Browsing by Author "Reis, Sara"
Now showing 1 - 6 of 6
Results Per Page
Sort Options
- Benchmarking computer-vision-based facial emotion classification algorithms while wearing surgical masksPublication . Coelho, Luis; Reis, Sara; Moreira, Cristina; Cardoso, Helena; Sequeira, Miguela; Coelho, RaquelEffective human communication relies heavily on emotions, making them a crucial aspect of interaction. As technology progresses, the desire for machines to exhibit more human-like characteristics, including emotion recognition, grows. DeepFace has emerged as a widely adopted library for facial emotion recognition. However, the widespread use of surgical masks after the COVID-19 pandemic presents a considerable obstacle to its performance. To assess this issue, we conducted a benchmark using the FER2013 dataset. The results revealed a substantial performance decline when individuals wore surgical masks. “Disgust” suffers a 22.6% F1-score reduction, while “Surprise” is least affected with a 48.7% reduction. Addressing these issues improves human–machine interfaces and paves the way for more natural machine communication.
- A low resource skeleton maturation estimation system for automatic hand X-Ray assessment in pediatric applicationsPublication . Campos, Ana; Silva, Maria; Azeredo, Ricardo; Coelho, Luis; Reis, Sara; Abreu, SílviaThe assessment of differences between skeletal age and chronological age in childhood is often based on the comparison of the patient's left hand x-ray with a reference atlas, performed by a experienced professional. This procedure involves a manual image analysis, that can be subject to inter rater variability posing several problems for clinical applications. In this paper a new methodology for skeleton maturation estimation based on automatic hand X-ray assessment for pediatric applications on a low resource devices (e.g. mobile device) is proposed. The pipeline covers hand-area estimation and bone-area estimation to achieve maturation scores which are then indexed with references images, separately for male and female. The proposed approach is based on simple image processing functions always bearing in mind the application on a mobile context. The involved steps are thoroughly presented and all the used functions are explained. The performance of the system was then evaluated using the complete pipeline. The obtained results pointed to an average error rate of 15,38±3,31%, which is subject to improvements. In particular, contrast enhancement in some lower quality images still offers some challenges.
- SMYD3 contributes to a more aggressive phenotype of prostate cancer and targets Cyclin D2 through H4K20me3Publication . Quintela Vieira, Ana Filipa; Costa-Pinheiro, Pedro; Almeida-Rios, Diogo; Pinho dos Santos Graça, Maria Inês; Reis, Sara; Simões-Sousa, Susana; Carneiro, Isa; Sousa, Elsa Joana; Godinho, Maria Inês; Baltazar, Fatima; Henrique, Rui; Jeronimo, CarmenProstate cancer (PCa) is one of the most incident cancers worldwide but clinical and pathological parameters have limited ability to discriminate between clinically significant and indolent PCa. Altered expression of histone methyltransferases and histone methylation patterns are involved in prostate carcinogenesis. SMYD3 transcript levels have prognostic value and discriminate among PCa with different clinical aggressiveness, so we decided to investigate its putative oncogenic role on PCa.We silenced SMYD3 and assess its impact through in vitro (cell viability, cell cycle, apoptosis, migration, invasion assays) and in vivo (tumor formation, angiogenesis). We evaluated SET domain's impact in PCa cells' phenotype. Histone marks deposition on SMYD3 putative target genes was assessed by ChIP analysis.Knockdown of SMYD3 attenuated malignant phenotype of LNCaP and PC3 cell lines. Deletions affecting the SET domain showed phenotypic impact similar to SMYD3 silencing, suggesting that tumorigenic effect is mediated through its histone methyltransferase activity. Moreover, CCND2 was identified as a putative target gene for SMYD3 transcriptional regulation, through trimethylation of H4K20.Our results support a proto-oncogenic role for SMYD3 in prostate carcinogenesis, mainly due to its methyltransferase enzymatic activity. Thus, SMYD3 overexpression is a potential biomarker for clinically aggressive disease and an attractive therapeutic target in PCa.
- Study of the Risk of Ankle Injury During Impact on the Ground and Definition of Support OrthosesPublication . Vieira, Helder; Ferraz, T.; Sousa, T.; Martins, I.; Marques, Maria Arcelina; Reis, SaraThis work studies the effect of different orthoses on preventing injuries in the ankle-foot joint. It was carried out using OpenSim and the available ankle-foot musculoskeletal model and AFO orthoses models. The motion situation assessed is related to placing the foot on the ground. It is also analyzed how a passive ankle-foot orthosis, muscles reflexes and muscle coactivation influence the risk of injury, namely during ankle inversion. Results indicate that muscle coactivation and the use of an AFO can reduce injury risk. Thus, an average stiffness AFO is best suited for preventing ankle injuries.
- The COVID-19 pandemic: How technology Is reshaping public health and medicinePublication . Coelho, Luis; Glotsos, Dimitrios; Reis, Sara(extrato) The outbreak of the novel coronavirus severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) pandemic has been a watershed moment in human history, causing a profound shift in the global landscape that has affected every aspect of our lives. The virus has not only brought the world to a standstill but has also challenged our values, beliefs, and societal structures, exposing the vulnerabilities and inequalities that exist within our systems. The COVID-19 pandemic has posed unprecedented challenges to the global community, and technology has emerged as a key tool in managing the spread of the virus and mitigating its impact on society. From contact tracing to remote work and telemedicine, technology has enabled us to respond to the crisis in innovative and effective ways. Bioengineering is a multidisciplinary field that applies engineering principles and techniques to solve problems in the life sciences.
- The importance of ethical reasoning in next generation tech educationPublication . Reis, Sara; Coelho, Luis; Sarmet, Max; Araújo, Joana; Corchado, Juan M.Artificial intelligence (AI) is having a profound impact on human life, with both benefits and drawbacks in the societal, environmental, and technological realms. However, the ethical implications of AI are often not addressed in technology education, leaving future professionals with a lack of awareness in this area. This is concerning, as AI has the potential to greatly information delivery and affect human thinking, interaction, decision-making, and communication. To address these issues, there is a need for a framework to guide and help future AI developers make ethically responsible decisions. In this paper we propose a framework to foster ethical awareness and promote respect for human dignity and well-being, while also preventing harm. It is designed to be incorporated into technology education, ensuring that future professionals are equipped to navigate the ethical implications of AI. By prioritizing ethical reasoning in technology education, we can build a better and more responsible AI industry, ensuring that AI can provide benefits for society and does not cause harm. Additionally, a tech industry that values ethics and social responsibility will be better equipped to build technology that serves the public interest, rather than solely maximizing profits. Teaching ethical reasoning in technology education is a crucial step in preparing future professionals to make informed and ethical decisions in the development and use of AI systems. It will lead to a better and more responsible AI industry that benefits all of society.