Domain Knowledge Research Articles

Automated 3D convolutional neural network architecture design using genetic algorithm for pulmonary nodule classification

Cancer of the lungs is considered one of the primary causes of death among patients globally. Early detection contributes significantly to the success of pulmonary cancer treatment. To aid the pulmonary nodule classification, many models for the analysis of medical image utilizing deep learning have been developed. Convolutional neural network (CNN) recently, has attained remarkable results in various image classification tasks. Nevertheless, the CNNs performance is heavily dependent on their architectures which still heavily reliant on human domain knowledge. This study introduces a cutting-edge approach that leverages genetic algorithms (GAs) to automatically design 3D CNN architectures for differentiation between benign and malignant pulmonary nodules. The suggested algorithm utilizes the dataset of lung nodule analysis 2016 (LUNA16) for evaluation. Notably, our approach achieved exceptional model accuracy, with evaluations on the testing dataset yielding up to 95.977%. Furthermore, the algorithm exhibited high sensitivity, showcasing its robust performance in distinguishing between benign and malignant nodules. Our findings demonstrate the outstanding capabilities of the proposed algorithm and show an outstanding performance and attain a state of art solution in lung nodule classification.

Understanding the factors that influence CT utilization for mild traumatic brain injury in a low resource setting - a qualitative study using the Theoretical Domains Framework

IntroductionIn low resource settings (LRS), utilization of Computed Tomography scan (CTS) for mild traumatic brain injuries (mTBIs) presents unique challenges and considerations given the limited infrastructure, financial resources, and trained personnel. The Theoretical Domains Framework (TDF) offers a comprehensive theoretical lens to explore factors influencing the decision-making to order CTS for mTBI by imaging referrers (IRs). ObjectivesThe primary objective was to explore IRs’ beliefs about factors influencing CT utilization in mTBIs using TDF in Uganda.Differences in the factors influencing CTS ordering behavior across specialties, levels of experience, and hospital category were also explored. Materials and MethodsIn-depth semi-structured interviews guided by TDF were conducted among purposively selected IRs from 6 tertiary public and private hospitals with functional CTS services. A thematic analysis was performed with codes and emerging themes developed based on the TDF. ResultsEleven IRs including medical officers, non-neurosurgeon specialists and neurosurgeons aged on average 42 years (SD+/-12.3 years) participated.Identified factors within skills domain involved IRs’ clinical assessment and decision-making abilities, while beliefs about capabilities and consequences encompassed their confidence in diagnostic abilities and perceptions of CTS risks and benefits. The environmental context and resources domain addressed the availability of CT scanners and financial constraints. The knowledge domain elicited IRs’ understanding of clinical guidelines and evidence-based practices while social influences considered peer influence and institutional culture. For memory, attention & decision processes domain, IRs adherence to guidelines and intentions to order CT scans were cited. ConclusionUsing TDF, IRs identified several factors believed to influence decision making to order CTS in mTBI in a LRS. The findings can inform stakeholders to develop targeted strategies and evidence-based interventions to optimize CT utilization in mTBI such as; educational programs, workflow modifications, decision support tools, and infrastructure improvements, among others.

Creativity in a music composition community: an analysis of online comments

ABSTRACT Scholars have often highlighted the intrinsic features of technology to support the generation and sharing of ideas (Craft 2011). By studying user interactions within informal online communities, researcher can elucidate the ways technology impacts creativity and learning within these groups. This qualitative content analysis (Hsieh and Shannon 2005) used a systems-based approach to creativity (Csikszentmihalyi 1999) to examine the interactions within an online community (Noteflight) focused on Western standard music notation-based composition. One popular, publicly available, original musical score was selected. Online comments were collected and analysed. Findings highlight the diversity and abundance of feedback given to the composer as well as the many ways users engaged with domain knowledge. This online community allows individuals to share knowledge, learn about the social norms associated with giving feedback, and explore creative ideas regarding music composition. Implications from this study highlight the ways music educators and technology designers can develop web-based music learning environments that support creativity and life-long engagement.

