Equal Error Rate Values Research Articles

Deep learning-based authentication for insider threat detection in critical infrastructure

In today’s cyber environment, threats such as data breaches, cyberattacks, and unauthorized access threaten national security, critical infrastructure, and financial stability. This research addresses the challenging task of protecting critical infrastructure from insider threats because of the high level of trust and access these individuals typically receive. Insiders may obtain a system administrator’s password through close observation or by deploying software to gather the information. To solve this issue, an innovative artificial intelligence-based methodology is proposed to identify a user by their password’s keystroke dynamics. This paper also introduces a new Gabor Filter Matrix Transformation method to transform numerical values into images by revealing the behavioral pattern of password typing. A siamese neural network (SNN) with the branches of convolutional neural networks is utilized for image comparison, aiming to detect unauthorized attempts to access critical infrastructure systems. The network analyzes the unique features of a user’s password timestamps transformed into images and compares them with previously submitted user passwords. The obtained results indicate that transforming the numerical values of keystroke dynamics into images and training an SNN leads to a lower equal error rate (EER) and higher user authentication accuracy than those previously reported in other studies. The methodology is validated on publicly available keystroke dynamics collections, the CMU and GREYC-NISLAB datasets, which collectively comprise over 30,000 password samples. It achieves the lowest EER value of 0.04545 compared to state-of-the-art methods for transforming non-image data into images. The paper concludes with a discussion of findings and potential future directions.

TypeFormer: transformers for mobile keystroke biometrics

The broad usage of mobile devices nowadays, the sensitiveness of the information contained in them, and the shortcomings of current mobile user authentication methods are calling for novel, secure, and unobtrusive solutions to verify the users’ identity. In this article, we propose TypeFormer, a novel transformer architecture to model free-text keystroke dynamics performed on mobile devices for the purpose of user authentication. The proposed model consists in temporal and channel modules enclosing two long short-term memory recurrent layers, Gaussian range encoding, a multi-head self-attention mechanism, and a block-recurrent transformer layer. Experimenting on one of the largest public databases to date, the Aalto mobile keystroke database, TypeFormer outperforms current state-of-the-art systems achieving equal error rate values of 3.25% using only five enrolment sessions of 50 keystrokes each. In such way, we contribute to reducing the traditional performance gap of the challenging mobile free-text scenario with respect to its desktop and fixed-text counterparts. To highlight the design rationale, an analysis of the experimental results of the different modules implemented in the development of TypeFormer is carried out. Additionally, we analyse the behaviour of the model with different experimental configurations such as the length of the keystroke sequences and the amount of enrolment sessions, showing margin for improvement.

Patterns Identification of Finger Outer Knuckles by Utilizing Local Directional Number

Finger Outer Knuckle (FOK) is a distinctive biometric that has grown in popularity recently. This results from its inborn qualities such as stability, protection, and specific anatomical patterns. Applications for the identification of FOK patterns include forensic investigations, access control systems, and personal identity. In this study, we suggest a method for identifying FOK patterns using Local Directional Number (LDN) codes produced from gradient-based compass masks. For the FOK pattern matching, the suggested method uses two asymmetric masks—Kirsch and Gaussian derivative—to compute the edge response and extract LDN codes. To calculate edge response on the pattern, an asymmetric compass mask made from the Gaussian derivative mask is created by rotating the Kirsch mask by 45 degrees to provide edge response in eight distinct directions. The edge response of each mask and the combination of dominating vector numbers are examined during the LDN code-generating process. A distance metric can be used to compare the LDN code's condensed representation of the FOK pattern to the original for matching purposes. On the Indian Institute of Technology Delhi Finger Knuckle (IITDFK) database, the efficiency of the suggested procedure is assessed. The data show that the suggested strategy is effective, with an Equal Error Rate (EER) of 10.78%. This value performs better than other EER values when compared to different approaches.

