Search results

Demand forecasts are a key component of planning efforts and are crucial for managing core operations. This study aims to evaluate the use of several machine learning (ML) algorithms to forecast demand for residential construction in Jordan.

The identification and selection of variables and ML algorithms that are related to the demand for residential construction are indicated using a literature review. Feature selection was done by using a stepwise backward elimination. The developed algorithm’s accuracy has been demonstrated by comparing the ML predictions with real residual values and compared based on the coefficient of determination.

Nine economic indicators were selected to develop the demand models. Elastic-Net showed the highest accuracy of (0.838) versus artificial neural networkwith an accuracy of (0.727), followed by Eureqa with an accuracy of (0.715) and the Extra Trees with an accuracy of (0.703). According to the results of the best-performing model forecast, Jordan’s 2023 first-quarter demand for residential construction is anticipated to rise by 11.5% from the same quarter of the year 2022.

The results of this study extend to the existing body of knowledge through the identification of the most influential variables in the Jordanian residential construction industry. In addition, the models developed will enable users in the fields of construction engineering to make reliable demand forecasts while also assisting in effective financial decision-making.

As data centres grow in size and complexity, traditional air-cooling methods are becoming less effective and more expensive. Immersion cooling, where servers are submerged in a dielectric fluid, has emerged as a promising alternative. Ensuring reliable operations in data centre applications requires the development of an effective control framework for immersion cooling systems, which necessitates the prediction of server temperature. While deep learning-based temperature prediction models have shown effectiveness, further enhancement is needed to improve their prediction accuracy. This study aims to develop a temperature prediction model using Long Short-Term Memory (LSTM) Networks based on recursive encoder-decoder architecture.

This paper explores the use of deep learning algorithms to predict the temperature of a heater in a two-phase immersion-cooled system using NOVEC 7100. The performance of recursive-long short-term memory-encoder-decoder (R-LSTM-ED), recursive-convolutional neural network-LSTM (R-CNN-LSTM) and R-LSTM approaches are compared using mean absolute error, root mean square error, mean absolute percentage error and coefficient of determination (R²) as performance metrics. The impact of window size, sampling period and noise within training data on the performance of the model is investigated.

The R-LSTM-ED consistently outperforms the R-LSTM model by 6%, 15.8% and 12.5%, and R-CNN-LSTM model by 4%, 11% and 12.3% in all forecast ranges of 10, 30 and 60 s, respectively, averaged across all the workloads considered in the study. The optimum sampling period based on the study is found to be 2 s and the window size to be 60 s. The performance of the model deteriorates significantly as the noise level reaches 10%.

The proposed models are currently trained on data collected from an experimental setup simulating data centre loads. Future research should seek to extend the applicability of the models by incorporating time series data from immersion-cooled servers.

The proposed multivariate-recursive-prediction models are trained and tested by using real Data Centre workload traces applied to the immersion-cooled system developed in the laboratory.

This study focuses on the classification of targets with varying shapes using radar cross section (RCS), which is influenced by the target’s shape. This study aims to develop a robust classification method by considering an incident angle with minor random fluctuations and using a physical optics simulation to generate data sets.

The approach involves several supervised machine learning and classification methods, including traditional algorithms and a deep neural network classifier. It uses histogram-based definitions of the RCS for feature extraction, with an emphasis on resilience against noise in the RCS data. Data enrichment techniques are incorporated, including the use of noise-impacted histogram data sets.

The classification algorithms are extensively evaluated, highlighting their efficacy in feature extraction from RCS histograms. Among the studied algorithms, the K-nearest neighbour is found to be the most accurate of the traditional methods, but it is surpassed in accuracy by a deep learning network classifier. The results demonstrate the robustness of the feature extraction from the RCS histograms, motivated by mm-wave radar applications.

This study presents a novel approach to target classification that extends beyond traditional methods by integrating deep neural networks and focusing on histogram-based methodologies. It also incorporates data enrichment techniques to enhance the analysis, providing a comprehensive perspective for target detection using RCS.

The central idea of this research article is to examine the characteristics of Clairaut submersions from Lorentzian trans-Sasakian manifolds of type (α, β) and also, to enhance this geometrical analysis with some specific cases, namely Clairaut submersion from Lorentzian α-Sasakian manifold, Lorentzian β-Kenmotsu manifold and Lorentzian cosymplectic manifold. Furthermore, the authors discuss some results about Clairaut Lagrangian submersions whose total space is a Lorentzian trans-Sasakian manifolds of type (α, β). Finally, the authors furnished some examples based on this study.

