Edge Learning

Machine Learning ( ML ) has demonstrated great promise in various fields, e.g., self-driving, smart city, which are fundamentally altering the way individuals and organizations live, work, and interact. Traditional centralized learning frameworks require uploading all training data from different sources to a remote data server, which incurs significant communication overhead, service latency, and privacy issues. To further extend the frontiers of the learning paradigm, a new learning concept, namely, Edge Learning ( EL ) is emerging. It is complementary to the cloud-based methods for big data analytics by enabling distributed edge nodes to cooperatively training models and conduct inferences with their locally cached data. To explore the new characteristics and potential prospects of EL, we conduct a comprehensive survey of the recent research efforts on EL. Specifically, we first introduce the background and motivation. We then discuss the challenging issues in EL from the aspects of data, computation, and communication. Furthermore, we provide an overview of the enabling technologies for EL, including model training, inference, security guarantee, privacy protection, and incentive mechanism. Finally, we discuss future research opportunities on EL. We believe that this survey will provide a comprehensive overview of EL and stimulate fruitful future research in this field.

Download Full-text

Authentication Protocols for Internet of Things: A Comprehensive Survey

Security and Communication Networks ◽

10.1155/2017/6562953 ◽

2017 ◽

Vol 2017 ◽

pp. 1-41 ◽

Cited By ~ 84

Author(s):

Mohamed Amine Ferrag ◽

Leandros A. Maglaras ◽

Helge Janicke ◽

Jianmin Jiang ◽

Lei Shu

Keyword(s):

Internet Of Things ◽

Future Research ◽

Communication Overhead ◽

Authentication Protocols ◽

Internet Of Vehicles ◽

Current Survey ◽

Comprehensive Survey ◽

Future Research Directions ◽

Target Environment ◽

Verification Techniques

In this paper, a comprehensive survey of authentication protocols for Internet of Things (IoT) is presented. Specifically more than forty authentication protocols developed for or applied in the context of the IoT are selected and examined in detail. These protocols are categorized based on the target environment: (1) Machine to Machine Communications (M2M), (2) Internet of Vehicles (IoV), (3) Internet of Energy (IoE), and (4) Internet of Sensors (IoS). Threat models, countermeasures, and formal security verification techniques used in authentication protocols for the IoT are presented. In addition a taxonomy and comparison of authentication protocols that are developed for the IoT in terms of network model, specific security goals, main processes, computation complexity, and communication overhead are provided. Based on the current survey, open issues are identified and future research directions are proposed.

Download Full-text

Methodology for Collecting a Training Dataset for an Intrusion Detection Model

Proceedings of the Institute for System Programming of RAS ◽

10.15514/ispras-2021-33(5)-5 ◽

2021 ◽

Vol 33 (5) ◽

pp. 83-104

Author(s):

Aleksandr Igorevich Getman ◽

Maxim Nikolaevich Goryunov ◽

Andrey Georgievich Matskevich ◽

Dmitry Aleksandrovich Rybolovlev

Keyword(s):

Attack Detection ◽

Training Data ◽

Training Dataset ◽

Training Models ◽

The Public ◽

Detection Model ◽

Computer Attacks ◽

Model Training ◽

Public Datasets

The paper discusses the issues of training models for detecting computer attacks based on the use of machine learning methods. The results of the analysis of publicly available training datasets and tools for analyzing network traffic and identifying features of network sessions are presented sequentially. The drawbacks of existing tools and possible errors in the datasets formed with their help are noted. It is concluded that it is necessary to collect own training data in the absence of guarantees of the public datasets reliability and the limited use of pre-trained models in networks with characteristics that differ from the characteristics of the network in which the training traffic was collected. A practical approach to generating training data for computer attack detection models is proposed. The proposed solutions have been tested to evaluate the quality of model training on the collected data and the quality of attack detection in conditions of real network infrastructure.

Download Full-text

Leveraging Expert Knowledge for Label Noise Mitigation in Machine Learning

Applied Sciences ◽

10.3390/app112211040 ◽

2021 ◽

Vol 11 (22) ◽

pp. 11040

Author(s):

Quoc Nguyen ◽

Tomoaki Shikina ◽

Daichi Teruya ◽

Seiji Hotta ◽

Huy-Dung Han ◽

...

