SlideShare a Scribd company logo
1 of 2
Download to read offline
Distributed Inference in Resource
Constrained IoT for Real
Surveillance
Abstract
Advances in communication technologies and computational capabilities of
Internet of Things (IoT) devices enable a range of complex applications that
require ever increasing processing of sensors' data. An illustrative example is
real-time video surveillance that captures videos of target scenes and process
them to detect anomalies using deep learning (DL). Running deep learning
models requires huge processing and incurs high computation delay and
energy consumption on resource
introduce methods for distributed inference over IoT devices and edge server.
Two distinct algorithms are proposed to split the deep neural network layers
computation between IoT device and an edge server; the early split strategy
(ESS) for battery powered IoT devices and the late split strategy (LSS) for IoT
devices connected to regular power source. The evaluation shows that both
the ESS and LSS schemes achieve the target inference delay deadline when
Distributed Inference in Resource-
Constrained IoT for Real-Time Video
Advances in communication technologies and computational capabilities of
Internet of Things (IoT) devices enable a range of complex applications that
require ever increasing processing of sensors' data. An illustrative example is
ce that captures videos of target scenes and process
them to detect anomalies using deep learning (DL). Running deep learning
models requires huge processing and incurs high computation delay and
energy consumption on resource-constraint IoT devices. In th
introduce methods for distributed inference over IoT devices and edge server.
Two distinct algorithms are proposed to split the deep neural network layers
computation between IoT device and an edge server; the early split strategy
battery powered IoT devices and the late split strategy (LSS) for IoT
devices connected to regular power source. The evaluation shows that both
the ESS and LSS schemes achieve the target inference delay deadline when
-
Time Video
Advances in communication technologies and computational capabilities of
Internet of Things (IoT) devices enable a range of complex applications that
require ever increasing processing of sensors' data. An illustrative example is
ce that captures videos of target scenes and process
them to detect anomalies using deep learning (DL). Running deep learning
models requires huge processing and incurs high computation delay and
constraint IoT devices. In this article, we
introduce methods for distributed inference over IoT devices and edge server.
Two distinct algorithms are proposed to split the deep neural network layers
computation between IoT device and an edge server; the early split strategy
battery powered IoT devices and the late split strategy (LSS) for IoT
devices connected to regular power source. The evaluation shows that both
the ESS and LSS schemes achieve the target inference delay deadline when
tested over VGG16 and MobileNet_V2 CNN models. In terms of
computational load, the ESS scheme achieves nearly 15–20% reduction
whereas LSS scheme achieves up to 60% reduction. The gains in energy
saving of IoT devices for both the ESS and LSS schemes are nearly 18% and
52%, respectively.

More Related Content

Similar to Distributed Inference in Resource-Constrained IoT for Real-Time Video Surveillance.pdf

Deep Learning Approaches for Information Centric Network and Internet of Things
Deep Learning Approaches for Information Centric Network and Internet of ThingsDeep Learning Approaches for Information Centric Network and Internet of Things
Deep Learning Approaches for Information Centric Network and Internet of Things
ijtsrd
 
DATA MANAGEMENT ISSUES AND STUDY ON HETEROGENEOUS DATA STORAGE IN THE INTERNE...
DATA MANAGEMENT ISSUES AND STUDY ON HETEROGENEOUS DATA STORAGE IN THE INTERNE...DATA MANAGEMENT ISSUES AND STUDY ON HETEROGENEOUS DATA STORAGE IN THE INTERNE...
DATA MANAGEMENT ISSUES AND STUDY ON HETEROGENEOUS DATA STORAGE IN THE INTERNE...
CSEIJJournal
 

Similar to Distributed Inference in Resource-Constrained IoT for Real-Time Video Surveillance.pdf (20)

Evolving the service provider architecture to unleash the potential of IoT - ...
Evolving the service provider architecture to unleash the potential of IoT - ...Evolving the service provider architecture to unleash the potential of IoT - ...
Evolving the service provider architecture to unleash the potential of IoT - ...
 
