Flash-flood hazard assessment using ensembles and Bayesian-based machine learning models: Application of the simulated annealing feature selection method

Flash-floods are increasingly recognized as a frequent natural hazard worldwide. Iran has been among the mostdevastated regions affected by the major floods. While the temporal flash-flood forecasting models are mainly developed for warning systems, the models for assessing hazardous areas can greatly contribute to adaptation and mitigation policy-making and disaster risk reduction. Former researches in the flash-flood hazard mapping have heightened the urge for the advancement of more accurate models. Thus, the current research proposes the state-of-the-art ensemble models of boosted generalized linear model (GLMBoost) and random forest (RF), and Bayesian generalized linear model (BayesGLM) methods for higher performance modeling. Furthermore, a pre-processing method, namely simulated annealing (SA), is used to eliminate redundant variables from the modeling process. Results of the modeling based on the hit and miss analysis indicates high performance for both models (accuracy = 90-92%, Kappa = 79-84%, Success ratio = 94-96%, Threat score = 80-84%, and Heidke skill score = 79-84%). The variables of distance from the stream, vegetation, drainage density, land use, and elevation have shown more contribution among others for modeling the flash-flood. The results of this study can significantly facilitate mapping the hazardous areas and further assist watershed managers to control and remediate induced damages of flood in the data-scarce regions.

Integrated machine learning methods with resampling algorithms for flood susceptibility prediction

Flood susceptibility projections relying on standalone models, with one-time train-test data splitting for model calibration, yields biased results. This study proposed novel integrative flood susceptibility prediction models based on multi-time resampling approaches, random subsampling (RS) and bootstrapping (BT) algorithms, integrated with machine learning models: generalized additive model (GAM), boosted regression tree (BTR) and multivariate adaptive regression splines (MARS). RS and BT algorithms provided 10 runs of data resampling for learning and validation of the models. Then the mean of 10 runs of predictions is used to produce the flood susceptibility maps (FSM). This methodology was applied to Ardabil Province on coastal margins of the Caspian Sea which faced destructive floods. The area under curve (AUC) of receiver operating characteristic (ROC) and true skill statistic (TSS) and correlation coefficient (COR) were utilized to evaluate the predictive accuracy of the proposed models. Results demonstrated that resampling algorithms improved the performance of Standalone GAM, MARS and BRT models. Results also revealed that Standalone models had better performance with the BT algorithm compared to the RS algorithm. BT-GAM model attained superior performance in terms of statistical measures (AUC = 0.98, TSS = 0.93, COR = 0.91), followed by BT-MARS (AUC = 0.97, TSS = 0.91, COR = 0.91) and BT-BRT model (AUC = 0.95, TSS = 0.79, COR = 0.79). Results demonstrated that the proposed models outperformed the benchmark models such as Standalone GAM, MARS, BRT, multilayer perceptron (MLP) and support vector machine (SVM). Given the admirable performance of the proposed models in a large scale area, the promising results can be expected from these models for other regions.

Coronary Artery Disease Diagnosis; Ranking the Significant Features Using a Random Trees Model

Heart disease is one of the most common diseases in middle-aged citizens. Among the vast number of heart diseases, coronary artery disease (CAD) is considered as a common cardiovascular disease with a high death rate. The most popular tool for diagnosing CAD is the use of medical imaging, e.g., angiography. However, angiography is known for being costly and also associated with a number of side effects. Hence, the purpose of this study is to increase the accuracy of coronary heart disease diagnosis through selecting significant predictive features in order of their ranking. In this study, we propose an integrated method using machine learning. The machine learning methods of random trees (RTs), decision tree of C5.0, support vector machine (SVM), and decision tree of Chi-squared automatic interaction detection (CHAID) are used in this study. The proposed method shows promising results and the study confirms that the RTs model outperforms other models.

