Massimo Martinelli
YOU?
Author Swipe
View article: Batch-CAM: Introduction to better reasoning in convolutional deep learning models
Batch-CAM: Introduction to better reasoning in convolutional deep learning models Open
Understanding the inner workings of deep learning models is crucial for advancing artificial intelligence, particularly in high-stakes fields such as healthcare, where accurate explanations are as vital as precision. This paper introduces …
View article: Unraveling the cellular mechanisms of thiopurine-induced pancreatitis in pediatric inflammatory bowel disease: Insights from induced pluripotent stem cell models
Unraveling the cellular mechanisms of thiopurine-induced pancreatitis in pediatric inflammatory bowel disease: Insights from induced pluripotent stem cell models Open
Thiopurines are effective drugs for inflammatory bowel disease, but their use is limited by side effects such as pancreatitis, whose mechanism remains unknown and may be more severe in children. This study investigated in a personalized wa…
View article: Testing for Faecal Gluten Immunogenic Peptides: Is It Useful to Evaluate Adherence to Gluten‐Free Diet?
Testing for Faecal Gluten Immunogenic Peptides: Is It Useful to Evaluate Adherence to Gluten‐Free Diet? Open
Aim Determination of faecal gluten immunogenic peptides (f‐GIP) has recently been proposed as new noninvasive method to detect gluten intake in celiac disease (CD). Our aim was to evaluate the use of f‐GIP for the adherence to gluten‐free …
View article: Blended diets and effects on gastrointestinal symptoms in children with gastrostomy tubes: A survey study
Blended diets and effects on gastrointestinal symptoms in children with gastrostomy tubes: A survey study Open
Objectives Interest is growing in the use of blended diets (BD) in children with gastrostomy. Evidence supporting the benefits of BD is conflicting, with limited data to assist physicians in clinical practice. The present survey aims to ev…
View article: GranoScan: an AI-powered mobile app for in-field identification of biotic threats of wheat
GranoScan: an AI-powered mobile app for in-field identification of biotic threats of wheat Open
Capitalizing on the widespread adoption of smartphones among farmers and the application of artificial intelligence in computer vision, a variety of mobile applications have recently emerged in the agricultural domain. This paper introduce…
View article: Research initiatives for advancing sustainability @SI-Lab
Research initiatives for advancing sustainability @SI-Lab Open
The presentation was delivered at the workshop "Ai for sustainability" held at ITAL-IA, 29-30 May 2024, Naples.
View article: Remote Sensing for Maritime Traffic Understanding
Remote Sensing for Maritime Traffic Understanding Open
The capability of prompt response in the case of critical circumstances occurring within a maritime scenario depends on the awareness level of the competent authorities. From this perspective, a quick and integrated surveillance service re…
View article: Deep learning methods for point-of-care ultrasound examination
Deep learning methods for point-of-care ultrasound examination Open
Point-of-care Test (POCT) is the delivery of medical care at or near the patient's bedside. Primarily employed in emergencies, where rapid diagnosis and treatment are critical, POCT is now being used in domestic telehealth solutions, as in…
View article: Efficient Deep Learning Approach for Olive Disease Classification
Efficient Deep Learning Approach for Olive Disease Classification Open
From ancient times olive tree cultivation has been one of the most crucial agricultural activities for Mediterranean countries.In recent years, the role of Artificial Intelligence in agriculture is increasing: its use ranges from monitorin…
View article: AI for Health and Well Being @SI Lab
AI for Health and Well Being @SI Lab Open
This presentation was delivered in the framework of a bilateral meeting between CNR and IVI on September 5, 2023.
View article: Are We Using Autoencoders in a Wrong Way?
