Language-Guided Cross-Subject Wearable Activity Recognition with Self-Supervised Transfer, Selective Prediction, and Edge Coaching Explanations
Keywords:
Wearable Activity Recognition, Cross-Subject Transfer, Self-Supervised Learning, Language-Guided Sensor Selection, Selective Prediction, Openpack, Edge InferenceAbstract
Cross-subject wearable activity recognition often fails when a model trained on one person encounters another person's motion range, pace, or sensor placement. This paper evaluates a compact language-guided transfer pipeline on two complete participant archives from the OpenPack v1.1.0 Zenodo record. Four arm and wrist inertial sensors and two wrist physiological devices produced 184 one-second statistics; 4,072 nonoverlapping five-second sequences represented ten packaging operations. The evaluation reverses source and target participants. Source sessions S01–S03 train the models, S04 selects models and calibration parameters, and S05 provides an internal test. Target sessions S01–S02 form a label-blind correlation-alignment pool after operation-window filtering, while S03–S05 remain an external cross-subject test. The method combines a 20% masked linear reconstruction objective, a transparent TF-IDF operation-to-sensor gate, target-to-source CORAL, BiGRU and compact attention branches, temperature scaling, and confidence-based abstention. The LG-SSL-CORAL ensemble reached external macro-F1 scores of 0.490 and 0.524 in the two directions, compared with 0.450 and 0.409 for BiGRU. Box-block paired bootstrap gains were 0.040 (95% CI 0.012–0.068) and 0.115 (0.089–0.145). Extra Trees remained a strong comparator with mean macro-F1 0.519 versus 0.507 for the proposed ensemble. Masked reconstruction improved the forward Conformer-lite result from 0.385 to 0.443, whereas CORAL and source-only temperature scaling were direction-sensitive. At 50% coverage, selective accuracy rose to 0.669 and 0.677, but a source-validation 10% risk rule did not transfer to the target subject. The language branch required 55.6 KiB of FP32 weights and 1.13 ms per sequence in a TensorFlow.js host-CPU proxy. The results establish both the benefit and the limits of language-guided sensor selection, covariance transfer, and confidence rejection in a strict two-participant cross-subject setting.
References
1] F. J. Ordóñez and D. Roggen, “Deep convolutional and LSTM recurrent neural networks for multimodal wearable activity recognition,” Sensors, vol. 16, no. 1, Art. no. 115, 2016, doi: 10.3390/s16010115.
[2] N. Yoshimura, J. Morales, T. Maekawa, and T. Hara, “OpenPack: A large-scale dataset for recognizing packaging works in IoT-enabled logistic environments,” in Proc. 2024 IEEE Int. Conf. Pervasive Computing and Communications (PerCom), Biarritz, France, 2024, pp. 90–97, doi: 10.1109/PerCom59722.2024.10494448.
[3] T. Maekawa, N. Yoshimura, J. Morales, and T. Hara, “Brief introduction of the OpenPack dataset and lessons learned from organizing activity recognition challenge using the dataset,” in Companion Proc. 2024 ACM Int. Joint Conf. Pervasive and Ubiquitous Computing, 2024, pp. 116–120, doi: 10.1145/3675094.3677597.
[4] J. Morales, N. Yoshimura, Q. Xia, A. Wada, Y. Namioka, and T. Maekawa, “MGA-Net+: Acceleration-based packaging work recognition using motif-guided attention networks,” Pervasive Mobile Comput., vol. 88, Art. no. 101735, 2023, doi: 10.1016/j.pmcj.2022.101735.
[5] J. Zhang, "From General Human Activity Recognition to Volleyball-Oriented Wearable Transfer Learning: Cross-Dataset Evidence from UCI HAR and WISDM for Domain Adaptation and Edge Deployment," J. Technol. Informatics Eng., vol. 4, no. 1, pp. 263-283, Apr. 2025, doi: 10.51903/jtie.v4i1.524.
[6] Q. Wu, G. Mi, and D. Wood, "Calibration-Light Subject-Independent Motor Imagery BCI via Self-Supervised Pretraining and Conformer," J. Technol. Informatics Eng., vol. 4, no. 1, pp. 239-262, Apr. 2025, doi: 10.51903/jtie.v5i1.493.
