1,720,974 research outputs found
Time series forecasting for predictive maintenance of refrigeration systems
No full textPredictive maintenance is a fundamental task in the context of Industry 4.0 to achieve high quality standards by optimizing interventions, before the actual occurrence of faults. Over the year, several machine learning techniques have been exploited to obtain models providing high fault detection accuracy, and, in general, proposed solutions consider it either as a classification or a regression task. Generally speaking, regression approaches requires more data but can obtain more refined results when it comes to the prediction of when a fault will happen. In this paper, we provide a contribution in this context by focusing on a scenario composed of industrial refrigeration systems, typically located in supermarkets, and studying the possibility of applying a Time Series Prediction approach to build an unsupervised predictive maintenance solution. In our investigation, we considered the SARIMAX model and verified, through an experimental campaign on real data, its adequateness for Automatic Fault Detection and Diagnostic (AFDD)
PhotoStyle60: A Photographic Style Dataset for Photo Authorship Attribution and Photographic Style Transfer
No full textPhotography, like painting, allows artists to express themselves through their unique style. In digital photography, this is achieved not only with the choice of the subject and the composition but also by means of post-processing operations. The automatic identification of a photographer from the style of a photo is a challenging task, for many reasons, including the lack of suitable datasets including photos taken by a diverse panel of photographers with a clear photographic style. In this paper we present PhotoStyle60, a new dataset including 5708 photographs from 60 professional and semi-professional photographers. Additionally, we selected a reduced version of the dataset, called PhotoStyle10 containing images from 10 clearly distinguishable experts. We designed the dataset to address two tasks in particular: photo authorship attribution and photographic style transfer. In the former, we conducted an extensive analysis of the dataset through several classification experiments. In the latter, we explored the potential of our dataset to transfer a photographer’s style to images from the Five-K dataset. Additionally, we propose also a simple but effective multi-image style transfer method that uses multiple samples of the target style. A user study demonstrated that such a method was able to reach accurate results, preserving the semantic content of the source photograph with very few artifacts
Semantic Hierarchical Indexing for Online Video Lessons Using Natural Language Processing
No full textHuge quantities of audio and video material are available at universities and teaching institutions, but their use can be limited because of the lack of intelligent search tools. This paper describes a possible way to set up an indexing scheme that offers a smart search modality, that combines semantic analysis of video/audio transcripts with the exact time positioning of uttered words. The proposal leverages NLP methods for topic modeling with lexical analysis of lessons’ transcripts and builds a semantic hierarchical index into the corpus of lessons analyzed. Moreover, using abstracting summarization, the system can offer short summaries on the subject semantically implied by the search carried out
The SemIoE Ontology: A Semantic Model Solution for an IoE-Based Industry
Full text linkRecently, the Industry 5.0 is gaining attention as a novel paradigm, defining the next concrete steps toward more and more intelligent, green-aware and user-centric digital systems. In an era in which smart devices typically adopted in the industry domain are more and more sophisticated and autonomous, the Internet of Things and its evolution, known as the Internet of Everything (IoE, for short), involving also people, robots, processes and data in the network, represent the main driver to allow industries to put the experiences and needs of human beings at the center of their ecosystems. However, due to the extreme heterogeneity of the involved entities, their intrinsic need and capability to cooperate, and the aim to adapt to a dynamic user-centric context, special attention is required for the integration and processing of the data produced by such an IoE. This is the objective of the present paper, in which we propose a novel semantic model that formalizes the fundamental actors, elements and information of an IoE, along with their relationships. In our design, we focus on state-of-the-art design principles, in particular reuse, and abstraction, to build 'SemIoE', a lightweight ontology inheriting and extending concepts from well-known and consolidated reference ontologies. The defined semantic layer represents a core data model that can be extended to embrace any modern industrial scenario. It represents the base of an IoE Knowledge Graph, on top of which, as an additional contribution, we analyze and define some essential services for an IoE-based industry
A Fully Privacy-Preserving Solution for Anomaly Detection in IoT using Federated Learning and Homomorphic Encryption
Full text linkAnomaly detection for the Internet of Things (IoT) is a very important topic in the context of cyber-security. Indeed, as the pervasiveness of this technology is increasing, so is the number of threats and attacks targeting smart objects and their interactions. Behavioral fingerprinting has gained attention from researchers in this domain as it represents a novel strategy to model object interactions and assess their correctness and honesty. Still, there exist challenges in terms of the performance of such AI-based solutions. The main reasons can be alleged to scalability, privacy, and limitations on adopted Machine Learning algorithms. Indeed, in classical distributed fingerprinting approaches, an object models the behavior of a target contact by exploiting only the information coming from the direct interaction with it, which represents a very limited view of the target because it does not consider services and messages exchanged with other neighbors. On the other hand, building a global model of a target node behavior leveraging the information coming from the interactions with its neighbors, may lead to critical privacy concerns. To face