Existing Vertical FL (VFL) methods often struggle with realistic and unaligned data partitions, and incur into high communication costs and significant operational complexity. This work introduces a novel approach to VFL, Active Participant Centric VFL (APC-VFL), that excels in scenarios where data samples among participants are partially aligned at training. Among its strengths, APC-VFL only requires a single communication step with the active participant. This is made possible through a local and unsupervised representation learning stage at each participant followed by a knowledge distillation step in the active participant. Compared to other VFL methods such as SplitNN or VFedTrans, APC-VFL consistently outperforms them across three popular VFL datasets in terms of F1, accuracy and communication costs as the ratio of aligned data is reduced.

Non-motor manifestations of Parkinson’s disease (PD) appear early and have a significant impact on the quality of life of patients, but few studies have evaluated their predictive potential with machine learning algorithms. We evaluated 9 algorithms for discriminating PD patients from controls using a wide collection of non-motor clinical PD features from two databases: Biocruces (96 subjects) and PPMI (687 subjects). In addition, we evaluated whether the combination of both databases could improve the individual results. For each database 2 versions with different granularity were created and a feature selection process was performed. We observed that most of the algorithms were able to detect PD patients with high accuracy (>80%). Support Vector Machine and Multi-Layer Perceptron obtained the best performance, with an accuracy of 86.3% and 84.7%, respectively. Likewise, feature selection led to a significant reduction in the number of variables and to better performance. Besides, the enrichment of Biocruces database with data from PPMI moderately benefited the performance of the classification algorithms, especially the recall and to a lesser extent the accuracy, while the precision worsened slightly. The use of interpretable rules obtained by the RIPPER algorithm showed that simply using two variables (autonomic manifestations and olfactory dysfunction), it was possible to achieve an accuracy of 84.4%. Our study demonstrates that the analysis of non-motor parameters of PD through machine learning techniques can detect PD patients with high accuracy and recall, and allows us to select the most discriminative non-motor variables to create potential tools for PD screening.

Nowadays the importance of digital competences is unarguable, and specially for people with functional diversity. On the other hand, the website should adapt to the user necessities automatically. This work focuses on the latter, in detecting navigation problems automatically. Firstly, the device used by the user will be detected by proposing two level hierarchy of supervised classifiers that divides in different levels errors of different criticality. Afterwards, in order to detect problems automatically, clustering algorithms and anomaly detection have been used, finding for each device a set of potential problems' indicators automatically. Moreover, the effect of cursor's adaptions in different problems has been analyzed.

Osasun-arlorako softwarean, beste esparru askotan bezala, erabilgarritasuna erronka handia da; batetik, datuak ugariak eta konplexuak direlako eta, bestetik, erabilera-testuingurua kritikoa delako. Jakina da langile klinikoek informazio kopuru egokia eskatzen dutela beren zereginak aurrera eramateko, eta, zentzu horretan, erabiltzaile-interfaze moldagarriak oso baliagarriak izan daitezke informazio-behar horiek asetzeko nahiz informazio-gainkargaren arazoari heltzeko. Erabiltzaile-interfazerako egokitzapenak inplementatu aurretik, baina, aldakorrak diren informazio-behar horiek identifikatu eta lehenetsi egin behar dira. Begi-arakatzaileak lagungarriak izan daitezke zeregin hauek erdiesteko, erabiltzaileen portaera bisuala antzeman baitezakete, zeina interesaren adierazle den. Zoritxarrez, arakatzaile horiek sistema hedatu batean erabiltzeak azpiegitura konplexuegia eskatzen du. Ekarpen honetan aztertu dugu ea erabiltzaileen portaera bisuala inferi ote daitekeen erabiltzaile horiek botiken segurtasunari lotutako arbel batean izandako elkarrekintzaren datuetatik abiatuz. Emaitzek aditzera eman dute bi alderdiak, hots, saguaren bidezko elkarrekintza eta portaera bisuala (karga kognitiboa), lotuta daudela; ezaugarri hauen arabera neurtuak, hurrenez hurren: saguaren ondoz ondoko bi kliken arteko denbora-tarteak eta sagu-pausatzeak, batetik, eta, bestetik, begiradaren finkapenaren iraupenak. Lanak eztabaidatzen du zer eragin izan dezakeen aurkikuntza horrek arbel medikoen egokitzapenen diseinuan.

Usability is a big challenge for medical software, on one side because data are of large size and complex and on the other because the context of use is critical. We know that clinicians call for the right amount and to this regard, adaptive user interfaces can help not only identifying these information needs but also alleviating the data overload. However, before implementing user interface adaptations, these particular information demands have to be identified and prioritised. Eye-trackers can help accomplishing such tasks, since they can gather the visual behaviour of users, which depict interest, but using them in a deployed system requires a complex infraestructure. In this contribution, we analyse whether visual behaviour of users on a medication safety dashboard can be inferred from their interaction data. The results show that the use of the mouse interaction and visual behaviour (cognitive load) are some-how connected, measured in terms of the following features respectively: dwell time and mouse hovers between two consecutive clicks, and duration of gaze fixations. The article discusses the significance of this statement for the design of adaptations in medical dashboards.