Keyword(s):

Machine Learning ◽

Expert Knowledge ◽

Classification Problem ◽

Training Data ◽

Noise Mitigation ◽

Label Noise ◽

Training Models ◽

Gradient Descent Algorithm ◽

Machine Learning Applications ◽

Model Training

In training-based Machine Learning applications, the training data are frequently labeled by non-experts and expose substantial label noise which greatly alters the training models. In this work, a novel method for reducing the effect of label noise is introduced. The rules are created from expert knowledge to identify the incorrect non-expert training data. Using the gradient descent algorithm, the violating data samples are weighted less to mitigate their effects during model training. The proposed method is applied to the image classification problem using Manga109 and CIFAR-10 dataset. The experiments show that when the noise level is up to 50% our proposed method significantly increases the accuracy of the model compared to conventional learning methods.

Download Full-text

A general deep learning model for bird detection in high resolution airborne imagery

10.1101/2021.08.05.455311 ◽

2021 ◽

Author(s):

Ben G Weinstein ◽

Lindsey Gardner ◽

Vienna Saccomanno ◽

Ashley Steinkraus ◽

Andrew Ortega ◽

...

Keyword(s):

Computer Vision ◽

Ecological Monitoring ◽

Training Data ◽

Fine Tuning ◽

Great Promise ◽

Detection Model ◽

Bird Detection ◽

Model Training ◽

Computational Resources ◽

And Behavior

Advances in artificial intelligence for image processing hold great promise for increasing the scales at which ecological systems can be studied. The distribution and behavior of individuals is central to ecology, and computer vision using deep neural networks can learn to detect individual objects in imagery. However, developing computer vision for ecological monitoring is challenging because it needs large amounts of human-labeled training data, requires advanced technical expertise and computational infrastructure, and is prone to overfitting. This limits application across space and time. One solution is developing generalized models that can be applied across species and ecosystems. Using over 250,000 annotations from 13 projects from around the world, we develop a general bird detection model that achieves over 65% recall and 50% precision on novel aerial data without any local training despite differences in species, habitat, and imaging methodology. Fine-tuning this model with only 1000 local annotations increases these values to an average of 84% recall and 69% precision by building on the general features learned from other data sources. Retraining from the general model improves local predictions even when moderately large annotation sets are available and makes model training faster and more stable. Our results demonstrate that general models for detecting broad classes of organisms using airborne imagery are achievable. These models can reduce the effort, expertise, and computational resources necessary for automating the detection of individual organisms across large scales, helping to transform the scale of data collection in ecology and the questions that can be addressed.

Download Full-text

Organizational Commitment and Lean Sustainability: Literature Review and Directions for Future Research

Sustainability ◽

10.3390/su13063357 ◽

2021 ◽

Vol 13 (6) ◽

pp. 3357 ◽

Cited By ~ 1

Author(s):

Amal Benkarim ◽

Daniel Imbeau

Keyword(s):

Organizational Commitment ◽

Literature Review ◽

Lean Manufacturing ◽

Affective Commitment ◽

Management Practices ◽

Employee Commitment ◽

Future Research ◽

Comprehensive Overview ◽

Narrative Literature Review ◽

Key Aspects

The vast majority of works published on Lean focus on the evaluation of tools and/or the strategies needed for its implementation. Although many authors highlight the degree of employee commitment as one of the key aspects of Lean, what has gone largely unnoticed in the literature, is that few studies have examined in-depth the concept of organizational commitment in connection with Lean. With this narrative literature review article, our main objective is (1) to identify and analyze an extensive body of literature that addresses the Lean Manufacturing approach and how it relates to employee commitment, emphasizing affective commitment as the main type of organizational commitment positively associated with Lean, and (2) to highlight the management practices required to encourage this kind of commitment and promote the success and sustainability of Lean. This paper aims to provide a comprehensive overview that can help researchers and practitioners interested in Lean better understand the importance of employee commitment in this type of approach, and as well, to identify related research questions.

Download Full-text

Review on the Use of Artificial Intelligence to Predict Fire Performance of Construction Materials and Their Flame Retardancy

Molecules ◽

10.3390/molecules26041022 ◽

2021 ◽

Vol 26 (4) ◽

pp. 1022

Author(s):

Hoang T. Nguyen ◽

Kate T. Q. Nguyen ◽

Tu C. Le ◽

Guomin Zhang

Keyword(s):

Artificial Intelligence ◽

Flame Retardancy ◽

Material Science ◽

Construction Materials ◽

Engineering Problem ◽

Future Research ◽

Fire Performance ◽

Structural Components ◽

Comprehensive Overview ◽

Fire Engineering

The evaluation and interpretation of the behavior of construction materials under fire conditions have been complicated. Over the last few years, artificial intelligence (AI) has emerged as a reliable method to tackle this engineering problem. This review summarizes existing studies that applied AI to predict the fire performance of different construction materials (e.g., concrete, steel, timber, and composites). The prediction of the flame retardancy of some structural components such as beams, columns, slabs, and connections by utilizing AI-based models is also discussed. The end of this review offers insights on the advantages, existing challenges, and recommendations for the development of AI techniques used to evaluate the fire performance of construction materials and their flame retardancy. This review offers a comprehensive overview to researchers in the fields of fire engineering and material science, and it encourages them to explore and consider the use of AI in future research projects.

