Rony Darazi

From Fall Detection to Fall Prevention: A Generic Classification of Fall-Related Systems

Falls are a major health problem for the frail community dwelling old people. For more than two decades, falls have been extensively investigated by medical institutions to mitigate their impact (e.g., lack of independence and fear of falling) and minimize their consequences (e.g., cost of hospitalization and so on). However, the problem of elderly falling does not only concern health-professionals but has also drawn the interest of the scientific community. In fact, falls have been the object of many research studies and the purpose of many commercial products from academia and industry. These studies have tackled the problem using fall detection approaches exhausting a variety of sensing methods. Lately, researcher has shifted their efforts to fall prevention where falls might be spotted before they even happen. Despite their restriction to clinical studies, early fall prediction systems have started to emerge. At the same time, current reviews in this field lack a common ground classification. In this context, the main contribution of this paper is to give a comprehensive overview on elderly falls and to propose a generic classification of fall-related systems based on their sensor deployment. An extensive research scheme from fall detection to fall prevention systems have also been conducted based on this common ground classification. Data processing techniques in both fall detection and fall prevention tracks are also highlighted. The objective of this paper is to deliver medical technologists in the field of public health a good position regarding fall-related systems.

Self-Adaptive Data Collection and Fusion for Health Monitoring Based on Body Sensor Networks

In the past few years, wireless body sensor networks (WBSNs) emerged as a low-cost solution for healthcare applications. In WBSNs, biosensors collect periodically physiological measurement and send them to the coordinator where the data fusion process takes place. However, processing the huge amount of data captured by the limited lifetime biosensors and taking the right decisions when there is an emergency are major challenges in WBSNs. In this paper, we introduce a biosensor data management framework, starting from data collection to decision making. First, we propose an adaptive data collection approach on the biosensor node level. This approach uses an early warning score system to optimize data transmission and estimates in real time the sensing frequency. Second, we present a data fusion model on the coordinator level using a decision matrix and fuzzy set theory. To evaluate our approach, we conducted multiple series of simulations on real sensor data. The results show that our approach reduces the amount of collected data, while maintaining data integrity. In addition, we show the impact of sampling and filtering data on the accuracy of the taken decisions and compare our data fusion approach with a basic decision tree algorithm.

Smart carpet using differential piezoresistive pressure sensors for elderly fall detection

Falls are events that affect almost every aging human being above the age of 65. These incidents can have major consequences on the physiological, psychological and socio-economical levels. In this paper, a simple smart carpet design is developed to detect falls using a novel sensing technique. Conventional sensing methods use either inertial measurement sensors (accelerometers, gyroscopes) or environmental sensors (infrared, force, vibration, acoustic, etc.). The proposed technique employs differential piezoresistive pressure sensors. The prototype of the system is implemented and tested using statistical methods. Experimental results show the sensitivity and the specificity of the system to be 88.8% and 94.9% respectively. The system could be deployed in home care environment as a final product. Our proposed sensing technique can be also integrated in beds to alert patients from falling during sleep.

Adaptive sampling algorithms with local emergency detection for energy saving in Wireless Body Sensor Networks

Nowadays, Wireless Body Sensor Networks (WBSN) are emerging as a low cost solution for healthcare application to find new solutions, regarding patient monitoring which is becoming the elusive requirement. Quicker emergency detection is the main purpose to create a quicker reaction and treatment if required, such as an abnormal variation of the respiration rate, which satisfies the goal of extending life expectancy. This process can help all the chronic patients who are most of the time living alone or in nursing homes. However, the limited lifetime bio-medical sensors bring on the energy consumption challenge as one of the leading challenges in WBSN. Moreover, detecting locally an emergency is also one of the main challenges in WBSN. In this paper, we propose an adaptive sampling approach, based on fisher test theory, that estimates and adapts the sensing frequency based on previous readings and the patient criticality. The main goal is to optimize the energy consumption. Furthermore, we show how emergency alerts can be supported locally on each node of the network. To validate the effectiveness of our approach we conducted several series of simulations and built a simple energy saving comparison.

Multisensor data fusion and decision support in wireless body sensor networks

Maintaining and improving the quality of life in ageing populations is a necessity. Hence, distant patient monitoring is a solution providing constant surveillance of vital signs and the detection of emergencies when they occur. In the past few years, wireless body sensor networks (WBSNs) emerged as a low cost solution for healthcare applications. In WBSNs, biosensors collect periodically physiological measures and send them to the coordinator where the data fusion process takes place. However, processing the huge amount of data captured by the limited lifetime biosensors and taking the right decisions when there is an emergency are major challenges in WBSNs. In this paper, we introduce a data fusion model using a decision matrix, an early warning score system and fuzzy set theory. We propose an algorithm at the coordinator level of the WBSN, aiming to take the appropriate decision when an emergency is detected.

