Specific Time Horizon Research Articles

Cyclinaclity Effects of Exchange Rates and Oil Prices

Understanding the concept of time scales is crucial when modeling economic and financial decisions. Within the time-frequency domain, this study delves into the relationship between fluctuations in oil prices and exchange rates across major oil-importing and exporting countries. The investigation employs various cross-wavelet techniques within the continuous wavelet transform framework, with a particular focus on wavelet coherence and phase-difference over the period 2000 to 2020. The results underscore a notable diversity in the connection between the oscillations of oil prices and exchange rates across diverse countries. This relationship is subject to temporal variations and is contingent upon the specific time horizon under consideration. In particular, our analysis reveals strong co-movements between oil prices and exchange rates across various time intervals and frequencies. Importing oil countries like New Zealand, Singapore, Brazil, and Taiwan exhibit particularly pronounced co-movements. Similarly, exporting oil countries such as Kuwait, Mexico, Russia, and Canada also display strong associations between oil prices and exchange rates. These correlations are intricately tied to key macroeconomic events, further highlighting the complex interplay between oil prices and exchange rate movements in different global regions. While a robust connection is evident in numerous countries, the strength of the relationship appears significantly weaker in several others. This variance underscores the nuanced nature of the association between the fluctuations in oil prices and exchange rates across the global landscape.

Mineral policy and sustainable development goals: Volatility forecasting in the Global South's minerals market

This paper aims to evaluate the volatility of precious metals, specifically Palladium, Gold, and Platinum, within the context of the global minerals market. The research focuses on understanding the price dynamics of these metals and their implications for sustainable development, particularly in the Global South. The study employs a comprehensive approach, utilizing advanced machine learning and deep learning models such as GRU, Huber, Lasso, LSTM, Random Forest, Ridge Regression, SVM, ANN, and XGBoost. These models are assessed based on their forecasting accuracy for different time horizons, using metrics such as RMSE and MAPE. The findings reveal that the ANN, XGBoost, and LSTM models exhibit robust performance in forecasting the volatility of precious metals across various time horizons. The research highlights the unique volatility patterns of each metal and underscores the effectiveness of machine learning techniques in capturing these dynamics. The study acknowledges limitations such as the exclusion of macroeconomic and geopolitical factors in the forecasting models. Future research is suggested to integrate these factors to enhance forecasting accuracy. The study's findings are pivotal for investors, policymakers, and market regulators, especially in the context of the Global South and sustainable development. The research offers valuable insights for risk management strategies, investment planning, and policy formulation aimed at promoting market stability and sustainable economic growth. The study emphasizes the importance of selecting appropriate forecasting models based on specific time horizons and market requirements.

ICEEMDAN-Informer-GWO: a hybrid model for accurate wind speed prediction.

Extensive research has been diligently conducted on wind energy technologies in response to pressing global environmental challenges and the growing demand for energy. Accurate wind speed predictions are crucial for the effective integration of large wind power systems. This study presents a novel and hybrid framework called ICEEMDAN-Informer-GWO, which combines three components to enhance the accuracy of wind speed predictions. The improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) component improves the decomposition of wind speed data, the Informer model provides computationally efficient wind speed predictions, and the grey wolf optimisation (GWO) algorithm optimises the parameters of the Informer model to achieve superior performance. Three different sets of wind speed prediction (WSP) models and wind farm data from Block Island, Gulf Coast, and Garden City are used to thoroughly assess the proposed hybrid framework. This evaluation focusses on WSP for three specific time horizons: 5minutes, 30minutes, and 1hour ahead. The results obtained from the three conducted experiments conclusively demonstrate that the proposed hybrid framework exhibits superior performance, leading to statistically significant improvements across all three time horizons.

