臺灣博碩士論文加值系統

This paper presents a running assistance system that adjusts the runner's stride frequency based on the Beats Per Minute (BPM) of the music being listened to. The proposed system continuously monitors the runner's heart rate and cadence in real time using a smartwatch. It adjusts the music's BPM to control the running stride frequency, thus maintaining the target heart rate. We have enhanced the traditional PI control algorithm to improve the system's precision for more stable heart rate control. Additionally, the system includes a vibration assistance feature to help the user's cadence synchronize with the music's tempo. The experimental results demonstrate the system's effectiveness in maintaining the target heart rate, a crucial factor in avoiding overexercise, and significantly reducing fatigue during running.

本文提出了一種跑步輔助系統，該系統根據所聽音樂的每分鐘節拍數 (BPM) 來調整跑步者的步頻。所提出的系統使用智慧手錶連續即時監測跑步者的心率和步頻。它透過調節音樂的 BPM 來控制跑步步頻，從而維持目標心率。我們對傳統的PI控制演算法進行了增強，提高了系統的精度，使心率控制更加穩定。此外，該系統還包括振動輔助功能，可幫助使用者的節奏與音樂的節奏同步。實驗結果表明，該系統能夠有效維持目標心率，這是避免運動過度的關鍵因素，並顯著減少跑步過程中的疲勞。

1 Introduction 1
2 Related Work 5
2.1 Traditional exercise tracking equipment/methods . . . . . . . . . . . . . 5
2.2 Exercisetrackingcontrolofmobile/smartdevices . . . . . . . . . . . . . 6
2.3 Runningcontroltechnique ......................... 8
3 System Overview 10
3.1 FeatureInformation............................. 10
3.2 SystemArchitecture............................. 11
3.3 StabilizeSystemFunctions......................... 12
3.3.1 VibrationAssistance ........................ 12
3.3.2 SimilarMusicSwitching...................... 13
4 System Design 15
4.1 MusicProcessing .............................. 15
4.2 Pre-trainingPhase............................. 16
4.2.1 HeartRateRegressionModel ................... 16
4.2.2 OptimizingtheControlParameters ................ 17
4.3 RecommendTargetHeartRate....................... 19
4.4 AutoControlAlgorithm .......................... 20
4.4.1 TraditionalPIDController ..................... 20
4.4.2 ImprovedController-WeightDecay. . . . . . . . . . . . . . . . 21
5 Experiment 24
5.1 ExperimentalSetup............................. 24
5.1.1 Environment&Equipment..................... 24
5.1.2 EvaluationMetrics ......................... 24
5.2 ExperimentResult ............................. 25
5.2.1 Pretrain-with/withoutvibration.................. 25
5.2.2 HRAverageAccuracy ....................... 27
5.2.3 RelevancebetweenSPM&HR .................. 28
5.2.4 Comparewithfixedkvalue .................... 29
5.2.5 ComparewithTraditionalPIController . . . . . . . . . . . . . . 31
5.2.6 PerformanceinDifferentExerciseHabits . . . . . . . . . . . . . 32
5.2.7 AssessingRunnerFatigueLevel.................. 33
6 Conclusion 34

