Abstract
There have been several approaches for wearable fall detection devices during the last twenty years. The majority of technologies relied on machine learning. Although the given findings appear that the issue is practically addressed, critical problems remain about feature extraction and selection. In this research, the constraint of machine learning on feature extraction is addressed by including a hybrid convolutional operation in our proposed deep residual network, called the DeepFall model. The proposed network automatically generates high-level motion signal characteristics that can be utilized to track falls and everyday activities. FallAllD dataset, a publicly available standard dataset for fall detection that gathered motion signals of falls and other events, was utilized to analyze the proposed network. We performed investigations using a 5-fold cross-validation technique to determine overall accuracy and F-measure. The experimental outcomes show that the proposed DeepFall performs better accuracy (95.19%) and F-measure (92.79%) than the state-of-the-art baseline deep learning networks.
Access provided by Autonomous University of Puebla. Download conference paper PDF
Similar content being viewed by others
Keywords
1 Introduction
The importance of fall detection systems (FDSs) for the elderly derives from the concept that serious fall-related problems could well be avoided with prompt and adequate medical care. The FDSs might be classified as either ambient or wearable. The first category is limited to residential use, but the latter benefits following the elderly inside and outside. This article discusses wearable fall detection technologies, and the sensors frequently utilized in this equipment are discussed in the next section.
Micro-Electro-Mechanical Systems (MEMS) permitted the production of a range of sensors, including accelerometers and gyroscopes, in compact and light-weight packaging as wearable technology advanced. These MEMS-based sensors are commonly employed in wearable devices presently. Accelerometers are the most often utilized sensors for fall detection and human activity identification due to their low energy consumption and techniques used to collect important body movement data.
Several FDSs have been designed in the past twenty years. Some of these strategies are threshold-based [12], however the most are machine learning-based [15], to mention just some. In threshold-based approaches, thresholds are determined based on the available data. Correspondingly, with machine learning-based approaches, the training phase depends on the available information.
Based on the interpretation of the findings acquired by wearable inertial sensors, machine learning (ML) techniques have demonstrated remarkable efficacy in differentiating between falls and typical motions or Activities of Daily Living (ADLs). Random forest, Support vector machine, Multi-layer perceptron, and k-nearest neighbors are four well-known and commonly employed ML techniques in FDSs [5]. Nevertheless, the effectiveness of these ML approaches was constrained by manual feature extraction.
Deep learning (DL) has been utilized extensively in the majority of areas throughout the globe [10, 11, 17]. In recent years, fall recognition has benefited more from the application of DL techniques [1, 7] than threshold-based procedures [2]. Designs of DL comprise layers, and each layer extracts the characteristics of the provided data or transforms the data. Typically, the last layers of models consisted of synthetic neurons. The data could be recorded as a vision-based image, raw data from an accelerometer and gyroscope. Several DL approaches are employed to identify autumnal occurrences [8]. Some systems are constructed using a single DL algorithm, while others combine many methods to get a greater detection rate [6]. Convolutional neural networks (CNNs) and recurrent neural networks (RNNs) are the most prevalent DL models for fall detection [9, 20].
In this study, we proposed a convolutional and residual block-based deep neural network named DeepFall model. Using the TensorFlow platform, the recommended model has been trained to identify falls and ADLs. The suggested model was assessed and compared on a public benchmark dataset against various baseline DL models (FallAllD dataset).
The article continues with the following outline: New relevant research is included in Sect. 2. The details of the proposed model are outlined in Sect. 3. The outcomes of our investigations can be seen in Sect. 4. The study finishes with a discussion of necessary future studies in Sect. 5.
2 Related Works
2.1 Fall Detection System
Current fall detection technologies may be loosely categorized into vision-based, ambient, and wearable sensors.
Vision-based sensors gather motion information by monitoring systems and extracting a person’s body photograph orientation or human skeleton annotations from collected video or image data [21] to detect a fall. Typically, the ambient sensor measures fall by gathering infrared [19], radar [13], and other signals from the scene sensor. Although it does not pose any privacy concerns, it comes at a slightly higher price. It is susceptible to noise and has a somewhat restricted detection range. Multiple low-cost sensors are used by wearable technology to monitor falls [18]. Its detecting abilities depend on the sensor being worn in real-time. However, the elderly may be unable to do so in some situations, such as having a bath. Furthermore, some older individuals may experience pain from their apparel.
