Search results

The purpose of this study is to make property price forecasts for the Chinese housing market that has grown rapidly in the last 10 years, which is an important concern for both government and investors.

This study examines Gaussian process regressions with different kernels and basis functions for monthly pre-owned housing price index estimates for ten major Chinese cities from March 2012 to May 2020. The authors do this by using Bayesian optimizations and cross-validation.

The ten price indices from June 2019 to May 2020 are accurately predicted out-of-sample by the established models, which have relative root mean square errors ranging from 0.0458% to 0.3035% and correlation coefficients ranging from 93.9160% to 99.9653%.

The results might be applied separately or in conjunction with other forecasts to develop hypotheses regarding the patterns in the pre-owned residential real estate price index and conduct further policy research.

The Chinese housing market has witnessed rapid growth during the past decade and the significance of housing price forecasting has undoubtedly elevated, becoming an important issue to investors and policymakers. This study aims to examine neural networks (NNs) for office property price index forecasting from 10 major Chinese cities for July 2005–April 2021.

The authors aim at building simple and accurate NNs to contribute to pure technical forecasts of the Chinese office property market. To facilitate the analysis, the authors explore different model settings over algorithms, delays, hidden neurons and data-spitting ratios.

The authors reach a simple NN with three delays and three hidden neurons, which leads to stable performance of about 1.45% average relative root mean square error across the 10 cities for the training, validation and testing phases.

The results could be used on a standalone basis or combined with fundamental forecasts to form perspectives of office property price trends and conduct policy analysis.

Harmonic drives are used widely in aviation, robotics and instrumentation due to their benefits including high transmission ratio, compact structure and zero backlash. One of the common faults of a harmonic drive is the axial movement of the input shaft. In such a case, its input shaft moves in the axial direction relative to the body of the harmonic drive. The purpose of this study is to propose two fault diagnosis methods based on the current signal of the driving servomotor for the axial movement failure in terms of input shafts of harmonic drives.

In the two proposed fault diagnosis methods, the wavelet threshold algorithm is firstly used for filtering noises of the motor current signal. Then, the feature of the denoised current signal is extracted by the empirical mode decomposition (EMD) method and the wavelet packet energy-entropy (WPEE) theory, respectively, obtaining two kinds of feature sets. After a deep learning model based on the deep belief network (DBN) is constructed and trained by using these feature sets, we finally identify the normal harmonic drives and the ones with the axial movement fault.

In contrast to the traditional back propagation (BP) neural network model and support vector machine (SVM) model, the fault diagnosis methods based on the combination of the EMD (as well as the WPEE) and the DBN model can obtain higher accuracy rates of fault diagnosis for axial movement of harmonic drives, which can be greater than or equal to 97% based on the data of the performed experiment.

The authors propose two fault diagnosis methods based on the current signal of the driving servomotor for the axial movement failure in terms of input shafts of harmonic drives, which are verified by the experiment. The presented study may be beneficial for the development of self-diagnosis and self-repair systems of different robots and precision machines using harmonic drives.

Deep learning (DL) is on the rise because it can make predictions and judgments based on data that is unseen. Blockchain technologies are being combined with DL frameworks in various industries to provide a safe and effective infrastructure. The review comprises literature that lists the most recent techniques used in the aforementioned application sectors. We examine the current research trends across several fields and evaluate the literature in terms of its advantages and disadvantages.

The integration of blockchain and DL has been explored in several application domains for the past five years (2018–2023). Our research is guided by five research questions, and based on these questions, we concentrate on key application domains such as the usage of Internet of Things (IoT) in several applications, healthcare and cryptocurrency price prediction. We have analyzed the main challenges and possibilities concerning blockchain technologies. We have discussed the methodologies used in the pertinent publications in these areas and contrasted the research trends during the previous five years. Additionally, we provide a comparison of the widely used blockchain frameworks that are used to create blockchain-based DL frameworks.

By responding to five research objectives, the study highlights and assesses the effectiveness of already published works using blockchain and DL. Our findings indicate that IoT applications, such as their use in smart cities and cars, healthcare and cryptocurrency, are the key areas of research. The primary focus of current research is the enhancement of existing systems, with data analysis, storage and sharing via decentralized systems being the main motivation for this integration. Amongst the various frameworks employed, Ethereum and Hyperledger are popular among researchers in the domain of IoT and healthcare, whereas Bitcoin is popular for research on cryptocurrency.

