Multi-fidelity deep neural networks for adaptive inference in the internet of multimedia things

Leroux, Sam; Bohez, Steven; Coninck, Elias De; Molle, Pieter Van; Vankeirsbilck, Bert; Verbelen, Tim; Simoens, Pieter; Dhoedt, Bart

doi:10.1016/j.future.2019.03.001

Cited by 12 publications

(13 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Data-driven digital twins are built using machine learning. In this domain, deep learning (DL) is the dominant branch today, yet DL comes with its own problems: it requires domain knowledge to select the appropriate machine learning pipeline and it is very resource hungry in terms of computing and storage resources [ 36 , 43 , 44 ]. AutoML approaches can be used to automate the pipeline building, but these tools are currently unable to deal with sequential data that is usually used in building behavioral models.…”

Section: Realization Aspects Of Ai-based System Elementsmentioning

confidence: 99%

An Artificial Intelligence-Based Collaboration Approach in Industrial IoT Manufacturing: Key Concepts, Architectural Extensions and Potential Applications

Trakadas

Simoens

Gkonis

et al. 2020

Sensors

Self Cite

View full text Add to dashboard Cite

The digitization of manufacturing industry has led to leaner and more efficient production, under the Industry 4.0 concept. Nowadays, datasets collected from shop floor assets and information technology (IT) systems are used in data-driven analytics efforts to support more informed business intelligence decisions. However, these results are currently only used in isolated and dispersed parts of the production process. At the same time, full integration of artificial intelligence (AI) in all parts of manufacturing systems is currently lacking. In this context, the goal of this manuscript is to present a more holistic integration of AI by promoting collaboration. To this end, collaboration is understood as a multi-dimensional conceptual term that covers all important enablers for AI adoption in manufacturing contexts and is promoted in terms of business intelligence optimization, human-in-the-loop and secure federation across manufacturing sites. To address these challenges, the proposed architectural approach builds on three technical pillars: (1) components that extend the functionality of the existing layers in the Reference Architectural Model for Industry 4.0; (2) definition of new layers for collaboration by means of human-in-the-loop and federation; (3) security concerns with AI-powered mechanisms. In addition, system implementation aspects are discussed and potential applications in industrial environments, as well as business impacts, are presented.

show abstract

Section: Realization Aspects Of Ai-based System Elementsmentioning

confidence: 99%

An Artificial Intelligence-Based Collaboration Approach in Industrial IoT Manufacturing: Key Concepts, Architectural Extensions and Potential Applications

Trakadas

Simoens

Gkonis

et al. 2020

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…Some accuracy loss also happens in the work proposed by Leroux et al [10], which build several neural networks with an increasing number of parameters. Their approach is called Multi-fidelity DNNs.…”

Section: Machine Learning and Iot Toolsmentioning

confidence: 99%

“…DeepThings [32] No No No along the neural ML IoT network layers Multifidelity [10] Yes Yes No N/A ML IoT Benedetto et al [30] No No Yes per neurons IoT * Not applicable. ** To use implemented functions.…”

Section: Machine Learning and Iot Toolsmentioning

confidence: 99%

“…The second approach partitions the neural network and executes in a distributed way on multiple devices. In some works that employ the first approach, pruning a neural network results in accuracy loss [8][9][10]. On the other hand, several works can apply the first approach to reduce DNN requirements and enable its execution on limited devices without any accuracy loss [11][12][13].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Partitioning Convolutional Neural Networks to Maximize the Inference Rate on Constrained IoT Devices

Oliveira

Borin

2019

Future Internet

View full text Add to dashboard Cite

Billions of devices will compose the IoT system in the next few years, generating a huge amount of data. We can use fog computing to process these data, considering that there is the possibility of overloading the network towards the cloud. In this context, deep learning can treat these data, but the memory requirements of deep neural networks may prevent them from executing on a single resource-constrained device. Furthermore, their computational requirements may yield an unfeasible execution time. In this work, we propose *dn2pciot, a new algorithm to partition neural networks for efficient distributed execution. Our algorithm can optimize the neural network inference rate or the number of communications among devices. Additionally, our algorithm accounts appropriately for the shared parameters and biases of *cnn. We investigate the inference rate maximization for the LeNet model in constrained setups. We show that the partitionings offered by popular machine learning frameworks such as TensorFlow or by the general-purpose framework METIS may produce invalid partitionings for very constrained setups. The results show that our algorithm can partition LeNet for all the proposed setups, yielding up to 38% more inferences per second than METIS.

show abstract

“…It not only optimizes the performance of the smart home system, but also improves the safety factor. In [9,10], the author experimentally verified the method of image recognition on different benchmark data sets, and concluded that the author's method can construct a network that supports multiple trade-offs between accuracy and computational cost. In [11], the author proposed a method of personal identity verification based on finger veins by exploring the direction and magnitude of competition from finger vein images.…”

mentioning

confidence: 99%

Deep Learning Based Image Recognition for 5G Smart IoT Applications

Ning

2020

Preprint

View full text Add to dashboard Cite

With the advent of the 5G era，the development of massive data learning algorithms and in-depth research on neural networks, deep learning methods are widely used in image recognition tasks. However, there is currently a lack of methods for identifying and classifying efficiently Internet of Things (IoT) images. This paper develops an IoT image recognition system based on deep learning, i.e., uses convolutional neural networks (CNN) to construct image recognition algorithms, and uses principal component analysis (PCA) and linear discriminant analysis (LDA) to extract image features, respectively. The effectiveness of the two PCA and LDA image recognition methods is verified through experiments. And when the image feature dimension is 25, the best image recognition effect can be obtained. The main classifier used for image recognition in the IoT is the support vector machine (SVM), and the SVM and CNN are trained by using the database of this paper. At the same time, the effectiveness of the two for image recognition is checked, and then the trained classifier is used for image recognition. It is found that a CNN and SVM-based secondary classification IoT image recognition method improves the accuracy of image recognition. The secondary classification method combines the characteristics of the SVM and CNN image recognition methods, and the accuracy of the image recognition method is verified to provide an effective improvement through experimental verification.

show abstract

Multi-fidelity deep neural networks for adaptive inference in the internet of multimedia things

Cited by 12 publications

References 9 publications

An Artificial Intelligence-Based Collaboration Approach in Industrial IoT Manufacturing: Key Concepts, Architectural Extensions and Potential Applications

An Artificial Intelligence-Based Collaboration Approach in Industrial IoT Manufacturing: Key Concepts, Architectural Extensions and Potential Applications

Partitioning Convolutional Neural Networks to Maximize the Inference Rate on Constrained IoT Devices

Deep Learning Based Image Recognition for 5G Smart IoT Applications

Contact Info

Product

Resources

About