Artificial Intelligence – State of Art Convolution Neural Network Architectures in a Nutshell

It is a well-known fact that all the Artificial Intelligence (AI)researches happening across multiple verticals such as Neuro Imaging, Computer Vision, Deep learning etc point to one master goal of modelling the human brain function by understanding how each part of the brain works. The Convolution neural network (CNN) is one of best deep architecture suitable to handle variety of inputs. In this paper we explore the different types of input data the CNN deep architecture can process and some of the CNN configuration changes that has proved good Accuracy. We have highlighted those specialized CNN architectures along with different types of data inputs they handle including the Functional Magnetic Resonance (fMRI) Neuro Image brain data input.

Download Full-text

Methods for Preventing Visual Attacks in Convolutional Neural Networks Based on Data Discard and Dimensionality Reduction

Applied Sciences ◽

10.3390/app11115235 ◽

2021 ◽

Vol 11 (11) ◽

pp. 5235

Author(s):

Nikita Andriyanov

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Network Inference ◽

Recognition Accuracy ◽

Network Architectures ◽

Reduced Dimensions ◽

Different Types ◽

Rectangular Area ◽

Noise Impulse ◽

Selection Of

The article is devoted to the study of convolutional neural network inference in the task of image processing under the influence of visual attacks. Attacks of four different types were considered: simple, involving the addition of white Gaussian noise, impulse action on one pixel of an image, and attacks that change brightness values within a rectangular area. MNIST and Kaggle dogs vs. cats datasets were chosen. Recognition characteristics were obtained for the accuracy, depending on the number of images subjected to attacks and the types of attacks used in the training. The study was based on well-known convolutional neural network architectures used in pattern recognition tasks, such as VGG-16 and Inception_v3. The dependencies of the recognition accuracy on the parameters of visual attacks were obtained. Original methods were proposed to prevent visual attacks. Such methods are based on the selection of “incomprehensible” classes for the recognizer, and their subsequent correction based on neural network inference with reduced image sizes. As a result of applying these methods, gains in the accuracy metric by a factor of 1.3 were obtained after iteration by discarding incomprehensible images, and reducing the amount of uncertainty by 4–5% after iteration by applying the integration of the results of image analyses in reduced dimensions.

Download Full-text

IMUMETER—A Convolution Neural Network-Based Sensor for Measurement of Aircraft Ground Performance

Sensors ◽

10.3390/s21144726 ◽

2021 ◽

Vol 21 (14) ◽

pp. 4726

Author(s):

Jarosław Pytka ◽

Piotr Budzyński ◽

Paweł Tomiło ◽

Joanna Michałowska ◽

Ernest Gnapowski ◽

...

Keyword(s):

Neural Network ◽

Artificial Intelligence ◽

Convolution Neural Network ◽

Flight Tests ◽

Motion Measurement ◽

Aircraft Flight ◽

Acceleration Data ◽

Measurement Results ◽

Measurement And Analysis ◽

Ground Distance

The paper presents the development of the IMUMETER sensor, designed to study the dynamics of aircraft movement, in particular, to measure the ground performance of the aircraft. A motivation of this study was to develop a sensor capable of airplane motion measurement, especially for airfield performance, takeoff and landing. The IMUMETER sensor was designed on the basis of the method of artificial neural networks. The use of a neural network is justified by the fact that the automation of the measurement of the airplane’s ground distance during landing based on acceleration data is possible thanks to the recognition of the touchdown and stopping points, using artificial intelligence. The hardware is based on a single-board computer that works with the inertial navigation platform and a satellite navigation sensor. In the development of the IMUMETER device, original software solutions were developed and tested. The paper describes the development of the Convolution Neural Network, including the learning process based on the measurement results during flight tests of the PZL 104 Wilga 35A aircraft. The ground distance of the test airplane during landing on a grass runway was calculated using the developed neural network model. Additionally included are exemplary measurements of the landing distance of the test airplane during landing on a grass runway. The results obtained in this study can be useful in the development of artificial intelligence-based sensors, especially those for the measurement and analysis of aircraft flight dynamics.

Download Full-text

Recent Advances in Medical Image Processing

Acta Cytologica ◽

10.1159/000510992 ◽

2020 ◽

pp. 1-14

Author(s):

Zhen Huang ◽

Qiang Li ◽

Ju Lu ◽

Junlin Feng ◽

Jiajia Hu ◽

...

