Article
Mathematics
Ales Jandera, Tomas Skovranek
Summary: This work proposes a Customer behaviour hidden Markov model (CBHMM) to predict customer behavior and forecast store income in e-commerce. The model consists of three sub-models and uses a transition matrix to distinguish between decision-states of order completed, order uncompleted, or no order. The Viterbi algorithm is used to evaluate the completion of orders, followed by the estimation of forecasted store income. Comparisons with a baseline prediction model show that CBHMM outperforms in terms of R-squared criterion and has a higher PG value.
Article
Chemistry, Multidisciplinary
Anna Borucka, Edward Kozlowski, Rafal Parczewski, Katarzyna Antosz, Leszek Gil, Daniel Pieniak
Summary: Logistics processes and their effective planning, management, and implementation are crucial for businesses. This article analyzes the process of supplying raw materials for production tasks, specifically in a waste processing company where proper management and storage are necessary due to the toxicity of the waste to the environment. The article proposes the use of hidden Markov models, a statistical modeling tool, to assess the level of supply, as traditional methods may not always provide reliable information. The models represent a system as a Markov process with hidden states and visible outputs, with the distribution of outputs defined by a polynomial distribution.
APPLIED SCIENCES-BASEL
(2023)
Article
Engineering, Industrial
Morteza Soleimani, Felician Campean, Daniel Neagu
Summary: This paper presents a methodology for fault detection, prediction, and isolation in complex engineered systems, using HMM and BN to analyze data characteristics and capture causality for fault identification. The results show that the proposed methodology can identify faults faster and attribute them to the correct root cause.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2021)
Article
Transportation Science & Technology
Yan Zhao, Shengyin Shen, Henry X. Liu
Summary: Queue length estimation is crucial for traffic signal control, and this study proposes cycle-by-cycle queue length estimation methods based on the hidden Markov model in probe vehicle environments. The research explores the correlation of queue lengths in different cycles and successfully improves the accuracy of queue length estimation. Validation results show that the proposed methods outperform existing ones, demonstrating the effectiveness of the parameter learning algorithm in estimating parameters.
TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES
(2021)
Article
Statistics & Probability
Shoichi Eguchi, Hiroki Masuda
Summary: This article focuses on the relative model comparison for the parametric coefficients of an ergodic Levy driven model observed at high-frequency. The asymptotics is based on the fully explicit two-stage Gaussian quasi-likelihood function (GQLF) of the Euler-approximation type. For the selection of scale and drift coefficients, explicit Gaussian quasi-AIC and Gaussian quasi-BIC statistics are proposed through the stepwise inference procedure, and their asymptotic properties are proven. Numerical experiments are conducted to illustrate the theoretical findings.
ANNALS OF THE INSTITUTE OF STATISTICAL MATHEMATICS
(2023)
Article
Computer Science, Artificial Intelligence
Carlos Puerto-Santana, Pedro Larranaga, Concha Bielza
Summary: In a real-life process evolving over time, the relationship between relevant variables may change. Asymmetric hidden Markov models provide a dynamic framework where different inference models can be used for each state of the process. This paper modifies recent asymmetric hidden Markov models to incorporate an asymmetric autoregressive component for continuous variables, allowing the model to choose the optimal order of autoregression. The paper also demonstrates the adaptation of inference, hidden states decoding, and parameter learning for the proposed model. Experimental results with synthetic and real data showcase the capabilities of this new model.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2022)
Article
Geosciences, Multidisciplinary
C. Ghiringhelli, F. Bartolucci, A. Mira, G. Arbia
Summary: The assumption of second-order stationarity in spatial statistics may not be reasonable for modeling certain data. Therefore, a latent process is introduced to provide a more realistic representation. Markov chain Monte Carlo procedures are used for model comparison and parameter estimation, demonstrating the advantages of the proposed modeling strategy.
SPATIAL STATISTICS
(2021)
Article
Computer Science, Interdisciplinary Applications
J. L. Kirkby, Dang H. Nguyen, Duy Nguyen, Nhu N. Nguyen
Summary: A novel method is presented for estimating the parameters of a parametric diffusion process using a closed-form Maximum Likelihood estimator for an approximating Continuous Time Markov Chain (CTMC). The CTMC approximation eliminates time-discretization error during parameter estimation, making it suitable for econometric situations with infrequently sampled data.
