Cornel Barna

Visual analysis of geospatial habitat suitability model based on inverse distance weighting with paired comparison analysis.

Geospatial data analytical model is developed in this paper to model the spatial suitability of malaria outbreak in Vellore, Tamil Nadu, India. In general, Disease control strategies are only the spatial information like landscape, weather and climate, but also spatially explicit information like socioeconomic variable, population density, behavior and natural habits of the people. The spatial multi-criteria decision analysis approach combines the multi-criteria decision analysis and geographic information system (GIS) to model the spatially explicit and implicit information and to make a practical decision under different scenarios and different environment. Malaria is one of the emerging diseases worldwide; the cause of malaria is weather & climate condition of the study area. The climate condition is often called as spatially implicit information, traditional decision-making models do not use the spatially implicit information it most often uses spatially explicit information such as socio-economic, natural habits of the people. There is need to develop an integrated approach that consists of spatially implicit and explicit information. The proposed approach is used to identity an effective control strategy that prevents and control of malaria. Inverse Distance Weighting (IDW) is a type of deterministic method used in this paper to assign the weight values based on the neighborhood locations. ArcGIS software is used to develop the geospatial habitat suitability model.

Optimization of Non-rigid Demons Registration Using Cuckoo Search Algorithm

Video processing including registration has a significant role in surveillance and real-time applications. Image registration is considered a compulsory step in video registration for numerous aspects. One of the major challenges in image registration is to determine the optimal parameters during the registration process. Bio-inspired computational including natural and artificial cognitive systems can be employed to define the optimal solutions. The present work proposed a comprehensive automatic non-rigid video set registration algorithm using Demons algorithm. For optimal velocity smoothing kernels, the demons registration is optimized using cuckoo search (CS) algorithm, where there are no previous studies that have optimized demons algorithm using CS algorithm. A comparison between the CS algorithm and the particle swarm optimization (PSO)-based demons registration is conducted to evaluate the proposed system performance. Thus, the correlation coefficient is taken as a fitness function. The obtained results using CS show a minor increment of the optimized fitness value compared to PSO-based framework value. The proposed CS-based approach reports faster convergence rate than the PSO-based approach.

The Constant Effort Imposed Distance Braking for Urban Railway Vehicles

The paper presents an imposed distance braking method for urban railway vehicles, free of external devices and maintaining a constant braking effort thanks to a position controller. Its application improves the comfort and the traffic safety and reduces the weariness of the material and the perturbations injected into the electric power network

Predicting Ozone Layer Concentration Using Multivariate Adaptive Regression Splines, Random Forest and Classification and Regression Tree

Air pollution is one of the major environmental worries in recent time. Abrupt increase in the concentration of any gas leads to air pollution. The cities are mostly affected due to the abundance of population there. One of the worst gaseous pollutants is OZONE (O3). In this paper, we propose three predictive models for estimation of concentration of ozone gases in the air which are Random Forest, Multivariate Adaptive Regression Splines and Classification and Regression Tree. Evaluation of the prediction models indicates that the Multivariate Adaptive Regression Splines model describes the dataset better and has achieved significantly better prediction accuracy as compared to the Random Forest and Classification and Regression Tree. A detailed comparative study has been carried out on the performances of Random Forest, Multivariate Adaptive Regression Splines and Classification and Regression Tree. MARS gives the result by considering less variables as compared to other two. Moreover, Random Forest takes a little more time for building the tree as the elapsed time was calculated to 45 s in this case. In addition, variable importance for each model has been predicted. Observing all the graphs Multivariate Adaptive Regression Splines gives the closest curve of both train and test set when compared. It can be concluded that multivariate adaptive regression splines can be a valuable tool in predicting ozone for future.

Object labeling method using uncertainty measurement

In the article is presented a new method of object labeling, based on the uncertainty measurement of a fuzzy similarity. The labeling is performed on objects detected in a scene, based on information provided by a set of different sensors. First is computed the fuzzy similarity between the detected object and a rough set of possible prototypes, followed by a measurement of the uncertainty induced by the observation. For all these results obtained from each sensor, is computed the global uncertainty corresponding to the most likely label. If we have a time stream observations about the scene and the objects or the sensor system is moving, it can be improve the labeling process by suppressing the inconsistent observations and making new labeling determinations. In this last process are used different prototypes, corresponding to different observation distances and positions. Also, from this observations performed in a time frame, it can be analyzed the uncertainty variation, determined by the switch from one prototype to another.

Automatic Generation Control of an interconnected multi-area reheat thermal power systems with conventional proportional-integral controller considering various performance indices

This paper presents the analysis of Automatic Generation Control (AGC)/Load Frequency Control (LFC) of conventional three area interconnected thermal power systems. The current study considered suitable Generation Rate Constraints (GRC), reheat and non-reheat turbine. Optimum gain settings of the conventional controllers are obtained, both in the constraints and non-constraints modes using with three different performance indices. Dynamic performance of the system is analyzed considering one percent of step load disturbance is in either area of the system. Furthermore, time domain specification analysis is used for the system performance evaluation. The analysis established that Integral Time Absolute Error (ITAE) based conventional controllers yield better controlled response and good dynamic performance compared to other indices.

Spam Email Detection Using Deep Support Vector Machine, Support Vector Machine and Artificial Neural Network

Emails are a very important part of our life today for information sharing. It is used for both personal communication as well as business purposes. But the internet also opens up the prospect of an enormous amount of junk and useless information which overwhelms and irritates us. These unnecessary and unsolicited emails are what comprise of spam. This study presents the application of a classification model to classify spam emails from using a model- Deep Support Vector Machine (Deep SVM). Moreover, other classifier models like Support Vector Machine (SVM), Artificial Neural Network models have also been implemented to compare the performance of proposed Deep SVM model. Furthermore analysis has been done to compare all the performances using available numerical statistics obtained from these models to find the best model for the purpose. Spam filtering is a very essential feature in most email services and thus effective spam classification models are pertinent to the current digital communication scenario and various work has been done in this area.

Prediction of Customer Satisfaction Using Naive Bayes, MultiClass Classifier, K-Star and IBK

Customer satisfaction is an important term in business as well as marketing as it surely indicates how well the customer expectations have been met with by the product or the service. Thus a good prediction model for customer satisfaction can help any organization make better decisions with respect to its services and work in a more informed matter to improvise on the same. The problem considered in this study is optimization of customer satisfaction for the customers of San Francisco International Airport. This paper adopts three classification models Naive Bayes, MultiClass Classifier, K-Star and IBK as potential classifiers for prediction of customer satisfaction. The customer satisfaction depends on various factors. The factors which we consider are the user ratings for artwork and exhibitions, restaurants, variety stores, concessions, signage, directions inside SFO, information booths near baggage claim and departure, Wi-Fi, parking facilities, walkways, air train and an overall rating for the airport services. The ratings are obtained from a detailed customer survey conducted by the mentioned airport in 2015. The original survey focused on questions including airlines, destination airport, delays of flights, conveyance to and from the airport, security/immigration etc. but our study focuses on the previously mentioned questions. Graphs are plotted for actual and predicted values and compared to find the least amount of deviation from the actual values. The model which shows least deviation from actual values is considered optimal for the above mentioned problem.

Some aspects about 3D objects recognition and distance approximation

The present work approaches some important issues from image processing such as object recognition and distance estimations of different objects from the environment. As we know image processing deals with endowing computers with visual functions. Until now the capabilities of similar systems were limited to object recognition and to avoid obstacles. We have tried to combine those two capabilities into one system. In this application fuzzy techniques for controlling the luminosity of the image and some new filtering methods were addressed.