Search results

Histopathology biopsy imaging is currently the gold standard for the diagnosis of breast cancer in clinical practice. Pathologists examine the images at various magnifications to identify the type of tumor because if only one magnification is taken into account, the decision may not be accurate. This study explores the performance of transfer learning and late fusion to construct multi-scale ensembles that fuse different magnification-specific deep learning models for the binary classification of breast tumor slides.

Three pretrained deep learning techniques (DenseNet 201, MobileNet v2 and Inception v3) were used to classify breast tumor images over the four magnification factors of the Breast Cancer Histopathological Image Classification dataset (40×, 100×, 200× and 400×). To fuse the predictions of the models trained on different magnification factors, different aggregators were used, including weighted voting and seven meta-classifiers trained on slide predictions using class labels and the probabilities assigned to each class. The best cluster of the outperforming models was chosen using the Scott–Knott statistical test, and the top models were ranked using the Borda count voting system.

This study recommends the use of transfer learning and late fusion for histopathological breast cancer image classification by constructing multi-magnification ensembles because they perform better than models trained on each magnification separately.

The best multi-scale ensembles outperformed state-of-the-art integrated models and achieved an accuracy mean value of 98.82 per cent, precision of 98.46 per cent, recall of 100 per cent and F1-score of 99.20 per cent.

This study aims to improve the reliability of emergency safety barriers by using the subjective safety analysis based on evidential reasoning theory in order to develop on a framework for optimizing the reliability of emergency safety barriers.

The emergency event tree analysis is combined with an interval type-2 fuzzy-set and analytic hierarchy process (AHP) method. In order to the quantitative data is not available, this study based on interval type2 fuzzy set theory, trapezoidal fuzzy numbers describe the expert's imprecise uncertainty about the fuzzy failure probability of emergency safety barriers related to the liquefied petroleum gas storage prevent. Fuzzy fault tree analysis and fuzzy ordered weighted average aggregation are used to address uncertainties in emergency safety barrier reliability assessment. In addition, a critical analysis and some corrective actions are suggested to identify weak points in emergency safety barriers. Therefore, a framework decisions are proposed to optimize and improve safety barrier reliability. Decision-making in this framework uses evidential reasoning theory to identify corrective actions that can optimize reliability based on subjective safety analysis.

A real case study of a liquefied petroleum gas storage in Algeria is presented to demonstrate the effectiveness of the proposed methodology. The results show that the proposed methodology provides the possibility to evaluate the values of the fuzzy failure probability of emergency safety barriers. In addition, the fuzzy failure probabilities using the fuzzy type-2 AHP method are the most reliable and accurate. As a result, the improved fault tree analysis can estimate uncertain expert opinion weights, identify and evaluate failure probability values for critical basic event. Therefore, suggestions for corrective measures to reduce the failure probability of the fire-fighting system are provided. The obtained results show that of the ten proposed corrective actions, the corrective action “use of periodic maintenance tests” prioritizes reliability, optimization and improvement of safety procedures.

This study helps to determine the safest and most reliable corrective measures to improve the reliability of safety barriers. In addition, it also helps to protect people inside and outside the company from all kinds of major industrial accidents. Among the limitations of this study is that the cost of corrective actions is not taken into account.

Our contribution is to propose an integrated approach that uses interval type-2 fuzzy sets and AHP method and emergency event tree analysis to handle uncertainty in the failure probability assessment of emergency safety barriers. In addition, the integration of fault tree analysis and fuzzy ordered averaging aggregation helps to improve the reliability of the fire-fighting system and optimize the corrective actions that can improve the safety practices in liquefied petroleum gas storage tanks.

Supplier selection along with continuous evaluation of their performance is a crucial activity in healthcare supply chain management for effective utilization of scarce resources while providing quality service at an affordable price, and minimizing chances of stock-out, avoiding serious consequences on the illness or fatality of the patients. Presence of both qualitative and quantitative evaluation criteria, set of potential suppliers and participation of different stakeholders with varying interest make healthcare supplier selection a challenging task which can be effectively solved using any of the multi-criteria decision making (MCDM) methods.

To deal with various qualitative criteria, like cost, quality, delivery performance, reliability, responsiveness and flexibility, this paper proposes integration of grey system theory with a newly developed MCDM tool, i.e. mixed aggregation by comprehensive normalization technique (MACONT) to identify the best performing supplier for pharmaceutical items in a healthcare unit from a pool of six competing alternatives based on the opinions of three healthcare professionals.

