A5083456765- Industrial Vision Systems and Defect Detection
- Artificial Intelligence in Healthcare
- Machine Learning in Healthcare
- Stroke Rehabilitation and Recovery
- Context-Aware Activity Recognition Systems
- Time Series Analysis and Forecasting
- Emotion and Mood Recognition
- Human Pose and Action Recognition
- Cerebral Palsy and Movement Disorders
- Digital Transformation in Industry
- Balance, Gait, and Falls Prevention
- Autism Spectrum Disorder Research
- Face and Expression Recognition
- Fault Detection and Control Systems
- COVID-19 diagnosis using AI
- Advanced Steganography and Watermarking Techniques
- Blockchain Technology Applications and Security
- Face recognition and analysis
- EEG and Brain-Computer Interfaces
- Digital Media Forensic Detection
- Machine Fault Diagnosis Techniques
- Imbalanced Data Classification Techniques
- Non-Invasive Vital Sign Monitoring
- Neurological disorders and treatments
- Cryptographic Implementations and Security
Marche Polytechnic University
2015-2024
University of Macerata
2022-2024
Italian Institute of Technology
2018-2024
Condition monitoring together with predictive maintenance of electric motors and other equipment used by the industry avoids severe economic losses resulting from unexpected motor failures greatly improves system reliability. This paper describes a Machine Learning architecture for Predictive Maintenance, based on Random Forest approach. The was tested real example, developing data collection analysis, applying approach comparing it to simulation tool analysis. Data has been collected...
Abstract The Internet of Things (IoT), Big Data and Machine Learning (ML) may represent the foundations for implementing concept intelligent production, smart products, services, predictive maintenance (PdM). majority state-of-the-art ML approaches PdM use different condition monitoring data (e.g. vibrations, currents, temperature, etc.) run to failure predicting Remaining Useful Lifetime components. However, annotation component wear is not always easily identifiable, thus leading open...
As COVID-19 hounds the world, common cause of finding a swift solution to manage pandemic has brought together researchers, institutions, governments, and society at large. The Internet Things (IoT), artificial intelligence (AI)-including machine learning (ML) Big Data analytics-as well as Robotics Blockchain, are four decisive areas technological innovation that have been ingenuity harnessed fight this future ones. While these highly interrelated smart connected health technologies cannot...
As reliance on disruptive applications based Artificial Intelligence (AI) and Blockchain grows, the need for secure trustworthy solutions becomes ever more critical. Whereas much research has been conducted AI Blockchain, there is a shortage of comprehensive studies examining their integration from security perspective. Hence, this survey addresses such gap provides insights policymakers, researchers, practitioners exploiting Blockchain's evolving integration. Specifically, paper analyzes...
Predictive Maintenance (PdM) is a prominent strategy comprising all the operational techniques and actions required to ensure machine availability prevent machine-down failure. One of main challenges PdM design develop an embedded smart system monitor predict health status machine. In this work, we use data-driven approach based on learning applied woodworking industrial machines for major Italian corporation. Predicted failures probabilities are calculated through tree-based classification...
The diagnosis of type 2 diabetes (T2D) at an early stage has a key role for adequate T2D integrated management system and patient's follow-up. Recent years have witnessed increasing amount available electronic health record (EHR) data machine learning (ML) techniques been considerably evolving. However, managing modeling this information may lead to several challenges, such as overfitting, model interpretability, computational cost. Starting from these motivations, we introduced ML method...
This paper proposes a free dataset, available at the following link,1named KIMORE, regarding different rehabilitation exercises collected by RGB-D sensor. Three data inputs including RGB, depth videos, and skeleton joint positions were recorded during five physical exercises, specific for low back pain accurately selected physicians. For each exercise, dataset also provides set of features, specifically defined physicians, relevant to describe its scope. These validated with respect...
In this work we propose a real-time detection of mental stress during different cognitive tasks. Stress is classified processing Galvanic Skin Response (GSR), RR Interval and Body Temperature (BT) acquired by commercial smartwatch. The unobtrusive system proposed validated through clinical psychological tests.
Accurate risk stratification of critically ill patients with coronavirus disease 2019 (COVID-19) is essential for optimizing resource allocation, delivering targeted interventions, and maximizing patient survival probability. Machine learning (ML) techniques are attracting increased interest the development prediction models as they excel in analysis complex signals data-rich environments such critical care.We retrieved data on COVID-19 admitted to an intensive care unit (ICU) between March...
Smart homes play a strategic role for improving life quality of people, enabling to monitor people at home with numerous intelligent devices. Sensors can be installed provide continuous assistance without limiting the resident’s daily routine, giving her/him greater comfort, well-being and safety. This paper is based on development domestic technological solutions improve citizens users environment, features extracted from collected data. The proposed smart sensing architecture an integrated...
In this paper, the accuracy evaluation of Kinect v2 sensor is investigated in a rehabilitation scenario. The analysis provided terms joint positions and angles during dynamic postures used low-back pain rehabilitation. Although other studies have focused on validation positions, they present results only considering static whereas exercise monitoring involves to consider movements with wide range motion issues related joints tracking. work, represent clinical features, chosen by medical...
Kidney Disease (KD) may hide complex causes and is associated with a tremendous socio-economic impact. Timely identification management from the first level of medical care represent most effective strategy to address growing global burden sustainably. Clinical practice guidelines suggest utilizing estimated Glomerular Filtration Rate (eGFR) for routine evaluation within screening purpose. Accordingly, analysis Electronic Health Records (EHRs) using Machine Learning techniques offers great...
Nonlinear substitutions or S-boxes are important cryptographic primitives of modern symmetric ciphers. They designed to complicate the plaintext-ciphertext dependency. According ideas, S-box should be bijective, have high nonlinearity and algebraic immunity, low delta uniformity, linear redundancy. These criteria directly affect strength ciphers, providing resistance statistical, linear, algebraic, differential, other cryptanalysis techniques. Many researchers used various heuristic search...
The missing data mechanism is a relevant problem in Machine Learning (ML) and biomedical informatics communities. Real-world Electronic Health Record (EHR) datasets comprise several values, thus revealing high level of spatiotemporal sparsity the predictors' matrix. Several approaches state-of-the-art tried to deal with this by proposing different imputation strategies that (i) are often unrelated ML model, (ii) not conceived for EHR where laboratory exams prescribed uniformly over time...
The problem of continuous emotion recognition has been the subject several studies. proposed affective computing approaches employ sequential machine learning algorithms for improving classification stage, accounting time ambiguity emotional responses. Modeling and predicting state over is not a trivial because data labeling costly always feasible. This crucial issue in real-life applications, where sparse possibly captures only most important events rather than typical subtle changes that...
This paper proposes a specific domotic sensor network to measure the well-being of elderly people in private home environments through Machine Learning (ML) algorithms trained with daily surveys. The tests have been conducted 5 apartments lived by 8 older where non-obtrusive is installed. Two ML are compared, Random Forest (RF) and Regression Tree (RT), such that verify whether users' encoded behavioural patterns obtained from data. These data used compared three reference indices survey:...