Integration of internet of things with wireless sensor network
Integration of internet of things with wireless sensor networkIntegration of internet of things with wireless sensor network
Integration of internet of things with wireless sensor network
 
Database Management in Different Applications of IOT
Database Management in Different Applications of IOTDatabase Management in Different Applications of IOT
Database Management in Different Applications of IOT
 
Intelligent Internet of Things (IIoT): System Architectures and Communica...
   Intelligent Internet of Things (IIoT): System  Architectures and Communica...   Intelligent Internet of Things (IIoT): System  Architectures and Communica...
Intelligent Internet of Things (IIoT): System Architectures and Communica...
 
Deep Learning Approaches for Information Centric Network and Internet of Things
Deep Learning Approaches for Information Centric Network and Internet of ThingsDeep Learning Approaches for Information Centric Network and Internet of Things
Deep Learning Approaches for Information Centric Network and Internet of Things
 
On detecting and identifying faulty internet of things devices and outages
On detecting and identifying faulty internet of things devices and outagesOn detecting and identifying faulty internet of things devices and outages
On detecting and identifying faulty internet of things devices and outages
 
Edge computing and its role in architecting IoT
Edge computing and its role in architecting IoTEdge computing and its role in architecting IoT
Edge computing and its role in architecting IoT
 
Integrating Wireless Sensor Network into Cloud Services for Real-time Data Co...
Integrating Wireless Sensor Network into Cloud Services for Real-time Data Co...Integrating Wireless Sensor Network into Cloud Services for Real-time Data Co...
Integrating Wireless Sensor Network into Cloud Services for Real-time Data Co...
 
Towards internet of things iots integration of wireless sensor network to clo...
Towards internet of things iots integration of wireless sensor network to clo...Towards internet of things iots integration of wireless sensor network to clo...
Towards internet of things iots integration of wireless sensor network to clo...
 
Iot Report
Iot ReportIot Report
Iot Report
 
IoTwlcHITnewSlideshare.pptx
IoTwlcHITnewSlideshare.pptxIoTwlcHITnewSlideshare.pptx
IoTwlcHITnewSlideshare.pptx
 
Малоресурсная криптография - Сергей Мартыненко
Малоресурсная криптография - Сергей МартыненкоМалоресурсная криптография - Сергей Мартыненко
Малоресурсная криптография - Сергей Мартыненко
 
IOT.pdf
IOT.pdfIOT.pdf
IOT.pdf
 
1570272924-3
1570272924-31570272924-3
1570272924-3
 
DISTRIBUTED SYSTEM FOR 3D REMOTE MONITORING USING KINECT DEPTH CAMERAS
DISTRIBUTED SYSTEM FOR 3D REMOTE MONITORING USING KINECT DEPTH CAMERASDISTRIBUTED SYSTEM FOR 3D REMOTE MONITORING USING KINECT DEPTH CAMERAS
DISTRIBUTED SYSTEM FOR 3D REMOTE MONITORING USING KINECT DEPTH CAMERAS
 
Deep Learning and Big Data technologies for IoT Security
Deep Learning and Big Data technologies for IoT SecurityDeep Learning and Big Data technologies for IoT Security
Deep Learning and Big Data technologies for IoT Security
 
RPL AND COAP PROTOCOLS, EXPERIMENTAL ANALYSIS FOR IOT: A CASE STUDY
RPL AND COAP PROTOCOLS, EXPERIMENTAL ANALYSIS FOR IOT: A CASE STUDYRPL AND COAP PROTOCOLS, EXPERIMENTAL ANALYSIS FOR IOT: A CASE STUDY
RPL AND COAP PROTOCOLS, EXPERIMENTAL ANALYSIS FOR IOT: A CASE STUDY
 
RPL AND COAP PROTOCOLS, EXPERIMENTAL ANALYSIS FOR IOT: A CASE STUDY
RPL AND COAP PROTOCOLS, EXPERIMENTAL ANALYSIS FOR IOT: A CASE STUDYRPL AND COAP PROTOCOLS, EXPERIMENTAL ANALYSIS FOR IOT: A CASE STUDY
RPL AND COAP PROTOCOLS, EXPERIMENTAL ANALYSIS FOR IOT: A CASE STUDY
 
RPL AND COAP PROTOCOLS, EXPERIMENTAL ANALYSIS FOR IOT: A CASE STUDY
RPL AND COAP PROTOCOLS, EXPERIMENTAL ANALYSIS FOR IOT: A CASE STUDYRPL AND COAP PROTOCOLS, EXPERIMENTAL ANALYSIS FOR IOT: A CASE STUDY
RPL AND COAP PROTOCOLS, EXPERIMENTAL ANALYSIS FOR IOT: A CASE STUDY
 