Spatial hazard assessment of the PM10 using machine learning models in Barcelona, Spain

Air pollution, and especially atmospheric particulate matter (PM), has a profound impact on human mortality and morbidity, environment, and ecological system. Accordingly, it is very relevant predicting air quality. Although the application of the machine learning (ML) models for predicting air quality parameters, such as PM concentrations, has been evaluated in previous studies, those on the spatial hazard modeling of them are very limited. Due to the high potential of the ML models, the spatial modeling of PM can help managers to identify the pollution hotspots. Accordingly, this study aims at developing new ML models, such as Random Forest (RF), Bagged Classification and Regression Trees (Bagged CART), and Mixture Discriminate Analysis (MDA) for the hazard prediction of PM10 (particles with a diameter less than 10 µm) in the Barcelona Province, Spain. According to the annual PM10 concentration in 75 stations, the healthy and unhealthy locations are determined, and a ratio 70/30 (53/22 stations) is applied for calibrating and validating the ML models to predict the most hazardous areas for PM10. In order to identify the influential variables of PM modeling, the simulated annealing (SA) feature selection method is used. Seven features, among the thirteen features, are selected as critical features. According to the results, all the three-machine learning (ML) models achieve an excellent performance (Accuracy > 87% and precision > 86%). However, the Bagged CART and RF models have the same performance and higher than the MDA model. Spatial hazard maps predicted by the three models indicate that the high hazardous areas are located in the middle of the Barcelona Province more than in the Barcelona's Metropolitan Area.

Earth fissure hazard prediction using machine learning models

Earth fissures are the cracks on the surface of the earth mainly formed in the arid and the semi-arid basins. The excessive withdrawal of groundwater, as well as the other underground natural resources, has been introduced as the significant causing of land subsidence and potentially, the earth fissuring. Fissuring is rapidly turning into the nations' major disasters which are responsible for significant economic, social, and environmental damages with devastating consequences. Modeling the earth fissure hazard is particularly important for identifying the vulnerable groundwater areas for the informed water management, and effectively enforce the groundwater recharge policies toward the sustainable conservation plans to preserve existing groundwater resources. Modeling the formation of earth fissures and ultimately prediction of the hazardous areas has been greatly challenged due to the complexity, and the multidisciplinary involved to predict the earth fissures. This paper aims at proposing novel machine learning models for prediction of earth fissuring hazards. The Simulated annealing feature selection (SAFS) method was applied to identify key features, and the generalized linear model (GLM), multivariate adaptive regression splines (MARS), classification and regression tree (CART), random forest (RF), and support vector machine (SVM) have been used for the first time to build the prediction models. Results indicated that all the models had good accuracy (>86%) and precision (>81%) in the prediction of the earth fissure hazard. The GLM model (as a linear model) had the lowest performance, while the RF model was the best model in the modeling process. Sensitivity analysis indicated that the hazardous class in the study area was mainly related to low elevations with characteristics of high groundwater withdrawal, drop in groundwater level, high well density, high road density, low precipitation, and Quaternary sediments distribution.

A novel bias correction framework of TMPA 3B42 daily precipitation data using similarity matrix/homogeneous conditions

Reduction of bias in remotely sensed precipitation products is a major challenge in environment modeling, hydrology, and managing the water resources. Various bias correction techniques are applied to reduce the bias from pixel to gauge data. However, a successful methodology to improve bias correction on the daily scale is often challenging and limited. We present a methodology that can be used to correct the daily bias in remote sensing rainfall data, and to demonstrate the Tropical Rainfall Measuring Mission (TRMM) Multi-satellite Precipitation Analysis (TMPA) 3B42 data was used. The proposed bias correction method is based on the concept of similarity (homogeneous) conditions developed based on the periodicity and different percentile-based precipitation amount, and by identifying the best donor pixel to transfer bias correction factor to a specific ungauged pixel (the receptor pixel) based on the similarity (elevation, latitude, and longitude). Bias correction factors were obtained using the mean bias-removal (MBR) and multiplicative ratio (MR) techniques in the cells of the similarity matrix. The proposed methodology demonstrates a significant removal of bias associated with TMPA 3B42 data sets and it is capable of removing the bias in daily precipitation data on an average by 57% (51%) in the gauged pixels, and 25% (22%) in the ungauged pixels for MBR (MR) method.

