Data-Centric and Model-Centric AI: Twin Drivers of Compact and Robust Industry 4.0 Solutions

Hamid, Oussama H.

doi:10.3390/app13052753

Cited by 15 publications

(23 citation statements)

References 61 publications

(68 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…, and the last one follows Lemma 3 in [17]. Substituting ( 22), ( 23) into (21), we obtain (19), which finishes the proof. Lemma 5.…”

Section: Performance Analysissupporting

confidence: 59%

“…For the partial client participation scheme, i.e., |S t | = m, the main difference is using (19) instead of (18) in Lemma 4 when bound to E m t 2 . Following a similar proof above, we can obtain the result (25).…”

Section: Performance Analysismentioning

confidence: 99%

“…We introduce the derivative information to the update rule of a federated model, which represents the future trend information of the gradient change. With reference to the ongoing debate on model-centric AI and data-centric AI, our work belongs to the category of model-centric AI, highlighting the significance of further developing model-centric approaches [19]. In a nutshell, the contributions are elaborated on as follows.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Derivative-Incorporated Adaptive Gradient Method for Federated Learning

Gao

Cao³

et al. 2023

Mathematics

View full text Add to dashboard Cite

As a new machine learning technique, federated learning has received more attention in recent years, which enables decentralized model training across data silos or edge intelligent devices in the Internet of Things without exchanging local raw data. All kinds of algorithms are proposed to solve the challenges in federated learning. However, most of these methods are based on stochastic gradient descent, which undergoes slow convergence and unstable performance during the training stage. In this paper, we propose a differential adaptive federated optimization method, which incorporates an adaptive learning rate and the gradient difference into the iteration rule of the global model. We further adopt the first-order moment estimation to compute the approximate value of the differential term so as to avoid amplifying the random noise from the input data sample. The theoretical convergence guarantee is established for our proposed method in a stochastic non-convex setting under full client participation and partial client participation cases. Experiments for the image classification task are performed on two standard datasets by training a neural network model, and experiment results on different baselines demonstrate the effectiveness of our proposed method.

show abstract

“…, and the last one follows Lemma 3 in [17]. Substituting ( 22), ( 23) into (21), we obtain (19), which finishes the proof. Lemma 5.…”

Section: Performance Analysissupporting

confidence: 59%

Section: Performance Analysismentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Derivative-Incorporated Adaptive Gradient Method for Federated Learning

Gao

Cao³

et al. 2023

Mathematics

View full text Add to dashboard Cite

show abstract

“…Data-centric machine learning comprises a series of tasks, including standardization and normalization, data cleaning, feature extraction, dimensionality reduction, feature transformation, instance selection, undersampling, data synthesis, and oversampling 27 . However, even recognizing the importance of data-centric methods, the challenge is to find an appropriate balance between these and model-centric methods to provide a robust machine learning solution 28 . This paper aims to present a data-centric approach applied to The Cancer Genome Atlas (TCGA) data set and explore the potential benefits of oversampling and undersampling algorithms to address class imbalance, thus comparing their performance with that of six machine learning models (k nearest neighbors, support vector machine, multi-layer perceptron, logistic regression, random forest, and CatBoost).…”

Section: Introductionmentioning

confidence: 99%

A data-centric machine learning approach to improve prediction of glioma grades using low-imbalance TCGA data

Sánchez-Marqués,

García,

Sánchez

2024

Preprint

View full text Add to dashboard Cite

Accurate prediction and grading of gliomas play a crucial role in evaluating brain tumor progression, assessing overall prognosis, and treatment planning. In addition to neuroimaging techniques, identifying molecular biomarkers that can guide the diagnosis, prognosis and prediction of the response to therapy has aroused the interest of researchers in their use together with machine learning and deep learning models. Most of the research in this field has been model-centric, meaning it has been based on finding better performing algorithms. However, in practice, improving data quality can result in a better model. This study investigates a data-centric machine learning approach to determine their potential benefits in predicting glioma grades. We report six performance metrics to provide a complete picture of model performance. Experimental results indicate that standardization and oversizing the minority class increase the prediction performance of four popular machine learning models and two classifier ensembles applied on a low-imbalanced data set consisting of clinical factors and molecular biomarkers. The experiments also show that the two classifier ensembles significantly outperform three of the four standard prediction models. Furthermore, we conduct a comprehensive descriptive analysis of the glioma data set to identify relevant statistical characteristics and discover the most informative attributes using four feature ranking algorithms.

show abstract

“…In recent years, whether artificial intelligence technology is model-centric or data-centric has become a widely discussed topic. Hamid et al [13,14] compared the characteristics of model-centered artificial intelligence and data-centered artificial intelligence, analyzed the limitations of model-centered artificial intelligence, proposed the advantages of datacentered artificial intelligence, and emphasized that we should combine the two, rather than just focusing on one. Only by jointly developing the two can we make the current artificial intelligence more robust and powerful.…”

Section: Introductionmentioning

confidence: 99%

Critical Information Mining Network: Identifying Crop Diseases in Noisy Environments

Shao,

Yang,

et al. 2024

Symmetry

View full text Add to dashboard Cite

When agricultural experts explore the use of artificial intelligence technology to identify and detect crop diseases, they mainly focus on the research of a stable environment, but ignore the problem of noise in the process of image acquisition in real situations. To solve this problem, we propose an innovative solution called the Critical Information Mining Network (CIMNet). Compared with traditional models, CIMNet has higher recognition accuracy and wider application scenarios. The network has a good effect on crop disease recognition under noisy environments, and can effectively deal with the interference of noise to the recognition effect in actual farmland scenes. Consider that the shape of the leaves can be symmetrical or asymmetrical.First, we introduce the Non-Local Attention Module (Non-Local), which uses a unique self-attention mechanism to fully capture the context information of the image. The module overcomes the limitation of traditional convolutional neural networks that only rely on local features and ignore global features. Global features are particularly important when the image is disturbed by noise. Non-Local improves a more comprehensive visual understanding of crop disease recognition. Secondly, we have innovatively designed a Multi-scale Critical Information Fusion Module (MSCM). The module uses the Key Information Extraction Module (KIB) to dig into the shallow key features in the network deeply. The shallow key features strengthen the feature perception of the model to the noise image through texture and contour information, and then the shallow key features and deep features are fused to enrich the original deep feature information of the network. Finally, we conducted experiments on two public datasets, and the results showed that the accuracy of our model in crop disease identification under a noisy environment was significantly improved. At the same time, our model also showed excellent performance under stable conditions. The results of this study provide favorable support for the improvement of crop production efficiency.

show abstract

Data-Centric and Model-Centric AI: Twin Drivers of Compact and Robust Industry 4.0 Solutions

Cited by 15 publications

References 61 publications

A Derivative-Incorporated Adaptive Gradient Method for Federated Learning

A Derivative-Incorporated Adaptive Gradient Method for Federated Learning

A data-centric machine learning approach to improve prediction of glioma grades using low-imbalance TCGA data

Critical Information Mining Network: Identifying Crop Diseases in Noisy Environments

Contact Info

Product

Resources

About