Coherent Decisions Research Articles

Deep Recurrent Reinforcement Learning-Based Distributed Dynamic Spectrum Access in Multichannel Wireless Networks With Imperfect Feedback

This paper investigates Dynamic Spectrum Access (DSA) paradigm with imperfect feedback for multiuser wireless network. Each user selects an orthogonal channel in particular time slot to transmit packet with a certain transmission probability. In next time slot, the user who has transmitted a packet receives an ACK signal based on local observation. Bearing in mind the dynamic nature of wireless networks, it is appealing to develop a blended strategy to perform effective DSA. This paper aims to design a distributed Deep Reinforcement Learning (DRL) based scheme with an objective of maximizing network utility. In conventional DRL framework, it is assumed that the feedback received (ACK packet) is always correct but in wireless networks, it may be lost or corrupted due to noise. Furthermore, it is challenging to promise that the multiple agents will cooperate to make coherent decisions in order to accomplish the same objective, particularly under imperfect feedback. To tackle these challenges, this work proposes (i) Deep Recurrent Reinforcement Learning network with integrated GRU layer to optimize the network utility function and (ii) a feedback recovery mechanism using complete and incomplete replay buffers. Extensive simulations corroborate the success of proposed scheme in complex multiuser scenario and exhibit robustness against the detrimental effects of the imperfect feedback.

Joining metadata and textual features to advise administrative courts decisions: a cascading classifier approach

Decisions of regulatory government bodies and courts affect many aspects of citizens’ lives. These organizations and courts are expected to provide timely and coherent decisions, although they struggle to keep up with the increasing demand. The ability of machine learning (ML) models to predict such decisions based on past cases under similar circumstances was assessed in some recent works. The dominant conclusion is that the prediction goal is achievable with high accuracy. Nevertheless, most of those works do not consider important aspects for ML models that can impact performance and affect real-world usefulness, such as consistency, out-of-sample applicability, generality, and explainability preservation. To our knowledge, none considered all those aspects, and no previous study addressed the joint use of metadata and text-extracted variables to predict administrative decisions. We propose a predictive model that addresses the abovementioned concerns based on a two-stage cascade classifier. The model employs a first-stage prediction based on textual features extracted from the original documents and a second-stage classifier that includes proceedings’ metadata. The study was conducted using time-based cross-validation, built on data available before the predicted judgment. It provides predictions as soon as the decision date is scheduled and only considers the first document in each proceeding, along with the metadata recorded when the infringement is first registered. Finally, the proposed model provides local explainability by preserving visibility on the textual features and employing the SHapley Additive exPlanations (SHAP). Our findings suggest that this cascade approach surpasses the standalone stages and achieves relatively high Precision and Recall when both text and metadata are available while preserving real-world usefulness. With a weighted F1 score of 0.900, the results outperform the text-only baseline by 1.24% and the metadata-only baseline by 5.63%, with better discriminative properties evaluated by the receiver operating characteristic and precision-recall curves.

Enhanced Probabilistic Route Stability (EPRS) Protocol for Healthcare Applications of WBAN

Wireless Body Area Network (WBAN) is among the most promising technologies for enhancing life quality. WBANs enable constant monitoring of physiological processes by implanting or wearing small, low-power, intelligent sensor nodes in or on the human body. These sensor nodes may be placed either invasively or non-invasively. Patient data must be disseminated reliably and promptly for WBAN’s healthcare apps to function. For this reason, medical teams may use real-time apps for sharing vital information like blood pressure, an ECG, and an EEG. Critical data packets are delay-sensitive and must arrive at sink nodes within the time constraints that satisfy QoS for WBAN. However, networks’ unpredictable and dynamic nature (node mobility, link partitioning) makes reliable data transfer a challenging task. Additionally, postural mobility and ultra-short wireless range cause rapid topology changes, resulting in network partitioning. The network partitioning causes failure of data delivery to the sink or coordinator and causes a delay as well. In the case of normal data, it is not a big issue, but it is not tolerable for emergency data because it may be life-threatening. Consequently, compromising the link reliability and stability results in higher delays, increased packet re-transmissions, and decreased throughput performance. Therefore, we propose an Enhanced Probabilistic Route Stability (EPRS) scheme to address these issues. The proposed EPRS scheme introduces a cost function called Link Assessment Cost (LAC) that makes coherent decisions regarding route reliability in determining whether an active route is a good candidate for routing and satisfying QoS requirements. The LAC is based on two critical factors about link status, i.e., Route Stability Factor (RSF) and Expected Probability of link <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$E(p)$ </tex-math></inline-formula> . Based on these factors, a score is assigned to a link that determines the status (likelihood) of a link, either connected or disconnected. In this way, the multi-facet EPRS selects the most stable and reliable routes despite the disconnection in the networks, thereby improving the route stability and throughput, minimizing the end-to-end delay, route discovery calls, and re-transmissions as depicted by simulation results.

