ReID-DeePNet: A Hybrid Deep Learning System for Person Re-Identification

Mohammed, Hussam J.; Al-Fahdawi, Shumoos; Al-Waisy, Alaa S.; Zebari, Dilovan Asaad; Ibrahim, Dheyaa Ahmed; Mohammed, Mazin Abed; Kadry, Seifedine; Kim, Jung-Eun

doi:10.3390/math10193530

Cited by 15 publications

(4 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed work uses ResNets [22] in DCNN. Human age is determined by facial structure [14,29] and it may be different from that detected using our human eye. One may consider a sample age between 31 to 34 year old humans who may be have similar facial structure, which in this situation makes it difficult to distinguish by human being.…”

Section: F1-scorementioning

confidence: 99%

An Intelligent Human Age Prediction from Face Image Framework Based on Deep Learning Algorithms

Sathyavathi¹,

Baskaran²

2023

ITC

View full text Add to dashboard Cite

Age prediction is the task of extracting features from the human face image. Human aging factors can be expressed as multifactorial, gradual, time-dependent, physical, and biological damage. Attributes are extracted from a face image, and the aging factor depends on cells, tissues, and all living organisms. Human age prediction is distinct from chronological age prediction. Each human’s biological identity has unique characteristics. Age prediction depends on the maturity process of organs, other tissues, and cells. Many research works have been done on age classification using various techniques from human face images. It is a difficult task to the analysis of facial appearance. Issues in the existing algorithm are inefficient and require more computation time and storage space. To address these issues, this paper proposed a Deep convolutional neural network (DCNN) with a Cuckoo search algorithm (DCNN-CS). In this proposed work, DCNN-CS produces an effective age prediction from the human face image within a minimum execution time, handling a large dataset. The accuracy rate of the convolutional neural network (CNN) got 81.32, the Deep Neural Network (DNN) got 82.34, the Long short-term memory (LSTM) got 88.12, and the proposed work SLSTM-DNN got 91.45.

show abstract

Section: F1-scorementioning

confidence: 99%

An Intelligent Human Age Prediction from Face Image Framework Based on Deep Learning Algorithms

Sathyavathi¹,

Baskaran²

2023

ITC

View full text Add to dashboard Cite

show abstract

“…It is able to process vast volumes of data and decipher even the most complicated of situations with a relatively simple level of effort [9]. Some recent medical diagnoses have made use of techniques such as machine learning, bioinspired computing techniques, and deep learning methodologies [10]. To ameliorate the accuracy of our classification of diabetes mellitus, we made use of deep neural networks, a method that has seen a surge in popularity in recent years within the field of machine learning.…”

Section: Introductionmentioning

confidence: 99%

A New Preprocessing Method for Diabetes and Biomedical Data Classification

CHALO¹,

Aydilek²

2023

QAJ

View full text Add to dashboard Cite

People of all ages and socioeconomic levels, all over the world, are being diagnosed with type 2 diabetes at rates that are higher than they have ever been. It is possible for it to be the root cause of a wide variety of diseases, the most notable of which include blindness, renal illness, kidney disease, and heart disease. Therefore, it is of the utmost importance that a system is devised that, based on medical information, is capable of reliably detecting patients who have diabetes. We present a method for the identification of diabetes that involves the training of the features of a deep neural network between five and 10 times using the cross-validation training mode. The Pima Indian Diabetes (PID) data set was retrieved from the database that is part of the machine learning repository at UCI. In addition, the results of ten-fold cross-validation show an accuracy of 97.8%, a recall OF 97.8%, and a precision of 97.8% for PIMA dataset using RF algorithm. This research examined a variety of other biomedical datasets to demonstrate that machine learning may be used to develop an efficient system that can accurately predict diabetes. Several different types of machine learning classifiers, such as KNN, J48, RF, and DT, were utilized in the experimental findings of biological datasets. The findings that were obtained demonstrated that our trainable model is capable of correctly classifying biomedical data. This was demonstrated by achieving higher 99% accuracy, recall, and precision for parikson dataset.

show abstract

“…Recently, deep learning has shown very good results in computer vision fields such as image classification [1][2][3][4][5], object recognition [6][7][8][9][10][11], object tracking [12,13], etc. with the help of largecapacity artificial intelligence learning data and high-end computing resources.…”

Section: Introductionmentioning

confidence: 99%

A Universal Activation Function for Deep Learning

Hwang¹,

Kim²

2023

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

Recently, deep learning has achieved remarkable results in fields that require human cognitive ability, learning ability, and reasoning ability. Activation functions are very important because they provide the ability of artificial neural networks to learn complex patterns through nonlinearity. Various activation functions are being studied to solve problems such as vanishing gradients and dying nodes that may occur in the deep learning process. However, it takes a lot of time and effort for researchers to use the existing activation function in their research. Therefore, in this paper, we propose a universal activation function (UA) so that researchers can easily create and apply various activation functions and improve the performance of neural networks. UA can generate new types of activation functions as well as functions like traditional activation functions by properly adjusting three hyperparameters. The famous Convolutional Neural Network (CNN) and benchmark dataset were used to evaluate the experimental performance of the UA proposed in this study. We compared the performance of the artificial neural network to which the traditional activation function is applied and the artificial neural network to which the UA is applied. In addition, we evaluated the performance of the new activation function generated by adjusting the hyperparameters of the UA. The experimental performance evaluation results showed that the classification performance of CNNs improved by up to 5% through the UA, although most of them showed similar performance to the traditional activation function.

show abstract

ReID-DeePNet: A Hybrid Deep Learning System for Person Re-Identification

Cited by 15 publications

References 52 publications

An Intelligent Human Age Prediction from Face Image Framework Based on Deep Learning Algorithms

An Intelligent Human Age Prediction from Face Image Framework Based on Deep Learning Algorithms

A New Preprocessing Method for Diabetes and Biomedical Data Classification

A Universal Activation Function for Deep Learning

Contact Info

Product

Resources

About