Advanced internet of things for personalised healthcare systems

Network localization and navigation (NLN) is a promising paradigm, in which mobile nodes exploit spatiotemporal cooperation, to provide reliable location information for a diverse range of wireless applications. This paper presents a theoretical foundation of NLN, including a mathematical formulation for NLN, an introduction of equivalent Fisher information analysis, and determination of the fundamental limits of localization accuracy. Key ingredients such as spatiotemporal cooperation, array signal processing, and map exploitation are then studied. We also develop a geometric interpretation to provide insights into the essence of NLN for network design. Finally, the paper highlights the connection between the theoretical foundation and algorithm development for NLN, guiding the design and operation of practical localization systems.

A Theoretical Foundation of Network Localization and Navigation

Human activity detection within smart homes is one of the basis of unobtrusive wellness monitoring of a rapidly aging population in developed countries. Most works in this area use the concept of "activity" as the building block with which to construct applications such as healthcare monitoring or ambient assisted living. The process of identifying a specific activity encompasses the selection of the appropriate set of sensors, the correct preprocessing of their provided raw data and the learning/reasoning using this information. If the selection of the sensors and the data processing methods are wrongly performed, the whole activity detection process may fail, leading to the consequent failure of the whole application. Related to this, the main contributions of this review are the following: first, we propose a classification of the main activities considered in smart home scenarios which are targeted to older people's independent living, as well as their characterization and formalized context representation; second, we perform a classification of sensors and data processing methods that are suitable for the detection of the aforementioned activities. Our aim is to help researchers and developers in these lower-level technical aspects that are nevertheless fundamental for the success of the complete application.

/pdf/the-elderly-s-independent-living-in-smart-homes-a-1o0uo8j5kg.pdf

The Elderly’s Independent Living in Smart Homes: A Characterization of Activities and Sensing Infrastructure Survey to Facilitate Services Development

Fall detection is an important public healthcare problem. Timely detection could enable instant delivery of medical service to the injured. A popular nonintrusive solution for fall detection is based on videos obtained through ambient camera, and the corresponding methods usually require a large dataset to train a classifier and are inclined to be influenced by the image quality. However, it is hard to collect fall data and instead simulated falls are recorded to construct the training dataset, which is restricted to limited quantity. To address these problems, a three-dimensional convolutional neural network (3-D CNN) based method for fall detection is developed, which only uses video kinematic data to train an automatic feature extractor and could circumvent the requirement for large fall dataset of deep learning solution. 2-D CNN could only encode spatial information, and the employed 3-D convolution could extract motion feature from temporal sequence, which is important for fall detection. To further locate the region of interest in each frame, a long short-term memory (LSTM) based spatial visual attention scheme is incorporated. Sports dataset Sports-1 M with no fall examples is employed to train the 3-D CNN, which is then combined with LSTM to train a classifier with fall dataset. Experiments have verified the proposed scheme on fall detection benchmark with high accuracy as 100%. Superior performance has also been obtained on other activity databases.

Deep Learning for Fall Detection: Three-Dimensional CNN Combined With LSTM on Video Kinematic Data

Falls and fall-related injuries are major incidents, especially for elderly people, which often mark the onset of major deterioration of health. More than one-third of home-dwelling people aged 65 or above and two-thirds of those in residential care fall once or more each year. Reliable fall detection, as well as prevention, is an important research topic for monitoring elderly living alone in residential or hospital units. The aim of this study is to review the existing fall detection systems and some of the key research challenges faced by the research community in this field. We categorize the existing platforms into two groups: wearable and ambient devices; the classification methods are divided into rule-based and machine learning techniques. The relative merit and potential drawbacks are discussed, and we also outline some of the outstanding research challenges that emerging new platforms need to address.