A lightweight sensor ontology for supporting sensor selection, deployment, and data processing in forming processes

AbstractIn the era of smart manufacturing, modern manufacturing systems face high demands for enhancing process performance and reducing machine downtime. Sensors and process data are essential for successfully implementing data-driven approaches to guarantee robust and reliable process monitoring, tool conditioning, or quality assurance. However, the accuracy and performance of such approaches are highly dependent on the quality of the gathered sensor data and influenced by the implemented data acquisition and processing methods. For this purpose, this work proposes a lightweight sensor ontology to provide a comprehensive overview to characterize underlying relationships between the physical environment and the quality of the data sets. The extended sensor ontology, in combination with domain knowledge, aims to support engineers in fully exploiting the potential of sensor data to obtain trustworthy data sets in forming technologies. As a result, this approach can improve the implementation of automated and data-driven process monitoring of forming systems and tools.

A Novel Framework for Joint Learning of City Region Partition and Representation

The proliferation of multimodal big data in cities provides unprecedented opportunities for modeling and forecasting urban problems, such as crime prediction and house price prediction, through data-driven approaches. A fundamental and critical issue in modeling and forecasting urban problems lies in identifying suitable spatial analysis units, also known as city region partition. Existing works rely on subjective domain knowledge for static partitions, which is general and universal for all tasks. In fact, different tasks may need different city region partitions. To address this issue, we propose JLPR , a task-oriented framework for J oint L earning of region P artition and R epresentation. To make partitions fit tasks, JLPR integrates the region partition into the representation model training and learns region partitions using the supervision signal from the downstream task. We evaluate the framework on two prediction tasks (i.e., crime prediction and housing price prediction) in Chicago. Experiments show that JLPR consistently outperforms state-of-the-art partitioning methods in both tasks, which achieves above 25% and 70% performance improvements in terms of mean absolute error for crime prediction and house price prediction tasks, respectively. Additionally, we meticulously undertake three visualization case studies, which yield profound and illuminating findings from diverse perspectives, demonstrating the remarkable effectiveness and superiority of our approach.

V4RIN: visual analysis of regional industry network with domain knowledge.

The regional industry network (RIN) is a type of financial network derived from industry networks that possess the capability to describe the connections between specific industries within a particular region. For most investors and financial analysts lacking extensive experience, the decision-support information provided by industry networks may be too vague. Conversely, RINs express more detailed and specific industry connections both within and outside the region. As RIN analysis is domain-specific and current financial network analysis tools are designed for generalized analytical tasks and cannot be directly applied to RINs, new visual analysis approaches are needed to enhance information exploration efficiency. In this study, we collaborated with domain experts and proposed V4RIN, an interactive visualization analysis system that integrates predefined domain knowledge and data processing methods to support users in uploading custom data. Through multiple views in the system panel, users can comprehensively explore the structure, geographical distribution, and spatiotemporal variations of the RIN. Two case studies were conducted and a set of expert interviews with five domain experts to validate the usability and reliability of our system.

Enhancing Molecular Property Prediction through Task-Oriented Transfer Learning: Integrating Universal Structural Insights and Domain-Specific Knowledge.

Precisely predicting molecular properties is crucial in drug discovery, but the scarcity of labeled data poses a challenge for applying deep learning methods. While large-scale self-supervised pretraining has proven an effective solution, it often neglects domain-specific knowledge. To tackle this issue, we introduce Task-Oriented Multilevel Learning based on BERT (TOML-BERT), a dual-level pretraining framework that considers both structural patterns and domain knowledge of molecules. TOML-BERT achieved state-of-the-art prediction performance on 10 pharmaceutical datasets. It has the capability to mine contextual information within molecular structures and extract domain knowledge from massive pseudo-labeled data. The dual-level pretraining accomplished significant positive transfer, with its two components making complementary contributions. Interpretive analysis elucidated that the effectiveness of the dual-level pretraining lies in the prior learning of a task-related molecular representation. Overall, TOML-BERT demonstrates the potential of combining multiple pretraining tasks to extract task-oriented knowledge, advancing molecular property prediction in drug discovery.