[7] Z. S. Zhong, X. Pan, and Q. Lei, "Bridging Domains with Approximately Shared Features," in Proc. 28th Int. Conf. Artificial Intelligence and Statistics (AISTATS), PMLR, vol. 258, pp. 559-567, 2025.
[8] E. Eldele, M. Ragab, Z. Chen, M. Wu, C. K. Kwoh, X. Li, and C. Guan, “Time-series representation learning via temporal and contextual contrasting,” in Proc. IJCAI, 2021, pp. 2352–2359, doi: 10.24963/ijcai.2021/324.
[9] S. Deldari, H. Xue, A. Saeed, D. V. Smith, and F. D. Salim, “COCOA: Cross modality contrastive learning for sensor data,” Proc. ACM Interact. Mob. Wearable Ubiquitous Technol., vol. 6, no. 3, Art. no. 108, 2022, doi: 10.1145/3550316.
[10] H. Yuan et al., “Self-supervised learning for human activity recognition using 700,000 person-days of wearable data,” npj Digit. Med., vol. 7, Art. no. 91, 2024, doi: 10.1038/s41746-024-01062-3.
[11] H. Haresamudram, I. Essa, and T. Plötz, “Assessing the state of self-supervised human activity recognition using wearables,” Proc. ACM Interact. Mob. Wearable Ubiquitous Technol., vol. 6, no. 3, Art. no. 116, 2022, doi: 10.1145/3550299.
[12] Z. Hong et al., “CrossHAR: Generalizing cross-dataset human activity recognition via hierarchical self-supervised pretraining,” Proc. ACM Interact. Mob. Wearable Ubiquitous Technol., vol. 8, no. 2, Art. no. 64, 2024, doi: 10.1145/3659597.
[13] Q. Xia, T. Maekawa, J. Morales, T. Hara, H. Oshima, M. Fukuda, and Y. Namioka, “Preliminary investigation of SSL for complex work activity recognition in industrial domain via MoIL,” in Proc. 2024 IEEE PerCom Workshops, 2024, pp. 465–468, doi: 10.1109/PerComWorkshops59983.2024.10503195.
[14] G. Mi, T. Ye, and D. Wood, "A Lightweight Medical Foundation Model for Cross-Modal Multi-Task Pretraining and Parameter-Efficient Few-Shot Transfer on MedMNIST," J. Technol. Informatics Eng., vol. 4, no. 3, pp. 572-589, Dec. 2025, doi: 10.51903/jtie.v4i3.492.
[15] S. He, C. Li, and H. Rao, "Few-Shot Cold-Start Workload Forecasting for New AI Inference Tenants with Time-Series Foundation Models," J. Technol. Informatics Eng., vol. 4, no. 1, pp. 306-324, Apr. 2025, doi: 10.51903/jtie.v4i1.546.
[16] Q. Xin, "Self-Supervised Log Anomaly Detection with LogBERT-Style Transformers: Full Empirical Evaluation on a Reproducible SynHDFS Benchmark," J. Electr. Eng. Comput. Sci., vol. 11, no. 1, pp. 23-35, 2026, doi: 10.54732/jeecs.v11i1.3.
[17] S. Miao and L. Chen, “GOAT: A generalized cross-dataset activity recognition framework with natural language supervision,” Proc. ACM Interact. Mob. Wearable Ubiquitous Technol., vol. 8, no. 4, Art. no. 184, 2024, doi: 10.1145/3699736.
[18] Z. Leng, A. Bhattacharjee, H. Rajasekhar, L. Zhang, E. Bruda, H. Kwon, and T. Plötz, “IMUGPT 2.0: Language-based cross modality transfer for sensor-based human activity recognition,” Proc. ACM Interact. Mob. Wearable Ubiquitous Technol., vol. 8, no. 3, Art. no. 112, 2024, doi: 10.1145/3678545.
[19] H. Yan, H. Tan, Y. Ding, P. Zhou, V. Namboodiri, and Y. Yang, “Large language model-guided semantic alignment for human activity recognition,” arXiv:2410.00003v2, Oct. 2024, doi: 10.48550/arXiv.2410.00003.
[20] C. Wang et al., “UbiPhysio: Support daily functioning, fitness, and rehabilitation with action understanding and feedback in natural language,” Proc. ACM Interact. Mob. Wearable Ubiquitous Technol., vol. 8, no. 1, Art. no. 20, 2024, doi: 10.1145/3643552.
