3. Data-driven IoT Security Using Deep Learning Techniques

2020 ◽  
Author(s):  
Astaras Stefanos ◽  
Nikos Kefalakis ◽  
Angela-Maria Despotopoulou ◽  
John Soldatos
Keyword(s):  
Deep Learning ◽  
Data Driven ◽  
Iot Security ◽  
Learning Techniques

Deep Learning Techniques for IoT Security and Privacy

2022 ◽  
Author(s):  
Mohamed Abdel-Basset ◽  
Nour Moustafa ◽  
Hossam Hawash ◽  
Weiping Ding
Keyword(s):  
Deep Learning ◽  
Security And Privacy ◽  
Iot Security ◽  
Learning Techniques

scholarly journals A Review of Deep Learning Techniques for Forecasting Energy Use in Buildings

Energies ◽  
2021 ◽  
Vol 14 (3) ◽  
pp. 608
Author(s):  
Jason Runge ◽  
Radu Zmeureanu
Keyword(s):  
Feature Extraction ◽  
Deep Learning ◽  
Energy Use ◽  
Building Energy ◽  
Data Driven ◽  
Future Research ◽  
Nonlinear Phenomena ◽  
Energy Forecasting ◽  
Learning Techniques ◽  
Application Potential

Buildings account for a significant portion of our overall energy usage and associated greenhouse gas emissions. With the increasing concerns regarding climate change, there are growing needs for energy reduction and increasing our energy efficiency. Forecasting energy use plays a fundamental role in building energy planning, management and optimization. The most common approaches for building energy forecasting include physics and data-driven models. Among the data-driven models, deep learning techniques have begun to emerge in recent years due to their: improved abilities in handling large amounts of data, feature extraction characteristics, and improved abilities in modelling nonlinear phenomena. This paper provides an extensive review of deep learning-based techniques applied to forecasting the energy use in buildings to explore its effectiveness and application potential. First, we present a summary of published literature reviews followed by an overview of deep learning-based definitions and techniques. Next, we present a breakdown of current trends identified in published research along with a discussion of how deep learning-based models have been applied for feature extraction and forecasting. Finally, the review concludes with current challenges faced and some potential future research directions.

scholarly journals A Deep Insight in Challenges of Natural Language Processing and Usage of Deep Learning

2020 ◽  
Vol 8 (12s3) ◽  
pp. 50-54
Keyword(s):  
Deep Learning ◽  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Automatic Speech Recognition ◽  
Data Driven ◽  
Deep Insight ◽  
Pos Tagging ◽  
Learning Techniques ◽  
Using Data

Natural Language Processing (NLP) using the power of artificial intelligence has empowered the understanding of the language used by human. It has also enhanced the effectiveness of the communication between human and computers. The complexity and diversity of the huge datasets have raised the requirement for automatic analysis of the linguistic data by using data-driven approaches. The performance of the data-driven approaches is improved after the usage of different deep learning techniques in various application areas of NLP like Automatic Speech Recognition, POS tagging etc. The paper addresses the challenges faced in NLP and the use of deep learning techniques in different application areas of NLP.

scholarly journals RAIN-F+: The Data-Driven Precipitation Prediction Model for Integrated Weather Observations

2021 ◽  
Vol 13 (18) ◽  
pp. 3627
Author(s):  
Yeji Choi ◽  
Keumgang Cha ◽  
Minyoung Back ◽  
Hyunguk Choi ◽  
Taegyun Jeon
Keyword(s):  
Deep Learning ◽  
Learning Performance ◽  
Data Driven ◽  
Land Area ◽  
Rainfall Prediction ◽  
Precipitation Prediction ◽  
Learning Techniques ◽  
Weather Observations ◽  
Surface Station ◽  
Weather Observation

Quantitative precipitation prediction is essential for managing water-related disasters, including floods, landslides, tsunamis, and droughts. Recent advances in data-driven approaches using deep learning techniques provide improved precipitation nowcasting performance. Moreover, it has been known that multi-modal information from various sources could improve deep learning performance. This study introduces the RAIN-F+ dataset, which is the fusion dataset for rainfall prediction, and proposes the benchmark models for precipitation prediction using the RAIN-F+ dataset. The RAIN-F+ dataset is an integrated weather observation dataset including radar, surface station, and satellite observations covering the land area over the Korean Peninsula. The benchmark model is developed based on the U-Net architecture with residual upsampling and downsampling blocks. We examine the results depending on the number of the integrated dataset for training. Overall, the results show that the fusion dataset outperforms the radar-only dataset over time. Moreover, the results with the radar-only dataset show the limitations in predicting heavy rainfall over 10 mm/h. This suggests that the various information from multi-modality is crucial for precipitation nowcasting when applying the deep learning method.

