WoS
Permanent URI for this collectionhttps://hdl.handle.net/20.500.14411/18
Browse
15 results
Search Results
Article From Facial Expressions to Thermal Sensation: POMS-Validated AI-Based Mood Estimation Driving Psychology-Adaptive HVAC Control(Elsevier Science SA, 2026-06) Saleh Saleh, Yousif Abed; Sümer, Mustafa Erdi; Saleh, Yousif Abed Saleh; Lotfi, Bahram; Turhan, Cihan; Özbey, Mehmet FurkanThe psychological state of building occupants plays a critical role in how thermal environments are perceived and experienced, yet conventional Heating, Ventilation, and Air Conditioning (HVAC) control strategies largely ignore this factor. Current systems typically focus on environmental and personal parameters, overlooking the influence of mood state on thermal comfort. This omission can lead to suboptimal comfort levels, decreased occupant satisfaction, and inefficient energy use. Integrating psychological feedback into the HVAC control has the potential to transform indoor climate management into a truly occupant-centric process. To this aim, this study presents a novel framework that employs artificial intelligence (AI) and image processing together to estimate occupants' mood states in real time. Facial expressions are analysed using a deep learning-based computer vision model, and the resulting mood predictions are validated with the Profile of Mood States (POMS) questionnaire to ensure accuracy and reliability. Validated mood data directly informs the HVAC setpoint adjustments, enabling psychology-adaptive control that responds dynamically to occupants' current mood states. Moreover, the system operates in real time, combining low-latency image analysis with adaptive control algorithms to continuously align thermal conditions with validated mood estimations. Additionally, implementing mood-driven HVAC control shows potential for enhancing perceived comfort while improving energy efficiency. By bridging the gap between psychological state assessment and environmental control, this research contributes to the advancement of intelligent building systems, paving the way for more responsive, energy-conscious, and human-centered indoor environments.Article Citation - WoS: 3Citation - Scopus: 3Modelling the Positive and Negative Interaction Between Mood and Thermal Sensation in the Built Environment Using a Combined Markov Chain Monte Carlo Algorithm and Morris Method(Sage Publications Ltd, 2025-05-24) Ozbey, Mehmet Furkan; Turhan, CihanMood states, categorized into subscales such as Tension (TEN), Anger (ANG), Fatigue (FAT), Vigour (VIG), Confusion (CON), and Depression (DEP), affect occupants' perceptions of thermal environments. This study investigates the influence of these subscales on thermal sensation, exploring both positive and negative effects. Experiments were conducted in a temperate climate zone over an extended period, including both heating and cooling seasons, with 1159 volunteers. The Morris Method was used to assess the impact of psychological parameters (TEN, ANG, FAT, VIG, CON, DEP) on thermal sensation. Markov Chain Monte Carlo (MCMC) simulations, performed via Python code developed by the authors, evaluated the positive and negative impacts of these subscales across 30,000 simulations. Results showed that VIG was the most influential parameter, while CON and FAT had negative effects (feeling cooler) on thermal sensation. These findings emphasize the complex relationship between psychological factors and thermal perception, underlining the importance of mood states in designing environments that enhance thermal comfort. The study offers valuable insights into the interplay of emotional well-being and physiological responses, contributing to environmental psychology and climate-responsive design.Article Citation - WoS: 4Citation - Scopus: 4Integrating Personalized Thermal Comfort Devices for Energy-Efficient and Occupant-Centric Buildings(Mdpi, 2025-04-26) Turhan, Cihan; Carpino, CristinaPersonalized thermal comfort (PTC) systems aim to satisfy the individual thermal preferences of occupants rather than relying on average comfort indices. With the growing emphasis on sustainability and reducing energy consumption in buildings, energy efficiency has become a critical factor in the design and selection of PTC systems. While the development of PTC tools has accelerated in the last decade, selecting the most appropriate system remains a challenge due to the dynamic, uncertain, and multi-dimensional nature of the decision-making process. This study introduces a novel application of the KEMIRA-M multi-criteria decision-making (MCDM) method to identify the optimal PTC system for university office buildings-an area with limited prior investigation. A case study is conducted in a naturally ventilated office space located in a temperate climate zone. Eight distinct PTC alternatives are evaluated, including data-driven HVAC systems, wearable devices, and localized conditioning units. Six key criteria are considered: estimated energy consumption, capital cost, indoor and outdoor space requirements, system complexity, mobility, and energy efficiency. The results indicate that wearable wristbands, which condition the occupant's carpus area, offer the most balanced performance across criteria, while radiant ceiling/floor systems perform the poorest. Energy efficiency plays a crucial role in this evaluation, as it directly impacts both the operational cost and the environmental footprint of the system. The study's findings provide a structured and adaptable framework for HVAC engineers and designers to integrate PTC systems into occupant-centric and energy-efficient building designs.Article Estimation of the Mean Radiant Temperature in Office Buildings Using an Artificial Neural Network Developed in a Phyton Environment(Taylor & Francis Ltd, 2025-01-30) Ozbey, Mehmet Furkan; Lotfi, Bahram; Turhan, CihanThermal comfort describes an occupant's state of mind in a thermal environment, influenced by six parameters: air velocity, relative humidity, air temperature, mean radiant temperature (MRT), clothing value, and metabolic rate. MRT is the most problematic parameter since the obtaining process is difficult and time-consuming. MRT can be acquired by several methods such as calculations, measurements, assumptions, and software programmes. However, the methods have complexities and uncertainties. Comprehensive models are needed to obtain MRT. To this aim, this study presents an alternative method using one of the artificial intelligence methods, Artificial Neural Network (ANN), to predict MRT for indoor environments to abstain from the difficulties and complexities. A case building is selected in a university office building in Ankara, T & uuml;rkiye. The proposed model is developed and coded in a Python programming environment to predict the MRT using ANN. The results indicate that the ANN model, using only four inputs, predicts MRT with an R-2 value of 0.94 compared to the globe thermometer measurement method. The model's advantages over methods include simplicity, time efficiency and learning from the limited datasets such as difficulty in calculating terms like MRT.Article Citation - WoS: 10Citation - Scopus: 10Modeling the Mood State on Thermal Sensation With a Data Mining Algorithm and Testing the Accuracy of Mood State Correction Factor(Pergamon-elsevier Science Ltd, 2025-01) Yerlikaya-Ozkurt, Fatma; Ozbey, Mehmet Furkan; Turhan, CihanPsychology is proven as an influencing factor on thermal sensation. On the other hand, mood state is one of the significant parameters in psychology field. To this aim, in the literature, mood state correction factor on thermal sensation (Turhan and Ozbey coefficients) is derived utilizing with data-driven black-box model. However, novel models which present analytical form of the mood state correction factor should be derived based on the several descriptive variables on thermal sensation. Moreover, the result of this factor should also be checked with analytical model results. Therefore, this study investigates the modelling of mood state correction factor with a data mining algorithm, called Multivariate Adaptive Regression Splines (MARS). Additionally, the mood state is also taken as a thermal sensation parameter besides environmental parameters in this algorithm. The same data, which are collected from a university study hall in a temperate climate zone, are used and the model results are compared with the thermal sensation results based on mood state correction factor which is driven via black-box model. The results show that coefficient of correlation "r" between the MARS and black-box model is found as 0.9426 and 0.9420 for training and testing. Hence, the mood state is also modelled via a data mining algorithm with a high accuracy, besides the black-box model.Article Citation - WoS: 21Citation - Scopus: 22Sensitivity Analysis of the Effect of Current Mood States on the Thermal Sensation in Educational Buildings(Wiley-hindawi, 2022-08) Ozbey, Mehmet Furkan; Ceter, Aydin Ege; Orfioglu, Sevval; Alkan, Nese; Turhan, CihanAdaptive thermal comfort is a model which considers behavioral and psychological adjustments apart from Fanger's