An optimized biometric system with intra-and inter-modal feature-level fusion

Soviany, Sorin; Sandulescu, Virginia; Puşcoci, Sorin; Soviany, Cristina; Jurian, Mariana

doi:10.1109/ecai.2017.8166466

Cited by 3 publications

(5 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The intermodal fusion technique combines feature sets from various biometrics to create a single feature vector that incorporates all of the information needed for many human traits. Multimodal systems use this fusion [13].…”

Section: Theorectical Backgroundmentioning

confidence: 99%

“…Intramodal feature fusion is a technique for combining extracted feature subsets from many algorithms, samples, sensors, or instances obtained from the same biometric modality (human trait) [13]. In comparison to unimodal biometric systems, a multi-instance biometric system based on intramodal feature fusion provides numerous advantages [14,15].…”

Section: Theorectical Backgroundmentioning

confidence: 99%

See 1 more Smart Citation

Fingerprint Intramodal Biometric System Based on ABC Feature Fusion

Jooda¹,

Oke

Omidiora

et al. 2021

AJRCoS

View full text Add to dashboard Cite

Unimodal biometrics system (UBS) drawbacks include noisy data, intra-class variance, inter-class similarities, non-universality, which all affect the system's classification performance. Intramodal fingerprint fusion can overcome the limitations imposed by UBS when features are fused at the feature level as it is a good approach to boost the performance of the biometric system. However, feature level fusion leads to high dimensionality of feature space which can be overcame by Feature Selection (FS). FS improves the performance of classification by selecting only relevant and useful information from extracted feature sets being an optimization problem. Artificial Bee Colony (ABC) is an optimizing algorithm that has been frequently used in solving FS problems because of its simple concept, use of few control parameters, easy implementation and good exploration characteristics. ABC was proposed for optimized feature selection prior to the classification of Fingerprint Intramodal Biometric System (FIBS). Performance evaluation of ABC-based FIBS showed the system had a Sensitivity of 97.69% and RA of 96.76%. The developed ABC optimized feature selection reduced the high dimensionality of features space prior to classification tasks thereby increasing sensitivity and recognition accuracy of FIBS.

show abstract

Section: Theorectical Backgroundmentioning

confidence: 99%

Section: Theorectical Backgroundmentioning

confidence: 99%

Fingerprint Intramodal Biometric System Based on ABC Feature Fusion

Jooda¹,

Oke

Omidiora

et al. 2021

AJRCoS

View full text Add to dashboard Cite

show abstract

“…The performances of these feature selection strategies should be compared on the datasets within the malware recognition application, in order to find out the suitable method to keep the best features, ensuring an optimal execution time vs. recognition accuracy ratio. However, some researches concerning these feature selection methods applied on biometric data suggests that the individual ranking has an optimal execution time for an overall feature space size that does not exceed 50 [26]. This is why the individual ranking could be considered if the feature extraction and fusion processes provide no more than 50 final features.…”

Section: B Feature Generation and Selectionmentioning

confidence: 99%

“…The feature selection is important for the malware detection because this process requires to properly exploit the most relevant input data properties to provide the target KPI with the complexity/costs minimization. Within this development framework, the chosen feature selection algorithm will provide outliers and redundancy removal to only retain the most informative features [26].…”

Section: B Feature Generation and Selectionmentioning

confidence: 99%

“…3. Actually, it is an extension of the hierarchical multimodal algorithms that were applied to develop biometric security models [22], [23], [26]. The difference results from the features the algorithms apply to; in this design the features are extracted and derived from some behavioral characteristics of the Android devices and apps under various real-time operational environments.…”

Section: Data Classification (The Classifier General Designsmentioning

confidence: 99%

See 1 more Smart Citation

Android Malware Detection and Crypto-Mining Recognition Methodology with Machine Learning

Soviany¹,

Scheianu²,

Suciu

et al. 2018

2018 IEEE 16th International Conference on Embedded and Ubiquitous Computing (EUC)

Self Cite

View full text Add to dashboard Cite

The paper proposes a Machine Learning methodology for Android malware detection and recognition, including crypto-mining applications using the blockchain. The design is based on a hierarchical classification method, with several decision stages. A combination of functional and statistical features is proposed to be applied for data classification in order to provide a high-performance malware recognition process. The specific contribution of this design methodology is the hierarchical classifier with detection and discrimination stages, respectively. Further works should be done for various features sets in order to achieve an optimized and high-accuracy modeling process supporting an innovative Machine Learning-based solution for Android malware detection.

show abstract

A Biometric Security Model with Co-Occurrence Matrices for Palmprint features

Soviany¹,

Puşcoci²

2019

2019 11th International Conference on Electronics, Computers and Artificial Intelligence (ECAI)

View full text Add to dashboard Cite

An optimized biometric system with intra-and inter-modal feature-level fusion

Cited by 3 publications

References 12 publications

Fingerprint Intramodal Biometric System Based on ABC Feature Fusion

Fingerprint Intramodal Biometric System Based on ABC Feature Fusion

Android Malware Detection and Crypto-Mining Recognition Methodology with Machine Learning

A Biometric Security Model with Co-Occurrence Matrices for Palmprint features

Contact Info

Product

Resources

About