Comparative analysis of SVR based on multiple optimization algorithms in indoor thermal comfort prediction

The prediction model of indoor thermal comfort PMV index based on least squares support vector machine (LS-SVM) is established by using the nonlinear relationship between human thermal comfort and its influencing factors and the characteristic that particle swarm has of fast global optimization. Adopting the parameters of least squares support vector machine optimized by Particle Swarm algorithm, the mapping relations between the six factors including indoor air temperature, relative humidity, air velocity, mean radiant temperature, human metabolic rate, thermal resistance and PMV index can be formed through the sample data learning. The experimental results show that the method is accurate and effective.

This study investigates the role of the air-to-radiant temperature offset, defined as the difference between air temperature and mean radiant temperature, in predicting thermal sensation in naturally ventilated office buildings located in warm Mediterranean climates. Although machine learning has advanced thermal comfort modeling by capturing complex relationships among environmental and physiological variables, most models continue to treat radiant effects indirectly, blending them into operative temperature rather than modeling the offset as a distinct predictor. This approach limits their ability to reflect the directional influence of radiative asymmetries commonly found in naturally ventilated environments. To address this gap, a data-driven approach using machine learning was employed. A curated subset of the ASHRAE Global Thermal Comfort Database II was used, filtered for naturally ventilated office spaces in the Csa climate zone during warm seasons. Eleven regression algorithms were compared to predict occupants’ thermal sensation votes based on operative temperature, air-to-radiant temperature offset, relative humidity, air velocity, and metabolic rate. Among these, a tuned Random Forest model achieved the highest performance, significantly outperforming traditional thermal comfort predictions. Feature importance and SHAP analysis revealed that the air-to-radiant temperature offset was an influential predictor, with clear non-linear effects on perceived comfort.

A comprehensive comparison and accuracy of different methods to obtain mean radiant temperature in indoor environment

The purpose of this study is to infer an acceptable range of thermal comfort for Japanese people during summer season with a view to the energy conservation in buildings. From September to October, 1984 six college-age Japanese males were exposed for 2.5 hours under seven different conditions in the Waseda University environmental test chamber so as to determine the effects of humidity on thermal and comfort sensations. The results analyzed from the 42 experiments in total are discribed. Fig. 1 shows plan and section of the test chamber. The volume of the test chamber is 19.2 m^3 and floor area is 8.5 m^2. Ceiling and right side wall panels have 5 cm thick air spaces behind the panels. Table 1 shows design specification of the chamber to attain hot and humid summer conditions. Room air temperature can be varied between 20℃ and 39℃ and absolute humidity between 8 g/kg and 27 g/kg. Maximum air change rate is about 100 h^<-1>. The scheme of the air conditioning system is shown in Fig. 2. Table 3 shows the test conditions and the deviation from the set point temperatures and humidities which were measured during actual experiments. Subjects wore almost the same clothings and the mean clo value was 0.45. The mean radiant temperature was equal to the air temperature and air velocity in the occupied zone around 0.25 m/s. Subjects were sitting on the chairs against the air movement direction. Antropometric data for the subjects are listed in Table 2. Fig.3 shows the experimental plan. At the beginning of the test (1) weight, (2) body temperature at armpit, (3) heart beat, blood pressure, (4) skin blood flow were measured. Every five minutes skin temperatures, room air temperature, humidity and room surface temperatures were measured. Remeasuring the above four items at the end of the test, thermal sensation and comfort sensation were asked to be answered as shown in Table 4. Modified temperature (MT) defined as the air temperature of 50 %rh, 0.1 m/s mean air velocity, 0.6 clo, 1.0 met and mean radiant temerature equaled to the air temperature, which would provide the same thermal sensation as under the actual thermal condition was used for data analyses. MT was calculated by Fanger's comfort equation. Fig. 5 shows experimental results of thermal sensation vote. There is no significant difference between 60 %rh and 80 %rh at the air temperature of 25℃. The difference of about 0.7 in thermal sensation vote was found between 40 %rh and 80 %rh at the air temperature of 28℃ and also about 0. 7 difference between 40 %rh and 60 %rh at 31℃. It was found that higher the temperature greater the difference in thermal sensation vote. This is considered to be caused by difference in humidity. In Table 5 the calculated regression equation for the estimated mean thermal sensation vote by Waseda collegeage Japanese male subjects is given as a function of modified temperature. The results with American collegeage male subjects and Danish college-age male subjects are also shown for comparison. Correlation coefficient between modified temperature and thermal sensation for all observations (n=42) was 0.807 and that for the mean of six subjects was 0.968. It was found that thermal sensation has a good relation to the modified temperature. The temperature corresponding to the neutral mean vote can be determined by substituting Y=4 (neutral) into each regression equation. The calculated results for different groups are given in Table 6. Fig. 6 shows the mean thermal sensation vote versus modified temperature for Waseda college-age Japanese male subjects, Danish college-age male subjects and American college-age male subjects. The regression line for Waseda subjects is found very similar to the one for Americans. The mean themal sensation vote versus ET for Waseda college-age Japanese male subjects is shown in Fig. 7. Correlation coefficient between ET and thermal sensation vote for the mean