COMPUTATIONAL STATISTICS & DATA ANALYSIS
(2022)
Article
Engineering, Civil
Andong Dai, Yunjun Xu
Summary: This study proposes a control augmentation framework to assist human operators in controlling a system, utilizing a Hidden Markov Model to estimate unknown parameters in a human internal vehicle model, resulting in reduced tracking errors.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Computer Science, Interdisciplinary Applications
Antonello Maruotti, Lea Petrella, Luca Sposito
Summary: This study introduces a hidden semi-Markov-switching quantile regression model as an extension of the hidden Markov-switching model, allowing arbitrary sojourn-time distributions. Through simulation study and empirical analysis, it investigates the relationship between the stock index from the emerging market of China and those from the advanced markets, as well as the determinants of high levels of pollution in an Italian small city.
COMPUTATIONAL STATISTICS & DATA ANALYSIS
(2021)
Article
Statistics & Probability
Abdullah Asilkalkan, Xuwen Zhu
Summary: In this paper, a hidden Markov model for modeling matrix-variate time series data is proposed, which demonstrates high accuracy and competitiveness in state classification.
Article
Mathematical & Computational Biology
Yei Eun Shin, Dawei Liu, Huiyan Sang, Toby A. Ferguson, Peter X. K. Song
Summary: This study analyzes the spreading patterns of ALS muscle weakness using spatiotemporal binary muscle strength data and proposes a hidden Markov model-based approach. The model is able to estimate the incidence rate of ALS disease and the probability of disease state transition while considering historical muscle conditions and their spatial relationships.
STATISTICS IN MEDICINE
(2021)
Article
Mathematics
Igor Sazonov, Dmitry Grebennikov, Andreas Meyerhans, Gennady Bocharov
Summary: A high-resolution mathematical model was proposed to quantify the contribution of stochastic effects to the variability of HIV life cycle kinetics, exploring statistical characteristics such as cell infection multiplicity, cooperative nature of viral replication, and variability in virus secretion. The study found that infecting each CD4(+) T cell with a fixed number of viruses leads to heterogeneity in infected cells, identifying bottleneck factors in virus production. Sensitivity analysis ranked model parameters with significant impact on viral progeny, highlighting potential therapeutical targets.
Article
Biotechnology & Applied Microbiology
Mladen Pavlecic, Mario Novak, Antonija Trontel, Nenad Mardetko, Marina Grubisic, Blanka Didak Ljubas, Vlatka Petravic Tominac, Rozelindra Coz Rakovac, Bozidar Santek
Summary: This study investigated the efficiency of bioethanol production from sugar beet cossettes using yeast in a horizontal rotating tubular bioreactor. A non-structural mathematical model was developed to describe substrate utilization and product formation. The results showed that rotation mode and speed greatly influenced the bioethanol yield.
FERMENTATION-BASEL
(2022)
Article
Engineering, Civil
Patrick Manser, Tom Haering, Tim Hillel, Janody Pougala, Rico Krueger, Michel Bierlaire
Summary: This paper presents a novel activity-based demand model that combines an optimisation framework for continuous temporal scheduling decisions with traditional discrete choice models for non-temporal choice dimensions. The framework resolves temporal scheduling conflicts to maximize individuals' daily utility by introducing flexibility parameters. It has three advantages over existing models and can be used to estimate and simulate city-scale case studies efficiently.
Article
Energy & Fuels
Mikkel L. Sorensen, Peter Nystrup, Mathias B. Bjerregard, Jan K. Moller, Peder Bacher, Henrik Madsen
Summary: This article introduces several advanced methods for multivariate forecasting of wind and solar power production and emphasizes the importance of correctly modeling the dependency between forecasts. Recent research has shown that forecast reconciliation can increase the accuracy of renewable energy forecasts. The article also presents the methodology for probabilistic forecasting and discusses the significance of choosing a proper approach for forecast evaluation to avoid misrepresentation.
WILEY INTERDISCIPLINARY REVIEWS-ENERGY AND ENVIRONMENT
(2023)
Article
Transportation Science & Technology
Hans True, Lasse Engbo Christiansen, Andreas Lindhardt Plesner, Andreas Lonstrup Ammitzboll, Bjorn Jerram Dahl
Summary: In this study, we numerically investigate the dynamic reactions of a moving wheelset model to real measured track irregularities. The objective is to determine if the dynamics can be used as input for the inverse problem of determining the true track geometry from measured wheelset reactions. Our findings show that the lateral motion of the wheelset often differs from the track geometry, and the reasons behind this discrepancy remain unknown. The dynamics of a wheelset to lateral track irregularities are generally not accurate enough to be used as a basis for describing the track irregularities.