Download Full-text

A Comprehensive Survey of Neural Architecture Search

ACM Computing Surveys ◽

10.1145/3447582 ◽

2021 ◽

Vol 54 (4) ◽

pp. 1-34

Author(s):

Pengzhen Ren ◽

Yun Xiao ◽

Xiaojun Chang ◽

Po-yao Huang ◽

Zhihui Li ◽

...

Keyword(s):

Research Work ◽

Search Space ◽

Feature Representation ◽

Future Research ◽

Related Research ◽

Neural Architecture ◽

Comprehensive Survey ◽

Future Research Directions ◽

Intuitive Idea ◽

New Perspective

Deep learning has made substantial breakthroughs in many fields due to its powerful automatic representation capabilities. It has been proven that neural architecture design is crucial to the feature representation of data and the final performance. However, the design of the neural architecture heavily relies on the researchers’ prior knowledge and experience. And due to the limitations of humans’ inherent knowledge, it is difficult for people to jump out of their original thinking paradigm and design an optimal model. Therefore, an intuitive idea would be to reduce human intervention as much as possible and let the algorithm automatically design the neural architecture. Neural Architecture Search ( NAS ) is just such a revolutionary algorithm, and the related research work is complicated and rich. Therefore, a comprehensive and systematic survey on the NAS is essential. Previously related surveys have begun to classify existing work mainly based on the key components of NAS: search space, search strategy, and evaluation strategy. While this classification method is more intuitive, it is difficult for readers to grasp the challenges and the landmark work involved. Therefore, in this survey, we provide a new perspective: beginning with an overview of the characteristics of the earliest NAS algorithms, summarizing the problems in these early NAS algorithms, and then providing solutions for subsequent related research work. In addition, we conduct a detailed and comprehensive analysis, comparison, and summary of these works. Finally, we provide some possible future research directions.

Download Full-text

Fully automated contrast and non-contrast cardiac view detection in echocardiography a multi-centre, multi-vendor study

European Heart Journal ◽

10.1093/ehjci/ehaa946.0078 ◽

2020 ◽

Vol 41 (Supplement_2) ◽

Author(s):

S Gao ◽

D Stojanovski ◽

A Parker ◽

P Marques ◽

S Heitner ◽

...

Keyword(s):

Neural Network ◽

Training Data ◽

Classification Model ◽

Validation Dataset ◽

Funding Source ◽

Private Company ◽

Validation Data ◽

Independent Test ◽

Model Training ◽

Confusion Matrices

Abstract Background Correctly identifying views acquired in a 2D echocardiographic examination is paramount to post-processing and quantification steps often performed as part of most clinical workflows. In many exams, particularly in stress echocardiography, microbubble contrast is used which greatly affects the appearance of the cardiac views. Here we present a bespoke, fully automated convolutional neural network (CNN) which identifies apical 2, 3, and 4 chamber, and short axis (SAX) views acquired with and without contrast. The CNN was tested in a completely independent, external dataset with the data acquired in a different country than that used to train the neural network. Methods Training data comprised of 2D echocardiograms was taken from 1014 subjects from a prospective multisite, multi-vendor, UK trial with the number of frames in each view greater than 17,500. Prior to view classification model training, images were processed using standard techniques to ensure homogenous and normalised image inputs to the training pipeline. A bespoke CNN was built using the minimum number of convolutional layers required with batch normalisation, and including dropout for reducing overfitting. Before processing, the data was split into 90% for model training (211,958 frames), and 10% used as a validation dataset (23,946 frames). Image frames from different subjects were separated out entirely amongst the training and validation datasets. Further, a separate trial dataset of 240 studies acquired in the USA was used as an independent test dataset (39,401 frames). Results Figure 1 shows the confusion matrices for both validation data (left) and independent test data (right), with an overall accuracy of 96% and 95% for the validation and test datasets respectively. The accuracy for the non-contrast cardiac views of >99% exceeds that seen in other works. The combined datasets included images acquired across ultrasound manufacturers and models from 12 clinical sites. Conclusion We have developed a CNN capable of automatically accurately identifying all relevant cardiac views used in “real world” echo exams, including views acquired with contrast. Use of the CNN in a routine clinical workflow could improve efficiency of quantification steps performed after image acquisition. This was tested on an independent dataset acquired in a different country to that used to train the model and was found to perform similarly thus indicating the generalisability of the model. Figure 1. Confusion matrices Funding Acknowledgement Type of funding source: Private company. Main funding source(s): Ultromics Ltd.