In order to study the indoor thermal comfort in the winter of subtropics region in which there is no heat supply system, field study of indoor thermal comfort was carried out in classrooms of a university in Xiamen. Data both from field measurements and questionnaire survey were collected and analyzed. Consequently, the neutral and preferred temperatures in the winter of Xiamen were obtained, which show slightly difference with previous studies across China. On the other hand, predicted mean vote (PMV), which was calculated by Thermal Comfort Program software, shows some deviations from the mean thermal sensation (MTS) summarized from questionnaires statistics. Finally, by using multivariate nonlinear regression model based on MATLAB, a new adaptive equation was developed, which could be used to predict the thermal response in classrooms in subtropics region. In addition, it was found that the predicted equation fits very well with the collected data, which reflects variation of thermal sensation in winter. Results from this study provide guidance for the measurement and prediction of thermal comfort in winter of the subtropics region.

The globe witnessed a rapid development of the concepts of sustainability, smart architecture, and intelligent buildings during recent decades. The Healthy environment, particularly thermal comfort, is an essential concern for planners, urbanists, and architects to produce a healthy and thermally comfortable environment. A better understanding of the parameters that affect the Outdoor Thermal Comfort (OTC) will enable urbanists and environmentalists to control the microclimate and to enhance environmental performance. Several parameters affect the thermal comfort of human-being such as air temperature, mean radiant temperature (MRT), air velocity, humidity, metabolic rate, and clothing insulation. Assessing the MRT is considered the most challenging parameter in outdoor spaces. Recent researches recognized several approaches to determine the OTC in different climatic zones. The influence of different climates and user groups has significantly altered the range of responses for thermal comfort. This paper focuses on reviewing the current state of knowledge on how to assess the OTC and the MRT in the hot arid climate. Results confirmed the integration of the appropriate OTC index with other design tools to evaluate the OTC and the MRT. It also confirmed that Physiological Equivalent Temperature (PET) and Predictive Mean Vote (PMV) are the most common indices. While ENVI-met and RayMan are the most common software to assess the OTC.

Enhancing indoor thermal comfort prediction in tropical regions: A transfer learning strategy in West Bengal

Indian Railways is one of the largest passenger transport networks in the “world” covering almost all parts of the subcontinent. Pantry car is an integral part of the railway, which provides food to the passengers during the journey. This study aims to evaluate the “indoor and outdoor thermal comfort parameters” and working conditions in the kitchen of the Indian “railway pantry car”. The field measurement was carried out during the summer season on six “Indian Railway Pantry Car Coaches (IRPCs)”. The “indoor and outdoor environmental parameters” were recorded during different cooking periods; “breakfast, lunch, snacks, and dinner” inside the pantry car. The consequence of this study revealed that the “indoor thermal comfort parameters” like; “wet-bulb temperature, mean radiant temperature, air temperature, relative humidity” were higher as compared to outdoor parameters except for air velocity. Most of the time, indoor parameters were higher during the lunch and snacks periods while lower at the breakfast period. Similarly, indoor Heat Index (HI) value was recorded higher than the outdoor. The indoor HI values range were found to be (40–58 °C), which indicated “danger to extreme danger” work condition. These outcomes will help to understand the “working environment of the railway pantry car kitchen”. Further, data measurements during winter and other seasons could be used to predict the thermal environment of the “pantry car”.KeywordsEnvironmental ergonomicsThermal comfortRailwayPantry car

