scholarly journals Class-Incremental Learning for Wireless Device Identification in IoT

2021 ◽  
Author(s):  
Yongxin Liu ◽  
Jian Wang ◽  
Jianqiang Li ◽  
Shuteng Niu ◽  
Houbing Song
Keyword(s):  
Incremental Learning ◽  
Historical Data ◽  
Real Data ◽  
Accurate Identification ◽  
Potential Conflict ◽  
Typical Application ◽  
Device Identification ◽  
Iot Devices ◽  
New Perspective ◽  
Channel Separation

<div>Deep Learning (DL) has been utilized pervasively in the Internet of Things (IoT). One typical application of DL in IoT is device identification from wireless signals, namely Non-cryptographic Device Identification (NDI). However, learning components in NDI systems have to evolve to adapt to operational variations, such a paradigm is termed as Incremental Learning (IL). Various IL algorithms have been proposed and many of them require dedicated space to store the increasing amount of historical data, and therefore, they are not suitable for IoT or mobile applications. However, conventional IL schemes can not provide satisfying performance when historical data are not available. In this paper, we address the IL problem in NDI from a new perspective, firstly, we provide a new metric to measure the degree of topological maturity of DNN models from the degree of conflict of class-specific fingerprints. We discover that an important cause for performance degradation in IL enabled NDI is owing to the conflict of devices' fingerprints. Second, we also show that the conventional IL schemes can lead to low topological maturity of DNN models in NDI systems. Thirdly, we propose a new Channel Separation Enabled Incremental Learning (CSIL) scheme without using historical data, in which our strategy can automatically separate devices' fingerprints in different learning stages and avoid potential conflict. Finally, We evaluated the effectiveness of the proposed framework using real data from ADS-B (Automatic Dependent Surveillance-Broadcast), an application of IoT in aviation. The proposed framework has the potential to be applied to accurate identification of IoT devices in a variety of IoT applications and services. Data and code available at IEEE Dataport (DOI: 10.21227/1bxc-ke87) and \url{https://github.com/pcwhy/CSIL}}.<br></div>

scholarly journals Class-Incremental Learning for Wireless Device Identification in IoT

2021 ◽  
Author(s):  
Yongxin Liu ◽  
Jian Wang ◽  
Jianqiang Li ◽  
Shuteng Niu ◽  
Houbing Song
Keyword(s):  
Incremental Learning ◽  
Historical Data ◽  
Real Data ◽  
Accurate Identification ◽  
Potential Conflict ◽  
Typical Application ◽  
Device Identification ◽  
Iot Devices ◽  
New Perspective ◽  
Channel Separation

<div>Deep Learning (DL) has been utilized pervasively in the Internet of Things (IoT). One typical application of DL in IoT is device identification from wireless signals, namely Non-cryptographic Device Identification (NDI). However, learning components in NDI systems have to evolve to adapt to operational variations, such a paradigm is termed as Incremental Learning (IL). Various IL algorithms have been proposed and many of them require dedicated space to store the increasing amount of historical data, and therefore, they are not suitable for IoT or mobile applications. However, conventional IL schemes can not provide satisfying performance when historical data are not available. In this paper, we address the IL problem in NDI from a new perspective, firstly, we provide a new metric to measure the degree of topological maturity of DNN models from the degree of conflict of class-specific fingerprints. We discover that an important cause for performance degradation in IL enabled NDI is owing to the conflict of devices' fingerprints. Second, we also show that the conventional IL schemes can lead to low topological maturity of DNN models in NDI systems. Thirdly, we propose a new Channel Separation Enabled Incremental Learning (CSIL) scheme without using historical data, in which our strategy can automatically separate devices' fingerprints in different learning stages and avoid potential conflict. Finally, We evaluated the effectiveness of the proposed framework using real data from ADS-B (Automatic Dependent Surveillance-Broadcast), an application of IoT in aviation. The proposed framework has the potential to be applied to accurate identification of IoT devices in a variety of IoT applications and services. Data and code available at IEEE Dataport (DOI: 10.21227/1bxc-ke87) and \url{https://github.com/pcwhy/CSIL}}.<br></div>

scholarly journals Formal Proofs of Orthogonality for Class-Incremental Learning for Wireless Device Identification in IoT

