automatica
V. Ruykova. Generalized Predictive Control with Disturbance Compensation for Time-delay Processes

Key Words: Generalized predictive controller; disturbance compensation; time-delay; Diophantine equation.

Abstract. The aim of this paper is to design predictive algorithm for control of time-delayed systems with the possibility of measurable disturbance compensation. A new approach to extended Generalized Predictive Control (GPC) has been proposed. Three Diophantine equations are solved non recursively. The cost function and the control law of the GPC are derived. Simulation examples are presented to show results of the design. Two cases are considered – in case of delay between the input and the output of the process, less than the delay, between the disturbance and the output of the process, and in case of delay between the input and the output of the process, greater than the delay between the disturbance and the output of the process. In both cases, comparisons were made between a standard GPC, a compensator with future interference values included in the GPC, a compensator without future interference values included in the GPC and a classic compensator for one case. The results show that the GPC cannot completely eliminate the disturbances, even when the future disturbances values are included in the control. Complete elimination of the disturbances is possible only when the weighting factor, that distributes the energy of the controller, is zero.

Read More

automatica
M. Petrov. Multiple Objective Optimisation for the Ethanol Production from Strain Saccharomyces sereviciae

Key Words: Multiple objective optimisation; ethanol production; Saccharomyces sereviciae; general multiple objective optimisation; fuzzy optimisation; fuzzy multiple-objective optimisation.

Abstract. A fuzzy procedure is applied in order to find the optimal feed policy of a fed-batch fermentation process for ethanol production using a Saccharomyces serevicieae. The policy consists in feed flow rate, feed concentration, and fermentation time. In this study biotechnological process is formulated as a general multiple objective optimisation problem. By using an assigned membership function for each of the objectives, the general multiple objective optimisation problem can be converted into a maximizing decision problem. In order to obtain a global solution, a method of fuzzy sets theory is introduced to solve the maximizing decision problem. After this multiple optimisation, the useful product quality is raised and the residual substrate concentration is decreased at the end of the process. Thus, the process productiveness is increased.

Read More

automatica
S. Miteva, D. Popov. Integration of Cryobattery into Conventional Energy Conversion System

Key Words: Liquid air; energy storage; regenerative steam cycle; feed water; waste heat.

Abstract. The aim of the present study is to evaluate an option of integration of liquid air energy storage (LAES) into regenerative steam turbine cycle. The waste heat from LAES discharge is used for feed water preheating. Thermodynamic analysis shows that the newly proposed hybrid LAES system has a round-trip efficiency of 16% higher than the standalone LAES.

Read More

informatics
Zh. Zhejnov, J. Urumov. Modeling the Influence of Deformation on Bragg Fibers Losses

Key Words: Bragg fiber; bending; losses; Photonic Crystal Fiber; model of deformation.