Performance of deep reinforcement learning algorithms in two-echelon inventory control systems

This study conducts a comprehensive analysis of deep reinforcement learning (DRL) algorithms applied to supply chain inventory management (SCIM), which consists of a sequential decision-making problem focussed on determining the optimal quantity of products to produce and ship across multiple capacitated local warehouses over a specific time horizon. In detail, we formulate the problem as a Markov decision process for a divergent two-echelon inventory control system characterised by stochastic and seasonal demand, also presenting a balanced allocation rule designed to prevent backorders in the first echelon. Through numerical experiments, we evaluate the performance of state-of-the-art DRL algorithms and static inventory policies in terms of both cost minimisation and training time while varying the number of local warehouses and product types and the length of replenishment lead times. Our results reveal that the Proximal Policy Optimization algorithm consistently outperforms other algorithms across all experiments, proving to be a robust method for tackling the SCIM problem. Furthermore, the (s, Q)-policy stands as a solid alternative, offering a compromise in performance and computational efficiency. Lastly, this study presents an open-source software library that provides a customisable simulation environment for addressing the SCIM problem, utilising a wide range of DRL algorithms and static inventory policies.

Climate change effects on rainfall extreme value distribution: the role of skewness

Quantifying the potential effects of Climate Change (CC) on hydrological scales is a topic with a more and more increasing interest for the scientific community, given the CC impact on agriculture, industry, economy, human health, ecosystems, among the others. In this context, the paper focuses on the sub-daily Annual Maxima (AM) of rainfall height time series, and specifically on the crucial role played by initial skewness, i.e. the skewness of the observed rainfall series used to evaluate potential parametric trends. Here a quick and user-friendly methodology is proposed, that is aimed at quantifying plausible future changes in terms of probability distributions assumed at rain gauge scale, from projections of any climatic model. In detail, the Generalized Extreme Value (GEV) and the Two-Component Extreme Value (TCEV) distributions are adopted as probability functions suitable for modelling observed rainfall AM series, which could increase their frequency and magnitude into future horizons under CC. EURO-CORDEX projections for Europe are considered, under the hypothesis that the values of the change factor, i.e. the ratio between the values of a specific quantile at two specific time horizons, are invariant when moving from an areally-averaged scale (typical for any climate model) to a point rain gauge scale, which induces that future changes are provided (in terms of frequency and magnitude of extreme events) without the need of any spatial downscaling from the assumed projections. The proposed methodology can contribute to hazard quantification associated to potential climate changes, and thus it can play a crucial role in the assessment of hydraulic structures resilience; the obtained results, specific for the study area of Italy, but easily extendable on a global scale, showed that larger increases in frequency of future heavy events are expected for time series with “EV1 alike” values of initial skewness.

Deep learning-based identification of eyes at risk for glaucoma surgery

To develop and evaluate the performance of a deep learning model (DLM) that predicts eyes at high risk of surgical intervention for uncontrolled glaucoma based on multimodal data from an initial ophthalmology visit. Longitudinal, observational, retrospective study. 4898 unique eyes from 4038 adult glaucoma or glaucoma-suspect patients who underwent surgery for uncontrolled glaucoma (trabeculectomy, tube shunt, xen, or diode surgery) between 2013 and 2021, or did not undergo glaucoma surgery but had 3 or more ophthalmology visits. We constructed a DLM to predict the occurrence of glaucoma surgery within various time horizons from a baseline visit. Model inputs included spatially oriented visual field (VF) and optical coherence tomography (OCT) data as well as clinical and demographic features. Separate DLMs with the same architecture were trained to predict the occurrence of surgery within 3 months, within 3–6 months, within 6 months–1 year, within 1–2 years, within 2–3 years, within 3–4 years, and within 4–5 years from the baseline visit. Included eyes were randomly split into 60%, 20%, and 20% for training, validation, and testing. DLM performance was measured using area under the receiver operating characteristic curve (AUC) and precision-recall curve (PRC). Shapley additive explanations (SHAP) were utilized to assess the importance of different features. Model prediction of surgery for uncontrolled glaucoma within 3 months had the best AUC of 0.92 (95% CI 0.88, 0.96). DLMs achieved clinically useful AUC values (> 0.8) for all models that predicted the occurrence of surgery within 3 years. According to SHAP analysis, all 7 models placed intraocular pressure (IOP) within the five most important features in predicting the occurrence of glaucoma surgery. Mean deviation (MD) and average retinal nerve fiber layer (RNFL) thickness were listed among the top 5 most important features by 6 of the 7 models. DLMs can successfully identify eyes requiring surgery for uncontrolled glaucoma within specific time horizons. Predictive performance decreases as the time horizon for forecasting surgery increases. Implementing prediction models in a clinical setting may help identify patients that should be referred to a glaucoma specialist for surgical evaluation.