SwipeFormer: Transformers for mobile touchscreen biometrics

The growing number of mobile devices over the past few years brings a large amount of personal information, which needs to be properly protected. As a result, several mobile authentication methods have been developed. In particular, behavioural biometrics has become one of the most relevant methods due to its ability to extract the uniqueness of each subject in a secure, non-intrusive, and continuous way. This article presents SwipeFormer, a novel Transformer-based system for mobile subject authentication by means of swipe gestures in an unconstrained scenario (i.e., subjects could use their personal devices freely, without restrictions on the direction of swipe gestures or the position of the device). Our proposed system contains two modules: (i) a Transformer-based feature extractor, and (ii) a similarity computation module. Mobile data from the touchscreen and different background sensors (accelerometer and gyroscope) have been studied, including in the analysis both Android and iOS operating systems. A complete analysis of SwipeFormer is carried out using an in-house large-scale database acquired in unconstrained scenarios. In these operational conditions, SwipeFormer achieves Equal Error Rate (EER) values of 6.6% and 3.6% on Android and iOS respectively, outperforming the state of the art. In addition, we evaluate SwipeFormer on the popular publicly available databases Frank DB and HuMIdb, achieving EER values of 11.0% and 5.0% respectively, outperforming previous approaches under the same experimental setup.

Text-Independent Speaker Recognition System Using Feature-Level Fusion for Audio Databases of Various Sizes

To improve the speaker recognition rate, we propose a speaker recognition model based on the fusion of different kinds of speech features. A new type of feature aggregation methodology with a total of 18 features is proposed and includes mel frequency cepstral coefficient (MFCC), linear predictive coding (LPC), perceptual linear prediction (PLP), root mean square (RMS), centroid, and entropy features along with their delta (Δ) and delta–delta (ΔΔ) feature vectors. The proposed approach is tested on five different sizes of speech datasets, namely the NIST-2008, voxforge, ELSDSR, VCTK, and voxceleb1 speech corpora. The results are evaluated using the MATLAB classification learner application with the linear discriminant (LD), K nearest neighbor (KNN), and ensemble classifiers. For the NIST-2008 and voxforge datasets, the best SI accuracy of 96.9% and 100% and the lowest speaker verification (SV) equal error rate (EER) values of 0.2% and 0% are achieved with the LD and KNN classifiers, respectively. For the VCTK and ELSDSR datasets, the best SI accuracy of 100% and the lowest SV EER of 0% are achieved with all three classifiers using different feature-level fusion approaches, while the highest SI accuracy and lowest EER achieved on the voxceleb1 database are 90% and 4.07%, respectively, using the KNN classifier. From the experimental results, it is observed that the fusion of different features with their delta and delta–delta values shows an increase in speaker identification accuracy of 10–50%, and the EER value for SV is reduced compared to the value obtained with a single feature.

On the speaker discriminatory power asymmetry regarding acoustic-phonetic parameters and the impact of speaking style.

This study aimed to assess what we refer to as the speaker discriminatory power asymmetry and its forensic implications in comparisons performed in different speaking styles: spontaneous dialogues vs. interviews. We also addressed the impact of data sampling on the speaker's discriminatory performance concerning different acoustic-phonetic estimates. The participants were 20 male speakers, Brazilian Portuguese speakers from the same dialectal area. The speech material consisted of spontaneous telephone conversations between familiar individuals, and interviews conducted between each individual participant and the researcher. Nine acoustic-phonetic parameters were chosen for the comparisons, spanning from temporal and melodic to spectral acoustic-phonetic estimates. Ultimately, an analysis based on the combination of different parameters was also conducted. Two speaker discriminatory metrics were examined: Cost Log-likelihood-ratio (Cllr) and Equal Error Rate (EER) values. A general speaker discriminatory trend was suggested when assessing the parameters individually. Parameters pertaining to the temporal acoustic-phonetic class depicted the weakest performance in terms of speaker contrasting power as evidenced by the relatively higher Cllr and EER values. Moreover, from the set of acoustic parameters assessed, spectral parameters, mainly high formant frequencies, i.e., F3 and F4, were the best performing in terms of speaker discrimination, depicting the lowest EER and Cllr scores. The results appear to suggest a speaker discriminatory power asymmetry concerning parameters from different acoustic-phonetic classes, in which temporal parameters tended to present a lower discriminatory power. The speaking style mismatch also seemed to considerably impact the speaker comparison task, by undermining the overall discriminatory performance. A statistical model based on the combination of different acoustic-phonetic estimates was found to perform best in this case. Finally, data sampling has proven to be of crucial relevance for the reliability of discriminatory power assessment.