RAILWAY ENGINEERING SCIENCE
(2023)
Article
Engineering, Electrical & Electronic
Mohsen Banaei, Francesco D'Ettorre, Razgar Ebrahimy, S. Ali Pourmousavi, Emma M. V. Blomgren, Henrik Madsen
Summary: In this study, a new approach is proposed to determine a group of contract hour sets to provide maximum flexibility of swimming pool heating systems. The proposed approach is validated through simulation studies and cost-benefit analysis.
INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS
(2023)
Article
Automation & Control Systems
Kenneth Leerbeck, Peder Bacher, Christian Heerup, Henrik Madsen
Summary: In many applications, it is important to determine the heat demand of cabinets, but measuring the mass flow through each cabinet is expensive and not feasible in large-scale deployments. Therefore, it is crucial to estimate the valve sizes from monitoring data. The present paper proposes a novel method for estimating cabinet evaporator valve constants using time series data and shows that an Auto-Regressive Moving Average model with eXogenous variables effectively eliminates auto-correlation and provides more accurate estimates.
JOURNAL OF PROCESS CONTROL
(2023)
Article
Energy & Fuels
Mads E. Hansen, Nystrup Peter, Jan K. Moller, Madsen Henrik
Summary: We investigate the reconciliation of wind power forecasts in a spatial hierarchy with three levels. By using a relatively simple model at the lowest level, we are able to improve the accuracy of the total forecast through spatial reconciliation. The results show that the accuracy of the forecasts for both the entire region and individual regions can be significantly increased.
Article
Energy & Fuels
E. M. V. Blomgren, F. D'Ettorre, O. Samuelsson, M. Banaei, R. Ebrahimy, M. E. Rasmussen, N. H. Nielsen, A. R. Larsen, H. Madsen
Summary: Power transformers are costly assets in power grids and are often loaded above their rated limits due to increasing electricity demand. This study proposes a grey-box model for online estimation and forecasting of transformer temperature using limited non-intrusive measurements. The model has shown high accuracy and low computational time, making it suitable for online applications. With a six-hour prediction horizon, the mean average error was 0.4-0.6℃, and the model can also account for uncertainty by providing prediction intervals.
SUSTAINABLE ENERGY GRIDS & NETWORKS
(2023)
Article
Energy & Fuels
Dorian Esteban Guzman Razo, Henrik Madsen, Christof Wittwer
Summary: Accurate prediction of energy generation and consumption, especially for small- and medium-scale photovoltaic (PV) systems, is crucial in a market with increasing renewable energy. In this study, we propose an algorithm that can accurately predict the power output of unknown PV systems using on-site measured data and irradiance. We achieved a high level of accuracy with a mean deviation of -1.14 W/kW(p) and a mean absolute percentage deviation of 1.81% for the year 2020.
FRONTIERS IN ENERGY RESEARCH
(2023)
Article
Energy & Fuels
Julien Leprince, Henrik Madsen, Jan Kloppenborg Moller, Wim Zeiler
Summary: This work proposes a novel multi-dimensional hierarchical forecasting method that connects predictions from different time horizons and abstraction levels to provide decision-makers with a common view of the future. The method is evaluated on two different case studies to predict building electrical loads and demonstrates the value of hierarchical-coherent learning. Existing obstacles are clearly delineated, presenting distinct pathways for future work.
Article
Energy & Fuels
Julien Leprince, Amos Schledorn, Daniela Guericke, Dominik Franjo Dominkovic, Henrik Madsen, Wim Zeiler
Summary: To achieve the carbon emission reduction goals in line with the Paris agreement, it is crucial to plan resilient and sustainable energy systems. This study focuses on bridging the gap between building occupants and smart-city energy networks to improve urban energy planning. The impact of user behavior on energy planning is assessed through a stochastic energy community sizing and operation problem, and the results reveal that occupant behavior is a significant factor affecting energy community planning. This research highlights the importance of connecting occupants to cities for more resilient and efficient urban energy strategies.