[21] W. Chen, J. Cheng, L. Wang, W. Zhao, and W. Matusik, “Sensor2Text: Enabling natural language interactions for daily activity tracking using wearable sensors,” Proc. ACM Interact. Mob. Wearable Ubiquitous Technol., vol. 8, no. 4, Art. no. 192, 2024, doi: 10.1145/3699747.
[22] Y. Li and S. Lu, "Language-Guided Feature Selection for DDoS and Intrusion Detection on CICIDS2017," J. Technol. Informatics Eng., vol. 4, no. 1, pp. 284-305, Apr. 2025, doi: 10.51903/jtie.v4i1.531.
[23] Q. Wu, S. Meng, and J. Zhao, "Text-Grounded LLM-Assisted Design Rationale Interfaces: Turning Advertising Layout Metadata into Explainable UI/UX Decision Cards," Int. J. Graph. Des., vol. 3, no. 1, pp. 216-240, May 2025, doi: 10.51903/ijgd.v3i1.3713.
[24] H. Xu, Y. Chen, and A. Med, "Automatic Detection and Explanation of Dark Patterns from Interface Microcopy: Empirical Comparison of BERT-Style Encoders, RoBERTa-Style Encoders, and LLM-Style Decoders on the ec-darkpattern Dataset," J. Technol. Informatics Eng., vol. 4, no. 3, pp. 590-612, Dec. 2025, doi: 10.51903/jtie.v4i3.491.
[25] Y. Li, S. Lu, and L. Zhao, "LLM-as-Design-Critic: Aligning AI-Generated UI Feedback with Human Graphic Design Judgment," Int. J. Graph. Des., vol. 3, no. 1, pp. 196-215, May 2025, doi: 10.51903/ijgd.v3i1.3661.
[26] C. Guo, G. Pleiss, Y. Sun, and K. Q. Weinberger, “On calibration of modern neural networks,” in Proc. 34th Int. Conf. Machine Learning, vol. 70, 2017, pp. 1321–1330.
[27] Y. Geifman and R. El-Yaniv, “SelectiveNet: A deep neural network with an integrated reject option,” in Proc. 36th Int. Conf. Machine Learning, vol. 97, 2019, pp. 2151–2159.
[28] Q. Xin, "Uncertainty-Aware Late Fusion for 3D Perception (Confidence Calibration + Fusion Rule Learning)," J. Technol. Informatics Eng., vol. 4, no. 1, pp. 215-238, Feb. 2025, doi: 10.51903/jtie.v4i1.485.
[29] Z. S. Zhong, J. Chen, E. Zhong, and X. Sun, "Evidence-Calibrated RAG for Unanswerable Question Answering: Retrieval Coverage, Abstention Calibration, and Hallucination-Proxy Analysis on SQuAD 2.0," J. Technol. Informatics Eng., vol. 4, no. 2, pp. 502-520, Aug. 2025, doi: 10.51903/jtie.v4i2.536.
[30] J. Jin, "Calibrated Resume-Job Matching for Trustworthy LLM-Assisted Recruiter Screening: Pairwise Matching, Probability Calibration, and Selective Refusal on Two Public Recruitment Datasets," J. Technol. Informatics Eng., vol. 4, no. 3, pp. 625-648, Dec. 2025, doi: 10.51903/jtie.v4i3.529.
[31] Y. Chen, Y. Zhang, D. Chau, and M. Sherman, "Credit Card Default Risk Tiering with Probability Calibration and Uncertainty-Driven Rejection: A Reproducible Study on the UCI Credit Card Clients Dataset," J. Adv. Comput. Syst., vol. 3, no. 4, pp. 31-47, Apr. 2023, doi: 10.69987/JACS.2023.30403.
[32] J. Jin, T. Huang, and S. Lu, "A Model-Risk-Friendly Probability of Default Workflow: Calibration, Distribution-Free Uncertainty Quantification, and SHAP Explanations on the UCI Credit Card Default Dataset," J. Adv. Comput. Syst., vol. 4, no. 6, pp. 74-85, Jun. 2024, doi: 10.69987/JACS.2024.40606.
