Search results

This study aims to develop a regression-based machine learning model to predict housing price, determine and interpret factors that contribute to housing prices using different data sets available publicly. The significant determinants that affect housing prices will be first identified by using multinomial logistics regression (MLR) based on the level of relative importance. A comprehensive study is then conducted by using SHapley Additive exPlanations (SHAP) analysis to examine the features that cause the major changes in housing prices.

Predictive analytics is an effective way to deal with uncertainties in process modelling and improve decision-making for housing price prediction. The focus of this paper is two-fold; the authors first apply regression analysis to investigate how well the housing independent variables contribute to the housing price prediction. Two data sets are used for this study, namely, Ames Housing dataset and Melbourne Housing dataset. For both the data sets, random forest regression performs the best by achieving an average R² of 86% for the Ames dataset and 85% for the Melbourne dataset, respectively. Second, multinomial logistic regression is adopted to investigate and identify the factor determinants of housing sales price. For the Ames dataset, the authors find that the top three most significant factor variables to determine the housing price is the general living area, basement size and age of remodelling. As for the Melbourne dataset, properties having more rooms/bathrooms, larger land size and closer distance to central business district (CBD) are higher priced. This is followed by a comprehensive analysis on how these determinants contribute to the predictability of the selected regression model by using explainable SHAP values. These prominent factors can be used to determine the optimal price range of a property which are useful for decision-making for both buyers and sellers.

By using the combination of MLR and SHAP analysis, it is noticeable that general living area, basement size and age of remodelling are the top three most important variables in determining the house’s price in the Ames dataset, while properties with more rooms/bathrooms, larger land area and closer proximity to the CBD or to the South of Melbourne are more expensive in the Melbourne dataset. These important factors can be used to estimate the best price range for a housing property for better decision-making.

A limitation of this study is that the distribution of the housing prices is highly skewed. Although it is normal that the properties’ price is normally cluttered at the lower side and only a few houses are highly price. As mentioned before, MLR can effectively help in evaluating the likelihood ratio of each variable towards these categories. However, housing price is originally continuous, and there is a need to convert the price to categorical type. Nonetheless, the most effective method to categorize the data is still questionable.

The key point of this paper is the use of explainable machine learning approach to identify the prominent factors of housing price determination, which could be used to determine the optimal price range of a property which are useful for decision-making for both the buyers and sellers.

The application of circular building adaptability (CBA) in adaptive reuse becomes an effective action for resource efficiency, long-lasting usability of the built environment and the sped-up transition to a circular economy (CE). This paper aims to explore to which extent CBA-related strategies are applied in adaptive reuse projects, considering enablers and obstacles.

A stepwise theory-practice-oriented approach was followed. Multiple-case studies of five circular adaptive reuse projects in The Netherlands were investigated, using archival research and in-depth interviews. A cross-case analysis of the findings was deductively conducted, to find and replicate common patterns.

The study revealed that configuration flexibility, product dismantlability and material reversibility were applied across the case studies, whereas functional convertibility and building maintainability were less applied. Low cost of material reuse, collaboration among team members and organisational motivation were frequently observed enabling factors. Lack of information, technical complexities, lack of circularity expertise and infeasibility of innovative circular solutions were frequently observed obstacles to applying CBA.

This paper provides practitioners with a set of CBA strategies that have been applied in the real world, facilitating the application of CBA in future adaptive reuse projects. Moreover, this set of strategies provides policymakers with tools for developing supportive regulations or amending existing regulations for facilitating CE through adaptive reuse.

This study provides empirical evidence on the application of CBA in different real-life contexts. It provides scholars and practitioners with a starting point for further developing guiding or decision-making tools for CBA in adaptive reuse.

The purpose of this study is to propose a new consumer value segmentation method for low-dimensional dense market datasets to quickly detect and cluster the most profitable customers for the enterprises.

In this study, the comprehensive segmentation bases (CSB) with richer meanings were obtained by introducing the weighted recency-frequency-monetary (RFM) model into the common segmentation bases (SB). Further, a new market segmentation method, the CSB-MBK algorithm was proposed by integrating the CSB model and the mini-batch k-means (MBK) clustering algorithm.

The results show that our proposed CSB model can reflect consumers' contributions to a market, as well as improve the clustering performance. Moreover, the proposed CSB-MBK algorithm is demonstrably superior to the SB-MBK, CSB-KMA and CSB-Chameleon algorithms with respect to the Silhouette Coefficient (SC), the Calinski-Harabasz (CH) Index , the average running time and superior to the SB-MBK, RFM-MBK and WRFM-MBK algorithms in terms of the inter-market value and characteristic differentiation.

This paper provides a tool for decision-makers and marketers to segment a market quickly, which can help them grasp consumers' activity, loyalty, purchasing power and other characteristics in a target market timely and achieve the precision marketing.

This study is the first to introduce the CSB-MBK algorithm for identifying valuable customers through the comprehensive consideration of the clustering quality, consumer value and segmentation speed. Moreover, the CSB-MBK algorithm can be considered for applications in other markets.