While assessing importance of the six evaluation criteria and performance of the alternative healthcare suppliers against those criteria using grey numbers, and exploring use of three normalization procedures and two aggregation operations of MACONT method, this integrated approach singles out S5 as the most compromised healthcare supplier for the considered problem. A sensitivity analysis of its ranking performance against varying values of both balance parameters and preference parameters also validates its solution accuracy and robustness.

This integrated approach can thus efficiently solve healthcare supplier selection problems based on qualitative evaluation criteria in uncertain group decision making environment. It can also be deployed to deal with other decision making problems in the healthcare sector, like supplier selection for healthcare devices, performance evaluation of healthcare units, ranking of physicians etc.

Water pipes degrade over time for a variety of pipe-related, soil-related, operational, and environmental factors. Hence, municipalities are necessitated to implement effective maintenance and rehabilitation strategies for water pipes based on reliable deterioration models and cost-effective inspection programs. In the light of foregoing, the paramount objective of this research study is to develop condition assessment and deterioration prediction models for saltwater pipes in Hong Kong.

As a perquisite to the development of condition assessment models, spherical fuzzy analytic hierarchy process (SFAHP) is harnessed to analyze the relative importance weights of deterioration factors. Afterward, the relative importance weights of deterioration factors coupled with their effective values are leveraged using the measurement of alternatives and ranking according to the compromise solution (MARCOS) algorithm to analyze the performance condition of water pipes. A condition rating system is then designed counting on the generalized entropy-based probabilistic fuzzy C means (GEPFCM) algorithm. A set of fourth order multiple regression functions are constructed to capture the degradation trends in condition of pipelines overtime covering their disparate characteristics.

Analytical results demonstrated that the top five influential deterioration factors comprise age, material, traffic, soil corrosivity and material. In addition, it was derived that developed deterioration models accomplished correlation coefficient, mean absolute error and root mean squared error of 0.8, 1.33 and 1.39, respectively.

It can be argued that generated deterioration models can assist municipalities in formulating accurate and cost-effective maintenance, repair and rehabilitation programs.

Digital resources such as smart applications reviews and online feedback information are important sources to seek customers’ feedback and input. This paper aims to help government entities gain insights on the needs and expectations of their customers. Towards this end, we propose an aspect-based sentiment analysis hybrid approach that integrates domain lexicons and rules to analyse the entities smart apps reviews. The proposed model aims to extract the important aspects from the reviews and classify the corresponding sentiments. This approach adopts language processing techniques, rules, and lexicons to address several sentiment analysis challenges, and produce summarized results. According to the reported results, the aspect extraction accuracy improves significantly when the implicit aspects are considered. Also, the integrated classification model outperforms the lexicon-based baseline and the other rules combinations by 5% in terms of Accuracy on average. Also, when using the same dataset, the proposed approach outperforms machine learning approaches that uses support vector machine (SVM). However, using these lexicons and rules as input features to the SVM model has achieved higher accuracy than other SVM models.

Every day, small and big incidents happen all over the world, and given the human, financial and spiritual damage they cause, proper planning should be sought to deal with them so they can be appropriately managed in times of crisis. This study aims to examine humanitarian supply chain models.

A new model is developed to pursue the necessary relations in an optimal way that will minimize human, financial and moral losses. In this developed model, in order to optimize the problem and minimize the amount of human and financial losses, the following subjects have been applied: magnitude of the areas in which an accident may occur as obtained by multiple attribute decision-making methods, the distances between relief centers, the number of available rescuers, the number of rescuers required and the risk level of each patient which is determined using previous data and machine learning (ML) algorithms.

For this purpose, a case study in the east of Tehran has been conducted. According to the results obtained from the algorithms, problem modeling and case study, the accuracy of the proposed model is evaluated very well.

Obtaining each injured person's priority using ML techniques and each area's importance or risk level, besides developing a bi-objective mathematical model and using multiple attribute decision-making methods, make this study unique among very few studies that concern ML in the humanitarian supply chain. Moreover, the findings validate the results and the model's functionality very well.

The existing literature reflects that the connection between enablers of Industry 4.0 (I4.0), Supply Chain (SC) sustainability and reliability is understudied. To cover this gap, the purpose of this study is to identify and benchmark the enablers of I4.0 for SC sustainability to build a Reliable Supply Chain (RSC).