Waste management regulatory framework in the circular economy context

One of the main challenges regarding the transition to a circular economy at the European level is waste management and achieving specific objectives. By 2025, the recycling and reuse rate of municipal waste should reach 55% and the total volume of recycled packaging 65%, according to European Directives (Waste Directive 05/07/2018). Statistical data and EEA reports are not encouraging: most European countries will not be able to reach these targets until 2025. The current work aims to analyze European legislation regarding waste management but also the national transposition measures communicated by the Member States. The reference statistical data regarding the efficiency of waste management, are also analyzed, at the member states level and at national level, to determine to what extent Romania has reached the targets set by the European Commission regarding waste management, depending on the specific time horizon set by the reference legislative policies.

Waste management regulatory framework in the circular economy context

One of the main challenges regarding the transition to a circular economy at the European level is waste management and achieving specific objectives. By 2025, the recycling and reuse rate of municipal waste should reach 55% and the total volume of recycled packaging 65%, according to European Directives (Waste Directive 05/07/2018). Statistical data and EEA reports are not encouraging: most European countries will not be able to reach these targets until 2025. The current work aims to analyze European legislation regarding waste management but also the national transposition measures communicated by the Member States. The reference statistical data regarding the efficiency of waste management, are also analyzed, at the member states level and at national level, to determine to what extent Romania has reached the targets set by the European Commission regarding waste management, depending on the specific time horizon set by the reference legislative policies.

The role of long-term power-law memory in controlling large-scale dynamical networks

Controlling large-scale dynamical networks is crucial to understand and, ultimately, craft the evolution of complex behavior. While broadly speaking we understand how to control Markov dynamical networks, where the current state is only a function of its previous state, we lack a general understanding of how to control dynamical networks whose current state depends on states in the distant past (i.e. long-term memory). Therefore, we require a different way to analyze and control the more prevalent long-term memory dynamical networks. Herein, we propose a new approach to control dynamical networks exhibiting long-term power-law memory dependencies. Our newly proposed method enables us to find the minimum number of driven nodes (i.e. the state vertices in the network that are connected to one and only one input) and their placement to control a long-term power-law memory dynamical network given a specific time-horizon, which we define as the ‘time-to-control’. Remarkably, we provide evidence that long-term power-law memory dynamical networks require considerably fewer driven nodes to steer the network’s state to a desired goal for any given time-to-control as compared with Markov dynamical networks. Finally, our method can be used as a tool to determine the existence of long-term memory dynamics in networks.

Funding startups using contingent option of value appreciation: theory and formula

PurposeThis paper provides a structural model to value startup companies and determine the optimal level of research and development (R&D) spending by these companies.Design/methodology/approachThis paper describes a new variant of float-the-money options, which can act as a financial instrument for financing R&D expenses for a specific time horizon or development stage, allowing the investor to share in the startup's value appreciation over that duration. Another innovation of this paper is that it develops a structural model for evaluating optimal level of R&D spending over a given time horizon. The paper deploys the Gompertz-Cox model for the R&D project outcomes, which facilitates investigation of how increased level of R&D input can enhance the company's value growth.FindingsThe author first introduces a time-varying drift term into standard Black-Scholes model to account for the varying growth rates of the startup at different stages, and the author interprets venture capital's investment in the startup as a “float-the-money” option. The author then incorporates the probabilities of startup failures at multiple stages into their financial valuation. The author gets a closed-form pricing formula for the contingent option of value appreciation. Finally, the author utilizes Cox proportional hazards model to analyze the optimal level of R&D input that maximizes the return on investment.Research limitations/implicationsThe integrated contingent claims model links the change in the financial valuation of startups with the incremental R&D spending. The Gompertz-Cox contingency model for R&D success rate is used to quantify the optimal level of R&D input. This model assumption may be simplistic, but nevertheless illustrative.Practical implicationsOnce supplemented with actual transaction data, the model can serve as a reference benchmark valuation of new project deals and previously invested projects seeking exit.Social implicationsThe integrated structural model can potentially have much wider applications beyond valuation of startup companies. For instance, in valuing a company's risk management, the level of R&D spending in the model can be replaced by the company's budget for risk management. As another promising application, in evaluating a country's economic growth rate in the face of rising climate risks, the level of R&D spending in this paper can be replaced by a country's investment in addressing climate risks.Originality/valueThis paper is the first to develop an integrated valuation model for startups by combining the real-world R&D project contingencies with risk-neutral valuation of the potential payoffs.