There is a lack of literature that summarizes the state-of-the-art methods incorporating blockchain and DL in popular domains such as healthcare, IoT and cryptocurrency price prediction. We analyze the existing research done in the past five years (2018–2023) to review the issues and emerging trends.

In recent decades, interest in digital transformation (DX) within the architecture, engineering, and construction (AEC) industry has significantly increased. Despite the existence of several literature reviews on DX research, there remains a notable lack of systematic quantitative and visual investigations into the structure and evolution of this field. This study aims to address this gap by uncovering the current state, key topics, keywords, and emerging areas in DX research specific to the AEC sector.

Employing a holistic review approach, this study undertook a thorough and systematic analysis of the literature concerning DX in the AEC industry. Utilizing a bibliometric analysis, 3,656 papers were retrieved from the Web of Science spanning the years 1990–2023. A scientometric analysis was then applied to these publications to discern patterns in publication years, geographical distribution, journals, authors, citations, and keywords.

The findings identify China, the USA, and England as the leading contributors in the field of DX in AEC sector. Prominent keywords include “building information modeling”, “design”, “system”, “framework”, “adoption”, “model”, “safety”, “internet of things”, and “innovation”. Emerging areas of interest are “deep learning”, “embodied energy”, and “machine learning”. A cluster analysis of keywords reveals key research themes such as “deep learning”, “smart buildings”, “virtual reality”, “augmented reality”, “smart contracts”, “sustainable development”, “building information modeling”, “big data”, and “3D printing”.

This study is among the earliest to provide a comprehensive scientometric mapping of the DX field. The findings presented here have significant implications for both industry practitioners and the scientific community, offering a thorough overview of the current state, prominent keywords, topics, and emerging areas within DX in the AEC industry. Additionally, this research serves as an invaluable reference and guideline for scholars interested in this subject.

Previous research has demonstrated that Digital Twins (DT) are extensively employed to improve sustainable construction methods. Nonetheless, their uptake in numerous nations is still constrained. This study seeks to identify and examine the digital twin’s implementation barriers in construction building projects to augment operational performance and sustainability.

An iterative two-stage approach was adopted to explore the phenomena under investigation. General DT Implementation Barriers were first identified from extant literature and subsequently explored using primary questionnaire survey data from Hong Kong building industry professionals.

Survey results illustrated that Lack of methodologies and tools, Difficulty in ensuring a high level of performance in real-time communication, Impossibility of directly measuring all data relevant to the DT, need to share the DT among multiple application systems involving multiple stakeholders and Uncertainties in the quality and reliability of data are the main barriers for adopting digital twins' technology. Moreover, Ginni’s mean difference measure of dispersion showed that the stationary digital twin’s barriers adoption is needed to share the DT among multiple application systems involving multiple stakeholders.

The study’s findings offer valuable guidance to the construction industry. They help stakeholders adopt digital twins' technology, which, in turn, improves cost efficiency and sustainability. This adoption reduces project expenses and enhances environmental responsibility, providing companies a competitive edge in the industry.

This research rigorously explores barriers to Digital Twin (DT) implementation in the Hong Kong construction industry, employing a systematic approach that includes a comprehensive literature review, Ranking Analysis (RII) and Ginni’s coefficient of mean difference (GM). With a tailored focus on Hong Kong, the study aims to identify, analyze and provide novel insights into DT implementation challenges. Emphasizing practical relevance, the research bridges the gap between academic understanding and real-world application, offering actionable solutions for industry professionals, policymakers and researchers. This multifaceted contribution enhances the feasibility and success of DT implementation in construction projects within the Architecture, Engineering and Construction (AEC) sector.

The study aims to investigate the presence of herding behavior in the stock market of UK with a special emphasis on news sentiment regarding the economy. The authors focus on the news sentiment because in the current digital era, investors take their decision making on the basis of current trends projected by news and media platforms.

For empirical modeling, the authors use machine learning models to investigate the presence of herding behavior in UK stock market for the period starting from 2006 to 2021. The authors use support vector regression, single layer neural network and multilayer neural network models to predict the herding behavior in the stock market of the UK. The authors estimate the herding coefficients using all the models and compare the findings with the linear regression model.