DATA MANAGEMENT ISSUES AND STUDY ON HETEROGENEOUS DATA STORAGE IN THE INTERNE...
DATA MANAGEMENT ISSUES AND STUDY ON HETEROGENEOUS DATA STORAGE IN THE INTERNE...DATA MANAGEMENT ISSUES AND STUDY ON HETEROGENEOUS DATA STORAGE IN THE INTERNE...
DATA MANAGEMENT ISSUES AND STUDY ON HETEROGENEOUS DATA STORAGE IN THE INTERNE...
 

More from OKOKPROJECTS

More from OKOKPROJECTS (20)

Distributed State Estimation With Deep Neural Networks for Uncertain Nonlinea...
Distributed State Estimation With Deep Neural Networks for Uncertain Nonlinea...Distributed State Estimation With Deep Neural Networks for Uncertain Nonlinea...
Distributed State Estimation With Deep Neural Networks for Uncertain Nonlinea...
 
DLTIF Deep Learning-Driven Cyber Threat Intelligence Modeling and Identificat...
DLTIF Deep Learning-Driven Cyber Threat Intelligence Modeling and Identificat...DLTIF Deep Learning-Driven Cyber Threat Intelligence Modeling and Identificat...
DLTIF Deep Learning-Driven Cyber Threat Intelligence Modeling and Identificat...
 
DGSSC A Deep Generative Spectral-Spatial Classifier for Imbalanced Hyperspect...
DGSSC A Deep Generative Spectral-Spatial Classifier for Imbalanced Hyperspect...DGSSC A Deep Generative Spectral-Spatial Classifier for Imbalanced Hyperspect...
DGSSC A Deep Generative Spectral-Spatial Classifier for Imbalanced Hyperspect...
 
Digital Restoration of Cultural Heritage With Data-Driven Computing A Survey.pdf
Digital Restoration of Cultural Heritage With Data-Driven Computing A Survey.pdfDigital Restoration of Cultural Heritage With Data-Driven Computing A Survey.pdf
Digital Restoration of Cultural Heritage With Data-Driven Computing A Survey.pdf
 
Dependable Intrusion Detection System for IoT A Deep Transfer Learning Based ...
Dependable Intrusion Detection System for IoT A Deep Transfer Learning Based ...Dependable Intrusion Detection System for IoT A Deep Transfer Learning Based ...
Dependable Intrusion Detection System for IoT A Deep Transfer Learning Based ...
 
DendroMap Visual Exploration of Large-Scale Image Datasets for Machine Learni...
DendroMap Visual Exploration of Large-Scale Image Datasets for Machine Learni...DendroMap Visual Exploration of Large-Scale Image Datasets for Machine Learni...
DendroMap Visual Exploration of Large-Scale Image Datasets for Machine Learni...
 
Dense Nested Attention Network for Infrared Small Target Detection.pdf
Dense Nested Attention Network for Infrared Small Target Detection.pdfDense Nested Attention Network for Infrared Small Target Detection.pdf
Dense Nested Attention Network for Infrared Small Target Detection.pdf
 
Detection of Small Moving Targets in Cluttered Infrared Imagery.pdf
Detection of Small Moving Targets in Cluttered Infrared Imagery.pdfDetection of Small Moving Targets in Cluttered Infrared Imagery.pdf
Detection of Small Moving Targets in Cluttered Infrared Imagery.pdf
 
Depression Screening in Humans With AI and Deep Learning Techniques.pdf
Depression Screening in Humans With AI and Deep Learning Techniques.pdfDepression Screening in Humans With AI and Deep Learning Techniques.pdf
Depression Screening in Humans With AI and Deep Learning Techniques.pdf
 
DeepTx Deep Learning Beamforming With Channel Prediction.pdf
DeepTx Deep Learning Beamforming With Channel Prediction.pdfDeepTx Deep Learning Beamforming With Channel Prediction.pdf
DeepTx Deep Learning Beamforming With Channel Prediction.pdf
 
DeHIN A Decentralized Framework for Embedding Large-Scale Heterogeneous Infor...
DeHIN A Decentralized Framework for Embedding Large-Scale Heterogeneous Infor...DeHIN A Decentralized Framework for Embedding Large-Scale Heterogeneous Infor...
DeHIN A Decentralized Framework for Embedding Large-Scale Heterogeneous Infor...
 
