Fuzzy based image edge detection algorithm for blood vessel detection in retinal images

With the continuing growth of voice-controlled devices, voice metrics have been widely used for user identification. However, voice biometrics is vulnerable to replay attacks and ambient noise. We identify that the fundamental vulnerability in voice biometrics is rooted in its indirect sensing modality (e.g., microphone). In this paper, we present VocalPrint, a resilient mmWave interrogation system which directly captures and analyzes the vocal vibrations for user authentication. Specifically, VocalPrint exploits the unique disturbance of the skin-reflect radio frequency (RF) signals around the near-throat region of the user, caused by the vocal vibrations during communication. The complex ambient noise is isolated from the RF signal using a novel resilience-aware clutter suppression approach for preserving fine-grained vocal biometric properties. Afterward, we extract the text-independent vocal tract and vocal source features and input them to an ensemble classifier for user authentication. VocalPrint is practical as it leverages a low-cost, portable, and energy-efficient hardware allowing effortless transition to a smartphone while having sufficient usability as typical voice authentication systems due to its non-contact nature. Our experimental results from 41 participants with different interrogation distances, orientations, and body motions show that VocalPrint can achieve over 96% authentication accuracy even under unfavorable conditions. We demonstrate the resilience of our system against complex noise interference and spoof attacks of various threat levels.

VocalPrint: exploring a resilient and secure voice authentication via mmWave biometric interrogation

The Era of Information and Communication Technology (ICT) and digital innovation lead to dynamic changes in the business environment, where business transactions continue to shift from cash-based transactions to electronic-based transactions. The e-payment system was not introduced to replace cash but as a better alternative to cash and trade barter. Electronic payments can be understood as a payment mechanism using electronic media that does not involve cash. Electronic payment system (e-payment) is an important aspect of e-commerce. This study intends to review the available literature for e-payment systems on e-commerce with a view to highlighting the scope of the e-payment system, and the methodology used by previous researchers so as to identify research gaps and recommend for future studies.

https://iopscience.iop.org/article/10.1088/1742-6596/1140/1/012033/pdf

A Review of E-Payment System in E-Commerce

In this paper, we present a novel pipelined near real-time speaker recognition architecture that enhances the performance of speaker recognition by exploiting the advantages of hybrid feature extraction techniques that contain the features of Gabor Filter (GF), Convolution Neural Networks (CNN), and statistical parameters as a single matrix set. This architecture has been developed to enable secure access to a voice-based user interface (UI) by enabling speaker-based authentication and integration with an existing Natural Language Processing (NLP) system. Gaining secure access to existing NLP systems also served as motivation. Initially, we identify challenges related to real-time speaker recognition and highlight the recent research in the field. Further, we analyze the functional requirements of a speaker recognition system and introduce the mechanisms that can address these requirements through our novel architecture. Subsequently, the paper discusses the effect of different techniques such as CNN, GF, and statistical parameters in feature extraction. For the classification, standard classifiers such as Support Vector Machine (SVM), Random Forest (RF) and Deep Neural Network (DNN) are investigated. To verify the validity and effectiveness of the proposed architecture, we compared different parameters including accuracy, sensitivity, and specificity with the standard AlexNet architecture.

A Near Real-Time Automatic Speaker Recognition Architecture for Voice-Based User Interface

Diabetes is one of the most prevalent diseases in the world, which is a metabolic disorder characterized by high blood sugar. Diabetes complications are leading to Diabetic Retinopathy (DR). The early stages of DR may have either no sign or cause minor vision problems, but later stages of the disease can lead to blindness. DR diagnosis is an exceedingly difficult task because of changes in the retina during the disease stages. An automatic DR early detection method can save a patient's vision and can also support the ophthalmologists in DR screening. This paper develops a model for the diagnostics of DR. Initially, we extract and fuse the ophthalmoscopic features from the retina images based on textural gray-level features like co-occurrence, run-length matrix, as well as the coefficients of the Ridgelet Transform. Based on the retina features, the Sequential Minimal Optimization (SMO) classification is used to classify diabetic retinopathy. For performance analysis, the openly accessible retinal image datasets are used, and the findings of the experiments demonstrate the quality and efficacy of the proposed method (we achieved 98.87% sensitivity, 95.24% specificity, 97.05% accuracy on DIARETDB1 dataset, and 90.9% sensitivity, 91.0% specificity, 91.0% accuracy on KAGGLE dataset).

