This article introduces a method for exploring liminal horror environments using a modified Wave Function Collapse algorithm. This approach employs real-time generated regions to create infinite, non-deterministic environments, removing the feeling of security due to familiarity. An eventdriven system further reinforces unpredictability by dynamically integrating horror experiences. While still in an exploratory stage, this method provides a foundation for future research on how architectural structures, unpredictability, and environmental cues contribute to unsettling experiences in games.

Gene and protein networks are very important to model complex large-scale systems in molecular biology. Inferring or reverseengineering such networks can be defined as the process of identifying gene/protein interactions from experimental data through computational analysis. However, this task is typically complicated by the enormously large scale of the unknowns in a rather small sample size. Furthermore, when the goal is to study causal relationships within the network, tools capable of overcoming the limitations of correlation networks are required. In this work, we make use of Bayesian Graphical Models to attach this problem and, specifically, we perform a comparative study of different state-of-the-art heuristics, analyzing their performance in inferring the structure of the Bayesian Network from breast cancer data.

As the popularity of wearables continues to scale, a substantial portion of the population has now access to (self-)monitorization of cardiovascular activity. In particular, the use of ECG wearables is growing in the realm of occupational health assessment, but one common issue that is encountered is the presence of noise which hinders the reliability of the acquired data. In this work, we propose an ECG denoiser based on bidirectional Gated Recurrent Units (biGRU). This model was trained on noisy ECG samples that were created by adding noise from the MIT-BIH Noise Stress Test database to ECG samples from the PTB-XL database. The model was initially trained and tested on data corrupted with the three most common sources of noise: electrode motion artifacts, muscle activation and baseline wander. After training, the model was able to fully reconstruct previously unseen signals, achieving Root-Mean-Square Error values between 0.041 and 0.023. For further testing the model’s robustness, we performed a data collection in an industrial work setting and employed our model to clean the noisy data, acquired from 43 workers using wearable sensors. The trained network proved to be very effective in removing real ECG noise, outperforming the available open-source solutions, while having a much smaller complexity compared to state-of-the-art Deep Learning approaches.

Bone fractures are among the main reasons for emergency room admittance and require a rapid response from doctors. Bone fractures can be severe and can lead to permanent disability if not treated correctly and rapidly. Using X-ray imaging in the emergency room to detect fractures is a challenging task that requires an experienced radiologist, a specialist who is not always available. The availability of an automatic tool for image classification can provide a second opinion for doctors operating in the emergency room and reduce the error rate in diagnosis. This study aims to increase the existing state-of-the-art convolutional neural networks’ performance by using various ensemble techniques. In this approach, different CNNs (Convolutional Neural Networks) are used to classify the images; rather than choosing the best one, a stacking ensemble provides a more reliable and robust classifier. The ensemble model outperforms the results of individual CNNs by an average of 10%.

Studies on childhood dysphonia have revealed considerable rates for voice disorders in 4 – 12 year-old children. The sustained vowel exercise is widely used as a technique in the vocal (re)education process. However this exercise can become tedious after a short practice. Here, we propose a novel dynamic difficulty adjustment model to be used in a serious game with the sustained vowel exercise to motivate children on practicing this exercise often. The model automatically adapts the difficulty of the challenges in response to the child’s performance. The model is not exclusive to this game and can be used in other games for dysphonia treatment. In order to measure the child’s performance, the model uses parameters that are relevant to the therapy treatment. The proposed model is based on the flow model in order to balance the difficulty of the challenges with the child’s skills.

Affective computing has been widely used to detect and recognize emotional states. The main goal of this study was to detect emotional states using machine learning algorithms automatically. The experimental procedure involved eliciting emotional states using film clips in an immersive and non-immersive virtual reality setup. The participants’ physiological signals were recorded and analyzed to train machine learning models to recognize users’ emotional states. Furthermore, two subjective ratings emotional scales were provided to rate each emotional film clip. Results showed no significant differences between presenting the stimuli in the two degrees of immersion. Regarding emotion classification, it emerged that for both physiological signals and subjective ratings, user-dependent models have a better performance when compared to user-independent models. We obtained an average accuracy of 69.29 ± 11.41% and 71.00 ± 7.95% for the subjective ratings and physiological signals, respectively. On the other hand, using user-independent models, the accuracy we obtained was 54.0 ± 17.2% and 24.9 ± 4.0%, respectively. We interpreted these data as the result of high inter-subject variability among participants, suggesting the need for user-dependent classification models. In future works, we intend to develop new classification algorithms and transfer them to real-time implementation. This will make it possible to adapt to a virtual reality environment in real-time, according to the user’s emotional state.