Securing IoT-Based RFID Systems: A Robust Authentication Protocol Using Symmetric Cryptography

Despite the many conveniences of Radio Frequency Identification (RFID) systems, the underlying open architecture for communication between the RFID devices may lead to various security threats. Recently, many solutions were proposed to secure RFID systems and many such systems are based on only lightweight primitives, including symmetric encryption, hash functions, and exclusive OR operation. Many solutions based on only lightweight primitives were proved insecure, whereas, due to resource-constrained nature of RFID devices, the public key-based cryptographic solutions are unenviable for RFID systems. Very recently, Gope and Hwang proposed an authentication protocol for RFID systems based on only lightweight primitives and claimed their protocol can withstand all known attacks. However, as per the analysis in this article, their protocol is infeasible and is vulnerable to collision, denial-of-service (DoS), and stolen verifier attacks. This article then presents an improved realistic and lightweight authentication protocol to ensure protection against known attacks. The security of the proposed protocol is formally analyzed using Burrows Abadi-Needham (BAN) logic and under the attack model of automated security verification tool ProVerif. Moreover, the security features are also well analyzed, although informally. The proposed protocol outperforms the competing protocols in terms of security.

Using multi-attribute decision-making approaches in the selection of a hospital management system

The most appropriate organizational software is always a real challenge for managers, especially, the IT directors. The illustration of the term "enterprise software selection", is to purchase, create, or order a software that; first, is best adapted to require of the organization; and second, has suitable price and technical support. Specifying selection criteria and ranking them, is the primary prerequisite for this action. This article provides a method to evaluate, rank, and compare the available enterprise software for choosing the apt one. The prior mentioned method is constituted of three-stage processes. First, the method identifies the organizational requires and assesses them. Second, it selects the best method throughout three possibilities; indoor-production, buying software, and ordering special software for the native use. Third, the method evaluates, compares and ranks the alternative software. The third process uses different methods of multi attribute decision making (MADM), and compares the consequent results. Based on different characteristics of the problem; several methods had been tested, namely, Analytic Hierarchy Process (AHP), Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS), Elimination and Choice Expressing Reality (ELECTURE), and easy weight method. After all, we propose the most practical method for same problems.

Factors Affecting Acceptance of Mobile Library Applications: Structural Equation Model

Acceptance and intention to use mobile applications in a library context is attracting a great deal of interest in education field. A sparse amount of research was conducted in mobile library applications (MLA) previously, investigating the influential factors of intention to use MLA. Research here aims to provide empirical support on acceptance of MLA, library access through mobile applications, with the model developed by taking a technology acceptance model (TAM) in MLA context by adding perceived mobility value, system accessibility and satisfaction for investigating the influence on behavioural intention to use MLA. A self-administrated cross-sectional survey was conducted to collect data from 321 users of MLA in the COMSATS Institute of Information Technology (CIIT) in Islamabad, while a structural equation model (SEM) using analysis of moment structure (AMOS) software was used for examining quantitative data. Results revealed that satisfaction and perceived ease of use are direct significant predictors of intention to use MLA, whereas system accessibility was influenced by the perceived ease of use. However, the perceived mobility value shows a weak effect on intention to use MLA in terms of perceived usefulness. Results serve as a guide for effective decision-making in development and resource allocation to ensure the success of the library’s vision and mission.

A hybrid approach for phishing web site detection

Purpose

This paper aims to present a hybrid approach based on classification algorithms that was capable of identifying different types of phishing pages. In this approach, after eliminating features that do not play an important role in identifying phishing attacks and also after adding the technique of searching page title in the search engine, the capability of identifying journal phishing and phishing pages embedded in legal sites was added to the presented approach in this paper.

Design/methodology/approach

The hybrid approach of this paper for identifying phishing web sites is presented. This approach consists of four basic sections. The action of identifying phishing web sites and journal phishing attacks is performed via selecting two classification algorithms separately. To identify phishing attacks embedded in legal web sites also the method of page title searching is used and then the result is returned. To facilitate identifying phishing pages the black list approach is used along with the proposed approach so that the operation of identifying phishing web sites can be performed more accurately, and, finally, by using a decision table, it is judged that the intended web site is phishing or legal.