Predicted Mean Vote (PMV)/Percentage of Dissatisfied (PPD) method. In the literature, the differences between the PMV/PPD method and adaptive thermal comfort were mainly considered in aspects of behavioral adjustments in an environment. Conversely, limited studies related to psychological adjustments were considered in detail for thermal comfort. This study purposes to investigate the effects of current mood state subscales on thermal sensation of the occupants for the first time in the literature. To this aim, the Profile of Mood States (POMS) questionnaire is used to determine the mood state of the occupants with six different subscales: Anger, Confusion, Vigor, Tension, Depression, and Fatigue. The experiments were conducted in a university study hall in Ankara, Turkey, which is in warm-summer Mediterranean climate (Csb) according to Koppen-Geiger Climate Classification. The distributions of each subscale were examined via Anderson Darling and Shapiro-Wilk tests accordingly given responses from the occupants. The sensitivity analysis was applied to the six subscales of the POMS with Monte Carlo simulation method by considering the distributions of each subscale. The results revealed that the current mood state has a crucial effect on the thermal sensation of the occupants. The subscales of the Depression and Vigor were found as the most vital ones among the six subscales. Only the pure effects of the Vigor and Depression would change the thermal sensation of the occupants 0.31 and 0.30, respectively. The Confusion was determined as the least effective subscale to the thermal sensation of the occupants. Moreover, with the combination of all the six subscales, the thermal sensation might change up to 1.32. Findings in this study would help researchers to develop the personalized thermal comfort systems.Article Citation - WoS: 19Citation - Scopus: 21Gender Inequity in Thermal Sensation Based on Emotional Intensity for Participants in a Warm Mediterranean Climate Zone(Elsevier France-editions Scientifiques Medicales Elsevier, 2023-03) Ceter, Aydin Ege; Ozbey, Mehmet Furkan; Turhan, CihanThe deficiencies of the one of the most preferred conventional thermal comfort models, the Predicted Mean Vote/ Percentage of Predicted Dissatisfied (PMV/PPD) method have emerged over time since the model does not take psychological parameters such as personal traits, mood states and adaptation into account. Therefore, re-searchers have focused on Adaptive Thermal Comfort models that integrate human behaviours into the model for better prediction of thermal comfort. In addition to the influence of the behaviours of occupants, thermal comfort may be evaluated as a subjective term, thus, the effect of one of the psychological parameters, current mood state, on thermal sensation cannot be ignored for predictions. Although, the effect of current mood state on thermal sensation is a vital concept, the findings of the studies are not effective and comprehensive in the literature. For this reason, the aim of this study is to examine the relationship between current mood state and thermal sensation in gender difference aspect. Therefore, a series of experiments were conducted in a university study hall between August 16th, 2021 and August 1st, 2022. The current mood states of the participants were evaluated with the Profile of Mood States (POMS) questionnaire and the results were represented by a novel approach called Emotional Intensity Score (EIS). One tailed t-test was applied for investigating the relationship between the EIS and the thermal sensation. Findings of the research showed that a significant association exists between the EIS and thermal sensation for male participants while no relationship was found for female.Article Citation - WoS: 21Citation - Scopus: 24A Novel Comfort Temperature Determination Model Based on Psychology of the Participants for Educational Buildings in a Temperate Climate Zone(Elsevier, 2023-10) Ozbey, Mehmet Furkan; Turhan, CihanMaintaining thermal comfort in the educational buildings is vital due to the impacts on learning effectiveness of students. Therefore, development of a proper comfort temperature in educational buildings is a must. In naturally ventilated and mixed-mode buildings, the adaptive thermal comfort model, which considers additively psychological, and behavioural factors to the Fanger's PMV/PPD model, is commonly applied based on regression analyses. However, the psychological adjustments based on current mood state are very limited in these adaptive thermal comfort models. Therefore, this study focuses on