Due to the inexpensive cost of sensors in recent times, wearable sensors have gained increasing popularity. To acquire the three-axis acceleration at various points and the three-axis rotation angular velocity in a gyroscope, the most popular locations for wearable sensors are the calf, spine, head, pelvis, and feet [4].
2.2 Automatic Fall Detection by Using DL
Approaches for ML are primarily separated into classical pattern recognition and classification and recognition based on DL. Conventional recognition techniques depend on manually extracted features for identification. Consequently, researchers recommend stricter parameters for fall detection. Initially, it is required to identify the physical components involved in the falling procedure. Second, it is necessary to evaluate how these traits are separated from ADLs such as sitting and leaping; otherwise, the feature selection method will be significantly slowed down. Classification and identification based on DL are being used in fall detection systems that can automatically extract feature data. Due to this benefit, DL approaches have gained increasing popularity among the scientific community. They have been utilized in various fields where they have performed a part equal to that of human specialists. In principle, the stages required in DL approaches using sensor data from wearable devices are to preprocess the received signals, extract features from signal segments, and train a model using these features as input [16]. Thus, current studies in wearable sensor data fall risk assessment concentrate primarily on technical aspects that optimize performance. Various DL methods utilize the retrieved information as input to forecast the occurrence of falls. Klenk et al. [3] built a fall detection system based on long short-term memory (LSTM), which used a long-time sequence as input and extracted temporal features efficiently.
3 Fall Detection Approach
The sensor-based fall detection approach used in this investigation includes four main operational phases, as shown in Fig. 1: data acquisition, data pre-processing, data generation, model construction, and evaluation.
3.1 FallAllD Dataset
The FallAllD dataset [14] is a free public standard dataset for fall identification. Motion signal data was collected from 15 healthful people (age 21–53, height 158–187 cm, and weight 48–85 kg) using three types of equipment: an accelerometer, gyroscope, magnetometer, and barometer. The individuals wore the wearable devices on three distinct body locations (neck, wrist, and waist). In this dataset, 44 categories of ADL and 35 categories of falls were conducted.
Each information recorder has an inertial measurement unit, LSM9DS1, built for tracking movement. This module includes 1) a 3D accelerometer (a sampling rate 238 Hz and a broad dynamic scope of 8 g), 2) a 3D gyroscope (a sampling rate 238 Hz and a geometric proportion of 2000 DPS), and 3) a 3D magnetometer (a frequency response 80 Hz). In addition, a separate data recorder is integrated with an MS5607 barometric sensor with 10 Hz sampling rate.
3.2 Pre-processing of Data
Original sensor data of the accelerometer and gyroscope were processed by making the following adjustments. First, the median filter and a third-order low-pass Butterworth filter with a 20-Hz cutoff frequency were employed to reduce noise. Then, the Min-Max method was utilized to normalize the data. Segmentation of the pre-processed sensor data was conducted using fixed-width 1-second of sliding windows with a 50% overlapping, as shown in Fig. 2.
3.3 Hybrid Deep Residual Neural Network
DeepFall model, a hybrid deep residual neural network introduced in this paper, consists of two primary details. The first part is a convolutional block automatically extracting low-level characteristics from unprocessed movement inputs. The second method hierarchically recovers combination characteristics from a mixture of Spatio-temporal and channel-specific data using the residual block. This residual block contained Conv1D, BN, and ReLU layers, including a direct connection to LSTM, as seen in Fig. 3.
3.4 Interpretation Measurements
The effectiveness of the proposed DL model is evaluated using four standard evaluation metrics obtained during the 10-fold cross-validation process: accuracy, precision, recall, and F-measure. These four metrics can be calculated using the following formulas:
The four most often used KPIs for fall detection are listed above. The classification is considered true positive (TP) for the group under study, whereas, for all other groups, it is considered true negative (TN). When sensor data from one group is incorrectly assigned to another, this is called a false positive (FP). On the other hand, a false positive (FP) designation could occur if data from an activity sensor that belongs to a different group was wrongly labeled as belonging to that group.
