scholarly journals Adaptive Load Balanced Routing in IOT Networks: A Distributed Learning Approach

2019 ◽  
Vol 3 (1) ◽  
pp. 1-5
Author(s):  
Rzgar Sirwan ◽  
Muzhir Ani
Keyword(s):  
Large Scale ◽  
Low Cost ◽  
Distributed Learning ◽  
Low Complexity ◽  
Learning Approach ◽  
Traffic Efficiency ◽  
Data Channel ◽  
Iot Devices ◽  
Balancing Efficiency ◽  
Networked Society

Facilitating large-scale load-efficient Internet of things (IoT) connectivity is a vital step toward realizing the networked society. Although legacy wide-area wireless systems are heavily based on network-side coordination, such centralized methods will become infeasible in the future, by the unbalanced signaling level and the expected increment in the number of IoT devices. In the present work, this problem is represented through self-coordinating for IoT networks and learning from past communications. In this regard, first, we assessed low-complexity distributed learning methods that can be applied to IoT communications. We presented a learning solution then, for adapting devices’ communication parameters to the environment to maximize the reliability and load balancing efficiency in data transmissions. Moreover, we used leveraging instruments from stochastic geometry to assess the behavior of the presented distributed learning solution against centralized coordinations. Ultimately, we analyzed the interplay amongst traffic efficiency, communications’ reliability against interference and noise over data channel, as well as reliability versus adversarial interference over feedback and data channels. The presented learning approach enhanced both reliability and traffic efficiency within IoT communications considerably. By such promising findings obtained via lightweight learning, our solution becomes promising in numerous low-power low-cost IoT uses.

scholarly journals Edge-Based Missing Data Imputation in Large-Scale Environments

Information ◽  
2021 ◽  
Vol 12 (5) ◽  
pp. 195
Author(s):  
Davide Andrea Guastella ◽  
Guilhem Marcillaud ◽  
Cesare Valenti
Keyword(s):  
Urban Environment ◽  
Large Scale ◽  
Smart Cities ◽  
Low Cost ◽  
Real Data ◽  
Missing Data Imputation ◽  
Large Scale Data ◽  
Iot Devices ◽  
Edge Based ◽  
The One

Smart cities leverage large amounts of data acquired in the urban environment in the context of decision support tools. These tools enable monitoring the environment to improve the quality of services offered to citizens. The increasing diffusion of personal Internet of things devices capable of sensing the physical environment allows for low-cost solutions to acquire a large amount of information within the urban environment. On the one hand, the use of mobile and intermittent sensors implies new scenarios of large-scale data analysis; on the other hand, it involves different challenges such as intermittent sensors and integrity of acquired data. To this effect, edge computing emerges as a methodology to distribute computation among different IoT devices to analyze data locally. We present here a new methodology for imputing environmental information during the acquisition step, due to missing or otherwise out of order sensors, by distributing the computation among a variety of fixed and mobile devices. Numerous experiments have been carried out on real data to confirm the validity of the proposed method.

scholarly journals Outlier Detection in IoT Using Generative Adversarial Network

2020 ◽  
pp. 306-311
Author(s):  
B. Joyce Beula Rani ◽  
L. Sumathi
Keyword(s):  
Deep Learning ◽  
Internet Of Things ◽  
Outlier Detection ◽  
Large Scale ◽  
Detection Methods ◽  
Learning Approach ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Detection Approach ◽  
Iot Devices

Usage of IoT products have been rapidly increased in past few years. The large number of insecure Internet of Things (IoT) devices with low computation power makes them an easy and attractive target for attackers seeking to compromise these devices and use them to create large-scale attacks. Detecting those attacks is a time consuming task and it needs to be identified shortly since it keeps on spreading. Various detection methods are used for detecting these attacks but attack mechanism keeps on evolving so a new detection approach must be introduced to detect their presence and thus blocking their spreading. In this paper a deep learning approach called GAN – Generative Adversarial Network can be used to detect this outlier and achieve 85% accuracy.

