Personalised Federated Learning with BERT Fine Tuning. Case Study on Twitter Sentiment Analysis

2022 ◽  
pp. 193-202
Author(s):  
Jose Antonio Ruiz-Millán ◽  
Eugenio Martínez-Cámara ◽  
M. Victoria Luzón ◽  
Francisco Herrera
Keyword(s):  
Sentiment Analysis ◽  
Fine Tuning

scholarly journals Sparse Autoencoder-based Multi-head Deep Neural Networks for Machinery Fault Diagnostics with Detection of Novelties

2021 ◽  
Vol 34 (1) ◽  
Author(s):  
Zhe Yang ◽  
Dejan Gjorgjevikj ◽  
Jianyu Long ◽  
Yanyang Zi ◽  
Shaohui Zhang ◽  
...  
Keyword(s):  
Fault Diagnosis ◽  
Supervised Classification ◽  
Deep Neural Networks ◽  
Activation Function ◽  
Reconstruction Error ◽  
Fine Tuning ◽  
Fault Diagnostics ◽  
Sparse Autoencoder

AbstractSupervised fault diagnosis typically assumes that all the types of machinery failures are known. However, in practice unknown types of defect, i.e., novelties, may occur, whose detection is a challenging task. In this paper, a novel fault diagnostic method is developed for both diagnostics and detection of novelties. To this end, a sparse autoencoder-based multi-head Deep Neural Network (DNN) is presented to jointly learn a shared encoding representation for both unsupervised reconstruction and supervised classification of the monitoring data. The detection of novelties is based on the reconstruction error. Moreover, the computational burden is reduced by directly training the multi-head DNN with rectified linear unit activation function, instead of performing the pre-training and fine-tuning phases required for classical DNNs. The addressed method is applied to a benchmark bearing case study and to experimental data acquired from a delta 3D printer. The results show that its performance is satisfactory both in detection of novelties and fault diagnosis, outperforming other state-of-the-art methods. This research proposes a novel fault diagnostics method which can not only diagnose the known type of defect, but also detect unknown types of defects.

scholarly journals Sentiment Analysis of Lockdown in India During COVID-19: A Case Study on Twitter

2020 ◽  
pp. 1-11
Author(s):  
Prasoon Gupta ◽  
Sanjay Kumar ◽  
R. R. Suman ◽  
Vinay Kumar
Keyword(s):  
Sentiment Analysis

scholarly journals Using Social Media in Tourist Sentiment Analysis: A Case Study of Andalusia during the Covid-19 Pandemic

2021 ◽  
Vol 13 (7) ◽  
pp. 3836
Author(s):  
David Flores-Ruiz ◽  
Adolfo Elizondo-Salto ◽  
María de la O. Barroso-González
Keyword(s):  
Social Media ◽  
Sentiment Analysis ◽  
Cost Savings ◽  
Mass Scale ◽  
Tourism Sector ◽  
The Social ◽  
Analytical Tools ◽  
Media Data

This paper explores the role of social media in tourist sentiment analysis. To do this, it describes previous studies that have carried out tourist sentiment analysis using social media data, before analyzing changes in tourists’ sentiments and behaviors during the COVID-19 pandemic. In the case study, which focuses on Andalusia, the changes experienced by the tourism sector in the southern Spanish region as a result of the COVID-19 pandemic are assessed using the Andalusian Tourism Situation Survey (ECTA). This information is then compared with data obtained from a sentiment analysis based on the social network Twitter. On the basis of this comparative analysis, the paper concludes that it is possible to identify and classify tourists’ perceptions using sentiment analysis on a mass scale with the help of statistical software (RStudio and Knime). The sentiment analysis using Twitter data correlates with and is supplemented by information from the ECTA survey, with both analyses showing that tourists placed greater value on safety and preferred to travel individually to nearby, less crowded destinations since the pandemic began. Of the two analytical tools, sentiment analysis can be carried out on social media on a continuous basis and offers cost savings.

