Occupant Comfort Research Articles

Internet of things and deep learning-enhanced monitoring for energy efficiency in older buildings

Retrofitting older buildings for energy efficiency is paramount in today's sustainability and environmental awareness era. Older buildings contribute greatly to energy waste since they typically lack new energy-efficient technology. Reducing carbon emissions, lowering energy bills, and extending the life of these historic landmarks all depend on fixing the energy inefficiency that plagues these buildings. Despite advanced technologies' remarkable progress, the potential of the Internet of Things and deep learning in older buildings has not been unexplored. Major obstacles include expensive and out-of-date infrastructure and the difficulty of incorporating new technology into historically significant structures. Existing research has mostly ignored older infrastructures' unique requirements and limitations in favour of current or newly built services. In addition, comprehensive research on integrating deep learning with the Internet of Things in this specific environment has been lacking. Smart building energy management is made possible by the Internet of Things (IoT) and deep learning. Architectural limitations, outmoded infrastructure, and the necessity for non-invasive retrofitting solutions all contribute to the difficulty of energy monitoring and improvement in older buildings. This research proposes combining the IoT with Deep Learning-enhanced Predictive Energy Modeling (DL-PEM) to make an energy management system that can change and adapt to the needs of older buildings. Data from IoT sensors is collected on occupancy, temperature, lighting, and equipment usage and then analyzed using Deep Learning models to determine the most efficient energy consumption patterns. Beyond its energy-saving potential, this method has many potential uses. Spotting and fixing structural problems before they become major can improve occupant comfort, reduce maintenance costs, and pave the way for predictive maintenance. Integration with the Smart grid and demand response programs can be facilitated, too, improving the reliability of the power system as a whole. Our IoT and Deep Learning-based energy management solution optimizes energy usage, reduces expenses, and mitigates environmental impact in older buildings, as shown by extensive simulation studies. The system's performance is compared to more conventional methods, and its flexibility is evaluated in various building and usage contexts. The experimental outcomes show the suggested DL-PEM model increases the energy demand forecasting analysis, energy consumption analysis, thermal comfort optimization analysis, seasonal variation analysis, and occupancy data analysis.

Modal analysis of Shanghai world financial center based on using ANSYS

This study delves into the resonance phenomena within the complex structure of the Shanghai Global Financial Center. By utilizing ANSYS simulations, we can accurately predict the vibration patterns and magnitudes exhibited by the building under various conditions. These resonance phenomena have the potential to significantly impact the buildings stability, occupant comfort, and overall structural integrity. This research conducts a thorough analysis of the self-resonance conditions of the Shanghai Global Financial Center through the application of ANSYS software. The study successfully identifies resonance frequencies and provides a deeper understanding of resonance mechanisms. These findings offer valuable insights for comprehending and mitigating resonance-related issues. Moreover, they hold great significance for the design and engineering of super-tall skyscrapers, offering essential guidance to ensure their safety and performance. AMSS_0403rchitects and engineers can use this knowledge to optimize the design and construction of such impressive structures, ultimately contributing to the advancement of tall building technology. Enze Li and Zhe Yu are dedicated to data collection, Bowen You and Yizhao Wang specialize in modeling and data recording and analysis, while Zhijie Shen and Enze Li are responsible for carefully crafting and refining the paper.

Research progress in home energy management systems consideration of comfort

According to statistics, the carbon dioxide emissions from Chinas power industry account for about 40% of the total energy consumption and carbon dioxide emissions, while residential electricity consumption accounts for 36.6% of the total social electricity consumption. However, ordinary households have low electricity efficiency and serious waste. In the context of the national strategy of carbon peak and carbon neutrality, the Home Energy Management System (HEMS) has been introduced to improve household electricity efficiency, reduce electricity consumption, and achieve energy conservation and emission reduction while ensuring the comfort of residents. This article introduces the current research status of home energy management systems that take into account user comfort, and shows some optimization models for home energy management systems that take into account user comfort. It specifically elaborates on the optimization models for household appliances and comfort, briefly outlines the relatively trendy load prediction and scheduling optimization models, and proposes some suggestions and prospects for popularizing knowledge related to home energy management systems for family members using smart homes and temperature comfort modeling based on the current development status.