Abstract. The article analyzes the losses in one type of Photonic Crystal Fiber – Bragg fiber. It is one-dimensional fiber, made as coaxial cylindrical layers. The fiber cladding is a dielectric mirror realized as a multilayer dielectric coating. The paper proposes a method based on geometric optics for the analysis of light propagation losses in a multilayer microstructured fiber with an air core, as a result of tunneling. A model of M-layer fiber with set refractive indices of the dielectric layers is proposed. The angles of incidence and reflection of the boundaries of each two layers of the fiber cladding according to Snelius’ law are calculated. The transverse reflection coefficients of each boundary between two layers for TM and TE polarization are calculated. The electric fields of the reflected and incident beams are calculated. The magnitudes of these vectors are recursively related to each boundary of the previous and next fiber layer. The input power of the light in the first fiber layer for TE and TM polarization is calculated. The losses from light reflection when it passing through all layers of the fiber as a function of the reflection coefficients are calculated. The normalized attenuation is calculated. The characteristic equation for the optical waveguide is decided. The angles of reflection in different modes are calculated. The distance between two consecutive reflections of the beam is calculated as a function of the reflection coefficients for the different polarizations and the reflection angles of the layers for TE and TM polarizations. They determine the reflection coefficient and the phase change when light passes through the whole fiber. The delays of the rays with TE and TM polarization are obtained. The expressions for the chromatic dispersion of the fiber for TE and TM polarization are then derived. A mathematical model of the deformation, presented as a change in the geometry of the fiber in this section as part of a circle is proposed. For this section of the deformed fiber by geometric transformations the connection between the angles of incidence and reflection in the straight and in the round section of the deformed fiber is calculated. The distance between two consecutive reflections from the fiber boundary surface of the rays trajectory is determined by the number of consecutive reflections in the core of the fiber. The reflection losses in TE and TM polarization, which are proportional to the number of beam reflections, are then determined. The phase delays for beams with TE and TM polarization for a fiber of a certain length are determined as the sum of the individual delays in the reflections of the beams. The proposed mathematical model and algorithm for calculating the attenuation of the fiber for different modes of TE and TM polarization, an example of M-layer PCF fiber with air core and alternating dielectric layers with two alternating coefficients and thicknesses is solved, so as to create at the average wavelength of light a phase shift of 900. A MATLAB program has been written. It simulates the attenuation and dispersion of a fiber with set optical parameters. After solving the characteristic equation for this fiber with the introduced parameters, the normalized attenuations for TE and TM polarization are calculated for fiber with and without deformation for different propagating modes. Calculations have been made for fibers with core radius of 20-200 μm for a light wavelength of 1559 nm. The attenuation and chromatic dispersion graphs for TE and TM polarization of several straight and deformed fibers with the same length and different number of layers were plotted. A conclusion about the influence of the core diameter, the bending radius and the number layers of the fiber cladding on the losses of the different propagated modes is made. A comparison of PCF losses and ordinary quartz single-mode fibers was made. In conclusion, the disadvantage of the proposed method is that only the meridional rays of the propagating light are analyzed and the dielectric losses in the fiber cladding are not taken into account. The advantage of the proposed method is the small computational complexity and the correct qualitative result of the PCF analysis with certain parameters. Guidelines for future development are proposed – analysis of the losses of the fiber, taking into account the non-meridional rays in the fiber. The possibilities for using PCF for information transmission and as dispersion compensators in telecommunications are pointed. The possibility of using the method for optimization of certain parameters of PCF of this kind is proposed.

Read More

intelligent systems
G. Gergov, J. Cruz, E. Kirilova. A Comparative Evaluation of the Predictive Ability of PLS and RBF ANN Calibration Techniques Applied to SW-NIR Meat Data

Key Words: NIR spectroscopy; Partial Least Square method; Radial Basis Functions Neural Networks; moisture content; fat content; pork meat samples.

Abstract. In this study the performance of linear and nonlinear chemometric methods has been investigated and compared. The transmittance spectra of pork meat samples were collected by SW-NIR (short wave near infrared) analyser in the spectral range of 850 nm to 1,050 nm. Partial Least Square (PLS1) method and Radial Basis Functions Neural Networks (RBF NN) were chosen for chemometric analysis of that samples for determination of moisture and fat content. The reason for using RBF ANN is significant nonlinearity which is exhibited between the spectra and the fat and moisture content. PLS1 and RBF NN with different architecture have been combined with different pre-processing techniques such as first derivative (D1), standard normal variate (SNV), multiplicative signal correction (MSC) and the combinations of MSC and SNV with first derivative. It was found that optimal pre-processing was MSC for moisture, and the combination of D1and SNV for fat. When PLS1 was used, results showed reduction of RMSEP and REP using MSC with 15 and 13% for moisture determination. In case of PLS1 fat determination considerable reduction of RMSEP and REP was observed using a combination of D1 and SNV with 48 and 47%. Compared to PLS1 regression with suitable preprocessing, RBF ANN showed better results: reduction of RMSEP and REP using a combination of D1 and SNV with 48% for moisture, and reduction using a combination of D1 and SNV with 59% for fat determination. These improvements together with the facility of SW-NIR technology to be implemented in the process engineering made it ideal for the meat industry.

Read More

intelligent systems
G. Kolev, E. Koleva. Integrated Smart Home System

Key Words: Internet of Things; Wireless Sensor Network; smart home; integration; voice assistant.

