{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T17:37:08Z","timestamp":1790185028242,"version":"4.1.0"},"reference-count":42,"publisher":"MDPI AG","issue":"19","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Samruk-Kazyna JSC"}],"content-domain":{"domain":["www.mdpi.com"],"crossmark-restriction":true},"short-container-title":["Sensors"],"abstract":"<jats:p>Early train detection is vital for ensuring the safety of railway personnel, particularly in remote locations where fixed signaling infrastructure is unavailable. Unlike many existing solutions that rely on high-power, high-cost sensors and compute platforms, this work presents a lightweight, low-cost, and portable framework designed to run entirely on resource-constrained microcontrollers with just kilobytes of Random Access Memory (RAM). The proposed system uses vibration data from low-cost accelerometers and employs a simple yet effective Linear Regression (LR) model for almost real-time prediction of train arrival times. To ensure feasibility on low-end hardware, a parallel-processing framework is introduced, enabling continuous data collection, Machine Learning (ML) inference, and wireless communication with strict timing and energy constraints. The decision-making process, including data preprocessing and ML prediction, completes in under 10 ms, and alerts are transmitted via LoRa, enabling kilometer-range communication. Field tests on active railway lines confirm that the system detects approaching trains 15 s in advance with no false negatives and a small number of explainable false positives. Power characterization demonstrates that the system can operate for more than 6 days on a 10 Ah battery, with potential for months of operation using wake-on-vibration modes.<\/jats:p>","DOI":"10.3390\/s25196045","type":"journal-article","created":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T09:37:21Z","timestamp":1759311441000},"page":"6045","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Cost-Effective Train Presence Detection and Alerting Using Resource-Constrained Devices"],"prefix":"10.3390","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6682-9071","authenticated-orcid":false,"given":"Dimitrios","family":"Zorbas","sequence":"first","affiliation":[{"name":"School of Engineering & Digital Sciences, Nazarbayev University, Astana 010000, Kazakhstan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-3583-6422","authenticated-orcid":false,"given":"Maral","family":"Baizhuminova","sequence":"additional","affiliation":[{"name":"School of Engineering & Digital Sciences, Nazarbayev University, Astana 010000, Kazakhstan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4542-2691","authenticated-orcid":false,"given":"Dnislam","family":"Urazayev","sequence":"additional","affiliation":[{"name":"School of Engineering & Digital Sciences, Nazarbayev University, Astana 010000, Kazakhstan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0600-5576","authenticated-orcid":false,"given":"Aida","family":"Eduard","sequence":"additional","affiliation":[{"name":"School of Engineering & Digital Sciences, Nazarbayev University, Astana 010000, Kazakhstan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9610-9830","authenticated-orcid":false,"given":"Gulim","family":"Nurgazina","sequence":"additional","affiliation":[{"name":"School of Engineering & Digital Sciences, Nazarbayev University, Astana 010000, Kazakhstan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4323-3023","authenticated-orcid":false,"given":"Nursultan","family":"Atymtay","sequence":"additional","affiliation":[{"name":"School of Engineering & Digital Sciences, Nazarbayev University, Astana 010000, Kazakhstan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7202-404X","authenticated-orcid":false,"given":"Marko","family":"Ristin","sequence":"additional","affiliation":[{"name":"School of Engineering & Digital Sciences, Nazarbayev University, Astana 010000, Kazakhstan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,10,1]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Berlin, E., and Van Laerhoven, K. (2012, January 