DefQ Defensive Quantization Against Inference Slow-Down Attack for Edge Compu...
DefQ Defensive Quantization Against Inference Slow-Down Attack for Edge Compu...DefQ Defensive Quantization Against Inference Slow-Down Attack for Edge Compu...
DefQ Defensive Quantization Against Inference Slow-Down Attack for Edge Compu...
 
Deep-Learning-Driven Proactive Maintenance Management of IoT-Empowered Smart ...
Deep-Learning-Driven Proactive Maintenance Management of IoT-Empowered Smart ...Deep-Learning-Driven Proactive Maintenance Management of IoT-Empowered Smart ...
Deep-Learning-Driven Proactive Maintenance Management of IoT-Empowered Smart ...
 
Deep-Distributed-Learning-Based POI Recommendation Under Mobile-Edge Networks...
Deep-Distributed-Learning-Based POI Recommendation Under Mobile-Edge Networks...Deep-Distributed-Learning-Based POI Recommendation Under Mobile-Edge Networks...
Deep-Distributed-Learning-Based POI Recommendation Under Mobile-Edge Networks...
 
DeepCog A Trustworthy Deep Learning-Based Human Cognitive Privacy Framework i...
DeepCog A Trustworthy Deep Learning-Based Human Cognitive Privacy Framework i...DeepCog A Trustworthy Deep Learning-Based Human Cognitive Privacy Framework i...
DeepCog A Trustworthy Deep Learning-Based Human Cognitive Privacy Framework i...
 
DeepCrowd A Deep Model for Large-Scale Citywide Crowd Density and Flow Predic...
DeepCrowd A Deep Model for Large-Scale Citywide Crowd Density and Flow Predic...DeepCrowd A Deep Model for Large-Scale Citywide Crowd Density and Flow Predic...
DeepCrowd A Deep Model for Large-Scale Citywide Crowd Density and Flow Predic...
 
D2Net Deep Denoising Network in Frequency Domain for Hyperspectral Image.pdf
D2Net Deep Denoising Network in Frequency Domain for Hyperspectral Image.pdfD2Net Deep Denoising Network in Frequency Domain for Hyperspectral Image.pdf
D2Net Deep Denoising Network in Frequency Domain for Hyperspectral Image.pdf
 
Decentralized Federated Learning for Industrial IoT With Deep Echo State Netw...
Decentralized Federated Learning for Industrial IoT With Deep Echo State Netw...Decentralized Federated Learning for Industrial IoT With Deep Echo State Netw...
Decentralized Federated Learning for Industrial IoT With Deep Echo State Netw...
 
Cyber Code Intelligence for Android Malware Detection.pdf
Cyber Code Intelligence for Android Malware Detection.pdfCyber Code Intelligence for Android Malware Detection.pdf
Cyber Code Intelligence for Android Malware Detection.pdf
 
CSKG4APT A Cybersecurity Knowledge Graph for Advanced Persistent Threat Organ...
CSKG4APT A Cybersecurity Knowledge Graph for Advanced Persistent Threat Organ...CSKG4APT A Cybersecurity Knowledge Graph for Advanced Persistent Threat Organ...
CSKG4APT A Cybersecurity Knowledge Graph for Advanced Persistent Threat Organ...
 

Recently uploaded

SPLICE Working Group: Reusable Code Examples
SPLICE Working Group:Reusable Code ExamplesSPLICE Working Group:Reusable Code Examples
SPLICE Working Group: Reusable Code Examples
Peter Brusilovsky
 
Spellings Wk 4 and Wk 5 for Grade 4 at CAPS
Spellings Wk 4 and Wk 5 for Grade 4 at CAPSSpellings Wk 4 and Wk 5 for Grade 4 at CAPS
Spellings Wk 4 and Wk 5 for Grade 4 at CAPS
AnaAcapella
 
SURVEY I created for uni project research
SURVEY I created for uni project researchSURVEY I created for uni project research
SURVEY I created for uni project research
CaitlinCummins3
 

Recently uploaded (20)

Supporting Newcomer Multilingual Learners
Supporting Newcomer  Multilingual LearnersSupporting Newcomer  Multilingual Learners
Supporting Newcomer Multilingual Learners
 
