Search

Feature selection is the process of picking the most effective feature among a considerable number of features in the dataset. However, choosing the best subset that gives a higher performance in classification is challenging. This study constructed and validated multiple metaheuristic algorithms to optimize Machine Learning (ML) models in diagnosing Alzheimer’s. This study aims to classify Cognitively Normal (CN), Mild Cognitive Impairment (MCI), and Alzheimer’s by selecting the best features. The features include Freesurfer features extracted from Magnetic Resonance Imaging (MRI) images and clinical data. We have used well-known ML algorithms for classifying, and after that, we used multiple metaheuristic methods for feature selection and optimizing the objective function of the classification. We considered the objective function a macro-average F1 score because of the imbalanced data. Our procedure not only reduces the irreverent features but also increases the classification performance. Results showed that metaheuristic algorithms could improve the performance of ML methods in diagnosing Alzheimer’s by 20%. We found that classification performance can be significantly enhanced by using appropriate metaheuristic algorithms. Metaheuristic algorithms can help find the best features for medical classification problems, especially Alzheimer’s.

A cloud manufacturing (CMfg) system is presented as a novel service- and customer-oriented manufacturing paradigm that integrates the distributed manufacturing enterprises to share their manufacturing capabilities or resources and collaborate as an interconnected system in a dynamic environment. Since the high performance of this system depends on the formation of a suitable group of manufacturing service providers, this paper develops an integrated c onfiguration design and capacity planning problem for the CMfg system by considering the dynamic environment of this system. In this regard, dynamic service providers and dynamic demand are considered as two aspects of the dynamic nature of this system. A multi-period multi-objective mathematical model is proposed by maximising the utilities of all three stakeholders of the system. Moreover, three extensions of a discrete multi-objective grey wolf optimiser (DMOGWO) algorithm are devised to solve the medium- and large-scale instances. A comprehensive computational experiment is conducted to assess the performance of the developed meta-heuristic algorithms. Furthermore, by carrying out a sensitivity analysis, some managerial insight is suggested for the managers. [ABSTRACT FROM AUTHOR]

Product design is an innovative process that, through the stages of problem statement, concept, and initial and detailed design, meets the needs of customers, the requirements of companies, and their limitations. In the current process of product design and development, formulating design objectives plays a crucial role in objective setting, project implementation, product needs and requirements specification, and performing activities validation. Currently, the role of the design and development stages in the sustainability of products, identifying strategies for improving this stage is of particular significance, and paying attention to the product planning and definition process group and focusing on establishing sustainability principles in the target book and defining new attributes can be regarded as one of the sustainable product development strategies. Consequently, this research is a case study in the field of applying the sustainability principles in the target book as one of the deliverables at the stage of product planning. The present study proposes strategies towards developing the attributes of the target book as a tool for exerting sustainability pillars in the process of design and development by means of surveying automotive industry experts, applying the DEMATEL and Fuzzy ANP combined method, and evaluating and determining new attributes. [ABSTRACT FROM AUTHOR]

The recent trend of globalisation of the economy has been accelerated thanks to emerging new communication technologies. This forces some companies to be adapted to rapidly changing market requirements utilising a multi-factory production network. Job scheduling in such a distributed manufacturing system, is significantly complicated especially in the presence of dynamic events. Furthermore, production systems need to be flexible to timely react to the imposed changes. Hence, reconfigurable machine tools (RMTs) can be used as a resource for flexibility in manufacturing systems. This paper deals with a distributed job-shop rescheduling problem, in which the facilities benefit from reconfigurable machines. Firstly, the problem is mathematically formulated to minimise total weighted lateness in a static state. Then, the dynamic version is extent based on a designed conceptual framework of rescheduling module to update the current schedule. Since the problem is NP-hard, a self-adaptive hybrid equilibrium optimiser algorithm is proposed. The experiments show that the proposed EO algorithm is extremely efficient. Finally, a simulation-optimisation model is developed to evaluate the performance of the manufacturing system facing stochastic arriving jobs. The obtained results show that the production system can be very flexible relying on its distributed facilities and reconfigurable machines. [ABSTRACT FROM AUTHOR]

This paper develops an integrated model for the distribution of post-disaster temporary shelters after a large-scale disaster. The proposed model clusters impacted areas using an Adaptive Neuro-Fuzzy Inference System (ANFIS) method and then prioritizes the points of clusters by affecting factors on the route reliability using a permanent matrix. The model’s objectives are to minimize the maximum service time, maximize the route reliability and minimize the unmet demand. In the case of ground relief, the possibility of a breakdown in the vehicle is considered. Due to the disaster’s uncertain nature, the demands of impacted areas are considered in the form of fuzzy numbers, and then the equivalent crisp counterpart of the non-deterministic is made by Jimenez’s method. Since the developed model is multi-objective, the Non-dominated Sorting Genetic Algorithm (NSGA-II) and Multi-Objective Firefly Algorithm (MOFA) are applied to find efficient solutions. The results confirm higher accuracy and lower computational time of the proposed MOFA. The findings of this study can contribute to the growing body of knowledge about disaster management strategies and have implications for critical decision-makers involved in post-disaster response projects. Furthermore, this study provides valuable information for national decision-makers in countries with limited experience with disasters and where the destructive consequences of disasters on the built environment are increasing.

With the rapid transition towards Industry 4.0, many industries have recognised the need to develop intelligent maintenance systems and predictive analytics tools that are able to optimise the performance of complex assets throughout their entire lifecycle. This paper adopts a machine learning (ML) technology to enhance the resilience of marine propulsion systems by predicting mean-time between failures (MTBF) and prioritising condition-based maintenance (CBM) activities. The factors considered for the analysis include a series of attributes (in total 16 features) which directly or indirectly represent the state of the system subject to degradation. From the results obtained, it is found out that the feed-forward neural network (FFNN) has the least mean square errors (MSE) and, thus, it is the most suitable method for numerical and discretized estimations. The results from a greedy search algorithm also show that two attributes of 'gas generator rate of revolutions' and 'gas turbine rate of revolutions' are the most significant parameters influencing system reliability, and therefore, they require closer monitoring. Furthermore, a decision support system (DSS) dashboard is designed to help marine propulsion system operators make informed maintenance decisions and find an improved balance in their spare parts inventory. [ABSTRACT FROM AUTHOR]