Automatic, Qualitative Scoring of the Interlocking Pentagon Drawing Test (PDT) Based on U-Net and Mobile Sensor Data

We implemented a mobile phone application of the pentagon drawing test (PDT), called mPDT, with a novel, automatic, and qualitative scoring method for the application based on U-Net (a convolutional network for biomedical image segmentation) coupled with mobile sensor data obtained with the mPDT. For the scoring protocol, the U-Net was trained with 199 PDT hand-drawn images of 512 × 512 resolution obtained via the mPDT in order to generate a trained model, Deep5, for segmenting a drawn right or left pentagon. The U-Net was also trained with 199 images of 512 × 512 resolution to attain the trained model, DeepLock, for segmenting an interlocking figure. Here, the epochs were iterated until the accuracy was greater than 98% and saturated. The mobile senor data primarily consisted of x and y coordinates, timestamps, and touch-events of all the samples with a 20 ms sampling period. The velocities were then calculated using the primary sensor data. With Deep5, DeepLock, and the sensor data, four parameters were extracted. These included the number of angles (0–4 points), distance/intersection between the two drawn figures (0–4 points), closure/opening of the drawn figure contours (0–2 points), and tremors detected (0–1 points). The parameters gave a scaling of 11 points in total. The performance evaluation for the mPDT included 230 images from subjects and their associated sensor data. The results of the performance test indicated, respectively, a sensitivity, specificity, accuracy, and precision of 97.53%, 92.62%, 94.35%, and 87.78% for the number of angles parameter; 93.10%, 97.90%, 96.09%, and 96.43% for the distance/intersection parameter; 94.03%, 90.63%, 92.61%, and 93.33% for the closure/opening parameter; and 100.00%, 100.00%, 100.00%, and 100.00% for the detected tremor parameter. These results suggest that the mPDT is very robust in differentiating dementia disease subtypes and is able to contribute to clinical practice and field studies.

Download Full-text

Automatic, Qualitative Scoring of the Clock Drawing Test (CDT) Based on U-Net, CNN and Mobile Sensor Data

Sensors ◽

10.3390/s21155239 ◽

2021 ◽

Vol 21 (15) ◽

pp. 5239

Author(s):

Ingyu Park ◽

Unjoo Lee

Keyword(s):

Deep Learning ◽

Scoring System ◽

Learning Algorithms ◽

Sensor Data ◽

Smart Devices ◽

Mobile Sensor ◽

Convolutional Network ◽

Clock Drawing Test ◽

Clock Drawing ◽

Drawing Test

The Clock Drawing Test (CDT) is a rapid, inexpensive, and popular screening tool for cognitive functions. In spite of its qualitative capabilities in diagnosis of neurological diseases, the assessment of the CDT has depended on quantitative methods as well as manual paper based methods. Furthermore, due to the impact of the advancement of mobile smart devices imbedding several sensors and deep learning algorithms, the necessity of a standardized, qualitative, and automatic scoring system for CDT has been increased. This study presents a mobile phone application, mCDT, for the CDT and suggests a novel, automatic and qualitative scoring method using mobile sensor data and deep learning algorithms: CNN, a convolutional network, U-Net, a convolutional network for biomedical image segmentation, and the MNIST (Modified National Institute of Standards and Technology) database. To obtain DeepC, a trained model for segmenting a contour image from a hand drawn clock image, U-Net was trained with 159 CDT hand-drawn images at 128 × 128 resolution, obtained via mCDT. To construct DeepH, a trained model for segmenting the hands in a clock image, U-Net was trained with the same 159 CDT 128 × 128 resolution images. For obtaining DeepN, a trained model for classifying the digit images from a hand drawn clock image, CNN was trained with the MNIST database. Using DeepC, DeepH and DeepN with the sensor data, parameters of contour (0–3 points), numbers (0–4 points), hands (0–5 points), and the center (0–1 points) were scored for a total of 13 points. From 219 subjects, performance testing was completed with images and sensor data obtained via mCDT. For an objective performance analysis, all the images were scored and crosschecked by two clinical experts in CDT scaling. Performance test analysis derived a sensitivity, specificity, accuracy and precision for the contour parameter of 89.33, 92.68, 89.95 and 98.15%, for the hands parameter of 80.21, 95.93, 89.04 and 93.90%, for the numbers parameter of 83.87, 95.31, 87.21 and 97.74%, and for the center parameter of 98.42, 86.21, 96.80 and 97.91%, respectively. From these results, the mCDT application and its scoring system provide utility in differentiating dementia disease subtypes, being valuable in clinical practice and for studies in the field.