A deep reinforcement learning-based method for dynamic quality of service aware energy and occupant comfort management in intelligent buildings

Buildings are responsible for 30 % oof the world’s energy consumption, about half of which is consumed by Heating, Ventilation, and Air Conditioning (HVAC) systems. Intelligent control of these can significantly reduce global energy consumption. However, these systems are also one the most important means of providing comfort to occupants within buildings. These two control objectives may conflict with each other, which means that reducing the energy consumption of the HVAC systems may lead to dissatisfaction among buildings’ occupants. Thus, in most cases, to handle the trade-off, weights are assigned to these objectives which indicate their importance. The priority of these goals may change throughout the operation, meaning that the value of assigned weights must change. To solve this problem, existing methods needed to be retrained every time that the weights changed, which is time-consuming and costly. Thus, an algorithm that can adapt to weight changes in operation time is needed. In this research, a dynamic multi-objective deep reinforcement learning algorithm is introduced to control the power of the HVAC system. Since it is needed to control the continuous power of the HVAC system, a Deep Deterministic Policy Gradient (DDPG) algorithm empowered by Tunable Training, is proposed which can adapt to changes of objectives weights. The controller can adapt to changes in the importance of objectives during operation and does not need to be retrained. The proposed method is compared with a dynamic multi-objective Deep Q-Network (DQN) Algorithm, which is used for discrete control, in a smart home. The results show that the cost of energy in the proposed method is up to 14 % lower than the DML-DQN algorithm.

Optimization of Distributed Energy Resources Operation in Green Buildings Environment.

Without a well-defined energy management plan, achieving meaningful improvements in human lifestyle becomes challenging. Adequate energy resources are essential for development, but they are both limited and costly. In the literature, several solutions have been proposed for energy management but they either minimize energy consumption or improve the occupant's comfort index. The energy management problem is a multi-objective problem where the user wants to reduce energy consumption while keeping the occupant's comfort index intact. To address the multi-objective problem this paper proposed an energy control system for a green environment called PMC (Power Management and Control). The system is based on hybrid energy optimization, energy prediction, and multi-preprocessing. The combination of GA (Genetic Algorithm) and PSO (Particle Swarm Optimization) is performed to make a fusion methodology to improve the occupant comfort index (OCI) and decrease energy utilization. The proposed framework gives a better OCI when compared with its counterparts, the Ant Bee Colony Knowledge Base framework (ABCKB), GA-based prediction framework (GAP), Hybrid Prediction with Single Optimization framework (SOHP), and PSO-based power consumption framework. Compared with the existing AEO framework, the PMC gives practically the same OCI but consumes less energy. The PMC framework additionally accomplished the ideal OCI (i-e 1) when compared with the existing model, FA-GA (i-e 0.98). The PMC model consumed less energy as compared to existing models such as the ABCKB, GAP, PSO, and AEO. The PMC model consumed a little bit more energy than the SOHP but provided a better OCI. The comparative outcomes show the capability of the PMC framework to reduce energy utilization and improve the OCI. Unlike other existing methodologies except for the AEO framework, the PMC technique is additionally confirmed through a simulation by controlling the indoor environment using actuators, such as fan, light, AC, and boiler.

Occupancy Comfort Evaluation in Green Building Rating Tools in Malaysia: A Comparative Review

Passive design strategy is the approach that maximizing utilization of natural resources to achieve occupancy comfort which covers the thermal comfort, visual comfort and acoustic comfort while minimizing secondary energy usage. Adapting passive design strategy during building design-stage is beneficial in reducing energy load of the building for long term, furthermore to reduce the energy consumption in day to day building operation. Applying Green Building Rating Tools, GBRT promotes passive design strategy for non-residential building and will assist the building designer to comply with the local and international standard. The minimum requirement of occupancy comfort is captured in GBRT rating system with different approach and intension of the system. This review summarize the coverage of passive design strategy sectors for non-residential building in Malaysia by comparing three GBRT system namely Green Building Index, GBI NCNR, MyCREST ICSAS and GreenRE NRB system. GreenRE NRB seems more aggressive in occupancy comfort evaluation compared to GBI NCNR and MyCREST ICSAS. GreenRE allocates 48.7% of total marks focus on occupancy comfort aspect while GBI and MyCREST allocates 14% and 13.2% respectively from the total score. MyCrest had enforce the mandatory compliance of OTTV, RTTV and Uroof to meet baseline requirement as per MS1525:2019 with zero marks allocation. Based on marks percentage allocation, GBI and MyCrest prioritizing visual comfort while GreenRE give more focus on thermal comfort with higher marks allocation. All rating system give less focus on acoustic comfort. On average, 16.3% of marks covers the thermal comfort, 9% covers visual comfort and 1% cover acoustic comfort. GBI and MyCrest focus more on green building materials which covers the building lifecycle includes water management and waste disposal. All system contributes to Malaysia-UNFCCC ratification of Paris Agreement on 45% GHG reduction in longer runs.