CSR disclosure and ownership structure: insights from a dynamic empirical framework using an emerging economy context

PurposeThis study examines the bi-directional relationship between corporate social responsibility disclosure (CSRD) and ownership structure through a dynamic empirical framework in an emerging economy context.Design/methodology/approachData over 10 years are used to investigate the response of disclosure to ownership structure variables and vice versa. Dynamic bi-directional relationships are hypothesised and empirically investigated using a panel vector autoregressive (PVAR) model. The ownership structure variables used are government ownership, block ownership and director ownership, while CSRD is constructed as a score through content analysis.FindingsA bi-directional negative relationship between CSRD and government ownership is found, revealing a preference for the state to invest in companies with opaque disclosure. CSRD is found to respond negatively to block ownership, albeit weakly. Results also show that directors prefer to own shares in the company they manage when there are low levels of CSRD.Research limitations/implicationsThe current empirical set-up of using a small emerging economy may not carry to the context of larger emerging economies where the institutional context may differ. Thus, future research could use this dynamic empirical approach to re-examine the questions raised in this paper using data from other emerging economies. The use of a longer time series makes it feasible to explore further analysis what was not possible in this study, such as an impulse response analysis examining the reaction of the variables of interest, CSRD and ownership variables for a specific time horizon to particular changes or shocks associated with one of the endogenous variables in the PVAR.Practical implicationsA major implication is that expecting disclosure practices to improve due to government and director initiatives would be less likely in emerging economies. State and director shareholders prefer to invest in opaque companies because they may purposely choose to keep the minimum disclosure levels. The paper calls for a transparent process and ethical guidelines to guide government investment in firms.Originality/valueThe study investigates the bi-directional relationship between ownership structure and CSRD in contrast to the existing literature's presupposed one-way relationship between these variables by demonstrating that bi-directionality does matter. This paper also contributes to the CSRD literature in the emerging economy context. The bi-directional negative relationship between CSRD and government ownership calls for a transparent selection process of board members as representatives of the state in those companies where the government has an ownership stake. It also calls for a transparent process and ethical guidelines to guide government investment in firms.

Dynamic Conditional Correlation and Volatility Spillover between Conventional and Islamic Stock Markets: Evidence from Developed and Emerging Countries

This study aims to investigate the dynamic conditional correlation and volatility spillover between the conventional and Islamic stock markets in developed and emerging countries in order to develop better portfolio and asset allocation strategies. We used both multivariate GARCH (MGARCH) and multi-scales-based maximal overlap discrete wavelet transform (MODWT) approaches to investigate dynamic conditional correlation and volatility spillover between conventional and Islamic stock markets in developed and emerging countries. The results show that conventional and Islamic markets move together in the long run for a specific time horizon and present time-varying volatility and dynamic conditional correlation, while volatility movement changes due to financial catastrophes and market conditions. Further, the findings point out that Chinese conventional and Islamic stock indexes showed higher volatility, whereas Malaysian conventional and Islamic stock indexes showed comparatively lower volatility during the global financial crisis. This study provides fresh insights and practical implications for risk management, asset allocation, and portfolio diversification strategies that evaluate stock market reactions to the crisis in the international avenues of finance literature.

