Fall detection is a major problem in the healthcare department. Elderly people are more prone to fall than others. There are more than 50% of injury-related hospitalizations in people aged over 65. Commercial fall detection devices are expensive and charge a monthly fee for their services. A more affordable and adaptable system is necessary for retirement homes and clinics to build a smart city powered by IoT and artificial intelligence. An effective fall detection system would detect a fall and send an alarm to the appropriate authorities. We propose a framework that uses edge computing where instead of sending data to the cloud, wearable devices send data to a nearby edge device like a laptop or mobile device for real-time analysis. We use cheap wearable sensor devices from MbientLab, an open source streaming engine called Apache Flink for streaming data analytics, and a long short-term memory (LSTM) network model for fall classification. The model is trained using a published dataset called “MobiAct.” Using the trained model, we analyse optimal sampling rates, sensor placement, and multistream data correction. Our edge computing framework can perform real-time streaming data analytics to detect falls with an accuracy of 95.8%.
Detecting patterns in real time streaming data has been an interesting and challenging data analytics problem. With the proliferation of a variety of sensor devices, real-time analytics of data from the Internet of Things (IoT) to learn regular and irregular patterns has become an important machine learning problem to enable predictive analytics for automated notification and decision support. In this work, we address the problem of learning an irregular human activity pattern, fall, from streaming IoT data from wearable sensors. We present a deep neural network model for detecting fall based on accelerometer data giving 98.75 percent accuracy using an online physical activity monitoring dataset called “MobiAct”, which was published by Vavoulas et al. The initial model was developed using IBM Watson studio and then later transferred and deployed on IBM Cloud with the streaming analytics service supported by IBM Streams for monitoring real-time IoT data. We also present the systems architecture of the real-time fall detection framework that we intend to use with Mbientlab's wearable health monitoring sensors for real time patient monitoring at retirement homes or rehabilitation clinics.
Data analytics with unsupervised clustering of data streams has provided revolutionary breakthroughs in fields like healthcare, and E-commerce. IBM Streams and Apache Spark are among the most useful and popular data analytics tools that help engineers and researchers extend the abilities to store, analyze, transform, and visualize data for business use. IBM Streams is capable of ingesting, filtering, analyzing, and associating massive volumes of continuous data streams and the Streams Processing Language (SPL) enables coding custom stream graphs to process data and handle real-time events. Apache Spark has unified analytics edge for large scale data processing with high performance for both batch and streaming data. We developed adapters without using third party tools to facilitate data transfer between IBM Streams and Apache Spark to support new and legacy data analytic systems. An example use case would be IBM Streams ingesting and processing realtime data streams, and then passing the data to Spark to train or update machine learning algorithms in real time that can be re-deployed in the IBM Streams data processing pipeline. This paper provides an overview of the structure of the data processing pipeline, describes the implementation details and the principle behind the design.
In this data age, connected devices are continuously generating petabytes of images, text, and internet of things (IoT) sensor data. One approach to efficiently store this massive data is to extract the relevant and representative features and store only those features instead of the continuous streaming data. However, it raises a question as to the amount of information content we can retain from the data and if we can reconstruct the pseudo-original data when needed. By facilitating relevant and representative feature extraction, storage and reconstruction of near original pattern, we aim to address some of the challenges faced by the explosion of the streaming data. We present a preliminary study, where we explored multiple autoencoders for the concise feature extraction and reconstruction for human activity recognition (HAR) sensor data. Our Multi-Layer Perceptron (MLP) deep autoencoder achieved a storage reduction of 90.18%, where as convolutional autoencoder achieved 11.18%. For Long-Short Term Memory (LSTM) autoencoder the reduction was 91.47% and for convolutional LSTM autoencoder it was 72.35%. The storage reduction depended on the size and dimension of the concise representation. For higher dimensions of the representation, the storage reduction was low. But relevant information retention was high which was validated by the classification performed on the reconstructed data.
Efficient querying and retrieval of healthcare data is posing a critical challenge today with numerous connected devices continuously generating petabytes of images, text, and internet of things (IoT) sensor data. One approach to efficiently store the healthcare data is to extract the relevant and representative features and store only those features instead of the continuous streaming data. However, it raises a question as to the amount of information content we can retain from the data and if we can reconstruct the pseudo-original data when needed. By facilitating relevant and representative feature extraction, storage and reconstruction of near original pattern, we aim to address some of the challenges faced by the explosion of the streaming data. We present a preliminary study, where we explored multiple autoencoders for concise feature extraction and reconstruction for human activity recognition (HAR) sensor data. Our Multi-Layer Perceptron (MLP) deep autoencoder achieved a storage reduction of 90.18% compared to the three other implemented autoencoders namely convolutional autoencoder, Long-Short Term Memory (LSTM) autoencoder, and convolutional LSTM autoencoder which achieved storage reductions of 11.18%, 49.99%, and 72.35% respectively. Encoded features from the autoencoders have smaller size and dimensions which help to reduce the storage space. For higher dimensions of the representation, storage reduction was low. But retention of relevant information was high, which was validated by classification performed on the reconstructed data.