A5086347537- Online Learning and Analytics
- Online and Blended Learning
- Innovative Teaching and Learning Methods
- Intelligent Tutoring Systems and Adaptive Learning
- Image Retrieval and Classification Techniques
- Education and Technology Integration
- Mental Health Research Topics
- Multimodal Machine Learning Applications
- Emotion and Mood Recognition
- Sparse and Compressive Sensing Techniques
- EEG and Brain-Computer Interfaces
- Image Processing and 3D Reconstruction
- Advanced Image and Video Retrieval Techniques
- Digital Media Forensic Detection
- Child Development and Digital Technology
- Functional Brain Connectivity Studies
- Advanced Chemical Sensor Technologies
- Nutritional Studies and Diet
- Domain Adaptation and Few-Shot Learning
- Aesthetic Perception and Analysis
- Currency Recognition and Detection
- Blind Source Separation Techniques
- Impact of Technology on Adolescents
- Teacher Education and Leadership Studies
- Experimental Learning in Engineering
Intel (United States)
2014-2024
Ege University
2013-2023
Ca' Foscari University of Venice
2018-2023
Intel (United Kingdom)
2017-2022
Venice International University
2021
European Centre for Living Technology
2018-2021
University of Milano-Bicocca
2017-2018
Indiana University
2010-2017
We developed a real-time, multimodal Student Engagement Analytics Technology so that teachers can provide just-in-time personalized support to students who risk disengagement. To investigate the impact of technology, we ran an exploratory semester-long study with teacher in two classrooms. used multi-method approach consisting quasi-experimental design evaluate technology and case understand environmental social factors surrounding classroom setting. The results show had significant on...
Educational technology research has found that parents of young children widely share concerns about extended screen time, lack physical activity, and social interaction. Kid Space was developed to address these by enabling multi-modal immersive collaborative play-based learning. utilizes multiple sensing technologies with an space through a human-scale wall projection incorporates conversational AI agent interact children, understand individual progress, personalize learning experiences in...
Climate change presents a significant challenge to lagoon ecosystems, which are highly valued coastal environments known for their provision of unique ecosystem services. As important as fragile, lagoons vulnerable both natural processes and anthropogenic activities, this vulnerability is exacerbated by the impacts climate change, likely result in severe ecological consequences. The complexity water quality (WQ) processes, characterized compounding interconnected pressures, highlights...
The learner-centered paradigm of instruction differs in such fundamental ways from the teacher-centered that it requires technology to serve very different functions. In 2006, a research team at Indiana University began work on identifying those functions and published their results 2008. Subsequently, elaborated refined functional specifications, which are described herein as Personalized Integrated Educational System (PIES), system has not yet been developed support education. four major...
Compressive Sensing (CS) theory asserts that sparse signal reconstruction is possible from a small number of linear measurements. Although CS enables low-cost sampling, it requires non-linear and costly reconstruction. Recent literature works show compressive image classification in domain without the signal. In this work, we introduce DCT base method extracts binary discriminative features directly These measurements can be obtained by using (i) random or pseudorandom measurement matrix,...
We explore the feasibility of measuring learner engagement and classifying level based on machine learning applied data from 2D/3D camera sensors eye trackers in a 1:1 setting. Our results are nine pilot sessions held local high school where we recorded features related to student while consuming educational content. label collected as Engaged or NotEngaged observing videos students their screens. Based data, perceptual user (e.g., body posture, facial points, gaze) extracted. use feature...
Affective states play a crucial role in learning. Existing Intelligent Tutoring Systems (ITSs) fail to track affective of learners accurately. Without an accurate detection such states, ITSs are limited providing truly personalized learning experience. In our longitudinal research, we have been working towards developing empathic autonomous 'tutor' closely monitoring students real-time using multiple sources data understand their corresponding emotional engagement. We focus on detecting...
Although machine use in education was introduced the 1920s with instructional radio and 1950s television, these technologies lacked one of most important components learning - interaction. Computers have filled this void. The functions they served, ways been used, terms given changed since their introduction to our schools, but rooted presence educational lives has continually increased over time. Our in-depth review literature illustrated that there are three distinct periods computing...
Automatic food analysis has been an important task for not only personal dietary monitoring to treat and control health-related problems, but can also find usage at public environments such as smart restaurants where recommendations are made based on calorie counting. In applications a very crucial stage correct measurement is the accurate segmentation of regions. this work, we address semantic images with Deep Learning. Additionally, explore non-food by getting advantage supervised...
Since the spring of 2020, many early childhood education programs (pre-K, K, 1st, and 2nd grades) had to close as governments around world took serious measures slow down transmission COVID-19. As a result, pandemic forced teachers start teaching online continue supporting their students remotely. Unfortunately, there were few lessons that these could learn from experience cope with this change since learning in settings been scarce until outbreak pandemic. In response, goal interview study...
Learner-centered education has been touted as an improvement over teacher-centered educational systems. However, educators and researchers need to be cautious about its problems, in addition considering benefits. The authors set out identify challenges learner-centered through the eyes of a truly school with self-directed, project-based learning approach. During their interviews, three administrators all nine teachers described that they faced instruction assessment. hope is study makes...
In this paper, we investigate detection of students' behavioral engagement states (On-Task vs. Off-Task) in authentic classroom settings. We propose a multimodal approach, based on three unobtrusive modalities readily available 1:1 learning scenario where technologies are incorporated. These are: (1)Appearance: upper-body video captured using camera; (2) Context-Performance: interaction and performance data related to content; (3) Mouse: mouse movements during process. For each modality,...
Abstract Previous research showed that the parents acknowledged technology's benefits for their young children's learning, however, they are still worried about extended screen time, lack of physical activity and social interactions. To address these concerns, we developed Kid Space to enable pedagogically appropriate technology use children in early childhood education by combining various sensing technologies with a multi‐modal conversational artificial intelligence system can interact...