Download Full-text

Secure Mobile Sensor Data Transfer using Asymmetric Cryptography Algorithms

2020 International Conference on Cyber Warfare and Security (ICCWS) ◽

10.1109/iccws48432.2020.9292392 ◽

2020 ◽

Author(s):

Nouman Kabir ◽

Shaharyar Kamal

Keyword(s):

Data Transfer ◽

Sensor Data ◽

Mobile Sensor ◽

Asymmetric Cryptography

Download Full-text

Accuracy of soft tissue balancing in total knee arthroplasty using surgeon-defined assessment versus a gap-balancer or electronic sensor

Journal of Orthopaedic Surgery and Research ◽

10.1186/s13018-021-02439-w ◽

2021 ◽

Vol 16 (1) ◽

Author(s):

Ran Zhao ◽

Yanqing Liu ◽

Hua Tian

Keyword(s):

Total Knee Arthroplasty ◽

Soft Tissue ◽

Knee Arthroplasty ◽

Sensor Data ◽

Soft Tissue Balancing ◽

Electronic Sensor ◽

Prior Performance ◽

Cumulative Summation ◽

Total Knee ◽

Sensitivity Specificity

Abstract Background Soft tissue balancing is essential for the success of total knee arthroplasty (TKA) and is mainly dependent on surgeon-defined assessment (SDA) or a gap-balancer (GB). However, an electronic sensor has been developed to objectively measure the gap pressure. This study aimed to evaluate the accuracy of soft tissue balancing using SDA and GB compared with a sensor. Methods Forty-eight patients undergoing TKA (60 knees) were prospectively enrolled. Soft tissue balancing was sequentially performed using SDA, a GB, and an electronic sensor. We compared the SDA, GB, and sensor data to calculate the sensitivity, specificity, and accuracy at 0°, 45°, 90°, and 120° flexion. Cumulative summation (CUSUM) analysis was performed to assess the surgeon’s performance during the sensor introductory phase. Results The sensitivity of SDA was 63.3%, 68.3%, 80.0%, and 80.0% at 0°, 45°, 90°, and 120°, respectively. The accuracy of the GB compared with sensor data was 76.7% and 71.7% at 0° and 90°, respectively. Cohen’s kappa coefficient for the accuracy of the GB was 0.406 at 0° (moderate agreement) and 0.227 at 90° (fair agreement). The CUSUM 0° line achieved good prior performance at case 45, CUSUM 90° and 120° showed a trend toward good prior performance, while CUSUM 45° reached poor prior performance at case 8. Conclusion SDA was a poor predictor of knee balance. GB improved the accuracy of soft tissue balancing, but was still less accurate than the sensor, particularly for unbalanced knees. SDA improved with ongoing use of the sensor, except at 45° flexion.

Download Full-text

Probabilistic model for vehicle trajectories reconstruction using sparse mobile sensor data on freeways

2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC) ◽

10.1109/itsc.2016.7795628 ◽

2016 ◽

Cited By ~ 4

Author(s):

Xiaonian Shan ◽

Peng Hao ◽

Xiaohong Chen ◽

Kanok Boriboonsomsin ◽

Guoyuan Wu ◽

...

