Created at 10pm, Apr 26
cyranodbMedicine
0
Support System to Improve Reading Activity in Parkinson’s Disease and Essential Tremor Patients
Contract ID
Vzmd4Bio9gknUkeUdF2ykt-ss6aLQuTNSAvll_Kg7Ks
File Type
PDF
Entry Count
60
Embed. Model
jina_embeddings_v2_base_en
Index Type
hnsw

Abstract

The use of information and communication technologies (ICTs) to improve the quality of life of people with chronic and degenerative diseases is a topic receiving much attention nowadays. We can observe that new technologies have driven numerous scientific projects in e-Health, encompassing Smart and Mobile Health, in order to address all the matters related to data processing and health. Our work focuses on helping to improve the quality of life of people with Parkinson’s Disease (PD) and Essential Tremor (ET) by means of a low-cost platform that enables them to read books in an easy manner. Our system is composed of two robotic arms and a graphical interface developed for Android platforms. After several tests, our proposal has achieved a 96.5% accuracy for A4 80 gr non-glossy paper. Moreover, our system has outperformed the state-of-the-art platforms considering different types of paper and inclined surfaces. The feedback from ET and PD patients was collected at “La Princesa” University Hospital in Madrid and was used to study the user experience. Several features such as ease of use, speed, correct behavior or confidence were measured via patient feedback, and a high level of satisfaction was awarded to most of them. According to the patients, our system is a promising tool for facilitating the activity of reading.

Average time 66.577.588.599.5191725334149576573818997105113121129137145153161169177185193Time (seconds) Number of observation realized (200 observations) Figure 8. Average time with the thick wheel model. Different results were obtained in the case of the thin wheel model with 65 gr/m2 and A4 sized glossy paper. The average time is 11.6 s per page, which is higher than with the thick wheel, meaning that the system is able to turn nearly 310 pages per hour. The results are shown in Figure 9. The increase in time is a consequence of the page selection time augmentation when using the thin wheel model. Nevertheless, it must be remembered that the thin wheel model achieves greater precision when turning glossy lightweight pages. Time in seconds 8101214161820191725334149576573818997105113121129137145153161169177185193Time (seconds) Number of observation realized (200 observations) Average time 11.6123 sec.
id: 29619f2ca0d0c70cf1da764b21db548a - page: 8
Figure 9. Average time with the thin wheel model. 8 of 16 Sensors 2017, 17, 1006 The Bookreader 2 model was tested too, using 80 gr/m2, A4 sized paper without a glossy surface. The results are shown in Figure 10. The average time is less than that of the other models, as the selection action does not involve two servo motors, but just one. However, it should be noted that the error rate is higher than that of our proposal. Furthermore, this noticeable average time decrease is due to the fact that only correctly turned pages are being considered in this study. Figure 10. Average time with the Bookreader 2 model.
id: 7f0903e2b9e34b778b98f6f6f03deca4 - page: 8
4.4. Arms Location It is very important to establish a relationship between the book dimensions and the position of the robotic arms in order to ensure successful page selection. This test was carried out on different ring bound books because of the stability that they offer when a page has to be turned to the left. Each test was performed on 100 A4 sized pages (21 29.7 cm). In addition, glossy and non-glossy surfaces were used, employing the thin wheel model for glossy pages and the thick wheel model for non-glossy pages. Figure 11 shows how the system was deployed and the three distances that were evaluated. The results are shown in Table 1. Figure 11. Location of distances between book and robotic arms. 9 of 16 Sensors 2017, 17, 1006 Table 1. Average time and success rate for different weight/gloss/distance congurations. Weight (gr/m2) Glossy Page Distance between the the Lifting Center of Arm and Right Page (cm) Average Time Success Rate 80 80 80 80 80
id: 5b3cc48a8812194cccf3d94d886ed616 - page: 9
Yes Yes Yes Yes Yes 10 11 12 13 14 12.8562 12.9456 13.0127 12.8754 12.8652 94% 83% 75% 69% 57% 80 80 80 80 80 No No No No No 10 11 12 13 13 7.0124 7.0235 7.0982 7.1623 7.2156 87% 92% 96% 92% 91% 70 70 70 70 70 Yes Yes Yes Yes Yes 10 11 12 13 14 11.2156 11.6879 11.9564 11.8754 11.6523 92% 82% 74% 65% 48% 70 70 70 70 70 No No No No No 10 11 12 13 14 7.2156 7.3956 7.4181 7.4536 7.5689 93% 93% 95% 91% 90% 65 65 65 65 65 Yes Yes Yes Yes Yes 10 11 12 13 14 11.4948 11.2244 11.8509 11.2208 11.1031 93% 84% 83% 62% 54% 65 65 65 65 65
id: b3bdcb7f7d21241e28ccd5cdb7404679 - page: 10
How to Retrieve?
# Search

curl -X POST "https://search.dria.co/hnsw/search" \
-H "x-api-key: <YOUR_API_KEY>" \
-H "Content-Type: application/json" \
-d '{"rerank": true, "top_n": 10, "contract_id": "Vzmd4Bio9gknUkeUdF2ykt-ss6aLQuTNSAvll_Kg7Ks", "query": "What is alexanDRIA library?"}'
        
# Query

curl -X POST "https://search.dria.co/hnsw/query" \
-H "x-api-key: <YOUR_API_KEY>" \
-H "Content-Type: application/json" \
-d '{"vector": [0.123, 0.5236], "top_n": 10, "contract_id": "Vzmd4Bio9gknUkeUdF2ykt-ss6aLQuTNSAvll_Kg7Ks", "level": 2}'