[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125356-en":3,"doc-seo-125356-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},125356,962075114101,"Seraphina","https://ap-avatar.wpscdn.com/avatar/e000253a75eb197efd?x-image-process=image/resize,m_fixed,w_180,h_180&k=1780044092746381165",8,"Research & Report","Investigating lightweight and interpretable machine learning models for efficient and explainable stress detection - Research approach","Stress detection using machine learning is constrained by the difficulty of maintaining high accuracy with a reduced set of heart rate variability (HRV) statistical features. This study proposes lightweight, computationally efficient ML models for IoT deployment, combining feature selection and hyper-parameter tuning. Using the publicly available SWELL-KW dataset, k-NN and Decision Tree achieve competitive performance with minimal features, with k-NN reaching 99.3% accuracy using three selected features. Benchmarking on an 8 GB NVIDIA Jetson Orin Nano preserves 99.26% accuracy and completes training in 31 s, supported by local interpretable explanations.","TYPE Methods  \nPUBLISHED 13 August 2025  \nDOI 10.3389/fdgth.2025.1523381  \nEDITED BY  \nUwe Aickelin,  \nThe University of Melbourne, Australia  \nREVIEWED BY  \nSurender Redhu, Kongsberg Digital, Norway Sharda Tripathi,  \nBirla Institute of Technology and Science, India *CORRESPONDENCE  \nDebasish Ghose  \n [debasish.ghose@kristiania.no](debasish.ghose@kristiania.no)  \nRECEIVED 05 November 2024  \nACCEPTED 21 July 2025  \nPUBLISHED 13 August 2025  \nCITATION  \nGhose D, Chatterjee A, Balapuwaduge IAM, Lin Y and Dash SP (2025) Investigating lightweight and interpretable machine learning models for efficient and explainable stress detection.  \nFront. Digit. Health 7:1523381 .  \ndoi: 10.3389/fdgth.2025.1523381  \nCOPYRIGHT  \n© 2025 Ghose, Chatterjee, Balapuwaduge, Lin and Dash. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.  \nInvestigating lightweight and interpretable machine learning models for efficient and explainable stress detection  \nDebasish Ghose1*, Ayan Chatterjee2, Indika A. M. Balapuwaduge3, Yuan Lin1 and Soumya P. Dash4  \n1School of Economics, Innovation, and Technology, Kristiania University College, Bergen, Norway, 2Department of Digital Technology, NILU, Kjeller, Norway, 3Department of Information and Communication Technology, University of Agder (UiA), Grimstad, Norway, 4School of Electrical Sciences, Indian Institute of Technology Bhubaneswar, Khordha, Odisha, India  \nStress is a common human reaction to demanding circumstances, and prolonged and excessive stress can have detrimental effects on both mental and physical health. Heart rate variability (HRV) is widely used as a measure of stress due to its ability to capture variations in the time intervals between heartbeats. However, achieving high accuracy in stress detection through machine learning (ML), using a reduced set of statistical features extracted from HRV, remains a significant challenge. In this study, we aim to address these challenges by proposing lightweight ML models that can effectively detect stress using minimal HRV features and are computationally efficient enough for IoT deployment. We have developed ML models incorporating efficient feature selection techniques and hyper-parameter tuning. The publicly available SWELL-KW dataset has been utilized for evaluating the performance of our models. Our results demonstrate that lightweight models such as k-NN and Decision Tree can achieve competitive accuracy while ensuring lower computational demands, making them ideal for real-time applications. Promisingly, among the developed models, the k-nearest neighbors (k-NN) algorithm has emerged as the best-performing model, achieving an accuracy score of 99 . 3% using only three selected features. To confirm real-world deployability, we benchmarked the best model on an 8 GB NVIDIA Jetson Orin Nano edge device, where it retained 99. 26% accuracy and completed training in 31 s. Furthermore, our study has incorporated local interpretable model-agnostic explanations to provide comprehensive insights into the predictions made by the k-NN-based architecture.  \nKEYWORDS  \nstress detection, ML models, IoT device, explainable AI, health  \n1 Introduction  \nStress is our body’s response to pressure from challenging situations or life events. It can manifest as a feeling of being overwhelmed or under pressure. While some amount of stress can be beneficial, experiencing overwhelming stress over an extended period is often referred to as chronic or long-term stress, which requires attention. Chronic stress not only  \nFrontiers in Digital Health 01 [frontiersin.org](frontiersin.org)  \naff","cbCaiuVWllfLiBJC","https://ap.wps.com/l/cbCaiuVWllfLiBJC","pdf",2658900,1,19,"English","en",105,"# Introduction\n# Related Background and Challenges\n# Proposed Lightweight and Interpretable Models\n## Feature Selection and Hyper-parameter Tuning\n## Dataset Evaluation (SWELL-KW)\n## Real-world Benchmarking on Jetson Orin Nano\n## Local Interpretable Explanations","[{\"question\":\"Why is stress detection from HRV challenging for machine learning?\",\"answer\":\"High accuracy is difficult to achieve when restricting the model to a reduced set of HRV statistical features, which also increases computational constraints for real-time systems.\"},{\"question\":\"What models does the study propose for efficient and explainable stress detection?\",\"answer\":\"The study develops lightweight machine learning models using feature selection and hyper-parameter tuning, including k-NN and Decision Tree.\"},{\"question\":\"How well do the best model and the system-level deployment perform?\",\"answer\":\"k-NN achieves 99.3% accuracy using only three selected features, and on an 8 GB NVIDIA Jetson Orin Nano edge device it retains 99.26% accuracy while completing training in 31 seconds.\"}]","Investigating lightweight and interpretable machine learning models for efficient and explainable stress detection - Research approach | PDF",1785898388,48,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"investigating-lightweight-and-interpretable-machine-learning-models-for-efficient-and-explainable-stress-detection-research-approach","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/investigating-lightweight-and-interpretable-machine-learning-models-for-efficient-and-explainable-stress-detection-research-approach/125356/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why is stress detection from HRV challenging for machine learning?","Question",{"text":75,"@type":76},"High accuracy is difficult to achieve when restricting the model to a reduced set of HRV statistical features, which also increases computational constraints for real-time systems.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What models does the study propose for efficient and explainable stress detection?",{"text":80,"@type":76},"The study develops lightweight machine learning models using feature selection and hyper-parameter tuning, including k-NN and Decision Tree.",{"name":82,"@type":73,"acceptedAnswer":83},"How well do the best model and the system-level deployment perform?",{"text":84,"@type":76},"k-NN achieves 99.3% accuracy using only three selected features, and on an 8 GB NVIDIA Jetson Orin Nano edge device it retains 99.26% accuracy while completing training in 31 seconds.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},"General","general"]