Objective: To characterise the use of an electronic medication safety dashboard by exploring and contrasting interactions from primary users (i.e. pharmacists) who were leading the intervention and secondary users (i.e. non-pharmacist staff) who used the dashboard to engage in safe prescribing practices. Materials and methods: We conducted a 10-month observational study in which 35 health professionals used an instrumented medication safety dashboard for audit and feedback purposes in clinical practice as part of a wider intervention study. We modelled user interaction by computing features representing exploration and dwell time through user interface events that were logged on a remote database. We applied supervised learning algorithms to classify primary against secondary users. Results: We observed values for accuracy above 0.8, indicating that 80% of the time we were able to distinguish a primary user from a secondary user. In particular, the Multilayer Perceptron (MLP) yielded the highest values of precision (0.88), recall (0.86) and F-measure (0.86). The behaviour of primary users was distinctive in that they spent less time between mouse clicks (lower dwell time) on the screens showing the overview of the practice and trends. Secondary users exhibited a higher dwell time and more visual search activity (higher exploration) on the screens displaying patients at risk and visualisations. Discussion and conclusion: We were able to distinguish the interactive behaviour of primary and secondary users of a medication safety dashboard in primary care using timestamped mouse events. Primary users were more competent on population health monitoring activities, while secondary users struggled on activities involving a detailed breakdown of the safety of patients. Informed by these findings, we propose workflows that group these activities and adaptive nudges to increase user engagement.

This work analyses the navigation in the enrolment web information area of the University of the Basque Country. A complete data mining process shows that successful and failure navigation behaviors can be modeled using machine learning techniques. Unsupervised learning algorithms have been applied on two different domains: URLs visited by the users in each session (navigation sequence) and some interaction parameters extracted from the recorded click-stream (navigation style). Both domains have been used satisfactorily to model the behavior of success and failure navigation sessions achieving more than 78% of accuracy predicting success or failure sessions. Furthermore, the clustering based on the navigation style was able to identify the main characteristics of each type of session and to build a subsystem that enables to detect failure type sessions with high precision.

(its size and complexity) and its context of use. This results in user interfaces with a high-density of data that do not support optimal decision-making by clinicians. Anecdotal evidence indicates that clinicians demand the right amount of information to carry out their tasks. This suggests that adaptive user interfaces could be employed in order to cater for the information needs of the users and tackle information overload. Yet, since these information needs may vary, it is necessary first to identify and prioritise them, before implementing adaptations to the user interface. As gaze has long been known to be an indicator of interest, eye tracking allows us to unobtrusively observe where the users are looking, but it is not practical to use in a deployed system. Here, we address the question of whether we can infer visual behaviour on a medication safety dashboard through user interaction data. Our findings suggest that, there is indeed a relationship between the use of the mouse (in terms of clickstreams and mouse hovers) and visual behaviour in terms of cognitive load. We discuss the implications of this finding for the design of adaptive medical dashboards.

The reduction of energy consumption in buildings is one of the goals to improve energy efficiency. One way to achieve energy savings in buildings is to develop intelligent control strategies for heating systems that are able to reduce power consumption without affecting the thermal comfort. An intelligent control system must be able to predict the temperature of the building in order to manage the heating system. In this paper, we present a rule-based model that is able to predict the indoor temperature for different values of k (hours ahead in time). The model has been learned with FRULER, a genetic fuzzy system that generates accurate and simple knowledge bases. Our approach has been validated with real data from a residential college.

The dramatic increase in the amount of information stored on the web makes it more important to familiarize people with disabilities and elderly people with digital devices and applications and to adapt websites to enable their use by these users. D iscapnet is a website mainly aimed at visually disabled people, and navigation is a challenging task for its users. In this context, system evaluation and problem detection become crucial aspects for enhancing user experience and may contribute greatly to diminishing the existing technological gap. This study proposes a system based on web-mining techniques that collects in-use information while the user is accessing the web (thus, being a noninvasive system). The proposed system models users in the wild and discovers navigation problems appearing in Discapnet and can also be used for problem detection when new users are navigating the site. The system was tested and its efficiency demonstrated in an experiment involving navigation under supervision, in which 82.6% of a set of disabled people were automatically labeled as having problems with the website.

The dramatic increase in the amount of information stored on the web makes it more important to familiarize people with disabilities and elderly people with digital devices and applications and to adapt websites to enable their use by these users. Discapnet is a website mainly aimed at visually disabled people, and navigation is a challenging task for its users. In this context, system evaluation and problem detection become crucial aspects for enhancing user experience and may contribute greatly to diminishing the existing technological gap. This study proposes a system based on web‐mining techniques that collects in‐use information while the user is accessing the web (thus, being a noninvasive system). The proposed system models users in the wild and discovers navigation problems appearing in Discapnet and can also be used for problem detection when new users are navigating the site. The system was tested and its efficiency demonstrated in an experiment involving navigation under supervision, in which 82.6% of a set of disabled people were automatically labeled as having problems with the website.