[33] S. Chen, S. He, and E. Sun, "Risk-Bounded GPU Resource Oversubscription via Conformal Demand Envelopes in Production AI Clusters," J. Adv. Comput. Syst., vol. 4, no. 5, pp. 119-134, May 2024, doi: 10.69987/JACS.2024.40509.
[34] Q. Xin, "Log Anomaly Detection with Conformal Alert Control and Evidence-Grounded Incident Ticket Generation," AVITEC, vol. 8, no. 2, May 2026, doi: 10.28989/avitec.v8i2.3974.
[35] Y. Zhou, H. Zhao, Y. Huang, T. Riedel, M. Hefenbrock, and M. Beigl, “TinyHAR: A lightweight deep learning model designed for human activity recognition,” in Proc. ACM ISWC, 2022, pp. 89–93, doi: 10.1145/3544794.3558467.
[36] D. Smilkov et al., “TensorFlow.js: Machine learning for the web and beyond,” in Proc. 2nd MLSys Conf., 2019, pp. 309–321.
[37] T. Kautz, B. H. Groh, J. Hannink, U. Jensen, H. Strubberg, and B. M. Eskofier, “Activity recognition in beach volleyball using a deep convolutional neural network: Leveraging the potential of deep learning in sports,” Data Min. Knowl. Discov., vol. 31, no. 6, pp. 1678–1705, 2017, doi: 10.1007/s10618-017-0495-0.
[38] Y. Wang, Y. Zhao, R. H. M. Chan, and W. J. Li, “Volleyball skill assessment using a single wearable micro inertial measurement unit at wrist,” IEEE Access, vol. 6, pp. 13758–13765, 2018, doi: 10.1109/ACCESS.2018.2792220.
[39] Z. Wen, R. Zhang, and C. Wang, "Optimization of Bi-Directional Gated Loop Cell Based on Multi-Head Attention Mechanism for SSD Health State Classification Model," in Proc. 2025 6th Int. Conf. Electronic Communication and Artificial Intelligence (ICECAI), Chengdu, China, 2025, doi: 10.1109/ICECAI66283.2025.11171441.
[40] C. Wang, Z. Wen, R. Zhang, P. Xu, and Y. Jiang, "GPU Memory Requirement Prediction for Deep Learning Task Based on Bidirectional Gated Recurrent Unit Optimization Transformer," in Proc. 2025 5th Int. Conf. Artificial Intelligence, Virtual Reality and Visualization (AIVRV), Chengdu, China, pp. 31-35, 2025, doi: 10.1109/AIVRV67401.2025.11350369.
[41] B. Zhou, H. Wang, and X. Chang, "Distilling VMAF into an Edge-Deployable Quality Predictor: A Pilot Shot-Level Proxy with LLM-Ready Quality Tokens," J. Technol. Informatics Eng., vol. 4, no. 2, pp. 447-463, Aug. 2025, doi: 10.51903/jtie.v4i2.522.
[42] H. Wang, Y. Ren, and X. Chang, "Layout-Aware Progressive PDF Rendering: AI Prioritization of PDF Slices to Reduce Time-to-Functional-First-Frame on FUNSD," J. Technol. Informatics Eng., vol. 4, no. 2, pp. 425-446, Aug. 2025, doi: 10.51903/jtie.v4i2.523.
[43] Q. Xin, Z. Xu, L. Guo, F. Zhao, and B. Wu, "IoT Traffic Classification and Anomaly Detection Method Based on Deep Autoencoders," Appl. Comput. Eng., vol. 69, pp. 64-70, 2024, doi: 10.54254/2755-2721/69/20241511.
[44] Q. Xin, "LiDAR-Camera Object-Level Fusion for Multi-Target Tracking Using JPDA and EKF: A Reproducible Empirical Study on a PandaSet-Parameterised Five-Sequence Dataset," J. Technol. Informatics Eng., vol. 5, no. 1, pp. 54-76, Apr. 2026, doi: 10.51903/jtie.v5i1.486.
[45] S. Lu and D. Zhou, "TinyLLM-Assisted Intrusion Detection for Real-Time IoT Networks," J. Adv. Comput. Syst., vol. 4, no. 8, pp. 72-87, Aug. 2024, doi: 10.69987/JACS.2024.40809.
[46] J. Jin, "Evidence-Chain Reliable RAG: Hallucination Detection, Source Attribution, and Deterministic Provenance Explanations," J. Technol. Informatics Eng., vol. 4, no. 2, pp. 520-533, Aug. 2025, doi: 10.51903/jtie.v4i2.535.