scholarly journals Joint Optimization for Visual Data Transmission in the Resource Constraint 5G IoT

2021 ◽  
Vol 256 ◽  
pp. 02014
Author(s):  
Jingce Xu ◽  
Xinsheng Zhang ◽  
Jianfei Lu
Keyword(s):  
Data Transmission ◽  
Autonomous Vehicles ◽  
Large Scale ◽  
Limited Resource ◽  
Low Complexity ◽  
Resource Constraint ◽  
Visual Data ◽  
Building Management ◽  
Iot Devices ◽  
Single Objective

With the integration of 5G and Internet of Things (IoT), the application of large-scale IoT devices networking is increasingly extensive, such as building management, property maintenance, autonomous vehicles, healthcare, and shopping to tourism. In these scenes, the volume of data transmission is quite large, especially visual data (image, video, et al). However, due to the limited resource of IoT devices, such as battery, power, bandwidth, visual data transmission is complex to optimize, single objective optimization is difficult to insure the optimal latency, throughput and power at the same time. In this paper, we propose a method to jointly optimize the resource allocation of visual data transmission in resource constraint 5G IoT. Instead of single objective optimization, we combine the bandwidth, power consumption and latency into a hybrid model, then propose a low-complexity algorithm to solve this multiple objective optimization problem. The simulation results demonstrate that the proposed method increases the comprehensive utility of visual data transmission in the resource constraint 5G-IoT by 35%-48% compared with existing approaches.

Bringing Security to The Smallest Embedded Systems

2017 ◽  
Author(s):  
JOSEPH YIU
Keyword(s):  
Internet Of Things ◽  
Embedded Systems ◽  
Low Cost ◽  
Security Requirements ◽  
The Internet ◽  
Security Measures ◽  
Significant Challenge ◽  
Iot Devices

The increasing need for security in microcontrollers Security has long been a significant challenge in microcontroller applications(MCUs). Traditionally, many microcontroller systems did not have strong security measures against remote attacks as most of them are not connected to the Internet, and many microcontrollers are deemed to be cheap and simple. With the growth of IoT (Internet of Things), security in low cost microcontrollers moved toward the spotlight and the security requirements of these IoT devices are now just as critical as high-end systems due to:

An Assessment of a Low-Cost Wastewater Disposal System after Twenty-Five Years of Operation

1987 ◽  
Vol 19 (5-6) ◽  
pp. 701-710 ◽  
Author(s):  
B. L. Reidy ◽  
G. W. Samson
Keyword(s):  
Large Scale ◽  
Low Cost ◽  
Wastewater Disposal ◽  
Industrial Base ◽  
Industrial Wastewaters ◽  
The Past ◽  
Gasification Process ◽  
Appropriate Treatment ◽  
Environmentally Safe ◽  
Coal Resource

A low-cost wastewater disposal system was commissioned in 1959 to treat domestic and industrial wastewaters generated in the Latrobe River valley in the province of Gippsland, within the State of Victoria, Australia (Figure 1). The Latrobe Valley is the centre for large-scale generation of electricity and for the production of pulp and paper. In addition other industries have utilized the brown coal resource of the region e.g. gasification process and char production. Consequently, industrial wastewaters have been dominant in the disposal system for the past twenty-five years. The mixed industrial-domestic wastewaters were to be transported some eighty kilometres to be treated and disposed of by irrigation to land. Several important lessons have been learnt during twenty-five years of operating this system. Firstly the composition of the mixed waste stream has varied significantly with the passage of time and the development of the industrial base in the Valley, so that what was appropriate treatment in 1959 is not necessarily acceptable in 1985. Secondly the magnitude of adverse environmental impacts engendered by this low-cost disposal procedure was not imagined when the proposal was implemented. As a consequence, clean-up procedures which could remedy the adverse effects of twenty-five years of impact are likely to be costly. The question then may be asked - when the total costs including rehabilitation are considered, is there really a low-cost solution for environmentally safe disposal of complex wastewater streams?

scholarly journals Rapid, large-scale species discovery in hyperdiverse taxa using 1D MinION sequencing