Unstructured Document Information Extraction Method with Multi-Faceted Domain Knowledge Graph Assistance for M2M Customs Risk Prevention and Screening Application

As a crucial national security defense line, the existing risk prevention and screening system of customs falls short in terms of intelligence and diversity for risk identification factors. Hence, the urgent issues to be addressed in the risk identification system include intelligent extraction technology for key information from Customs Unstructured Accompanying Documents (CUADs) and the reliability of the extraction results. In the customs scenario, OCR is employed for M2M interactions, but current models have difficulty adapting to diverse image qualities and complex customs document content. We propose a hybrid mutual learning knowledge distillation (HMLKD) method for optimizing a pre-trained OCR model’s performance against such challenges. Additionally, current models lack effective incorporation of domain-specific knowledge, resulting in insufficient text recognition accuracy for practical customs risk identification. We propose a customs domain knowledge graph (CDKG) developed using CUAD knowledge and propose an integrated CDKG post-OCR correction method (iCDKG-PostOCR) based on CDKG. The results on real data demonstrate that the accuracies improve for code text fields to 97.70%, for character type fields to 96.55%, and for numerical type fields to 96.00%, with a confidence rate exceeding 99% for each. Furthermore, the Customs Health Certificate Extraction System (CHCES) developed using the proposed method has been implemented and verified at Tianjin Customs in China, where it has showcased outstanding operational performance.

Knowledge and attitude towards home quarantine instructions and associations with history of Covid-19 infection in Malaysia

IntroductionAlthough COVID-19 has entered the endemic phase, individuals infected with COVID-19 are required to adhere to home quarantine measures. By exploring the public’s knowledge and attitude towards recommended home quarantine measures, their readiness in containing potential COVID-19 outbreak can be determined. This study aimed to assess the public knowledge and attitude towards home quarantine instructions and their association with history of COVID-19 infections.MethodsThis was a web-based cross-sectional study conducted among the public in Malaysia between August to October 2022. All Malaysian adults over 18 years of age were included. Knowledge on home quarantine instructions and COVID-19 warning signs were measured using “True,” “False,” or “I’m not sure”, while attitude towards home quarantine instructions was measured using a five-point Likert Scale. The questionnaire was initially constructed in English and then translated into the national language, Bahasa Malaysia. Face and content validation were performed. The internal consistency of the questionnaire was found to be satisfactory.Results1,036 respondents were analyzed, comprised mostly of females (743, 71.6%) with a history of COVID-19 (673, 64.9%). In the knowledge domain, more than 80% of the respondents answered 9 out of 11 home quarantine instructions statements correctly. 457 (44.1%) were unaware or unsure about the minimum distance of the infected individual’s bed from the rest of the occupants in a shared bedroom. The respondents reported relatively weaker knowledge in identifying uncommon warning signs of COVID-19 deterioration, including anuria (162, 44.5%), ingestion problems (191, 52.5%), and immobility (195, 53.6%). In the attitude domain, more than 90% of respondents answered correctly in 8 out of 9 questions. Respondents with a previous history of COVID-19 infections had better knowledge than COVID-19 infection-naïve individuals towards both home quarantine instructions and COVID-19 warning signs.ConclusionMost respondents had good knowledge and attitude towards home quarantine instructions, with those previously infected with COVID-19 showing greater awareness of uncommon warning signs. However, there was a notable lack of awareness regarding physical distancing within shared rooms, appropriate disinfectant use and mobility limitation within the household. This study highlights the knowledge gaps to be improved in future educational campaigns.