Violence Detection Enhancement by Involving Convolutional Block Attention Modules Into Various Deep Learning Architectures: Comprehensive Case Study for UBI-Fights Dataset

The violence detection in surveillance videos is a complicated task, due to the requirements of extracting the spatio-temporal features in different videos environment, and various videos prospective cases. Hereby, in this paper, different architectures are proposed to perform this task in high performance, by using the UBI-Fights dataset as a comprehensive case study. The proposed architectures are based on involving the Convolutional Block Attention Modules (CBAM) with other simple layers (e.g., ConvLSTM2D or Conv2D&LSTM). In addition, using the Categorical Focal Loss (CFL) as loss function during architectures training to increase the focus on the most important features. To evaluate the proposed architectures, the performance metrics like are Area Under the Curve (AUC), and Equal Error Rate (EER); are mainly used, to declare the architecture ability of identifying the violence correctly, with low interaction value between classes. The performance results declare the ability of the proposed architectures, to achieve higher results that the state of art techniques. For example, the Conv2D&LSTM based architecture, get AUC value of 0.9493, and EER value of 0.0507; that outperform the most of the other proposed ones, and the state of art performance.

Extracting Phonetic Posterior-Based Features for Detecting Multiple Sclerosis From Speech.

Multiple sclerosis (MS) is a chronic inflammatory disease of the central nervous system which, in addition to affecting motor and cognitive functions, may also lead to specific changes in the speech of patients. Speech production, comprehension, repetition and naming tasks, as well as structural and content changes in narratives, might indicate a limitation of executive functions. In this study we present a speech-based machine learning technique to distinguish speakers with relapsing-remitting subtype MS and healthy controls (HC). We exploit the fact that MS might cause a motor speech disorder similar to dysarthria, which, with our hypothesis, might affect the phonetic posterior estimates supplied by a Deep Neural Network acoustic model. From our experimental results, the proposed posterior posteriorgram-based feature extraction approach is useful for detecting MS: depending on the actual speech task, we obtained Equal Error Rate values as low as 13.3%, and AUC scores up to 0.891, indicating a competitive and more consistent classification performance compared to both the x-vector and the openSMILE 'ComParE functionals' attributes. Besides this discrimination performance, the interpretable nature of the phonetic posterior features might also make our method suitable for automatic MS screening or monitoring the progression of the disease. Furthermore, by examining which specific phonetic groups are the most useful for this feature extraction process, the potential utility of the proposed phonetic features could also be utilized in the speech therapy of MS patients.

Empirical Comparison between Deep and Classical Classifiers for Speaker Verification in Emotional Talking Environments

Speech signals carry various bits of information relevant to the speaker such as age, gender, accent, language, health, and emotions. Emotions are conveyed through modulations of facial and vocal expressions. This paper conducts an empirical comparison of performances between the classical classifiers: Gaussian Mixture Model (GMM), Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Artificial neural networks (ANN); and the deep learning classifiers, i.e., Long Short-Term Memory (LSTM), Convolutional Neural Network (CNN), and Gated Recurrent Unit (GRU) in addition to the ivector approach for a text-independent speaker verification task in neutral and emotional talking environments. The deep models undergo hyperparameter tuning using the Grid Search optimization algorithm. The models are trained and tested using a private Arabic Emirati Speech Database, Ryerson Audio–Visual Database of Emotional Speech and Song dataset (RAVDESS) database, and a public Crowd-Sourced Emotional Multimodal Actors (CREMA) database. Experimental results illustrate that deep architectures do not necessarily outperform classical classifiers. In fact, evaluation was carried out through Equal Error Rate (EER) along with Area Under the Curve (AUC) scores. The findings reveal that the GMM model yields the lowest EER values and the best AUC scores across all datasets, amongst classical classifiers. In addition, the ivector model surpasses all the fine-tuned deep models (CNN, LSTM, and GRU) based on both evaluation metrics in the neutral, as well as the emotional speech. In addition, the GMM outperforms the ivector using the Emirati and RAVDESS databases.