11\u201314). Trainspotting: Combining Fast Features to Enable Detection on Resource-Constrained Sensing Devices. Proceedings of the 9th International Conference on Networked Sensing (INSS), Antwerp, Belgium.","DOI":"10.1109\/INSS.2012.6240520"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Bonde, A., Pan, S., Mirshekari, M., Ruiz, C., Noh, H.Y., and Zhang, P. (2020, January 21\u201324). OAC: Overlapping office activity classification through IoT-sensed structural vibration. Proceedings of the 2020 IEEE\/ACM Fifth International Conference on Internet-of-Things Design and Implementation (IoTDI), Sydney, Australia.","DOI":"10.1109\/IoTDI49375.2020.00028"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Yan, F., Gu, Y., and Sun, Y. (2025). Deep Learning-Based Train Obstacle Detection Technology: Application and Testing in Metros. Electronics, 14.","DOI":"10.3390\/electronics14071318"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"114638","DOI":"10.1109\/ACCESS.2023.3309814","article-title":"A Review on Deep Learning Techniques for Railway Infrastructure Monitoring","volume":"11","author":"Griseta","year":"2023","journal-title":"IEEE Access"},{"key":"ref_5","unstructured":"Hellman, A.D., Poirier, P.J., and John, A. (2019). Analysis of Non-Track-Circuit Highway-Rail Grade Crossing Train Detection Technologies, United States. Federal Railroad Administration. Office of Research, Development & Technology. Technical, Report."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"111728","DOI":"10.1016\/j.sna.2019.111728","article-title":"A Review of Railway Infrastructure Monitoring Using Fiber Optic Sensors","volume":"303","author":"Du","year":"2020","journal-title":"Sens. Actuators A Phys."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Zhang, M., Liu, Z., Shen, C., Wu, J., and Zhao, A. (2022). A Review of Radio Frequency Identification Sensing Systems for Structural Health Monitoring. Materials, 15.","DOI":"10.3390\/ma15217851"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Dias, S., Sousa, P.J.S.C.P., Nunes, J., Afonso, F., Viriato, N., Tavares, P.J., and Moreira, P.M.G.P. (2025). Deterministic Light Detection and Ranging (LiDAR)-Based Obstacle Detection in Railways Using Data Fusion. Appl. Sci., 15.","DOI":"10.3390\/app15063118"},{"key":"ref_9","unstructured":"Z\u00f6llner Signal GmbH (2025, August 29). Warning Systems for Track Work. Available online: https:\/\/www.zoellner.de\/en\/rail\/solutions\/warning-systems-for-track-work."},{"key":"ref_10","unstructured":"RailWorks Corporation (2025, August 29). ZoneGuard Roadway Worker Protection System. Available online: https:\/\/www.milleringenuity.com\/roadway-worker-protection\/."},{"key":"ref_11","unstructured":"Protran Technology (2025, August 29). Portable Train Detector Kit. Available online: https:\/\/www.protransafety.com\/rail\/safety\/roadway-worker\/portable-train-detector-kit."},{"key":"ref_12","unstructured":"Schweizer Electronic, AG (2025, August 29). Minimel Lynx ATWS: Automatic Radio Warning System. Available online: https:\/\/schweizer-electronic.com\/en\/warning-systems\/temporary-warning-systems\/minimel-lynx-atws-automatic-radio-warning-system."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Serna, A.A., Yu, X., and Saniie, J. (June, January 30). AI-Based Security Surveillance and Hazard Detection for Train Platform Safety. Proceedings of the 2024 IEEE International Conference on Electro Information Technology (eIT), Eau Claire, WI, USA.","DOI":"10.1109\/eIT60633.2024.10609931"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"106594","DOI":"10.1016\/j.aap.2022.106594","article-title":"Artificial Intelligence-Aided Railroad Trespassing Detection and Data Analytics: Methodology and a Case Study","volume":"168","author":"Zhang","year":"2022","journal-title":"Accid. Anal. Prev."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"6427","DOI":"10.1109\/TITS.2024.3412170","article-title":"Railway Intrusion Detection Based on Machine Vision: A Survey, Challenges, and Perspectives","volume":"25","author":"Cao","year":"2024","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"15515","DOI":"10.1109\/JSEN.2020.3031861","article-title":"Artificial Intelligence-based Surveillance System for Railway Crossing Traffic","volume":"21","author":"Sikora","year":"2020","journal-title":"IEEE Sens. J."