A novel deep learning neural network for fast-food image classification and prediction using modified loss function

Abstract: In this paper, I built an AI model using deep learning, which identifies whether a given image is of an Arduino, a Beaglebone Black or a Jetson Nano. The identification of the object is based on prediction. The model is trained using 300 to 350 datasets of each category and is tested multiple times using different images at different angles, background colour and size. After multiple testing, the model is found to have 95 percent accuracy. Model used is Sequential and uses Convolution Neural Network (CNN) as its architecture. The activation function of each layer is RELU and for the output layer is Softmax. The output is a prediction and hence it is of probability type. This is a type of an application based project. The entire scripting is done using Python 3 programming language. Keywords: image classification, microcontroller boards, python, AI, deep learning, neural network

Download Full-text

Deep Learning-Based X-Ray Baggage Hazardous Object Detection – An FPGA Implementation

Revue d intelligence artificielle ◽

10.18280/ria.350510 ◽

2021 ◽

Vol 35 (5) ◽

pp. 431-435

Author(s):

Vijayakumar Ponnusamy ◽

Diwakar R. Marur ◽

Deepa Dhanaskodi ◽

Thangavel Palaniappan

Keyword(s):

Neural Network ◽

Deep Learning ◽

Image Classification ◽

Real Time ◽

Activation Function ◽

Data Representation ◽

Fpga Implementation ◽

X Ray ◽

Computationally Intensive ◽

Deep Learning Neural Network

This work proposes deep learning neural network-based X-ray image classification. The X-ray baggage scanning machinery plays an essential role in the safeguard of customs, airports, and other systematically very important landmarks and infrastructures. The technology at present of baggage scanning machines is designed on X-ray attenuation. The detection of threatful objects is built on how different objects attenuate the X-ray beams going through them. In this paper, the deep convolutional neural network of YOLO is utilized in classifying baggage images. Real-time performance of the baggage image classification is an essential one for security scanning. There are many computationally intensive operations in the You Only Look Once (YOLO) architecture. The computational intensive operations are implemented in the Field Programmable Gate Array (FPGA) platform to optimize process delays. The critical issues involved in those implementations include data representation, inner products computation and implementation of activation function and resolving these issues will also be a significant task. The FPGA implementation results show that with less resource occupancy, the YOLO implementation provides maximum accuracy of 98.9% in classifying X-ray baggage images and identifying hazardous materials. This result proves that the proposed implementation is best suited for practical system deployments for real-time Baggage scanning.

Download Full-text

COMPARISON OF THE PRECISION OF OPTICAL DIFFERENTATION BETWEEN NEOPLASTIC AND NON-NEOPLASTIC SUBCENTRIMETRIC POLYP HISTOLOGY BY ENDOSCOPIC EXPERTS AND ARTEFICIAL INTELLIGENCE DEEP LEARNING NEURAL NETWORK (POLYPBRAIN)

10.1055/s-0040-1704154 ◽

2020 ◽

Author(s):

L Madácsy ◽

M Szalai ◽

Á Finta ◽

K Zsobrák ◽

L Oczella ◽

...

Keyword(s):

Neural Network ◽

Deep Learning ◽

Deep Learning Neural Network

Download Full-text

Augmented Reality Maintenance Assistant Using YOLOv5

Applied Sciences ◽

10.3390/app11114758 ◽

2021 ◽

Vol 11 (11) ◽

pp. 4758

Author(s):

Ana Malta ◽

Mateus Mendes ◽

Torres Farinha

Keyword(s):

Neural Network ◽

Deep Learning ◽

Object Recognition ◽

Augmented Reality ◽

Real Time ◽

Recognition System ◽

High Accuracy ◽

Video Streams ◽

The Neural Network ◽

Deep Learning Neural Network

Maintenance professionals and other technical staff regularly need to learn to identify new parts in car engines and other equipment. The present work proposes a model of a task assistant based on a deep learning neural network. A YOLOv5 network is used for recognizing some of the constituent parts of an automobile. A dataset of car engine images was created and eight car parts were marked in the images. Then, the neural network was trained to detect each part. The results show that YOLOv5s is able to successfully detect the parts in real time video streams, with high accuracy, thus being useful as an aid to train professionals learning to deal with new equipment using augmented reality. The architecture of an object recognition system using augmented reality glasses is also designed.

Download Full-text