Tipo de publicación: Conference Paper

Publicado en: Advances in Human Factors and Systems Interaction

Tipo de publicación: Journal Article

Publicado en: Journal of Ambient Intelligence and Humanized Computing

Tipo de publicación: Book Chapter

Publicado en: Advances in Design for Inclusion

Tipo de publicación: Book Chapter

Publicado en: Ambient Assisted Living. ICT-based Solutions in Real Life Situations

Descripción:

It is very common to interact with notifications every day with our mobile devices. Notifications have advantages and disadvantages. They bring information for the user, but they are also interruptions. In this study, the authors provide a solution for scheduling events through notifications. They created an application using the Google Calendar platform and the Swift programming language to respond to events through notifications. Then, the participants evaluated the application through the usability scale of the system (SUS), and the results were positive. The authors received excellent comments and feedback from the participants in the evaluation.

Tipo de publicación: Conference Paper

Publicado en: 2019 IV Jornadas Costarricenses de Investigación en Computación e Informática (JoCICI)

Descripción:

This paper proposes the creation of a smart meeting room through the incorporation of a PIR sensor and an AWS IoT button that allows the booking system to reflect a more precise availability of meeting rooms according to the actual occupancy status. The Internet of Things (IoT) devices are controlled using a Wi-Fi module that allows them to connect to the REST web service and to integrate with the open source Meeting Room Booking System (MRBS). In order to evaluate the system a storyboard evaluation was conducted with 47 participants. All participants filled out the User Experience Questionnaires (UEQ), described the product using three words and expressed their opinion through open comments. Finally, 19 participants took part in a real-life simulation of the smart meeting room and evaluated the system using the UEQ questionnaire. Based on the positive acceptance reflected in the evaluations, results show that the proposed system is considered very attractive and useful by the participants.

Tipo de publicación: Conference Paper

Publicado en: 2019 IV Jornadas Costarricenses de Investigación en Computación e Informática (JoCICI)

Descripción:

Intelligent Personal Assistant (IPA) has experienced an important market growth, therefore, an increase in its development by having more people interested in devices that use this software. This opens possibilities for develop new games that people can be interested in. This article presents a framework proposal to create audio games using IPA enabled devices. In order to evaluate the framework, a prototype was designed and presented to 30 participants. The results obtained indicated that a 97.6% of the interviewees were attracted to the idea of playing a game using and IPA.

Tipo de publicación: Conference Paper

Publicado en: Advances in Human Factors in Wearable Technologies and Game Design

Descripción:

Standardized questionnaires are well-known, reliable, and inexpensive instruments to evaluate user experience (UX). Although the structure, content, and application procedure of the three most recognized questionnaires (AttrakDiff, UEQ, and meCUE) are known, there is no systematic literature review (SLR) that classifies how these questionnaires have been used in primary studies reported academically. This SLR seeks to answer five research questions (RQs), starting with identifying the uses of each questionnaire over the years and by geographic region (RQ1) and the median number of participants per study (how many participants is considered enough when evaluating UX?) (RQ2). This work also aims to establish whether these questionnaires are combined with other evaluation instruments and with which complementary instruments are they used more frequently (RQ3). In addition, this review intends to determine how the three questionnaires have been applied in the fields of ubiquitous computing and ambient intelligence (RQ4) and also in studies that incorporate nontraditional interfaces, such as haptic, gesture, or speech interfaces, to name a few (RQ5). Methods. A systematic literature review was conducted starting from 946 studies retrieved from four digital databases. The main inclusion criteria being the study describes a primary study reported academically, where the standardized questionnaire is used as a UX evaluation instrument in its original and complete form. In the first phase, 189 studies were discarded by screening the title, abstract, and keyword list. In the second phase, 757 studies were full-text reviewed, and 209 were discarded due to the inclusion/exclusion criteria. The 548 resulting studies were analyzed in detail. Results. AttrakDiff is the questionnaire that counts the most uses since 2006, when the first studies appeared. However, since 2017, UEQ has far surpassed AttrakDiff in uses per year. The contribution of meCUE is still minimal. Europe is the region with the most extended use, followed by Asia. Within Europe, Germany greatly exceeds the rest of countries (RQ1). The median number of participants per study is 20, considering the aggregated data from the three questionnaires. However, this median rises to 30 participants in journal studies while it stays in 20 in conference studies (RQ2). Almost 4 in 10 studies apply the questionnaire as the only evaluation instrument. The remaining studies used between one and five complementary instruments, among which the System Usability Scale (SUS) stands out (RQ3). About 1 in 4 studies analyzed belong to ubiquitous computing and ambient intelligence fields, in which UEQ increases the percentage of uses when compared to its general percentage, particularly in topics such as IoT and wearable interfaces. However, AttrakDiff remains the predominant questionnaire for studies in smart cities and homes and in-vehicle information systems (RQ4). Around 1 in 3 studies include nontraditional interfaces, being virtual reality and gesture interfaces the most numerous. Percentages of UEQ and meCUE uses in these studies are higher than their respective global percentages, particularly in studies using virtual reality and eye tracking interfaces. AttrakDiff maintains its overall percentage in studies with tangible and gesture interfaces and exceeds it in studies with nontraditional visual interfaces, such as displays in windshields or motorcycle helmets (RQ5).

Tipo de publicación: Journal Article

Publicado en: Advances in Human-Computer Interaction

Descripción:

Emotion recognition is important in the context of smart buildings and IoT, because it allows the environment to have a better notion of the mood of the humans who are present. With a view to developing such projects, in this article we analyze the performance of an emotion classifier that uses a convolutional neural network. Specifically, we focus on analyzing the impact of the epochs and batch size hyperparameters. To do this, we propose an experimental design with the following hypothesis: "The number of epochs that the model trains and the size of the batch given by iteration in each epoch influence the accuracy of an emotion classifier built from networks. convolutional neurons using the VGG16 architecture".

