Engineering and Information Technology Collected Works - Research Publications
Permanent URI for this collection
Search Results
1 - 10 of 306
-
ItemProbabilistic hesitant fuzzy multiple criteria decision-making with triangular norm based similarity and entropy measures(Elsevier, 2024-06-01)Existing probabilistic hesitant fuzzy set (PHFS) measures are constructed using two information measures: hesitancy and unwrapped probabilities. We argue that unifying these semantic terms in PHFS information theory is not logical. We introduce a new class of information measures for PHFSs, which address the logical wrapping of hesitant fuzzy sets (HFS) and probability. We propose several similarity measures for these sets that use the Triangular norm operator. We consider the relationship between measures of entropy and similarity and represent the axiomatic definition of PHFS entropy measures. Finally, we use case studies to demonstrate applications of these information measures. We describe two multiple-criteria decision-making algorithms. The last step is devoted to PHFS ranking procedures: one based on the score function of alternatives and the other based on the relative closeness of alternatives. This contribution describes new information measures and uses case studies to illustrate how they can be applied to decision-making processes.
-
ItemNo Preview AvailableEditorial: Special issue on operations research and machine learning(Taylor and Francis Group, 2024)Many machine learning techniques work through optimizing specific objective functions. Supervised learning techniques are to minimize the prediction error such as mean square error (MSE) and misclassification rate, or maximize the conditional likelihood, posterior probability, etc. Unsupervised learning techniques usually group instances into clusters in a way that instances within each group are optimally similar while they are distant from instances in other groups. In reinforcement learning, the goal of an agent is to maximize its cumulative reward. However, there is still room to exploit optimization and operations research (OR) in machine learning, and vice versa.
-
ItemOptimised deep k-nearest neighbour's based diabetic retinopathy diagnosis(ODeep-NN) using retinal images(SPRINGER, 2024-03-09)Diabetes mellitus has been regarded as one of the prime health issues in present days, which can often lead to diabetic retinopathy, a complication of the disease that affects the eyes, causing loss of vision. For precisely detecting the condition's existence, clinicians are required to recognise the presence of lesions in colour fundus images, making it an arduous and time-consuming task. To deal with this problem, a lot of work has been undertaken to develop deep learning-based computer-aided diagnosis systems that assist clinicians in making accurate diagnoses of the diseases in medical images. Contrariwise, the basic operations involved in deep learning models lead to the extraction of a bulky set of features, further taking a long period of training to predict the existence of the disease. For effective execution of these models, feature selection becomes an important task that aids in selecting the most appropriate features, with an aim to increase the classification accuracy. This research presents an optimised deep k-nearest neighbours'-based pipeline model in a bid to amalgamate the feature extraction capability of deep learning models with nature-inspired metaheuristic algorithms, further using k-nearest neighbour algorithm for classification. The proposed model attains an accuracy of 97.67 and 98.05% on two different datasets considered, outperforming Resnet50 and AlexNet deep learning models. Additionally, the experimental results also portray an analysis of five different nature-inspired metaheuristic algorithms, considered for feature selection on the basis of various evaluation parameters.
-
ItemCapturing prediction uncertainty in upstream cell culture models using conformal prediction and Gaussian processes(ML Research Press, 2023)This extended abstract compares the efficacy of Gaussian process and conformal XGBoost regressions in capturing prediction uncertainty in simulated and industrial cell culture data.
-
ItemDiagnostic Clinical Decision Support based on Deep Learning and Knowledge-based Systems for Psoriasis: From Diagnosis to Treatment Options(Elsevier, 2023-11)Psoriasis is an acute immuno-dermatological disease, affecting people of all ages, which significantly decreases quality of life. While the standard approach to identification and diagnosis of psoriasis is based on dermatologist decisions, various Deep Learning (DL) methods have been utilized to create Computer-Aided Diagnosis (CAD) systems to detect and classify psoriasis cases. In response to the knowledge gap of an existing practical and functional DL-based solution to psoriasis diagnosis, this study proposed an ensemble Convolutional Neural Network (CNN) model using Residual Network 50 Version 2 (ResNet50V2), ResNet101V2, and ResNet152V2 networks to create a CAD system for detecting and classifying psoriatic images. This ensemble model determines whether an input image is psoriatic using a binary classification procedure in the initial stage and classifies the psoriatic images into seven variants utilizing a multi-class classification. Furthermore, a treatment suggestion system was embedded within the diagnostic algorithm to suggest the best treatment options for psoriasis variants using a Multi-Criteria Decision Making (MCDM) method with the aim of reducing the disease symptoms in patients. A web-based Decision and Diagnostic Support System (D&DSS) is constructed to determine whether an input image is psoriatic, classify the psoriatic images into different variants, and accordingly recommend the best treatment options based on the observed disease symptoms in a patient. Nevertheless, the functionality and reliability of the proposed D&DSS are validated with high accuracy rates in both diagnostic and identification stages of the approach, which ratifies the practicality of this proposition.