Exploring Online Activities to Predict the Final Grade of Student

Student success rate is a significant indicator of the quality of the educational services offered at higher education institutions (HEIs). It allows students to make their plans to achieve the set goals and helps teachers to identify the at-risk students and make timely interventions. University decision-makers need reliable data on student success rates to formulate specific and coherent decisions to improve students’ academic performance. In recent years, EDM has become an effective tool for exploring data from student activities to predict their final grades. This study presents a case study for predicting the students’ final grades based on their activities in Moodle Learning Management System (LMS) and attendance in online lectures conducted via Zoom by applying statistical and machine learning techniques. The data set consists of the final grades for 105 students who study Object-Oriented Programming at the University of Plovdiv during the 2021–2022 year, data for their activities in the online course (7057 records), and attendance to lectures (738). The predictions are based on 46 attributes. The Chi-square test is utilized to assess the association between students’ final grades and event context (lectures, source code, exercise, and assignment) and the relationships between attendance at lectures and final results. The logistic regression model is utilized to assess the actual impact of event context on “Fail” students in a multivariate setup. Four machine learning algorithms (Random Forest, XGBoost, KNN, and SVM) are applied using 70% of training data and 30% of test data to predict the students’ final grades. Five-fold cross validation was also utilized. The results show correlations between the students’ final grades and their activity in the online course and between students’ final grades and attendance at lectures. All applied machine learning algorithms performed moderately well predicting the students’ final results, as the Random Forest algorithm obtained the highest prediction accuracy—78%. The findings of the study clearly show that the Random Forest algorithm may be used to predict which students will fail after eight weeks. Such data-driven predictions are significant for teachers and decision-makers and allow them to take measures to reduce the number of failed students and identify which types of learning resources or student activities are better predictors of the student’s academic performance.

Risk heatmaps as visual displays: Opening movie studios after the COVID-19 shutdown.

Upon shutting down operations in early 2020 due to the COVID-19 pandemic, the movie industry assembled teams of experts to help develop guidelines for returning to operation. It resulted in a joint report, The Safe Way Forward, which was created in consultation with union members and provided the basis for negotiations with the studios. A centerpiece of the report was a set of heatmaps displaying SARS-CoV-2 risks for a shoot, as a function of testing rate, community infection prevalence, community transmission rate (R0), and risk measure (either expected number of cases or probability of at least one case). We develop and demonstrate a methodology for evaluating such complex displays, in terms of how well they inform potential users, in this case, workers deciding whether the risks of a shoot are acceptable. We ask whether individuals making hypothetical return-to-work decisions can (a) read display entries, (b) compare display entries, and (c) make inferences based on display entries. Generally speaking, respondents recruited through the Amazon MTurk platform could interpret the display information accurately and make coherent decisions, suggesting that heatmaps can communicate complex risks to lay audiences. Although these heatmaps were created for practical, rather than theoretical, purposes, these results provide partial support for theoretical accounts of visual information processing and identify challenges in applying them to complex settings.

