A cloudbased mobile human fall forecasting system using
A cloud-based mobile human fall forecasting system using recurrent neural networks Mehrgan Khoshpasand CS 4997 July 27 2018 Supervisor: Alireza Manashty
Content • Introduction • Related works • Neural network • Proposed System • Results • Conclusion and Future works
Introduction • In 2008– 2009, about 1 in 3 seniors aged 65 and older, were concerned about future falls. • In 2008– 2009, approximately 20% of Canadians aged 65 and older (862, 000 seniors) reported a fall in the previous year. • Contributed to 73, 190 hospitalizations.
Introduction(cont. ) • Many successful fall detection systems has been proposed. • Predicting human falls can prevent major injuries. • Many people are carrying sensor-packed smartphones everyday. • In this project, the goal was to only use sensors in the smart-phones.
Related works • Tsinganos et al. (2017) proposed a fall detection system on android; used a threshold algorithm; enhanced the accuracy by using a k Nearest Neighbor (k. NN) classifier to %94. 89. • Shen et al. (2017) proposed a system that can predict falls by recording humans’ gate data and using fuzzy Petri net model. Up to 79%.
Related works(cont. ) • Yang et al. proposed a fall prediction algorithm that can predict human falls 0. 4 seconds before happening. Used Recurrent Neural Network with accuracy up to 71%. • The system by Tong et al. used wearable device that collects tri-axial accelerometer data and uses a hidden Markov model (HMM)-based method. They claim their method predicted 100% of falls 200 ms before happening.
Objective • A fall forecasting system. • Using smartphone-sensors and recurrent neural network. • Alerting user in order to prevent some of the human falls
Deep Neural Network • Allows a machine to be fed with raw data and to automatically discover the representations needed for detection or classification. • Many layers of information-processing stages are exploited inside a multi-layer Neural Network • Each layer consists of numbers of units performing simple function on the weighted sum of inputs coming from the previous layer. • Many complex functions can be learned with minimal domain expertise.
Deep Neural Network(cont. ) • Training the neural network involves adjusting some internal parameters of the network, called weights, in order to minimize a loss function. • Weights are adjusted by calculating the gradient vector of error with respect of each weight. • (Stochastic) Gradient Descent and Back-propagation. • Deep learning been applied with great success to the detection, segmentation, and recognition of objects and regions in images.
Feed Forward Neural Network
Recurrent Neural Network •
Recurrent Neural Network(cont. )
Long Short-Term Memory(LSTM) • As result of growing or shrinking the backpropagated gradients at each time step in RNNs, gradients usually explode or vanish over many time steps. • self-loops to produce paths where the gradient can flow for a long period • In a cell, weights are gated which means weights can change dynamically based on the input sequence.
LSTM(cont. )
Proposed System
System overview(cont. )
Results
0 1 4 7 10 13 16 19 22 25 28 31 34 37 40 43 46 49 52 55 58 61 64 67 70 73 76 79 82 85 88 91 94 97 100 103 106 Sum Vector 2 1, 5 1 Sum vector Results(cont. ) ADL sample 0, 5 1 3 2, 5 0 -1 -2 -3 -4 -5 -6 unpredicted fall sample
predicted fall sample 10 8 6 4 2 -2 -4 0 -2 1 9 17 25 33 41 49 57 65 73 81 89 97 105 113 121 129 137 145 153 161 169 177 185 193 201 209 217 225 233 241 249 257 0 1 8 15 22 29 36 43 50 57 64 71 78 85 92 99 106 113 120 127 134 141 148 155 162 169 176 183 190 197 204 211 218 Results(cont. ) predicted fall sample 10 8 6 4 2
Conclusion • Designed a model for fall forecasting using LSTM • Created an i. OS app for fall forecasting • Used URFD fall dataset for fall forecasting • Find the need for a fall forecasting dataset • Some falls are challenging to forecast
Future works • Add Android support • Using current smart-phone fall detection systems to build a real fall dataset • Putting the model on the phone instead of cloud • Open-sourcing the project
References • [1] The Frailty. Epidemiology of Falls (world report). pdf. pages 3– 7, 2001. • [2] Mohammad Habib, Mas Mohktar, Shahrul Kamaruzzaman, Kheng Lim, Tan Pin, and Fatimah Ibrahim. Smartphone-Based Solutions for Fall Detection and Prevention: Challenges and Open Issues. Sensors, 14(12): 7181– 7208, 2014. • [3] Shih Hung Yang, Wenlong Zhang, Yizou Wang, and Masayoshi Tomizuka. Fall-prediction algorithm using a neural network for safety enhancement of elderly. 2013 CACS International Automatic Control Conference, CACS 2013 - Conference Digest , pages 245– 249, 2013. • [4] Christopher M Bishop. Pattern recognition and machine learning, 5 th Edition. Information science and statistics. Springer, 2007. • [5] Ian Goodfellow, Yoshua Bengio, and Aaron Courville. Deep Learning MIT Press, 2016. • [6] Rong Kuan Shen, Cheng Ying Yang, Victor R. L. Shen, and Wei Cheng Chen. A Novel Fall Prediction System on Smartphones. IEEE Sensors Journal , 17(6): 1865– 1871, 2017. • [7] Anne Ngu, Yeahuay Wu, Habil Zare, and Andrew Polican B. Fall Detec-tion Using Smartwatch Sensor Data with Accessor Architecture Anne. 10347(June), 2017. • [8] Ramesh Rajagopalan, Irene Litvan, and Tzyy-Ping Jung. Fall Predic- tion and Prevention Systems: Recent Trends, Challenges, and Future Research Directions. Sensors , 17(11): 2509, 2017.
References (cont. ) • [9] Lina Tong, Quanjun Song, Yunjian Ge, and Ming Liu. HMM-based hu- man fall detection and prediction method using tri-axial accelerometer. IEEE Sensors Journal , 13(5): 1849– 1856, 2013. • [10] Panagiotis Tsinganos and Athanassios Skodras. A smartphone-based fall detection system for the elderly. International Symposium on Image and Signal Processing and Analysis, ISPA , (September): 53– 58, 2017. • [11] Yann Le. Cun, Yoshua Bengio, Hinton Geoffrey, Geoffrey Hinton, Lecun Y. , Bengio Y. , Hinton G. , and Hinton Geoffrey. Deep learning. Nature, 521(7553): 436– 444, 2015. • [12] Xu Tao and Zhou Yun. Fall prediction based on biomechanics equilib-rium using kinect. international Journal of Distributed Sensor Networks, 13(4), 2017. • [13] Sepp Hochreiter and J urgen Schmidhuber. Long Short Term Memory, (1993): 1– 28, 1996. • [14] Bogdan Kwolek and Michal Kepski. Human fall detection on embed-ded platform using depth maps and wireless accelerometer. Computer Methods and Programs in Biomedicine, 117(3): 489– 501, 2014.
- Slides: 23