Taxonomy of performance shaping factors in manufacturing: A systematic literature review

AbstractHuman error in manufacturing can have substantial consequences, including loss of life, injuries, productivity, and financial losses. Human reliability analysis (HRA) methods can be used to evaluate the likelihood of human error in manufacturing tasks and identify potential sources of error. Performance shaping factors (PSFs) are internal and external factors that influence human performance and can affect the likelihood of human reliability estimates in HRA methods. Understanding the impact of PSFs on human performance in manufacturing is essential for developing effective strategies to minimize the likelihood of human error and improve the safety and efficiency of manufacturing processes. This systematic review scrutinizes the literature on PSFs within manufacturing, highlighting HRA applications. Using the PRISMA protocol, studies from 2000 to 2024 across engineering and psychology were examined, culminating in the analysis of 35 pertinent works. The review identifies and contrasts various PSF taxonomies from established HRA methods like SPAR‐H, HEART, CREAM, and THERP, revealing their diverse applications in different manufacturing settings. The review also uncovers a tendency to devise taxonomies through the lens of experts' domain knowledge, particularly tailored to discrete manufacturing contexts. A critical gap is observed in the lack of a uniform PSF framework, with the current literature reflecting a disparate understanding of PSFs' roles, definitions, and interrelations. This absence is further pronounced by the inadequate integration of human factors in the dialogue surrounding Industry 4.0. The analysis points to the necessity of harmonizing PSFs to better assess human reliability amid technological integration. The findings emphasize the need for an industry‐specific PSF framework that aligns with the intricacies of manufacturing operations, thus enabling more accurate HRA outcomes and informing strategies for error reduction and process optimization.

Exploration of materials fatigue influence factors using interpretable machine learning

AbstractData‐driven fatigue strength predictions are gaining popularity. Nevertheless, many machine learning models lack trustworthiness due to their limited decision‐making transparency which often hinders their practical application. In this investigation, we assess the expressiveness of the model‐agnostic explainable AI method known as SHapley Additive exPlanations (SHAP) for data‐driven fatigue strength prediction. Our study demonstrates that the SHAP feature sensitivity analysis underpins known physical relations from materials processing and fatigue theory. This even applies in view of the high‐dimensional, cross‐correlated fatigue feature space and despite data heterogeneity (different steels, component designs, and loads). For instance, SHAP indicates a fatigue strength increase with higher solid solution‐strengthening element concentrations, such as chromium and nickel. SHAP identifies correlations rather than causality. Thus, data science and domain knowledge should be closely linked during the SHAP assessment. If this is satisfied, plausible causal relations can be inferred, and spurious ones arising from confounding variables can be discarded.

F rugal L ight : Symmetry-Aware Cyclic Heterogeneous Intersection Control using Deep Reinforcement Learning with Model Compression, Distillation and Domain Knowledge

Developing countries need to better manage fast increasing traffic flows, owing to rapid urbanization. Else, increasing traffic congestion would increase fatalities due to reckless driving, as well as keep vehicular emissions and air pollution critically high in cities like New Delhi. State-of-the-art traffic signal control methods in developed countries, however, use expensive sensing, computation, and communication resources. How far can control algorithms go, under resource constraints, is explored through the design and evaluation of FrugalLight (FL) in this article. We also captured and processed a real traffic dataset at a busy intersection in New Delhi, India, using efficient techniques on low cost embedded devices. This dataset ( https://delhi-trafficdensity-dataset.github.io ) contains traffic density information at fine time granularity of one measurement every second, from all approaches of the intersection for 40 days. FrugalLight ( https://github.com/sachin-iitd/FrugalLight ) is evaluated on the collected traffic dataset from New Delhi and another open source traffic dataset from New York. FrugalLight matches the performance of state-of-the-art Convolutional Neural Network (CNN) based sensing and Deep Reinforcement Learning (DRL) based control algorithms, while utilizing resources less by an order of magnitude. We further explore improvements using a careful combination of knowledge distillation and domain knowledge based DRL model compression, with employing Model-Agnostic Meta-Learning to quickly adapt to traffic at new intersections. The collected real dataset and FrugalLight therefore opens up opportunities for resource efficient RL based intersection control design for the ML research community, where the controller should have limited carbon footprint. Such intelligent, green, intersection controllers can help reduce traffic congestion and associated vehicular emissions, even if compute and communication infrastructure is limited in low resource regions. This is a critical step toward achieving two of the United Nations Sustainable Development Goals (SDG), namely sustainable cities and communities and climate action.