[47] B. Zhang, H. Rao, and D. Zhao, "Evidence-Grounded RAG for Cloud-Native DevOps: Hallucination-Resistant AIOps Question Answering over Private Operations Documents," J. Adv. Comput. Syst., vol. 4, no. 3, pp. 109-125, Mar. 2024, doi: 10.69987/JACS.2024.40308.
[48] G. Liu, C. Li, and E. Zhang, "OpsLLM for Cloud Incident Triage: Bilingual RAG-Based Root Cause Analysis and Alert Summarization for AI Infrastructure Operations," J. Adv. Comput. Syst., vol. 4, no. 4, pp. 97-111, Apr. 2024, doi: 10.69987/JACS.2024.40408.
[49] C. Li, J. Bai, and S. Wang, "Evidence-Chain Reliable RAG: Word-Level Hallucination Detection, Source Attribution, and Provenance Explanation for LLM Applications," J. Adv. Comput. Syst., vol. 4, no. 2, pp. 76-92, Feb. 2024, doi: 10.69987/JACS.2024.40207.
[50] J. Nie, G. Liu, C. Li, and T. Zou, "Evidence-Constrained Incident Visualization Cards for Distributed Cloud Logs: A UI/UX Framework for Turning Hadoop, OpenStack, and ZooKeeper Logs into Actionable SRE Design Interfaces," Int. J. Graph. Des., vol. 4, no. 1, pp. 179-185, Apr. 2026, doi: 10.51903/ijgd.v4i1.3703.
[51] W. Su, H. Rao, and E. Ma, "Privacy and Data-Integrity Risk Cards for LLM Agents: A UI/UX Design Framework for Secure Human Oversight under Prompt-Injection Attacks," Int. J. Graph. Des., vol. 4, no. 1, pp. 186-191, Apr. 2026, doi: 10.51903/ijgd.v4i1.3699.
[52] J. Jin, "LLM-Style Evidence Cards for Scientific Search Interfaces: A UI/UX Design Framework for Retrieval Transparency, Ranking Trust, and Visual Evidence Hierarchy," Int. J. Graph. Des., vol. 3, no. 2, pp. 397-414, Oct. 2025, doi: 10.51903/ijgd.v3i2.3698.
[53] B. Zhou, C. Li, and L. Liu, "Risk-Calibrated Patient-Facing AI Safety Cards: A UI/UX Design Framework for Rubric-Based Medical Risk Communication," Int. J. Graph. Des., vol. 3, no. 2, pp. 365-380, Oct. 2025, doi: 10.51903/ijgd.v3i2.3696.
[54] C. Li, B. Zhou, and K. Gao, "Risk-Calibrated Patient-Facing AI Safety Cards: A UI/UX Benchmark for Explainable Medical AI Response Interfaces," Int. J. Graph. Des., vol. 3, no. 2, pp. 381-394, Oct. 2025, doi: 10.51903/ijgd.v3i2.3709.
[55] Z. S. Zhong, Q. Wu, and G. Mi, "Uncertainty-Aware Medical Image Explanation Cards: LLM-Generated Visual Explanations for AI-Assisted Radiology Interfaces," Int. J. Graph. Des., vol. 3, no. 2, pp. 415-436, Oct. 2025, doi: 10.51903/ijgd.v3i2.3616.
[56] T. Ye, X. Chang, and E. Zhong, "Uncertainty-Aware Breast Ultrasound Explanation Cards: A Visual Communication Framework for Image-Based AI Diagnostic Support Using BreastMNIST_224," Int. J. Graph. Des., vol. 3, no. 2, pp. 365-380, Oct. 2025, doi: 10.51903/ijgd.v3i2.3701.
[57] Y. Zhang and H. Zhang, "Visualizing the Right Counseling Support: Evidence-Linked Recommendation Cards for Explainable Mental Health Intake Interfaces," Int. J. Graph. Des., vol. 3, no. 1, pp. 214-229, May 2025, doi: 10.51903/ijgd.v3i1.3722.
