Search

In the present research work, an electrical resistance tomography (ERT) system is utilized as a means for real-time fault detection and diagnosis (FDD) during a reactive crystallization process. The calcium carbonate crystallization is part of the carbon capture and utilization scheme where process monitoring and malfunction diagnostics strategies are presented. The graphical logic representation of the fault tree analysis methodology is used to develop the system failure states. The measurement consistency due to the use of a single electrode from a set of ERT electrodes for malfunction identification is experimentally and quantitatively investigated based on the sensor sensitivity and standard deviation criteria. Electrical current measurements are employed to develop a LabVIEW-based process automation program by using the process-specific knowledge and historical process data. Averaged electrical current is correlated to the mechanical failure of the stirrer through standard deviation evaluation, and slopes of the measured data are used to monitor the pump and concentrations status. The performance of the implemented methodology for detecting the induced faults and abnormalities is tested at different operating conditions, and a basic signal-based alarming technique is developed.

Crystallization is a significant procedure in the manufacturing of many pharmaceutical and solid food products. In-situ Electrical Resistance Tomography (ERT) is a novel Process Analytical Tool (PAT) to provide a cheap and quick way to test, visualize, and evaluate the progress of crystallization processes. In this work, the spatial accuracy of the non-conductive phantoms in low conductivity solutions was evaluated. Gauss-Newton, Linear Back Projection, and iterative Total Variation reconstruction algorithms were used to compare the phantom reconstructions for tap water, industrial-grade saturated sucrose solution, and demineralized water. Cylindrical phantom measuring 10 mm in diameter and a cross-section area of 1.5 % of the total beaker area was detected at the center of the beaker. Two phantoms with a 10 mm diameter were visualized separately in non-central locations. The quantitative evaluations were done for the phantoms with radii ranging from 10 mm to 50 mm in demineralized water. Multiple factors such as ERT device and sensor development, FEM mesh density and simulations, image reconstruction algorithms, number of iterations, segmentation methods, and morphological image processing methods were discussed and analyzed to achieve spatial accuracy. The development of ERT imaging modality for the purpose of monitoring crystallization in low conductivity solutions was performed satisfactorily.

The paper presents a web application for navigation through the university campus, which is based on Global Positioning System GPS and OpenStreetMap. The application has a multilayer structure and multi-labelling support. The proposed solution ensures better management of visual data and more efficient image processing comparing to the other known methods. With the new search system, users can place a lot of information on one layer without losing the legibility of displayed data. All the information that was displayed on the map was grouped and assigned to the appropriate categories.Therefore a map contains a lot of related information that needs to be linked to each other. The system has been divided into modules that ensure the integrity of the displayed things. Presenting so much information at the same time is managed by modules. Their main job is to provide results that is then segregated and grouped. The system presented in this paper was applied for Lodz University of Technology.

Electrical capacitance tomography (ECT) is one of non-invasive visualization techniques which can be used for industrial process monitoring. However, acquiring images trough 3D ECT often requires performing time consuming complex computations on large size matrices. Therefore, a new parallel approach for 3D ECT image reconstruction is proposed, which is based on application of multi-GPU, multi-node algorithms in heterogeneous distributed system. This solution allows to speed up the required data processing. Distributed measurement system with a new framework for parallel computing and a special plugin dedicated to ECT are presented in the paper. Computing system architecture and its main features are described. Both data distribution as well as transmission between the computing nodes are discussed. System performance was measured using LBP and the Landweber&rsquo, s reconstruction algorithms which were implemented as a part of the ECT plugin. Application of the framework with a new network communication layer reduced data transfer times significantly and improved the overall system efficiency.

A new approach to solve the inverse problem in electrical capacitance tomography is presented. The proposed method is based on an artificial neural network to estimate three different parameters of a circular object present inside a pipeline, i.e. radius and 2D position coordinates. This information allows the estimation of the distribution of material inside a pipe and determination of the characteristic parameters of a range of flows, which are characterised by a circular objects emerging within a cross section such as funnel flow in a silo gravitational discharging process. The main advantages of the proposed approach are explicitly: the desired characteristic flow parameters are estimated directly from the measured capacitances and rapidity, which in turn is crucial for online flow monitoring. In a classic approach in order to obtain these parameters in the first step the image is reconstructed and then the parameters are estimated with the use of image processing methods. The obtained results showed significant reduction of computations time in comparison to the iterative LBP or Levenberg-Marquard algorithms.

Electrical Capacitance Tomography is a non-invasive imaging technique, which allows visualization of the industrial processes interior and can be applied to many branches of the industry. Image reconstruction process, especially in case of 3D images, is a very time consuming task (when using classic processors and algorithms), which in turn leads to an unacceptable waiting time and currently limits the use of 3D Electrical Capacitance Tomography. Reconstruction using deterministic methods requires execution of many basic operations of linear algebra, such as matrix transposition, multiplication, addition and subtraction. In order to reach real-time reconstruction a 3D ECT computational subsystem must be able to transform capacitance data into images in a fraction of a second. By assuming, that many of the computations can be performed in parallel using modern, fast graphics processor and by altering the algorithms, time to achieve high quality image reconstruction will be shortened significantly. The research conducted while analysing ECT algorithms has also shown that, although dynamic development of GPU computational capabilities and its recent application for image reconstruction in ECT has significantly improved calculations time, in modern systems a single GPU is not enough to perform many tasks. Distributed Multi-GPU solutions can reduce reconstruction time to only a fraction of what was possible on pure CPU systems. Nevertheless performed tests clearly illustrate the need for further optimizations of previously developed algorithms.

