Computing and Information Systems - Research Publications
Permanent URI for this collection
Search Results
1 - 10 of 15
-
ItemRun or Pat: Using Deep Learning to Classify the Species Type and Emotion of Pets(EEE, 2021-01-01)Deep learning has been applied in many contexts. In this paper we present a novel application area: to detect the species type and emotion of pets with focus on a diverse set of dog and cat collections comprising 52 dog and 23 cat species. Building on an extensive collection of labelled images with over 300 images per species type, we explore a range of deep learning models to develop a classifier for species type and their associated emotion. We outline the realization of the technical solution delivered through a mobile application (iPhone/Android) and present results based on feedback based on real world adoption and utilisation by the broader mobile application community.
-
ItemA hybrid mathematical modelling approach for energy generation from hazardous waste during the COVID-19 pandemic(Elsevier BV, 2021-09-15)The COVID-19 virus in a short time has caused a terrible crisis that has been spread around the world. This crisis has affected human life in several dimensions, one of which is a sharp increase in urban waste. This increase in waste volume during the pandemic, in addition to the intense increase in costs associated with the risks of virus contagion through infectious waste. In this study, a hybrid mathematical modelling approach including a Bi-level programming model for infectious waste management has been proposed. At the higher level of the model, government decisions regarding the total costs related to infectious waste must be minimized. At this level, the collected infectious waste is converted into energy, the revenue of which is returned to the system. The lower level relates to the risks of virus contagion through infectious waste, which can be catastrophic if ignored. This study has considered the low, medium, high and very high prevalence scenarios as key parameters for the production of waste. In addition, the uncertainty in citizens’ demand for waste collection was also included in the proposed model. The results showed that by energy production from waste during the COVID-19 pandemic, 34% of the total cost of collecting and transporting waste can be compensated. Finally, this paper obtained useful managerial insights using the data of Kermanshah city as a real case.
-
ItemPatient-Ventilator Asynchrony Detection via Similarity Search Methods(ACM Press, 2021)Patient-ventilator asynchrony (PVA) is a common cause of ventilation-related medical complications and are traditionally only able to be reliably identified by trained clinicians. The need for constant monitoring and limited access to trained experts are major challenges in managing PVA, both of which can potentially be solved by automating the detection process. In this research, we propose a new data-driven approach to PVA detection using several similarity and randomness measures, including how unusual a time window is in the series and randomness of the time window. We found that all these similarity or randomness measures can be estimated with variants of the highly efficient Matrix Profile (MP) algorithm, and that one base routine can be repeated to generate all the features used in classification. We show that MP-based features, when used in combination with basic statistical and spectral features, can achieve an F-2 score of over 0.9 for two classes of PVA events in a sample of participants with modete to high rate of PVA occurrence.
-
ItemPrimary care datasets for early lung cancer detection: an AI led approach(Springer, 2021)Cancer is one of the most common and serious medical conditions, with significant challenges in the detection of cancer originating from the non-specific nature of symptoms and very low prevalence. For general practitioners (GPs), this can be particularly important, as they are the primary contact for patients for most medical conditions. This places high significance on using the data available to a GP to design decision support tools that will aid GPs in detecting cancer as early as possible. With pathology data being one of the datasets available in the GP electronic medical record (EMR), our work targets this type of data in an attempt to incorporate an early cancer detection tool in existing GP practices. We focus on utilizing full blood count pathology results to design features that can be used in an early cancer detection model 3 to 6 months ahead of standard diagnosis. This research focuses initially on lung cancer but can be extended to other types of cancer. Additional challenges are present in this type of data due to the irregular and infrequent nature of doing pathology tests, which are also considered in designing the AI solution. Our findings demonstrate that hematological measures from pathology data are a suitable choice for a cancer detection tool that can deliver early cancer diagnosis up to 6 months ahead for up to 8 out of 10 patients, in a way that is easily incorporated in current GP practice.
-
ItemConstructing classifiers for imbalanced data using diversity optimisation(ELSEVIER SCIENCE INC, 2021-07)Imbalanced data is challenging in classification. This paper proposes a new approach to address imbalanced data by adopting diversity optimisation to generate synthetic instances for over-sampling the minority class. Diversity optimisation assures that the generated instances are close to the minority group but not identical. It also ensures the optimal spread of the generated instances in the space. We develop two formulations named as Diversity-based Average Distance Over-sampling (DADO) and Diversity-based Instance-Wise Over-sampling (DIWO). We evaluate the proposed formulations’ performance by designing experiments using both synthetic and real data with unbalanced classes. We examine the performance through area under curve (AUC), F1-score and g-mean measures in comparison with comparable synthetic over-sampling methods. We compare the methods using the obtained measures of the best performing classifier and statistical testing of all combinations over three imbalance levels using seven classifiers. The results show that both proposed formulations perform competitive to improve the performance of classifiers, and DIWO outperforms other comparable methods. Both perform robust by reducing the classifiers’ variance. We discuss the strengths and limitations of these formulations using the real data examples, runtime complexity and sensitivity analysis. We also demonstrate the possibility of utilising DADO and DIWO for multi-class imbalanced data.