A new dam structural response estimation paradigm powered by deep learning and transfer learning techniques

2021 ◽  
pp. 147592172110097
Author(s):  
Yangtao Li ◽  
Tengfei Bao ◽  
Zhixin Gao ◽  
Xiaosong Shu ◽  
Kang Zhang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Time Series ◽  
Deep Learning ◽  
Transfer Learning ◽  
Health Monitoring ◽  
Structural Response ◽  
Data Driven ◽  
Structural Health ◽  
Learning Techniques

With the rapid development of information and communication techniques, dam structural health assessment based on data collected from structural health monitoring systems has become a trend. This allows for applying data-driven methods for dam safety analysis. However, data-driven models in most related literature are statistical and shallow machine learning models, which cannot capture the time series patterns or learn from long-term dependencies of dam structural response time series. Furthermore, the effectiveness and applicability of these models are only validated in a small data set and part of monitoring points in a dam structural health monitoring system. To address the problems, this article proposes a new modeling paradigm based on various deep learning and transfer learning techniques. The paradigm utilizes one-dimensional convolutional neural networks to extract the inherent features from dam structural response–related environmental quantity monitoring data. Then bidirectional gated recurrent unit with a self-attention mechanism is used to learn from long-term dependencies, and transfer learning is utilized to transfer knowledge learned from the typical monitoring point to the others. The proposed paradigm integrates the powerful modeling capability of deep learning networks and the flexible transferability of transfer learning. Rather than traditional models that rely on experience for feature selection, the proposed deep learning–based paradigm directly utilizes environmental monitoring time series as inputs to accurately estimate dam structural response changes. A high arch dam in long-term service is selected as the case study, and three monitoring items, including dam displacement, crack opening displacement, and seepage are used as the research objects. The experimental results show that the proposed paradigm outperforms conventional and shallow machine learning–based methods in all 41 tested monitoring points, which indicates that the proposed paradigm is capable of dealing with dam structural response estimation with high accuracy and robustness.

scholarly journals Physics Guided Deep Learning for Data-Driven Aircraft Fuel Consumption Modeling

Aerospace ◽  
2021 ◽  
Vol 8 (2) ◽  
pp. 44
Author(s):  
Mevlut Uzun ◽  
Mustafa Umut Demirezen ◽  
Gokhan Inalhan
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Supervised Learning ◽  
Fuel Consumption ◽  
Performance Model ◽  
Training Data ◽  
Data Driven ◽  
Physical Knowledge ◽  
Learning Techniques ◽  
Flight Regimes

This paper presents a physics-guided deep neural network framework to estimate fuel consumption of an aircraft. The framework aims to improve data-driven models’ consistency in flight regimes that are not covered by data. In particular, we guide the neural network with the equations that represent fuel flow dynamics. In addition to the empirical error, we embed this physical knowledge as several extra loss terms. Results show that our proposed model accomplishes correct predictions on the labeled test set, as well as assuring physical consistency in unseen flight regimes. The results indicate that our model, while being applicable to the aircraft’s complete flight envelope, yields lower fuel consumption error measures compared to the model-based approaches and other supervised learning techniques utilizing the same training data sets. In addition, our deep learning model produces fuel consumption trends similar to the BADA4 aircraft performance model, which is widely utilized in real-world operations, in unseen and untrained flight regimes. In contrast, the other supervised learning techniques fail to produce meaningful results. Overall, the proposed methodology enhances the explainability of data-driven models without deteriorating accuracy.

scholarly journals Machine Learning and Deep Learning Techniques for IoT-based Intrusion Detection Systems: A Literature Review

2021 ◽  
pp. 296-314
Author(s):  
Laiby Thomas ◽  
Subramanya Bhat
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Literature Review ◽  
Intrusion Detection ◽  
Detection System ◽  
Main Idea ◽  
Intrusion Detection Systems ◽  
Iot Security ◽  
Detection Systems ◽  
Learning Techniques

Purpose: The authors attempt to examine the work done in the area of Intrusion Detection System in IoT utilizing Machine Learning/Deep Learning technique and various accessible datasets for IoT security in this review of literature. Methodology: The papers in this study were published between 2014 and 2021 and dealt with the use of IDS in IoT security. Various databases such as IEEE, Wiley, Science Direct, MDPI, and others were searched for this purpose, and shortlisted articles used Machine Learning and Deep Learning techniques to handle various IoT vulnerabilities. Findings/Result: In the past few years, the IDS has grown in popularity as a result of their robustness. The main idea behind intrusion detection systems is to detect intruders in a given region. An intruder is a host that tries to connect to other nodes without permission in the world of the Internet of Things. In the field of IDS, there is a research gap. Different ML/DL techniques are used for IDS in IoT. But it does not properly deal with complexity issues. Also, these techniques are limited to some attacks, and it does not provide high accuracy. Originality: A review had been executed from various research works available from online databases and based on the survey derived a structure for the future study. Paper Type: Literature Review.

Sign in / Sign up

Export Citation Format

Share Document