| DC 欄位 |
值 |
語言 |
| DC.contributor | 資訊工程學系 | zh_TW |
| DC.creator | 洪苡晴 | zh_TW |
| DC.creator | Yi-Ching Hung | en_US |
| dc.date.accessioned | 2021-7-26T07:39:07Z | |
| dc.date.available | 2021-7-26T07:39:07Z | |
| dc.date.issued | 2021 | |
| dc.identifier.uri | http://ir.lib.ncu.edu.tw:444/thesis/view_etd.asp?URN=108522076 | |
| dc.contributor.department | 資訊工程學系 | zh_TW |
| DC.description | 國立中央大學 | zh_TW |
| DC.description | National Central University | en_US |
| dc.description.abstract | 復健有助於治療運動和職業傷害。在傳統的復健過程中,治療師會依據不同
患者所需要的復健而分配指定的動作,讓患者在下次到醫院就診之間執行。這
依賴患者正確記住動作和執行這些動作。這會發生一些患者忘記執行動作或無
法詳細回憶每個動作的情況,結果延誤了復健治療的進度。或者在最壞的情況
下,患者可能會因為執行了不正確的復健動作而受到更嚴重的傷害。為了解決
上述問題,治療師和患者之間需要一個監督機制。一方面,可以提醒患者何時
復健,也能透過患者的智慧型手機顯示需要執行的復健動作。另一方面,也可
以幫助治療師監督患者復健的進度。在這項研究中,我們提出了一個 HRNet-
based rehabilitation monitoring system,是由一個 iOS 應用程式和伺服器端的服務組成。應用程式負責顯示和上傳復健影片。伺服器端計算影片中治療師的動作與患者的動作之間的相似度分數以及每個動作的重複次數。這些統計
資料將顯示給治療師和患者。實驗表明,相似度計算的 F1-Score 高達 0.9,重
複次數的 Soft Accuracy 則高於 90%。 | zh_TW |
| dc.description.abstract | The rehabilitation treatment helps to heal minor sports and occupational in- juries. In a traditional rehabilitation process, a therapist will assign certain actions to a patient to perform in between hospital visits, and it will rely on the patient to remember actions correctly and the schedule to perform them. It happens frequently that some patients forget to perform actions or fail to recall each action in detail. As a consequence, the progress of rehabilitation treatment is delayed or, in the worst case, the patient may suffer from additional injury caused by performing incorrect actions. To resolve these issues, a monitoring system is necessary between the therapist and the patient. On one hand, it can remind the patient when to per-form the actions and display the actions for the patient to follow via the patient’s smartphone. On the other hand, it helps the therapist monitor the progress of the rehabilitation for the patient. In this research, we propose a HRNet-based rehabilitation monitoring system, which consists of an iOS app and several components at the server-side. The app is in charge of displaying and collecting action videos. The server computes the similarity score between the therapist’s actions and the patient’s ones in the videos and the number of repetitions of each action. Theses stats will be shown to both of the patient and therapist. The extensive experiments show that the F1-Score of the similarity calculation is as high as 0.9 and the soft accuracy of the number of repetitions is higher than 90%. | en_US |
| DC.subject | Pose Detection | zh_TW |
| DC.subject | Rehabilitation | zh_TW |
| DC.title | A HRNet-based Rehabilitation Monitoring System | en_US |
| dc.language.iso | en_US | en_US |
| DC.type | 博碩士論文 | zh_TW |
| DC.type | thesis | en_US |
| DC.publisher | National Central University | en_US |