Research on an olfactory neural system model and its applications based on deep learning

2019 ◽  
Vol 32 (10) ◽  
pp. 5713-5724
Author(s):  
Jin Zhang ◽  
Tiantian Tian ◽  
Shengchun Wang ◽  
Xiaofei Liu ◽  
Xuanyu Shu ◽  
...  
Keyword(s):  
Deep Learning ◽  
Neural System ◽  
System Model

Implementation of Deep Learning Neural Network for Retinal Images

2020 ◽  
pp. 77-95
Author(s):  
R. Murugan
Keyword(s):  
Deep Learning ◽  
Semantic Segmentation ◽  
Neural System ◽  
Neural Systems ◽  
Retinal Images ◽  
Manual Segmentation ◽  
Convolutional Network ◽  
The World ◽  
Deep Learning Neural Network ◽  
Wide Assortment

The retinal parts segmentation has been recognized as a key component in both ophthalmological and cardiovascular sickness analysis. The parts of retinal pictures, vessels, optic disc, and macula segmentations, will add to the indicative outcome. In any case, the manual segmentation of retinal parts is tedious and dreary work, and it additionally requires proficient aptitudes. This chapter proposes a supervised method to segment blood vessel utilizing deep learning methods. All the more explicitly, the proposed part has connected the completely convolutional network, which is normally used to perform semantic segmentation undertaking with exchange learning. The convolutional neural system has turned out to be an amazing asset for a few computer vision assignments. As of late, restorative picture investigation bunches over the world are rapidly entering this field and applying convolutional neural systems and other deep learning philosophies to a wide assortment of uses, and uncommon outcomes are rising constantly.

scholarly journals Modelling Drosophila motion vision pathways for decoding the direction of translating objects against cluttered moving backgrounds

2020 ◽  
Vol 114 (4-5) ◽  
pp. 443-460
Author(s):  
Qinbing Fu ◽  
Shigang Yue
Keyword(s):  
Motion Perception ◽  
Computational Modelling ◽  
Fruit Fly ◽  
Neural System ◽  
Direction Selectivity ◽  
System Model ◽  
Wide Field ◽  
Motion Vision ◽  
Preferred Direction ◽  
On And Off Pathways

Abstract Decoding the direction of translating objects in front of cluttered moving backgrounds, accurately and efficiently, is still a challenging problem. In nature, lightweight and low-powered flying insects apply motion vision to detect a moving target in highly variable environments during flight, which are excellent paradigms to learn motion perception strategies. This paper investigates the fruit fly Drosophila motion vision pathways and presents computational modelling based on cutting-edge physiological researches. The proposed visual system model features bio-plausible ON and OFF pathways, wide-field horizontal-sensitive (HS) and vertical-sensitive (VS) systems. The main contributions of this research are on two aspects: (1) the proposed model articulates the forming of both direction-selective and direction-opponent responses, revealed as principal features of motion perception neural circuits, in a feed-forward manner; (2) it also shows robust direction selectivity to translating objects in front of cluttered moving backgrounds, via the modelling of spatiotemporal dynamics including combination of motion pre-filtering mechanisms and ensembles of local correlators inside both the ON and OFF pathways, which works effectively to suppress irrelevant background motion or distractors, and to improve the dynamic response. Accordingly, the direction of translating objects is decoded as global responses of both the HS and VS systems with positive or negative output indicating preferred-direction or null-direction translation. The experiments have verified the effectiveness of the proposed neural system model, and demonstrated its responsive preference to faster-moving, higher-contrast and larger-size targets embedded in cluttered moving backgrounds.

scholarly journals Measuring optimality of a neural system by a logic gate model

2021 ◽  
Author(s):  
Robert Friedman
Keyword(s):  
Caenorhabditis Elegans ◽  
Information Transmission ◽  
Muscle Fiber ◽  
Neural Circuit ◽  
Logic Gate ◽  
Neural System ◽  
System Model ◽  
Nematode Worm ◽  
Worm Caenorhabditis Elegans ◽  
Gate Design

The nematode worm, Caenorhabditis elegans, is a relatively simple neural system model for measuring the efficiency of information transmission from sensory organ to muscle fiber. With the potential to measure this efficiency, a method is proposed to compare the organization of an idealized neural circuit with a logic gate design. This approach is useful for analysis of a neural circuit that is not tractable to a strictly biological model, and where the assumptions of a logic gate design have applicability. Also, included in the results is an abstract perspective of the electrical-specific synaptic network in the somatic system of the nematode worm.

scholarly journals Technical Access in Blood Glucose Detection using ANN

2019 ◽  
Vol 8 (9S2) ◽  
pp. 332-335
Keyword(s):  
Blood Glucose ◽  
Human Services ◽  
Neural System ◽  
System Model ◽  
Correlation Technique ◽  
Glucose Detection

Early re-affirmation of patients builds the expense of human services and it exceptionally impacts the notoriety of the clinic. Discovering readmission in essential stage, enables the clinics to give extraordinary consideration for those patients, and after that can lessen the rate of readmission. In this work build up another model utilizing profound learning. It is the correlation technique between AI and profound learning. Typically, Logistic relapse is utilized for all sort of expectation. Be that as it may, as per this information fake neural system model in profound learning give promising outcome than strategic relapse

Detecting lubricating oil components through a new clustering method based on sample data

2018 ◽  
Vol 70 (3) ◽  
pp. 552-559 ◽  
Author(s):  
Guijun Wang ◽  
Guoying Zhang
Keyword(s):  
Neural System ◽  
Mineral Elements ◽  
System Model ◽  
Lubricating Oil ◽  
Clustering Method ◽  
Content Type ◽  
Sample Data ◽  
Fuzzy Neural ◽  
Data Pair ◽  
Component Content

Purpose This paper aims to overcome the defect that the traditional clustering method is excessively dependent on initial clustering radius and also provide new technical measures for detecting the component content of lubricating oil based on the fuzzy neural system model. Design/methodology/approach According to the layers model of the fuzzy neural system model for the given sample data pair, the new clustering method can be implemented, and through the fuzzy system model, the detection method for the selected oil samples is given. By applying this method, the composition contents of 30 kinds of oil samples in lubricating oil are checked, and the actual composition contents of oil samples are compared. Findings Through the detection of 21 mineral elements in 30 oil samples, it can be known that the four mineral elements such as Zn, P, Ca and Mg have largest contribution rate to the lubricating oil, and they can be regarded as the main factors for classification of lubricating oil. The results show that the fuzzy system to be established based on sample data clustering has better performance in detection lubricant component content. Originality/value In spite of lots of methods for detecting the component of lubricating oil at the present, there is still no detection of the component of lubricating oil through clustering method based on sample data pair. The new nearest clustering method is proposed in this paper, and it can be more effectively used to detect the content of lubricating oil.

Sign in / Sign up

Export Citation Format

Share Document