Jacek M. Czerniak

Heuristic algorithm for interpretation of multi-valued attributes in similarity-based fuzzy relational databases

In this work, we are presenting implementation details and extended scalability tests of the heuristic algorithm, which we had used in the past [1,2] to discover knowledge from multi-valued data entries stored in similarity-based fuzzy relational databases. The multi-valued symbolic descriptors, characterizing individual attributes of database records, are commonly used in similarity-based fuzzy databases to reflect uncertainty about the recorded observation. In this paper, we present an algorithm, which we developed to precisely interpret such non-atomic values and to transfer the fuzzy database tuples to the forms acceptable for many regular (i.e. atomic values based) data mining algorithms.

Evolutionary Approach to Data Discretization for Rough Sets Theory

This article presents the LDGen method which is based on genetic algorithm. The author proposed evolutionary approach to the solution of the discretization problem for systems that induce rules on the basis of rough sets theory. The study describes details of the method with special focus on the crossing operator. The proposed approach concerns working with multidimensional samples. Thanks to application of the authors own method of for visualizing multidimensionality, i.e. so called Pipes of Samples, it was possible to visualize up to 360 dimensions, which is usually sufficient in case of problems the Rough Sets Theory deals with. Mutation and crossing methods were developed using this visualisation so that, for real numbers, it allowed to create individuals that describe one solution of the discretization. Hence the population is a set of many complete discretizations of all the attributes.

Representation of a trend in OFN during fuzzy observance of the water level from the Crisis control center

This paper presents the issue of fuzzy arithmetic calculations in two different notations. The well-known L-R notation proposed by Dubois-Prade, which enjoys a well-earned recognition of the researchers dealing with fuzzy logic was presented on one hand. On the other hand, a OFN notation introduced by Kosiński was discussed. Comparative calculations were performed using the data of the benchmark “Dam and Crisis control center paradox”. That benchmark is available in two versions, where the opposite trend is visible at the dam and at the CCC (Crisis control center). In one of the versions, the water level at the observed area decreases and increases at the dam, while in the other version the situation is opposite. The trend difference detection can aid the short-term forecast of the situation change at the monitored area. Results of the applied calculations in OFN notation show that this arithmetic is sensitive to trend differences related to the order characteristic for those numbers. Relationship between the fuzzy logic and the trend of the observed phenomena is an added value to the generalization of OFN and it is also a good signal for the future development of applications of such fuzzy calculations, being their unique feature at the same time.

Quality of Services Method as a DDoS Protection Tool

Presently, one of the main problems of computer networks are Distributed Denial of Service attacks which can block network re- sources like servers. In order to prevent such situations some mecha- nisms are needed. This paper gives an overview of the Quality of Services methods. A DDoS attack model is described for development purposes. In conslusion some new QoS features are presented. According to pre- sented features QoS method could be used as a protection tool against DDoS attack which is also proven in this paper. The ability to implement the proposed QoS features has already been partially tested. Presented results suggest that the method could be applied widely in practice.

Approach to Solve a Criteria Problem of the ABC Algorithm Used to the WBDP Multicriteria Optimization

This article describes the use of the bees algorithm for optimization of the multi-object structure of a welded beam. This problem has been used as a benchmark of the bees algorithm. This article presents an approach to improve the ABC algorithm criteria used for the WBDP multicriteria optimization. The contents of the article show the analysis of the problem, conducted based on the mathematical calculations of the beam dimensions. The further part constitutes a comparison of the received results with the results of the ABC operation. Based on the standards, an additional criterion was established, which verifies the correctness of the results.