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"El-Alami, A., Nadir, Y., and Mansouri, K. (2024, January 28\u201329). A Hybrid Vehicle Tracking System for Low-power Embedded Devices. Proceedings of the 2024 International Conference on Circuit, Systems and Communication (ICCSC), Fes, Morocco.","DOI":"10.1109\/ICCSC62074.2024.10617125"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"411","DOI":"10.1109\/JETCAS.2019.2911899","article-title":"Low-power Computer Vision: Status, Challenges, and Opportunities","volume":"9","author":"Alyamkin","year":"2019","journal-title":"IEEE J. Emerg. Sel. Top. Circuits Syst."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Lin, C., Sun, G., Wu, D., and Xie, C. (2023). Vehicle Detection and Tracking with Roadside LiDAR Using Improved ResNet18 and the Hungarian Algorithm. Sensors, 23.","DOI":"10.3390\/s23198143"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Jin, X., Yang, H., He, X., Liu, G., Yan, Z., and Wang, Q. (2023). Robust LiDAR-Based Vehicle Detection for On-Road Autonomous Driving. Remote Sens., 15.","DOI":"10.3390\/rs15123160"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"13442","DOI":"10.1109\/JSEN.2021.3066714","article-title":"A Camera and LiDAR Data Fusion Method for Railway Object Detection","volume":"21","author":"Zhangyu","year":"2021","journal-title":"IEEE Sens. J."},{"key":"ref_22","unstructured":"Sato, K., Ishida, S., Kajimura, J., Uchino, M., Tagashira, S., and Fukuda, A. (2018, January 8\u201310). Initial Evaluation of Acoustic Train Detection System. Proceedings of the Intelligent Transportation Systems Asia\u2013Pacific Forum Fukuoka, Fukuoka, Japan."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1051\/aacus\/2021011","article-title":"Direction of Arrival Estimation of Partial Sound Sources of Vehicles with a Two-Microphone Array","volume":"5","author":"Rocha","year":"2021","journal-title":"Acta Acust."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Dumont, V., Tribaldos, V.R., Ajo-Franklin, J., and Wu, K. (2020, January 10\u201313). Deep Learning for Surface Wave Identification in Distributed Acoustic Sensing Data. Proceedings of the International Conference on Big Data, Atlanta, GA, USA.","DOI":"10.1109\/BigData50022.2020.9378084"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"106769","DOI":"10.1016\/j.ymssp.2020.106769","article-title":"An Analysis of Railway Track Behaviour Based on Distributed Optical Fibre Acoustic Sensing","volume":"142","author":"Milne","year":"2020","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"tdac048","DOI":"10.1093\/tse\/tdac048","article-title":"Condition Monitoring and Fault Diagnosis Strategy of Railway Point Machines Using Vibration Signals","volume":"5","author":"Sun","year":"2023","journal-title":"Transp. Saf. Environ."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Meyer, A. (2022). Vibration Fault Diagnosis in Wind Turbines Based on Automated Feature Learning. Energies, 15.","DOI":"10.3390\/en15041514"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"101008","DOI":"10.1016\/j.iot.2023.101008","article-title":"Real-Time Classification of Cattle Behavior Using Wireless Sensor Networks","volume":"25","author":"Navarro","year":"2024","journal-title":"Internet Things"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"89845","DOI":"10.1109\/ACCESS.2024.3417377","article-title":"Vibration Signal Based Abnormal Gait Detection and Recognition","volume":"12","author":"Chen","year":"2024","journal-title":"IEEE Access"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"040029","DOI":"10.1063\/1.5042999","article-title":"Train Arrival Warning System at Railroad Crossing Using Accelerometer Sensor and Neural Network","volume":"1977","author":"Ardiansyah","year":"2018","journal-title":"AIP Conf. Proc."