An integrated method comprising DEA and machine learning for risk management is proposed in this paper. Initially, in the process of risk assessment, the DEA cross-efficiency method is used to ...evaluate a set of risk factors obtained from the FMEA. This FMEA-DEA cross-efficiency method not only overcomes some drawbacks of FMEA, but also eliminates several limitations of DEA to offer a high discrimination capability of decision units. For risk treatment and monitoring processes, an ML mechanism is utilized to predict the degree of remaining risk depending on simulated data corresponding to the risk treatment scenario. Prediction using ML is more accurate since the predictive power of this model is better than that of DEA which potentially contains errors. The motivation for this study is that the combination of the DEA and ML approaches gives a flexible and realistic choice in risk management. Based on a case study of logistics business, the results ascertain that the short-term and urgent solutions in service cost and performance are necessary to sustainable logistics operations under the COVID-19 pandemic. The prediction findings show that the risk of skilled personnel is the next concern once the service cost and performance strategies have been prioritised. This approach allow decision-makers to assess the risk level for handling forthcoming events in unusual conditions. It also serves as a useful knowledge repository such that appropriate risk mitigation strategies can be planned and monitored. The outcome of our empirical evaluation indicates that the proposed approach contributes towards robustness in sustainable business operations.
This handbook presents a useful collection of AI techniques, as well as other complementary methodologies, useful for the design and development of intelligent decision support systems. The book ...includes a variety of real-world problems in different domains.
Purpose - To propose a generic method to simplify the fuzzy logic-based failure mode and effect analysis (FMEA) methodology by reducing the number of rules that needs to be provided by FMEA users for ...the fuzzy risk priority number (RPN) modeling process.Design methodology approach - The fuzzy RPN approach typically requires a large number of rules, and it is a tedious task to obtain a full set of rules. The larger the number of rules provided by the users, the better the prediction accuracy of the fuzzy RPN model. As the number of rules required increases, ease of use of the model decreases since the users have to provide a lot of information rules for the modeling process. A guided rules reduction system (GRRS) is thus proposed to regulate the number of rules required during the fuzzy RPN modeling process. The effectiveness of the proposed GRRS is investigated using three real-world case studies in a semiconductor manufacturing process.Findings - In this paper, we argued that not all the rules are actually required in the fuzzy RPN model. Eliminating some of the rules does not necessarily lead to a significant change in the model output. However, some of the rules are vitally important and cannot be ignored. The proposed GRRS is able to provide guidelines to the users which rules are required and which can be eliminated. By employing the GRRS, the users do not need to provide all the rules, but only the important ones when constructing the fuzzy RPN model. The results obtained from the case studies demonstrate that the proposed GRRS is able to reduce the number of rules required and, at the same time, to maintain the ability of the Fuzzy RPN model to produce predictions that are in agreement with experts' knowledge in risk evaluation, ranking, and prioritization tasks.Research limitations implications - The proposed GRRS is limited to FMEA systems that utilize the fuzzy RPN model.Practical implications - The proposed GRRS is able to simplify the fuzzy logic-based FMEA methodology and make it possible to be implemented in real environments.Originality value - The value of the current paper is on the proposal of a GRRS for rule reduction to enhance the practical use of the fuzzy RPN model in real environments.
In this paper, a novel evolutionary algorithm is applied to tackle job-shop scheduling tasks in manufacturing environments. Specifically, a modified micro genetic algorithm (MmGA) is used as the ...building block to formulate an ensemble model to undertake multi-objective optimisation problems in job-shop scheduling. The MmGA ensemble is able to approximate the optimal solution under the Pareto optimality principle. To evaluate the effectiveness of the MmGA ensemble, a case study based on real requirements is conducted. The results positively indicate the effectiveness of the MmGA ensemble in undertaking job-shop scheduling problems.
This study aims to use the fractional Fourier transform for analyzing various types of Hyers–Ulam stability pertaining to the linear fractional order differential equation with Atangana and Baleanu ...fractional derivative. Specifically, we establish the Hyers–Ulam–Rassias stability results and examine their existence and uniqueness for solving nonlinear problems. Simulation examples are presented to validate the results.
•A hybrid intelligent system is proposed for medical data classification tasks.•The proposed system is able to learn incrementally and explain its predictions.•Benchmark medical data sets are used to ...evaluate the effectiveness of the system.•The results ascertain the usefulness of the system for medical decision support.•The knowledge base is presented as a decision tree for interpretation by users.
In this paper, a hybrid intelligent system that consists of the Fuzzy Min–Max neural network, the Classification and Regression Tree, and the Random Forest model is proposed, and its efficacy as a decision support tool for medical data classification is examined. The hybrid intelligent system aims to exploit the advantages of the constituent models and, at the same time, alleviate their limitations. It is able to learn incrementally from data samples (owing to Fuzzy Min–Max neural network), explain its predicted outputs (owing to the Classification and Regression Tree), and achieve high classification performances (owing to Random Forest). To evaluate the effectiveness of the hybrid intelligent system, three benchmark medical data sets, viz., Breast Cancer Wisconsin, Pima Indians Diabetes, and Liver Disorders from the UCI Repository of Machine Learning, are used for evaluation. A number of useful performance metrics in medical applications which include accuracy, sensitivity, specificity, as well as the area under the Receiver Operating Characteristic curve are computed. The results are analyzed and compared with those from other methods published in the literature. The experimental outcomes positively demonstrate that the hybrid intelligent system is effective in undertaking medical data classification tasks. More importantly, the hybrid intelligent system not only is able to produce good results but also to elucidate its knowledge base with a decision tree. As a result, domain users (i.e., medical practitioners) are able to comprehend the prediction given by the hybrid intelligent system; hence accepting its role as a useful medical decision support tool.
