A5046880480- Cloud Computing and Resource Management
- IoT and Edge/Fog Computing
- Parallel Computing and Optimization Techniques
- Distributed and Parallel Computing Systems
- Scientific Computing and Data Management
- Mobile Crowdsensing and Crowdsourcing
- Software System Performance and Reliability
- Anomaly Detection Techniques and Applications
- Embedded Systems Design Techniques
- Big Data and Business Intelligence
- Human Mobility and Location-Based Analysis
- Caching and Content Delivery
- Constraint Satisfaction and Optimization
- Industrial Vision Systems and Defect Detection
- Manufacturing Process and Optimization
- Energy Efficient Wireless Sensor Networks
- Transportation and Mobility Innovations
- Neural Networks and Applications
- Data Stream Mining Techniques
- Advanced Memory and Neural Computing
- Auction Theory and Applications
- Green IT and Sustainability
- Privacy-Preserving Technologies in Data
- Gaze Tracking and Assistive Technology
- Distributed Sensor Networks and Detection Algorithms
Politecnico di Milano
2021-2025
University of Tabriz
2014-2022
This paper proposes an auto-profiling tool for OSCAR, open-source platform able to support serverless computing in cloud and edge environments. The tool, named OSCAR-P, is designed automatically test a specified application workflow on different hardware node combinations, obtaining relevant information the execution time of individual components. It then uses collected data build performance models using machine learning, making it possible predict unseen configurations. preliminary...
The recent migration towards Internet of Things determined the rise a Computing Continuum paradigm where Edge and Cloud resources coordinate to support execution Artificial Intelligence (AI) applications, becoming foundation use-cases spanning from predictive maintenance machine vision healthcare. This generates fragmented scenario computing storage power are distributed among multiple devices with highly heterogeneous capacities. runtime management AI applications executed in is...
Artificial Intelligence (AI) and Deep Learning (DL) are pervasive today, with applications spanning from personal assistants to healthcare. Nowadays, the accelerated migration towards mobile computing Internet of Things, where a huge amount data is generated by widespread end devices, determining rise edge paradigm, resources distributed among devices highly heterogeneous capacities. In this fragmented scenario, efficient component placement resource allocation algorithms crucial orchestrate...
Mobile Crowdsensing (MCS) is a new paradigm that leverages the collective sensing ability of crowd so special task can be performed through aggregation information collected from personal mobile devices. While MCS brings several benefits, its application prevented by challenges such as efficient recruitment users, effective mechanisms for rewarding users to encourage participation, and an fast enough approach managing underlying resources support large-scale applications involving large...
Artificial Intelligence (AI) and Deep Learning (DL) are pervasive today, with applications spanning from personal assistants to healthcare. Nowadays, the accelerated migration towards mobile computing Internet of Things, where a huge amount data is generated by widespread end devices, determining rise edge paradigm, resources distributed among devices highly heterogeneous capacities. In this fragmented scenario, efficient component placement resource allocation algorithms crucial orchestrate...
This paper proposes an automated framework for efficient application profiling and training of Machine Learning (ML) performance models, composed two parts: OSCAR-P aMLLibrary. is auto-profiling tool designed to automatically test serverless workflows running on multiple hardware node combinations in cloud edge environments. obtains relevant information the execution time individual components. These data are later used by aMLLibrary train ML-based models. makes it possible predict...
The adoption of Artificial intelligence (AI) technologies is steadily increasing. However, to become fully pervasive, AI needs resources at the edge network. cloud can provide processing power needed for big data, but computing close where data are produced and therefore crucial their timely, flexible, secure management. In this paper, we introduce AI-SPRINT project, which will solutions seamlessly design, partition, run applications in continuum environments. offer novel tools development,...
The most challengeable issue in wireless sensor networks is the limited energy of their nodes that are distributed a field for collecting information from environment.Thus, efficiency and lifetime these consider one important controversial issues this field.In paper, new effective routing algorithm presented which based on static clustering multi-hop transmission.The SCMR (Static Clustering Based Multi-hop Routing) Algorithm verified with MATLAB simulator.Simulation results show method...
Artificial Intelligence (AI) applications are gaining popularity as they seamlessly integrate into end-user devices, enhancing the quality of life. In recent years, there has been a growing focus on designing Smart Eye-Wear (SEW) that can optimize user experiences based specific usage domains. However, SEWs face limitations in computational capacity and battery This paper investigates SEW proposes an algorithm to minimize energy consumption 5G connection costs while ensuring high...