A practical real-time control strategy for high-performance building HVAC operation concerning potential pandemic outbreaks in post-pandemic era

The lessons learned from the COVID-19 pandemic emphasize the need for building HVAC systems to be adaptable and prepared to adjust their operation for infection risk mitigation for future pandemics. Most guidelines suggest increasing outdoor air fraction in HVAC systems during pandemics. However, this approach is not energy-efficient due to the conditioning of additional outdoor air, and many practical systems face limitations in introducing more outdoor air than normal due to capacity or design constraints. Therefore, there is an urgent need for an alternative solution for HVAC system operation during pandemics that is energy-efficient, can effectively mitigate infection risks and does not require extensive retrofits to existing systems. To meet this need, this study proposes a practical real-time control strategy for high-performance HVAC operation in response to potential pandemic outbreaks. First, a supply air temperature (SAT) reset scheme for infection risk mitigation is proposed based on Mamdani fuzzy inference theory. Then, a coordinated control scheme is proposed to coordinate SAT reset with chilled water temperature adjustment for energy-efficiency enhancement. This strategy does not require system equipment retrofits but only changes in control logic to transition to pandemic operation. The effectiveness of the proposed strategy is validated in a high-fidelity Modelica-based simulation environment under various weather conditions. Results show that, compared to normal operation, the proposed strategy can significantly reduce new infection cases by 32∼46 % without increasing energy use, and may even achieve slight energy savings of 9∼13 %, while maintaining expected occupant comfort.

Energy retrofitting of hospital buildings considering climate change: An approach integrating automated machine learning with NSGA-III for multi-objective optimization

In the context of sustainable development, energy-saving renovation of existing buildings can not only effectively reduce energy consumption but also improvement the residential comfort and office environments. This study proposes an optimization method for building energy-saving renovation based on automated machine learning and the NSGA-III algorithm, aiming at efficiently and accurately identifying the best energy-saving renovation schemes. The results showed that automated machine learning could provide a predictive model for multi-objective optimization analysis in a relatively short training time, with an average prediction accuracy of over 95%. And the Stacked Ensemble algorithm and Gradient Boosting Machine algorithm perform the best among all the algorithms considered in this study. Additionally, climate change significantly affects the energy-saving benefits and thermal comfort performance of renovation measures, thereby altering the choice of optimal schemes. The final renovation schemes obtained through the NSGA-III and entropy weight TOPSIS method can achieve an energy saving rate of 22.06% to 26.48% under typical climate scenarios, while also improving thermal comfort time by 31.87% to 43.73%. In future climate scenarios, an energy saving rate of 32.73% to 33.02% and a thermal comfort time of 40.20% to 42.29% can be achieved. Combining these two technologies can quickly and effectively find the best balance among energy consumption, whole life cycle cost, and thermal comfort time. The method proposed in this paper offers new perspectives and tools for researchers in the field of building energy conservation, demonstrating the application potential of automated machine learning and the NSGA-III algorithm in the energy-saving renovation of hospital buildings.

A circular approach to stone wool: Alkali-activated lightweight aggregates

This study investigates the high-value recycling of stone wool from construction and demolition waste into alkali-activated lightweight insulation aggregates, designed for ground cover insulation. Various proportions of milled and as-is stone wools are alkali-activated to produce aggregates. The aggregates demonstrate loose bulk densities ranging from 720 to 850 kg m−3 and dry thermal conductivity from 0.075 to 0.094 W m−1·K−1, with moderate water sorption capacities. The fibre morphology of as-is stone wool influences rheology, introducing a greater number of pores or defects, which results in a decrease in mechanical strength. Hydrothermal simulations reveal that the floor assembly of the rehabilitated crawl space, partially filled with the fabricated aggregates, shows a reduction in water content and an increase in floor surface temperature. This observation suggests potential benefits for maintaining the structural integrity of buildings and enhancing occupant comfort.