Findings

In this paper, a hybrid approach based on classification algorithms to identify phishing web sites is presented that has the ability to identify a new type of phishing attack known as journal phishing. The presented approach considers the most used features and adds new features to identify these attacks and to eliminate unused features in the identifying process of these attacks, does not have the problems of previous techniques and can identify journal phishing too.

Originality/value

The major advantage of this technique was considering all of the possible and effective features in identifying phishing attacks and eliminating unused features of previous techniques; also, this technique in comparison with other similar techniques has the ability of identifying journal phishing attacks and phishing pages embedded in legal sites.

DyHAP: Dynamic Hybrid ANFIS-PSO Approach for Predicting Mobile Malware

To deal with the large number of malicious mobile applications (e.g. mobile malware), a number of malware detection systems have been proposed in the literature. In this paper, we propose a hybrid method to find the optimum parameters that can be used to facilitate mobile malware identification. We also present a multi agent system architecture comprising three system agents (i.e. sniffer, extraction and selection agent) to capture and manage the pcap file for data preparation phase. In our hybrid approach, we combine an adaptive neuro fuzzy inference system (ANFIS) and particle swarm optimization (PSO). Evaluations using data captured on a real-world Android device and the MalGenome dataset demonstrate the effectiveness of our approach, in comparison to two hybrid optimization methods which are differential evolution (ANFIS-DE) and ant colony optimization (ANFIS-ACO).

Forecasting of Underactuated Robotic Finger Contact Forces by Support Vector Regression Methodology

Robotic manipulators have very strong nonlinearities. Analytical modeling of the robotic gripper is very challenging task. Therefore in this paper soft computing methods is applied in order to estimate contact forces of the robotic finger. Support vector regression (SVR) with radial and polynomial basis functions and the soft computing methods were used. The primary purpose of this study are in clarification of kinetostatic examining of a new finger mechanism utilizing pseudo-unbending body model. The results show the better prediction accuracy with SVR methodology with radial basis function (RBF).

Adaptive Neuro-Fuzzy Determination of the Effect of Experimental Parameters on Vehicle Agent Speed Relative to Vehicle Intruder

Intelligent Transportation Systems rely on understanding, predicting and affecting the interactions between vehicles. The goal of this paper is to choose a small subset from the larger set so that the resulting regression model is simple, yet have good predictive ability for Vehicle agent speed relative to Vehicle intruder. The method of ANFIS (adaptive neuro fuzzy inference system) was applied to the data resulting from these measurements. The ANFIS process for variable selection was implemented in order to detect the predominant variables affecting the prediction of agent speed relative to intruder. This process includes several ways to discover a subset of the total set of recorded parameters, showing good predictive capability. The ANFIS network was used to perform a variable search. Then, it was used to determine how 9 parameters (Intruder Front sensors active (boolean), Intruder Rear sensors active (boolean), Agent Front sensors active (boolean), Agent Rear sensors active (boolean), RSSI signal intensity/strength (integer), Elapsed time (in seconds), Distance between Agent and Intruder (m), Angle of Agent relative to Intruder (angle between vehicles °), Altitude difference between Agent and Intruder (m)) influence prediction of agent speed relative to intruder. The results indicated that distance between Vehicle agent and Vehicle intruder (m) and angle of Vehicle agent relative to Vehicle Intruder (angle between vehicles °) is the most influential parameters to Vehicle agent speed relative to Vehicle intruder.

A Lightweight Radio Propagation Model for Vehicular Communication in Road Tunnels

