Filippo Betello

ORCID: 0009-0006-0945-9688
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Recommender Systems and Techniques
  • Topic Modeling
  • Image Retrieval and Classification Techniques
  • AI in cancer detection
  • Brain Tumor Detection and Classification
  • Colorectal Cancer Screening and Detection
  • Spam and Phishing Detection
  • Neuroscience and Neural Engineering
  • Explainable Artificial Intelligence (XAI)
  • Bayesian Modeling and Causal Inference
  • EEG and Brain-Computer Interfaces
  • Sentiment Analysis and Opinion Mining
  • Neural dynamics and brain function
  • Advanced Bandit Algorithms Research
  • Mycobacterium research and diagnosis
  • Generative Adversarial Networks and Image Synthesis

Sapienza University of Rome
2023-2024

Breast cancer is the most widespread neoplasm among women and early detection of this disease critical. Deep learning techniques have become great interest to improve diagnostic performance. However, distinguishing between malignant benign masses in whole mammograms poses a challenge, as they appear nearly identical an untrained eye, region (ROI) constitutes only small fraction entire image. In paper, we propose framework, parameterized hypercomplex attention maps (PHAM), overcome these...

10.1016/j.patrec.2024.04.014 article EN cc-by Pattern Recognition Letters 2024-04-18

Visual neural decoding, namely the ability to interpret external visual stimuli from patterns of brain activity, is a challenging task in neuroscience research. Recent studies have focused on characterizing activity across multiple neurons that can be described terms population-level features. In this study, we combine spatial, spectral, and temporal features achieve manifold classification capable characterize perception simulate working memory human brain. We treat spatio-temporal spectral...

10.1016/j.neucom.2024.127654 article EN cc-by-nc-nd Neurocomputing 2024-04-15

Sequential Recommender Systems (SRSs) are widely used to model user behavior over time, yet their robustness remains an under-explored area of research. In this paper, we conduct empirical study assess how the presence fake users, who engage in random interactions, follow popular or unpopular items, focus on a single genre, impacts performance SRSs real-world scenarios. We evaluate two SRS models across multiple datasets, using established metrics such as Normalized Discounted Cumulative...

10.48550/arxiv.2410.09936 preprint EN arXiv (Cornell University) 2024-10-13

Sequential Recommender Systems (SRSs) have emerged as a highly efficient approach to recommendation systems. By leveraging sequential data, SRSs can identify temporal patterns in user behaviour, significantly improving accuracy and relevance.Ensuring the reproducibility of these models is paramount for advancing research facilitating comparisons between them. Existing works exhibit shortcomings replicability results, leading inconsistent statements across papers. Our work fills gaps by...

10.48550/arxiv.2408.03873 preprint EN arXiv (Cornell University) 2024-08-07

Deep image inpainting is a computer vision task that uses Neural Networks to generate plausible content complete an image, for example the restoration of damaged or removal unwanted elements captured in picture. This paper deep restore endoscopic images are affected by various types artifacts. To this end, we developed transfer learning-based procedure CSA model, which was originally proposed unrelated tasks including from Paris StreetView Dataset. The system trained and validated on...

10.1109/med59994.2023.10185683 article EN 2023-06-26

Sequential Recommender Systems (SRSs) are widely employed to model user behavior over time. However, their robustness in the face of perturbations training data remains a largely understudied yet critical issue. A fundamental challenge emerges previous studies aimed at assessing SRSs: Rank-Biased Overlap (RBO) similarity is not particularly suited for this task as it designed infinite rankings items and thus shows limitations real-world scenarios. For instance, fails achieve perfect score 1...

10.48550/arxiv.2307.13165 preprint EN cc-by arXiv (Cornell University) 2023-01-01

Breast cancer is the most widespread neoplasm among women and early detection of this disease critical. Deep learning techniques have become great interest to improve diagnostic performance. Nonetheless, discriminating between malignant benign masses from whole mammograms remains challenging due them being almost identical an untrained eye region (ROI) occupying a minuscule portion entire image. In paper, we propose framework, parameterized hypercomplex attention maps (PHAM), overcome these...

10.48550/arxiv.2310.07633 preprint EN cc-by arXiv (Cornell University) 2023-01-01
Coming Soon ...