Stochastic neural network based data analysis‐related talent recruitment optimization via CDN server

Edge computing is a fast-growing and much needed technology in healthcare. The problem of implementing artificial intelligence on edge devices is the complexity and high resource intensity of the most known neural network data analysis methods and algorithms. The difficulty of implementing these methods on low-power microcontrollers with small memory size calls for the development of new effective algorithms for neural networks. This study presents a new method for analyzing medical data based on the LogNNet neural network, which uses chaotic mappings to transform input information. The method effectively solves classification problems and calculates risk factors for the presence of a disease in a patient according to a set of medical health indicators. The efficiency of LogNNet in assessing perinatal risk is illustrated on cardiotocogram data obtained from the UC Irvine machine learning repository. The classification accuracy reaches ~91% with the~3–10 kB of RAM used on the Arduino microcontroller. Using the LogNNet network trained on a publicly available database of the Israeli Ministry of Health, a service concept for COVID-19 express testing is provided. A classification accuracy of ~95% is achieved, and~0.6 kB of RAM is used. In all examples, the model is tested using standard classification quality metrics: precision, recall, and F1-measure. The LogNNet architecture allows the implementation of artificial intelligence on medical peripherals of the Internet of Things with low RAM resources and can be used in clinical decision support systems.

Download Full-text

Determination of Rock Type Using Hydraulic Flow Unit Concept to Predict Permeability with Artificial Neural Network

Journal of Earth Energy Science, Engineering, and Technology ◽

10.25105/jeeset.v1i2.3942 ◽

2018 ◽

Vol 1 (2) ◽

Author(s):

Ghanima Yasmaniar ◽

Ratnayu Sitaresmi ◽

Suryo Prakoso

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Data Analysis ◽

Rock Type ◽

Flow Unit ◽

West Java ◽

North West ◽

Hydraulic Flow ◽

Core Data ◽

The North

<em>Permeability is one of the important of reservoir characteristics, but is difficult to predict it. The accurate permeability values can be obtained from core data analysis, but it is not possible to do at all of the well intervals in the field. This study used 191 sandstone core samples from the Upper Cibulakan Formation in the North West Java Basin. The concept of HFU (Hydraulic Flow Unit) developed by Kozeny-Carman is used to generate the relationship between porosity and permeability for each rock type. Afterward, to estimate the permeability value at uncored intervals, the statistical methods of artificial neural network based on log data are used on G-19 Well, G Field which is located in the North West Java Basin. Based on core data analysis from this research, the reservoir consists of eight HFU with different equations to estimate permeability for each HFU. From this reserarch, the results of permeability calculations at uncored intervals are not much different from the core data at the same depth. Therefore the approach of permeability prediction can be used to determine the value of permeability without performing core data analysis so that it can save the company expenses.</em>

Download Full-text

Detection of the homotopy type of an object using differential invariants of an approximating map

Computer Optics ◽

10.18287/2412-6179-2019-43-4-611-617 ◽

2019 ◽

Vol 43 (4) ◽

pp. 611-617

Author(s):

S.V. Kurochkin

Keyword(s):

Neural Network ◽

Data Analysis ◽

Homotopy Type ◽

Morse Theory ◽

Object Representation ◽

Differential Invariants ◽

Topological Data Analysis ◽

Higher Dimension ◽

Differential Topology ◽

Open Questions

A method of topological data analysis is proposed that allows one to find out the homotopy type of the object under study. Unlike mature and widely used methods based on persistent homologies, our method is based on computing differential invariants of some map associated with an approximating map. Differential topology tools and the analogy with the main result in Morse theory are used. The approximating map can be constructed in the usual way using a neural network or otherwise. The method allows one to identify the homotopy type of an object in the plane because the number of circles in the homotopy equivalent object representation as a wedge is expressed through the degree of some map associated with the approximating map. The performance of the algorithm is illustrated by examples from the MNIST database and transforms thereof. Generalizations and open questions relating to a higher-dimension case are discussed.

Download Full-text