that without hyperparameter optimisation, using Capsules significantly reduces overfitting and improves the training efficiency. Additionally, results also show that the branched input models can learn multivariate data more consistently with or without Capsules in comparison to the non-branched input models. The proposed model architecture was also tested on an open-source benchmark, where it achieved state-of-the-art performance in outlier detection, and overall performs best over the metrics tested in comparison to current state-of-the art methods.

Ben Malin, Tatiana Kalganova, Nikoloas Boulgouris

This review examines the means with which faithfulness has been evaluated across open-ended summarization, question-answering and machine translation tasks. We find that the use of LLMs as a faithfulness evaluator is commonly the metric that is most highly correlated with human judgement. The means with which other studies have mitigated hallucinations is discussed, with both retrieval augmented generation (RAG) and prompting framework approaches having been linked with superior faithfulness, whilst other recommendations for mitigation are provided. Research into faithfulness is integral to the continued widespread use of LLMs, as unfaithful responses can pose major risks to many areas whereby LLMs would otherwise be suitable. Furthermore, evaluating open-ended generation provides a more comprehensive measure of LLM performance than commonly used multiple-choice benchmarking, which can help in advancing the trust that can be placed within LLMs.

Ben Malin, Tatiana Kalganova, Nikolaos Boulgouris

We present a methodology for improving the accuracy of faithfulness evaluation in Large Language Models (LLMs). The proposed methodology is based on the combination of elementary faithfulness metrics into a combined (fused) metric, for the purpose of improving the faithfulness of LLM outputs. The proposed strategy for metric fusion deploys a tree-based model to identify the importance of each metric, which is driven by the integration of human judgements evaluating the faithfulness of LLM responses. This fused metric is demonstrated to correlate more strongly with human judgements across all tested domains for faithfulness. Improving the ability to evaluate the faithfulness of LLMs, allows for greater confidence to be placed within models, allowing for their implementation in a greater diversity of scenarios. Additionally, we homogenise a collection of datasets across question answering and dialogue-based domains and implement human judgements and LLM responses within this dataset, allowing for the reproduction and trialling of faithfulness evaluation across domains.

Sara Alaswad, Tatiana Kalganova, Wasan Awad

As Artificial Intelligence (AI), particularly Large Language Models (LLMs), becomes increasingly embedded in education systems worldwide, ensuring their ethical, legal, and contextually appropriate deployment has become a critical policy concern. This paper offers a comparative analysis of AI-related regulatory and ethical frameworks across key global regions, including the European Union, United Kingdom, United States, China, and Gulf Cooperation Council (GCC) countries. It maps how core trustworthiness principles, such as transparency, fairness, accountability, data privacy, and human oversight are embedded in regional legislation and AI governance structures. Special emphasis is placed on the evolving landscape in the GCC, where countries are rapidly advancing national AI strategies and education-sector innovation. To support this development, the paper introduces a Compliance-Centered AI Governance Framework tailored to the GCC context. This includes a tiered typology and institutional checklist designed to help regulators, educators, and developers align AI adoption with both international norms and local values. By synthesizing global best practices with region-specific challenges, the paper contributes practical guidance for building legally sound, ethically grounded, and culturally sensitive AI systems in education. These insights are intended to inform future regulatory harmonization and promote responsible AI integration across diverse educational environments.

Ubada El Joulani, Tatiana Kalganova, Stergios-Aristoteles Mitoulis et al.

Critical infrastructure, such as transport networks, underpins economic growth by enabling mobility and trade. However, ageing assets, climate change impacts (e.g., extreme weather, rising sea levels), and hybrid threats ranging from natural disasters to cyber attacks and conflicts pose growing risks to their resilience and functionality. This review paper explores how emerging digital technologies, specifically Artificial Intelligence (AI), can enhance damage assessment and monitoring of transport infrastructure. A systematic literature review examines existing AI models and datasets for assessing damage in roads, bridges, and other critical infrastructure impacted by natural disasters. Special focus is given to the unique challenges and opportunities associated with bridge damage detection due to their structural complexity and critical role in connectivity. The integration of SAR (Synthetic Aperture Radar) data with AI models is also discussed, with the review revealing a critical research gap: a scarcity of studies applying AI models to SAR data for comprehensive bridge damage assessment. Therefore, this review aims to identify the research gaps and provide foundations for AI-driven solutions for assessing and monitoring critical transport infrastructures.