-
ItemA Review on Human-AI Interaction in Machine Learning and Insights for Medical Applications(MDPI, 2021-02)OBJECTIVE: To provide a human-Artificial Intelligence (AI) interaction review for Machine Learning (ML) applications to inform how to best combine both human domain expertise and computational power of ML methods. The review focuses on the medical field, as the medical ML application literature highlights a special necessity of medical experts collaborating with ML approaches. METHODS: A scoping literature review is performed on Scopus and Google Scholar using the terms "human in the loop", "human in the loop machine learning", and "interactive machine learning". Peer-reviewed papers published from 2015 to 2020 are included in our review. RESULTS: We design four questions to investigate and describe human-AI interaction in ML applications. These questions are "Why should humans be in the loop?", "Where does human-AI interaction occur in the ML processes?", "Who are the humans in the loop?", and "How do humans interact with ML in Human-In-the-Loop ML (HILML)?". To answer the first question, we describe three main reasons regarding the importance of human involvement in ML applications. To address the second question, human-AI interaction is investigated in three main algorithmic stages: 1. data producing and pre-processing; 2. ML modelling; and 3. ML evaluation and refinement. The importance of the expertise level of the humans in human-AI interaction is described to answer the third question. The number of human interactions in HILML is grouped into three categories to address the fourth question. We conclude the paper by offering a discussion on open opportunities for future research in HILML.
-
ItemOn the Importance of Diversity in Re-Sampling for Imbalanced Data and Rare Events in Mortality Risk Models(ACM, 2021)Surgical risk increases significantly when patients present with comorbid conditions. This has resulted in the creation of numerous risk stratification tools with the objective of formulating associated surgical risk to assist both surgeons and patients in decision-making. The Surgical Outcome Risk Tool (SORT) is one of the tools developed to predict mortality risk throughout the entire perioperative period for major elective in-patient surgeries in the UK. In this study, we enhance the original SORT prediction model (UK SORT) by addressing the class imbalance within the dataset. Our proposed method investigates the application of diversity-based selection on top of common re-sampling techniques to enhance the classifier's capability in detecting minority (ĝ€mortality') events. Diversity amongst training datasets is an essential factor in ensuring re-sampled data keeps an accurate depiction of the minority/majority class region, thereby solving the generalization problem of mainstream sampling approaches. We incorporate the use of the Solow-Polasky measure as a drop-in functionality to evaluate diversity, with the addition of greedy algorithms to identify and discard subsets that share the most similarity. Additionally, through empirical experiments, we prove that the performance of the classifier trained over diversity-based dataset outperforms the original classifier over ten external datasets. Our diversity-based re-sampling method elevates the performance of the UK SORT algorithm by 1.4%.
-
ItemAn interval-based aggregation approach based on Bagging and Interval Agreement Approach in ensemble learning(IEEE, 2020-12-01)The main aim in ensemble learning is using multiple classifiers rather than one classifier to aggregate classifiers' outputs for more accurate classification. Generating an ensemble classifier generally is composed of three steps: selecting a base classifier, applying a sampling strategy to generate different simple classifiers and aggregating the classifiers' outputs. This paper focuses on the classifiers' outputs aggregation step in ensemble learning and presents a new interval-based aggregation approach using Bagging and Interval Agreement Approach (IAA). Bagging is an ensemble learning approach to generate ensembles of classifiers by manipulation of the training data set and IAA is an aggregation approach in decision making which was introduced to combine decision makers' opinions when they present their opinions by intervals. In this paper, we use Bagging approach to generate uncertainty intervals for simple classifiers in ensemble learning and implement IAA to aggregate the intervals with the aim of capturing uncertainty. In fact, we design some experiments to encourage researchers to use interval modeling in ensemble learning because it preserves more uncertainty and leads to more accurate classification. We compare the results of implementing the proposed method to the majority vote, as the most commonly used aggregation function in ensemble learning, for 10 medical data sets. The results show the better performance of the proposed interval-based aggregation approach in binary classification when it comes to ensemble learning. The Bayesian signed-rank test confirms the competency of our proposed approach in this research.
-
ItemTransfer Learning to Enhance Amenorrhea Status Prediction in Cancer and Fertility Data with Missing Values(Productivity Press (Taylor & Francis), 2020)
-
ItemHigher order hesitant fuzzy choquet integral operator and its application to multiple criteria decision making(University of Sistan and Baluchestan, 2021-01-01)Generally, the criteria involved in a decision making problem are interactive or inter- dependent, and therefore aggregating them by the use of traditional operators which are based on additive measures is not logical. This verifies that we have to implement fuzzy measures for modelling the interaction phenomena among the criteria. On the other hand, based on the recent extension of hesitant fuzzy set, called higher order hesitant fuzzy set (HOHFS) which allows the membership of a given element to be defined in forms of several possible generalized types of fuzzy set, we encourage to propose the higher order hesitant fuzzy (HOHF) Choquet integral operator. This concept not only considers the importance of the higher order hesitant fuzzy arguments, but also it can reflect the correlations among those arguments. Then, a detailed discussion on the aggregation properties of the HOHF Choquet integral operator will be presented. To enhance the application of HOHF Choquet integral operator in decision making, we first assess the appropriate energy policy for the socio-economic development. Then, the efficiency of the proposed HOHF Choquet integral operator-based technique over a number of exiting techniques is further verified by employing another decision making problem associated with the technique of TODIM (an acronym in Portuguese of Interactive and Multicriteria Decision Making).