the psychological adjustments in terms of Profile of Mood States in order to predict comfort temperature of students in a case building. The experiments are conducted in a university on a temperate climate zone for a long period-data including both heating and cooling seasons. In this study, the comfort temperatures for each student are determined via Griffith method for the case building. Moreover, the current mood states of students are assessed utilizing the Profile of Mood States survey, which are collected via a developed mobile application. As a conclusion, the relation between the current mood state of the students and comfort temperature are statistically investigated. The results show that a Griffith constant are found as 0.332/K and mean annual comfort temperature is found as 21.32 degrees C in the case building. Additionally, a significant difference is found in the comfort temperatures among the students who have more, or fewer concerns than typically reported. The novelty of the study is to present a comfort temperature determination model which considers human psychology as a starter study in the literature.Article Citation - WoS: 15Citation - Scopus: 16Integration of Psychological Parameters Into a Thermal Sensation Prediction Model for Intelligent Control of the Hvac Systems(Elsevier Science Sa, 2023-10) Turhan, Cihan; Ozbey, Mehmet Furkan; Lotfi, Bahram; Akkurt, Gulden Gokcen; Gökçen Akkurt, GüldenConventional thermal comfort models take physiological parameters into account on thermal comfort models. On the other hand, psychological behaviors are also proven as a vital parameter which affects the thermal sensation. In the literature, limited studies which combine both physiological and psychological parameters on the thermal sensation models are exist. To this aim, this study develops a novel Thermal Sensation Prediction Model (TSPM) in order to control the HVAC system by considering both parameters. A data-driven TSPM, which includes Fuzzy Logic (FL) model, is developed and coded using Phyton language by the authors. Two physiological parameters (Mean Radiant Temperature and External Temperature) and one psychological parameter (Emotional Intensity Score (EIS) including Vigour, Depression, Tension with total of 32 subscales) are selected as inputs of the model. Besides the physiological parameters which are decided intentionally considering a manual ventilated building property, the most influencing three sub- psychological parameters on thermal sensation are also selected in the study. While the physiological parameters are measured via environmental data loggers, the psychological parameters are collected simultaneously by the Profile of Mood States questionnaire. A total of 1159 students are participated to the questionnaire at a university study hall between 15th of August 2021 and 15th of September 2022. The results showed that the novel model predicted Thermal Sensation Vote (TSV) with an accuracy of 0.92 of R2. The output of this study may help to develop an integrated Heating Ventilating and Air Conditioning (HVAC) system with Artificial Intelligence - enabled Emulators that also includes psychological parameters.Conference Object Citation - WoS: 3Citation - Scopus: 3Design and Validation of a Fault Tolerant Fuzzy Control for a Wind Park High-Fidelity Simulator(Ieee, 2021-09-29) Simani, Silvio; Turhan, Cihan; Farsoni, SaverioTo enhance both the safety and the efficiency of offshore wind park systems, faults must be accommodated in their earlier occurrence, in order to avoid costly unplanned maintenance. Therefore, this paper aims at implementing a fault tolerant control strategy by means of a data-driven approach relying on fuzzy logic. In particular, fuzzy modelling is considered here as it enables to approximate unknown nonlinear relations, while managing uncertain measurements and disturbance. On the other hand, the model of the fuzzy controller is directly estimated from the input-output signals acquired from the wind farm system, with fault tolerant capabilities. In general, the use of purely nonlinear relations and analytic methods would require more complex design tools. The design is therefore enhanced by the use of fuzzy model prototypes obtained via a data-driven approach, thus representing the key point if real-time solutions have to implement the proposed fault tolerant control strategy. Finally, a high-fidelity simulator including hardware-in-the-loop modules is exploited to validate the reliability and robustness characteristics of the developed methodologies also for on-line implementations.