Ayman Elhalwagy, Tatiana Kalganova

The generalisation of Neural Networks (NN) to multiple datasets is often overlooked in literature due to NNs typically being optimised for specific data sources. This becomes especially challenging in time-series-based multi-dataset models due to difficulties in fusing sequential data from different sensors and collection specifications. In a commercial environment, however, generalisation can effectively utilise available data and computational power, which is essential in the context of Green AI, the sustainable development of AI models. This paper introduces "Dataset Fusion," a novel dataset composition algorithm for fusing periodic signals from multiple homogeneous datasets into a single dataset while retaining unique features for generalised anomaly detection. The proposed approach, tested on a case study of 3-phase current data from 2 different homogeneous Induction Motor (IM) fault datasets using an unsupervised LSTMCaps NN, significantly outperforms conventional training approaches with an Average F1 score of 0.879 and effectively generalises across all datasets. The proposed approach was also tested with varying percentages of the training data, in line with the principles of Green AI. Results show that using only 6.25\% of the training data, translating to a 93.7\% reduction in computational power, results in a mere 4.04\% decrease in performance, demonstrating the advantages of the proposed approach in terms of both performance and computational efficiency. Moreover, the algorithm's effectiveness under non-ideal conditions highlights its potential for practical use in real-world applications.

Adam Byerly, Tatiana Kalganova

We provide a definition for class density that can be used to measure the aggregate similarity of the samples within each of the classes in a high-dimensional, unstructured dataset. We then put forth several candidate methods for calculating class density and analyze the correlation between the values each method produces with the corresponding individual class test accuracies achieved on a trained model. Additionally, we propose a definition for dataset quality for high-dimensional, unstructured data and show that those datasets that met a certain quality threshold (experimentally demonstrated to be > 10 for the datasets studied) were candidates for eliding redundant data based on the individual class densities.

Adam Byerly, Tatiana Kalganova

We show that, for each of five datasets of increasing complexity, certain training samples are more informative of class membership than others. These samples can be identified a priori to training by analyzing their position in reduced dimensional space relative to the classes' centroids. Specifically, we demonstrate that samples nearer the classes' centroids are less informative than those that are furthest from it. For all five datasets, we show that there is no statistically significant difference between training on the entire training set and when excluding up to 2% of the data nearest to each class's centroid.

Adam Byerly, Tatiana Kalganova, Anthony J. Grichnik

We present a dataset consisting of high-resolution images of 13 micro-PCBs captured in various rotations and perspectives relative to the camera, with each sample labeled for PCB type, rotation category, and perspective categories. We then present the design and results of experimentation on combinations of rotations and perspectives used during training and the resulting impact on test accuracy. We then show when and how well data augmentation techniques are capable of simulating rotations vs. perspectives not present in the training data. We perform all experiments using CNNs with and without homogeneous vector capsules (HVCs) and investigate and show the capsules' ability to better encode the equivariance of the sub-components of the micro-PCBs. The results of our experiments lead us to conclude that training a neural network equipped with HVCs, capable of modeling equivariance among sub-components, coupled with training on a diversity of perspectives, achieves the greatest classification accuracy on micro-PCB data.

Ivars Dzalbs, Tatiana Kalganova

The Multi-Depot Vehicle Routing Problem (MDVRP) is a real-world model of the simplistic Vehicle Routing Problem (VRP) that considers how to satisfy multiple customer demands from numerous depots. This paper introduces a hybrid 2-stage approach based on two population-based algorithms - Ant Colony Optimization (ACO) that mimics ant behaviour in nature and the Imperialist Competitive Algorithm (ICA) that is based on geopolitical relationships between countries. In the proposed hybrid algorithm, ICA is responsible for customer assignment to the depots while ACO is routing and sequencing the customers. The algorithm is compared to non-hybrid ACO and ICA as well as four other state-of-the-art methods across 23 common Cordreaus benchmark instances. Results show clear improvement over simple ACO and ICA and demonstrate very competitive results when compared to other rival algorithms.

Ivars Dzalbs, Tatiana Kalganova, Ian Dear

The multidimensional knapsack problem is a well-known constrained optimization problem with many real-world engineering applications. In order to solve this NP-hard problem, a new modified Imperialist Competitive Algorithm with Constrained Assimilation (ICAwICA) is presented. The proposed algorithm introduces the concept of colony independence, a free will to choose between classical ICA assimilation to empires imperialist or any other imperialist in the population. Furthermore, a constrained assimilation process has been implemented that combines classical ICA assimilation and revolution operators, while maintaining population diversity. This work investigates the performance of the proposed algorithm across 101 Multidimensional Knapsack Problem (MKP) benchmark instances. Experimental results show that the algorithm is able to obtain an optimal solution in all small instances and presents very competitive results for large MKP instances.

Jonas Skackauskas, Tatiana Kalganova, Ian Dear et al.