Exploring the impact of HCI on smart buildings: A comprehensive literature review on user experience and sustainability

This paper provides insights into the application of human-computer interaction (HCI) principles in the field of smart building design, particularly their impact on improving occupant comfort, building energy efficiency, and the user interaction experience. The research context focuses on advances in HCI and the importance of smart buildings in enhancing quality of life and sustainability. The research theme focuses on how HCI principles can be utilized to improve the user interface design of smart buildings in order to promote more effective user-building system interactions. Through an extensive review of existing literature in the area of HCI and smart buildings, including recent research papers, case study reports, and technical overviews, this study concentrates on analyzing examples of HCI applications in smart lighting, temperature control systems, and energy management. Through this comprehensive literature review, this paper aims to illustrate how HCI principles can provide theoretical and practical guidance for the design of more humanized, interactive and environmentally friendly smart buildings, thereby providing insights and recommendations for future smart building design and research.

Prefabricated Envelope Green Remodeling Potential of Public Office Buildings in Korea

The public sector should reduce energy consumption and carbon emissions from the building stock, thereby serving as a role model for the private sector. In Korea, public buildings are leading the green remodeling business initiative as part of a carbon-neutral strategy. Building envelope retrofitting is essential for the green remodeling of existing buildings because it significantly affects the buildings’ aesthetic appearance, occupant comfort, and energy usage. From the perspectives of constructability and cost, prefabricated envelope systems offer various advantages and can contribute to the growth of the green remodeling business. To develop an effective prefabricated envelope system, a thorough analysis of the existing building stock must be conducted. Therefore, this study aims to investigate existing public office buildings in Korea to obtain a better understanding of the considerations necessary for developing prefabricated envelope systems. The survey utilized the image search and road-view functions of map services, following an appropriate sample design. Based on the survey results, the characteristics of the building types and envelopes, as well as considerations for developing prefabricated envelope systems are discussed. Furthermore, this study quantitatively analyzed the energy conservation potential through building energy simulations.

3D reconstruction of semantic-rich digital twins for ACMV monitoring and anomaly detection via scan-to-BIM and time-series data integration

Current research in air-conditioning and mechanical ventilation (ACMV) operation focuses on isolated sub-processes and analytical models. Digital twins, as digital replicas of assets, processes, or systems in the built environment, enable facilities manager (FM) to gain insights into the physical features of space, equipment performance, and energy efficiency. This study presents the 3D reconstruction of semantic-rich digital twins, which encompasses conditional and machine learning-enabled monitoring with 3D geometric models, for ACMV modeling and operation. The proposed framework involves a hybrid rule-based and data-driven approach to forecast the performance of indoor environment and identify potential anomalies throughout ACMV operation. Following this, a scan-to-BIM process is undertaken, with the aid of Simultaneous Localization and Mapping algorithms, to semi-automatically generate the as-built geometric models. Lastly, semantic enrichment of BIM is performed by incorporating time-series data from the rule-based and data-driven approach with 3D geometric models. The proposed approach supports the reconstruction of content-aware and semantic-rich digital twins, which utilize sensor-derived time-series data and 3D geometric models, to conduct advanced analysis for intelligent ACMV operation towards energy efficiency and occupant comfort.

Digital occupancy assessment for lighting evaluation: a pilot study to prepare for real-time research results

The relationship between lighting and human well-being is pivotal in architecture and environmental design. Adequate lighting enhances visual appeal and significantly influences occupant comfort, productivity, and satisfaction. This pilot study aimed to integrate digital occupancy assessment methods to understand indoor lighting conditions' impact on occupant well-being. Hypotheses explored the potential link between lighting conditions and occupant well-being, as assessed through physiological indicators and the influence of interior attributes on occupants' perceptions and physiological responses. The identified main components were satisfaction with artificial and daylighting, ambiance, and stimulation. The study explored the relationship between lighting conditions, physiological responses, and subjective assessments, revealing potential influences on occupant perceptions. A real-time data visualization could be valuable for data-intensive projects, enhancing comprehension and decision-making for facility management. While limited by the small sample size, trends, and moderate correlations were observed, indicating the need for larger, more diverse samples in future research.

Sustainable Structural System Selection Using Hybrid Fuzzy Multi-Criteria Decision Model Based on Seismic Performance

In the rapidly evolving field of sustainable construction, this study aims to address the critical need for advancement in the building industry, focusing on vital indicators like energy efficiency and cost-effectiveness, as well as improving occupant comfort. This research introduces a novel approach to support the choice of suitable structural systems for mass housing projects, with a case study on Iran’s national housing scheme. This methodology involves a four-phase process, beginning with compiling a database from existing studies to outline primary and secondary indicators affecting structural system selection. It utilizes the fuzzy AHP method for criteria prioritization and the fuzzy TOPSIS technique for alternatives (LSF, 3DP, ICF, TRC, and RCCF). The study identified the light steel framing (LSF) system as the optimal choice for Iran’s housing needs based on various criteria. Then, in the final phase, the study evaluates the seismic performance of cold-formed steel (CFS) frames with various sheathing panel types (OSB, DFP, CSP, and GWB) under monotonic loads, examining key seismic parameters across 38 frame setups. The findings reveal that LSF structures can effectively withstand seismic events within the elastic behavior range, suggesting that this construction approach is viable for enhancing mass housing production in Iran’s construction sector.