This research discourse based on classifications of submersion, mainly Clairaut submersions, whose total manifolds is Lorentzian trans-Sasakian manifolds and its all classes like Lorentzian Sasakian, Lorenztian Kenmotsu and Lorentzian cosymplectic manifolds. In addition, the authors have explored some axioms of Clairaut Lorentzian submersions and illustrates our findings with some non-trivial examples.

The major finding of this study is to exhibit a necessary and sufficient condition for a submersions to be a Clairaut submersions and also find a condition for Clairaut Lagrangian submersions from Lorentzian trans-Sasakian manifolds.

The results and examples of the present manuscript are original. In addition, more general results with fair value and supportive examples are provided.

The purpose of this paper is to advance our understanding of international crisis mediation by introducing and examining the nested insider-partial mediator (NIPM) concept, a nuanced perspective on IPM behavior. This study challenges the traditional view of effective mediators as external, unbiased entities by delving into the behavior and contribution of mediators who are deeply embedded in the conflict environment, such as South Korea’s unique position in navigating the US–DPRK crisis in 2017–2018. By analyzing South Korea’s dual role as mediator and negotiator and its employment of both nondirective and directive mediation strategies, the paper demonstrates the potential effectiveness of NIPMs in managing complex biases and contributing to de-escalation in intense crisis scenarios.

This paper uses a focused single-case study approach to analyze South Korea’s role as an NIPM. Using a process-tracing methodology, it examines how contextual factors such as relationships, interests and inherent biases influenced South Korea’s mediation strategies in this complex geopolitical scenario. Empirical evidence was retrieved from public sources, including official statements and press interviews, providing an empirical foundation for understanding NIPM behavior. This approach facilitates a detailed study of South Korea’s unique mediation role within the intricate dynamics of the Korean Peninsula conflict.

The study’s findings illustrate the pivotal role NIPMs can play in complex international conflicts, underlining the significant potential of NIPMs in crisis prevention. The findings highlight South Korea’s adept navigation through intricate geopolitical dynamics, leveraging its unique insider position and established relationships with both the USA and North Korea. This behavior was instrumental in mitigating a potentially explosive situation, steering the crisis toward negotiation and de-escalation. The research underscores the effectiveness of the NIPM framework in understanding the nuanced behavior of mediators who are deeply integrated into multi-level conflicts, influenced by their connections, interests and inherent biases.

This research not only broadens the theoretical framework of insider-partial mediation by introducing the concept of NIPM, but also has practical implications for policymakers and practitioners in leveraging regional mediation strategies for international crisis mitigation. The study underscores the importance of mediators’ deep-rooted connections, biases and vested interests in influencing their mediation tactics, thus offering a comprehensive understanding of the multifaceted nature of international mediation in complex geopolitical conflicts.

Religion could drive development. Although Ghana is touted as the most religious country in the world, notably, some Charismatic/Pentecostal churches operate at the expense of community development and members’ welfare. This study sought to achieve three objectives: to determine whether there is an opportunity for organizing the various churches for interfaith cooperative collective action; to assess the association between people’s religiosity and the propensity to join interfaith cooperative collective action and to assess people’s perceptions of the institutional framework that could facilitate the organization of the religious community in Ghana for interfaith collective action.

Descriptive statistics and an ordered probit model (OPM) were used to analyze cross-sectional data from a representative sample of households in the Greater Accra Region. Thematic analysis was also used to analyze the qualitative data.

The study found that generally, there is a positive response to a proposal to mobilize churches in an interfaith cooperative collective action, but distrust poses a great threat to interfaith cooperative collective action. The study also found that affiliation with the Seventh-Day Adventist Church and Pentecostal/Charismatic is negatively (positively) associated with the propensity to join a collective action, respectively. Finally, the results of the study found that accountability, proper management and fair distribution of the proceeds from a collective action will help in mobilizing churches in Ghana in an interfaith collective action.

This is the first major study to explore the possibility of interfaith collective action among religious denominations aimed at accelerating poverty reduction and wealth creation in any developing country.

