Weight Prediction of Bedridden Patients via Kinect by Image Enhancement with Median Filler and Artificial Neural Network

Worapon Manosroi; Apisak Phromfaiy; Dussadee Buntam

Authors

Worapon Manosroi Smart Electronic Engineering, Faculty of Industrial Technology, Uttaradit Rajabhat University, Uttaradit, Thailand
Apisak Phromfaiy Computer Engineering, Faculty of Industrial Technology, Uttaradit Rajabhat University, Uttaradit, Thailand
Dussadee Buntam Logistic Engineering, Faculty of Industrial Technology, Uttaradit Rajabhat University, Uttaradit, Thailand

Keywords:

Kinect, Neural Network, Image Processing

Abstract

Drug dosage for treatment of bedridden patients need to calculated based on patient body weight. Currently, the methods for calculating such a weight exhibit many limitations, including the need to move a patient to weigh, which may worsen the symptoms of a patient. Weighing bed, which yields high accuracy, is nevertheless very expensive, making the treatment cost higher. Prediction of the weight from the patient size is also normally not accurate. The present research therefore proposed a method for predicting the weight of a bedridden patient by Kinect, with image enhancement using median filter and artificial neural network. One hundred weight data of normal people, which were used instead of those belonging to real patients, were divided into 3 groups for training, testing, and validation at 70%, 15%, and 15%, respectively. Eighteen neural network architectures were designed. The results showed that the suitable artificial neural network that could be used to predict the body weight consisted of 3 nodes in the hidden layers; Lavenberg-Maqurdt algorithm should be used as the training function, while tan-sigmoid transfer function should be used as the activation function; R and RMSE values were noted to be 0.93393 and 5.92, respectively.

References

Microsoft Co., 2011, Xbox 360 Kinect Sensor, United States of America, pp. 1-18.

Kaenchan, S., Mongkolnam, P., Watanapa, B. and Sathienpong, S., 2013, “Automatic Multiple Kinect Cameras Setting for Simple Walking Posture Analysis,” International Computer Science and Engineering Conference (ICSEC), Nakhon Pathom, pp. 245-249.

Berger, K., Ruhl, K., Brummer, C., Schroder, Y., Scholz, A. and Magnor, M., 2011, “Markerless Motion Capture using Multiple Color-Depth Sensors,” 16th International Workshop on Vision, Modeling, and Visualization (VMV 2011), 4-6 October 2011, Berlin, Germany.

Darina, K., Alexander R., Miroslav C. and Vladimír T., 2017, “Utilisation of Kinect Sensors for the Design of a Human-robot Collaborative Woekcell,” Advances in Science and Technology Research Journal, 11 (4), pp. 270-278.

Kongsro, J., 2014, “Estimation of Pig Weight Using a Microsoft Kinect Prototype Imaging System,” Computers and Electronics in Agriculture, 109 (1), pp. 32-35.

Pezzuolo, A., Guarino, M., Sartori, L. González, L. and Marinello, F., 2018, “On-barn Pig Weight Estimation Based on Body Measurements by a Kinect v1 Depth Camera,” Computers and Electronics in Agriculture, 148 (1), pp. 29-36.

Wongtrairat, W., Sopon, T. and Wongsuthavas, S., 2016, “Weight Estimation of Native Cow by Image Processing,” Engineering, Science, Technology and Architecture Conference 2016, Nakhon Ratchasima, pp. 682-685. (In Thai).

Samperio, E., Lidón, I., Rebollar, R., Castejón-Limas, M. and Álvarez-Aparicio, C., 2021, “Lambs’ Live Weight Estimation Using 3D Images,” Animal, 15 (8), pp. 1-7.

Kavalerov, B., Kilin, G. and Suslov, A., 2020, “Neural Network Architecture Choice for Modelling Various Configuration Power System,” International Conference on Innovation Energy 2020 (IE 2020), Perm, Russia, pp. 1-7.

Chen, Y., Lei, T., Yao, S. and Wang, H., 2020, “PM2.5 Prediction Model Based on Combinational Hammerstein Recurrent Neural Networks,” Mathematics, 8 (12), pp. 1-23.

Chaisuwan, T., Suksawang, P. and Mekparyup, J., 2020, “Development of Tournament Selection of Genetic Algorithm for Forecasting Rainfall with Artificial Neural Network,” Princess of Naradhiwas University Journal, 12 (3), pp. 245-261. (In Thai).

Prapaporn, W., 2019, "An Analysis on Material Quantity Relationship of Reinforced Concrete Buildings between Multiple Linear Regression and Artificial Neural Network," Naresuan University Engineering Journal, 14 (1), pp. 84-102.

Pattajarukul, B., 2013, Fundamentals of Digital Image Processing, Se-Education, Bangkok, p. 384.

Sibi, P., Joned, S. and Siddarth, P., 2013, “Analysis of Different Activation Functions Using Back Propagation Neural Networks,” Journal of Theoretical and Applied Information Technology, 47 (3), pp. 1264-1268.

The MathWorks, Inc., 2004, Neural Network Toolbox User’s Guide, Massachusetts, pp. 1-846.

Katemukda, N., 2021, "Regression Analysis Applying for Defection Rescreening of Microelectronics Product," Ladkrabang Engineering Journal, 38(4), pp. 42-50.

Lei, S., Zhang, H., Wang, K. and Su, Z., 2019, “How Training Data Affect the Accuracy and Robustness of Neural Networks for Image Classification,” International Conference on Learning Representations, New Orleans, Louisiana, pp. 1-14.

Buntam, D., Permpoonsinsup, W. and Surin, P., 2020, “The Application of a Hybrid Model Using Mathematical Optimization and Intelligent Algorithms for Improving the Talc Pellet Manufacturing Process,” Symmetry, 12 (10), pp. 1-18.