/pdf/automatic-fall-monitoring-a-review-5jihhisvq7.pdf

Automatic Fall Monitoring: A Review

We propose in this paper a novel algorithm as well as architecture for the fall accident detection and corresponding wide area rescue system based on a smart phone and the third generation (3G) networks. To realize the fall detection algorithm, the angles acquired by the electronic compass (ecompass) and the waveform sequence of the triaxial accelerometer on the smart phone are used as the system inputs. The acquired signals are then used to generate an ordered feature sequence and then examined in a sequential manner by the proposed cascade classifier for recognition purpose. Once the corresponding feature is verified by the classifier at current state, it can proceed to next state; otherwise, the system will reset to the initial state and wait for the appearance of another feature sequence. Once a fall accident event is detected, the user's position can be acquired by the global positioning system (GPS) or the assisted GPS, and sent to the rescue center via the 3G communication network so that the user can get medical help immediately. With the proposed cascaded classification architecture, the computational burden and power consumption issue on the smart phone system can be alleviated. Moreover, as we will see in the experiment that a distinguished fall accident detection accuracy up to 92% on the sensitivity and 99.75% on the specificity can be obtained when a set of 450 test actions in nine different kinds of activities are estimated by using the proposed cascaded classifier, which justifies the superiority of the proposed algorithm.

A Smart Phone-Based Pocket Fall Accident Detection, Positioning, and Rescue System

In this paper, a wireless hand gesture recognition glove is proposed for real-time translation of Taiwanese sign language. To discriminate between different hand gestures, we have flex and inertial sensors embedded into the glove so that the three most important parameters, i.e., the posture of fingers, orientation of the palm, and motion of the hand, defined in Taiwanese Sign Language can be recognized without ambiguity. The finger flexion postures acquired by flex sensors, the palm orientation acquired by G-sensor, and the motion trajectory acquired by gyroscope are used as the input signals of the proposed system. The input signals will be acquired and examined periodically to see if it is a legal sign language gesture or not. Once the sampled signal can last longer than a predefined clock cycles, it is regarded as a valid gesture and will be sent to cell phone via Bluetooth for gesture discrimination and speech translation. With the proposed architecture and algorithm, the accuracy for gesture recognition is quite satisfactory. As we can see in experiments that an accuracy rate up to 94% on sensitivity for gesture recognition can be achieved which justifies the superiority of the proposed architecture.

A real-time portable sign language translation system

Many coding methods are more efficient with some images than others. In particular, run-length coding is very useful for coding areas of little changes. Adaptive predictive coding achieves high coding efficiency for fast changing areas like edges. In this paper, we propose a switching coding scheme that will combine the advantages of both run-length and adaptive linear predictive coding. For pixels in slowly varying areas, run-length coding is used; otherwise least-squares (LS)-adaptive predictive coding is used. Instead of performing LS adaptation in a pixel-by-pixel manner, we adapt the predictor coefficients only when an edge is detected so that the computational complexity can be significantly reduced. For this, we use a simple yet effective edge detector using only causal pixels. This way, the proposed system can look ahead to determine if the coding pixel is around an edge and initiate the LS adaptation in advance to prevent the occurrence of a large prediction error. With the proposed switching structure, very good prediction results can be obtained in both slowly varying areas and pixels around boundaries. Furthermore, only causal pixels are used for estimating the coding pixels in the proposed encoder; no additional side information needs to be transmitted. Extensive experiments as well as comparisons to existing state-of-the-art predictors and coders will be given to demonstrate its usefulness.

https://ir.nctu.edu.tw:443/bitstream/11536/10597/1/000248063900011.pdf

Least-Squares-Based Switching Structure for Lossless Image Coding

In predictive image coding, the least squares (LS)-based adaptive predictor is noted as an efficient method to improve prediction result around edges. However pixel-by-pixel optimization of the predictor coefficients leads to a high coding complexity. To reduce computational complexity, we activate the LS optimization process only when the coding pixel is around an edge or when the prediction error is large. We propose a simple yet effective edge detector using only causal pixels. The system can look ahead to determine if the coding pixel is around an edge and initiate the LS adaptation to prevent the occurrence of a large prediction error. Our experiments show that the proposed approach can achieve a noticeable reduction in complexity with only a minor degradation in the prediction results.

https://ir.nctu.edu.tw:443/bitstream/11536/13081/1/000233381700009.pdf

Lih-Jen Kau

Papers

A Smart Phone-Based Pocket Fall Accident Detection, Positioning, and Rescue System

A real-time portable sign language translation system

Least-Squares-Based Switching Structure for Lossless Image Coding

Adaptive lossless image coding using least squares optimization with edge-look-ahead

Muscle Fibers Inspired Electrospun Nanostructures Reinforced Conductive Fibers for Smart Wearable Optoelectronics and Energy Generators