Iris Liveness Detection Using Fragmental Energy of Haar Transformed Iris Images Using Ensemble of Machine Learning Classifiers

Contactless verification is possible with iris biometric identification, which helps prevent infections like COVID-19 from spreading. Biometric systems have grown unsteady and dangerous as a result of spoofing assaults employing contact lenses, replayed the video, and print attacks. The work demonstrates an iris liveness detection approach by utilizing fragmental coefficients of Haar transformed Iris images as signatures to prevent spoofing attacks for the very first time in the identification of iris liveness. Seven assorted feature creation ways are studied in the presented solutions, and these created features are explored for the training of eight distinct machine learning classifiers and ensembles. The predicted iris liveness identification variants are evaluated using recall, F-measure, precision, accuracy, APCER, BPCER, and ACER. Three standard datasets were used in the investigation. The main contribution of our study is achieving a good accuracy of 99.18% with a smaller feature vector. The fragmental coefficients of Haar transformed iris image of size 8 ∗ 8 utilizing random forest algorithm showed superior iris liveness detection with reduced featured vector size (64 features). Random forest gave 99.18% accuracy. Additionally, conduct an extensive experiment on cross datasets for detailed analysis. The results of our experiments show that the iris biometric template is decreased in size to make the proposed framework suitable for algorithmic verification in real-time environments and settings. © 2023 Tech Science Press. All rights reserved.

Detection of Iris Presentation Attacks Using Hybridization of Discrete Cosine Transform and Haar Transform With Machine Learning Classifiers and Ensembles

Iris biometric identification allows for contactless authentication, which helps to avoid the transmission of diseases like COVID-19. Biometric systems become unstable and hazardous due to spoofing attacks involving contact lenses, replayed video, cadaver iris, synthetic Iris, and printed iris. This work demonstrates the iris presentation attacks detection (Iris- PAD) approach that uses fragmental coefficients of transform iris images as features obtained using Discrete Cosine Transform (DCT), Haar Transform, and hybrid Transform. In experimental validations of the proposed method, three main types of feature creation are investigated. The extracted features are utilized for training seven different machine learning classifiers alias Support Vector Machine (SVM), Naive Bayes (NB), Random Forest (RF), and decision tree(J48) with ensembles of SVM CRF CNB, SVM CRF CRT, and RF CSVM CMLP (multi-layer perceptron) for proposed iris liveness detection. The proposed iris liveness detection variants are evaluated using various statistical measures: accuracy, Attack Presentation Classification Error Rate (APCER), Normal Presentation Classification Error Rate (NPCER), Average Classification Error Rate (ACER). Six standard datasets are used in the investigations. Total nine iris spoofing attacks are getting identified in the proposed method. Among all investigated variations of proposed iris-PAD methods, the 4 x 4 of fragmental coefficients of a Hybrid transformed iris image with RF algorithm have shown superior iris liveness detection with 99.95% accuracy. The proposed hybridization of transform for features extraction has demonstrated the ability to identify all nine types of iris spoofing attacks and proved it robust. The proposed method offers exceptional performances against the Synthetic iris spoofing images by using a random forest classifier. Machine learning has massive potential in a similar domain and could be explored further based on the research requirements.

School location analysis by integrating the accessibility, natural and biological hazards to support equal access to education

This study proposes a new model for land suitability for educational facilities based on spatial product development to determine the optimal locations for achieving education targets in West Java, Indonesia. Single-aspect approaches, such as accessibility and spatial hazard analyses, have not been widely applied in suitability assessments on the location of educational facilities. Model development was performed based on analyses of the economic value of the land and on the integration of various parameters across three main aspects: accessibility, comfort, and a multi-natural/biohazard (disaster) risk index. Based on the maps of disaster hazards, higher flood-prone areas are found to be in gentle slopes and located in large cities. Higher risks of landslides are spread throughout the study area, while higher levels of earthquake risk are predominantly in the south, close to the active faults and megathrusts present. Presently, many schools are located in very high vulnerability zones (2057 elementary, 572 junior high, 157 senior high, and 313 vocational high schools). The comfort-level map revealed 13,459 schools located in areas with very low and low comfort levels, whereas only 2377 schools are in locations of high or very high comfort levels. Based on the school accessibility map, higher levels are located in the larger cities of West Java, whereas schools with lower accessibility are documented far from these urban areas. In particular, senior high school accessibility is predominant in areas of lower accessibility levels, as there are comparatively fewer facilities available in West Java. Overall, higher levels of suitability are spread throughout West Java. These distribution results revealed an expansion of the availability of schools by area: senior high schools, 303,973.1 ha;vocational high schools, 94,170.51 ha;and junior high schools, 12,981.78 ha. Changes in elementary schools (3936.69 ha) were insignificant, as the current number of elementary schools is relatively much higher. This study represents the first to attempt to integrate these four parameters—accessibility, multi natural hazard, biohazard, comfort index, and land value—to determine potential areas for new schools to achieve educational equity targets. © 2021 by the authors. Licensee MDPI, Basel, Switzerland.

Using Susceptible-Exposed-Infectious-Recovered Model to Forecast Coronavirus Outbreak

The Coronavirus disease 2019 (COVID-19) outbreak was first discovered in Wuhan, China, and it has since spread to more than 200 countries. The World Health Organization proclaimed COVID-19 a public health emergency of international concern on January 30, 2020. Normally, a quickly spreading infection that could jeopardize the well-being of countless individuals requires prompt action to forestall the malady in a timely manner. COVID-19 is a major threat worldwide due to its ability to rapidly spread. No vaccines are yet available for COVID-19. The objective of this paper is to examine the worldwide COVID-19 pandemic, specifically studying Hubei Province, China;Taiwan;South Korea;Japan;and Italy, in terms of exposed, infected, recovered/deceased, original confirmed cases, and predict confirmed cases in specific countries by using the susceptible-exposed-infectious-recovered model to predict the future outbreak of COVID-19. We applied four differential equations to calculate the number of confirmed cases in each country, plotted them on a graph, and then applied polynomial regression with the logic of multiple linear regression to predict the further spread of the pandemic. We also compared the calculated and predicted cases of confirmed population and plotted them in the graph, where we could see that the lines of calculated and predicted cases do intersect with each other to give the perfect true results for the future spread of the virus. This study considered the cases from 22 January 2020 to 25 April 2020.