Abstract. An integrated Smart Home system for monitoring and management of the elements of the working environment or at home in Home Assistant platform and is integrated with a voice assistant (Google Assistant) has been developed. The structure of the Smart Home (SH) system is based on the concept of the Internet of Things (IoT), which includes connectivity of devices and actuators, as well as the presence of Wireless Sensor Network (WSN). The main functions in each SH depend strongly on the requirements, way of live, special health issues, availability of pets and appliances etc. of the household members, as well as the home/house architecture, location etc. The developed integrated system structure consists of the following main modules: connected devices, measuring (sensor) module, processing module, visualization module (interface), communication module (voice communication). The system allows monitoring and control of various parameters of the environment, determination of geolocation, tracking the state of the connected devices, provides ascertainment of conditions or constraints during the implementation of logical algorithms or actions, etc. The developed integrated system solves the problem of using various interface applications, communication protocols and standards by integration of all its elements in one Application Programming Interface (API) and simultaneously the system is expanding its scope through its integration with a voice assistant (Google Assistant). In the developed integrated system solutions with pre-set functions, default functions and user selection functions are implemented. Also, specially designed by the author (G. Kolev), made and tested IoT boards for stepper motor control, RGB LED strip, as well as IoT board for control of small relays for concealed mounting are applied. The system operation rules can be set by the user (directly or in time) or depending on the values obtained from the sensors (Sensor-based Linked Open Rules). The developed SH system gives also the possibility for building actions according to the geolocation of each of the devices (users) via the GPS system of the phone. Elements, connected with the energy utilization (consumption) efficiency – electricity, water and heat consumption efficiency are also considered. The optimization of the consumption is directly connected with cost savings which adds an additional benefit to the undeniable advantages of the Smart Home system development. The process of development of integrated remote-control Smart Home systems can continue without limitation in time as far as the imagination of the designer and/or the users reaches.

Read More

automatica
M. Hadjiski. Мutual Penetration and Enrichment as a Bilateral Accelerating Factor for the Development of Machine Learning and Automation

Key Words: Artificial intelligence; control theory; deep learning; industrial automation; machine learning; reinforcement learning.

Abstract. The study shows that the existence of fundamental similarities between control theory and machine learning is a real basis for productive interpenetration and enrichment with new concepts, methods and tools, which are mutually beneficial for overcoming a number of serious modern challenges such as the control of complex and autonomous systems, cybersecurity, intelligent robotics, bioautomatics. The continuous development of the control theory as a result of its own progress and under the influence of the ideas of artificial intelligence will not allow the transformation of automation into a routine engineering discipline. In turn, the systems based on artificial intelligence and machine learning are enriched with well-developed methods and procedures from the control theory in order to improve and create new algorithms and to ensure a higher speed, robust stability and optimality of the learning process. Industrial automation systems will absorb the innovative results of the interpenetrating development of artificial intelligence and control theory improving both the quality and scope, safety and security of operations.

Read More

automatica
M. Petrov. Optimisation of Biotechnological Processes through Combined Algorithm

Key Words: Fuzzy sets theory; random search with back step; combined algorithm; initial condition.

Abstract. A combined algorithm for optimisation of biotechnological processes has been developed. The algorithm includes a random search method for an optimal choice of an initial point and a method based of the fuzzy sets theory. Combining both methods overcomes а major disadvantage of the fuzzy optimisation method, connected with a determination of large scale problems. The combined algorithm has been successfully applied for optimisation of the initial condition and optimal control of the biotransformation process of whey fermentation by а strain Kluyveromyces lactis MC5.

Read More

informatics
R. Ivanov. Automatic Beacon Deployment for Indoor Localization

Key Words: Beacon deployment; indoor localization; Indoor Positioning Systems.

Abstract. Localization of visitors in public buildings is a key technology to create accessible environments using location-based services. The usability of these services and the satisfaction of their clients depend on the accurate calculation of the position of visitors. This is most often realized using wireless sensor networks. The localization accuracy depends on a number of factors, one of which is the deployment of the sensor nodes. This is a complex task, which is most often realized by experts. In this article, we offer a complete solution for creating systems for indoor localization, which includes: (1) Algorithm for fast partitioning of the building components into non-overlapping rectangles; (2) Algorithm for sensor nodes deployment based on the geometry of the rectangles obtained; and (3) Algorithm for optimizing the sensor nodes placement taking into account the connectivity between the building components (rooms and corridors), as well as the static objects, which are obstacles for radio signals. Numerous experiments have been implemented in stimulating and real environments, which prove the applicability of the proposed solution.

Read More

informatics
P. Vasilev, V. Sindrakovska. Relations between Standards IEC/EN 62264 and RAMI 4.0

Key Words: RAMI 4.0; IEC/EN 62264; asset; communication and presentation capabilities; activity; scheduling; model; web services; B2MML.

