A5046871502- Mosquito-borne diseases and control
- Adversarial Robustness in Machine Learning
- Explainable Artificial Intelligence (XAI)
- IoT and Edge/Fog Computing
- AI and HR Technologies
- Machine Learning in Materials Science
- Domain Adaptation and Few-Shot Learning
- Complex Systems and Time Series Analysis
- Machine Learning and Data Classification
- Advanced Neural Network Applications
- Fault Detection and Control Systems
- COVID-19 epidemiological studies
- Digital Imaging for Blood Diseases
- Brain Tumor Detection and Classification
- Complex Systems and Decision Making
- Fractal and DNA sequence analysis
- Real-time simulation and control systems
- Smart Agriculture and AI
- COVID-19 diagnosis using AI
- Chaos control and synchronization
- Petri Nets in System Modeling
Iquadrat (Spain)
2025
Universitat Oberta de Catalunya
2021-2023
Kumoh National Institute of Technology
2016-2017
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 obtain large image datasets with linked geo-tracking information. As number international collaborators grows, manual annotation by expert entomologists amount data gathered these users becomes too time demanding unscalable, posing strong need for automated classification mosquito...
As technology evolves, its consumers gain considerable advantages to bring prosperity for all humankind. It is so in medical environment. Even though there always has been standards hospital or other related sites, it possible people with the help of study about simple theory pathology and find another mechanism meet those standards, i.e., create new method healing illnesses. For consumer use, creating can be a significant benefit case maximizing usability minimizing cost, inventing...
Knowledge distillation (KD) remains challenging due to the opaque nature of knowledge transfer process from a Teacher Student, making it difficult address certain issues related KD. To this, we proposed UniCAM, novel gradient-based visual explanation method, which effectively interprets learned during Our experimental results demonstrate that with guidance Teacher's knowledge, Student model becomes more efficient, learning relevant features while discarding those are not relevant. We refer...
The re-emergence of mosquito-borne diseases (MBDs), which kill hundreds thousands people each year, has been attributed to increased human population, migration, and environmental changes. Convolutional neural networks (CNNs) have used by several studies recognise mosquitoes in images provided projects such as Mosquito Alert assist entomologists identifying, monitoring, managing MBD. Nonetheless, utilising CNNs automatically label input samples could involve incorrect predictions, may...
Many samples are necessary to train a convolutional neural network (CNN) achieve optimum performance while maintaining generalizability. Several studies, however, have indicated that not all input data in large datasets informative for the model, and using them training can degrade model's add uncertainty. Furthermore, some domains, such as medicine, there is insufficient labelled deep learning model from scratch, necessitating use of transfer fine-tune pretrained another domain. This paper...
To equip Convolutional Neural Networks (CNNs) with explainability, it is essential to interpret how opaque models take specific decisions, understand what causes the errors, improve architecture design, and identify unethical biases in classifiers. This paper introduces ADVISE, a new explainability method that quantifies leverages relevance of each unit feature map provide better visual explanations. this end, we propose using adaptive bandwidth kernel density estimation assign score respect...