[58] B. Zhang, Y. Ren, and J. Zou, "LLM-Style Explainable E-Commerce Recommendation Cards: A UI/UX Design Framework for Trust-Calibrated Product Recommendation," Int. J. Graph. Des., vol. 3, no. 2, pp. 381-396, Oct. 2025, doi: 10.51903/ijgd.v3i2.3697.
[59] G. Liu, S. He, and H. Wong, "LLM-Compatible Visual Brief Cards for AI Infrastructure Capacity Dashboards: A UI/UX Framework for Turning Forecast Risk into Graphic Design Decisions," Int. J. Graph. Des., vol. 3, no. 1, pp. 196-213, May 2025, doi: 10.51903/ijgd.v3i1.3723.
[60] J. Mu, Y. Lu, and E. Hwang, "Structured Visual Brief Interfaces for Advertising Design: A UI/UX Framework for Turning Creative Intentions into Designer-Editable Graphic Design Cards," Int. J. Graph. Des., vol. 4, no. 1, pp. 192-208, Apr. 2026, doi: 10.51903/ijgd.v4i1.3702.
[61] Y. Chen and M. Li, "From Hand-Drawn Sketches to Interactive Web Prototypes: A Reproducible Vision-Language Approach with Structural and Visual Consistency Evaluation," J. Technol. Informatics Eng., vol. 4, no. 2, pp. 364-384, Aug. 2025, doi: 10.51903/jtie.v4i2.490.
[62] Q. Xin, "Auditable Automated Essay Scoring and Formative Feedback: A Rubric-Grounded Pipeline for Secondary and Higher Education," J. Appl. Artif. Intell. Educ., vol. 2, no. 1, pp. 1-19, Jul. 2026, doi: 10.66053/jaaie.v2i1.348.
[63] J. Zhang, "Adaptive User Interface Design for Volleyball Learning Apps: Empirical Evidence from Google Play Reviews and Mobile Screen Analysis," Int. J. Graph. Des., vol. 3, no. 1, pp. 175-195, May 2025, doi: 10.51903/ijgd.v3i1.3618.
[64] N. Yoshimura, J. Morales, and T. Maekawa, “OpenPack: Public multi-modal dataset for packaging work recognition in logistics domain,” Zenodo, ver. 1.1.0, Apr. 24, 2024, doi: 10.5281/zenodo.11059235.
[65] B. Sun and K. Saenko, “Deep CORAL: Correlation alignment for deep domain adaptation,” in Computer Vision–ECCV 2016 Workshops, 2016, pp. 443–450, doi: 10.1007/978-3-319-49409-8_35.
[66] X. Qin, Y. Chen, J. Wang, and C. Yu, “Cross-dataset activity recognition via adaptive spatial-temporal transfer learning,” Proc. ACM Interact. Mob. Wearable Ubiquitous Technol., vol. 3, no. 4, Art. no. 148, 2019, doi: 10.1145/3369818.
[67] S. He, X. Chang, and E. Sun, "Cross-Cloud Transfer Learning for AI Training Capacity Forecasting under Workload and Topology Distribution Shift," J. Adv. Comput. Syst., vol. 4, no. 1, pp. 100-120, Jan. 2024, doi: 10.69987/JACS.2024.40108.
[68] P. Geurts, D. Ernst, and L. Wehenkel, “Extremely randomized trees,” Mach. Learn., vol. 63, no. 1, pp. 3–42, 2006, doi: 10.1007/s10994-006-6226-1.
[69] K. Cho et al., “Learning phrase representations using RNN encoder–decoder for statistical machine translation,” in Proc. EMNLP, Doha, Qatar, 2014, pp. 1724–1734, doi: 10.3115/v1/D14-1179.
[70] A. Vaswani et al., “Attention is all you need,” in Advances in Neural Information Processing Systems 30, 2017, pp. 5998–6008.
[71] A. Gulati et al., “Conformer: Convolution-augmented Transformer for speech recognition,” in Proc. Interspeech, 2020, pp. 5036–5040, doi: 10.21437/Interspeech.2020-3015.
[72] Q. Xin, "Probabilistic Bike-Sharing Demand Forecasting under Changing Weather and Seasonal Regimes with Transformer-Based Models," Findings, Mar. 2026, doi: 10.32866/001c.157499.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Oliver Thompson, Rachel Lu, Sophia Garcia, Kevin Li (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
Creative Commons Attribution 4.0 International (CC BY 4.0).
This work is licensed under a 