Abstract. The Reference Architectural Model for Industry (RAMI) 4.0 tends to unify the efforts for rapid development of new technologies of the information and communication technology sector by stating definitions of an asset and its role in the cyber-physical world with the use of presentation and communication functions applied to the asset. Furthermore, the standard describes how an asset should interact with the cyber-physical world. In order to introduce the asset as a conceptual fundament, the standard RAMI 4.0 extends the Equipment hierarchy model of another standard – IEC/EN 62264, which is well known and applied as an architectural framework within software integration projects of various information systems. The differences between, are that in IEC/EN 62264, a physical asset model corresponds to the equipment model, whereas the RAMI 4.0 states that an asset may present even a Product or Connected World (Cyber-Physical World). The introduced extension is necessary because th perspective of the two standards is different. IEC/EN 62264 defines objects and models for integration, in which a Product, as an abstraction of “what should be made?” is a part of Product Definition Model (Operations Definition Model), and when it is physically performed “what is actually made?”, it is a part of Material Model. As such, the objects “carrying” the integration information are different. The Connected world also is an asset in RAMI 4.0, because it has value for a company, while the whole subject of the IEC/EN 62264 standard is to integrate information systems, thus achieving “Connected World”. This is why the standard IEC/EN 62264 should be considered as a “roadmap” for the cyber-physical transformation of the RAMI 4.0 standard. The aim of the article is to discuss the importance and the assumption of non-implicit relations between the two standards as well as the concept for development of RAMI 4.0 administration shell based on IEC/EN 62264 architecture.

Read More

informatics
R. Kaltenborn. Integration in Educational Systems Extended with Artificial Intelligence – Based Technologies

Key Words: Artificial intelligence; intelligent learning system; integration; learning technologies; optimization; system of systems.

Abstract. The main problems related to the integration of diverse functional elements of advanced intelligent learning systems are considered. It is shown that the integration of the elements in the learning process is a complex multilayered process due to the great variety and complexity of the ongoing basic processes – cognitive, pedagogical, technological, social and interpersonal. It is emphasized that the need for the integration process to be solved as a multifactor optimization data-driven problem and the use of modern techniques in the field of artificial intelligence – machine learning, pattern recognition, natural language processes, network management.

Read More

automatica
N. Deliiski, D. Angelski. Computation of the Processing Medium Temperature during Autoclave Steaming of Non-frozen Wooden Prisms

Кey Words: Wooden prisms; veneer production; autoclave steaming; 2D model; processing medium temperature; energy consumption; heat balance; loading level of autoclave; moisture content of prisms.

Abstract. A methodology for computation of the processing medium temperature and connected with it energy consumption and heat fluxes during autoclave steaming of non-frozen ooden prisms for veneer production at limited heat power of the steam generator, depending on the dimensions of the prisms cross section, wood moisture content, and loading level of the autoclave has been suggested.
The methodology is based on the use of two personal mathematical models: 2D non-linear model of the temperature distribution in subjected to steaming non-frozen prismatic wood materials and model of the non-stationary heat balance of autoclaves for steaming wood materials. The heat balance of the autoclaves consist of following components: energy used for heating of the subjected to teaming wood materials, energy used for heating of the body of the autoclave and of the situated in it metal trolleys for positioning of the wood materials, energy used for heating of the insulating layer of the autoclave, energy used for covering of the heat emission from the autoclave in the surrounding air, energy used for filling in with steam the free (unoccupied by wood materials) part of the working volume of the autoclave and energy, which is accumulated in the gathered in the lower part of the autoclave condense water. For numerical solving of the models and practical application of the suggested methodology, a software package was prepared in the calculation environment of Visual FORTRAN Professional developed by Microsoft. Using this package computations and research of the non-stationary change of the processing medium temperature in an autoclave with a diameter of 2.4 m, length of its cylindrical part of 9.0 m and loading level of 40, 50, and 60% at a limited heat power of the steam generator, equal to 500 kW during the initial part of the steaming process in it of beech prisms with cross-section dimensions of 0.3 × 0.3 m, 0.4 × 0.4 m, and 0.5 × 0.5 m, initial temperature of 0 °C, basic density of 560 kg·m-3, moisture content of 0.4, 0.6, and 0.8 kg·kg-1 have been carried out. Simultaneously with this the heat fluxes and energy consumption required for the heating of the prisms and for the whole steaming process in the autoclave have been calculated. The suggested methodology can be used for the computation and model based automatic realization of energy efficient optimized regimes for autoclave steaming of different wood materials

Read More

informatics
P. Petrov, G. Kostadinov, P. Zhivkov, V. Velichkova, T. Balabanov. Approximated Sequences Reconstruction with Genetic Algorithms

Кey Words: Reconstruction; sequencing; genetic algorithms.