This paper aims to derive a reduced-order model for the heat transfer across the interface between a millimetric thermocapillary liquid bridge from silicone oil and the surrounding ambient gas.

Numerical solutions for the two-fluid model are computed covering a wide parametric space, making a total of 2,800 numerical flow simulations. Based on the computed data, a reduced single-fluid model for the liquid phase is devised, in which the heat transfer between the liquid and the gas is modeled by Newton’s heat transfer law, albeit with a space-dependent Biot function Bi(z), instead of a constant Biot number Bi.

An explicit robust fit of Bi(z) is obtained covering the whole range of parameters considered. The single-fluid model together with the Biot function derived yields very accurate results at much lesser computational cost than the corresponding two-phase fully-coupled simulation required for the two-fluid model.

Using this novel Biot function approach instead of a constant Biot number, the critical Reynolds number can be predicted much more accurately within single-phase linear stability solvers.

The Biot function for thermocapillary liquid bridges is derived from the full multiphase problem by a robust multi-stage fit procedure. The derived Biot function reproduces very well the theoretical boundary layer scalings.

This research investigates the distinct characteristics of blockchain technology to safeguard against the deterioration of handover information quality in the post-construction phase. The significance of effective management of handover information is highlighted by global building failures, such as the Grenfell Tower fire in London, UK. Despite existing technological interventions, there remains a paucity of understanding regarding the factors contributing to the decline in the quality of handover information during the post-construction phase.

This study employed a multi-case studies approach across five higher education institutions. It involved conducting semi-structured interviews with 52 asset management professionals, uncovering the underlying reasons for the decline in handover information quality. Building on these insights, the study performed a mapping exercise to align these identified factors with blockchain technology features and information quality dimensions, aiming to evaluate blockchain’s potential in managing quality handover information.

The study findings suggest that blockchain technology offers advantages but has limitations in addressing all the identified quality issues of managing handover information. Due to the lack of an automated process and file-based information exchange, updating handover information still requires an error-prone manual process, leading to potential information loss. Additionally, no solutions are available for encoding drawings for updates and validation.

This study proposes a framework integrating blockchain to enhance the information management process and improve handover information quality.

Manufacturing companies continue to encounter a diverse set of obstacles while embracing sustainable development goals. Accordingly, the purpose of this study is to explore critical sustainable development-related barriers to flexible packaging manufacturing companies in the New Zealand context.

Drawing on a qualitative multiple case studies approach, the authors collected data from the New Zealand flexible packaging industry. Semistructured interviews were conducted with the senior corporate managers in two large flexible packaging companies. Following the thematic analysis approach, the authors analyzed the information collected from the participants and synthesized our findings under the key dimensions of internal and external barriers to sustainable development.

The findings revealed that internal barriers to sustainable flexible packaging are linked to economic, operational and technical issues. Conversely, external barriers include global crises and disruption, customer behavior and preferences and institutional and infrastructural-related aspects. Based on the analysis of empirical findings, the authors further identified the underlying reasons for sustainable flexible packaging barriers and recommended guidelines that could assist corporate managers and policymakers in addressing obstacles inhibiting the flexible packaging industry from adopting sustainable business practices.

The authors argue that this study is one of the early studies to consider inhibiting factors to incorporate sustainable development into the New Zealand flexible packaging industry context. Building on a range of theoretical perspectives, the authors extend the current body of knowledge seeking to advance the sustainable development agenda in the New Zealand flexible packaging industry and offer recommended pathways fostering sustainable development in a distinctive manufacturing context.

Concrete, the second most used material in the world, surpassed only by water, relies on a vast amount of cement. The process of cement production emits substantial amounts of carbon dioxide (CO₂). Consequently, it is crucial to search for cement alternatives. Geopolymer concrete (GC) uses industrial by-product material instead of traditional cement, which not only reduces CO₂ emissions but also enhances concrete durability. On the other hand, the disposal of concrete waste in the landfills represents a significant environmental challenge, emphasising the urgent need for sustainable solutions. This study aimed to investigate waste concrete's best form and rate as the alternative aggregates in self-compacting and ambient-cured GC to preserve natural resources, reduce construction and demolition waste and decrease pertinent CO₂ emissions. The binding material employed in this research encompasses fly ash, slag, micro fly ash and anhydrous sodium metasilicate as an alkali activator. It also introduces the best treatment method to improve the recycled concrete aggregate (RCA) quality.

A total of25%, 50% and 100% of coarse aggregates are replaced with RCAs to cast self-compacting geopolymer concrete (SCGC) and assess the impact of RCA on the fresh, hardened and water absorption properties of the ambient-cured GC. Geopolymer slurry was used for coating RCAs and the authors examined the effect of one-day and seven-day cured coated RCA. The mechanical properties (compressive strength, splitting tensile strength and modulus of elasticity), rheological properties (slump flow, T500 and J-ring) and total water absorption of RCA-based SCGC were studied. The microstructural and chemical compositions of the concrete mixes were studied by the methods of energy dispersive X-Ray and scanning electron microscopy.

