Repositório IC-Online
Institution's Scientific Repository
Recent Submissions
Enhancing Customer Experience Through IIoT-Driven Coopetition: A Service-Dominant Logic Approach in Networks
Publication . da Silva, Agostinho Antunes; Cardoso, Antonio J. Marques
Background: In an increasingly digitized supply chain landscape, small and medium-sized enterprises (SMEs) face mounting challenges in regard to delivering differentiated and responsive customer experiences. This study investigates the role of Industrial Internet of Things-enabled coopetition networks (IIoT-CNs) in enhancing the customer experience and value cocreation among SMEs. Grounded in Service-Dominant Logic, this research explores how interfirm collaboration and real-time data integration influence key performance indicators (KPIs), including perceived product quality, delivery timeliness, packaging standards, and product performance. Methods: An experimental design involving SMEs in Portugal’s ornamental stone sector contrasts traditional operations with digitally integrated coopetition practices. Results: While individual KPI improvements were not statistically significant, regression analysis revealed a significant positive relationship between IIoT-CN participation and the overall customer experience. The reduced variance in the performance metrics further suggests increased consistency and reliability across the network. Conclusions: These findings highlight IIoT-CNs as a promising model for SME digital transformation, contingent on trust, interoperability, and collaborative governance. This study contributes empirical evidence and practical insights for advancing customer-centric innovation in SME-dominated supply chains.
All-digital reconfigurable STDCC radar baseband implementation in FPGA
Publication . Duarte, Luís; Ribeiro, Carlos; Alves, Luís N.; Caldeirinha, Rafael F. S.
This paper reports the architecture of an all-digital Swept Time-Delay Cross-Correlator (STDCC) baseband. Until recently, the sliding correlator technique has been mainly em-ployed for sounding the radio propagation channel. However, recent benchmarks have shown promising results in target detection context when compared to commercially available solutions. STDCC takes advantage of the sliding correlation properties of Pseudo-Noise (PN) sequences. Therefore, this paper presents the baseband generation for this new radar technique with on-the-fly sequence tuning using a Field-Programmable Gate Array (FPGA). The reconfigurable STDCC radar baseband generates both PN sequences digitally and requires a low-cost ADC to acquire the time dilated result. At the end, the proposed architecture is evaluated regarding resource usage efficiency and then the radar performance will be discussed in terms of the all-digital PN sequence spectrum and the real-time slide correlation. Our analysis confirmed a strong correlation between both sequence length and sampling frequency with radar detectable distance.
Bibliometric Analysis of Key Variables in Tourism: Destination, Competitiveness, Image, Quality, and Tourist Satisfaction (2000–2023)
Publication . Pereira, José Marques; Almeida, Paulo; Almeida, Giovana Goretti Feijó
In the scientific literature on tourism, a set of variables is frequently utilized. The objective of this study is to analyze the scenario of scientific publications on these variables between 2000 and 2023. This analysis employs a bibliometric approach, utilizing data collected from the Scopus database. The bibliometric method was employed, with a focus on five variables (tourism destination, competitiveness, image, quality, and satisfaction) and five indicators (author, year, country, journal, and affiliation) essential for mapping research patterns and identifying key trends in the field of tourism. The findings demonstrate that the five variables under examination are inherently interrelated. The image of the destination is of particular importance, as it influences the quality of life of residents and the experiences of tourists, which in turn affects the competitiveness of the destination. The results also demonstrate the multidimensional nature of these variables in shaping
tourism destination dynamics. This study underscores the value of bibliometric analysis as a strategic tool for synthesizing and deepening tourism literature. The findings not only highlight the primary research contributions and trends but also identify gaps and opportunities for future research, thereby promoting continuous advancement in tourism knowledge and best practices.
Fast video encoding based on random forests
Publication . Tahir, Muhammad; Taj, Imtiaz A.; Assuncao, Pedro A. A.; Asif, Muhammad
Machine learning approaches have been increasingly used to reduce the high computational complexity of high-efficiency video coding (HEVC), as this is a major limiting factor for real-time implementations, due to the decision process required to find optimal coding modes and partition sizes for the quad-tree data structures defined by the standard. This paper proposes a systematic approach to reduce the computational complexity of HEVC based on an ensemble of online and offline Random Forests classifiers. A reduced set of features for training the Random Forests classifier is proposed, based on the rankings obtained from information gain and a wrapper-based approach. The best model parameters are also obtained through a consistent and generalizable method. The proposed Random Forests classifier is used to model the coding unit and transform unit-splitting decision and the SKIP-mode prediction, as binary classification problems, taking advantage from the combination of online and offline approaches, which adapts better to the dynamic characteristics of video content. Experimental results show that, on average, the proposed approach reduces the computational complexity of HEVC by 62.64% for the random access (RA) profile and 54.57% for the low-delay (LD) main profile, with an increase in BD-Rate of 2.58% for RA and 2.97% for LD, respectively. These results outperform the previous works also using ensemble classifiers for the same purpose.
ROI -BASED CODING OF BIOMEDICAL IMAGES FOR MACHINE ANALYSIS
Publication . Nicolau, Daniel Filipe da Silva; Faria, Sérgio Manuel Maciel de; Távora, Luís Miguel de Oliveira Pegado de Noronha e; Thomaz, Lucas Arrabal
The increasing volume of data acquired and generated daily in the healthcare sector,
driven by technological advancements, brings significant benefits to patient diagnosis
and research. However, this growth also presents considerable challenges in the
analysis and processing of such data. To address these difficulties, computer vision
algorithms have emerged as powerful tools, capable of automating repetitive and
time-consuming tasks, enabling faster and more accurate processing.
At the same time, the growing volume of data places pressure on storage and
transmission capabilities, demanding efficient compression methods to minimise
its size. In the literature, various approaches are found, primarily divided into
two categories: lossy and lossless compression. While lossless methods ensure data
integrity, they do not achieve compression rates as high as lossy algorithms. The
latter, despite significantly reducing file sizes, introduces distortions that may
compromise image quality, affecting the accuracy of automated systems.
This dissertation focuses on two main challenges: first, evaluating the impact of
image compression on the performance of biomedical computer vision systems, and
second, improving compression efficiency without compromising the accuracy of
these algorithms. To this end, detection and segmentation models, such as YOLOv8
and SAM, were used to analyse the effect of distortion caused by encoding on the
localisation and segmentation of mitochondria in two datasets of electron microscopy
images.
To enhance model performance at higher compression levels, two methodologies
were implemented. The first focuses on domain adaptation, fine-tuning the models
to recognise and compensate for distortions introduced by compression, specifically
in HEVC/H.265 and VVC/H.266 encoders. The second approach proposes contentaware
encoder adaptation, allowing the assignment of different quality levels to
selected regions of interest. This method aims to reduce storage and bandwidth
requirements without significantly compromising the performance of deep learningbased
models.
Experimental results demonstrate that region-of-interest-based encoding strategies
effectively reduce compression rates while maintaining model accuracy. In particular,
the proposed methodologies allowed to achieve an average performance improvement
of up to 23.70% for the same bpp range and a data size reduction of up to 74.96%.
Additionally, a Pareto-based optimisation algorithm was proposed to determine the most suitable encoding configurations for different standards and models, ensuring
a balance between compression efficiency and object detection performance.