Radio propagation models (RPMs) are generally employed in Vehicular Ad Hoc Networks (VANETs) to predict path loss in multiple operating environments (e.g. modern road infrastructure such as flyovers, underpasses and road tunnels). For example, different RPMs have been developed to predict propagation behaviour in road tunnels. However, most existing RPMs for road tunnels are computationally complex and are based on field measurements in frequency band not suitable for VANET deployment. Furthermore, in tunnel applications, consequences of moving radio obstacles, such as large buses and delivery trucks, are generally not considered in existing RPMs. This paper proposes a computationally inexpensive RPM with minimal set of parameters to predict path loss in an acceptable range for road tunnels. The proposed RPM utilizes geometric properties of the tunnel, such as height and width along with the distance between sender and receiver, to predict the path loss. The proposed RPM also considers the additional attenuation caused by the moving radio obstacles in road tunnels, while requiring a negligible overhead in terms of computational complexity. To demonstrate the utility of our proposed RPM, we conduct a comparative summary and evaluate its performance. Specifically, an extensive data gathering campaign is carried out in order to evaluate the proposed RPM. The field measurements use the 5 GHz frequency band, which is suitable for vehicular communication. The results demonstrate that a close match exists between the predicted values and measured values of path loss. In particular, an average accuracy of 94% is found with R2 = 0.86.

Impact of multi-task on symptomatic patient affected by chronical vestibular disorders

PURPOSE

After a vestibular deficit some patients may be affected by chronical postural instability. The aim of this study was to identify the emotional and cognitive factors of these symptomatic patients. In particular, the double cognitive task and the anxiety disorder were identified by our patients. Through a retrospective study, 14 patients (65.4 ± 18 years) participated in the experiment.

METHOD

The experimentation consists in the study of the standing position of our patients through the aggregate of the trajectories of the center of pressure (COP) using a force plate device. With the aim of isolating the emotional and cognitive influence, this experimentation was defined in two conditions. In the first one, the patients were asked to maintain their balance without additional tasks. In the second one, the patients were submitted to an additional cognitive arithmetic task. The stabilogram surface, length (the forward and backward displacement distance during deviations in COP), lateral and the antero-posterior deviations were assessed.

RESULTS

Our results showed an increase of postural instability of patients affected by chronical vestibular disorders when submitted to the double task. The patients submitted to the cognitive task present a larger surface of activity in comparison with the free-task one (Wilcoxon test p-value equals p = 0.0453). In addition, their displacements inside this area are more important (p = 0.0338). The COP of all our patients deviated forward in the presence of the double task.

CONCLUSION

The increase in instability during the double cognitive task could be explained by an additional stress caused by the desire to make a success of the cognitive task.

Prediction of ultrasonic pulse velocity for enhanced peat bricks using adaptive neuro-fuzzy methodology

Ultrasonic pulse velocity is affected by defects in material structure. This study applied soft computing techniques to predict the ultrasonic pulse velocity for various peats and cement content mixtures for several curing periods. First, this investigation constructed a process to simulate the ultrasonic pulse velocity with adaptive neuro-fuzzy inference system. Then, an ANFIS network with neurons was developed. The input and output layers consisted of four and one neurons, respectively. The four inputs were cement, peat, sand content (%) and curing period (days). The simulation results showed efficient performance of the proposed system. The ANFIS and experimental results were compared through the coefficient of determination and root-mean-square error. In conclusion, use of ANFIS network enhances prediction and generation of strength. The simulation results confirmed the effectiveness of the suggested strategies.

RAIRS2 a new expert system for diagnosing tuberculosis with real-world tournament selection mechanism inside artificial immune recognition system

Tuberculosis is a major global health problem that has been ranked as the second leading cause of death from an infectious disease worldwide, after the human immunodeficiency virus. Diagnosis based on cultured specimens is the reference standard; however, results take weeks to obtain. Slow and insensitive diagnostic methods hampered the global control of tuberculosis, and scientists are looking for early detection strategies, which remain the foundation of tuberculosis control. Consequently, there is a need to develop an expert system that helps medical professionals to accurately diagnose the disease. The objective of this study is to diagnose tuberculosis using a machine learning method. Artificial immune recognition system (AIRS) has been used successfully for diagnosing various diseases. However, little effort has been undertaken to improve its classification accuracy. In order to increase the classification accuracy, this study introduces a new hybrid system that incorporates real tournament selection mechanism into the AIRS. This mechanism is used to control the population size of the model and to overcome the existing selection pressure. Patient epacris reports obtained from the Pasteur laboratory in northern Iran were used as the benchmark data set. The sample consisted of 175 records, from which 114 (65 %) were positive for TB, and the remaining 61 (35 %) were negative. The classification performance was measured through tenfold cross-validation, root-mean-square error, sensitivity, and specificity. With an accuracy of 100 %, RMSE of 0, sensitivity of 100 %, and specificity of 100 %, the proposed method was able to successfully classify tuberculosis cases. In addition, the proposed method is comparable with top classifiers used in this research.