SPLICE Working Group: Reusable Code Examples
SPLICE Working Group:Reusable Code ExamplesSPLICE Working Group:Reusable Code Examples
SPLICE Working Group: Reusable Code Examples
 
How to Manage Website in Odoo 17 Studio App.pptx
How to Manage Website in Odoo 17 Studio App.pptxHow to Manage Website in Odoo 17 Studio App.pptx
How to Manage Website in Odoo 17 Studio App.pptx
 
ESSENTIAL of (CS/IT/IS) class 07 (Networks)
ESSENTIAL of (CS/IT/IS) class 07 (Networks)ESSENTIAL of (CS/IT/IS) class 07 (Networks)
ESSENTIAL of (CS/IT/IS) class 07 (Networks)
 
Observing-Correct-Grammar-in-Making-Definitions.pptx
Observing-Correct-Grammar-in-Making-Definitions.pptxObserving-Correct-Grammar-in-Making-Definitions.pptx
Observing-Correct-Grammar-in-Making-Definitions.pptx
 
Spellings Wk 4 and Wk 5 for Grade 4 at CAPS
Spellings Wk 4 and Wk 5 for Grade 4 at CAPSSpellings Wk 4 and Wk 5 for Grade 4 at CAPS
Spellings Wk 4 and Wk 5 for Grade 4 at CAPS
 
An overview of the various scriptures in Hinduism
An overview of the various scriptures in HinduismAn overview of the various scriptures in Hinduism
An overview of the various scriptures in Hinduism
 
OS-operating systems- ch05 (CPU Scheduling) ...
OS-operating systems- ch05 (CPU Scheduling) ...OS-operating systems- ch05 (CPU Scheduling) ...
OS-operating systems- ch05 (CPU Scheduling) ...
 
UChicago CMSC 23320 - The Best Commit Messages of 2024
UChicago CMSC 23320 - The Best Commit Messages of 2024UChicago CMSC 23320 - The Best Commit Messages of 2024
UChicago CMSC 23320 - The Best Commit Messages of 2024
 
Sternal Fractures & Dislocations - EMGuidewire Radiology Reading Room
Sternal Fractures & Dislocations - EMGuidewire Radiology Reading RoomSternal Fractures & Dislocations - EMGuidewire Radiology Reading Room
Sternal Fractures & Dislocations - EMGuidewire Radiology Reading Room
 
e-Sealing at EADTU by Kamakshi Rajagopal
e-Sealing at EADTU by Kamakshi Rajagopale-Sealing at EADTU by Kamakshi Rajagopal
e-Sealing at EADTU by Kamakshi Rajagopal
 
24 ĐỀ THAM KHẢO KÌ THI TUYỂN SINH VÀO LỚP 10 MÔN TIẾNG ANH SỞ GIÁO DỤC HẢI DƯ...
24 ĐỀ THAM KHẢO KÌ THI TUYỂN SINH VÀO LỚP 10 MÔN TIẾNG ANH SỞ GIÁO DỤC HẢI DƯ...24 ĐỀ THAM KHẢO KÌ THI TUYỂN SINH VÀO LỚP 10 MÔN TIẾNG ANH SỞ GIÁO DỤC HẢI DƯ...
24 ĐỀ THAM KHẢO KÌ THI TUYỂN SINH VÀO LỚP 10 MÔN TIẾNG ANH SỞ GIÁO DỤC HẢI DƯ...
 
ĐỀ THAM KHẢO KÌ THI TUYỂN SINH VÀO LỚP 10 MÔN TIẾNG ANH FORM 50 CÂU TRẮC NGHI...
ĐỀ THAM KHẢO KÌ THI TUYỂN SINH VÀO LỚP 10 MÔN TIẾNG ANH FORM 50 CÂU TRẮC NGHI...ĐỀ THAM KHẢO KÌ THI TUYỂN SINH VÀO LỚP 10 MÔN TIẾNG ANH FORM 50 CÂU TRẮC NGHI...
ĐỀ THAM KHẢO KÌ THI TUYỂN SINH VÀO LỚP 10 MÔN TIẾNG ANH FORM 50 CÂU TRẮC NGHI...
 