A SURVEY ON ORGANIZATIONAL RESILIENCE IN IRANIAN RESTAURANTS DURING COVID-19

Purpose- The COVID-19 Pandemic influenced and damaged many small and medium businesses. Business resilience in any organization represents the strength and tolerance of that organization in times of crisis. In this study, a general picture of the quality of restaurant management in Iran is examined from the lens of business resilience related constructs adopted from Organizational Resilience HealthCheck, a free self-assessment tool from the Organizational Resilience web site of Dept. of Home Affairs of Australian government. Methodology- HealthCheck examines and provides benchmarks about the flexibility of the organization and the business to adapt and evolve in global markets to contain and address short-term shocks and long-term crises or challenges. The SMEs covered in this research include 52 restaurants in three major cities in Iran. The organizational resilience and the experiences accumulated from the COVID-19 outbreak have been investigated against independent variables, such as: leadership and decision making, network and social capital, situational awareness, and the employee’s engagements within the organization. These questions examine and review the components of leadership in the organization under critical conditions and organizational experiences in the crisis. Findings- The data and findings have shown that decision making related indicators, are correlated with indicators of business resilience. In the issue of Employee Engagement that represents the lack of employee’s engagement, there is a mild correlation with the problems of the organization and business. In other words, the lack of empathic environment. The existence of an administrative system helps to better prepare a business to identify crises and to behavioral readiness to face them. This approach in the administrative system will lead to more coherent decisions to allocate resources to face crises. There is a relatively strong correlation between familiarity with risk management and the ability to predict crises. Conclusion- The findings illustrate that management skills, knowledge, and awareness lead to the ability of anticipating crises before the occur. It has also been observed that familiarity with crisis management and risk will lead to the creation of guidelines and protocols to face risks. A strong parallel between behavioral readiness for crises in business and the ability to respond to the crisis means that by raising the awareness and pre-awareness of the crisis, the response is much faster in the event of a crisis. Behavioral readiness in the organization for crises is capable of identifying crises. In Iran, due to the lack of governmental support for this business, there were more severe problems, and the situation even forced many activists and investors in the field to invest in other markets and industries. The lack of governmental and businesses readiness for such crises can also be another reason for failing to succeed. Keywords: Organizational resilience, resilience, hospitality industry, restaurant industry, SMEs, crisis, Covid-19 JEL Codes: G12, G14, C22

Spirituality Led Ethical Decision Making with Yogic Yamas and Niyamas

If reason isn't the primary anchor in extraordinary crises, then what drives decision making? Is there a spirituality led ethical foundation to reality that goes beyond decision makers' perceptions of dichotomies? We examine how ethics and spirituality are part of one holistic framework shaping the organizational decision making processes. This conceptual paper addresses: How can Yogic Yamas and Niyamas (disciplinary restraints and observances) as expressions of spirituality led ethics, enrich ethical decision making towards a trustful environment sustainably? Three philosophical texts for Astānga Yoga in Indian spiritual traditions were used through hermeneutics based qualitative-research methodology. Among the salient contributions, we explore the concepts of Āstikya (belief or trust in higher consciousness) and Īsvarapranidhāna (committing what one does to higher consciousness) for enriching the discourse on spirituality led ethical decision making. We propose an integrative approach to achieve coherent decisions by bringing a universal and contextual spiritual base for coping with crises.

Explainable AI for Glaucoma Prediction Analysis to Understand Risk Factors in Treatment Planning

Glaucoma causes irreversible blindness. In 2020, about 80 million people worldwide had glaucoma. Existing machine learning models are limited to glaucoma prediction, where clinicians, patients, and medical experts are unaware of how data analysis and decision-making are handled. Explainable AI (XAI) and Interpretable Machine Learning (IML) create opportunities to increase user confidence in the decision-making process. This paper proposes XAI and IML models for analyzing glaucoma predictions/ results. XAI primarily uses Adaptive Neuro-Fuzzy Inference System (ANFIS) and Pixel Density Analysis (PDA) to provide trustworthy explanations for glaucoma predictions from infected and healthy images. IML uses Sub-modular Pick Local Interepratble Model-Agonistic Explanation (SPLIME) to explain results coherently. SP-LIME interprets Spike Neural Network (SNN) results. Using two different publicly available datasets, namely fundus images i.e. coherence tomography images of the eyes and clinical medical records of glaucoma patients, our experimental results show that XAI and IML models provide convincing and coherent decisions for clinicians/medical experts and patients.

Performance analysis of a DNN classifier for power system events using an interpretability method

Nowadays, there is a clear need for Machine Learning methods capable of extracting relevant and reliable information from synchrophasor data. In this paper, the application of an explainable data-driven method is carried out in order to inspect the performance of DNN classifier for event identification using synchrophasor measurements. The DNN classifier is the Long–Short Term Memory (LSTM) which is suitable for the extraction of dynamic features. The key advantage of this approach is the use of an interpretability inspection named SHAP (SHapley Additive exPlanation) values, based on cooperative game theory (Shapley values), which provide the means to evaluate the predictions of the LSTM and detecting possible bias. The main contributions are stated as follows: (i) it explains how the LSTM classifier is making its decisions; (ii) it helps the designer to improve the training of the classifier; (iii) certify that the resulting classifier has a consistent and coherent performance according to domain knowledge of the problem; (iv) when the user understands that the classifier is making coherent decisions, it clearly reduces the concerns of the application of DNN methods in critical infrastructure. Additionally, the proposed approach is evaluated using real synchrophasor event records from the Brazilian Interconnected Power System (BIPS).