Transdisciplinary fine-grained citation content analysis: A multi-task learning perspective for citation aspect and sentiment classification

The diffusion of citation knowledge is an important measure of transdisciplinary scientific impact and the diversity of transdisciplinary citation content (sentences). Moreover, combining citation sentiment (CS) and citation aspect (CA) can help researchers identify the attitudes, ideas, or positions reflected in the evolution of scientific elements (e.g., theories, techniques, and methods). This is because of their use by scholars from different disciplines, paving the way toward transdisciplinary penetration and the development of domain knowledge through the proliferation of cited knowledge. However, most studies mainly address citation aspect classification (CAC) and citation sentiment classification (CSC) separately, ignoring their shared features of interactions. In this study, we construct a dataset for transdisciplinary citation content analysis using citations and academic full texts from the Chinese Social Sciences Citation Index (CSSCI), which includes 14,832 manually-annotated citations. Thereafter, we utilized the developed dataset to conduct a transdisciplinary fine-grained citation content analysis by combining CAC and CSC. The objective of the CAC task was to classify transdisciplinary citations into theoretical concepts (TC), methodological techniques (MT), and data information (DI), whereas the CSC task classified citations into positive, negative, and neutral classes. Furthermore, we leveraged a multi-task learning (MTL) model to perform CAC and CSC jointly and then compared its performance to those of several widely-used deep learning models. Our model achieved 83.10 % accuracy for CAC and 80.46 % accuracy for CSC, demonstrating its superiority to single-task systems. This indicates the strong correlation between the CAC and CSC of transdisciplinary citation tasks, benefiting from each other when learned concurrently. This new method can be used as an auxiliary decision support system to extend the analysis of transdisciplinary citation content.

Unravelling uncertainty in trajectory prediction using a non-parametric approach

Predicting the trajectories of road agents is fundamental for self-driving cars. Trajectory prediction contains many sources of uncertainty in data and modelling. A thorough understanding of this uncertainty is crucial in a safety-critical task like auto-piloting a vehicle. In practice, it is necessary to distinguish between the uncertainty caused by partial observability of all factors that may affect a driver’s near-future decisions, the so-called aleatoric uncertainty, and the uncertainty of deploying a model in new scenarios that are possibly not present in the training set, the so-called epistemic uncertainty. They reflect the trade-off between data collection and model improvement In this paper, we propose a new framework to systematically quantify both sources of uncertainty. Specifically, to approximate the spatial distribution of an agent’s future position, we propose a 2D histogram-based deep learning model combined with deep ensemble techniques for measuring aleatoric and epistemic uncertainty by entropy-based quantities. The proposed Uncertainty Quantification Network (UQnet) employs a causal part to enhance its generalizability so rare driving behaviours can be effectively identified. Experiments on the INTERACTION dataset show that UQnet is able to give more robust predictions in generalizability tests compared to the correlation-based models. Further analysis presents that high aleatoric uncertainty cases are mainly caused by heterogeneous driving behaviours and unknown intended directions. Based on this aleatoric uncertainty component, we estimate the lower bounds of mean-square-error and final-displacement-error as indicators for the predictability of trajectories. Furthermore, the analysis of epistemic uncertainty illustrates that domain knowledge of speed-dependent driving behaviour is essential for adapting a model from low-speed to high-speed situations. Our paper contributes to motion forecasting with a new framework, that recasts the problem of accuracy improvement in a way that focuses on differentiating between unpredictable components and rare cases for which more and different data should be collected.