Tipo de publicación: Conference Paper

Publicado en: 2021 IEEE V Jornadas Costarricenses de Investigación en Computación e Informática (JoCICI)

Descripción:

This paper focuses on the recognition and classification of Activities of Daily Living (ADLs) that are carried out in a kitchen. To do this, a Recurrent Neural Network architecture of the Long-Short Term Memory (LSTM) type is implemented as a classifier. The ARAS dataset is used for training and evaluation. A classifier is obtained with an average value in the F1 metric of 95.33% for the chosen data set.

Tipo de publicación: Conference Paper

Publicado en: 2021 IEEE V Jornadas Costarricenses de Investigación en Computación e Informática (JoCICI)

Descripción:

In recent years there has been an increase of voice interfaces, driven by developments in Artificial Intelligence and the expansion of commercial devices that use them, such as smart assistants present on phones or smart speakers. One field that could take advantage of the potential of voice interaction is in the self-administered surveys data collection, such as standardized UX evaluation questionnaires. This work proposes a set of conversational design patterns for standardized UX evaluation questionnaires that use semantic difference scales as a means of collecting quantitative information on user experience, as is the case of AttrakDiff and UEQ (User Experience Questionnaire). The presented design patterns seek to establish a natural conversation created in accordance with the user, the conservation of context between subsequent questions, the minimization of statements and with statement repair mechanisms not completely understood by the user or voice agent, as eliciting explanation of a concept or repetition.

Tipo de publicación: Book Chapter

Publicado en: Lecture Notes in Networks and Systems

Descripción:

The usage of IoT devices is rapidly growing. Many users may want to add them to their homes to automate certain tasks, help themselves with information, or monitor their environment continuously. Quick IoT development is taking place on privacy, protocols, and other areas. However, the user interface area is being left out of the efforts. Mobile applications and websites are focused on technical requirements only. Research is not focused on the interaction of the user with the application, so standards and/or tendencies may not be utilized. This investigation aims to implement a smart house application interface focused on the user instead of the technical requirements. To start, the card sorting technique is used to group IoT devices into meaningful groups for users. Then, an interface prototype of a smart house application is created with the feedback obtained from the card sorting activity. Finally, the prototype is evaluated by using a standardized questionnaire.

Tipo de publicación: Conference Paper

Publicado en: International Conference on Ubiquitous Computing and Ambient Intelligence

Descripción:

The AttrakDiff questionnaire is a widely used instrument for measuring User Experience. However, a Spanish version of the questionnaire has yet to be validated. This represents a significant limitation, given the importance of the Spanish-speaking community. This study aims to translate and validate AttrakDiff to Spanish. Several techniques for translation were used, and the results were joined in a translation proposal. The translated version was evaluated in two scenarios. First, an evaluation with 200 + participants to assess the translation proposal. Second, an evaluation of three systems to perform a factorial analysis and determine the correlations between questions of the same dimension. The results of this study will contribute to the advancement of UX research and practice in the Spanish-speaking context and provide a valuable tool for practitioners and researchers who work with Spanish-speaking users.

Tipo de publicación: Book Chapter

Publicado en: Proceedings of the 15th International Conference on Ubiquitous Computing & Ambient Intelligence (UCAmI 2023)

Descripción:

Thalassemia, a hereditary blood disorder, causes abnormal hemoglobin production—alpha- and beta-thalassemia are its variants. This leads to decreased hemoglobin levels and accounted for 16,800 deaths in 2015, affecting 1.5% of the global population. Diagnosis involves blood tests and genetic screening, but many severe cases go undiagnosed due to limited registries and screening, resulting in high mortality. Our work suggests using gene expression profiling and machine learning to identify biomarkers for thalassemia. Using an Isolation Forest algorithm, we found 72 anomalous genes. Validation showed significant terms like cytoplasmic translation and apoptosis, indicating potential pathways for thalassemia. We also found genes related to iron homeostasis, linking oxidative stress and apoptosis to thalassemia. Comparing with another study, we found common processes. Five genes identified in AmiGO are up-regulated in thalassemia and could be biomarkers due to their abnormal expression and biological role. This highlights the potential of machine learning in refining diagnosis and understanding molecular pathways for better patient management, calling for further research.

Tipo de publicación: Book Chapter

Publicado en: ICT for Intelligent Systems

Descripción:

This paper consolidates the efforts of our research group in designing and developing voice applications for smart speakers and intelligent personal assistants (such as Amazon Alexa, Google Assistant, Siri, and Cortana) over recent years. We present six case studies: a career guidance system, an application for educational fairs, an appointment booking system for a dentist's office, a set of games for seniors, a notification system for smart farming, and the use of smart speakers as mechanisms to evaluate user experience. These case studies encompass various contexts, each requiring unique approaches. Each voice application was individually evaluated using standardized questionnaires and customized surveys. Additionally, we conducted two parallel evaluations to address key questions about human interaction with intelligent personal assistants. These evaluations involved both expert groups and end-users of the voice applications. Finally, we synthesize the knowledge, experiences, and perspectives gathered over these years to present a list of lessons learned, aimed at guiding researchers and developers in enhancing the user experience (UX) of voice applications.

Tipo de publicación: Conference Paper

Publicado en: 2024 IEEE VII Congreso Internacional en Inteligencia Ambiental, Ingeniería de Software y Salud Electrónica y Móvil (AmITIC)