A hybrid noise robust model for multireplay attack detection in Automatic speaker verification systems

Biometric Systems are automatic methods of verifying the identity of a person based on some characteristics such as fingerprint, face, speech etc. Speech biometrics involves verifying the identity of a person based on voice. The process is called speaker verification, and such biometric systems are called Automatic Speaker Verification systems. However, these systems are prone to malicious attacks such as replay attacks. Thus, Automatic Speaker Verification systems need to be robust against these attacks. Existing approaches have worked majorly with single-replay attacks. The proposed work in this paper explores three back-end models: Convolutional Neural Network, Long Short-Term Memory and hybrid of these two models, with different input feature formats. It analyses their performance in a diverse multi-replay attack detection scenario, using the Voice Spoofing Detection Corpus. In the frontend of the proposed hybrid system, mel-spectrograms is used as the feature extraction technique for Convolutional Neural Network based model, and Constant-Q Cepstral Coefficient approach is used for extracting features for Long Short-Term Memory based model. A comparison of this hybrid model’s performance is done with past approaches in single-replay attack detection as well. The average Equal Error Rate achieved on the test set was 0.036 for single-replayed attack and 0.0296 for two times replayed. The hybrid model consistently outperforms other models with lower Equal Error Rate values, thus showing promising results, paving the way for future research along this line. Further, an analysis on unseen noisy audio files suggests the proposed model’s utility in noise-robust systems as well.

Novel hybrid DNN approaches for speaker verification in emotional and stressful talking environments

In this work, we conducted an empirical comparative study of the performance of text-independent speaker verification in emotional and stressful environments. This work combined deep models with shallow architecture, which resulted in novel hybrid classifiers. Four distinct hybrid models were utilized: deep neural network-hidden Markov model (DNN-HMM), deep neural network-Gaussian mixture model (DNN-GMM), Gaussian mixture model-deep neural network (GMM-DNN), and hidden Markov model-deep neural network (HMM-DNN). All models were based on novel implemented architecture. The comparative study used three distinct speech datasets: a private Arabic dataset and two public English databases, namely Speech Under Simulated and Actual Stress (SUSAS) and Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS). The test results of the aforementioned hybrid models demonstrated that the proposed HMM-DNN leveraged the verification performance in emotional and stressful environments. Results also showed that HMM-DNN outperformed all other hybrid models in terms of equal error rate (EER) and area under the curve (AUC) evaluation metrics. The average resulting verification system based on the three datasets yielded EERs of 7.19, 16.85, 11.51, and 11.90% based on HMM-DNN, DNN-HMM, DNN-GMM, and GMM-DNN, respectively. Furthermore, we found that the DNN-GMM model demonstrated the least computational complexity compared to all other hybrid models in both talking environments. Conversely, the HMM-DNN model required the greatest amount of training time. Findings also demonstrated that EER and AUC values depended on the database when comparing average emotional and stressful performances.

Fingerprint recognition model using DTCWT algorithm

The automation in all walks of daily life is required for secure communication by overcoming with traditional techniques like Badges, Personal ID cards etc., In the proposed research work Dual Tree Complex Wavelet Transformation (DTCWT) fingerprint recognition method for data base FVC 2004 DB 3_A is carried out. The Preprocessing has been carried out for all the images to obtain uniform size i.e., Region of Interest (ROI). The Three stage DTCWT algorithm is utilized to achieve final characteristics for the size of 2x × 2y images. The ED (Euclidean distance) method is employed for matching and Evaluation terms like False acceptance rate (FAR), Equal Error rate (EER) and False rejection rate (FRR) are measured. It is visually examined that in contrast from contemporary algorithms FAR, EER and FRR values are strengthened with the proposed method.

An Efficient GCD-Based Cancelable Biometric Algorithm for Single and Multiple Biometrics

Cancelable biometrics are required in most remote access applications that need an authentication stage such as the cloud and Internet of Things (IoT) networks. The objective of using cancelable biometrics is to save the original ones from hacking attempts. A generalized algorithm to generate cancelable templates that is applicable on both single and multiple biometrics is proposed in this paper to be considered for cloud and IoT applications. The original biometric is blurred with two co-prime operators. Hence, it can be recovered as the Greatest Common Divisor (GCD) between its two blurred versions. Minimal changes if induced in the biometric image prior to processing with co-prime operators prevents the recovery of the original biometric image through a GCD operation. Hence, the ability to change cancelable templates is guaranteed, since the owner of the biometric can pre-determine and manage the minimal change induced in the biometric image. Furthermore, we test the utility of the proposed algorithm in the single- and multi-biometric scenarios. The multi-biometric scenario depends on compressing face, fingerprint, iris, and palm print images, simultaneously, to generate the cancelable templates. Evaluation metrics such as Equal Error Rate (EER) and Area and Receiver Operator Characteristic curve (AROC) are considered. Simulation results on single- and multi-biometric scenarios show high AROC values up to 99.59%, and low EER values down to 0.04%.