Integrating Internet of Things (IoT) Approach to Post-Occupancy Evaluation (POE): An Experimental At-the-Moment Occupant Comfort Control System

This paper describes an empirical experiment of Internet of Things (IoT)’s integration in the Post-Occupancy Evaluation (POE) process. The experiment aimed to trial a novel IoT approach to enabling building user responsiveness to prevalent IEQ for individualised comfort. The purpose is to provide a system that mitigates a common issue of centralised air conditioning that limits occupants’ control over their immediate environment. To achieve this, an IoT platform was developed with smart IEQ monitoring sensors and wearable devices and trialled with PhD researchers in a shared university workspace. The findings provided empirical evidence of IoT’s enhanced benefits to improving user control over their individual comfort and enabling positive energy behaviour in buildings. Specifically, the IoT system provided real-time insight into CO2 concentration data while enabling responsive occupant interaction with their immediate environment and at-the-moment mitigation actions. Outputs of the experiment showed that the perceptions of participants about the stuffiness of the air, productivity, and healthy environment were significantly better after taking the mitigation action compared to before. Also, we found a significant relationship between measured CO2 concentration readings and perceived air stuffiness (p = 0.004) and productivity (p = 0.006) and a non-significant relationship between CO2 concentration readings and perceived healthy environment (p = 0.058). Interestingly, we observed that irrespective of the similarities in recorded CO2 concentration readings being within acceptable ranges (632–712 ppm), the perception of air stuffiness significantly differed (p = 0.018) before and after the mitigation actions. The effectiveness of the developed IoT platform was evidenced as most of the participants found the process very easy to participate in with little interruptions to their work as little time was consumed. The results are useful in modifying approaches to building occupant comfort and energy behaviour in commercial and residential settings.

Summer and winter performance evaluation of double layered PTFE dome with aerogel-glass wool thermal insulation- field experiments and numerical simulation

Achieving optimal thermal performance in large membrane-enclosed buildings presents a significant challenge. Aerogel mats offer potential for enhanced insulation, but their effectiveness in varying seasonal conditions is yet to be fully determined. The current study investigates the thermal performance of an enclosed dome with double-layered PTFE membrane roof integrated with aerogel-glass wool insulation mats. This research utilizes field experiments to assess indoor thermal comfort and numerical model to evaluate the effectiveness of the dome’s insulation capabilities during summer and winter conditions. The Aerogel integrated areas show a difference of 10.26/3.72 °C for summer/winter while that of 9.36/3.22 °C for glass wool-integrated areas. An online thermal comfort tool utilized maximum indoor temperature values during both seasons obtained from numerical results indicating that winter comfort falls within ASHRAE comfort range with PMV value −0.48 but summer conditions require enhancements. Additionally, the study assessed the insulation’s effectiveness using Maximum Reduction in Temperature (MRT), Decay Factor (DF), and Time Delay (TD) indicators. Results showed significant thermal lag, with peak temperature delays of up to 3.1 h in summer and 2.2 h in winter. Notable temperature differences between the dome’s inner and outer surfaces, alongside 28 % and 27 % DF reductions during summer and winter, respectively, demonstrated the roof insulation’s effectiveness. These findings support the use of both experimental and numerical methods to develop thermal management practices that improve sustainable building design, emphasizing occupant comfort and energy efficiency.

Prediction of residential building occupancy using Machine learning with integrated sensor and survey Data: Insights from a living lab in Morocco

Building occupancy information is essential for effective energy management in buildings through the adoption of energy conservation and occupant-centric control strategies. These strategies endeavor to contribute to optimizing energy consumption while ensuring occupant comfort. This study focuses on advanced occupancy modeling techniques to enhance energy efficiency in residential buildings, utilizing various data-driven techniques. Various Machine Learning models, such as Random Forest, Bayesian Network, Decision Trees, Support Vector Machines, K-Nearest Neighbors, eXtreme Gradient Boosting, and Regularized Greedy Forest, have been evaluated for predicting and classifying building occupancy. Employing a living lab approach within a residential setting, the research evaluates model performance using two ground truth datasets: IoT sensor and survey data. Experimental tests use Accuracy and F1_score as evaluation criteria, demonstrating accuracy rates ranging from 70% to 95.96%. The results highlight the performance of these models in predicting residential occupancy, offering valuable insight into two approaches to occupancy modeling. The Random Forest model performs exceptionally well in capturing occupancy trends, while the Bayesian Network model, combined with expert knowledge, provides detailed predictions of occupancy types and zones. The research also addresses challenges related to data collection, including privacy concerns. It presents effective occupancy modeling strategies for residential energy management.

