Deep belief network-based hybrid model for multimodal biometric system for futuristic security applications

Vijay, M.; Indumathi, G.

doi:10.1016/j.jisa.2020.102707

Cited by 20 publications

(6 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The three scores were fed to the Deep Belief Neural Network. The results revealed that the suggested method achieved a maximum accuracy of 95.36%, a 95.85% sensitivity rate, and 98.79% specificity [16]. Xiong et al developed an innovative multimodal biometric identification system to recognize the face and the iris.…”

Section: Related Workmentioning

confidence: 99%

“…They are classified into two kinds: unimodal and multimodal systems [15]. Unimodal biometric systems use a single biometric, whereas multimodal biometric systems integrate two or more biometrics [16,17]. Multimodal biometric systems have attracted more attention than unimodal ones, as they can enhance the security level and improve the overall recognition rate by fusion of multiple biometric sources together [18].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Novel Fusion System Based on Iris and Ear Biometrics for E-exams

Shaban¹,

Ahmed²,

Elsheweikh³

2023

Intelligent Automation &Amp; Soft Computing

View full text Add to dashboard Cite

With the rapid spread of the coronavirus epidemic all over the world, educational and other institutions are heading towards digitization. In the era of digitization, identifying educational e-platform users using ear and iris based multimodal biometric systems constitutes an urgent and interesting research topic to preserve enterprise security, particularly with wearing a face mask as a precaution against the new coronavirus epidemic. This study proposes a multimodal system based on ear and iris biometrics at the feature fusion level to identify students in electronic examinations (E-exams) during the COVID-19 pandemic. The proposed system comprises four steps. The first step is image preprocessing, which includes enhancing, segmenting, and extracting the regions of interest. The second step is feature extraction, where the Haralick texture and shape methods are used to extract the features of ear images, whereas Tamura texture and color histogram methods are used to extract the features of iris images. The third step is feature fusion, where the extracted features of the ear and iris images are combined into one sequential fused vector. The fourth step is the matching, which is executed using the City Block Distance (CTB) for student identification. The findings of the study indicate that the system's recognition accuracy is 97%, with a 2% False Acceptance Rate (FAR), a 4% False Rejection Rate (FRR), a 94% Correct Recognition Rate (CRR), and a 96% Genuine Acceptance Rate (GAR). In addition, the proposed recognition system achieved higher accuracy than other related systems.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Novel Fusion System Based on Iris and Ear Biometrics for E-exams

Shaban¹,

Ahmed²,

Elsheweikh³

2023

Intelligent Automation &Amp; Soft Computing

View full text Add to dashboard Cite

show abstract

“…This framework makes it extremely difficult for an attacker to gain unauthorized access to the system without simulating all of the genuine user's biometric inputs. Vijay and Indumathi (2021) proposed a multimodal biometric consisting of three traits: iris, ear, and finger vein, the features of which are extracted using the BiComp masking method. The recognition score is then calculated for each of the three traits using a multi-support vector neural network (multi-SVNN) classifier.…”

Section: Related Workmentioning

confidence: 99%

Biometric Cloud Services for Web-Based Examinations

Rukhiran

Pukdesree

Netinant

2022

International Journal of Information Technology and Web Engineering

View full text Add to dashboard Cite

Biometric recognition may be used in conjunction with human authentication on a smartphone to improve accuracy, reliability, and simplicity, and to aid in fraud prevention and user authentication. While single biometric authentication addresses environmental degradation and sensor noise limitations, and the single point of failure scenario in biometric systems can result in more robust biometric systems, multimodal biometric authentication can improve the accuracy of identification and recognition. The purpose of this research is to propose a facial and speech authentication system that is cloud-based and supports a web-based examination approach. The system enables students' biometrics to be registered, students to be recognized, and student recognition results to be reported. The confusion matrix is used to compare the results of positive and negative detection in various ways, including accuracy score, precision value, and recall value. Adaptive multimodal biometric authentication should be designed and evaluated for further research using the optimal weights for each biometric.

show abstract

“…It can read a large number of chest X-rays in a fraction of the time that individuals can. Clinicians have been able to identify and monitor coronavirus patients more quickly as a result of this (Vijay & Indumathi, 2021). In Nigeria, for example, technology has been utilized on a small but practical basis to help individuals estimate the risk of infection.…”

Section: Artificial Intelligence and Covid-193mentioning

confidence: 99%

Intelligent Diagnosis of Covid-19 Based on CNN-PNN

Khorsheed

2022

JLMA

View full text Add to dashboard Cite

Today the whole world suffers and fears the epidemic of the Coronavirus and the developed waves in it, as we have now reached the fourth wave, and this is a serious matter. Where the statistics of the Coronavirus in the current data showed that 213 countries are affected by this epidemic, and about 6 millions of deaths are recorded. This virus spreads rapidly, and patients mainly suffer from breathing. The patient who suffers from pre-existing health problems will be more likely to contract this disease, so there was an urgent need for artificial intelligence to enter to quickly detect this virus, so the world turned to deep learning, which is one of the most powerful methods and techniques for classification because of its use of Bayas Rule, where there is no possibility of error. This paper proposes CNN (Convolutional Neural Networks) and PNN (Proprestitc Neural Networks) mixed tomography scanning model to classify Covid-19 images, the proposed network called the CNN-PNN model. The CNN-PNN model can use CNN to compute the dependency and continuity features of the output of the middle layer of the PNN model, and correlate the properties of these middle levels with the final full network to predict the classification.

show abstract

Deep belief network-based hybrid model for multimodal biometric system for futuristic security applications

Cited by 20 publications

References 17 publications

A Novel Fusion System Based on Iris and Ear Biometrics for E-exams

A Novel Fusion System Based on Iris and Ear Biometrics for E-exams

Biometric Cloud Services for Web-Based Examinations

Intelligent Diagnosis of Covid-19 Based on CNN-PNN

Contact Info

Product

Resources

About