Article
Energy & Fuels
Hjorleifur G. Bergsteinsson, Mikkel Lindstrom Sorensen, Jan Kloppenborg Moller, Henrik Madsen
Summary: District heating is an efficient method of distributing heat in densely populated areas at a low cost. However, with the addition of decentralized heat sources, the operational complexity increases, especially in terms of temperature optimization. This paper proposes a methodology to reconcile local heat load forecasts in a coherent manner, resulting in improved forecast accuracy.
Article
Energy & Fuels
Christoffer Rasmussen, Niels Lassen, Peder Bacher, Tor Helge Dokka, Henrik Madsen
Summary: This article introduces a new method for estimating the thermal properties of buildings, taking into account the stochastic human effect on energy consumption. By combining the energy signature method with a hidden state that describes human interactions, the model accuracy is improved and bias is reduced. The demonstration case showed that human interactions increase the total heat loss of the building.
Article
Infectious Diseases
Morten Rasmussen, Frederik Trier Moller, Vithiagaran Gunalan, Sharmin Baig, Marc Bennedbaek, Lasse Engbo Christiansen, Arieh Sierra Cohen, Kirsten Ellegaard, Anders Fomsgaard, Kristina Traeholt Franck, Nicolai Balle Larsen, Tine Graakjaer Larsen, Ria Lassauniere, Charlotta Polacek, Amanda Gammelby Qvesel, Raphael Niklaus Sieber, Lasse Dam Rasmussen, Marc Stegger, Katja Spiess, Man-Hung Eric Tang, Lasse Skafte Vestergaard, Thomas Emil Andersen, Silje Vermedal Hoegh, Rune Micha Pedersen, Marianne Nielsine Skov, Kat Steinke, Thomas Vognbjerg Sydenham, Morten Hopp, Lene Nielsen, Tyra Grove Krause, Henrik Ullum, Pikka Jokelainen
Summary: This article describes 10 cases of the SARS-CoV-2 variant BA.2.86 detected in Denmark, providing information on its molecular characteristics and results from wastewater surveillance. The variant is classified as a variant under monitoring by the World Health Organization, and further global monitoring of this variant and other SARS-CoV-2 variants is highly recommended.
Article
Engineering, Electrical & Electronic
Mohsen Banaei, Hani Raouf-Sheybani, Majid Oloomi-Buygi, Razgar Ebrahimy, Henrik Madsen
Summary: This paper introduces a Nash equilibrium approach to model the interactions between futures and day-ahead markets, discussing the effects of uncertainties in wind farms' output power and transmission system capacity on market players' strategies and evaluating the behavior of speculators.
INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
K. Leerbeck, P. Bacher, C. Heerup, H. Madsen
Summary: This paper presents a data-driven grey box model for fault diagnostics and control optimization of supermarket refrigeration systems. The model is validated using data from ten evaporators in a Danish supermarket, and the parameters are estimated using a Kalman filter and maximum likelihood method. The study demonstrates that the model is robust and accurate, and highlights the importance of re-estimating parameters.
Article
Computer Science, Interdisciplinary Applications
Peder Bacher, Hjorleifur G. Bergsteinsson, Linde Frolke, Mikkel L. Sorensen, Julian Lemos-Vinasco, Jon Liisberg, Jan Kloppenborg Moller, Henrik Aalborg Nielsen, Henrik Madsen
Summary: Online forecasting is crucial for decision-making systems that rely on forecasts. These systems require frequent updates and the ability to adapt to changing data and models. The R package onlineforecast provides a flexible setup for creating and running custom models in an operational setting.
Article
Biology
Iain Hunter, Raz Leib
Summary: Natural movement is related to health, but it is difficult to measure. Existing methods cannot capture the full range of natural movement. Comparing movement across different species helps identify common biomechanical and computational principles. Developing a system to quantify movement in freely moving animals in natural environments and relating it to life quality is crucial. This study proposes a theoretical framework based on movement ability and validates it in Drosophila.
JOURNAL OF THEORETICAL BIOLOGY
(2024)
Article
Biology
Andy Gardner
Summary: Fisher's geometric model is a useful tool for predicting key properties of Darwinian adaptation, and here it is applied to predict differences between the evolution of altruistic versus nonsocial phenotypes. The results suggest that the effect size maximizing probability of fixation is smaller in the context of altruism and larger in the context of nonsocial phenotypes, leading to lower overall probability of fixation for altruism and higher overall probability of fixation for nonsocial phenotypes.