Privacy-preserving iris authentication using fully homomorphic encryption

Rapid advancement in technology has led to the use of biometric authentication in every field. In particular, from the past few years, iris recognition systems has gained overwhelming advancement over other biometric traits due to its stability and uniqueness. Directly storing the templates into a centralized server leads to privacy concerns. Many state-of-the-art iris authentication systems based on cancelable biometrics and bio-cryptosystems have been introduced to provide security for the iris templates. However, these works suffer from accuracy loss relative to unprotected systems, or they require auxiliary data (AD), which compromise the privacy of the templates and security of the system. To address this, we propose a novel privacy-preserving iris authentication using fully homomorphic encryption which ensures the confidentiality of the templates and restricts the leakage of data from the templates. Our method improves the recognition accuracy by generating rotation invariant iris codes and reduces the computational time by using the batching scheme. Our approach satisfies all the requirements specified in the ISO/IEC 24745 standard. The proposed method has experimented on four benchmark publicly available iris databases which illustrate that our method can be practically achievable with no loss in the accuracy and preserve the privacy of the iris templates. Our method encrypts and computes the Hamming distance of 2560-dimensional iris features in about 0.0185 seconds only with an equal error rate value of 0.19% for CASIA-V 1.0 database.

Deep representations for cross‐spectral ocular biometrics

One of the major challenges in ocular biometrics is the cross-spectral scenario, i.e. how to match images acquired in different wavelengths. This study designs and extensively evaluates cross-spectral ocular verification methods using well known deep learning representations based on the iris and periocular regions. Using as inputs, the bounding boxes of non-normalised iris–periocular regions, the authors fine-tune convolutional neural network models, originally trained for face recognition. On the basis of the experiments carried out in two publicly available cross-spectral ocular databases, they report results for intra-spectral and cross-spectral scenarios, with the best performance being observed when fusing ResNet-50 deep representations from both the periocular and iris regions. When compared to the state of the art, they observed that the proposed solution consistently reduces the equal error rate values by 90%/93%/96% and 61%/77%/83% on the cross-spectral scenario and in the PolyU bi-spectral and cross-eye–cross-spectral datasets. Finally, they evaluate the effect that the ‘deepness’ factor of feature representations has in recognition effectiveness, and based on a subjective analysis of the most problematic pairwise comparisons – they point out further directions for this field of research.

Multi-Biometric System Based on Cutting-Edge Equipment for Experimental Contactless Verification

Biometric verification methods have gained significant popularity in recent times, which has brought about their extensive usage. In light of theoretical evidence surrounding the development of biometric verification, we proposed an experimental multi-biometric system for laboratory testing. First, the proposed system was designed such that it was able to identify and verify a user through the hand contour, and blood flow (blood stream) at the upper part of the hand. Next, we detailed the hard and software solutions for the system. A total of 40 subjects agreed to be a part of data generation team, which produced 280 hand images. The core of this paper lies in evaluating individual metrics, which are functions of frequency comparison of the double type faults with the EER (Equal Error Rate) values. The lowest value was measured for the case of the modified Hausdorff distance metric - Maximally Helicity Violating (MHV). Furthermore, for the verified biometric characteristics (Hamming distance and MHV), appropriate and suitable metrics have been proposed and experimented to optimize system precision. Thus, the EER value for the designed multi-biometric system in the context of this work was found to be 5%, which proves that metrics consolidation increases the precision of the multi-biometric system. Algorithms used for the proposed multi-biometric device shows that the individual metrics exhibit significant accuracy but perform better on consolidation, with a few shortcomings.