BMC Biology ◽  
2019 ◽  
Vol 17 (1) ◽  
Author(s):  
Amrita Srivathsan ◽  
Emily Hartop ◽  
Jayanthi Puniamoorthy ◽  
Wan Ting Lee ◽  
Sujatha Narayanan Kutty ◽  
...  
Keyword(s):  
Dna Sequences ◽  
Large Scale ◽  
Low Cost ◽  
Small Body ◽  
Small Subset ◽  
Similar Species ◽  
Large Species ◽  
Morphological Examination ◽  
Species Discovery ◽  
Short Period

Abstract Background More than 80% of all animal species remain unknown to science. Most of these species live in the tropics and belong to animal taxa that combine small body size with high specimen abundance and large species richness. For such clades, using morphology for species discovery is slow because large numbers of specimens must be sorted based on detailed microscopic investigations. Fortunately, species discovery could be greatly accelerated if DNA sequences could be used for sorting specimens to species. Morphological verification of such “molecular operational taxonomic units” (mOTUs) could then be based on dissection of a small subset of specimens. However, this approach requires cost-effective and low-tech DNA barcoding techniques because well-equipped, well-funded molecular laboratories are not readily available in many biodiverse countries. Results We here document how MinION sequencing can be used for large-scale species discovery in a specimen- and species-rich taxon like the hyperdiverse fly family Phoridae (Diptera). We sequenced 7059 specimens collected in a single Malaise trap in Kibale National Park, Uganda, over the short period of 8 weeks. We discovered > 650 species which exceeds the number of phorid species currently described for the entire Afrotropical region. The barcodes were obtained using an improved low-cost MinION pipeline that increased the barcoding capacity sevenfold from 500 to 3500 barcodes per flowcell. This was achieved by adopting 1D sequencing, resequencing weak amplicons on a used flowcell, and improving demultiplexing. Comparison with Illumina data revealed that the MinION barcodes were very accurate (99.99% accuracy, 0.46% Ns) and thus yielded very similar species units (match ratio 0.991). Morphological examination of 100 mOTUs also confirmed good congruence with morphology (93% of mOTUs; > 99% of specimens) and revealed that 90% of the putative species belong to the neglected, megadiverse genus Megaselia. We demonstrate for one Megaselia species how the molecular data can guide the description of a new species (Megaselia sepsioides sp. nov.). Conclusions We document that one field site in Africa can be home to an estimated 1000 species of phorids and speculate that the Afrotropical diversity could exceed 200,000 species. We furthermore conclude that low-cost MinION sequencers are very suitable for reliable, rapid, and large-scale species discovery in hyperdiverse taxa. MinION sequencing could quickly reveal the extent of the unknown diversity and is especially suitable for biodiverse countries with limited access to capital-intensive sequencing facilities.

scholarly journals Virtualizing AI at the Distributed Edge Towards Intelligent IoT Applications

2021 ◽  
Vol 10 (1) ◽  
pp. 13
Author(s):  
Claudia Campolo ◽  
Giacomo Genovese ◽  
Antonio Iera ◽  
Antonella Molinaro
Keyword(s):  
Resource Constraints ◽  
Smart Cities ◽  
Traditional Approach ◽  
Low Cost ◽  
Iot Applications ◽  
Software And Hardware ◽  
Iot Devices ◽  
Consumer Devices ◽  
Hardware Platforms ◽  
Smart Factories