Keyword(s):

Neural Network ◽

Artificial Intelligence ◽

Machine Learning ◽

Image Processing ◽

Medical Imaging ◽

Medical Image ◽

Medical Image Processing ◽

Convolution Neural Network ◽

Artificial Intelligence Technology ◽

Deep Convolution Neural Network

Background: Application and development of the artificial intelligence technology have generated a profound impact in the field of medical imaging. It helps medical personnel to make an early and more accurate diagnosis. Recently, the deep convolution neural network is emerging as a principal machine learning method in computer vision and has received significant attention in medical imaging. Key Message: In this paper, we will review recent advances in artificial intelligence, machine learning, and deep convolution neural network, focusing on their applications in medical image processing. To illustrate with a concrete example, we discuss in detail the architecture of a convolution neural network through visualization to help understand its internal working mechanism. Summary: This review discusses several open questions, current trends, and critical challenges faced by medical image processing and artificial intelligence technology.

Download Full-text

IoT programming to Develop Self Driving Robotics Car using OpenCV and Other Emerging Technologies

10.36227/techrxiv.12055956.v1 ◽

2020 ◽

Author(s):

Mohammed Maaz ◽

Sabah Mohammed

Keyword(s):

Neural Network ◽

Artificial Intelligence ◽

Deep Learning ◽

The Self ◽

Reverse Direction ◽

Raspberry Pi ◽

Specific Direction ◽

Different Types ◽

Practical Model ◽

Individual Effort

The advancement of Artificial Intelligence & Deep Learning has catalyzed the field of technology. The progression in these fields is exponentially increasing, and the discoveries which were once just an imagination are now changed into reality. The evolution of cars each year has made a lot of difference in people travelling from one place to another. One such reform involving Artificial Intelligence & Deep Learning is the birth of a self-driving car. The future is here where one can reach their destination hassle-free safely without the fear of accidents. This paper introduces a practical model of the self-driving robotics car, which can travel from one position to another on different types of tracks. A Pi-camera module is attached with the help of Raspberry Pi, which sends series of image frames to the Convolutional neural network, which then foretells the car to move in a specific direction, i.e. right, left, forward and reverse direction. The outcome is the robotics car, which travels in the desired direction without any individual effort.

Download Full-text

Robust and Blind Multiple Image Watermarking Using CNN and DWT in Video

SMART MOVES JOURNAL IJOSCIENCE ◽

10.24113/ijoscience.v6i3.275 ◽

2020 ◽

Vol 6 (3) ◽

pp. 8-13

Author(s):

Farha Khan ◽

M. Sarwar Raeen

Keyword(s):

Neural Network ◽

Wavelet Coefficient ◽

Image Watermarking ◽

High Capacity ◽

Multimedia Systems ◽

Convolution Neural Network ◽

Discrete Wavelet ◽

Host Image ◽

Different Types ◽

Result Analysis

Digital watermarking was introduced as a result of rapid advancement of networked multimedia systems. It had been developed to enforce copyright technologies for cover of copyright possession. Due to increase in growth of internet users of networks are increasing rapidly. It has been concluded that to minimize distortions and to increase capacity, techniques in frequency domain must be combined with another technique which has high capacity and strong robustness against different types of attacks. In this paper, a robust multiple watermarking which combine Discrete Cosine Transform (DCT), Discrete Wavelet Transform (DWT)and Convolution Neural Network techniques on selected middle band of the video frames is used. This methodology is considered to be robust blind watermarking because it successfully fulfills the requirement of imperceptibility and provides high robustness against a number of image-processing attacks such as Mean filtering, Median filtering, Gaussian noise, salt and pepper noise, poison noise and rotation attack. The proposed method embeds watermark by decomposing the host image. Convolution neural network calculates the weight factor for each wavelet coefficient. The watermark bits are added to the selected coefficients without any perceptual degradation for host image. The simulation is performed on MATLAB platform. The result analysis is evaluated on PSNR and MSE which is used to define robustness of the watermark that means that the watermark will not be destroyed after intentional or involuntary attacks and can still be used for certification. The analysis of the results was made with different types of attacks concluded that the proposed technique is approximately 14% efficient as compared to existing work.