Systematic literature review of health economic models developed for multiple myeloma to support future analyses

AimsThe goal of this study was to review the economic evaluations of health technologies in multiple myeloma (MM) and provide guidance and recommendations for future health economic analyses.Materials and methodsA systemic literature review (SLR) was conducted on original economic assessment studies and structured review papers focusing on the studies in MM. The search was limited to English language papers published from 1 January 2000 onwards. Publications not applying any type of modelling methodology to describe disease progression and patient pathways over a specific time horizon were excluded.ResultsA total of 2,643 publications were initially identified, of which 148 were eligible to be included in the full-text review phase. From these, 49 publications were included in the final analysis. Most published health economic analyses supported by models came from high-income countries. Evaluations from middle-income countries were rarely published. Diagnostic technologies were rarely modelled and integrated care had not been modelled. Very few models investigated MM treatments from a societal perspective and there was a relative lack of evaluations regarding minimal residual disease (MRD).LimitationsLimitations of the publications included differences between trial populations and modelled populations, justification of methods, lack of confounder analyses, and small trial populations. Limitations of our study included the infeasibility of comparing MM economic evaluations due to the significant variance in modelled therapeutic lines and indications, and the relative scarcity of published economic evaluations from non-high-income countries.ConclusionsAs published economic models lacked many of the elements of the complex and heterogeneous patient pathways in MM and they focused on single decision problems, a thorough, open-source economic whole disease modelling framework is needed to assess the economic value of a wide range of technologies across countries with various income levels with a more detailed view on MM, by including patient-centric and societal aspects.

Framework for extracting rails and setting-out railway line axis based on UAV photogrammetric measurements

ABSTRACT Technical diagnostics enables assessing the current technical condition of a railway line and adjacent infrastructure, and forecasting its changes over a specific time horizon. One of its elements is the periodic monitoring of rail position and their geometry. This article presents a new framework for the setting-out of a railway track axis. The process presented in the manuscript is based on the specific filtration and extraction of rails from a point cloud originating from the photogrammetric process. Data was acquired using a small unmanned aerial vehicle (UAV). A railway track axis setting-out using the process described herein was related to dynamic satellite track measurement. An average accuracy achieved in the horizontal plane is 1.6 cm which corresponds to the accuracy of the source photogrammetric product. The achieved accuracy enables using this method to be suitable for technical track monitoring, geoinformation, and cartographic work.

A Genetic Algorithm for Solving Periodic Heterogeneous Vehicle Routing Problem

This paper addresses the periodic heterogeneous vehicle routing problem (PHVRP), an extension of the classical vehicle routing problems (VRP). This problem is known to be confined to various real-world instances where each customer's demand should be served within a specific time horizon and a maximum demand quantity that can be delivered at each visit. The heterogeneous capacitated vehicles are available to perform the services for each customer. This paper aims to minimize the total traveling time of routes for all vehicles over the time horizon so that the customers' demands can be delivered. Thus, a novel coding scheme is also proposed to directly convert a random sequence of integers into a feasible solution, which is then embedded into algorithms. Furthermore, this paper also compares the performance of the Genetic Algorithm (GA) with the particle swarm optimization algorithm (PSO). The numerical results of the experiments show that the proposed GA is superior to PSO. However, the computation time of PSO is faster than GA.

Short Term Electric Power Load Forecasting Using Principal Component Analysis and Recurrent Neural Networks

Electrical load forecasting study is required in electric power systems for different applications with respect to the specific time horizon, such as optimal operations, grid stability, Demand Side Management (DSM) and long-term strategic planning. In this context, machine learning and data analytics models represent a valuable tool to cope with the intrinsic complexity and especially design future demand-side advanced services. The main novelty in this paper is that the combination of a Recurrent Neural Network (RNN) and Principal Component Analysis (PCA) techniques is proposed to improve the forecasting capability of the hourly load on an electric power substation. A historical dataset of measured loads related to a 33/11 kV MV substation is considered in India as a case study, in order to properly validate the designed method. Based on the presented numerical results, the proposed approach proved itself to accurately predict loads with a reduced dimensionality of input data, thus minimizing the overall computational effort.