Application of Statistical Monitoring Using Autocorrelated Data and With the Influence of Multicollinearity in a Steel Process

The purpose of this article is to demonstrate a practical application of control charts in an industrial process that has data auto-correlated with each other. Although the control charts created by Walter A. Shewhart are very effective in monitoring processes, there are very important statistical assumptions for Shewhart&amp;#39;s control charts to be applied correctly. Choosing the correct Control Chart is essential for managers to be able to make coherent decisions within companies. With this study, it was possible to demonstrate that the original data collected in the process, which at first appeared to have many special causes of variation, was actually a stable process (no anomalies present). However, this finding required the use of autoregressive models, multivariate statistics, autocorrelation and normality tests, multicollinearity analysis and the use of the EWMA control chart. It was concluded that it is of fundamental importance to choose the appropriate control chart for monitoring industrial processes, to ensure that changes in processes do not incorporate non-existent variations and do not cause an increase in the number of defective products.

Multi-Agent Deep Reinforcement Learning Multiple Access for Heterogeneous Wireless Networks With Imperfect Channels

This paper investigates a futuristic spectrum sharing paradigm for heterogeneous wireless networks with imperfect channels. In the heterogeneous networks, multiple wireless networks adopt different medium access control (MAC) protocols to share a common wireless spectrum and each network is unaware of the MACs of others. This paper aims to design a distributed deep reinforcement learning (DRL) based MAC protocol for a particular network, and the objective of this network is to achieve a global <inline-formula><tex-math notation="LaTeX">$\alpha$</tex-math></inline-formula> -fairness objective. In the conventional DRL framework, feedback/reward given to the agent is always correctly received, so that the agent can optimize its strategy based on the received reward. In our wireless application where the channels are noisy, the feedback/reward (i.e., the ACK packet) may be lost due to channel noise and interference. Without correct feedback, the agent (i.e., the network user) may fail to find a good solution. Moreover, in the distributed protocol, each agent makes decisions on its own. It is a challenge to guarantee that the multiple agents will make coherent decisions and work together to achieve the same objective, particularly in the face of imperfect feedback channels. To tackle the challenge, we put forth (i) a feedback recovery mechanism to recover missing feedback information, and (ii) a two-stage action selection mechanism to aid coherent decision making to reduce transmission collisions among the agents. Extensive simulation results demonstrate the effectiveness of these two mechanisms. Last but not least, we believe that the feedback recovery mechanism and the two-stage action selection mechanism can also be used in general distributed multi-agent reinforcement learning problems in which feedback information on rewards can be corrupted.

Measuring Uncertainty in Forensic Science

This paper aims at describing the ways in which uncertainty is (or is not) measured in the field of forensic science and how the measure of uncertainty can be used to make better judicial decisions. From the traditional fingerprint comparison to the latest advances in forensic DNA analysis, we discuss the advantages and drawbacks of various ways of reporting forensic science results. We point to past and current controversies, and analyze what remains to be done in the field to ensure that the probative value of forensic science evidence is communicated to judicial fact finders in a way that is scientifically robust, balanced and transparent, to allow them to make coherent decisions.

Towards a Sustainable Landscape: Constructing Identities and Ambitions in a Citizen Initiative in the Making

The recent proliferation of citizen initiatives that aim to contribute to sustainable landscape transition prompted us to study how members of such an initiative in-the-making try to position themselves in their environment in order to make a meaningful contribution. We use a single case study in the east of the Netherlands to study how members discursively construct identities and ambitions through the inclusion of people and ideas over time. We applied an interactional framing analysis to 20 audio-recorded and transcribed meetings of the citizen initiative. The results show that various actors and ideas were included over time, resulting in the construction of different ambitions and identities over time. Ambitions changed in response to new event and changing circumstances. To justify these changing ambitions, the members constructed new identities during their conversations, using different interactional framing strategies. The study reveals that the process of finding an ambition and identity continuously changed direction, paradoxically, due to a lack of direction that hindered the members in making coherent and sustainable decisions. We conclude that a citizen initiative should actively interact with their relation groups to find a direction that supports the process of effectively positioning their initiative and contributes to the shared goal of improving the quality of the living environment.

