Search results

Near-fault pulse-like ground motions have distinct and very severe effects on reinforced concrete (RC) structures. However, there is a paucity of recorded data from Near-Fault Ground Motions (NFGMs), and thus forecasting the dynamic seismic response of structures, using conventional techniques, under such intense ground motions has remained a challenge.

The present study utilizes a 2D finite element model of an RC structure subjected to near-fault pulse-like ground motions with a focus on the storey drift ratio (SDR) as the key demand parameter. Five machine learning classifiers (MLCs), namely decision tree, k-nearest neighbor, random forest, support vector machine and Naïve Bayes classifier , were evaluated to classify the damage states of the RC structure.

The results such as confusion matrix, accuracy and mean square error indicate that the Naïve Bayes classifier model outperforms other MLCs with 80.0% accuracy. Furthermore, three MLC models with accuracy greater than 75% were trained using a voting classifier to enhance the performance score of the models. Finally, a sensitivity analysis was performed to evaluate the model's resilience and dependability.

The objective of the current study is to predict the nonlinear storey drift demand for low-rise RC structures using machine learning techniques, instead of labor-intensive nonlinear dynamic analysis.

The ways communities have regarded disasters and natural hazards in the cultural sphere can provide a lens to inform the understanding of their ability to withstand shocks and the factors that led to such conditions. Only by tracing the complexities of creating, transmitting and preserving a culture of preparedness among disaster-vulnerable communities can researchers and practitioners claim to be working toward policy that is informed by the communities’ own experience and design policy or programming on their behalf.

In efforts to prevent, respond to and recover from disasters, what alternatives are available to top-down strategies for imposing expert knowledge on lay publics? How is the context of communities’ socioecological context understood in the development of programs and policy on their behalf? What can be learned from community narratives and cultural practices to inform disaster risk reduction?

I collected examples of how different communities perceive, prevent and respond to disaster through art, music and literature and analyzed how these were embedded into local narratives and how historical context influenced such approaches. My findings show that communities use cultural practices to contextualize experiences of hazards into their collective narrative; that is, storytelling and commemoration make disasters comprehensible. By incorporating such findings into existing policies and programs, institutions may be able to more effectively apply them to affected communities or build new ones around their actual needs and experiences.

By framing disasters as an anthropological inquiry, practitioners can better recognize the influence of a place’s nuance in the disaster management canon–guided by these details, not despite them.

Prefabricated columns connected by grouted sleeves are increasingly used in practical projects. However, seismic fragility analyses of such structures are rarely conducted. Seismic fragility analysis has an important role in seismic hazard evaluation. In this paper, the seismic fragility of sleeve connected prefabricated column is analyzed.

A model for predicting the seismic demand on sleeve connected prefabricated columns has been created by incorporating engineering demand parameters (EDP) and probabilities of seismic failure. The incremental dynamics analysis (IDA) curve clusters of this type of column were obtained using finite element analysis. The seismic fragility curve is obtained by regression of Exponential and Logical Function Model.

The IDA curve cluster gradually increased the dispersion after a peak ground acceleration (PGA) of 0.3 g was reached. For both columns, the relative displacement of the top of the column significantly changed after reaching 50 mm. The seismic fragility of the prefabricated column with the sleeve placed in the cap (SPCA) was inadequate.

The sleeve was placed in the column to overcome the seismic fragility of prefabricated columns effectively. In practical engineering, it is advisable to utilize these columns in regions susceptible to earthquakes and characterized by high seismic intensity levels in order to mitigate the risk of structural damage resulting from ground motion.

The purpose of this study is to present the possibilities of co-creation-type reconstruction methods by focusing on examples of reconstruction in communities affected by the 2011 disaster in Japan. This is because the reconstruction of a community is not a matter of supplementing what has been physically lost, but must include social and cultural aspects. We will also conduct research based on the idea that by placing the residents, who are the bearers of the community, in the lead role, we can achieve a recovery that promotes maturity, rather than a recovery that overwrites the community.

This research was initially conducted for the purpose of reconstruction assistance, but in the process, the author conducted research using information obtained through material surveys on local history and self-governing activities, interview surveys on pre-disaster life, and participatory observation of reconstruction activities. In order to extract knowledge on co-creative reconstruction methods, the author focused on the actual state of cooperation between residents, experts involved in reconstruction support, and the government, based on past research conducted by the author, and extracted what could be considered co-creation from this.

Co-creative reconstruction is defined as a state in which a shared vision for reconstruction is created by each organization involved in the reconstruction process, with the residents at the core, and collaboration is generated beyond the organizational framework in order to achieve the objectives. This case study can be divided into the following three stages: the stage where the local residents start the recovery process, the stage where a vision for recovery is drawn up based on the recovery project organized by the government, and the stage where collaboration beyond the organizational framework is created to achieve the recovery vision.