It is evident from the test observations that 100% replacement of natural aggregate with coated RCA using geopolymer slurry containing fly ash, slag, micro fly ash and anhydrous sodium metasilicate cured for one day before mixing enhances the concrete's quality and complies with the flowability requirements. Assessment is based on the fresh and hardened properties of the SCGC with various RCA contents and coating periods. The fresh properties of the mix with a seven-day curing time for coated RCA did not meet the requirements for self-compacting concrete, while this mix demonstrated better compressive strength (31.61 MPa) and modulus of elasticity (15.39 GPa) compared to 29.36 MPa and 9.8 GPa, respectively, for the mix with one-day cured coated RCA. However, incorporating one-day-cured coated RCA in SCGC demonstrated better splitting tensile strength (2.32 MPa) and water absorption (15.16%).

A potential limitation of this study on SCGC with coated RCAs is the focus on the short-term behaviour of this concrete. This limited time frame may not meet the long-term requirements for ensuring the sustained durability of the structures throughout their service life.

This paper highlights the treatment technique of coating RCA with geopolymer slurry for casting SCGC.

This paper aims to generate a better understanding of how challenges and opportunities for sustainable change during digitalization relate to the organizing work of change agents mandated to facilitate technology adoption from within local work organizations.

This study examines the work of welfare technology coordinators, health-care professionals who are mandated to facilitate the use of technologies in home-based services in a Norwegian city. Data comprise ethnographic observations of meetings and work practices, interviews and documents collected over one year. A practice-based approach was applied to analyze how the welfare technology coordinators go about integrating technologies with the work practices, and the forms of negotiations this work implies in their work community.

The analysis identified four sets of practices in the coordinators’ work: exploring and integrating new technologies into work practices, legitimizing aims and values, formalizing routines and responsibilities and critically considering existing and envisioned service practices. Through these practices, emerging problems and disconnections in the service organization were attended to in a continuous manner.

The study contributes to the literature by examining the work of internal change agents mandated to facilitate multiple and simultaneous technology adoption and demonstrates the importance of recognizing the continuous efforts and negotiations of these agents as significant to sustainable organizing.

The purpose of this study to investigate the organized porous network zinc (OPNZ) scaffolds. Their mechanical characteristics, surface roughness and fracture mechanism were assessed in relation to their structural properties. The prospects of fused deposition modeling (FDM) for printing metal scaffolds via rapid tooling have also been studied.

Zn scaffolds with different pore and strut sizes were manufactured via the rapid tooling method. This method is a multistep process that begins with the 3D printing of a polymer template. Later, a paraffin template was obtained from the prepared polymer template. Finally, this paraffin template was used to fabricate the Zn scaffold using microwave sintering. The characterization of prepared Zn samples involved structural characterization, microstructural study, surface roughness testing and compression testing. Moreover, based on the Gibson–Ashby model analysis, the model equations’ constant values were evaluated, which can help in predicting the mechanical properties of Zn scaffolds.

The scanning electron microscopy study confirmed that the fabricated sample pores were open and interconnected. The X-ray diffraction analysis revealed that the Zn scaffold contained hexagonal closed-packed Zn peaks related to the a-Zn phase, validating that scaffolds were free from contamination and impurity. The range for ultimate compressive strength, compressive modulus and plateau stresses for Zn samples were found to be 6.75–39 MPa, 0.14–3.51 GPa and 1.85–12.6 MPa by adjusting their porosity, which are comparable with the cancellous bones. The average roughness value for the Zn scaffolds was found to be 1.86 µm.

This research work can widen the scope for extrusion-based FDM printers for fabricating biocompatible and biodegradable metal Zn scaffolds. This study also revealed the effects of scaffold structural properties like porosity, pore and strut size effect on their mechanical characteristics in view of tissue engineering applications.

The theory of complex adaptive systems (CASs) represents an interesting perspective to study the characteristics of circular supply chains (CSCs). In this regard, the current literature lacks evidence regarding coordination and integration mechanisms, characteristics of the environment and emerging system properties of CSCs. This paper aims to fill this gap and focuses on how and why companies design (i.e. configure and coordinate) their CSCs and what value these design choices help to create across different industries.

The authors use a multiple case study approach and analyze data collected from a sample of five sustainable start-ups operating in the fashion and construction industries in Italy to better understand how these companies design (i.e. configure and coordinate) their CSCs.

Results reveal that in the two industries under investigation, the design of CSCs built around open and closed–loop logic is triggered by the intention to solve a negative sustainability impact. The sustainability impact determines whether the value is restored within the same supply chain, in another, or inside or outside the same industry. Interestingly, start-ups appear to coordinate other CSC actors with three leading roles: (1) orchestrator, (2) integrated orchestrator and (3) circular manufacturer. The coordination role of the start-ups differs in each supply chain configuration based on the level of vertical integration of manufacturing activities.

From a theoretical perspective, the authors' results expand previous supply chain management (SCM) literature by presenting an empirical analysis of the configuration and coordination of CSCs, and discussing the drivers for creating such circularity from a CAS perspective. From a managerial perspective, the authors offer a practical experience to entrepreneurs on how to transform circular and sustainable business model aspirations into CSC practices.