Deep Convolutional Gaussian Processes

Blomqvist, Kenneth; Kaski, Samuel; Heinonen, Markus

doi:10.1007/978-3-030-46147-8_35

Cited by 30 publications

(25 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Gaussian Processes (GPs) with Radial Basis Function Kernels (RBF) [52] and other forms of comparative strategy create consistency overall and allow for a limitless quantity of basic functions, but these are rarely used, even though some past research has demonstrated that it can show promise [53].…”

Section: Forecastingmentioning

confidence: 99%

A Comparison of Feature Selection and Forecasting Machine Learning Algorithms for Predicting Glycaemia in Type 1 Diabetes Mellitus

et al. 2021

View full text Add to dashboard Cite

Type 1 diabetes mellitus (DM1) is a metabolic disease derived from falls in pancreatic insulin production resulting in chronic hyperglycemia. DM1 subjects usually have to undertake a number of assessments of blood glucose levels every day, employing capillary glucometers for the monitoring of blood glucose dynamics. In recent years, advances in technology have allowed for the creation of revolutionary biosensors and continuous glucose monitoring (CGM) techniques. This has enabled the monitoring of a subject’s blood glucose level in real time. On the other hand, few attempts have been made to apply machine learning techniques to predicting glycaemia levels, but dealing with a database containing such a high level of variables is problematic. In this sense, to the best of the authors’ knowledge, the issues of proper feature selection (FS)—the stage before applying predictive algorithms—have not been subject to in-depth discussion and comparison in past research when it comes to forecasting glycaemia. Therefore, in order to assess how a proper FS stage could improve the accuracy of the glycaemia forecasted, this work has developed six FS techniques alongside four predictive algorithms, applying them to a full dataset of biomedical features related to glycaemia. These were harvested through a wide-ranging passive monitoring process involving 25 patients with DM1 in practical real-life scenarios. From the obtained results, we affirm that Random Forest (RF) as both predictive algorithm and FS strategy offers the best average performance (Root Median Square Error, RMSE = 18.54 mg/dL) throughout the 12 considered predictive horizons (up to 60 min in steps of 5 min), showing Support Vector Machines (SVM) to have the best accuracy as a forecasting algorithm when considering, in turn, the average of the six FS techniques applied (RMSE = 20.58 mg/dL).

show abstract

Section: Forecastingmentioning

confidence: 99%

A Comparison of Feature Selection and Forecasting Machine Learning Algorithms for Predicting Glycaemia in Type 1 Diabetes Mellitus

et al. 2021

View full text Add to dashboard Cite

show abstract

“…We focus on data-driven beamforming based mmWave fingerprinting for outdoor localization. Motivated by our prior work on CSI image-based localization [11,17], we also create mmWave beamforming images as fingerprints, which can be effectively handled by the DCGP model [16] to estimate location. DCGP integrates the convolutional structure and Gaussian process in a Bayesian framework, which can effectively extract hierarchical features from 2-D beamforming images to improve the robustness of localization performance.…”

Section: Constructing Beamforming Imagesmentioning

confidence: 99%

“…In addition, we construct the layers by using convolutions of patch response functions g l c : R h l−1 ×w l−1 ×C l−1 → R over the input one patch at a time, which can build the next layer representation. The C patch responses at each of the first L − 1 layers are considered as independent GPs with shared prior [16], where each patch response is defined by…”

Section: Training Deep Convolutional Gaussian Processmentioning

confidence: 99%

“…Although the existing deep learning based approaches (e.g., CNN) can achieve acceptable outdoor localization accuracy for mmWave networks in some cases, there is no guarantee on their robustness, because of the black-box approach of the deep learning models. In this paper, we propose a deep convolutional Gaussian process (DCGP) based regression approach for mmWave outdoor localization, which is different from the original DCGP method [16] that is focused on image classification problems. In addition, compared with CNN, DCGP is a fully Bayesian kernel method with no neural network component, which can provide uncertainty estimation on location predictions [16].…”

Section: Introductionmentioning

confidence: 99%

“…In this paper, we propose a deep convolutional Gaussian process (DCGP) based regression approach for mmWave outdoor localization, which is different from the original DCGP method [16] that is focused on image classification problems. In addition, compared with CNN, DCGP is a fully Bayesian kernel method with no neural network component, which can provide uncertainty estimation on location predictions [16]. Also, DCGP leverages the convolutional structure for deep Gaussian process, which can detect hierarchical combinations of local features in the mmWave dataset, especially in NLOS environments.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Deep Convolutional Gaussian Processes for Mmwave Outdoor Localization

Wang

Patil

Yang

et al. 2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Millimeter Wave (mmWave) communications, as a core technique of 5G, can be leveraged for outdoor localization because of its large bandwidth and massive antenna array. Fingerprinting based mmWave outdoor localization methods using deep learning are highly suitable for non-line-of-sight (NLOS) environments. In this paper, we propose a deep convolutional Gaussian process (DCGP) based regression approach to achieve high robustness for fingerprinting-based mmWave outdoor localization, which exploits the convolutional structure for deep Gaussian process to allow uncertainty estimation on location predictions. Specially, we present a system architecture of mmWave based outdoor localization, including beamforming image construction and DCGP training, where DCGP model can effectively learn the location features from mmWave beamforming images. Our experimental results show that the proposed DCGP method can achieve higher outdoor localization accuracy than a CNNbased baseline method.

show abstract

Classification of cassava leaf diseases using deep Gaussian transfer learning model

Ahishakiye

Mwangi

Murithi

et al. 2023

Engineering Reports

View full text Add to dashboard Cite

In Sub‐Saharan Africa, experts visually examine the plants and look for disease symptoms on the leaves to diagnose cassava diseases, a subjective method. Machine learning algorithms have been employed to quickly identify and classify crop diseases. In this study, we propose a model that integrates a transfer learning approach with a deep Gaussian convolutional neural network model. In this study, two pre‐trained transfer learning models were used, that is, MobileNet V2 and VGG16, together with three different kernels: a hybrid kernel (a product of a squared exponential kernel and a rational quadratic kernel), a squared exponential kernel, and a rational quadratic kernel. In experiments using MobileNet V2 and the three kernels, the hybrid kernel performed better, with an accuracy of 90.11%, compared to 86.03% and 85.14% for the squared exponential kernel and a rational quadratic kernel, respectively. Additionally, experiments using VGG16 and the three kernels showed that the hybrid kernel performed better, with an accuracy of 88.63%, compared to the squared exponential kernel's accuracy of 84.62% and the rational quadratic kernel's accuracy of 83.95%, respectively. All the experiments were done using a traditional computer with no access to GPU and this was the major limitation of the study.

show abstract

Deep Convolutional Gaussian Processes

Cited by 30 publications

References 13 publications

A Comparison of Feature Selection and Forecasting Machine Learning Algorithms for Predicting Glycaemia in Type 1 Diabetes Mellitus

A Comparison of Feature Selection and Forecasting Machine Learning Algorithms for Predicting Glycaemia in Type 1 Diabetes Mellitus

Deep Convolutional Gaussian Processes for Mmwave Outdoor Localization

Classification of cassava leaf diseases using deep Gaussian transfer learning model

Contact Info

Product

Resources

About