HYBRID IMPROVED BACTERIAL SWARM OPTIMIZATION ALGORITHM FOR HAND-BASED MULTIMODAL BIOMETRIC AUTHENTICATION SYSTEM

This paper proposes a Hybrid Improved Bacterial Swarm (HIBS) optimization algorithm for the minimization of Equal Error Rate (EER) as a performance measure in a hand-based multimodal biometric authentication system. The hybridization of the algorithm was conducted by incorporating Bacterial Foraging Optimization (BFO) and Particle Swarm Optimization (PSO) algorithm to mitigate weaknesses in slow and premature convergence. In the proposed HIBS algorithm, the slow convergence of BFO algorithm was mitigated by using the random walk procedure of Firefly algorithm as an adaptive varying step size instead of using fixed step size. Concurrently, the local optima trap (i.e. premature convergence) of PSO algorithm was averted by using mutation operator. The HIBS algorithm was tested using benchmark functions and compared against classical BFO, PSO and other hybrid algorithms like Genetic Algorithm-Bacterial Foraging Optimization (GA-BFO), Genetic Algorithm-Particle Swarm Optimization (GA-PSO) and other BFO-PSO algorithms to prove its exploration and exploitation ability. It was observed from the experimental results that the EER values, after the influence of the proposed HIBS algorithm, dropped to 0.0070% and 0.0049% from 1.56% and 0.86% for the right and left hand images of the Bosphorus database, respectively. The results indicated the ability of the proposed HIBS in optimization problem where it optimized relevant weights in an authentication system.

Point Grouping Method for Finger Vein Recognition

In finger vein recognition, vein points-based methods classified the image points into vein points and non-vein points and only measured the vein points for the recognition. All points-based methods utilized the features of all points regardless of the difference of vein points and non-vein points. This paper proposes a point grouping method for finger vein recognition by integrating the advantages of the above-mentioned two kinds of methods. In the proposed method, all image points are considered in the recognition, and the points are classified into multiple groups in both feature extraction and similarity measurement. The matched (unmatched) points are separately found from each group pair of the enrolled image and the probe and are fused to obtain the similarity (dissimilarity) score. Moreover, we incorporate the idea of the point grouping into two popular finger vein recognition methods and devise the corresponding point grouping assisted methods, namely, point grouping assisted anatomy structure analysis-based vein extraction and point grouping assisted Gabor. The experimental results on finger vein databases demonstrate the efficacy of the point grouping assisted methods. The equal error rate values of our point grouping methods are lower about 1% than their base methods on SDUD in the multiple templates' mode and on HKPUD in the single template mode.

A continuous smartphone authentication method based on gait patterns and keystroke dynamics

Behavioral biometrics, such as gait patterns and keystroke dynamics, have been becoming increasingly used in human identity recognition research for enhancing the smartphone security. A new multimodal authentication method able to strengthen the smartphone authentication system is proposed in this paper. The proposed mechanism acquires gait patterns from the accelerometer, as well as keystroke dynamics, continuously without user intervention through simultaneous walk and text input. More specifically, features are extracted from both modalities. Afterward, a feature level fusion method is applied to build a multimodal biometrics profile for the user. Fused feature vectors are subjected to the sequential floating forward selection algorithm to reduce their dimensions as well as the computational complexity. The effectiveness of the proposed method is examined through a real multimodal dataset collected from 20 subjects under various scenarios, using different machine learning classifiers. The experimental results achieved a promising accuracy of 99.11% when using multilayer perceptron classifier with the average false acceptance rate, false rejection rate and equal error rate values of 0.684%, 7%, and 1%, respectively. Furthermore, the security strength of the proposed method was evaluated against two types of attacks, the zero-effort attack and minimal-effort mimicking attack. Results demonstrate that our approach represents a robust and secure authentication solution.

Robust technique for fingerprint template protection

Fingerprint authentication systems generally save data extracted from fingerprint as minutiae template in the database. However, it is often found that databases can be attacked and compromised by the adversary. So if minutiae points of a user are leaked, the fingerprint can be generated from them. The fingerprint cannot be changed as the finger is a part of the human body. Hence, securing information extracted from the fingerprint is required. In this study, the authors propose a highly secure technique that uses location information of the minutia points to construct a highly secured template for a user. For every minutia point, secured modified location is generated by using information of its neighbouring minutiae and a key-set. They have achieved 2, 1, and 3.1% equal error rate values for FVC2002 DB1, DB2, and DB3 fingerprint databases, respectively, under the same key scenario. Analysis done for several attacks shows that the proposed technique is very robust and secure. The experimental results are extremely encouraging and they demonstrate the efficiency of the proposed technique.