In this work, we improved the link prediction part of a web mining system developed for a tourism website (Bidasoa Turismo, BTw). First, we replaced the PAM clustering algorithm used in the profiling part of the system with the adaptation of other system, SEP/COP, which is based on a hierarchical clustering algorithm and is able to automatically adjust to the number of clusters required. Secondly, we modified the implementation of the exploitation part, i.e. the use of these profiles for link prediction, so that it adapts better to the system. Thirdly, we applied both systems, the original and the improved one, to another environment called Discapnet which is a website aimed at people with disabilities. Values of the calculated performance metrics confirm the improvement of the system and its generality for different environments.

Web personalization becomes essential in industries and specially for the case of users with special needs such as visually impaired people. Adaptation may very much speed up the navigation of visually impaired people and contribute to diminish the existing technological gap. This work is the first stage of a web mining process carried out in discapnet: a website created to promote the social and work integration of people with disabilities where slow navigation has been detected. Based on observation in-use where behaviours emerge applying a web mining process to server log data, we designed a system to generate user navigation profiles and adapt to the web site through link prediction. Two approaches for user profiling were implemented: a global system built based on the complete database and a modular approach carried out discovering the navigation profiles within different zones. Although both approaches are effective, the modular approach outperforms. When 25% of the navigation of the new user has happened the designed system is able to propose a set of links where nearly 60% of them (2 out of 3) is among the ones the new user will be using in the future. This will definitely make the navigation easier saving a lot of time.

Websites are important tools for tourism destinations. The information acquired from the use of tourism websites can be very useful for the travel agents. It will provide insight about the users’ preferences, requirements and habits that are very useful for marketing campaigns or website redesign. Using machine learning techniques to build user profiles allows taking into account their real preferences. This paper presents a navigation-log based web application to profile users accessing the web of Bidasoa Turismo. The profiles are built based on the combination of web usage information stored in web log files and web content information to obtain more comprehensible profiles. The experiments show that we are able to find specific user profiles.

The validation of the results obtained by clustering algorithms is a fundamental part of the clustering process. The most used approaches for cluster validation are based on internal cluster validity indices. Although many indices have been proposed, there is no recent extensive comparative study of their performance. In this paper we show the results of an experimental work that compares 30 cluster validity indices in many different environments with different characteristics. These results can serve as a guideline for selecting the most suitable index for each possible application and provide a deep insight into the performance differences between the currently available indices.

The tourism industry has experienced a shift from offline to online travellers and this has made the use of intelligent systems in the tourism sector crucial. These information systems should provide tourism consumers and service providers with the most relevant information, more decision support, greater mobility and the most enjoyable travel experiences. As a consequence, Destination Marketing Organizations (DMOs) not only have to respond by adopting new technologies, but also by interpreting and using the knowledge created by the use of these techniques. This work presents the design of a general and non-invasive web mining system, built using the minimum information stored in a web server (the content of the website and the information from the log files stored in Common Log Format (CLF)) and its application to the Bidasoa Turismo (BTw) website. The proposed system combines web usage and content mining techniques with the three following main objectives: generating user navigation profiles to be used for link prediction; enriching the profiles with semantic information to diversify them, which provides the DMO with a tool to introduce links that will match the users taste; and moreover, obtaining global and language-dependent user interest profiles, which provides the DMO staff with important information for future web designs, and allows them to design future marketing campaigns for specific targets. The system performed successfully, obtaining profiles which fit in more than 60% of cases with the real user navigation sequences and in more than 90% of cases with the user interests. Moreover the automatically extracted semantic structure of the website and the interest profiles were validated by the BTw DMO staff, who found the knowledge provided to be very useful for the future. (C) 2013 Elsevier Ltd. All rights reserved.

Teknologia berriak direla medio informazio asko metatzen da gaur egun eta gainera, gehiena formatu digitalean. Askotan, informazio hori kontzienteki gordetzen da eta beste hainbatetan berriz, gure ekintzen albo ondorio gisa. Metatutako informazio hori guztia, zergatik ez erabili datuetan bertan ez dagoen ezagutza sortzeko? Hauxe da datu-meatzaritza eta ikasketa automatikoko tekniken helburua. Webguneetan nabigatzen dugunean uzten dugun aztarna izan liteke datu-meatzaritzak zukua atera diezaiokeen datu multzoetako bat. Lortutako ezagutzak erabilera anitz ditu: baliabideak egokitzea edo webgunea pertsonalizatzea, gomendio sistema baten oinarri izatea edo zerbitzu-emaileari bere webgunean nabigatzen duten erabiltzaile moten berri ematea. Ezagutza hori lortzeko erabil litezkeen tresnak eta prozesua deskribatzea da artikulu honen helburua.