Compared to normal urban development, reconstruction projects in disaster-stricken areas are carried out simultaneously in a short period of time. Therefore, in order to capture the details of reconstruction, it is necessary to limit the target area and continue participant observation. However, the limited number of areas to be studied makes it difficult to conduct comparative verification. In addition, the unclear concept of “co-creation” requires the formation of common values through the verification of various case studies. Therefore, it is essential to form an environment in which various case studies can be collected and discussed.

Many of the research reports on earthquake recovery are extracts on specific themes. As a result, it is difficult to obtain an overall picture of how specific areas are recovering. As such, there are few examples that can serve as a reference when confronting reconstruction and an exploratory approach to the unclear future is required. Therefore, this study has practical findings in that it presents concrete sample information by clearly indicating issues and reconstruction systems on a long-term time horizon.

It is nonsense to impose a uniform recovery plan in the midst of a mature society with increasingly diverse values. It is necessary to explore the possibility of bottom-up reconstruction in which residents play a leading role as a way to realize individualized and diverse reconstruction. This study presents the possibility of promoting reconstruction while maintaining equal relationships among residents, experts, and the government.

First, the study captures the actual situation of the village before the earthquake and the actual situation of the village during the reconstruction process, using the village as the basic unit. Second, it captures the reconstruction process of the village over a 10-year time frame. According to a specific timeline, the activities, discussions, and institutional changes to promote reconstruction are positioned. Third, in the limited phase of earthquake reconstruction, the project is providing information and analysis from a comprehensive and multifaceted perspective by narrowing down the target areas and continuing high-resolution surveys.

Several studies were made on paired site and soil–structure interaction (SSI) effects, but most of them were site specific. This paper aims to investigate the impact of SSI effects in conjunction with local soil condition effects on the seismic response of typical multistory low- to mid-rise–reinforced concrete (RC) buildings resting on Algerian regulatory design sites through a global explicit transfer function (TF).

A preliminary quantification of SSI effects associated with site effects is carried out through a frequency-domain solution based on the concept of rock-to-soil surface displacement TF performed for each design site category. It results from the combination of the TFs of structure, foundation and soil and reflects how seismic waves are amplified due to changes in the geological contrast between the rock and overlying soil deposits. As well, response modification factors, denoting displacement ratios of the building responses within the flexible and site-structure conditions with respect to the fixed-base one, are carried out.

In the context of Algerian seismic regulation, the study provides a clear vision of how and when site or SSI effects are expected to be influential, as opposed to the fixed-base hypothesis still retained by the current regulation. This helps engineers to be aware of the extent of the expected seismic damage.

The research applies to low- to mid-rise RC buildings within the Algerian seismic regulation, but it may also be expanded to other examples that fall under other seismic regulations.

The response modification ratio is a quantitative approach to assessing response fluctuations. It draws attention to how the roof level drift varies depending on the condition. These results can be used as numerical parameters in structural seismic design when the structure is comparable because they provide useful information about how the two phenomena interact with the structure.

The study goes beyond particular situations dealing with site specific and offers effective indicators and quantitative evaluation of combined site and SSI effects according to the current national seismic provisions, where no indication about site or SSI effects exists.

Purpose: The study aims to analyse and discuss the effect of COVID-19 on businesses. The chapter discusses the various machine learning (ML) tools and techniques, which can help in better decision making by businesses in the present world.

Need for the Study: COVID-19 has increased the role of VUCA elements in the business environment, and there is a need to address the challenges faced by businesses in such environment. ML and artificial learning can help businesses in facing such challenges.

Methodology: The focus and approach of the chapter are in the context of using artificial intelligence (AI) and ML techniques for decision making during the COVID-19 pandemic in a VUCA business environment.

Findings: The key findings and their implications emphasise the importance of understanding and implementing AI and ML techniques in business strategies during times of crisis.

Practical Implications: The chapter’s content is in the context of using AI and ML techniques during the COVID-19 pandemic and in a VUCA business environment.

The purpose of this paper is the dynamic analysis and seismic damage assessment of steel sheet pile quay wall with inelastic behavior underground motions using several accelerograms.

Finite element analysis is conducted using the Plaxis 2D software to generate the numerical model of quay wall. The extension of berth 25 at the port of Bejaia, located in northeastern Algeria, represents a case study. Incremental dynamic analyses are carried out to examine variation of the main response parameters under seismic excitations with increasing Peak ground acceleration (PGA) levels. Two global damage indices based on the safety factor and bending moment are introduced to assess the relationship between PGA and the damage levels.