2021 ◽  
Author(s):  
Yongxin Liu ◽  
Jian Wang ◽  
Jianqiang Li ◽  
Shuteng Niu ◽  
Houbing Song
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Incremental Learning ◽  
Learning Algorithm ◽  
Formal Proof ◽  
Formal Proofs ◽  
Device Identification ◽  
Wireless Device ◽  
Channel Separation ◽  
Approximate Orthogonality

<div> <div> <div> <p>This document provides a formal proof and supple- mentary information of the paper: Class-Incremental Learning for Wireless Device Identification in IoT. The original paper focuses on providing a novel and efficient incremental learning algorithm. In this document, we explicitly explain why the mem- ory representations (latent device fingerprints in our application) in Artificial Neural Networks approximate orthogonality with insights for the invention of our Channel Separation Incremental Learning algorithm. </p> </div> </div> </div>

scholarly journals Identifying IoT Devices Based on Spatial and Temporal Features from Network Traffic

2021 ◽  
Vol 2021 ◽  
pp. 1-16
Author(s):  
Feihong Yin ◽  
Li Yang ◽  
Jianfeng Ma ◽  
Yasheng Zhou ◽  
Yuchen Wang ◽  
...  
Keyword(s):  
Network Traffic ◽  
Network Flow ◽  
Data Augmentation ◽  
Accurate Identification ◽  
Device Identification ◽  
Data Packets ◽  
Temporal Features ◽  
Communication Traffic ◽  
Iot Devices ◽  
The One

With the rapid growth of the Internet of Things (IoT) devices, security risks have also arisen. The preidentification of IoT devices connected to the network can help administrators to set corresponding security policies according to the functionality and heterogeneity of the devices. However, the existing methods are based on manually extracted features and prior knowledge to identify the IoT devices, which increases the difficulty of the device identification task and reduces the timeliness. In this paper, we present CBBI, a novel IoT device identification approach. On the one hand, CBBI uses a hybrid neural network model Conv-BiLSTM to automatically learn the representative spatial and temporal features from the network traffic, such as the position relationship of the internal organization structure in network communication traffic, the time sequence of the data packets, and the duration of the network flow. On the other hand, CBBI contains the data augmentation module FGAN that solves the problem of data imbalance in deep learning and improves the accuracy of the model. Finally, we used the public dataset and laboratory dataset to evaluate CBBI from multiple dimensions. The evaluation results for different datasets show that our approach achieves the accurate identification of IoT devices.

scholarly journals Formal Proofs of Orthogonality for Class-Incremental Learning for Wireless Device Identification in IoT

2021 ◽  
Author(s):  
Yongxin Liu ◽  
Jian Wang ◽  
Jianqiang Li ◽  
Shuteng Niu ◽  
Houbing Song
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Incremental Learning ◽  
Learning Algorithm ◽  
Formal Proof ◽  
Formal Proofs ◽  
Device Identification ◽  
Wireless Device ◽  
Channel Separation ◽  
Approximate Orthogonality

<div> <div> <div> <p>This document provides a formal proof and supple- mentary information of the paper: Class-Incremental Learning for Wireless Device Identification in IoT. The original paper focuses on providing a novel and efficient incremental learning algorithm. In this document, we explicitly explain why the mem- ory representations (latent device fingerprints in our application) in Artificial Neural Networks approximate orthogonality with insights for the invention of our Channel Separation Incremental Learning algorithm. </p> </div> </div> </div>

scholarly journals Northern dialect evidence for the chronology of the Great Vowel Shift

2014 ◽  
Vol 2 (2) ◽  
pp. 87-102
Author(s):  
Hilary Prichard
Keyword(s):  
Middle English ◽  
Historical Data ◽  
Dialect Contact ◽  
Chain Analysis ◽  
Vowel Shift ◽  
New Perspective ◽  
Dialect Geography

This paper demonstrates how the tools of dialect geography may fruitfully lend a new perspective to historical data in order to address the lingering questions left by previous analyses. A geographic examination ofSurvey of English Dialectsdata provides evidence in favor of a push-chain analysis of the Great Vowel Shift, in which the Middle English high-mid long vowels raised before the high long vowels were diphthongized. It is also demonstrated that the so-called “irregular” dialect outcomes, which have previously been cited as evidence for a lack of unity of the Great Vowel Shift, are no longer problematic when viewed in the light of a theory of dialect contact, and can in fact refine our understanding of the chronology and geographic extent of the shift itself.