Keyword(s):

Probabilistic Model ◽

Sensor Data ◽

Mobile Sensor ◽

Vehicle Trajectories

Download Full-text

The Clock Drawing Test: Performance differences between the free-drawn and incomplete-copy versions in patients with MCI and dementia

Dementia & Neuropsychologia ◽

10.1590/s1980-5764-2016dn1003009 ◽

2016 ◽

Vol 10 (3) ◽

pp. 227-231 ◽

Cited By ~ 2

Author(s):

Bárbara Costa Beber ◽

Renata Kochhann ◽

Bruna Matias ◽

Márcia Lorena Fagundes Chaves

Keyword(s):

Cognitive Impairment ◽

Test Performance ◽

Diagnostic Value ◽

Control Group ◽

Cognitive Screening ◽

Scoring Method ◽

Clock Drawing Test ◽

Clock Drawing ◽

Healthy Elderly ◽

Drawing Test

ABSTRACT Background: The Clock Drawing Test (CDT) is a brief cognitive screening tool for dementia. Several different presentation formats and scoring methods for the CDT are available in the literature. Objective: In this study we aimed to compare performance on the free-drawn and "incomplete-copy" versions of the CDT using the same short scoring method in Mild Cognitive Impairment (MCI) and dementia patients, and healthy elderly participants. Methods: 90 participants (controlled for age, sex and education) subdivided into control group (n=20), MCI group (n=30) and dementia group (n=40) (Alzheimer's disease - AD=20; Vascular Dementia - VD=20) were recruited for this study. The participants performed the two CDT versions at different times and a blinded neuropsychologist scored the CDTs using the same scoring system. Results: The scores on the free-drawn version were significantly lower than the incomplete-copy version for all groups. The dementia group had significantly lower scores on the incomplete-copy version of the CDT than the control group. MCI patients did not differ significantly from the dementia or control groups. Performance on the free-drawn copy differed significantly among all groups. Conclusion: The free-drawn CDT version is more cognitively demanding and sensitive for detecting mild/early cognitive impairment. Further evaluation of the diagnostic value (accuracy) of the free-drawn CDT in Brazilian MCI patients is needed.

Download Full-text

A Kalman Filter-Based Queue Length Estimation Method with Low-Penetration Mobile Sensor Data at Signalized Intersections

Transportation Research Record Journal of the Transportation Research Board ◽

10.1177/0361198118798734 ◽

2018 ◽

Vol 2672 (45) ◽

pp. 253-264 ◽

Cited By ~ 7

Author(s):

Juyuan Yin ◽

Jian Sun ◽

Keshuang Tang

Keyword(s):

Kalman Filter ◽

Queue Length ◽

Estimation Method ◽

Mobile Internet ◽

Internet Technology ◽

Sensor Data ◽

Linear Regression Method ◽

Mobile Sensor ◽

Length Estimation ◽

Queue Lengths

Queue length estimation is of great importance for signal performance measures and signal optimization. With the development of connected vehicle technology and mobile internet technology, using mobile sensor data instead of fixed detector data to estimate queue length has become a significant research topic. This study proposes a queue length estimation method using low-penetration mobile sensor data as the only input. The proposed method is based on the combination of Kalman Filtering and shockwave theory. The critical points are identified from raw spatiotemporal points and allocated to different cycles for subsequent estimation. To apply the Kalman Filter, a state-space model with two state variables and the system noise determined by queue-forming acceleration is established, which can characterize the stochastic property of queue forming. The Kalman Filter with joining points as measurement input recursively estimates real-time queue lengths; on the other hand, queue-discharging waves are estimated with a line fitted to leaving points. By calculating the crossing point of the queue-forming wave and the queue-discharging wave of a cycle, the maximum queue length is also estimated. A case study with DiDi mobile sensor data and ground truth maximum queue lengths at Huanggang-Fuzhong intersection, Shenzhen, China, shows that the mean absolute percentage error is only 11.2%. Moreover, the sensitivity analysis shows that the proposed estimation method achieves much better performance than the classical linear regression method, especially in extremely low penetration rates.

Download Full-text