A Study on Spatial Analysis Using R-Based Deep Learning

Park, Se-Jeong; Choi, Kookhyun; Park, Jeawon; Kim, Jong-Bae

doi:10.14257/ijseia.2016.10.5.09

Cited by 2 publications

(2 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The RNN network model is mainly composed of an input layer, multiple hidden layers and an output layer. The hidden layer of the RNN contains a connection with itself, and there are corresponding weight matrices and deviation vectors between adjacent layers [23]. The calculation formulas for the output value t v of the hidden layer node at time t and the predicted value t z of the output layer in the RNN forward propagation algorithm are as follows:…”

Section: Recurrent Neural Network Time Series Image Prediction Based ...mentioning

confidence: 99%

Clinical Study of Deep Learning-Based Giant Needling Combined with Conventional Acupuncture for Treatment of Limb Dysfunction Due to Stroke

2022

IJFM

View full text Add to dashboard Cite

With the development of computer technology and the deepening of machine learning research, the application prospects of artificial intelligence technology in the medical field are becoming more and more broad. Deep learning algorithm is a method tool that realizes machine learning so as to be as close as possible to artificial intelligence. Its application in clinical medicine is the current hot direction of artificial intelligence in the medical field. Therefore, clinical medical research combining deep learning algorithms with traditional therapies is of great significance to the application and development of deep learning in the medical field. This article uses deep learning algorithms to study a clinical treatment plan that combines the giant needling method in traditional medicine with conventional acupuncture therapy for stroke patients with limb dysfunction. This article mainly uses the convolutional neural network in the deep learning algorithm to establish a tracking prediction model. Through the time-series signal of the neural response of stroke patients, acupoint detection and medical image processing, the study of the giant needling method combined with conventional acupuncture therapy on the limb dysfunction of stroke the clinical treatment effect. This article analyzes the limb function and therapeutic effect of the giant needling method combined with conventional acupuncture therapy before and after the clinical treatment of stroke-related limb dysfunction. This paper studies the advantages and disadvantages of deep learning algorithms and other machine learning algorithms in the clinical data processing of stroke-related limb dysfunction through comparative analysis. Studies have shown that during the six months of stroke recovery, which is mainly based on the treatment of limb dysfunction, deep learning has a prediction accuracy of 91.44% for stroke patients limb dysfunction. Data collection, medical imaging and processing for clinical studies on stroke limb dysfunction the prediction accuracy is far superior to other machine learning algorithms.

show abstract

Section: Recurrent Neural Network Time Series Image Prediction Based ...mentioning

confidence: 99%

Clinical Study of Deep Learning-Based Giant Needling Combined with Conventional Acupuncture for Treatment of Limb Dysfunction Due to Stroke

2022

IJFM

View full text Add to dashboard Cite

show abstract

“…Machine learns to predict an inference on data inputs scopes and have been evolved into another learning known as Deep Learning (DL) thus existing models increase its complexity and convolution of the networks dimensions. DL algorithms are more likely appointed to handle huge volumes of datasets and have undoubtedly now penetrated all aspects in our daily lives (Park et al, 2016) ML have been developed in various of fields (Tehrany, Jones, & Shabani, 2019;Topol, 2019) and its importance to geospatial field has grown but now yet mature. The previous researchers have developed algorithms in such as Flood Susceptibility Mapping (Sachdeva, Bhatia, & Verma, 2017), Flood Risk Assessment (Opella & Hernandez, 2019) and even in development of personalised services in Smart Cities (Chin, Callaghan, & Lam, 2017).…”

Section: Motivationmentioning

confidence: 99%

Machine Learning in Big Lidar Data: A Review

Teri

Musliman

2019

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Abstract. Machine Learning used to refer as one Artificial Intelligence subsection that perform self-learning computational algorithms either supervised learning or unsupervised learning tasks. Machine Learning can compute a prediction onto hidden data patterns that hardly for human to detect. This valuable information and predictions able to help companies or researchers make a crucial decision making especially in natural disasters. In Geographic Information Systems (GIS), the advancement of Machine Learning used literally on satellite imagery analyses and fewer on LIDAR point clouds. In this paper presents an overview of Machine Learning definitions, big geospatial data, Machine Learning types and models, and advancement researches using Machine Learning in big LIDAR data.

show abstract

A Study on Spatial Analysis Using R-Based Deep Learning

Cited by 2 publications

References 6 publications

Clinical Study of Deep Learning-Based Giant Needling Combined with Conventional Acupuncture for Treatment of Limb Dysfunction Due to Stroke

Clinical Study of Deep Learning-Based Giant Needling Combined with Conventional Acupuncture for Treatment of Limb Dysfunction Due to Stroke

Machine Learning in Big Lidar Data: A Review

Contact Info

Product

Resources

About