scholarly journals A Supply Chain Vulnerability Map for the Automotive and Electronic Industries in Brazil

2020 ◽  
Vol 3 (2) ◽  
pp. 83 ◽  
Author(s):  
Mauricio F. Blos ◽  
Hui-Ming Wee
Keyword(s):  
Risk Management ◽  
Supply Chain ◽  
Historical Data ◽  
Methodological Approach ◽  
Real Data ◽  
Economic Downturn ◽  
Supply Chain Risk Management ◽  
Supply Chain Risk ◽  
Vulnerability Map ◽  
Hazard Vulnerability

This paper aims to explore various perspectives of the Supply Chain Risk Management (SCRM) as they relate to the automotive and electronic industries in Brazil based on the historical data from 2010 to 2016. The methodological approach was based on the Supply Chain Vulnerability Map (SCVM). The SCVM was tested in its totaliness and two more riskswere added to the hazard vulnerability category to form the SCVM II. The exploratory surveys were used to better understand the impacts on the automotive and electronic industries in Brazil during the study period. An interesting finding was that most of the major automotive and electronic industries are concerned with integrating risk management, governance and compliance in the supply chain. The findings of the empiricalinvestigation and SCRM historical data indicate that managers must integrate risk management, governance and compliance in the supply chain and use the proposed SCVM II. This research revealed the risks that surrounded the supply chain during the time period covered. In the study, the researchers added two more risks to the hazard vulnerability category: item 10, deficient rainfall (as seen in Manaus and São Paulo) and number 13, viral epidemics (to reflect the Zika virus around Brazil), it was named as SCVMII. Among the limitations of the research was that the study applied real data which might vary drastically due to economic downturn of the country. This might affect the performance of the investigated industries.

scholarly journals A Non-Linear Autoregressive Model for Indoor Air-Temperature Predictions in Smart Buildings

Electronics ◽  
2019 ◽  
Vol 8 (9) ◽  
pp. 979 ◽  
Author(s):  
Alessandro Aliberti ◽  
Lorenzo Bottaccioli ◽  
Enrico Macii ◽  
Santa Di Cataldo ◽  
Andrea Acquaviva ◽  
...  
Keyword(s):  
Air Temperature ◽  
Indoor Air ◽  
Decisive Role ◽  
Real Data ◽  
Total Energy Consumption ◽  
Innovative Methodology ◽  
Non Linear ◽  
Temperature Forecasting ◽  
Iot Devices ◽  
The Many

In recent years, the contrast against energy waste and pollution has become mandatory and widely endorsed. Among the many actors at stake, the building sector energy management is one of the most critical. Indeed, buildings are responsible for 40 % of total energy consumption only in Europe, affecting more than a third of the total pollution produced. Therefore, energy control policies of buildings (for example, forecast-based policies such as Demand Response and Demand Side Management) play a decisive role in reducing energy waste. On these premises, this paper presents an innovative methodology based on Internet-of-Things (IoT) technology for smart building indoor air-temperature forecasting. In detail, our methodology exploits a specialized Non-linear Autoregressive neural network for short- and medium-term predictions, envisioning two different exploitation: (i) on realistic artificial data and (ii) on real data collected by IoT devices deployed in the building. For this purpose, we designed and optimized four neural models, focusing respectively on three characterizing rooms and on the whole building. Experimental results on both a simulated and a real sensors dataset demonstrate the prediction accuracy and robustness of our proposed models.

