12 May 2021 in IEEE Access
Monitoring the spread of disease-carrying mosquitoes is a first and necessary step to control severe diseases such as dengue, chikungunya, Zika or yellow fever. Previous citizen science projects have been able to obtain large image datasets with linked geo-tracking information. As the number of international collaborators grows, the manual annotation by expert entomologists of the large amount of data gathered by these users becomes too time demanding and unscalable, posing a strong need for automated classification of mosquito species from images. We introduce the application of two Deep Convolutional Neural Networks in a comparative study to automate this classification task. We use the transfer learning principle to train two state-of-the-art architectures on the data provided by the Mosquito Alert project, obtaining testing accuracy of 94%. In addition, we applied explainable models based on the Grad-CAM algorithm to visualise the most discriminant regions of the classified images, which coincide with the white band stripes located at the legs, abdomen, and thorax of mosquitoes of the Aedes albopictus species. The model allows us to further analyse the classification errors. Visual Grad-CAM models show that they are linked to poor acquisition conditions and strong image occlusions.
17 January 2025 in IEEE Vehicular Technology Magazine
The 6G ecosystem is anticipated to encompass a diverse array of business actors, including mobile network operators, infrastructure providers, and service providers. Existing network management systems, which traditionally map technological and administrative domains on a one-to-one basis, are inadequate for managing such a complex environment. This necessitates innovative distributed architectures with varying levels of abstraction. To address these challenges, we present 6GINTENSE, a novel network management architecture designed to handle the distributed and heterogeneous nature of 6G through two key abstractions. First, the network-compute fabric component facilitates multi-domain mapping at the resource level by abstracting resource pools, including deep-edge nodes equipped with sensing capabilities. Second, the domain manager and orchestrator serves as a central entity for service orchestration, providing a global perspective on the infrastructure. The proposed architecture leverages the intent-based networking paradigm at all architectural layers, emphasizing its critical role in enabling autonomous networks. Furthermore, it integrates an innovative native artificial intelligence toolkit, which is pervasive across all layers.
27 October 2021 in IEEE Journal of Selected Topics in Signal Processing
The re-emergence of mosquito-borne diseases (MBDs), which kill hundreds of thousands of people each year, has been attributed to increased human population, migration, and environmental changes. Convolutional neural networks (CNNs) have been used by several studies to recognise mosquitoes in images provided by projects such as Mosquito Alert to assist entomologists in identifying, monitoring, and managing MBD. Nonetheless, utilising CNNs to automatically label input samples could involve incorrect predictions, which may mislead future epidemiological studies. Furthermore, CNNs require large numbers of manually annotated data. In order to address the mentioned issues, this paper proposes using the Monte Carlo Dropout method to estimate the uncertainty scores in order to rank the classified samples to reduce the need for human supervision in recognising Aedes albopictus mosquitoes. The estimated uncertainty was also used in an active learning framework, where just a portion of the data from large training sets was manually labelled. The experimental results show that the proposed classification method with rejection outperforms the competing methods by improving overall performance and reducing entomologist annotation workload. We also provide explainable visualisations of the different regions that contribute to a set of samples’ uncertainty assessment.
10 October 2023 in The Visual Computer