Heritage mosques are the gems of the country as they preserve the history of local communities and nation. Many studies have been executed on the architectural characteristics of Malaysia heritage mosques. However, the empirical studies on its indoor environmental condition and thermal comfort are still lacking. Therefore, the objective of this study is to identify the indoor environmental condition and thermal comfort of Malaysia heritage mosque by using the field measurement method. The selected heritage mosque for this study is Masjid Tanah, which is located at Masjid Tanah, Alor Gajah, Melaka. Two multiparameter ventilation meters were used in the field measurement. The variables measured were air temperature and air velocity, while the indoor predicted comfort temperature was calculated using the adaptive thermal comfort model equation. The results show that the average indoor air temperatures were lower than the average outdoor air temperatures throughout the measurement. This is also similar with the indoor air velocities which were lower than the outdoor wind speeds at all times. Meanwhile, the results also demonstrate that the average indoor air temperatures were also lower than the indoor predicted comfort temperatures during the morning hours until 1 pm. The overall findings indicate that the architectural characteristics of the selected heritage mosque has a good response to the local climate. However, some improvements are necessary in enhancing the indoor thermal comfort. The findings can be used as guides for achieving a more comfortable indoor environmental condition of heritage mosques, as well as the modern mosques also.

This paper introduces an application of the dandelion optimization (DO) algorithm in antenna arrays. This is the first time that the DO algorithm has been used for optimizing antenna arrays. For antenna array optimization, sidelobe level (SLL) and deep nulls are key technical indicators. A lower SLL can improve the signal-to-noise ratio and reduce the impact of clutter signals outside the main beam. Deep nulls need to be aligned with the direction of interference to eliminate the influence of interference sources. The combination of the two can effectively improve the anti-interference ability of the entire system. Therefore, antenna arrays with ultra-low sidelobes and ultra-deep nulls are currently hot in the field of antenna array design and are also some of the key technologies needed to achieve modern high-performance radar systems. As a new type of evolutionary algorithm inspired by nature, the DO algorithm is inspired by the wind propagation behavior of dandelions in nature. This algorithm iteratively updates the population from three stages of ascent, descent, and landing, ultimately finding the optimal position. It has good optimization ability in solving complex problems such as those involving nonlinearity, discreteness, and non-convexity, and the antenna array pattern synthesis optimization problem belongs to multivariate nonlinear problems. Therefore, the DO algorithm can be effectively applied in the field of antenna array optimization. In this work, we use the following method to obtain an optimized pattern of a linear array with the lowest sidelobe level (SLL), null placement in particular directions, and a lower notch in particular directions: by controlling the antenna array’s element spacing and leaving the phase unchanged to optimize the current amplitudes and by controlling the excitation current and phase fixation of the antenna array and changing the element spacing. In the first and second examples, different algorithms are used to reduce the SLL of the antenna. In the first example, the DO algorithm reduces the SLL to −33.37 dB, which is 2.67 dB, 2.67 dB, 3.77 dB, 2.74 dB, and 2.52 dB lower than five other algorithms. In the second example, the SLL optimized by the DO algorithm is −42.56 dB, which is 5.04 dB and 1.48 dB lower than two other algorithms. In both examples, the DO algorithm reduces the SLL lower than other algorithms when the main lobe of the antenna is not significantly widened. Examples 3, 4, and 5 use the DO algorithm to optimize the amplitude of the current, generating deep nulls and deep notches in specific directions. In Example 3, the DO algorithm obtains a depth of nulls equal to −187.6 dB, which is 66.7 dB and 44.3 dB lower than that of the flower pollination algorithm (FPA) and the chaotic colony predation algorithm (CCPA), respectively. In Example 4, the deep null obtained by the DO algorithm is as low as −98.69 dB, which is 6.67 dB lower than the deep null obtained by the grey wolf optimization (GWO) algorithm. In Example 5, the deep notch obtained by the DO algorithm is as low as −63.1 dB, which is 6.4 dB and 1.9 dB lower than the spider monkey optimization (SMO) algorithm and the grasshopper optimization algorithm (GOA), respectively. The data prove that the DO algorithm produces deeper nulls and notches than other algorithms. The last two examples involve reducing sidelobe levels and generating deep nulls by optimizing the spacing between elements. In Example 5, the SLL obtained using the DO algorithm is −22.8766 dB, which is 0.1998 dB lower than the lowest SLL of −22.6768 dB among other algorithms. In Example 6, the SLL obtained using the DO algorithm is −20.1012 dB, and the null depth is −125.1 dB, which is 1.592 dB lower than the SLL obtained by the cat swarm optimization (CSO) algorithm and 19.1 dB lower than the deep null obtained by the GWO algorithm, respectively. In summary, the results of six simulation experiments indicate that the DO algorithm has better optimization ability in linear array optimization than other evolutionary algorithms.

