Automatic detection of cognitive impairment in elderly people using an entertainment chatbot with Natural Language Processing capabilities.

Previous researchers have proposed intelligent systems for therapeutic monitoring of cognitive impairments. However, most existing practical approaches for this purpose are based on manual tests. This raises issues such as excessive caretaking effort and the white-coat effect. To avoid these issues, we present an intelligent conversational system for entertaining elderly people with news of their interest that monitors cognitive impairment transparently. Automatic chatbot dialogue stages allow assessing content description skills and detecting cognitive impairment with Machine Learning algorithms. We create these dialogue flows automatically from updated news items using Natural Language Generation techniques. The system also infers the gold standard of the answers to the questions, so it can assess cognitive capabilities automatically by comparing these answers with the user responses. It employs a similarity metric with values in [0, 1], in increasing level of similarity. To evaluate the performance and usability of our approach, we have conducted field tests with a test group of 30 elderly people in the earliest stages of dementia, under the supervision of gerontologists. In the experiments, we have analysed the effect of stress and concentration in these users. Those without cognitive impairment performed up to five times better. In particular, the similarity metric varied between 0.03, for stressed and unfocused participants, and 0.36, for relaxed and focused users. Finally, we developed a Machine Learning algorithm based on textual analysis features for automatic cognitive impairment detection, which attained accuracy, F-measure and recall levels above 80%. We have thus validated the automatic approach to detect cognitive impairment in elderly people based on entertainment content. The results suggest that the solution has strong potential for long-term user-friendly therapeutic monitoring of elderly people.

Evaluation of Abstraction Capabilities and Detection of Discomfort with a Newscaster Chatbot for Entertaining Elderly Users.

We recently proposed a novel intelligent newscaster chatbot for digital inclusion. Its controlled dialogue stages (consisting of sequences of questions that are generated with hybrid Natural Language Generation techniques based on the content) support entertaining personalisation, where user interest is estimated by analysing the sentiment of his/her answers. A differential feature of our approach is its automatic and transparent monitoring of the abstraction skills of the target users. In this work we improve the chatbot by introducing enhanced monitoring metrics based on the distance of the user responses to an accurate characterisation of the news content. We then evaluate abstraction capabilities depending on user sentiment about the news and propose a Machine Learning model to detect users that experience discomfort with precision, recall, F1 and accuracy levels over 80%.

Wireless remote monitoring of toxic gases in shipbuilding.

Large-scale wireless sensor networks have not achieved market impact, so far. Nevertheless, this technology may be applied successfully to small-scale niche markets. Shipyards are hazardous working environments with many potential risks to worker safety. Toxic gases generated in soldering processes in enclosed spaces (e.g., cargo holds) are one such risk. The dynamic environment of a ship under construction makes it very difficult to plan gas detection fixed infrastructures connected to external monitoring stations via wired links. While portable devices with gas level indicators exist, they require workers to monitor measurements, often in situations where they are focused on other tasks for relatively long periods. In this work, we present a wireless multihop remote gas monitoring system for shipyard environments that has been tested in a real ship under construction. Using this system, we validate IEEE 802.15.4/Zigbee wireless networks as a suitable technology to connect gas detectors to control stations outside the ships. These networks have the added benefit that they reconfigure themselves dynamically in case of network failure or redeployment, for example when a relay is moved to a new location. Performance measurements include round trip time (which determines the alert response time for safety teams) and link quality indicator and packet error rate (which determine communication robustness).

Ambient intelligence systems for personalized sport training.