A review of explainable fashion compatibility modeling methods

The paper reviews methods used in the fashion compatibility recommendation domain. We select methods based on reproducibility, explainability, and novelty aspects and then organize them chronologically and thematically. We presented general characteristics of publicly available datasets that are related to the fashion compatibility recommendation task. Finally, we analyzed the representation bias of datasets, fashion-based algorithms’ sustainability, and explainable model assessment. The paper describes practical problem explanations, methodologies, and published datasets that may serve as an inspiration for further research. The proposed structure of the survey organizes knowledge in the fashion recommendation domain and will be beneficial for those who want to learn the topic from scratch, expand their knowledge, or find a new field for research. Furthermore, the information included in this paper could contribute to developing an effective and ethical fashion-based recommendation system.

As Teachers Not Tourists: Creating Knowledge During a Short-Term Study Abroad Program

Here, I address the call for teacher education programs to feature international elements to help pre-service teachers craft powerful classroom instruction and successfully work with students from culturally diverse backgrounds. I share a qualitative investigation of participants’ experiences during a short-term study abroad program in Japan that explored contemporary disaster preparedness as a result of the Great East Japan Earthquake and Tsunami. The program sponsors, the Japanese Ministry of Foreign Affairs, hoped participants would develop an appreciation for the people and culture of Japan while they learned about disaster preparedness. I wondered if collecting curriculum items during a short-term study abroad program could help social studies pre-service teachers create—not just receive—historical domain knowledge? In Japan, participants collected items to use as featured resources around which they designed classroom activities for secondary students. Their activities demonstrated three levels of second-order historical domain knowledge and two elements of civic competence. This study suggests that pre-service teachers with no previous international experience may require explicit modeling and scaffolding to translate their short-term study abroad participation into dynamic learning. Another implication is that participants need strong support to consider the photographs they capture as artifacts of contemporary material culture.

Utilizing Generative AI for Instructional Design: Exploring Strengths, Weaknesses, Opportunities, and Threats

AbstractRecently, generative AI has been at the center of disruptive innovation in various settings, including educational sectors. This article investigates ChatGPT, which is one of the most prominent generative AI in the market, to explore its usefulness and potential for instructional design. Four researchers used a set of prompts to generate a course map for an online course that is aimed to teach the topic of makerspace and conducted SWOT analysis to identify strengths, weaknesses, opportunities, and threats of using generative AI for instructional design. The findings suggest that there is promise in using ChatGPT as an efficient and effective tool for creating course maps, yet it still requires the domain knowledge and instructional design expertise to warrant quality and reliability of the tool.

An intelligent BIM-enabled digital twin framework for real-time structural health monitoring using wireless IoT sensing, digital signal processing, and structural analysis

Structural health monitoring (SHM) of civil infrastructure is critically important due to its direct influence on public safety and economic activities. Exiting Building Information Modeling (BIM)-based SHM systems often use offline data processing techniques to analyze and visualize structural health data. Despite some of them adopting Internet of Things (IoT) to enable real-time sensor data collection, sensor data quality still remains uncertain due to a lack of sensor signal preprocessing in those existing systems. Additionally, the IoT-based SHM systems often disregard structural analysis domain knowledge, which is important for accurate and precise SHM. Therefore, there is still a need to improve existing systems and practices by enabling more efficient and reliable data collection and processing as well as providing more representative SHM data visualization in BIM. As such, this paper proposes an intelligent BIM-enabled digital twin (DT) framework that integrates wireless IoT sensing and communication, digital signal processing (DSP), and structural analysis domain knowledge. The proposed system (1) leverages IoT sensing and wireless communication to enable autonomous and real-time SHM sensor data collection and transmission, (2) applies and compares multiple DSP techniques to preprocess the sensor data/signals, and (3) innovatively embraces structural analysis expertise into structural behavior visualization in BIM by performing sensor data interpolation for enabling the visualization of structural behaviors at different locations of a structural element/component. The proposed BIM-enabled DT framework was demonstrated and tested for monitoring and visualizing the structural deformations of critical structural components using a prototyped structural frame subject to bending forces. The developed framework could be used and extended for any structural elements (such as beams, columns, trusses, slabs, arches, bracings, walls, footings, foundations, and girders, among others) and could be applied to any kind of structure. Experimental results showed that the proposed framework could effectively monitor and intuitively visualize the structural deformations under different load configurations with a high DT updating frequency of 5 Hz. The innovation of this study is reflected by integrating structural analysis expertise with IoT-enabling sensing data analytics in order to improve the representativeness of real-time structural behavior visualization in BIM and to advance the DT-based SHM systems in a faster and more adaptive direction. Ultimately, this paper contributes to the body of knowledge by developing a generic and easily extendable BIM-enabled DT framework for SHM with high sensor data quality and improved visualization to advance the existing practices of BIM-based SHM for civil infrastructure asset management.