Generally, optimization is defined as the process of determining the minimum or maximum value that depends on the function of the goal, even now there are many problems regarding optimization. One of them is the problem regarding the selection of goods to be included in a limited storage medium called Knapsack problem. Knapsack problems have different types and variations. This study will solve the problem of bounded knapsack multiple constraints by implementing the Grey Wolf Optimizer (GWO) algorithm. The problem of bounded knapsack multiple constraints has more than one subject with the items that are inserted into the dimension storage media can be partially or completely inserted, but the number of objects is limited. The aim of this study is to determine the results of using the Grey Wolf Optimizer (GWO) algorithm for solving the problem of multiple constraints bounded knapsack and compare the optimal solutions obtained by the simplex method using the Solver Add-In in Microsoft Excel. The data used in this study is primary data. There are two parameters to be tested, namely population parameters and maximum iteration. The test results of the two parameters show that the population parameters and maximum iterations have the same effect, where the greater the value of the population parameters and the maximum iteration, the results obtained are also getting closer to the optimal value. In addition, based on the results of the final experiment it is known that the comparison of the results of the GWO algorithm and the simplex method has a fairly small percentage deviation which indicates that the GWO algorithm produces results that are close to the optimal value.&#x0D; Keywords: GWO algorithm, Knapsack, Multiple Constraints Bounded Knapsack.

Experimental study on the physiological parameters of occupants under different temperatures and prediction of their thermal comfort using machine learning algorithms

Design and low energy ventilation solutions for atria in the tropics

Vernacular architecture employs numerous elements for enhancing natural ventilation, especially in the Mediterranean climate. However, the cooling effectiveness of natural ventilation also relies on occupant behaviour and is highly determined by urban scale attributes. Still, airflow in real, inhomogeneous historic urban settings is rarely integrated in the thermal comfort studies of historic buildings. In this study, a multi-scale approach is adopted in order to assess the role of ventilation in establishing thermal comfort in earthen buildings, in real field conditions. This is achieved by addressing field monitoring of air velocity, temperature and relative humidity in: a) a dense (packing density λp=0.60) and inhomogeneous historic neighbourhood in Nicosia, Cyprus (measurement at a reference height); b) the street-canyon (measured at the mid-height of a narrow canyon with aspect ratio 2); and c) the interior of a typical adobe building with semi-open, pass-through spaces (portico) and closed timber projections with multiple openings, called sachnisi. Building ventilation was addressed as a function of in-street and rooftop airflow. Indoor thermal comfort was assessed in the case of specific ventilation patterns, comparing three adaptive comfort models. The results highlight the complexity of airflow in real inhomogeneous urban canopies and demonstrate that air velocity level in the street canyon is approximately one third of the reference free-stream wind velocity, while indoor air velocity remains at minimum levels. The study also reveals the contribution of night-time ventilation in cooling. Finally, spatial differentials of indoor environmental conditions in the portico were recorded for the first time, demonstrating the role of the sachnisi as a wind-capture element.

The grey wolf optimization (GWO) algorithm was proposed in 2014 and after several years of applications, it was used worldwide and all over the subjects which involved computation. Various improvements have been raised to increase the capability of optimization. Based on the best performance of the slimd mould (SM) algorithm in optimization, a hybridization of the SM and GWO algorithms was proposed about the updating equations, and the GWO algorithm with multiple tunnels for individuals to update their positions during iterations was revised. Simulation experiments were carried out and comparisons were made between the GWO algorithm with variable weights and our proposed new one. Better performance were confirmed and reported as conclusions.