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"1025","DOI":"10.1007\/s10586-019-02971-9","article-title":"Image Classification on IoT Edge Devices: Profiling and Modeling","volume":"23","author":"Petrini","year":"2020","journal-title":"Clust. Comput."},{"key":"ref_32","unstructured":"Elliott, D., Otero, C.E., Wyatt, S., and Martino, E. (2021). Tiny transformers for environmental sound classification at the edge. arXiv."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Der Yang, M., Tseng, H.H., Hsu, Y.C., and Tseng, W.C. (2020, January 10\u201313). Real-Time Crop Classification Using Edge Computing and Deep Learning. Proceedings of the 17th Annual Consumer Communications & Networking Conference (CCNC), Las Vegas, NV, USA.","DOI":"10.1109\/CCNC46108.2020.9045498"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"9000970","DOI":"10.1155\/2021\/9000970","article-title":"Attenuation Law of Train-Induced Vibration Response of Subgrade in Beijing\u2013Harbin Railway","volume":"2021","author":"Wang","year":"2021","journal-title":"Shock Vib."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Hsu, W.L., Chen, W.B., and Hsieh, M.T. (2024). Comparative Analysis of Methods for Predicting Train-Induced Vibrations. J. Low Freq. Noise, Vib. Act. Control, 14613484241298737.","DOI":"10.1177\/14613484241298737"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Zhang, J., Zhang, Y., Song, B., Zhang, Y., and Sun, J. (2023, January 20\u201323). Vibration Detection Based on Multi-Sensor Information Fusion for Industrial Internet of Things. Proceedings of the 97th Vehicular Technology Conference (VTC), Florence, Italy.","DOI":"10.1109\/VTC2023-Spring57618.2023.10200923"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"618","DOI":"10.1109\/JRFID.2024.3411814","article-title":"An Innovative Multi-Port LoRa-Based Wireless Node for Railway Signaling and Positioning","volume":"8","author":"Paolini","year":"2024","journal-title":"IEEE J. Radio Freq. Identif."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Suharjono, A., Mukhlisin, M., Wardihani, E.D., Muhlasah Novitasari, M., Khusna, E.M., Feryando, D.A., Adi, W.T., Pramono, S., Apriantoro, R., and Mujahidin, I. (2023, January 13\u201315). Performance Evaluation of LoRa 915 MHz for IoT Communication System on Indonesian Railway Tracks with Environmental Factor Propagation Analysis. Proceedings of the 2nd International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT), Bali, Indonesia.","DOI":"10.1109\/IAICT59002.2023.10205909"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"26633","DOI":"10.1109\/ACCESS.2021.3057602","article-title":"An Experimental Study on the Use of LoRa Technology in Vehicle Communication","volume":"9","author":"Torres","year":"2021","journal-title":"IEEE Access"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"10283","DOI":"10.1109\/JIOT.2021.3121778","article-title":"Urban Vehicle Localization in Public LoRaWan Network","volume":"9","author":"Li","year":"2022","journal-title":"IEEE Internet Things J."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"101062","DOI":"10.1016\/j.iot.2024.101062","article-title":"Ad-hoc Train-Arrival Notification System for Railway Safety in Remote Areas","volume":"25","author":"Eduard","year":"2024","journal-title":"Internet Things"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Magzym, Y., Eduard, A., Urazayev, D., Fafoutis, X., and Zorbas, D. (2023, January 4\u20137). Synchronized ESP-NOW for Improved Energy Efficiency. Proceedings of the IEEE International Black Sea Conference on Communications and Networking (BlackSeaCom), Istanbul, Turkey.","DOI":"10.1109\/BlackSeaCom58138.2023.10299761"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/25\/19\/6045\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T09:43:24Z","timestamp":1759311804000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/25\/19\/6045"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,1]]},"references-count":42,"journal-issue":{"issue":"19","published-online":{"date-parts":[[2025,10]]}},"alternative-id":["s25196045"],"URL":"https:\/\/doi.org\/10.3390\/s25196045","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,1]]}}}