Smart Cities Research Center

Funder

Organizational Unit

Publications

"Back in my day...": A Preliminary Study on the Differences in Generational Groups Perception of Musically-evoked Emotion

Publication . Louro, Pedro; Panda, Renato

The increasingly globalized world we live in today and the wide availability of music at our fingertips have led to more diverse musical tastes within younger generations than in older generations. Moreover, these disparities are still not well understood, and the extent to which they affect listeners' preferences and perception of music. Focusing on the latter, this study explores the differences in emotional perception of music between the Millennials and Gen Z generations. Interviews were conducted with six participants equally distributed between both generations by recording their listening experience and emotion perception on two previously compiled sets of songs representing each group. Significant differences between generations and possible contributing factors were found in the analysis of the conducted interviews. Findings point to differences in the perception of energy of songs with specific messages of suffering for love, as well as a tendency from the younger group to perceive a well-defined emotion in songs representing their generation in contrast to neutral responses from the other group. These findings are preliminary, and further studies are needed to understand their extent. Nevertheless, valuable insights can be extracted to improve music recommendation systems.

2024Conference object

Open access

Exploring Deep Learning Methodologies for Music Emotion Recognition

Publication . Louro, Pedro; Redinho, Hugo; Malheiro, Ricardo; Paiva, Rui Pedro; Panda, Renato

Classical machine learning techniques have dominated Music Emotion Recognition (MER). However, improvements have slowed down due to the complex and time-consuming task of handcrafting new emotionally relevant audio features. Deep Learning methods have recently gained popularity in the field because of their ability to automatically learn relevant features from spectral representations of songs, eliminating such necessity. Nonetheless, there are limitations, such as the need for large amounts of quality labeled data, a common problem in MER research. To understand the effectiveness of these techniques, a comparison study using various classical machine learning and deep learning methods was conducted. The results showed that using an ensemble of a Dense Neural Network and a Convolutional Neural Network architecture resulted in a state-of-the-art 80.20% F1-score, an improvement of around 5% considering the best baseline results, concluding that future research should take advantage of both paradigms, that is, conbining handcrafted features with feature learning.

2024Conference object

Open access

Remote Monitoring of Energy-autonomous Constructed Wetlands

Publication . Lopes, Simão; Barros, F.M.; Ferreira, Carlos; Mateus, D. M. R.; Matos, Pedro; Neves, Pedro; Pinho, Henrique J. O.

Constructed Wetlands systems (CW) are nature-based and sustainable technology for treating wastewater, contributing to the management and protection of freshwater resources. Moreover, CW can contribute to valorizing waste materials, producing reclaimed water for diverse applications, and producing plant biomass that can be material and energetically valorized. Because CW efficiency depends on several mechanisms such as physical, chemical, and biological, its real-time monitoring is essential to provide a better use of this technology. This work describes a smart framework for monitoring CW based on IoT devices and sensors, and data science tools providing real-time processing of gathered water quality parameters and environmental variables. Furthermore, the framework manages renewable energy sources to provide the required energy for CW operation and monitoring. Data collected from the sensor network show significant daily variations in water quality parameters. The future processing of these data can provide the development of models to improve the efficiency of the CW.

2023Journal article

Open access

A Pattern Recognition Framework to Investigate the Neural Correlates of Music

Publication . Guedes, Ana Gabriela; Sayal, Alexandre; Panda, Renato; Paiva, Rui Pedro; Direito, Bruno

Music can convey fundamental emotions like happiness and sadness and more intricate feelings such as tenderness or grief. Understanding the neural mechanisms underlying music-induced emotions holds promise for innovative, personalised neurorehabilitation therapies using music. Our study investigates the link between perceived emotions in music and their corresponding neural responses, measured using fMRI. Fifteen participants underwent fMRI scans while listening to 96 musical excerpts categorised into quadrants based on Russell’s valence-arousal model. Neural correlates of valence and arousal were identified in neocortical regions, especially within music-specific sub-regions of the auditory cortex. Through multivariate pattern analysis, distinct emotional quadrants were decoded with an average accuracy of 62% ±15%, surpassing the chance level of 25%. This capacity to discern music’s emotional qualities has implications for psychological interventions and mood modulation, enhancing music-based treatments and neurofeedback learning.

2023-10-27Conference object

Open access

Sustainable Production of Reclaimed Water by Constructed Wetlands for Combined Irrigation and Microalgae Cultivation Applications

Publication . Pinho, Henrique J. O.; Mateus, D. M. R.

Considering the increasing pressure on freshwater resources due to the constant increase in water consumption and insufficient wastewater control and treatment, recovering waste water is a path to overcoming water scarcity. The present work describes the potential of reusing treated wastewater (reclaimed water) for irrigation and production of microalgae biomass in an integrated way, through experimental evaluation of plant and microalgae growth, and creation of an application model. First, two parallel experiments were conducted to evaluate the use of reclaimed water produced by a constructed wetland filled with a mix of solid waste: the irrigation of a set of small pots filled with soil and planted with Tagetes patula L., and the cultivation of microalgae Chlorella sp.and a mixed microalgae population with predominant species of the genus Scenedesmus sp. in shaken flasks and tubular bubble column photobioreactors. Results indicated no negative effects of using the reclaimed water on the irrigated plants and in the cultivated microalgae. The growth indicators of plants irrigated with reclaimed water were not significantly different from plants irrigated with fertilized water. The growth indicators of the microalgae cultivated with reclaimed water are within the range of published data. Second, to apply the results to a case study, the seasonal variability of irrigation needs in an academic campus was used to propose a conceptual model for wastewater recovery. The simulation results of the model point to a positive combination of using reclaimed water for the irrigation of green spaces and microalgae production, supported by a water storage strategy. Water abstraction for irrigation purposes can be reduced by 89%, and 2074 kg dry weight microalgae biomass can be produced annually. Besides the need for future work to optimize the model and to add economical evaluation criteria, the model shows the potential to be applied to non-academic communities in the perspective of smarter and greener cities.

2021-02-13Journal article

Open access