4 Experimental Results
In the Google Colab-Pro+ system, every experiment in this research is conducted. We experiment to assess the recognition interpretation of the offered network and compare the model to benchmark DL algorithms in this study (CNN and LSTM). To assess the efficiency of the algorithm, we divided these laboratory experiments into three scenarios:
-
Scenario I: using movement signal data from neck-mounted wearable sensors,
-
Scenario II: using movement signal data from wrist-mounted wearable sensors,
-
Scenario III: using movement signal data from waist-mounted wearable sensors.
During experiments, movement signal data were acquired employing a 5-fold cross-validation methodology. Several tests were done to assess the identification effectiveness of various standard DL models (CNN and LSTM) and the suggested network. The precision and loss quantify the experimental findings, and F-measure is indicated in Table 1.
The proposed network obtained the maximum accuracy and F-measure in every scenario, according to the data. Incorporating an accuracy of 95.19% and an F-measure of 92.79%, the recommended network with movement signals from the waist position shows the most satisfactory performance.
5 Conclusion and Future Studies
Applying wearable sensors, we developed a hybrid DL model to address the fall detection challenge in this work effectively. The proposed DL method utilizes some of the benefits of residual blocks. In this study, we investigated the proposed DeepFall network using the FallAllD standard dataset for wearable sensors. Experimental findings revealed that the proposed network surpasses other models with the best accuracy (95.19%) and F-measure (92.79%).
Future research could also include evaluating the proposed DL model using a larger sample size of people with various fall circumstances. The efficacy might be significantly increased with the development of increasingly complex and compact DL networks and specific data representations based on time-frequency analysis.
References
Colón, L.N.V., DeLaHoz, Y., Labrador, M.: Human fall detection with smartphones. In: 2014 IEEE Latin-America Conference on Communications (LATINCOM), pp. 1–7 (2014). https://doi.org/10.1109/LATINCOM.2014.7041879
Hsieh, S.L., Yang, C.T., Li, H.J.: Combining wristband-type devices and smartphones to detect falls. In: 2017 IEEE International Conference on Systems, Man, and Cybernetics (SMC), pp. 2373–2377 (2017). https://doi.org/10.1109/SMC.2017.8122977
Klenk, J., et al.: The FARSEEING real-world fall repository: a large-scale collaborative database to collect and share sensor signals from real-world falls. Eur. Rev. Aging Phys. Act. 13, 8 (2016). https://doi.org/10.1186/s11556-016-0168-9
Mannini, A., Trojaniello, D., Cereatti, A., Sabatini, A.M.: A machine learning framework for gait classification using inertial sensors: application to elderly, post-stroke and huntington’s disease patients. Sensors 16(1), 134 (2016). https://doi.org/10.3390/s16010134
Martínez-Villaseñor, L., Ponce, H., Brieva, J., Moya-Albor, E., Núñez-Martínez, J., Peñafort-Asturiano, C.: UP-fall detection dataset: a multimodal approach. Sensors, 19(9) (2019). https://doi.org/10.3390/s19091988
Mekruksavanich, S., Hnoohom, N., Jitpattanakul, A.: A hybrid deep residual network for efficient transitional activity recognition based on wearable sensors. Appl. Sci. 12(10), 4988 (2022). https://doi.org/10.3390/app12104988
Mekruksavanich, S., Jantawong, P., Charoenphol, A., Jitpattanakul, A.: Fall detection from smart wearable sensors using deep convolutional neural network with squeeze-and-excitation module. In: 2021 25th International Computer Science and Engineering Conference (ICSEC), pp. 448–453 (2021). https://doi.org/10.1109/ICSEC53205.2021.9684626
Mekruksavanich, S., Jitpattanakul, A.: Deep learning approaches for continuous authentication based on activity patterns using mobile sensing. Sensors 21(22), 7519 (2021). https://doi.org/10.3390/s21227519