This paper proposes an extension method for Ant Colony Optimization (ACO) algorithm called Dynamic Impact. Dynamic Impact is designed to solve challenging optimization problems that has nonlinear relationship between resource consumption and fitness in relation to other part of the optimized solution. This proposed method is tested against complex real-world Microchip Manufacturing Plant Production Floor Optimization (MMPPFO) problem, as well as theoretical benchmark Multi-Dimensional Knapsack problem (MKP). MMPPFO is a non-trivial optimization problem, due the nature of solution fitness value dependence on collection of wafer-lots without prioritization of any individual wafer-lot. Using Dynamic Impact on single objective optimization fitness value is improved by 33.2%. Furthermore, MKP benchmark instances of small complexity have been solved to 100% success rate where high degree of solution sparseness is observed, and large instances have showed average gap improved by 4.26 times. Algorithm implementation demonstrated superior performance across small and large datasets and sparse optimization problems.

Adam Byerly, Tatiana Kalganova, Ian Dear

Most capsule network designs rely on traditional matrix multiplication between capsule layers and computationally expensive routing mechanisms to deal with the capsule dimensional entanglement that the matrix multiplication introduces. By using Homogeneous Vector Capsules (HVCs), which use element-wise multiplication rather than matrix multiplication, the dimensions of the capsules remain unentangled. In this work, we study HVCs as applied to the highly structured MNIST dataset in order to produce a direct comparison to the capsule research direction of Geoffrey Hinton, et al. In our study, we show that a simple convolutional neural network using HVCs performs as well as the prior best performing capsule network on MNIST using 5.5x fewer parameters, 4x fewer training epochs, no reconstruction sub-network, and requiring no routing mechanism. The addition of multiple classification branches to the network establishes a new state of the art for the MNIST dataset with an accuracy of 99.87% for an ensemble of these models, as well as establishing a new state of the art for a single model (99.83% accurate).

Ivars Dzalbs, Tatiana Kalganova

Ant Colony algorithm has been applied to various optimization problems, however most of the previous work on scaling and parallelism focuses on Travelling Salesman Problems (TSPs). Although, useful for benchmarks and new idea comparison, the algorithmic dynamics does not always transfer to complex real-life problems, where additional meta-data is required during solution construction. This paper looks at real-life outbound supply chain problem using Ant Colony Optimization (ACO) and its scaling dynamics with two parallel ACO architectures - Independent Ant Colonies (IAC) and Parallel Ants (PA). Results showed that PA was able to reach a higher solution quality in fewer iterations as the number of parallel instances increased. Furthermore, speed performance was measured across three different hardware solutions - 16 core CPU, 68 core Xeon Phi and up to 4 Geforce GPUs. State of the art, ACO vectorization techniques such as SS-Roulette were implemented using C++ and CUDA. Although excellent for TSP, it was concluded that for the given supply chain problem GPUs are not suitable due to meta-data access footprint required. Furthermore, compared to their sequential counterpart, vectorized CPU AVX2 implementation achieved 25.4x speedup on CPU while Xeon Phi with its AVX512 instruction set reached 148x on PA with Vectorized (PAwV). PAwV is therefore able to scale at least up to 1024 parallel instances on the supply chain network problem solved.

Adam Byerly, Tatiana Kalganova

Capsules are the name given by Geoffrey Hinton to vector-valued neurons. Neural networks traditionally produce a scalar value for an activated neuron. Capsules, on the other hand, produce a vector of values, which Hinton argues correspond to a single, composite feature wherein the values of the components of the vectors indicate properties of the feature such as transformation or contrast. We present a new way of parameterizing and training capsules that we refer to as homogeneous vector capsules (HVCs). We demonstrate, experimentally, that altering a convolutional neural network (CNN) to use HVCs can achieve superior classification accuracy without increasing the number of parameters or operations in its architecture as compared to a CNN using a single final fully connected layer. Additionally, the introduction of HVCs enables the use of adaptive gradient descent, reducing the dependence a model's achievable accuracy has on the finely tuned hyperparameters of a non-adaptive optimizer. We demonstrate our method and results using two neural network architectures. First, a very simple monolithic CNN that when using HVCs achieved a 63% improvement in top-1 classification accuracy and a 35% improvement in top-5 classification accuracy over the baseline architecture. Second, with the CNN architecture referred to as Inception v3 that achieved similar accuracies both with and without HVCs. Additionally, the simple monolithic CNN when using HVCs showed no overfitting after more than 300 epochs whereas the baseline showed overfitting after 30 epochs. We use the ImageNet ILSVRC 2012 classification challenge dataset with both networks.