Multiscale and multidisciplinary data-driven reservoir characterization of a fractured carbonate field in Kurdistan

Abstract The combination of traditional subsurface interpretation techniques with advanced data analytics is a key stepping stone for better predicting reservoir quality, especially in heterogeneous and complex geological systems. The Peshkabir oil and gas field, located in the north of the Kurdistan Region of Iraq and within the Tawke Production Sharing Contract, is one such heterogeneous system. Well oil rates vary significantly across the field and cannot be simply correlated to fracture densities measured at the wells. Understanding which fractures matter and what influences reservoir deliverability is a question of major importance for maximizing oil production. The carbonate reservoirs include karstified vuggy zones and hydrothermal dolostones, in addition to an extensively developed fractured network. This paper presents a geological conceptual model for the Peshkabir field, and an application of Python based data science techniques to identify key predictors of reservoir deliverability from drilling, logging and production data. We demonstrate that the major advantage of the application of advanced data analytics is that it can enable the recognition of patterns and associations in a complex, high-dimensional parameter environment whereas traditional interpretation methods typically only allow for the comparison of two or three parameters at a time. This method allows the integration of dynamic and static data effectively and empowers the interpreter to incorporate all the available insights which, coupled with domain knowledge, allows for data-driven decision-making.

Intelligent adaptive lighting algorithm: Integrating reinforcement learning and fuzzy logic for personalized interior lighting

The lighting requirements are subjective and one light setting cannot work for all. However, there is little work on developing smart lighting algorithms that can adapt to user preferences. To address this gap, this paper uses fuzzy logic and reinforcement learning to develop an adaptive lighting algorithm. In particular, we develop a baseline fuzzy inference system (FIS) using the domain knowledge, generating light recommendation based on a set of intuitive rules. These rules, derived from existing literature, are based on environmental conditions i.e. daily glare index, and user information including age, activity, and chronotype. Through a feedback mechanism, the user interacts with the algorithm, correcting the algorithm output to their preferences. We interpret these corrections as rewards to a Q-learning algorithm, which tunes the FIS parameters online to match the user preferences. The Q-learning is a model-free learning algorithm that learns to act optimally by interacting with the user and the rewards it receives. This allows the proposed algorithm to work in a model-free manner, effectively handling the uncertainties that might arise from the individualistic preferences of users. To the authors’ best knowledge, this algorithm is pioneering work in designing intelligent algorithms for personalized lighting control, featuring several elements of novelty, including the number of environmental and user-related inputs, the continuous control of light intensity as opposed to common on/off control, and the ability to learn user preferences. The algorithm is implemented in a real aircraft cabin and is evaluated in an extensive user study. The implementation results demonstrate that the developed algorithm possesses the capability to learn user preferences while successfully adapting to a wide range of environmental conditions and user characteristics. This underscores its viability as a potent solution for intelligent light management, featuring advanced learning capabilities.