-
ItemAn operational planning for emergency medical services considering the application of IoT(Springer, 2023)In the last two years, the worldwide outbreak of the COVID-19 pandemic and the resulting heavy casualties have highlighted the importance of further research in healthcare. In addition, the advent of new technologies such as the Internet of Things (IoT) and their applications in preventing and detecting casualty cases has attracted a lot of attention. The IoT is able to help organize medical services by collecting significant amounts of data and information. This paper proposes a novel mathematical model for Emergency Medical Services (EMS) using the IoT. The proposed model is designed in two phases. In the first phase, the data is collected by the IoT, and the demands for ambulances are categorized and prioritized. Then in the second phase, ambulances are allocated to demand areas (patients). Two main objectives of the proposed model are reducing total costs and the mortality risk due to lack of timely service. In addition, demand uncertainty for ambulances is considered with various scenarios at demand levels. Numerical experiments have been conducted on actual data from a case study in Kermanshah, Iran. Due to the NP-hard nature of the mathematical model, three meta-heuristic algorithms Multi-Objective Simulated Annealing (MOSA) algorithm and Multi-Objective Particle Swarm Optimization (MOPSO) algorithm, and L-MOPSO have been used to solve the proposed model on medium and large scales in addition to the exact solution method. The results show that the proposed model significantly reduces mortality risk, in addition to reducing total cost. Data analysis also led to useful managerial insights.
-
ItemAn Uncertainty-Accuracy-Based Score Function for Wrapper Methods in Feature Selection(IEEE, 2023-08-13)Feature Selection (FS) is an effective preprocessing method to deal with the curse of dimensionality in machine learning. Redundant features in datasets decrease the classification performance and increase the computational complexity. Wrapper methods are an important category of FS methods that evaluate various feature subsets and select the best one using performance measures related to a classifier. In these methods, the accuracy of classifiers is the most common performance measure for FS. Although the performance of classifiers depends on their uncertainty, this important criterion is neglected in these methods. In this paper, we present a new performance measure called Uncertainty-Accuracy-based Performance Measure for Feature Selection (UAPMFS) that uses an ensemble approach to measure both the accuracy and uncertainty of classifiers. UAPMFS uses bagging and uncertainty confusion matrix. This performance measure can be used in all wrapper methods to improve FS performance. We design two experiments to evaluate the performance of UAPMFS in wrapper methods. In experiments, we use the leave-one-variable-out strategy as the common strategy in wrapper methods to evaluate features. We also define a feature score function based on UAPMFS to rank and select features. In the first experiment, we investigate the importance of considering uncertainty in the FS process and show how neglecting uncertainty affects FS performance. In the second experiment, we compare the performance of the UAPMFS-based feature score function with the most common feature score functions for FS. Experimental results show the effectiveness of the proposed performance measure on different datasets.
-
ItemNo Preview AvailableA decision modeling approach for smart e-tourism data management applications based on spherical fuzzy rough environment (vol 143, 110297, 2023)(ELSEVIER, 2023-12)The authors regret the inadvertent omission of second affiliation of author A.S. Albahri. Affiliation is presented as below: Department of Computer Technology Engineering, College of Information Technology, Imam Ja'afar Al-Sadiq University, Baghdad, Iraq. The authors would like to apologise for any inconvenience caused.
-
ItemA Diversity-Based Synthetic Oversampling Using Clustering for Handling Extreme Imbalance(Springer, 2023)Imbalanced data are typically observed in many real-life classification problems. However, mainstream machine learning algorithms are mostly designed with the underlying assumption of a relatively well-balanced distribution of classes. The mismatch between reality and algorithm assumption results in a deterioration of classification performance. One form of approach to address this problem is through re-sampling methods, although its effectiveness is limited; most re-sampling methods fail to consider the distribution of minority and majority instances and the diversity within synthetically generated data. Diversity becomes increasingly important when minority data becomes more sparse, as each data point becomes more valuable. They should all be considered during the generation process instead of being regarded as noise. In this paper, we propose a cluster-based diversity re-sampling method, combined with NOAH algorithm. Neighbourhood-based Clustering Diversity Over-sampling (NBCDO) is introduced with the aim to complement our previous cluster-based diversity algorithm Density-based Clustering Diversity Over-sampling (DBCDO). It first uses a neighbourhood-based clustering algorithm to consider the distribution of both minority and majority class instances, before applying NOAH algorithm to encourage diversity optimisation during the generation of synthetic instances. We demonstrate the implementation of both cluster-based diversity methods by conducting experiments over 10 real-life datasets with ≤ 5% imbalance ratio and show that our proposed cluster-based diversity algorithm (NBCDO, DBCDO) brings performance improvements over its comparable methods (DB-SMOTE, MAHAKIL, KMEANS-SMOTE, MC-SMOTE).
-
ItemA Lightweight Window Portion-Based Multiple Imputation for Extreme Missing Gaps in IoT Systems(Institute of Electrical and Electronics Engineers (IEEE), 2023)Intelligent techniques, including artificial intelligence and deep learning, normally perform on complete data without missing data. Multiple imputation is indispensable for addressing missing data resulting in unbiased estimates and dealing with uncertainty by providing more valid results. Most state-of-the-art techniques focus on high missing rates (around 50%-60%) and short missing gaps, while imputation for extreme missing gaps and missing rates is an important challenge for multivariate time-series data generated through the Internet of Things (IoT). Hence, we propose a Lightweight Window Portion-based Multiple Imputation (LWPMI) based on multivariate variables, correlation, data fusion, regression, and multiple imputations. We conduct extensive experiments by generating extreme missing gaps and high missing rates ranging from 10% to 90% on data generated by sensors. We also investigate different sets of feature to examine how LWPMI works when features have high, weak, or a mixture of high and weak correlation. All the obtained results prove LWPMI outperforms baseline techniques in preserving pattern, structure, and trend in both 90% extreme missing gap and missing rates.