Download Full-text

Access Control Mechanisms in Named Data Networks

ACM Computing Surveys ◽

10.1145/3442150 ◽

2021 ◽

Vol 54 (3) ◽

pp. 1-35

Author(s):

Boubakr Nour ◽

Hakima Khelifi ◽

Rasheed Hussain ◽

Spyridon Mastorakis ◽

Hassine Moungla

Keyword(s):

Access Control ◽

Holistic Approach ◽

Future Internet ◽

Lessons Learned ◽

Future Research ◽

Communication Model ◽

Control Mechanisms ◽

Internet Communication ◽

Future Internet Architecture ◽

Comprehensive Survey

Information-Centric Networking (ICN) has recently emerged as a prominent candidate for the Future Internet Architecture (FIA) that addresses existing issues with the host-centric communication model of the current TCP/IP-based Internet. Named Data Networking (NDN) is one of the most recent and active ICN architectures that provides a clean-slate approach for Internet communication. NDN provides intrinsic content security where security is directly provided to the content instead of communication channel. Among other security aspects, Access Control (AC) rules specify the privileges for the entities that can access the content. In TCP/IP-based AC systems, due to the client-server communication model, the servers control which client can access a particular content. In contrast, ICN-based networks use content names to drive communication and decouple the content from its original location. This phenomenon leads to the loss of control over the content, causing different challenges for the realization of efficient AC mechanisms. To date, considerable efforts have been made to develop various AC mechanisms in NDN. In this article, we provide a detailed and comprehensive survey of the AC mechanisms in NDN. We follow a holistic approach towards AC in NDN where we first summarize the ICN paradigm, describe the changes from channel-based security to content-based security, and highlight different cryptographic algorithms and security protocols in NDN. We then classify the existing AC mechanisms into two main categories: Encryption-based AC and Encryption-independent AC . Each category has different classes based on the working principle of AC (e.g., Attribute-based AC, Name-based AC, Identity-based AC). Finally, we present the lessons learned from the existing AC mechanisms and identify the challenges of NDN-based AC at large, highlighting future research directions for the community.

Download Full-text

Artificial Intelligence, 3D Documentation, and Rock Art—Approaching and Reflecting on the Automation of Identification and Classification of Rock Art Images

Journal of Archaeological Method and Theory ◽

10.1007/s10816-021-09518-6 ◽

2021 ◽

Author(s):

Christian Horn ◽

Oscar Ivarsson ◽

Cecilia Lindhé ◽

Rich Potter ◽

Ashely Green ◽

...

Keyword(s):

Artificial Intelligence ◽

Bronze Age ◽

Data Augmentation ◽

Rock Art ◽

Training Data ◽

Future Research ◽

Rock Surface ◽

Southern Scandinavia ◽

Bounding Boxes

AbstractRock art carvings, which are best described as petroglyphs, were produced by removing parts of the rock surface to create a negative relief. This tradition was particularly strong during the Nordic Bronze Age (1700–550 BC) in southern Scandinavia with over 20,000 boats and thousands of humans, animals, wagons, etc. This vivid and highly engaging material provides quantitative data of high potential to understand Bronze Age social structures and ideologies. The ability to provide the technically best possible documentation and to automate identification and classification of images would help to take full advantage of the research potential of petroglyphs in southern Scandinavia and elsewhere. We, therefore, attempted to train a model that locates and classifies image objects using faster region-based convolutional neural network (Faster-RCNN) based on data produced by a novel method to improve visualizing the content of 3D documentations. A newly created layer of 3D rock art documentation provides the best data currently available and has reduced inscribed bias compared to older methods. Several models were trained based on input images annotated with bounding boxes produced with different parameters to find the best solution. The data included 4305 individual images in 408 scans of rock art sites. To enhance the models and enrich the training data, we used data augmentation and transfer learning. The successful models perform exceptionally well on boats and circles, as well as with human figures and wheels. This work was an interdisciplinary undertaking which led to important reflections about archaeology, digital humanities, and artificial intelligence. The reflections and the success represented by the trained models open novel avenues for future research on rock art.

Download Full-text