When thermochromic material meets shape memory alloy: A new smart window integrating thermal storage, temperature regulation, and ventilation

Traditional windows have poor thermal insulation performance, resulting in significant indoor heat loss in winter and outdoor heat entry in summer. Thermochromic smart windows can effectively block solar radiant heat by automatically adjusting light transmittance, thereby reducing air conditioning loads and leading to significant energy savings. In this study, the poly N-isopropyl acrylamide (PNIPAm)-based thermochromic hydrogel, modified MXene nanoparticles, and NiTi shape memory alloy (SMA) are integrated to endow the smart window with heat storage, temperature control, and ventilation. The smart window achieves 88.6% visible light transmission and 70% solar modulation. The inclusion of MXene nanoparticles further enhances photothermal response efficiency, while the ventilation system ensures efficient and fresh indoor air circulation. Compared to the common glass, the smart window reduces the indoor temperature by 8 °C, demonstrating its excellent temperature regulation ability. Simulation results indicate that in Shanghai, Cairo, Singapore, and Kuwait, the employment of thermochromic smart windows can reduce heating, ventilation, and air conditioning energy consumption (HVAC) by 32.6%, 49.9%, 42.7%, and 34.1%, respectively. This versatile thermochromic smart window is expected to significantly improve building efficiency and occupant comfort, offering a sustainable solution for future building designs.

Towards Sustainable Living through Thermoneutral Temperature Management in Subtropical Steppe Climates

This study addresses the critical interplay between sustainable living and thermal comfort within residential buildings in subtropical steppe (BSh) climates, particularly in Northern Iraq. With the global imperative to enhance energy efficiency and occupant well-being, this research emphasizes the identification of thermoneutral indoor air temperature ranges that both support sustainable energy use and ensure the occupants’ thermal comfort. By analyzing the acceptable temperature limits across different building orientations during summer and winter, the study utilizes the predicted mean vote–predicted percentage dissatisfied (PMV-PPD) index approach to establish thermal comfort thresholds. The findings reveal that the optimal summer and winter indoor air temperatures are 29.2 °C and 19.4 °C, respectively, with variations across orientations highlighting the significant influence of building directionality on achieving thermoneutral conditions. A wider range of accepted temperatures exists in the eastward orientation in summer (between 26.6 °C and 29.2 °C). The study advances our understanding of sustainable thermal comfort practices, proposing orientation-specific temperature ranges as a cornerstone for reducing energy consumption without compromising occupant comfort in subtropical steppe climates.

Data-efficient comfort modeling: Active transfer learning for predicting personal thermal comfort using limited data

Personal comfort models are used to predict thermal comfort responses at the individual level rather than predicting the average thermal comfort responses for large populations. These models, data-driven in nature, need to be trained on large amounts of occupant comfort feedback and sensor data to achieve accurate predictions. However, collecting such data is often expensive and labor-intensive in reality. To address this, we proposed a data-efficient active transfer learning (ATL) framework to improve the performance of personal comfort models under limited data. To demonstrate the validity of this framework, we developed a base Convolutional Neural Network-Long Short-term Memory (CNNLSTM) model alongside two transfer learning models utilizing feature extraction (TL-CNNLSTM-FE) and fine-tuning (TL-CNNLSTM-FE) approaches, enhanced by a novel active learning strategy. Using these models, three comfort prediction tasks (i.e., thermal preference, thermal acceptability, and air movement preference) were performed by transferring the knowledge from the ASHRAE Global Thermal Comfort Database II to a limited dataset collected in the tropics. Empirical results indicate that the active transfer learning framework proposed was able to consistently outperform the base and transfer learning models using only less than 10% of the training data for all personal comfort tasks, highlighting the effectiveness of this strategy. The implications of this work are especially useful for the research community working on the practical applications of data-efficient machine learning approaches for personal thermal comfort predictions.