In recent years, there has been growing interest in taking advantage of the technological progress in information technology and computer science to enhance the synergy between multidisciplinary organisations with a mutual objective of improving scientific knowledge and engaging society in cultural activities. Such an example of collaboration networks includes those where governmental, scientific and cultural institutions work in unison to provide services that support research through the use of technology while disseminating information and promoting cultural heritage. Here, we present a case study implementing the results of the work between multidisciplinary departments of the NOVA University Lisbon and third-party cultural heritage organisations. In particular, a mobile and desktop PC application uses augmented reality to showcase results obtained from analysis of artwork by Amadeo de Souza-Cardoso using artificial intelligence. The mobile application is intended to be used to enhance museum visitors’ experience and strengthen the link between scientific, governmental, and heritage organisations.

This paper presents research on how to use Virtual Reality with gamified exercises in a therapeutic context with children, focusing on the particular case of warning sensations triggered by sensory properties of food (sensory food aversion). To achieve this goal, we developed a tool featuring several food exposure challenges for patients to use. In the gamified system, the child explores a virtual environment while facing the food they have a problem with. These environments present tasks that resemble typical interactions performed in the real world to develop accommodation. The therapist also has an external system to control the system from outside. In addition, the system sends data collected during the session for the therapist to analyze. We researched how to keep a child engaged in therapeutic tasks and how a child perceives virtual interaction interfaces. The results suggest our system kept the users engaged. Moreover, data show a tendency for the users’ results (ease of use, presence, and performance) to remain the same when using controllers or hand tracking. The preliminary results are encouraging and allow us to apply the current system to a wider audience.

The intelligent choice of extractants and entrainers can improve current mixture separation techniques allowing better efficiency and sustainability of chemical processes that are both used in industry and laboratory practice. The most promising approach is a straightforward comparison of selectivity at infinite dilution between potential candidates. However, selectivity at infinite dilution values are rarely available for most compounds so a theoretical estimation is highly desired. In this study, we suggest a Quantitative Structure–Property Relationship (QSPR) approach to the modelling of the selectivity at infinite dilution of ionic liquids. Additionally, auxiliary models were developed to overcome the potential bias from big activity coefficient at infinite dilution from the solute. Data from SelinfDB database was used as training and internal validation sets in QSPR model development. External validation was done with the data from literature. The selection of the best models was done using decision functions that aim to diminish bias in prediction of the data points associated with the underrepresented ionic liquids or extreme temperatures. The best models were used for the virtual screening for potential azeotrope breakers of aniline + n-dodecane mixture. The subject of screening was a combinatorial library of ionic liquids, created based on the previously unused combinations of cations and anions from SelinfDB and the test set extractants. Both selectivity at infinite dilution and auxiliary models show good performance in the validation. Our models’ predictions were compared to the ones of the COSMO-RS, where applicable, displaying smaller prediction error. The best ionic liquid to extract aniline from n-dodecane was suggested.

In the last decades, the digital image has moved between the thin line that separates its exponential multi-plication and its continuous danger of invisibility and loss. Despite the fact of being constantly used on the internet or social network interactions, the difficulties in filtering, gathering, authenticating and preserving new media images have led them to be a type of art barely collected by contemporary art museums. Even more, the huge amount of material produced not only by artists or creatives but also by citizens makes it impossible for cultural institutions to tackle the task of preserving a significant percentage of it. Museums seem to be unable to distinguish what might be considered art or heritage among the massive amount of images that fed popular culture. Nevertheless, the irruption of blockchain culture has focused on the importance of digital images as an identity, social and economic asset. NFTs seem to attempt to remedy the weaknesses of the digital image by associating it with a verifiable and supposedly incorruptible contract. This study tries to analyse the precariousness of the digital image as a key element in the emergence and sudden rise and fall of the so-called “crypto-art”. To this end, the idea of the “poor image” outlined by Steyerl is followed. The aim is to clarify whether the digital images associated with blockchain transactions solve the problematic obsolescent and unstable condition of the works, or if, on the contrary, these are used as fuel for a new ultra-liberal financial machine being quickly consumed and discarded.