[1] S. Ben-Yaacov, “Moving to the music: using science and
sound to optimize your workout.” https://whyy.org/articles/ moving-to-the-music-using-science-and-sound-to-optimize-your-workout/, 2016.
[2] J.P.Lopes-Silva,A.E.Lima-Silva,R.Bertuzzi,andM.D.Silva-Cavalcante,“Influ- ence of music on performance and psychophysiological responses during moderate- intensity exercise preceded by fatigue,” Physiology and behavior, vol. 139, pp. 274– 280, 2015.
[3] P.C.Terry,C.I.Karageorghis,M.L.Curran,O.V.Martin,andR.L.Parsons-Smith, “Effects of music in exercise and sport: A meta-analytic review.,” Psychological bulletin, vol. 146, no. 2, p. 91, 2020.
[4] P. Laukka and L. Quick, “Emotional and motivational uses of music in sports and exercise: A questionnaire study among athletes,” Psychology of Music, vol. 41, no. 2, pp. 198–215, 2013.
[5] C. Girard, A. Ibeas, R. Vilanova, and A. Esmaeili, “Robust discrete-time linear con- trol of heart rate during treadmill exercise,” in 2016 24th Iranian Conference on Electrical Engineering (ICEE), pp. 1113–1118, 2016.
[6] S. Su, L. Wang, B. Celler, and A. Savkin, “Heart rate control during treadmill exercise,” in 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference, pp. 2471–2474, 2005.
[7] L. Wang, Y. Yang, and S. Su, “Nonparametric modelling based model predictive control for human heart rate regulation during treadmill exercise,” in 2021 43rd An- nual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp. 148–151, 2021.
[8] F. Rahmati, S. Nikanfar, and A. Nikoofard, “Design of tube model predictive con- troller to control human heart rate by treadmill velocity,” in 2023 9th International Conference on Control, Instrumentation and Automation (ICCIA), pp. 1–6, 2023.
[9] P.-C.Hung,Y.-C.Liu,C.-L.Lin,andW.-C.Huang,“Non-contactphysiologicalmon- itor based fuzzy control for treadmill,” in 2023 IEEE 32nd International Symposium on Industrial Electronics (ISIE), pp. 1–4, 2023.
[10] T. N. Nguyen, H. Nguyen, S. Su, and B. Celler, “Robust online adaptive neural net- work control for the regulation of treadmill exercises,” in 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, pp. 1005– 1008, 2011.
[11] Z. Liu, X. Liu, and K. Li, “Deeper exercise monitoring for smart gym using fused rfid and cv data,” in IEEE INFOCOM 2020 - IEEE Conference on Computer Com- munications, pp. 11–19, 2020.
[12] H. Ding, J. Han, L. Shangguan, W. Xi, Z. Jiang, Z. Yang, Z. Zhou, P. Yang, and J. Zhao, “A platform for free-weight exercise monitoring with passive tags,” IEEE Transactions on Mobile Computing, vol. 16, no. 12, pp. 3279–3293, 2017.
[13] B.-S. Lin, L.-Y. Wang, Y.-T. Hwang, P.-Y. Chiang, and W.-J. Chou, “Depth-camera-based system for estimating energy expenditure of physical activities in gyms,” IEEE Journal of Biomedical and Health Informatics, vol. 23, no. 3, pp. 1086–1095, 2019.
[14] M. U. Islam, H. Mahmud, F. B. Ashraf, I. Hossain, and M. K. Hasan, “Yoga posture recognition by detecting human joint points in real time using microsoft kinect,” in 2017 IEEE Region 10 Humanitarian Technology Conference (R10-HTC), pp. 668– 673, 2017.
[15] C.-H. Hsia, C.-H. Chien, H.-W. Hsu, Y.-F. Chang, and J.-S. Chiang, “Analyses of basketball player field goal shooting postures for player motion correction using kinect sensor,” in 2014 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS), pp. 222–225, IEEE, 2014.
[16] S.Karvekar,M.Abdollahi,andE.Rashedi,“Adata-drivenmodeltoidentifyfatigue level based on the motion data from a smartphone,” in 2019 IEEE Western New York Image and Signal Processing Workshop (WNYISPW), pp. 1–5, 2019.
[17] P. Li, Y. Wang, Y. Tian, T.-S. Zhou, and J.-S. Li, “An automatic user-adapted physical activity classification method using smartphones,” IEEE Transactions on Biomedical Engineering, vol. 64, no. 3, pp. 706–714, 2016.
[18] Z. Xuan, M. Liu, J. Nie, M. Zhao, S. Xia, and X. Jiang, “Canrun: Non-contact, acoustic-based cadence estimation on treadmills using smartphones,” in Proceedings of Cyber-Physical Systems and Internet of Things Week 2023, pp. 272–277, 2023.
[19] A. Otsubo, H. Suwa, Y. Arakawa, and K. Yasumoto, “Beatsync: Walking pace con- trol through beat synchronization between music and walking,” in 2019 IEEE In- ternational Conference on Pervasive Computing and Communications Workshops (PerCom Workshops), pp. 367–369, 2019.
[20] A. Galli, F. Ghisio, L. Ginestretti, M. Salaris, and M. D. Santambrogio, “The ral- coach: A virtual coach technology for recreational runners,” in 2022 IEEE Interna- tional Workshop on Sport, Technology and Research (STAR), pp. 35–40, 2022.
[21] J.-J. Chen, Y.-F. Chung, C.-P. Chang, C.-T. King, and C.-H. Hsu, “A wearable vir- tual coach for marathon beginners,” in 2014 20th IEEE International Conference on Parallel and Distributed Systems (ICPADS), pp. 915–920, 2014.
[22] Y. Du, C. Zhang, E. Wang, Y. Tang, Y. Xu, and L. Cui, “Music rhythm matching based on dynamic step frequency,” in 5th International Conference on Crowd Sci- ence and Engineering, ICCSE ’21, (New York, NY, USA), p. 113–118, Association for Computing Machinery, 2022.
[23] Y.Chen,C.-C.Chen,L.-C.Tang,andW.-H.Chieng,“Mid-distancerunningexercise assistance system via iot and exercise-oriented music,” in 2023 IEEE World AI IoT Congress (AIIoT), pp. 0264–0272, 2023.
[24] J. Ahn, H.-K. Ra, H. J. Yoon, S. H. Son, and J. Ko, “On-device filter design for self- identifying inaccurate heart rate readings on wrist-worn ppg sensors,” IEEE Access, vol. 8, pp. 184774–184784, 2020.
[25] A.Brondin,M.Nordström,C.M.Olsson,andD.Salvi,“Opensourcestepcounteral- gorithm for wearable devices,” in Companion Proceedings of the 10th International Conference on the Internet of Things, pp. 1–7, 2020.
[26] H.-F. Chang Chien, Y.-S. Lee, I.-H. Tai, and T.-Y. Shiang, “身體加速度及步頻分 別與心跳之相關性-前導性實驗,” 運動表現期刊, vol. 3, no. 1, pp. 23–27, 2016.
[27] E. Van Dyck, B. Moens, J. Buhmann, M. Demey, E. Coorevits, S. Dalla Bella, and M. Leman, “Spontaneous entrainment of running cadence to music tempo,” Sports Medicine - Open, vol. 1, no. 15, 2015.
[28] S. A. Miles, R. A. Miranda, and M. T. Ullman, “Sex differences in music: A fe- male advantage at recognizing familiar melodies,” Frontiers in psychology, vol. 7, p. 163687, 2016.
[29] 黃聰謀, 應用類神經網路於 PID 控制器之設計研究 dA study of PID controller design based on artificial neural network. PhD thesis, 撰者, 2004.
[30] A.JudyandW.Ira,“Energy-yieldingmacronutrientsandenergymetabolisminsport nutrition,” British Journal of Nutrition, vol. 85, pp. 511–512, 2001.