Are We Using Autoencoders in a Wrong Way? Open
Autoencoders are certainly among the most studied and used Deep Learning models: the idea behind them is to train a model in order to reconstruct the same input data. The peculiarity of these models is to compress the information through a…
View article: Efficient adaptive ensembling for image classification
Efficient adaptive ensembling for image classification Open
In recent times, with the exception of sporadic cases, the trend in computer vision is to achieve minor improvements compared to considerable increases in complexity. To reverse this trend, we propose a novel method to boost image classifi…
View article: Editorial: Artificial intelligence in point of care diagnostics
Editorial: Artificial intelligence in point of care diagnostics Open
EDITORIAL article Front. Digit. Health, 11 July 2023Sec. Health Informatics Volume 5 - 2023 | https://doi.org/10.3389/fdgth.2023.1236178
View article: Explaining Ensemble Models for Lung ultrasound Classification
Explaining Ensemble Models for Lung ultrasound Classification Open
Correct classification is the main aspect in evaluating the quality of an artificial intelligence system, but what happens when you reach top accuracy and no method explains how it works? In our study, we aim at addressing the black-box pr…
View article: Efficient Lung Ultrasound Classification
Efficient Lung Ultrasound Classification Open
A machine learning method for classifying lung ultrasound is proposed here to provide a point of care tool for supporting a safe, fast, and accurate diagnosis that can also be useful during a pandemic such as SARS-CoV-2. Given the advantag…
View article: Efficient Lung Ultrasound Classification
Efficient Lung Ultrasound Classification Open
A machine learning method for classifying Lung UltraSound is here proposed to pro- vide a point of care tool for supporting a safe, fast and accurate diagnosis, that can also be useful during a pandemic like as SARS-CoV-2. Given the advant…
View article: A phenotyping weeds image dataset for open scientific research
A phenotyping weeds image dataset for open scientific research Open
This in-house-built image dataset consists of 10810 weed images captured through a dedicated phenotyping activity in quasi-field conditions. The targets are seven of the most widespread and hard-to-control weeds in wheat (but also in other…
View article: A phenotyping weeds image dataset for open scientific research
A phenotyping weeds image dataset for open scientific research Open
This in-house-built image dataset consists of 10810 weed images captured through a dedicated phenotyping activity in quasi-field conditions. The targets are seven of the most widespread and hard-to-control weeds in wheat (but also in other…
View article: Medical-Waste-4.0-Dataset: v0.1
Medical-Waste-4.0-Dataset: v0.1 Open
This dataset was acquired in the framework of the Medical Waste Treating 4.0 funded by the Tuscany Region. The dataset aims to be a valuable resource for devising and testing computer vision methods for the primary sorting of medical waste…
View article: Medical-Waste-4.0-Dataset: v0.1
Medical-Waste-4.0-Dataset: v0.1 Open
This dataset was acquired in the framework of the Medical Waste Treating 4.0 funded by the Tuscany Region. The dataset aims to be a valuable resource for devising and testing computer vision methods for the primary sorting of medical waste…
View article: Improving plant disease classification by adaptive minimal ensembling
Improving plant disease classification by adaptive minimal ensembling Open
A novel method for improving plant disease classification, a challenging and time-consuming process, is proposed. First, using as baseline EfficientNet, a recent and advanced family of architectures having an excellent accuracy/complexity …
View article: Efficient Adaptive Ensembling for Image Classification
Efficient Adaptive Ensembling for Image Classification Open
In recent times, with the exception of sporadic cases, the trend in Computer Vision is to achieve minor improvements compared to considerable increases in complexity. To reverse this trend, we propose a novel method to boost image classifi…
View article: Colonic Function Investigations in Children
Colonic Function Investigations in Children Open
Disorders of colonic motility, most often presenting as constipation, comprise one of the commonest causes of outpatient visits in pediatric gastroenterology. This review, discussed and created by the European Society for Pediatric Gastroe…
View article: Augmented reality, artificial intelligence and machine learning in Industry 4.0: case studies at SI-Lab
Augmented reality, artificial intelligence and machine learning in Industry 4.0: case studies at SI-Lab Open
In recent years, the impressive advances in artificial intelligence, computer vision, pervasive computing, and augmented reality made them rise to pillars of the fourth industrial revolution. This short paper aims to provide a brief survey…
View article: Augmented reality, artificial intelligence and machine learning in Industry 4.0: case studies at SI-Lab
Augmented reality, artificial intelligence and machine learning in Industry 4.0: case studies at SI-Lab Open
In recent years, the impressive advances in artificial intelligence, computer vision, pervasive computing, and augmented reality made them rise to pillars of the fourth industrial revolution. This short paper aims to provide a brief survey…
View article: SI-Lab Annual Research Report 2021
SI-Lab Annual Research Report 2021 Open
The Signal & Images Laboratory (SI-Lab) is an interdisciplinary research group in computer vision, signal analysis, intelligent vision systems and multimedia data understanding. It