Multisensor Data Fusion for Patient Risk Level Determination and Decision-support in Wireless Body Sensor Networks

Wireless Body Sensor Networks (WBSNs) are a low-cost solution for healthcare applications allowing continuous and remote monitoring. However, many challenges are addressed in WBSNs such as limited energy resources, early detection of emergencies and fusion of large amount of heterogeneous data in order to take decisions. In this paper, we propose a multisensor data fusion approach enabling one to determine the patient risk level based on vital signs scores. Consequently, a corresponding decision is taken routinely and each time an emergency is detected. This approach is based on early warning score systems, a fuzzy inference system and a technique determining the score of a vital sign given its past and current value. We evaluate our approach on real healthcare datasets.

Iterative time domain estimation of rapidly changing channel for OFDM systems in a cognitive radio context

Rapidly changing channels typically occurs in high speed situations where Doppler phenomena, related to the terminals high speed, affects the use of OFDM systems by producing a loss of orthogonality between different carriers. Thus, the channel estimation and equalisation become a challenging problem especially when the number of pilot carriers is limited. In this paper we make use of the cognitive abilities provided by cognitive radio systems in order to propose an iterative Time Domain Linear Minimum Mean Square Error (TD-LMMSE) estimation algorithm for rapidly changing channels in OFDM system. The TD-LMMSE emulates the effect of a sliding window, and iteratively remove the interference caused by the data field. Simulation results, showing a significant gain in terms of MSE and Bit Error Rate (BER) compared to other state of the art algorithms are reported over a wide Signal-to-Noise Ratio (SNR) range.

Multisensor guided walker for visually impaired elderly people

Assisted living for people with disabilities remains a current research challenge. Many systems have been developed to help disabled and frail people gain their self-sufficiency during their activities of daily living (ADL). In this article, we propose a new design concept to help visually impaired (VI) elderly patients move in their home environment. The system is made of a light-weight medical walker where sensory components and processing electronics are installed and operated. Behavioral and environmental information are collected using proper sensors mounted on walkers frame. Direction data are provided using audible notification. The system uses a hardware guiding technique based on ultrasonic and optical sensors for obstacle detection and accelerometer for fall and vibration detection. The algorithm developed for this purpose triggers an audible notification to alert the patient if there is an obstacle ahead. While many developed walkers are complex, expensive and require training to be used, our electronic walker gathers flexibility, reliability, ease of use and future expendability. Unlike other products, the electronic walker is also suitable for indoor and outdoor use. The results obtained after testing the system proved effectiveness. The use of low cost components makes our walker affordable as a final product.

Health risk assessment and decision-making for patient monitoring and decision-support using Wireless Body Sensor Networks

Abstract This paper proposes a generalized multi-sensor fusion approach and a health risk assessment and decision-making (Health-RAD) algorithm for continuous and remote patient monitoring purposes using a Wireless Body Sensor Network (WBSN). Health-RAD determines the patient’s health condition severity level routinely and each time a critical issue is detected based on vital signs scores. Hence, a continuous health assessment and a monitoring of the improvement or the deterioration of the state of the patient is ensured. The severity level is represented by a risk variable whose values range between 0 and 1. The higher the risk value, the more critical the patient’s health condition is and the more it requires medical attention. Moreover, we calculate the score of a vital sign using its past and current value, thus assessing its status based on its evolution during a period of time and not only on sudden deviations. We propose a generalized multi-sensor data fusion approach regardless of the number of monitored vital signs. The latter is employed by Health-RAD to find the severity level of the patient’s health condition based on his/her vital signs scores. It is based on a fuzzy inference system (FIS) and early warning score systems (EWS). This approach is tested with a previously proposed energy-efficient data collection approach, thus forming a complete framework. The proposed approach is evaluated on real healthcare datasets and the results are compared with another approach from the literature in terms of data reduction, energy consumption, risk assessment of vital signs, the patient’s health risk level determination and accuracy. The results show that both approaches have coherently assessed the health condition of different Intensive Care Unit (ICU) patients. Yet, our proposed approach overcomes the other approach in terms of energy consumption (around 86% less energy consumption) and data reduction (around 70% for sensing and more than 90% for transmission). Additionally, contrary to our proposed framework, the approach taken from the literature requires an offline model building and depends on available patient datasets.

Blind digital watermarking in PDF documents using Spread Transform Dither Modulation

In this paper, a blind digital watermarking scheme for Portable Document Format (PDF) documents is proposed. The proposed method is based on a variant Quantization Index Modulation (QIM) method called Spread Transform Dither Modulation (STDM). Each bit of the secret message is embedded into a group of characters, more specifically in their x-coordinate values. The method exhibits experiments of two opposite objectives: transparency and robustness, and is motivated to present an acceptable distortion value that shows sufficient robustness under high density noises attacks while preserving sufficient transparency.