Detection of diabetic retinopathy using a fusion of textural and ridgelet features of retinal images and sequential minimal optimization classifier

Diabetic retinopathy (i.e., DR), is an eye disorder caused by diabetes, diabetic retinopathy detection is an important task in retinal fundus images due the early detection and treatment can potentially reduce the risk of blindness. Retinal fundus images play an important role in diabetic retinopathy through disease diagnosis, disease recognition (i.e., by ophthalmologists), and treatment. The current state-of-the-art techniques are not satisfied with sensitivity and specificity. In fact, there are still other issues to be resolved in state-of-the-art techniques such as performances, accuracy, and easily identify the DR disease effectively. Therefore, this paper proposes an effective image processing method for detection of diabetic retinopathy diseases from retinal fundus images that will satisfy the performance metrics (i.e., sensitivity, specificity, accuracy). The proposed automatic screening system for diabetic retinopathy was conducted in several steps: Pre-processing, optic disc detection and removal, blood vessel segmentation and removal, elimination of fovea, feature extraction (i.e., Micro-aneurysm, retinal hemorrhage, and exudates), feature selection and classification. Finally, a software-based simulation using MATLAB was performed using DIARETDB1 dataset and the obtained results are validated by comparing with expert ophthalmologists. The results of the conducted experiments showed an efficient and effective in sensitivity, specificity and accuracy.

An effective image processing method for detection of diabetic retinopathy diseases from retinal fundus images

/pdf/a-hybrid-svm-naive-bayes-classifier-for-bright-lesions-333vstb84e.pdf

A Hybrid SVM NAÏVE-BAYES Classifier for Bright Lesions Recognition in Eye Fundus Images

This empirical study focused on investigating the perceived trust surrogated by a number of hy-pothesized factors and its effect on the choice of method of payment. The data were collected using a questionnaire, as the instrument for the primary data collection, with total collected back responses of 214 from customers of MarkaVIP. Structural equation modeling technique was used to fully analyze the data in order to determine what level of the relationship between the constituting factors of the perceived trust and the method of payment. The main findings were related to confirming the seven main hypotheses of the research that were related to testing if some factors were important to forming perceived trust by customers. Four factors (reputation, security, familiarity, and ease of use) were found to have a positive effect and the remaining three were not (privacy, size and usefulness). In addition, having perceived trust meant no preference to any method of payment by the customers.

/pdf/perceived-trust-and-payment-methods-an-empirical-study-of-1as829awm1.pdf

Perceived Trust and Payment Methods: An Empirical Study of MarkaVIP Company

In attempt to increase the rate of Arabic phonemes recognition, we introduce a novel hybrid recognition algorithm. The algorithm is composed of the learning vector quantization (LVQ) and hidden Markov model (HMM). The hybrid algorithm used to recognizing Arabic phonemes in continuous open-vocabulary speech. A recorded Arabic corpus of different TV news for modern standard Arabic was used for training and testing purposes. We employ a data driven approach to generate the training feature vectors that embed the frame neighboring correlation information. Next, we generate the phonemes codebooks using the K-means splitting algorithm. Then, we trained the generated codebooks using the LVQ algorithm. We achieved a performance of 98.49 % during independent classification training and 90 % during dependent classification training. When using the trained LVQ codebooks in Arabic utterance transcription, the phoneme recognition rate was 72 % using LVQ only. We combined the LVQ codebooks with the single state HMM model using enhanced Viterbi algorithm which includes the phonemes bigrams. We achieved 89 % of Arabic phonemes recognition rate based on the hybrid LVQ/HMM algorithm.

Arabic phonemes recognition using hybrid LVQ/HMM model for continuous speech recognition

The whale optimisation algorithm (WOA) is a newly proposed evolutionary algorithm that uses a simulation model based on the bubble-net hunting mechanism of humpback whales to find solutions for different classes of optimisation problems. WOA may occasionally converge to suboptimal solutions because of the loss of diversity in its population of candidate solutions. The island model is a distributed approach that is commonly used to control the population diversity in evolutionary algorithms. This paper introduces an improved version of WOA namely island-based whale optimisation algorithm (iWOA) that incorporates the island model into WOA. The iWOA algorithm was compared to well-known optimisation algorithms using 18 standard benchmark functions. The simulation results indicate that iWOA improves the accuracy of results compared to WOA and other popular evolutionary algorithms. In addition, the sensitivity analysis of iWOA to its parameters indicates that its convergence behaviour is sensitive to the parameters of the island model.

Khalid M.O. Nahar

Papers

An effective image processing method for detection of diabetic retinopathy diseases from retinal fundus images

A Hybrid SVM NAÏVE-BAYES Classifier for Bright Lesions Recognition in Eye Fundus Images

Perceived Trust and Payment Methods: An Empirical Study of MarkaVIP Company

Arabic phonemes recognition using hybrid LVQ/HMM model for continuous speech recognition

Island-based whale optimisation algorithm for continuous optimisation problems