The results show a strong evidence of herding behavior in the stock market of the UK during different time regimes. Furthermore, when the authors incorporate the economic uncertainty news sentiment in the model, the results show a significant improvement. The results of support vector regression, single layer perceptron and multilayer perceptron model show the evidence of herding behavior in UK stock market during global financial crises of 2007–08 and COVID’19 period. In addition, the authors compare the findings with the linear regression which provides no evidence of herding behavior in all the regimes except COVID’19. The results also provide deep insights for both individual investors and policy makers to construct efficient portfolios and avoid market crashes, respectively.

In the existing literature of herding behavior, news sentiment regarding economic uncertainty has not been used before. However, in the present era this parameter is quite critical in context of market anomalies hence and needs to be investigated. In addition, the literature exhibits varying results about the existence of herding behavior when different methodologies are used. In this context, the use of machine learning models is quite rare in the herding literature. The machine learning models are quite robust and provide accurate results. Therefore, this research study uses three different models, i.e. single layer perceptron model, multilayer perceptron model and support vector regression model to investigate the herding behavior in the stock market of the UK. A comparative analysis is also presented among the results of all the models. The study sheds light on the importance of economic uncertainty news sentiment to predict the herding behavior.

The Multi-Stakeholder Recommendation System learns consumer and producer preferences to make fair and balanced recommendations. Exclusive consumer-focused studies have improved the recommendation accuracy but lack in addressing producers' priorities for promoting their diverse items to target consumers, resulting in minimal utility gain for producers. These techniques also neglect latent and implicit stakeholders' preferences across item categories. Hence, this study proposes a personalized diversity-based optimized multi-stakeholder recommendation system by developing the deep learning-based diversity personalization model and establishing the trade-off relationship among stakeholders.

The proposed methodology develops the deep autoencoder-based diversity personalization model to investigate the producers' latent interest in diversity. Next, this work builds the personalized diversity-based objective function by evaluating the diversity distribution of producers' preferences in different item categories. Next, this work builds the multi-stakeholder, multi-objective evolutionary algorithm to establish the accuracy-diversity trade-off among stakeholders.

The experimental and evaluation results over the Movie Lens 100K and 1M datasets demonstrate that the proposed models achieve the minimum average improvement of 40.81 and 32.67% over producers' utility and maximum improvement of 7.74 and 9.75% over the consumers' utility and successfully deliver the trade-off recommendations.

The proposed algorithm for measuring and personalizing producers' diversity-based preferences improves producers' exposure and reach to various users. Additionally, the trade-off recommendation solution generated by the proposed model ensures a balanced enhancement in both consumer and producer utilities.

Project portfolio benefit (PPB) evaluation is crucial for project portfolio management decisions. However, PPB is complex in composition and affected by synergy and ambidexterity. Ignoring these characteristics can result in inaccurate assessments, impeding the management and optimization of benefit. Considering the above complexity of PPB evaluation, this study aims to propose a refined PPB evaluation model to provide decision support for organizations.

A back propagation neural network optimized via genetic algorithm and pruning algorithm (P-GA-BPNN) is constructed for PPB evaluation. First, the benefit evaluation criteria are established. Second, the inputs and expected outputs for model training and testing are determined. Then, based on the optimization of BPNN via genetic algorithm and pruning algorithm, a PPB evaluation model is constructed considering the impacts of ambidexterity and synergy on PPB. Finally, a numerical example was applied to validate the model.

The results indicate that the proposed model can be used for effective PPB evaluation. Moreover, it shows superiority in terms of MSE and fitting effect through extensive comparative experiments with BPNN, GA-BPNN, and SVM models. The robustness of the model is also demonstrated via data random disturbance experiment and 10-cross-validation. Therefore, the proposed model could serve as a valuable decision-making tool for PPB management.

This study extends prior research by integrating the impacts of synergy and ambidexterity on PPB when conducting PPB evaluation, which facilitates to manage and enhance PPB. Besides, the structural redundancy of existing assessment methods is solved through the dynamic optimization of the network structure via the pruning algorithm, enhancing the effectiveness of PPB decision-making tools.