Analyzing and resolving a communication crisis in Dhaka textiles LTD.pptx
Analyzing and resolving a communication crisis in Dhaka textiles LTD.pptxAnalyzing and resolving a communication crisis in Dhaka textiles LTD.pptx
Analyzing and resolving a communication crisis in Dhaka textiles LTD.pptx
 
Đề tieng anh thpt 2024 danh cho cac ban hoc sinh
Đề tieng anh thpt 2024 danh cho cac ban hoc sinhĐề tieng anh thpt 2024 danh cho cac ban hoc sinh
Đề tieng anh thpt 2024 danh cho cac ban hoc sinh
 
SURVEY I created for uni project research
SURVEY I created for uni project researchSURVEY I created for uni project research
SURVEY I created for uni project research
 
Graduate Outcomes Presentation Slides - English (v3).pptx
Graduate Outcomes Presentation Slides - English (v3).pptxGraduate Outcomes Presentation Slides - English (v3).pptx
Graduate Outcomes Presentation Slides - English (v3).pptx
 
diagnosting testing bsc 2nd sem.pptx....
diagnosting testing bsc 2nd sem.pptx....diagnosting testing bsc 2nd sem.pptx....
diagnosting testing bsc 2nd sem.pptx....
 
How to Send Pro Forma Invoice to Your Customers in Odoo 17
How to Send Pro Forma Invoice to Your Customers in Odoo 17How to Send Pro Forma Invoice to Your Customers in Odoo 17
How to Send Pro Forma Invoice to Your Customers in Odoo 17
 
The Story of Village Palampur Class 9 Free Study Material PDF
The Story of Village Palampur Class 9 Free Study Material PDFThe Story of Village Palampur Class 9 Free Study Material PDF
The Story of Village Palampur Class 9 Free Study Material PDF
 

Distributed Inference in Resource-Constrained IoT for Real-Time Video Surveillance.pdf

  • 1. Distributed Inference in Resource Constrained IoT for Real Surveillance Abstract Advances in communication technologies and computational capabilities of Internet of Things (IoT) devices enable a range of complex applications that require ever increasing processing of sensors' data. An illustrative example is real-time video surveillance that captures videos of target scenes and process them to detect anomalies using deep learning (DL). Running deep learning models requires huge processing and incurs high computation delay and energy consumption on resource introduce methods for distributed inference over IoT devices and edge server. Two distinct algorithms are proposed to split the deep neural network layers computation between IoT device and an edge server; the early split strategy (ESS) for battery powered IoT devices and the late split strategy (LSS) for IoT devices connected to regular power source. The evaluation shows that both the ESS and LSS schemes achieve the target inference delay deadline when Distributed Inference in Resource- Constrained IoT for Real-Time Video Advances in communication technologies and computational capabilities of Internet of Things (IoT) devices enable a range of complex applications that require ever increasing processing of sensors' data. An illustrative example is ce that captures videos of target scenes and process them to detect anomalies using deep learning (DL). Running deep learning models requires huge processing and incurs high computation delay and energy consumption on resource-constraint IoT devices. In th introduce methods for distributed inference over IoT devices and edge server. Two distinct algorithms are proposed to split the deep neural network layers computation between IoT device and an edge server; the early split strategy battery powered IoT devices and the late split strategy (LSS) for IoT devices connected to regular power source. The evaluation shows that both the ESS and LSS schemes achieve the target inference delay deadline when - Time Video Advances in communication technologies and computational capabilities of Internet of Things (IoT) devices enable a range of complex applications that require ever increasing processing of sensors' data. An illustrative example is ce that captures videos of target scenes and process them to detect anomalies using deep learning (DL). Running deep learning models requires huge processing and incurs high computation delay and constraint IoT devices. In this article, we introduce methods for distributed inference over IoT devices and edge server. Two distinct algorithms are proposed to split the deep neural network layers computation between IoT device and an edge server; the early split strategy battery powered IoT devices and the late split strategy (LSS) for IoT devices connected to regular power source. The evaluation shows that both the ESS and LSS schemes achieve the target inference delay deadline when
  • 2. tested over VGG16 and MobileNet_V2 CNN models. In terms of computational load, the ESS scheme achieves nearly 15–20% reduction whereas LSS scheme achieves up to 60% reduction. The gains in energy saving of IoT devices for both the ESS and LSS schemes are nearly 18% and 52%, respectively.