The peer review history for this article is available at: https://publons.com/publon/10.1108/IJSE-08-2023-0670

This paper aims to validates a framework using the Uses and Gratifications Theory (UGT) to study the effect of values, i.e. Functional Value (FV), Social Value (SV), Emotional Value (EV) and Monetary Value (MV), on the Patronage Intention (PI) of Social Network Users (SNU’s) with mediating role of Perceived Usefulness (PU).

A survey method was used to collect responses from 302 SNUs, and the variance-based structural equation method was used to understand the relationships among the constructs.

The results found a significant positive effect of FV and EV on Perceived Usefulness (PU) and MV and PU on Patronage intention (PI) of SNUs. Further, PU partially mediated the relationship of EV with PI.

This study used the UGT to understand the effect of values on the PI of SNUs. This research study contributes to the existing social networks/social media literature.

Diabetes is one of the life-threatening chronic diseases, which is already affecting 422m people globally based on (World Health Organization) WHO report as at 2018. This costs individuals, government and groups a whole lot; right from its diagnosis stage to the treatment stage. The reason for this cost, among others, is that it is a long-term treatment disease. This disease is likely to continue to affect more people because of its long asymptotic phase, which makes its early detection not feasible.

In this study, the authors have presented machine learning models with feature selection, which can detect diabetes disease at its early stage. Also, the models presented are not costly and available to everyone, including those in the remote areas.

The study result shows that feature selection helps in getting better model, as it prevents overfitting and removes redundant data. Hence, the study result when compared with previous research shows the better result has been achieved, after it was evaluated based on metrics such as F-measure, Precision-Recall curve and Receiver Operating Characteristic Area Under Curve. This discovery has the potential to impact on clinical practice, when health workers aim at diagnosing diabetes disease at its early stage.

This study has not been published anywhere else.

Visual aesthetics are a vital aspect of environmental quality. The objective of this study is to demonstrate the implementation of visibility analysis and visual quality standards on a campus to enhance productivity and effectiveness.

This study has identified the most crucial and valuable metrics for evaluating the visual quality of open spaces through an analysis of theoretical foundations and relevant background information. To achieve research goal, a multi-method approach was employed, incorporating a survey, user satisfaction ratings and ISOVIST simulation techniques. Specifically, this study focused on assessing the quality of open spaces in three open areas located on the campus of the Iran University of Science and Technology.

Based on the study’s findings, the most significant factors that students considered when evaluating the visual quality of open spaces on the Iran University of Science and Technology campus were green areas, gathering spaces and architectural elements such as furniture, color and texture. Among the three open areas examined, “Open Space One” was identified as the most satisfactory location for students. According to the study, “sensory richness,” “complexity” and “mystery” were significant indicators of students' satisfaction in this area. This area also had the widest radius and field of view feasible, which gave it a feeling of openness and spaciousness.

This study explores the influence of students' experiences, behavioral patterns and visual analyses on their use of open spaces on university campuses, with a focus on the Iran University of Science and Technology. By assessing students' satisfaction levels with these spaces, this research provides valuable insights that can guide the initial analysis stage before the design process and facilitate design optimization during the development stages. The results highlight the importance of considering user experiences and visual analysis when planning and creating open spaces on university campuses.

Highlights

1. Conducting an initial analysis before developing a design plan can be very helpful in understanding how users think and behave.

2. The three criteria of visual quality that have the strongest correlation with students' satisfaction with “open space” are “mystery,” “sensory richness” and “complexity.”

3. Two factors, namely the “radius of vision” and the “area” index, significantly influence students' satisfaction with open spaces.

4. Outdoor designers should incorporate “green space” and “gathering spaces” into their designs since the presence of these is effective in attracting and satisfying students.

5. The number of people using an open space has little to do with how satisfied students are with it.

6. Half of the students use open areas between 11:00 and 14:00, so the provision of “canopy” and “shelter” in these spaces is essential.

Conducting an initial analysis before developing a design plan can be very helpful in understanding how users think and behave.

The three criteria of visual quality that have the strongest correlation with students' satisfaction with “open space” are “mystery,” “sensory richness” and “complexity.”

Two factors, namely the “radius of vision” and the “area” index, significantly influence students' satisfaction with open spaces.

Outdoor designers should incorporate “green space” and “gathering spaces” into their designs since the presence of these is effective in attracting and satisfying students.

The number of people using an open space has little to do with how satisfied students are with it.

Half of the students use open areas between 11:00 and 14:00, so the provision of “canopy” and “shelter” in these spaces is essential.