Download Full-text

It may be time to perfect the neuron of artificial neural network

10.36227/techrxiv.12477266.v2 ◽

2020 ◽

Author(s):

Gang Liu

Keyword(s):

Neural Network ◽

Artificial Intelligence ◽

Input Data ◽

Basic Unit ◽

Future Research ◽

Brain Neuron ◽

Artificial Neuron ◽

The Neural Network ◽

Artificial Neural ◽

The Brain

In recent years, artificial neural networks (ANNs) have won numerous contests in pattern recognition, machine learning, and artificial intelligence. The basic unit of an ANN is to mimic neurons in the brain. Neuron in ANNs is expressed as f(wx+b) or f(wx).This structure does not consider the information processing capabilities of dendrites. However, recently, studies shown that dendrites participate in pre-calculation in the brain. Concretely, biological dendrites play a role in the pre-processing to the interaction information of input data. Therefore, it's time to perfect the neuron of the neural network. This paper, add dendrite processing section, presents a novel artificial neuron, according to our previous studies (CR-PNN or Gang transform). The dendrite processing section can be expressed as WA.X. Because I perfected the basic unit of ANNs-neuron, there are so many networks to try, this article gives the basic architecture for reference in future research.

Download Full-text

Hey, look over there: Distraction effects on rapid sequence recall

10.1101/787861 ◽

2019 ◽

Author(s):

Daniel Miner ◽

Christian Tetzlaff

Keyword(s):

Neural Network ◽

Computational Model ◽

Everyday Life ◽

Recurrent Neural Network ◽

Distinct Effect ◽

Rapid Sequence ◽

Basic Understanding ◽

Different Types ◽

The Brain ◽

Huge Variety

AbstractIn the course of everyday life, the brain must store and recall a huge variety of representations of stimuli which are presented in an ordered or sequential way. The processes by which the ordering of these various things is stored and recalled are moderately well understood. We use here a computational model of a cortex-like recurrent neural network adapted by a multitude of plasticity mechanisms. We first demonstrate the learning of a sequence. Then, we examine the influence of different types of distractors on the network dynamics during the recall of the encoded ordered information being ordered in a sequence. We are able to broadly arrive at two distinct effect-categories for distractors, arrive at a basic understanding of why this is so, and predict what distractors will fall into each category.

Download Full-text

Brain Tumor Detection using Enhanced Convolution Neural Network for MR Images

International Journal of Recent Technology and Engineering - 2 ◽

10.35940/ijrte.b6051.0710221 ◽

2021 ◽

Vol 10 (2) ◽

pp. 10-13

Author(s):

M.B. Bramarambika ◽

◽

M Sesha Shayee ◽

Keyword(s):

Neural Network ◽

Brain Tumor ◽

Brain Tumors ◽

Detection System ◽

Human Life ◽

Classification Problem ◽

Tumor Detection ◽

Convolution Neural Network ◽

Brain Images ◽

The Brain

Brain tumor is a mass that grows unevenly in the brain and directly affects human life. The mass occurs spontaneously because of the tissues surrounding the brain or the skull. There are two types of Brain tumor such as Benign and Malignant. Malignant brain tumors contain cancer cells and grow quickly and spread through to other brain and spine regions as well. Accurate and prompt diagnosis of brain tumors is essential for implementing an effective treatment of this disease. Brain images produced by the Magnetic Resonance Imaging (MRI) technique are a rich source of data for brain tumor diagnosis and treatment in the medical field. Due to the existence of a large number of features compared to the other imaging types. The performance of existing methods is inadequate considering the medical significance of the classification problem. Earlier methods relied on manually delineated tumor regions, prior to classification. This prevented them from being fully automated. The automatic algorithms developed using CNN and its variants could not achieve an influential improvement in performance. In order to overcome such an issue, the proposed one is automatic brain tumor detection system, which is “ Enhanced Convolution Neural Network (CNN) Algorithm for MRI Images” for the detection of brain tumor is useful to detect and classify the Glioma part into low Glioma and high Glioma.

Download Full-text

Self-repairing mechanical components using artificial Intelligence

Scientific Bulletin of Naval Academy ◽

10.21279/1454-864x-21-i1-002 ◽

2021 ◽

Vol XXIV (1) ◽

pp. 17-28

Author(s):

PLEȘA Mihail Iulian

Keyword(s):

Neural Network ◽

Artificial Intelligence ◽

Cellular Automata ◽

Convolution Neural Network ◽

Mechanical Component ◽

Small Seed ◽

Ca Model ◽

Mechanical Components

In this paper, we study the applicability of artificial intelligence for designing mechanical components that can repair themselves. We use the Cellular Automata (CA) model implemented as a Convolution Neural Network (CNN) to simulate the automatic growth and repair of a mechanical component from a small seed. Concretely, we start with an empty 2D grid of cells. Using the CNN, the cells will learn to self-organize into the image of a mechanical component. We simulate the damage to the component by deleting some parts of the imagine and show how they are automatically regenerated.

Download Full-text