An Intelligent System Avoids Forgetting Things

A team of researchers from the University of Granada (UGR) has created a system with Artificial Intelligence techniques which notifies elderly people or people with special needs of the forgetting of certain everyday tasks. This system uses sensors distributed in the environment in order to detect their actions and mobile devices which remind them, for example, to take their keys before they leave home.

An elderly lady is about to go to bed. She goes into her room, sits down on the bed, takes off her slippers and turns off the light. Suddenly, before getting into bed, a small alarm goes off and a mobile device reminds her that she has not taken her tablets.

This is how the new intelligent system developed by researchers from the Department of Computer Science and Artificial Intelligence of the UGR works. María Ros Izquierdo is from the Higher Technical School of Computer Engineering of the UGR and the co-author of a study which is published this month in the Expert Systems with Applications magazine . «It is a prototype which, in a non-intrusive manner, facilitates the control of the activity of people with special needs and increases their independence», she explained to SINC.

The system recognizes the everyday actions of the users by means of RFID (Radio Frequency Identification) labels. These labels are discreetly placed on the objects that the individuals touch most often, in such a way that, when they do so, a signal is sent to a computer or mobile device situated in the house itself or at an assistance centre some distance away.

The activities of the people are assessed with Artificial Intelligence techniques (data mining and formal grammar) in order to compile a list of actions such as remembering to take the keys or the mobile phone before leaving home. «It is not necessary to use cameras or microphones, and the devices which are used do not entail any technological complications for users, nor do they modify their daily routines», clarified Ros.

In order to evaluate the system, the scientists have designed a Tagged World, an intelligent space which simulates the rooms of a house, with sensors embedded in the environment which help to recognize the behavior of its occupants. The researchers monitored each user so as to obtain an individualized database. They later verified with a test the reliability of the system and the degree of intrusion felt by the participants.

«The system does not modify the life of the users, but does positively modify that of the people who look after them», indicated Ros, who recalled that elderly people or those with special needs often reject the aid of others and demand more independence. The new system may help to achieve this objective.
Descargar

Small Rodents Encourage The Formation Of Scrubland

After two years of research over five degraded landscapes in the National Park of Sierra Nevada (Granada), scientists have established for the first time that field mice base their diet on holm oak and pine seeds, causing a deterioration of the habitats and an extension of scrubland in the forests.

The trees in the forests such as the holm oaks, rowans and pines have unexpected predators which are impeding their expansion over the mountains. In 98.5% of cases it is field mice and other rodents which eat a large proportion of the seeds which have been scattered before they are able to germinate.

Luis Matías is the main author of the work and a researcher for the Land Ecology Research Group at the University of Granada. «If the choice of the seeds they eat is not random, in other words, they eat the seeds of a determined species more often, this will be reflected in a greater emergence of seedlings among those species which are eaten less, which could alter the structure of the plant community», he told SINC.

Between 2004 and 2005, the research team exposed the seeds of six species to the predators and analyzed the numbers which were eaten . «Some species were ravaged much more than others, and this selection pattern was maintained in the different habitats throughout the two years of study», explained Matías.

The new research, recently published in Plant Ecology, shows that this phenomenon is constant in time and in the different landscapes and habitats. In this sense, according to the researchers, «the species which undergo the highest rate of depredation are the dominant arboreal species (the pine, holm oak and rowan), while the scrubland species suffer much less consumption».

Pine and holm oak seeds, the favorite food

The rodents prefer the seeds from the holm oak, quercus ilex, of which a total of 77.4% are eaten, the pine, pinus sylvestris, (73.3%), and the rowan, sorbus aria, (69.2%). The mice prefer the seeds of these particular trees to those of the scrubland owing to their components, as those from the holm oak contain a high percentage of lipids.

As a result of eating fewer scrubland seeds, the rodents encourage the formation of a plant structure dominated by scrubland. «Curiously, it is the scrubland where the rodents are most abundant, as they find food and shelter from their predators there», the scientist clarified. In other words, the seed predators favour the habitat which is most propitious for them.

However, the scientists conclude that longer experiments are required because «the uses of the soil and the selection of food by the rodents may vary from year to year, depending on the availability of food resources, the abundance of rodents and their predators and the climatic conditions».
Descargar