Gabriele Civitarese

Fine-grained recognition of abnormal behaviors for early detection of mild cognitive impairment

According to the World Health Organization, the rate of people aged 60 or more is growing faster than any other age group in almost every country, and this trend is not going to change in a near future. Since senior citizens are at high risk of non communicable diseases requiring long-term care, this trend will challenge the sustainability of the entire health system. Pervasive computing can provide innovative methods and tools for early detecting the onset of health issues. In this paper we propose a novel method relying on medical models, provided by cognitive neuroscience researchers, describing abnormal activity routines that may indicate the onset of early symptoms of mild cognitive impairment. A non-intrusive sensor-based infrastructure acquires low-level data about the interaction of the individual with home appliances and furniture, as well as data from environmental sensors. Based on those data, a novel hybrid statistical-symbolical technique is used to detect first the activities being performed and then the abnormal aspects in carrying out those activities, which are communicated to the medical center. Differently from related works, our method can detect abnormal behaviors at a fine-grained level, thus providing an important tool to support the medical diagnosis. In order to evaluate our method we have developed a prototype of the system and acquired a large dataset of abnormal behaviors carried out in an instrumented smart home. Experimental results show that our technique has a high precision while generating a small number of false positives.

SmartFABER: Recognizing fine-grained abnormal behaviors for early detection of mild cognitive impairment

OBJECTIVE In an ageing world population more citizens are at risk of cognitive impairment, with negative consequences on their ability of independent living, quality of life and sustainability of healthcare systems. Cognitive neuroscience researchers have identified behavioral anomalies that are significant indicators of cognitive decline. A general goal is the design of innovative methods and tools for continuously monitoring the functional abilities of the seniors at risk and reporting the behavioral anomalies to the clinicians. SmartFABER is a pervasive system targeting this objective. METHODS A non-intrusive sensor network continuously acquires data about the interaction of the senior with the home environment during daily activities. A novel hybrid statistical and knowledge-based technique is used to analyses this data and detect the behavioral anomalies, whose history is presented through a dashboard to the clinicians. Differently from related works, SmartFABER can detect abnormal behaviors at a fine-grained level. RESULTS We have fully implemented the system and evaluated it using real datasets, partly generated by performing activities in a smart home laboratory, and partly acquired during several months of monitoring of the instrumented home of a senior diagnosed with MCI. Experimental results, including comparisons with other activity recognition techniques, show the effectiveness of SmartFABER in terms of recognition rates.

From lab to life: Fine-grained behavior monitoring in the elderly's home

Sensor-based activity monitoring systems promise to prolong independent living of frail elderly people, including those affected by cognitive disorders. Different solutions are already available on the market, which use wireless sensors installed in the home to track the daily living routines of the senior. Those systems provide caregivers with statistics about detected activities; some of them may trigger real-time notifications when they identify a risk situation. Long-term monitoring of finegrained behavioral anomalies can be an important tool to support the diagnosis of neurodegenerative diseases. However, current commercial systems can only monitor high-level activity routines. For this reason, in a previous work we devised a novel method to recognize fine-grained abnormal behaviors of elderly people at home based on sensor data. Experiments in the lab showed the effectiveness of that method. In this paper we present our experience about the implementation of the system in the home of an elderly person with diagnosis of mild cognitive impairment. After illustrating the current implementation, we discuss preliminary results and outline research directions. In particular, a preliminary clinicians assessment indicates the potential utility of this system to support the diagnosis, and the benefits that would be gained by extending the system to monitor additional parameters, including neurovegetative aspects and motor behavior. We also discuss directions for addressing the encountered technological issues, for improving our reasoning algorithms with more extensive support of uncertainty, and for “closing the loop” by making the senior an active part of the system.