Proposed CAEva Simulation Method for Evacuation of People from a Buildings on Fire

This paper presents practical applications of the cellular automata theory for building fire simulation using the CAEva method. Thanks to the tests carried out using appropriately configured program, realistic results of simulated evacuation of people from the building have been achieved. The paper includes the references to actual fire disasters and provides numbers of their resulting casualties. Using such a kind of predication in civil engineering should increase the fire safety of buildings. Simulations described in this paper seem to be very useful, particularly in case of building renovation or temporary unavailability of escape routes. Using them, it is possible to visualize potential hazards and to avoid increased risk in case of fire. Inappropriate operation of buildings, including insouciant planning of renovations are among frequent reasons of tragic accidents cited by fire brigade information services. Similar problems are encountered by inspectors who assess spontaneous fire accidents or arsons during mas events, where wrong safety procedures or inappropriate attempts to cut costs resulted in tragedy. Thanks to the proposed solutions it shall be easier to envisage consequences of problematic decisions causing temporary or permanent unavailability of escape routes. This is exactly the problem analyzed by this paper. It does not take into account, by the rule, the influence of \(\mathrm{CO}_{2}\) and other gases on evacuation difficulty. The described method has been analyzed using descriptions of real life fires, the participants of which were neither asleep nor asphyxiated with carbon monoxide, while the escape was hindered by fire, room layout as well as stress and number of the event participants. The results achieved for such conditions are approximate to the actual (reallife) outcomes, which proved the method to be correct.

Practical Application of OFN Arithmetics in a Crisis Control Center Monitoring

In this paper there is a comparision of fuzzy arithmetic calculations in two different notations. The first is well-known L-R notation proposed by Dubois-Prade. It is well known for the researchers who deal with fuzzy logic. The second if OFN notation. This notation was introduced by Kosinski. The same data was used for comparative calculations using the benchmark “Dam and Crisis control center paradox”. There was an observation of water level at the dam with two trends: when the water level increases and decreases. This could cause the different short-term forecast for mentioned situation. The result which was achieved using two different fuzzy arithmetic showed, that OFN notation is sensitive to the trend differences. The authors showed that it provides an extra value which is a relationship between the fuzzy logic and the trend of the observer phenomena.

Optimization of Fuel Consumption in Firefighting Water Capsule Flights of a Helicopter

This article presents a possible use of ABC method for optimization of fuel consumption of helicopter which transport water capsule. There are lot of attibutes of flight e.g. the mass of the capsule, velocity, altitude, aerodynamic coefficients of the capsule, and horizontal and vertical winds. The presented method is focused on mentioned attributes. The problem is very important because helicopters are used in real hughe fire and it will be quite good if the fueal needed for this will be as low as possible. That is why authors presents theoretical models of flight of a bag filled with water which is then dropped from an aircraft moving horizontally. The resulet achived by numerical computations are later compared with the results measured for the trajectory of a capsule of water dropped from a helicopter. There ia also a discussion of the experimental and numerical results achieved in mentioned experiment.

AAO as a new strategy in modeling and simulation of constructional problems optimization

Abstract The article presents a new multi-criteria optimization method called Artificial Acari Optimization (AAO). AAO method was tested with five well-known benchmark structural problems i.e.: welded beam, pressure vessel, speed reducer, spring design and gear train problem. The results were compared on other representatives of Swarm Intelligence mainstream which are bee algorithms MBO, BCO and ABC. Numerous references show dominance of ABC over MBO and BCO. To check this, a detailed comparisons of AAO results were made and introduced together with the results of the ABC algorithm.

Artificial Acari Optimization as a new strategy for global optimization of multimodal functions

Abstract In the article, the authors present the application of new optimization methods called Artificial Acari Optimization (AAO) and analyze it with other known algorithms for specific groups of benchmarks. The authors were inspired by the social behavior of Acari (mites) creating a strategy for herd searching for solutions. In the article results obtained for AAO were compared with other algorithms belonging to swarm intelligence: particle swarm optimization (PSO), glowworm swarm based optimization algorithm (GSO) and artificial bee colony (ABC). In a benchmark test four functions often used in testing methods of optimization were applied. These functions include: Ackley – with a relatively uniform surface, having tens of local minimums and one global maximum with a much lower value than most of the local minimums; Sphere with a single plane, having just one minimum; Easom characterized by a constant plane over overwhelming majority of domain with only one steep minimum, and Eggholder function with uneven surface having dozens of local minimums, where local minimums are close to the value of the only one global minimum.