A hybrid neural network comprising fuzzy ARTMAP and fuzzy c-means clustering is proposed for pattern classification with incomplete training and test data. Two benchmark problems and a real medical ...pattern classification tasks are employed to evaluate the effectiveness of the hybrid network. The results are analyzed and compared with those from other methods.
•The proposed approach predicts pedestrian walking path within built environments.•Including environmental effects on walking path under normal conditions.•Considering diverse and uncertain aspects ...of perception from surroundings.•Employing fuzzy logic technique to predict pedestrians walking trajectories.•Trajectory datasets were collected using a motion-tracking system.
This paper investigates the effectiveness of a fuzzy logic-based approach to modelling of pedestrian steering behaviours through built environments under normal, non-panic conditions. The proposed approach considers the effects of surrounding objects on a pedestrian’s walking path. The developed model associates vague and fuzzy characteristics of a pedestrian’s environmental perceptions with his/her steering behaviours. This is a challenging problem, as a pedestrian’s perceptions in a specific environment vary from one individual to another, and are subjective in nature. To formulate a realistic model with a high degree of fidelity, a number of factors that include variable pedestrian speeds and step-lengths are incorporated. To validate the proposed fuzzy logic model, a hallway in an indoor environment is used as a case study. A dynamic contour map that represents the effects of physical perceptible objects within the pedestrian’s field of view is established, and the proposed model is deployed to yield the predicted walking path of a pedestrian through a corridor. The environmental stimuli are modelled as attractive or repulsive socio-psychological forces that affect the pedestrian’s decision in choosing the next step position of the walking trajectory. A data set containing real walking trajectories is collected using appropriate motion tracking devices for evaluation of the proposed model. Four different scenarios are used for evaluation. The predicted walking paths from the fuzzy logic model and the real ones (collected from real experiments) are analysed and compared. The results in terms of statistical error measurements show improved performance in the scenario with variable speeds and step-lengths. The outcomes positively demonstrate the usefulness of the proposed approach in modelling pedestrian steering behaviours.
In this research, we propose a variant of the Bare-Bones Particle Swarm Optimization (BBPSO) algorithm for hyper-parameter selection and deep architecture generation for image, audio and video ...classification tasks. Since the search process of the original BBPSO model is guided by a single leader and the particles’ personal best experiences, there is a lack of interactions pertaining to the neighbouring elite solutions. To overcome this limitation, we propose a versatile search process for a modified BBPSO model that incorporates a number of effective components and operations. These include the neighbouring and global best signals, search actions with Cauchy/Levy scale factors, sub-dimension operations guided by the local and global elite solutions, and a Levy-driven local search mechanism. Moreover, root-finding algorithms are employed which use informative mathematical principles to estimate new root offspring for leader/particle enhancement. A reinforcement learning algorithm is subsequently used to identify the optimal sequential deployment of these numerical analysis methods to increase robustness. Several medical imaging data sets, i.e., ISIC 2017, PH2 and Dermofit skin lesion databases, the ALL-IDB2 microscopic blood image data set, the MURA musculoskeletal radiographic database, the CK + facial expression data set, as well as the Coswara respiratory audio data set and UCF101 video action data set, are employed for evaluation. The proposed BBPSO-optimized Convolutional Neural Network (CNN), bidirectional Long Short-Term Memory (BiLSTM) with attention mechanism, and CNN-BiLSTM models outperform those devised by other PSO and BBPSO variants, as well as state-of-the-art existing studies, significantly, for image, audio respiratory abnormality and realistic video action recognition.
This paper proposes a facial expression recognition system using evolutionary particle swarm optimization (PSO)-based feature optimization. The system first employs modified local binary patterns, ...which conduct horizontal and vertical neighborhood pixel comparison, to generate a discriminative initial facial representation. Then, a PSO variant embedded with the concept of a micro genetic algorithm (mGA), called mGA-embedded PSO, is proposed to perform feature optimization. It incorporates a nonreplaceable memory, a small-population secondary swarm, a new velocity updating strategy, a subdimension-based in-depth local facial feature search, and a cooperation of local exploitation and global exploration search mechanism to mitigate the premature convergence problem of conventional PSO. Multiple classifiers are used for recognizing seven facial expressions. Based on a comprehensive study using within- and cross-domain images from the extended Cohn Kanade and MMI benchmark databases, respectively, the empirical results indicate that our proposed system outperforms other state-of-the-art PSO variants, conventional PSO, classical GA, and other related facial expression recognition models reported in the literature by a significant margin.