Operational research applied to decisions in home health care: A systematic literature review

The efficient deployment of resources in home-based care is considered crucial for the sustainability of health and social care systems worldwide. The aim of this study was to identify and review operational research approaches to support decision-making in home health care. We identified a set of linked decisions at different planning levels (strategic, tactical, operational) and conducted a systematic review of operational research approaches used to address these decisions. We also sampled OR literature applied to analogous decisions in other settings. The 77 papers selected focused predominantly on solutions for staff-to-patient allocation, visit scheduling and staff routing, few of which were adopted by organisations. Few studies dealt with tactical decisions of team size and composition or strategic decisions of districting, and we found no studies on contract design for commissioning home health care, on staff role definitions or on reassessment of patient need. Integrative work is scarce and the aspects of system performance considered are variable and diverse. For these reasons the literature does not provide guidance for home health care services aspiring to effective and coherent decisions across planning levels. OR approaches from other areas of application provide some insights for future research aimed at addressing this shortfall.

The Road to Women Empowerment through the Mechanism of Self Help Groups

Women constitute 48.10 percent of the population of India and only 27 percent of this adult women population has a steady income, which makes women ‘poorest of the poor (World Bank 2019). It has been asserted that comprehensive progression and inclusive development in India would be conceivable only when women are considered as equivalent agents in the development debate (Mazumdar 2004). In this parlance, the development agencies have increasingly regarded ‘empowerment’ as an essential objective to improve the status of marginalized women in India.Though empowerment as a process induces the social environment which enables individuals to make coherent decisions, women empowerment takes a step further by enabling women to become confident, courageous, and self-reliant to make decisions in and outside the household (Hulme and Moseley 1996; Buckley 1997). Amidst the broad umbrella of women empowerment, economic empowerment has significantly influenced the policymakers, which is ascertained to bridge this gap between poverty alleviation strategy and empowerment of women which eventually aims to dissuade gender inequalities and gender power relations (World Bank 2017). In this stride, microfinance programs, consisting of a broad range of services such as microcredits, micro-insurance, micro-savings, and micro- pensions, are considered admissible tools (Bateman and Chang 2012: 33). Though the microfinance programs have emerged as a key vehicle to accelerate women empowerment (Sankaran 2005), there have arisen doubts about its potency due to hegemony of its ‘financial systems approach’ and dichotomy of women’s well-being and agency (Johnson and Kidder 1999; Mayoux 1999; Kabeer 1998).The goal of this paper is to examine the mirage of microfinance and women empowerment by critically analyzing the workings of the Self Help Group Bank Linkage Programme (‘SHG’), an offshoot of microfinance programs in India (‘Research Question’). The need for this assessment becomes even more critical now when women are at the epicenter of the COVID 19 pandemic, both socially and economically. I will be exploring the impact of SHGs on women's empowerment as viewed from their participation in agency, resources, and achievements (Kabeer 1999). I will further investigate whether economic empowerment, as offered by the SHGs, leads to economic development and democratization for the collective. To test the hypothesis of the paper, I will be inspecting the workings of Ankuram Sangamam Poram (‘ASP’), an SHG federation, in the state of Andhra Pradesh, India. My analysis of the research question will be split into five sections: 1. Tenets and discourses of women empowerment2. Growth of SHGs in India and its co-relation with women empowerment 3. SHG’s women’s empowerment goal vis-à-vis women’s democratization4. Case Study Analysis of ASP5. Conclusion

The role of the BRICS group in the international arena: a legal network under construction

ABSTRACTStarting from the first summit, which focused on the economic dimension, the BRICS countries have broadened the group’s horizons to other issues. Contrary to sceptical predictions, the group was able, at that time, to overcome differences and stress common features. Under these premises, this paper will briefly examine the instruments used by BRICS to create a unique form of legal network, based on soft law policies and legal transplant and exchange of best law practices; however, the absence of coherent decisions in the group’s external actions and the lack of implementation of certain internal projects also represent relevant drawbacks. Through the analysis of BRICS’ internal and external activities and forms of cooperation, this work aims at discussing important issues related to the future of the group and its role in the international dimension: will BRICS be able to act as a unified bloc in the global arena? Will these states be able to strengthen their cooperation? In conclusion, the BRICS union is an innovative phenomenon of global cooperation and well worth studying; nonetheless, some critical reflections and developments are required in order to consider the group a successful actor on the international scene.