JOURNAL OF THEORETICAL BIOLOGY
(2024)
Article
Biology
Thomas F. Pak, Joe Pitt-Francis, Ruth E. Baker
Summary: Cell competition is a process where cells interact in multicellular organisms to determine a winner or loser status, with loser cells being eliminated through programmed cell death. The winner cells then populate the tissue. The outcome of cell competition is context-dependent, as the same cell type can win or lose depending on the competing cell type. This paper proposes a mathematical framework to study the emergence of winner or loser status, highlighting the role of active cell death and identifying the factors that drive cell competition in a cell-based modeling context.
JOURNAL OF THEORETICAL BIOLOGY
(2024)
Article
Biology
Haruto Tomizuka, Yuuya Tachiki
Summary: Batesian mimicry is a strategy in which palatable prey species resemble unpalatable prey species to avoid predation. The evolution of this mimicry plays a crucial role in protecting the unpalatable species from extinction.
JOURNAL OF THEORETICAL BIOLOGY
(2024)
Article
Biology
Jason W. Olejarz, Martin A. Nowak
Summary: Gene drive technology shows potential for population control, but its release may have unpredictable consequences. The study suggests that the failure of suppression is a natural outcome, and there are complex dynamics among wild populations.
JOURNAL OF THEORETICAL BIOLOGY
(2024)
Article
Biology
Hamid Ravaee, Mohammad Hossein Manshaei, Mehran Safayani, Javad Salimi Sartakhti
Summary: Gene expression analysis is valuable for cancer classification and phenotype identification. IP3G, based on Generative Adversarial Networks, enhances gene expression data and discovers phenotypes in an unsupervised manner. By converting gene expression profiles into images and utilizing IP3G, new phenotype profiles can be generated, improving classification accuracy.
JOURNAL OF THEORETICAL BIOLOGY
(2024)
Article
Biology
Beatrix Rahnsch, Leila Taghizadeh
Summary: This study forecasts the evolution of the COVID-19 pandemic in Germany using a network-based inference method and compares it with other approaches. The results show that the network-inference based approach outperforms other methods in short-to mid-term predictions, even with limited information about the new disease. Furthermore, predictions based on the estimation of the reproduction number in Germany can yield more reliable results with increasing data availability, but still cannot surpass the network-inference based algorithm.
JOURNAL OF THEORETICAL BIOLOGY
(2024)
Article
Biology
Rongsheng Huang, Qiaojun Situ, Jinzhi Lei
Summary: Maintaining tissue homeostasis requires appropriate regulation of stem cell differentiation. Random inheritance of epigenetic states plays a pivotal role in stem cell differentiation. This computational model provides valuable insights into the intricate mechanism governing stem cell differentiation and cell reprogramming, offering a promising path for enhancing the field of regenerative medicine.
JOURNAL OF THEORETICAL BIOLOGY
(2024)
Article
Biology
Patrick Vincent N. Lubenia, Eduardo R. Mendoza, Angelyn R. Lao
Summary: This study compares insulin signaling in healthy and type 2 diabetes states using reaction network analysis. The results show similarities and differences between the two conditions, providing insights into the mechanisms of insulin resistance, including the involvement of other complexes, less restrictive interplay between species, and loss of concentration robustness in GLUT4.
JOURNAL OF THEORETICAL BIOLOGY
(2024)
Article
Biology
Nuverah Mohsin, Heiko Enderling, Renee Brady-Nicholls, Mohammad U. Zahid
Summary: Mathematical modeling is crucial in understanding radiobiology and designing treatment approaches in radiotherapy for cancer. This study compares three tumor volume dynamics models and analyzes the implications of model selection. A new metric, the point of maximum reduction of tumor volume (MRV), is introduced to quantify the impact of radiotherapy. The results emphasize the importance of caution in selecting models of response to radiotherapy due to the artifacts imposed by each model.
JOURNAL OF THEORETICAL BIOLOGY
(2024)
Article
Biology
Armindo Salvador
Summary: Michael Savageau's Biochemical Systems Analysis papers have had a significant impact on Systems Biology, generating core concepts and tools. This article provides a brief summary of these papers and discusses the most relevant developments in Biochemical Systems Theory since their publication.
JOURNAL OF THEORETICAL BIOLOGY
(2024)