this issue, the strategy proposed in this paper exploits Federated Learning to compute a global behavioral fingerprinting model for a target object, by analyzing its interactions with different peers in the network. Our solution allows the training of such models in a distributed way by relying also on a secure delegation strategy to involve less capable nodes in IoT. Moreover, through homomorphic encryption and Blockchain technology, our approach guarantees the privacy of both the target object and the different workers, as well as the robustness of the strategy in the presence of attacks. All these features lead to a secure fully privacy-preserving solution whose robustness, correctness, and performance are evaluated in this paper using a detailed security analysis and an extensive experimental campaign. Finally, the performance of our model is very satisfactory, as it consistently discriminates between normal and anomalous behaviors across all evaluated test sets, achieving an average accuracy value of 0.85
A deep reinforcement learning approach for security-aware service acquisition in IoT
No full textThe emerging Internet of Things (IoT) landscape is characterized by a high number of heterogeneous smart devices and services often provided by third parties. Although machine-based Service Level Agreements (SLA) have been recently leveraged to establish and share policies in this scenario, system owners do not always give full transparency regarding the security and privacy of the offered features. Hence, the issue of making end users aware of the overall system security levels and the fulfillment of their privacy requirements through the provision of the requested service remains a challenging task. To tackle this problem, we propose a complete framework that allows users to choose suitable levels of privacy and security requirements for service acquisition in IoT. Our approach leverages a Deep Reinforcement Learning solution in which a user agent, inside the environment, is trained to select the best encountered smart objects providing the user target services on behalf of its owner. This strategy is designed to allow the agent to learn from experience by moving in a complex, multi-dimensional environment and reacting to possible changes. During the learning phase, a key task for the agent is to adhere to deadlines while ensuring user security and privacy requirements. Finally, to assess the performance of the proposed approach, we carried out an extensive experimental campaign. The obtained results also show that our solution can be successfully deployed on very basic and simple devices typically available in an IoT setting
A novel IoT trust model leveraging fully distributed behavioral fingerprinting and secure delegation
No full textA defense mechanism against label inference attacks in Vertical Federated Learning
No full textVertical Federated Learning (VFL, for short) is a category of Federated Learning that is gaining increasing attention in the context of Artificial Intelligence. According to this paradigm, machine/deep learning models are trained collaboratively among parties with vertically partitioned data. Typically, in a VFL scenario, the labels of the samples are kept private from all parties except the aggregating server, that is, the label owner. However, recent work discovered that by exploiting the gradient information returned by the server to bottom models, with the knowledge of only a small set of auxiliary labels on a very limited subset of training data points, an adversary could infer the private labels. These attacks are known as label inference attacks in VFL. In our work, we propose a novel framework called KDk (knowledge distillation with k-anonymity) that combines knowledge distillation and k-anonymity to provide a defense mechanism against potential label inference attacks in a VFL scenario. Through an exhaustive experimental campaign, we demonstrate that by applying our approach, the performance of the analyzed label inference attacks decreases consistently, even by more than 60%, maintaining the accuracy of the whole VFL almost unaltered
Predicting Tweet Engagement with Graph Neural Networks
No full textSocial Networks represent one of the most important online sources to share content across a world-scale audience. In this context, predicting whether a post will have any impact in terms of engagement is of crucial importance to drive the profitable exploitation of these media. In the literature, several studies address this issue by leveraging direct features of the posts, typically related to the textual content and the user publishing it. In this paper, we argue that the rise of engagement is also related to another key component, which is the semantic connection among posts published by users in social media. Hence, we propose TweetGage, a Graph Neural Network solution to predict the user engagement based on a novel graph-based model that represents the relationships among posts. To validate our proposal, we focus on the Twitter platform and perform a thorough experimental campaign providing evidence of its quality
The role of social media on the evolution of companies: A Twitter analysis of Streaming Service Providers
No full textIn recent years, Social Networks and, in particular, Twitter have proved to be a fertile ground for those scholars and companies interested in exploring the effectiveness of brand marketing communications. This is even more true when it comes to TV Streaming Service Providers, such as Netflix or Amazon. For these types of companies, Twitter represents not only a valuable source of data for business intelligence, but also a connected and co-viewing platform and outage detection system. In this paper, we carry out our analysis by exploring and comparing, through disparate machine learning techniques and natural language processing solutions, the behavior of several Twitter accounts corresponding to different Streaming Service Providers by considering their possible stage in the Technology Adoption Life Cycle. Interestingly, such an analysis allows for the identification of the most suitable strategies that can be carried out on Twitter by Streaming Service Providers to improve the user involvement on the basis of their current stage. To the best of our knowledge, a complete analysis able to depict Twitter strategies of success for Streaming Service Providers does not exist in current literature yet
- …