Let the objects tell what you are doing

Recognition of activities of daily living (ADLs) performed in smart homes proved to be very effective when the interaction of the inhabitant with household items is considered. Analyzing how objects are manipulated can be particularly useful, in combination with other sensor data, to detect anomalies in performing ADLs, and hence to support early diagnosis of cognitive impairments for elderly people. Recent improvements in sensing technologies can overcome several limitations of the existing techniques to detect object manipulations, often based on RFID, wearable sensors and/or computer vision methods. In this work we propose an unobtrusive solution which shifts all the monitoring burden at the objects side. In particular, we investigate the effectiveness of using tiny BLE beacons equipped with accelerometer and temperature sensors attached to everyday objects. We adopt statistical methods to analyze in realtime the accelerometer data coming from the objects, with the purpose of detecting specific manipulations performed by seniors in their homes. We describe our technique and we present the preliminary results obtained by evaluating the method on a real dataset. The results indicate the potential utility of the method in enriching ADLs and abnormal behaviors recognition systems, by providing detailed information about object manipulations.

Monitoring objects manipulations to detect abnormal behaviors

With a growing population of elderly people the number of subjects at risk of cognitive disorders is rapidly increasing. Many research groups are studying pervasive solutions to continuously and unobtrusively monitor fragile subjects at their homes, reducing health-care costs and supporting medical diagnosis. Among the several behavioral aspects which clinicians are interested in monitoring, anomalous behaviors while performing activities of daily living are of great importance. In this work, we aim at improving the state of the art on this topic by enabling the recognition of fine-grained anomalies by detecting specific object manipulations. We attach tiny Bluetooth Low Energy accelerometers to several household objects in order to detect which manipulations are performed by the inhabitant on which object. Detected manipulations, combined with data from other environmental sensors deployed in the home, are used to infer ADLs and fine-grained abnormal behaviors. Preliminary results on a dataset with hundreds of complex activities captured in a smarthome environment show the effectiveness of the proposed method.

Behavioral monitoring in smart-home environments for health-care applications

Although the method discussed in this work already obtained promising results, we plan to extend it in several directions. First of all, anomaly recognition relies on a too rigid formalisms which is not able to capture the intrinsic noise of sensor measurements. Moreover, semi-supervised ADLs recognition techniques (e.g., active learning) will be evaluated in order to better adapt the model to different users and environments. Last but not least, we aim to improve our algorithms in order to support parallel activities and multi-inhabitants scenarios.

Analysis of long-term abnormal behaviors for early detection of cognitive decline

Several researchers have proposed methods and designed systems for the automatic recognition of activities and abnormal behaviors with the goal of early detecting cognitive impairment. In this paper, we propose LOTAR, a hybrid behavioral analysis system coupling state of the art machine learning techniques with knowledge-based and data mining methods. Medical models designed in collaboration with cognitive neuroscience researchers guide the recognition of short- and long-term abnormal behaviors. In particular, we focus on historical behavior analysis for long-term anomaly detection, which is the principal novelty with respect to our previous works. We present preliminary results obtained by evaluating the method on a dataset acquired during three months of experimentation in a real patients home. Results indicate the potential utility of the system for long-term monitoring of cognitive health.

Demo abstract: Demonstration of the FABER system for fine-grained recognition of abnormal behaviors

The life expectancy is rapidly growing in many countries. According to the United Nations, the percentage of elderly population will rise from 5% in 2013 to 11% in 2050. The increasing aging of the population implies an increase of age-related diseases, and an increase in terms of health-care costs. The innovations introduced by pervasive computing, and in particular by sensor-based activity monitoring methods, can be exploited to early detect the onset of health issues. For this reason, we devised a novel method to recognize anomalies that a senior performs during the execution of activities of daily living, based on data acquired from unobtrusive sensors deployed at home. The objective is to support the clinicians in the early diagnosis of neurodegenerative diseases, providing them with fine-grained information about abnormal behaviors. In this paper, we present a demonstration of the method, based on a graphical tool that simulates the execution of activities and abnormal behaviors of an elderly person in a sensor-rich smart home.