scholarly journals Deep Sentiment Analysis: A Case Study on Stemmed Turkish Twitter Data

IEEE Access ◽  
2021 ◽  
pp. 1-1
Author(s):  
Harisu Abdullahi Shehu ◽  
Md. Haidar Sharif ◽  
Md. Haris Uddin Sharif ◽  
Ripon Datta ◽  
Sezai Tokat ◽  
...  
Keyword(s):  
Sentiment Analysis ◽  
Twitter Data

scholarly journals Comparative Life Cycle Impact Assessment between the Productions of Zinc from Conventional Concentrates Versus Waelz Oxides Obtained from Slags

2021 ◽  
Vol 13 (2) ◽  
pp. 580
Author(s):  
Voicu-Teodor Muica ◽  
Alexandru Ozunu ◽  
Zoltàn Török
Keyword(s):  
Life Cycle ◽  
Impact Assessment ◽  
Life Cycle Impact Assessment ◽  
Fine Tuning ◽  
Process Data ◽  
Medicinal Uses ◽  
Zinc Metal ◽  
Real Process ◽  
Life Cycle Impact

(1) Background: The importance of Zinc in today’s world can hardly be exaggerated—from anticorrosion properties, to its durability, aesthetic, and even medicinal uses—zinc is ever-present in our daily lives ever since its discovery in ancient times. The natural, essential, durable, and recyclable features of zinc make it a prized material with uses in many applications across a wide array of fields. The purpose of this study was to compare two life cycle impact assessments of zinc production by using two different main raw materials: (A) zinc concentrates (sulfide ore) and (B) Waelz oxides (obtained through recycling existing imperial smelting process furnace slags). The Waelz oxide scenario was based on a case study regarding the existing slag deposit located in Copsa Mica town, Sibiu county, Romania. (2) Methods: consequential life cycle impact assessment methods were applied to each built system, with real process data obtained from the case study enterprise. (3) Results: Overall, the use of slags in the Waelz kiln to produce zinc oxides for use in the production of zinc metal is beneficial to the environment in some areas (acidification, water, and terrestrial eutrophication), whereas in other areas it has a slightly larger impact (climate change, photochemical ozone formation, and ozone depletion). (4) Conclusions: The use of slags (considered a waste) is encouraged to produce zinc metal, where available. The results are not absolute, suggesting the further need for fine-tuning the input data and other process parameters.

On the phase detrending to disentangle refraction and diffraction on GNSS signals: a case study over Antarctica

2021 ◽  
Author(s):  
Luca Spogli ◽  
Hossein Ghobadi ◽  
Antonio Cicone ◽  
Lucilla Alfonsi ◽  
Claudio Cesaroni ◽  
...  
Keyword(s):  
Single Case ◽  
Cutoff Frequency ◽  
Satellite System ◽  
Fine Tuning ◽  
Scintillation Index ◽  
Ionospheric Scintillation ◽  
Iterative Filtering ◽  
Global Navigation Satellite ◽  
Value Changes

<p>We investigate the reliability of the phase scintillation index determined by receiving Global Navigation Satellite System (GNSS) signals at ground in the high-latitudes. To the scope, we report about the capabilities of recently introduced detrending scheme based on the signal decomposition provided by the Fast Iterative Filtering (FIF) technique. This detrending scheme enables a fine tuning of the cutoff frequency for phase detrending used in the phase scintillation index definition, aimed at disentangling diffraction and refraction effects. On a single case study based on GPS and Galileo data taken by a GNSS Ionospheric Scintillation Monitor Receiver (ISMR) in Concordia Station (Antarctica), we show how the FIF-based detrending allows deriving adaptive cutoff frequencies, whose value changes minute-by-minute. They are found to range between 0.4 Hz and 1.2 Hz. This allows better accounting for diffractive effects in phase scintillation index calculation and also showing the limitations on the use of such index, being still widely used in the community, both to characterize the features of ionospheric irregularities and to adopt mitigation solutions.</p>

Sign in / Sign up

Export Citation Format

Share Document