Diagnosing tuberculosis with a novel support vector machine-based artificial immune recognition system

Background:

Tuberculosis (TB) is a major global health problem, which has been ranked as the second leading cause of death from an infectious disease worldwide. Diagnosis based on cultured specimens is the reference standard, however results take weeks to process. Scientists are looking for early detection strategies, which remain the cornerstone of tuberculosis control. Consequently there is a need to develop an expert system that helps medical professionals to accurately and quickly diagnose the disease. Artificial Immune Recognition System (AIRS) has been used successfully for diagnosing various diseases. However, little effort has been undertaken to improve its classification accuracy.

Objectives:

In order to increase the classification accuracy of AIRS, this study introduces a new hybrid system that incorporates a support vector machine into AIRS for diagnosing tuberculosis.

Patients and Methods:

Patient epacris reports obtained from the Pasteur laboratory of Iran were used as the benchmark data set, with the sample size of 175 (114 positive samples for TB and 60 samples in the negative group). The strategy of this study was to ensure representativeness, thus it was important to have an adequate number of instances for both TB and non-TB cases. The classification performance was measured through 10-fold cross-validation, Root Mean Squared Error (RMSE), sensitivity and specificity, Youden’s Index, and Area Under the Curve (AUC). Statistical analysis was done using the Waikato Environment for Knowledge Analysis (WEKA), a machine learning program for windows.

Results:

With an accuracy of 100%, sensitivity of 100%, specificity of 100%, Youden’s Index of 1, Area Under the Curve of 1, and RMSE of 0, the proposed method was able to successfully classify tuberculosis patients.

Conclusions:

There have been many researches that aimed at diagnosing tuberculosis faster and more accurately. Our results described a model for diagnosing tuberculosis with 100% sensitivity and 100% specificity. This model can be used as an additional tool for experts in medicine to diagnose TBC more accurately and quickly.

A systematic review of approaches to assessing cybersecurity awareness

Purpose

– The purpose of this paper is to survey, explore and inform researchers about the previous methodologies applied, target audience and coverage of previous assessment of cybersecurity awareness by capturing, summarizing, synthesizing and critically comment on it. It is also conducted to identify the gaps in the cybersecurity awareness assessment research which warrants the future work.

Design/methodology/approach

– The authors used a systematic literature review technique to search the relevant online databases by using pre-defined keywords. The authors limited the search to retrieve only English language academic articles published from 2005 to 2014. Relevant information was extracted from the retrieved articles, and the ensuing discussion centres on providing the answers to the research questions.

Findings

– From the online searches, 23 studies that matched the search criteria were retrieved, and the information extracted from each study includes the authors, publication year, assessment method used, target audiences, coverage of assessment and assessment goals.

Originality/value

– The review of the retrieved articles indicates that no previous research was conducted in the assessment of the cybersecurity awareness using a programme evaluation technique. It was also found that few studies focused on youngsters and on the issue of safeguarding personal information.

Support vector machine firefly algorithm based optimization of lens system

Lens system design is an important factor in image quality. The main aspect of the lens system design methodology is the optimization procedure. Since optimization is a complex, nonlinear task, soft computing optimization algorithms can be used. There are many tools that can be employed to measure optical performance, but the spot diagram is the most useful. The spot diagram gives an indication of the image of a point object. In this paper, the spot size radius is considered an optimization criterion. Intelligent soft computing scheme support vector machines (SVMs) coupled with the firefly algorithm (FFA) are implemented. The performance of the proposed estimators is confirmed with the simulation results. The result of the proposed SVM-FFA model has been compared with support vector regression (SVR), artificial neural networks, and generic programming methods. The results show that the SVM-FFA model performs more accurately than the other methodologies. Therefore, SVM-FFA can be used as an efficient soft computing technique in the optimization of lens system designs.