IPT - Ci2 - Artigos em Conferências
Permanent URI for this collection
Browse
Recent Submissions
- MERGE App: A Prototype Software for Multi-User Emotion-Aware Music ManagementPublication . Louro, Pedro; Branco, Guilherme; Redinho, Hugo; Santos, Ricardo Correia Nascimento Dos; Malheiro, Ricardo; Panda, Renato; Paiva, Rui PedroWe present a prototype software for multi-user music library management using the perceived emotional content of songs. The tool offers music playback features, song filtering by metadata, and automatic emotion prediction based on arousal and valence, with the possibility of personalizing the predictions by allowing each user to edit these values based on their own emotion assessment. This is an important feature for handling both classification errors and subjectivity issues, which are inherent aspects of emotion perception. A path-based playlist generation function is also implemented. A multi-modal audio-lyrics regression methodology is proposed for emotion prediction, with accompanying validation experiments on the MERGE dataset. The results obtained are promising, showing higher overall performance on train-validate-test splits (73.20% F1-score with the best dataset/split combination).
- Improving Deep Learning Methodologies for Music Emotion RecognitionPublication . Louro, Pedro Lima; Redinho, Hugo; Malheiro, Ricardo; Paiva, Rui Pedro; Panda, RenatoMusic Emotion Recognition (MER) has traditionally relied on classical machine learning techniques. Progress on these techniques has plateaued due to the demanding process of crafting new, emotionally-relevant audio features. Recently, deep learning (DL) methods have surged in popularity within MER, due to their ability of automatically learning features from the input data. Nonetheless, these methods need large, high-quality labeled datasets, a well-known hurdle in MER studies. We present a comparative study of various classical and DL techniques carried out to evaluate these approaches. Most of the presented methodologies were developed by our team, if not stated otherwise. It was found that a combination of Dense Neural Networks (DNN) and Convolutional Neural Networks (CNN) achieved an 80.20% F1-score, marking an improvement of approximately 5% over the best previous results. This indicates that future research should blend both manual feature engineering and automated feature learning to enhance results.
- Exploring Song Segmentation for Music Emotion Variation DetectionPublication . Ferreira, Tomas; Redinho, Hugo; Louro, Pedro L.; Malheiro, Ricardo; Paiva, Rui Pedro; Panda, RenatoThis paper evaluates the impact of song segmentation on Music Emotion Variation Detection (MEVD). In particular, the All-In-One song-structure segmentation system was employed to this end and compared to a fixed 1.5-sec window approach. Acoustic features were extracted for each obtained segment/window, which were classified with SVMs. The attained results (best F1-score of 55.9%) suggest that, despite its promise, the potential of this song segmentation approach was not fully exploited, possibly due to the small employed dataset. Nevertheless, preliminary results are encouraging.
- "Back in my day...": A Preliminary Study on the Differences in Generational Groups Perception of Musically-evoked EmotionPublication . Louro, Pedro; Panda, RenatoThe 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.
- Exploring Deep Learning Methodologies for Music Emotion RecognitionPublication . Louro, Pedro; Redinho, Hugo; Malheiro, Ricardo; Paiva, Rui Pedro; Panda, RenatoClassical 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.
- Raising Awareness for Sustainable Development Goals Through Hands-On ExperimentsPublication . Costa, Maria Cristina; Mateus, D. M. R.; Pinho, Henrique J. O.With the aim of protecting our planet, the United Nations defined 17 Sustainable Development Goals (SDG), which requires the involvement of all countries to make an endeavour to achieve better living conditions. In this regard, stakeholders such as governments, regional and international organizations, and civil society need to work together to make efforts to meet these objectives. In addition, Higher Education Institutions have a crucial role, not only in developing research and disseminating SDG practices but also in intervening in society. This paper presents a collaborative project led by a Higher Education Institute and targeted to the school community. With the objective of strengthening consciousness for the development of good practices related to SDG, a workshop was prepared and implemented with primary school teachers. Besides providing knowledge about SDG, several hands-on experiments were presented to teachers to be reproduced with their students. Based on participant observation and enquiry forms applied to teachers and students, it was verified that the project was effective in enhancing recognition of teachers and students about the importance of providing good practices related to SDG. It is concluded that collaboration between higher education institutions and schools can trigger the implementation of sustainable development practices in the community.