Several research programs are tackling the use of Wireless Sensor Networks (WSN) at specific fields, such as e-Health, e-Inclusion or e-Sport. This is the case of the project "Ambient Intelligence Systems Support for Athletes with Specific Profiles", which intends to assist athletes in their training. In this paper, the main developments and outcomes from this project are described. The architecture of the system comprises a WSN deployed in the training area which provides communication with athletes' mobile equipments, performs location tasks, and harvests environmental data (wind speed, temperature, etc.). Athletes are equipped with a monitoring unit which obtains data from their training (pulse, speed, etc.). Besides, a decision engine combines these real-time data together with static information about the training field, and from the athlete, to direct athletes' training to fulfill some specific goal. A prototype is presented in this work for a cross country running scenario, where the objective is to maintain the heart rate (HR) of the runner in a target range. For each track, the environmental conditions (temperature of the next track), the current athlete condition (HR), and the intrinsic difficulty of the track (slopes) influence the performance of the athlete. The decision engine, implemented by means of (m, s)-splines interpolation, estimates the future HR and selects the best track in each fork of the circuit. This method achieves a success ratio in the order of 80%. Indeed, results demonstrate that if environmental information is not take into account to derive training orders, the success ratio is reduced notably.

eIMRT: a web platform for the verification and optimization of radiation treatment plans.

The eIMRT platform is a remote distributed computing tool that provides users with Internet access to three different services: Monte Carlo optimization of treatment plans, CRT & IMRT treatment optimization, and a database of relevant radiation treatments/clinical cases. These services are accessible through a user-friendly and platform independent web page. Its flexible and scalable design focuses on providing the final users with services rather than a collection of software pieces. All input and output data (CT, contours, treatment plans and dose distributions) are handled using the DICOM format. The design, implementation, and support of the verification and optimization algorithms are hidden to the user. This allows a unified, robust handling of the software and hardware that enables these computation-intensive services. The eIMRT platform is currently hosted by the Galician Supercomputing Center (CESGA) and may be accessible upon request (there is a demo version at http://eimrt.cesga.es:8080/eIMRT2/demo; request access in http://eimrt.cesga.es/signup.html). This paper describes all aspects of the eIMRT algorithms in depth, its user interface, and its services. Due to the flexible design of the platform, it has numerous applications including the intercenter comparison of treatment planning, the quality assurance of radiation treatments, the design and implementation of new approaches to certain types of treatments, and the sharing of information on radiation treatment techniques. In addition, the web platform and software tools developed for treatment verification and optimization have a modular design that allows the user to extend them with new algorithms. This software is not a commercial product. It is the result of the collaborative effort of different public research institutions and is planned to be distributed as an open source project. In this way, it will be available to any user; new releases will be generated with the new implemented codes or upgrades.

Monte Carlo verification of IMRT treatment plans on grid.

The eIMRT project is producing new remote computational tools for helping radiotherapists to plan and deliver treatments. The first available tool will be the IMRT treatment verification using Monte Carlo, which is a computational expensive problem that can be executed remotely on a GRID. In this paper, the current implementation of this process using GRID and SOA technologies is presented, describing the remote execution environment and the client.

Remote radiotherapy planning: the eIMRT project.

In this paper, we present the eIMRT project which is currently carried out by diverse institutions in Galicia (Spain) and the USA. The eIMRT project will offer radiotherapists a set of algorithms to optimize and validate radiotherapy treatments, both CRT- and IMRT-based, hiding the complexity of the computer infrastructure needed to solve the problem using GRID technologies. The new platform is designed to be independent from the medical accelerator models, scalable and open. Having a web portal as client, it is designed in three layers using web services, which will allow users to access the platform directly from any front-end and client. It has three main components, namely remote characterization of linear accelerators for Monte Carlo and convolution/superposition (C/S) dose-calculation techniques, remote Grid-enabled radiotherapy treatment planning optimization and verification and data depository.

A parallel optimization approach for controlling allele diversity in conservation schemes.

We propose a novel method to control allelic diversity in conservation schemes based on an optimization problem, characterized by a convex program subject to integer linear constraints. Departing from previous studies considering similar problems, we implement a parallel simulated annealing algorithm to minimize the number of alleles lost across generations. The proposed algorithm shows excellent timing and minimization performances. Execution time decreases linearly with the number of processors used, providing similar results in all cases.