Temporal integration of mitochondrial stress signals by the PINK1:Parkin pathway

BackgroundThe PINK1:Parkin pathway regulates the autophagic removal of damaged and dysfunctional mitochondria. While the response of this pathway to complete loss of ΔΨm, as caused by high concentrations of mitochondrial ionophores, has been well characterized, it remains unclear how the pathway makes coherent decisions about whether to keep or purge mitochondria in situations where ΔΨm is only partially lost or exhibits fluctuations, as has been observed in response to certain types of cellular stress.ResultsTo investigate the responses of the PINK1:Parkin pathway to mitochondrial insults of different magnitude and duration, controlled titration of the mitochondrial protonophore, CCCP, was used to manipulate ΔΨm in live cells, and the dynamics of PINK1 and Parkin recruitment was measured by fluorescence microscopy. In contrast to the stable accumulation of PINK1 and Parkin seen at completely depolarized mitochondria, partial depolarization produced a transient pulse of PINK1 stabilization and rapid loss, which was driven by small fluctuations in ΔΨm. As the rate of Parkin dissociation from the mitochondria and phospho-polyubiquitin chain removal was comparatively slow, repetitive pulses of PINK1 were able to drive a slow step-wise accumulation of Parkin and phospho-polyubiquitin leading to deferred mitophagy.ConclusionThese data suggest that the PINK1:Parkin mitophagy pathway is able to exhibit distinct dynamic responses to complete and partial mitochondrial depolarization. In this way, the pathway is able to differentiate between irretrievably damaged mitochondria and those showing signs of dysfunction, promoting either rapid or delayed autophagy, respectively.

Toward an Improved Monitoring of Engineering Projects

With the growing economic pressure, one lever for companies to be competitive is to efficiently monitor projects. To this goal, the different processes involved in the project must be carefully supervised and the project manager needs to be well-informed on their state and progress to take the best decisions thanks to accurate performances of indicators, process, and project. Another key factor of successful decision-making in engineering projects beyond taking into account information from the project manager on the project management (PM) is to consider information from the systems engineer on the product development. This paper proposes a process to monitor engineering projects relying on a set of project performance indicators that integrate the views of both project manager and systems engineer. This process includes three main activities: 1) defining project performance indicators related to the processes described by international guides and standards; 2) valuating and weighting these indicators by consulting project managers and systems engineers; and 3) constructing a hierarchical framework of indexes to support project monitoring. This proposal thus refers to the practices described in PM and systems engineering norms and improves them by involving project managers and systems engineers into decision-making, with the goal to take more coherent decisions.

Day-Ahead Hierarchical Probabilistic Load Forecasting With Linear Quantile Regression and Empirical Copulas

In the smart grid era, high granular data play an important role in providing an enormous amount of information for industry and commerce, both temporally and spatially. With massive data, a hierarchical structure can be constructed, containing load series at diverse levels. With the fluctuation and uncertainty of power supply and demand increasing rapidly, hierarchical probabilistic load forecasting is necessary for a hierarchy formed by power system network, which can provide comprehensive information on electricity consumption at different levels. System operators or power market participants can make coherent decisions based on coherent forecasting. The challenge for hierarchical probabilistic load forecasting is how to produce probabilistically coherent forecasts. In order to simplify the prediction procedure and improve the prediction accuracy, an effective approach that could generate probabilistically coherent forecasts for a hierarchy is introduced in this paper. The proposed methodology has three major achievements: 1) a naive multiple linear regression model is proposed for bottom-level series; 2) a novel approach of combining quantile regression and empirical copulas is proposed to estimate the joint distribution of random variables; 3) to improve the prediction accuracy, a weighted correction method based on constrained quantile regression is introduced to adjust predictive distributions at the bottom level. In case of studies, the effectiveness of our proposed method is verified by using two public datasets. Compared with four benchmarks, evaluation results show that the proposed approach makes better performance.

Textile reinforced mortars systems: a sustainable way to retrofit structural masonry walls under tsunami loads

Retrofit of existing structures is one of the most demanding and challenging tasks for practitioners. The research community is providing newer solutions and systems improving the compatibility and sustainability both in environmental and conservation fields. Textile reinforced mortars (TRMs) represent a good balance between strength provided by fibres and compatibility of mortars by the matrix. The main aim of the paper is to provide fast assessment tools for the effects of tsunami actions on masonry structures, assuming as main parameter the inundation depth, and to provide a comparably fast tool to design retrofit interventions with innovative strengthening systems. The peculiar multilinear behaviour of systems, like as TRM, is accounted for and some design equations and charts are provided, discussing the peculiarities of the material property variability to orient the designer to coherent and effective decisions; potential uncertainty and variability of substrate masonry are taken into account, too.