- Cultivation of Energy Crops in Constructed Wetlands for Wastewater Treatment: An OverviewPublication . Pinho, Henrique J. O.; Mateus, D. M. R.The need for sustainable, clean, and secure energy sources is a current issue for all nations. All kinds of vegetal biomass can be used as energy-source or as raw material for biofuel production, but some species are commonly classified as energy crops. This work evaluates the energy potential of 35 species of energy crops when produced in constructed wetlands (CW). Producing energy crops in CW is a route to link wastewater treatment to energy production, avoiding the abstraction of freshwater for crop irrigation, and simultaneously avoiding the use of arable land. However, for most of the energy crops, there are no data available in the literature about biomass productivity in CWs. Although 20 of the 35 crops have been tested as CW vegetation, the biomass productivity in CWs was only found for 13 species. Reported biomass productivity in CW is similar to or even higher than the productivity reported for conventional production, but most reported data is for pilot-scale CW, which points to the need for future work in full-scale systems. From the combination of biomass productivity and the biomass calorific value, Arundo donax, Miscanthus x giganteus, Cynodon dactylon, Phragmites australis, and Typha latifolia show higher ranges up to 3064 MJ/ha year for Arundo donax. Future works on CW design can be focused on the potential of using energy crops as vegetation.
- Smart Monitoring of Constructed Wetlands to Improve Efficiency and Water QualityPublication . Pinho, Henrique; Barros, Manuel; Teixeira, André; Oliveira, Luís; Matos, Pedro; Ferreira, Carlos; Mateus, DinaThe Smart monitoring of constructed wetlands to improve efficiency and water quality (SmarterCW) project aims to monitor biological wastewater treatment processes by gathering continuous data from remote water and environmental sensors. The acquired data can be processed and analyzed through data science tools to understand better the complex and coupled phenomena underneath wastewater treatment and monitor and optimize the system performance. The results will improve the efficiency and control of nature-based wastewater treatment technologies. The methodology comprises the following tasks and activities: Implementation of a set of electrochemical sensors in the input and output flow streams of pilot-scale constructed wetlands; Acquisition of water quality parameters such as pH, electrical conductivity, temperature, and ionic compounds; Acquisition of environmental parameters, such as temperature and humidity; Application of data analysis tools to design and optimize conceptual models to correlate pollutants removal with operative parameters in green technologies for wastewater treatment. This methodology was applied to a patent-protected pilot-scale modular constructed wetland in which filling media consists of a mixture of solid waste. A high-level IoT communication layer structure complements the system to support remote real-time water and environmental monitoring, system performance, and data dissemination.
- Low Cost LoRaWAN Image Acquisition System for Low Rate Internet of Things ApplicationsPublication . Frazão Correia, Pedro; Gomes, Marcela; Martins, Gabriel; Panda, RenatoThis paper proposes a low cost LoRaWAN image acquisition and transmission prototype for low rate and un-constrained delay IoT applications. Real scenario tests were performed and images, at distances up to 2.5 km from node to gateway in urban environment, were transmitted and correctly decoded. The obtained results show the effectiveness of a low-power wide-area (LPWAN) technology prototype for long distance image transmission in applications without delay constraints and where other wireless technologies are not available.
- Hydrogen Production via Wastewater Electrolysis – An Integrated Approach ReviewPublication . Cartaxo, Marco; Fernandes, José; Gomes, Mário; Pinho, Henrique J. O.; Nunes, Valentim; Coelho, PauloHuman activities generate enormous amounts of wastewater. The hydrogen production from this new resource has gained attention as an emergent technology. Incorporating photovoltaic energy production with different electrolysis systems which can treat wastewaters and produce hydrogen simultaneously will lead to an environmentally-friendly and sustainable hydrogen production.
- «
- 1 (current)
- 2
- 3
- »