This study benchmarks the I4.0 enablers for SC sustainability for building a RSC and analyses them with a multi-method approach. The identified potential enablers are validated empirically. A multi-method approach of Analytical Hierarchy Process (AHP), Decision Making Trial and Evaluation Laboratory (DEMATEL) and Preference Ranking for Organization Method for Enrichment Evaluation (PROMETHEE-II) was used to investigate the influence of the identified benchmarking enablers and develop an interrelationship diagram among the identified enablers.

This study benchmarks the potential enablers of I4.0 to achieve high ecological-economic-social gains in SCs considering the Indian scenario. Digitalization of the supply chain, decentralization, smart factory technologies and data security and handling are the most prominent enablers of I4.0 for SC sustainability to build a RSC.

The findings from the study may benefit managers, practitioners, specialists, researchers and policymakers interested in I4.0 sustainability applications.

As public–private partnerships (PPPs) have become preferred and veritable approach to deliver affordable housing, the seemingly lack of understanding of the significant factors that impact on success has become a notable setback. This study aims to delineate significant factors that can support decisions in affordable PPP public housing delivery.

Largely, a questionnaire survey was adopted to elicit insights from practitioners, policymakers and experts to develop an evaluative decision support model using an analytical hierarchy process and multi-attribute utility technique approach. Further, an expert illustration was conducted to evaluate and validate the results on the housing typologies.

The results revealed that energy efficiency and low-cost green building materials scored the highest weighting of all the criteria. Furthermore, multi-storey self-contained flats were found to be the most preferred housing typology and were significantly influenced by these factors. From the model evaluation, the scores on the factors of sustainability, affordability, cultural values and accountability were consistent across all typologies of housing whereas that of benchmarking, governance and transparency were varied.

The decision support factors captured varied dimensions of key factors that impact on affordable PPP housing that have not been considered in an integrated manner. These findings offer objective and systematic support to decision-making in affordable PPP housing delivery.

A community demonstrates the unique qualities and relationships between its members that distinguish it from other communities within a network. Network analysis relies heavily on community detection. Despite the traditional spectral clustering and statistical inference methods, deep learning techniques for community detection have grown in popularity due to their ease of processing high-dimensional network data. Graph convolutional neural networks (GCNNs) have received much attention recently and have developed into a potential and ubiquitous method for directly detecting communities on graphs. Inspired by the promising results of graph convolutional networks (GCNs) in analyzing graph structure data, a novel community graph convolutional network (CommunityGCN) as a semi-supervised node classification model has been proposed and compared with recent baseline methods graph attention network (GAT), GCN-based technique for unsupervised community detection and Markov random fields combined with graph convolutional network (MRFasGCN).

This work presents the method for identifying communities that combines the notion of node classification via message passing with the architecture of a semi-supervised graph neural network. Six benchmark datasets, namely, Cora, CiteSeer, ACM, Karate, IMDB and Facebook, have been used in the experimentation.

In the first set of experiments, the scaled normalized average matrix of all neighbor's features including the node itself was obtained, followed by obtaining the weighted average matrix of low-dimensional nodes. In the second set of experiments, the average weighted matrix was forwarded to the GCN with two layers and the activation function for predicting the node class was applied. The results demonstrate that node classification with GCN can improve the performance of identifying communities on graph datasets.

The experiment reveals that the CommunityGCN approach has given better results with accuracy, normalized mutual information, F1 and modularity scores of 91.26, 79.9, 92.58 and 70.5 per cent, respectively, for detecting communities in the graph network, which is much greater than the range of 55.7–87.07 per cent reported in previous literature. Thus, it has been concluded that the GCN with node classification models has improved the accuracy.

The study aims to identify and evaluate relevant criteria in the proposal and support of public administration policies for preventive maintenance comprised in a conservation approach to built heritage and aligned with local sustainable development of the historic center of the city of Sobral, in Brazil.

A novel multicriteria decision model adopting the Bayesian best-worst method is presented and its application and results are described. Though a systematic procedure, criteria were selected in order to protect the tangible and intangible values of cultural heritage, as well as its sustainable development. Then experts evaluate these criteria through an elicitation instrument.

The results show that for the decision problem over preventive maintenance, social contribution and historical record of built heritage are more important than its structural vulnerability, while architecture is less relevant. Due to the low restrictions, the subcriterion related to this property has the least influence. The weights can assist in the characterization of measures and policies for the protection of the built cultural heritage.

The use of a novel decision-making method in cultural heritage is an important initiative, given the frequent use of simple and inefficient methods. The identified and weighted criteria are important data to characterize the scenario and the topic. The results contribute to protection and development of the built heritage, encouraging the implementation of preventive conservation in the historic center, conferring to the public administration valuable information to support and propose initiatives.