The results obtained indicate that the sheet pile quay wall can safely withstand seismic loads up to PGAs of 0.35 g and that above 0.45 g, care should be taken with the risk of reaching the ultimate moment capacity of the steel sheet pile. However, for PGAs greater than 0.5 g, it was clearly demonstrated that the excessive deformations with material are likely to occur in the soil layers and in the structural elements.

The main contribution of the present work is a new double seismic damage index for a steel sheet pile supported quay wharf. The numerical modeling is first validated in the static case. Then, the results obtained by performing several incremental dynamic analyses are exploited to evaluate the degradation of the soil safety factor and the seismic capacity of the pile sheet wall. Computed values of the proposed damage indices of the considered quay wharf are a practical helping tool for decision-making regarding the seismic safety of the structure.

Contemporary stochastic optimal control by synergy of the probability density evolution method (PDEM) and conventional optimal controller exhibits less capability to guarantee economical energy consumption versus control efficacy when non-stationary stochastic excitations drive hysteretic structures. In this regard, a novel multiscale stochastic optimal controller is invented based on the wavelet transform and the PDEM.

For a representative point, a conventional control law is decomposed into sub-control laws by deploying the multiresolution analysis. Then, the sub-control laws are classified into two generic control laws using resonant and non-resonant bands. Both frequency bands are established by employing actual natural frequency(ies) of structure, making computed efforts depend on actual structural properties and time-frequency effect of non-stationary stochastic excitations. Gain matrices in both bands are then acquired by a probabilistic criterion pertaining to system second-order statistics assessment. A multi-degree-of-freedom hysteretic structure driven by non-stationary and non-Gaussian stochastic ground accelerations is numerically studied, in which three distortion scenarios describing uncertainties in structural properties are considered.

Time-frequency-dependent gain matrices sophisticatedly address non-stationary stochastic excitations, providing efficient ways to independently suppress vibrations between resonant and non-resonant bands. Wavelet level, natural frequency(ies), and ratio of control forces in both bands influence the scheme’s outcomes. Presented approach outperforms existing approach in ensuring trade-off under uncertainty and randomness in system and excitations.

Presented control law generates control efforts relying upon resonant and non-resonant bands, and deploys actual structural properties. Cost-function weights and probabilistic criterion are promisingly developed, achieving cost-effectiveness of energy demand versus controlled structural performance.

This research proposes a novel risk assessment model to elucidate the risk propagation process of industrial safety accidents triggered by natural disasters (Natech), identifies key factors influencing urban carrying capacity and mitigates uncertainties and subjectivity due to data scarcity in Natech risk assessment.

Utilizing disaster chain theory and Bayesian network (BN), we describe the cascading effects of Natechs, identifying critical nodes of urban system failure. Then we propose an urban carrying capacity assessment method using the coefficient of variation and cloud BN, constructing an indicator system for infrastructure, population and environmental carrying capacity. The model determines interval values of assessment indicators and weights missing data nodes using the coefficient of variation and the cloud model. A case study using data from the Pearl River Delta region validates the model.

(1) Urban development in the Pearl River Delta relies heavily on population carrying capacity. (2) The region’s social development model struggles to cope with rapid industrial growth. (3) There is a significant disparity in carrying capacity among cities, with some trends contrary to urban development. (4) The Cloud BN outperforms the classical Takagi-Sugeno (T-S) gate fuzzy method in describing real-world fuzzy and random situations.

The present research proposes a novel framework for evaluating the urban carrying capacity of industrial areas in the face of Natechs. By developing a BN risk assessment model that integrates cloud models, the research addresses the issue of scarce objective data and reduces the subjectivity inherent in previous studies that heavily relied on expert opinions. The results demonstrate that the proposed method outperforms the classical fuzzy BNs.

With the growth of organizations and businesses, customer acquisition and retention processes have become more complex in the long run. That is why customer lifetime value (CLV) has become crucial to sales managers. Predicting the CLV is a strategic weapon and competitive advantage in increasing profitability and identifying customers with more splendid profitability and is one of the essential key performance indicators (KPI) used in customer segmentation. Thus, this paper proposes a stacked ensemble learning method, a combination of multiple machine learning methods, for CLV prediction.

In order to utilize customers’ behavioral features for predicting the value of each customer’s CLV, the data of a textile sales company was used as a case study. The proposed stacked ensemble learning method is compared with several popular predictive methods named deep neural networks, bagging support vector regression, light gradient boosting machine, random forest and extreme gradient boosting.

Empirical results indicate that the regression performance of the stacked ensemble learning method outperformed other methods in terms of normalized rooted mean squared error, normalized mean absolute error and coefficient of determination, at 0.248, 0.364 and 0.848, respectively. In addition, the prediction capability of the proposed method improved significantly after optimizing its hyperparameters.

This paper proposes a stacked ensemble learning method as a new method for accurate CLV prediction. The results and comparisons support the robustness and efficiency of the proposed method for CLV prediction.