Popularity prediction for social media over arbitrary time horizons

Predicting the popularity of social media content in real time requires approaches that efficiently operate at global scale. Popularity prediction is important for many applications, including detection of harmful viral content to enable timely content moderation. The prediction task is difficult because views result from interactions between user interests, content features, resharing, feed ranking, and network structure. We consider the problem of accurately predicting popularity both at any given prediction time since a content item's creation and for arbitrary time horizons into the future. In order to achieve high accuracy for different prediction time horizons, it is essential for models to use static features (of content and user) as well as observed popularity growth up to prediction time. We propose a feature-based approach based on a self-excited Hawkes point process model, which involves prediction of the content's popularity at one or more reference horizons in tandem with a point predictor of an effective growth parameter that reflects the timescale of popularity growth. This results in a highly scalable method for popularity prediction over arbitrary prediction time horizons that also achieves a high degree of accuracy, compared to several leading baselines, on a dataset of public page content on Facebook over a two-month period, covering billions of content views and hundreds of thousands of distinct content items. The model has shown competitive prediction accuracy against a strong baseline that consists of separately trained models for specific prediction time horizons.

Remaining Useful Life Estimation from Event Data

Abstract—Prognostics aims to predict the degradation of equipment by estimating their remaining useful life (RUL) and/or the failure probability within a specific time horizon. The high demand of equipment prognostics in the industry have propelled researchers to develop robust and efficient prognostics techniques. Among data driven techniques for prognostics, machine learning and deep learning (DL) based techniques, particularly Recurrent Neural Networks (RNNs) have gained significant attention due to their ability of effectively representing the degradation progress by employing dynamic temporal behaviors. RNNs are well known for handling sequential data, especially continuous time series sequential data where the data follows certain pattern. Such data is usually obtained from sensors attached to the equipment. However, in many scenarios sensor data is not readily available and often very tedious to acquire. Conversely, event data is more common and can easily be obtained from the error logs saved by the equipment and transmitted to a backend for further processing. Nevertheless, performing prognostics using event data is substantially more difficult than that of the sensor data due to the unique nature of event data. Though event data is sequential, it differs from other seminal sequential data such as time series and natural language in the following manner, i) unlike time series data, events may appear at any time, i.e., the appearance of events lacks periodicity; ii) unlike natural languages, event data do not follow any specific linguistic rule. Additionally, there may be a significant variability in the event types appearing within the same sequence. Therefore, this paper proposes an RUL estimation framework to effectively handle the intricate and novel event data. The proposed framework takes discrete events generated by an equipment (e.g., type, time, etc.) as input, and generates for each new event an estimate of the remaining operating cycles in the life of a given component. To evaluate the efficacy of our proposed method, we conduct extensive experiments using benchmark datasets such as the CMAPSS data after converting the time-series data in these datasets to sequential event data. The event data conversion is carried out by careful exploration and application of appropriate transformation techniques to the time series. To the best of our knowledge this is the first time such event-based RUL estimation problem is introduced to the community. Furthermore, we propose several deep learning and machine learning based solution for the event-based RUL estimation problem. Our results suggest that the deep learning models, 1D-CNN, LSTM, and multi-head attention show similar RMSE, MAE and Score performance. Foreseeably, the XGBoost model achieve lower performance compared to the deep learning models since the XGBoost model fails to capture ordering information from the sequence of events.

OPTIMUM UNIT COMMITMENT SOLUTION OF A POWER SYSTEM BASED ON SALP SWARM ALGORITHM

This paper presents an algorithm to solve the unit commitment problem in a power system. The proposed algorithm employs the Salp swarm algorithm technique to search the optimum unit schedule for a particular daily demand pattern and specific time horizon. Different constraints are taken into consideration, transition cost (start-up and shut down )cost, mean-up time, mean-down time, spinning reserve, and power balance. The proposed algorithm is applied to 10-units and 26-unit. The obtained results are compared with other methods. It reveals the robustness of the proposed algorithm in terms of minimizing overall running costs.

The Height of Children and Adolescents in Colombia. A Review of More than Sixty Years of Anthropometric Studies, 1957-2020.

In this article, we present a review of the studies on the heights of children and teenagers in Colombia published since 1957. We focus on examining the geographic coverage, features of the population studied, height measurement techniques, authors’ profiles, and growth patterns in children. This relatively recent literature has been developed mainly by medical doctors who carried out rigorous measurements with highly specific time and space horizons. The first studies emphasized the differences among socioeconomic levels. Later, there was an interest in minority groups, such as indigenous people and Afro-descendants. Although most of the research lacked long-term vision, the overall balance shows that the country has been improving in anthropometric indicators over time, across territories, and in different socioeconomic groups.