Abstract. Sequences reconstruction is a problem often met in many research areas. The core of this problem is how to recreate a full sequence of ordered information when only chunks of it are known.
Sequence reconstruction is applied in fields like genetics, cryptography and encoding. In this research, an approximate reconstruction of sequences is proposed, which is applied in the gambling industry for reverse engineering of slot machine virtual reels. The importance of this problem is related to the control of gambling games parameters by law regulators. The problem in this research has a combinatorial nature. The analyzed sequences are taken from commercial slot machine games. When the gambler spins the virtual reels he/she does not know how symbols are distributed on the reels. The gambler sees only small parts of the reels when they are stopped. By observing the game for a long enough time the gambler can record these small parts of the reels observer on the screen.
Collecting enough information the gambler can try to reconstruct all positions of the symbols on the virtual reels. Such reconstruction is not trivial, because there is too much unknown information. If there are absolutely identical repeating patterns on the virtual reels the gambler can not find this out by just observing small chunks.
Reverse engineering is commonly used during the analysis of slot machine gambling games. There are many approaches such reverse reconstruction to be done. In most cases, the goal of the engineers is to reconstruct the virtual reels completely. The reconstruction is similar to puzzle solving by attaching each observed piece with a proper corresponding one. Such reconstruction is not always possible because in some cases there is more than one way of connecting the observed pieces. The contribution of this study is related to the approximate reconstruction of the sequences. It does not give a direct solution to the reconstruction problem. Instead of this, it gives an approximate solution. The goal is a little bit changed from the exact reconstruction of the virtual reels to the construction of such reels which will give close behavior of the slot machine gambling game if they are loaded inside the machine instead of the original reels. The innovative approach is that the search for a sub-optimal solution is done in the space of the chunks instead of in the space of the sequences. The proposed approximate reconstruction is approved by experiments with real industrial data.

Read More

informatics
V. Dimitrov, K. Kolev. Development of a Browser Based Strategy Game Application

Кey Words: Kinvey; JavaScript; jQuery; HTML; CSS.

Abstract. The proposed application discussed in the present article is a browser based strategy game. The programmable languages and tools used for its development including JavaScript, jQuery, HTML, CSS, Kinvey, Sublime Text, etc. The application is build using the 3-Tier Software Architecture. Some of the benefits of this architecture are scalability, speed of development, performance, availability, etc.

Read More

ecological systems
K. Boshnakov, B. Koumanova, M. Varbanov, E. Mihailov. Procedure for Analysis and Assessment of Water Quality in the Struma River

Кey Words: Neural classifiers; state of river waters; Struma river; presence of inadmissible pollution.

Abstract. The aim of the present work is to study the possibilities for developing a system for monitoring the state of the water on the Struma River and the presence of unacceptable pollution. The development of the algorithms of the monitoring system is in accordance with the normative documents of the Republic of Bulgaria and is built on the basis of monitoring measurements for the quality of the river waters from six monitoring points for the period 2010-2019. The following variables characterizing water quality were analyzed:
ammonium nitrogen (NH4-N), nitrate nitrogen (NO3-N), nitrite nitrogen (NO2-N), pH, biological oxygen demand (BOD), electrical conductivity (EC), total nitrogen (TN), total organic carbon (TOC), total phosphorus (TP), orthophosphate phosphorus (PO4-P), dissolved oxygen (DO), temperature (T) and chemical oxygen demand (COD).
The section of the river Struma from before Blagoevgrad to the border (bridge for the village of Topolnitsa) was chosen for the research. The available measurement data from six monitoring points in the considered section of the Struma River are as synchronized as possible.
Correlation analyzes were performed for the possibility of combining the available measurements from the six monitoring points and for the presence of a correlation dependence between the measured variables characterizing the water quality in the Struma River. The presence of correlations between the variables directs the use of the principal components method as a mathematical apparatus for building the monitoring system. Procedures have been developed for classifying the status of river waters depending on current measurements / analyzes. Expressions for the main components for eleven of the measured variables characterizing water quality are derived.
Research has been carried out to develop a procedure for classifying these measurements into the terms “excellent”, “good” and “moderate”.
Possibilities for classifications with neural networks have been studied. Measuring some of these variables is a lengthy procedure and can hardly be used for operational actions. For this reason, the possibilities for developing a procedure for monitoring and classifying the status of river waters on the basis of variables, which in principle can be measured automatically (pH, EC, DO and T), have been explored. They also apply the principal components method and classification with neural networks in the same classification categories.
The developed approaches for monitoring the quality of the waters of the Struma River can be applied for each measurement in the six monitored monitoring points.