Several Internet of Things (IoT) applications are booming which rely on advanced artificial intelligence (AI) and, in particular, machine learning (ML) algorithms to assist the users and make decisions on their behalf in a large variety of contexts, such as smart homes, smart cities, smart factories. Although the traditional approach is to deploy such compute-intensive algorithms into the centralized cloud, the recent proliferation of low-cost, AI-powered microcontrollers and consumer devices paves the way for having the intelligence pervasively spread along the cloud-to-things continuum. The take off of such a promising vision may be hurdled by the resource constraints of IoT devices and by the heterogeneity of (mostly proprietary) AI-embedded software and hardware platforms. In this paper, we propose a solution for the AI distributed deployment at the deep edge, which lays its foundation in the IoT virtualization concept. We design a virtualization layer hosted at the network edge that is in charge of the semantic description of AI-embedded IoT devices, and, hence, it can expose as well as augment their cognitive capabilities in order to feed intelligent IoT applications. The proposal has been mainly devised with the twofold aim of (i) relieving the pressure on constrained devices that are solicited by multiple parties interested in accessing their generated data and inference, and (ii) and targeting interoperability among AI-powered platforms. A Proof-of-Concept (PoC) is provided to showcase the viability and advantages of the proposed solution.

scholarly journals Recurrent Neural Network for Human Activity Recognition in Embedded Systems Using PPG and Accelerometer Data

Electronics ◽  
2021 ◽  
Vol 10 (14) ◽  
pp. 1715
Author(s):  
Michele Alessandrini ◽  
Giorgio Biagetti ◽  
Paolo Crippa ◽  
Laura Falaschetti ◽  
Claudio Turchetti
Keyword(s):  
Neural Network ◽  
Embedded System ◽  
Activity Recognition ◽  
Human Activity ◽  
Recurrent Neural Network ◽  
Low Cost ◽  
Low Complexity ◽  
Human Activity Recognition ◽  
Motion Artifacts ◽  
Accelerometer Data

Photoplethysmography (PPG) is a common and practical technique to detect human activity and other physiological parameters and is commonly implemented in wearable devices. However, the PPG signal is often severely corrupted by motion artifacts. The aim of this paper is to address the human activity recognition (HAR) task directly on the device, implementing a recurrent neural network (RNN) in a low cost, low power microcontroller, ensuring the required performance in terms of accuracy and low complexity. To reach this goal, (i) we first develop an RNN, which integrates PPG and tri-axial accelerometer data, where these data can be used to compensate motion artifacts in PPG in order to accurately detect human activity; (ii) then, we port the RNN to an embedded device, Cloud-JAM L4, based on an STM32 microcontroller, optimizing it to maintain an accuracy of over 95% while requiring modest computational power and memory resources. The experimental results show that such a system can be effectively implemented on a constrained-resource system, allowing the design of a fully autonomous wearable embedded system for human activity recognition and logging.

scholarly journals IoT Traffic: Modeling and Measurement Experiments

IoT ◽  
2021 ◽  
Vol 2 (1) ◽  
pp. 140-162
Author(s):  
Hung Nguyen-An ◽  
Thomas Silverston ◽  
Taku Yamazaki ◽  
Takumi Miyoshi
Keyword(s):  
Smart Home ◽  
Large Scale ◽  
Traffic Modeling ◽  
The Novel ◽  
Network Behavior ◽  
Performance Accuracy ◽  
Traffic Generator ◽  
Multiple Devices ◽  
Iot Devices ◽  
The Internet Of Things

We now use the Internet of things (IoT) in our everyday lives. The novel IoT devices collect cyber–physical data and provide information on the environment. Hence, IoT traffic will count for a major part of Internet traffic; however, its impact on the network is still widely unknown. IoT devices are prone to cyberattacks because of constrained resources or misconfigurations. It is essential to characterize IoT traffic and identify each device to monitor the IoT network and discriminate among legitimate and anomalous IoT traffic. In this study, we deployed a smart-home testbed comprising several IoT devices to study IoT traffic. We performed extensive measurement experiments using a novel IoT traffic generator tool called IoTTGen. This tool can generate traffic from multiple devices, emulating large-scale scenarios with different devices under different network conditions. We analyzed the IoT traffic properties by computing the entropy value of traffic parameters and visually observing the traffic on behavior shape graphs. We propose a new method for identifying traffic entropy-based devices, computing the entropy values of traffic features. The method relies on machine learning to classify the traffic. The proposed method succeeded in identifying devices with a performance accuracy up to 94% and is robust with unpredictable network behavior with traffic anomalies spreading in the network.

Sign in / Sign up

Export Citation Format

Share Document