Inversion of Pressure Data on a Vertical Array for Sea Floor Geoacoustic Properties

1998 ◽  
Vol 06 (01n02) ◽  
pp. 269-289 ◽  
Author(s):  
Purnima Ratilal ◽  
Peter Gerstoft ◽  
Joo Thiam Goh ◽  
Keng Pong Yeo
Keyword(s):  
Ambient Noise ◽  
Historical Data ◽  
Low Frequency ◽  
Real Data ◽  
Vertical Array ◽  
Trial Site ◽  
Matched Field Processing ◽  
High Frequencies ◽  
Sea Floor ◽  
Line Array

Estimation of the integral geoacoustic properties of the sea floor based on real data drawn from a shallow water site is presented. Two independent inversion schemes are used to deduce these properties. The first is matched-field processing of the pressure field on a vertical line array due to a projected source. The second approach is the inversion of ambient noise on a vertical array. Matched-field processing has shown to be successful in the inversion of high quality field data. Here, we show that it is also feasible with a more practical and less expensive data collection scheme. It will also be shown that low frequency inversion is more robust to variation and fluctuation in the propagating medium, whereas high frequencies are more sensitive to mismatches in a varying medium. A comparison is made of the estimates obtained from the two techniques and also with available historical data of the trial site.

scholarly journals Smart Digital Forensic Readiness Model for Shadow IoT Devices

2022 ◽  
Vol 12 (2) ◽  
pp. 730
Author(s):  
Funmilola Ikeolu Fagbola ◽  
Hein Venter
Keyword(s):  
Information Technology ◽  
Internet Of Things ◽  
Conceptual Model ◽  
Criminal Activity ◽  
Forensic Evidence ◽  
Device Identification ◽  
Digital Forensic ◽  
Privacy Breach ◽  
Evidence Gathering ◽  
Iot Devices

Internet of Things (IoT) is the network of physical objects for communication and data sharing. However, these devices can become shadow IoT devices when they connect to an existing network without the knowledge of the organization’s Information Technology team. More often than not, when shadow devices connect to a network, their inherent vulnerabilities are easily exploited by an adversary and all traces are removed after the attack or criminal activity. Hence, shadow connections pose a challenge for both security and forensic investigations. In this respect, a forensic readiness model for shadow device-inclusive networks is sorely needed for the purposes of forensic evidence gathering and preparedness, should a security or privacy breach occur. However, the hidden nature of shadow IoT devices does not facilitate the effective adoption of the most conventional digital and IoT forensic methods for capturing and preserving potential forensic evidence that might emanate from shadow devices in a network. Therefore, this paper aims to develop a conceptual model for smart digital forensic readiness of organizations with shadow IoT devices. This model will serve as a prototype for IoT device identification, IoT device monitoring, as well as digital potential evidence capturing and preservation for forensic readiness.

ИДЕНТИФИКАЦИЯ УСТРОЙСТВ И СИСТЕМ УЗКОПОЛОСНЫХ БЕСПРОВОДНЫХ СЕТЕЙ СВЯЗИ ИНТЕРНЕТА ВЕЩЕЙ. ЧАСТЬ II

2020 ◽  
Author(s):  
A.S. BORODIN ◽  
R.V. KIRICHEK ◽  
D.D. SAZONOV ◽  
 M.A. ROZHKOV ◽  
 A.V. KOLESNIKOV ◽  
...  
Keyword(s):  
Simulation Model ◽  
Identification System ◽  
Digital Object ◽  
Device Identification ◽  
Transport Industry ◽  
Iot Devices

A description of an identification system for IoT devices based on the Digital Object Architecture (DOA) is given. An analysis of alternative identifiers is given and the advantages of DOA for both identification and anti-counterfeit purposes are shown. The second part of the article presents the implementation of DOA technology on a specific example - the device identification system in the Russian transport industry. It is also developed a simulation model of a network fragment. A series of optimization experiments are performed. Представлено описание системы идентификации на базе архитектуры цифровых объектов (Digital Object Architecture - DOA), которая в настоящее время рассматривается в качестве приоритетной для идентификации устройств и приложений интернета вещей. Приведен анализ альтернативных идентификаторов и показаны преимущества DOA какдля за -дач идентификации, так и для борьбы с контрафактом. Во второй части статьи представлена реализация данной технологии на конкретном примере - системе идентификации устройств в транспортной отрасли России, а также разработана имитационная модель фрагмента сети, на базе которой анализировались различные параметры функционирования системы. Дано базовое описание разработанной имитационной модели и проведена серия оптимизационных экспериментов с целью улучшения производительности текущей системы.

Sign in / Sign up

Export Citation Format

Share Document