Mekruksavanich, S., Jitpattanakul, A.: CNN-based deep learning network for human activity recognition during physical exercise from accelerometer and photoplethysmographic sensors. In: Pandian, A.P., Fernando, X., Haoxiang, W. (eds.) Computer Networks, Big Data and IoT, pp. 531–542. Springer Nature Singapore, Singapore (2022). https://doi.org/10.1007/978-981-19-0898-9_42
Mekruksavanich, S., Jitpattanakul, A., Sitthithakerngkiet, K., Youplao, P., Yupapin, P.: ResNet-SE: channel attention-based deep residual network for complex activity recognition using wrist-worn wearable sensors. IEEE Access 10, 51142–51154 (2022). https://doi.org/10.1109/ACCESS.2022.3174124
Noppitak, S., Surinta, O.: dropcyclic: Snapshot ensemble convolutional neural network based on a new learning rate schedule for land use classification. IEEE Access 10, 60725–60737 (2022). https://doi.org/10.1109/ACCESS.2022.3180844
Pierleoni, P., et al.: A wearable fall detector for elderly people based on AHRS and barometric sensor. IEEE Sens. J. 16(17), 6733–6744 (2016). https://doi.org/10.1109/JSEN.2016.2585667
Sadreazami, H., Bolic, M., Rajan, S.: Fall detection using standoff radar-based sensing and deep convolutional neural network. IEEE Trans. Circuits Syst. II Express Briefs 67(1), 197–201 (2020). https://doi.org/10.1109/TCSII.2019.2904498
Saleh, M., Abbas, M., Le Jeannès, R.B.: FAllAllD: an open dataset of human falls and activities of daily living for classical and deep learning applications. IEEE Sens. J. 21(2), 1849–1858 (2021). https://doi.org/10.1109/JSEN.2020.3018335
Saleh, M., Jeannès, R.L.B.: Elderly fall detection using wearable sensors: a low cost highly accurate algorithm. IEEE Sens. J. 19(8), 3156–3164 (2019). https://doi.org/10.1109/JSEN.2019.2891128
Saleh, M., Jeannès, R.L.B.: FAllAllD: a comprehensive dataset of human falls and activities of daily living (2020). https://doi.org/10.21227/bnya-mn34
Shin, H.C., et al.: Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning. IEEE Trans. Med. Imaging 35(5), 1285–1298 (2016). https://doi.org/10.1109/TMI.2016.2528162
Tongyue, G., Jia, Y., Kaida, H., Qingxuan, H., Fengshou, Z.: Research and implementation of two-layer fall detection algorithm. In: 2018 5th International Conference on Systems and Informatics (ICSAI), pp. 70–74 (2018). https://doi.org/10.1109/ICSAI.2018.8599495
Tzeng, H.W., Chen, M.Y., Chen, J.Y.: Design of fall detection system with floor pressure and infrared image. In: 2010 International Conference on System Science and Engineering, pp. 131–135 (2010). https://doi.org/10.1109/ICSSE.2010.5551751
Vallabh, P., Malekian, R.: Fall detection monitoring systems: a comprehensive review. J. Ambient. Intell. Humaniz. Comput. 9, 1809–1833 (2018). https://doi.org/10.1007/s12652-017-0592-3
Yao, L., Yang, W., Huang, W.: A fall detection method based on a joint motion map using double convolutional neural networks. Multimedia Tools Appl. 1–18 (2020)
Acknowledgment
This research project was supported by the Thailand Science Research and Innovation fund; the University of Phayao (Grant No. FF65-RIM041); National Science, Research and Innovation (NSRF); and King Mongkut’s University of Technology North Bangkok with Contract No. KMUTNB-FF-66-07.
The authors also gratefully acknowledge the support provided by Thammasat University Research fund under the TSRI, Contract No. TUFF19/2564 and TUFF24/2565, for the project of “AI Ready City Networking in RUN”, based on the RUN Digital Cluster collaboration scheme.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Mekruksavanich, S., Jantawong, P., Hnoohom, N., Jitpattanakul, A. (2022). Wearable Fall Detection Based on Motion Signals Using Hybrid Deep Residual Neural Network. In: Surinta, O., Kam Fung Yuen, K. (eds) Multi-disciplinary Trends in Artificial Intelligence. MIWAI 2022. Lecture Notes in Computer Science(), vol 13651. Springer, Cham. https://doi.org/10.1007/978-3-031-20992-5_19
Download citation
DOI: https://doi.org/10.1007/978-3-031-20992-5_19
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-20991-8
Online ISBN: 978-3-031-20992-5
eBook Packages: Computer ScienceComputer Science (R0)