Read More

ecological systems
S. Kasabov, E. Kirilova. Application of NIR Spectroscopy Combined with Chemometric Modelling Methods for Environmental Analysis of Contamined Soils

Кey Words: NIR spectroscopy; chemometric methods; environmental analysis; contaminated soils.

Abstract. Conducting quantitative analysis of soil properties and contaminants in them is a crucial for an achievement of a good understanding of dynamics of ecosystems and a sustainable soil management.
This study presents the recent progress on the developed combined approaches including NIR spectroscopy and chemometrics for accurate, low-cost and reliable quantitative analysis of soil content, published in prestigious journals for the last 7 years. A classification of the approaches depending on the types of soils components, the type of applied pre-processing and chemometric methods
is done. Their main advantages and disadvantages are shown and some trends for future development are outlined.

Read More

automatica
M. Hadjiski. Cyber Security of Industrial Control Systems

Key Words: Advanced control; cyber security; industrial control system; networked control; resilience; simulation.

Abstract. An overview of the problems, research efforts and recent results on cyber security of Industrial Control Systems is provided. The interaction between the basic control sub-systemsthe advanced control of the plant, the system for predictive safety maintenance and the cyber-security control system is considered. In the paper is shown that cyber security should be treated as a holistic problem and could be successfully solved if tight integration of technological, organizational and human aspects will be achieved. Several approaches for design of contra-actions via implementation simulation and Artificial Intelligence-based technologies are analyzed. Some problems of attack-resilient control of Industrial Control Systems are discussed.

Read More

automatica
S. Yordanov, G. Mihalev. System for Automatic Reporting a Labour Productivity in Real Time Based on ESP32 Controller

Key Words: Internet of Things (IoT); Wi-Fi module ESP32; Arduino IDE development environment; LPWAN technologies; electronic accounting technologies.

Abstract. In this paper, an ESP32 application in implementing systems for automated reporting of the utilization rate of production capacities in real time is considered. A technical solution of remote control and monitoring of the production process in a textile company, through a dedicated module for sending the time spent on a remote server via Wi-Fi, Lan or Bluetooth is proposed. The obtained information is used to control the production process in real time and determination of the remuneration of workers.

Read More

automatica
V. Boishina. Situattion Predictive Control for Energetic Systems

Key Words: Distributed diagnosis; supervisor control; case base reasoning; predictive control.

Abstract. The research is mainly focused of using of possibility to collect the historical information about the behavior of the control system. The main focus is to illustrate using of the Case Base Predictive Control, which optimizes the way of choosing the optimal way of control of the system in respect of taking the decisions according to the historical experience about system behavior and fast changing outdoor parameters. The paper described forming of cases which describing different system situations and the appropriate way of choosing of the right way of system control. The proposed research represented the possibility to aplly Case Base Reasoning (CBR), based on the previous knowledge about system behavior and possible system disturbances caused from different environment changes (climatic and economic ones). The research propose the way of optimizing the control of energetic control system based on previous known cases.

Read More

informatics
Y. Aleksieva, H. Valchanov. Botnet Detection System Based on Genetic Algorithms

Key Words: Botnet attacks; DoS attacks; intrusion detecting system; genetic algorithms.

Abstract. One of the most common attacks against information security is Botnet. Recognizing such attacks requires the development of effective security systems. Intrusion detection systems collect information from different sources in computer systems and networks. For most systems, this information is compared to predefined patterns of abuse to identify attacks and vulnerabilities. Much of the existing host-based systems for botnet detection use techniques based on anomalies or rules. This paper presents some aspects of the implementation of a host-based botnet attack detection system. The system uses an anomaly detection technique based on a genetic algorithm.

Read More