Synthesis of the crystals is a very important step in manufacturing of many solid food products and pharmaceutical products. Electrical Resistance Tomography (ERT) provides an in-situ modality in observation of the progress in the process of batch reactor crystallization. Lowering of the conductivity in the non-ionic solutions such as sucrose solution poses challenges in the quantitative evaluation. In this work, the 2D electrical resistance tomography (2D-ERT) was implemented in laboratory-based batch reactor to observe circular, hollow and static sugar filled phantoms at various sucrose solution concentrations. The evaluations were done using a single plane of 16 surface electrode setup with voltage controlled current injection method. Modified Bayesian and iterative Gauss-Newton reconstruction methods were used to compare the phantom reconstructions qualitatively. It was observed that the 10 mm and 15 mm phantoms were discernible using both the reconstruction methods at the central location in the reactor vessel.

This paper presents new methods and models for forecasting stock prices and computing hybrid models, combining analytical and neural approaches. First, technical and fractal analyses are conducted and selected stock market indices calculated, such as moving averages and oscillators. Next, on the basis of these indices, an artificial neural network (ANN) provides predictions one day ahead of the closing prices of the assets. New technical analysis indicators using fractal modeling are also proposed. Three kinds of hybrid model with different degrees of fractal analysis were considered. The new hybrid modeling approach was compared to previous ANN-based prediction methods. The results showed that the hybrid model with fractal analysis outperforms other models and is more robust over longer periods of time.

Nowadays Wireless Sensor Network has become an interesting filed for researchers. The main concerns about Wireless Sensor Network are the life time and energy consumption. Because of these two reasons new protocols improving these network features are being developed all the time. This paper studies TEEN (Threshold Sensitive Energy Efficient Sensor Network) protocol. We improve the performance of choosing the Cluster Heads in the cluster areas using KNN (K Nearest Neighbours) algorithm, which use a distance between the nodes as a similarity measure to classify the nodes in the network. Therefore, most of routing protocol techniques and sensing task require to check the position of sensors in network to obtain information of location with high accuracy sensors in network. The modification in this protocol improves the life time and energy consumption compared with the original TEEN protocol.

The paper is focused on the concept of using open questions in an interactive computer system for assessing students' knowledge. The E-test System works as a web system in the local network in the Institute of Applied Computer Science, Lodz University of Technology. The system is used in practice for several years and supports academic teachers in the laborious process of tests' marking. The paper presents a new concept of open questions automatic evaluation by the use of Artificial Neural Networks (ANN). The system was tested experimentally on the basis of tests carried out on a large group of students. The paper reports on the results obtained by the use of new ANN based algorithm which is compared with Authors' previous solution.

Taking care of those who need help is the cornerstone of our society. Thanks to the constant advances we have access to a better and cheaper technology that can make our daily lives easier, so why not apply the same concepts to help us in taking care of our loved ones. In this article we present concepts of systems, built using commercially available devices, for simplifying and automating the monitoring of children behaviour, as well as health of the elderly and chronically ill people. By using off-the-shelf commodity devices (such as Smart TVs, fitness trackers and accessories for game consoles) we can reduce the cost of such systems and make them more affordable.

The word hacking very often evokes pejorative connotations. In IT to hack is to break security measures, that were introduced by the developer or the manufacturer. However to hack can also mean to make the application or device do more, that it was originally intended, to extend its capabilities. In this article we will show that by hacking (or rooting) a Samsung Smart TV it is possible to build a system that will allow remote management and monitoring of such device. Parental control is often very limited in functionality, usually just a PIN lock. By achieving arbitrary code execution we were able to extend the functionality drastically. This system is independent of manufacturer and can work and be extended even on older TV sets, that do not receive updates.

3D ECT provides a lot of challenging computational issues that have been reported in the past by many researchers. Image reconstruction using deterministic methods requires execution of many basic operations of linear algebra, such as matrix transposition, multiplication, addition and subtraction. In order to reach real-time reconstruction a 3D ECT computational subsystem has to be able to transform capacitance data into image in fractions of seconds. By assuming, that many of the computations can be performed in parallel using modern, fast graphics processor and by altering the algorithms time to achieve high quality image reconstruction will be shortened significantly. The research conducted while analysing ECT algorithms has also shown that, although dynamic development of GPU computational capabilities and its recent application for image reconstruction in ECT has significantly improved calculations time, in modern systems a single GPU is not enough to perform many tasks. Distributed Multi-GPU solutions can reduce reconstruction time to only a fraction of what was possible on pure CPU systems. Nevertheless performed tests clearly illustrate the need for developing a new distributed platform, which would be able to fully utilize the potential of the hardware. It has to take into account specific nature of computations in Multi-GPU systems.

The paper describes the architecture of the information expert system designed and dedicated to stock exchange data processing, analyzing and presentation. The system uses Artificial Neural Networks (ANN) combined with technical analysis and fractal analysis to predict future price of stock exchange assets. It also enables selection of companies, which assets will be increased. The selection of companies is based on comparing algorithms implementing Hopfield network. The system displays a list of the companies with the highest expected profit sorted in descending order.

3D ECT provides a lot of challenging computational issues that have been reported in the past by many researchers. Image reconstruction using deterministic methods requires execution of many basic operations of linear algebra, such as matrix transposition, multiplication, addition and subtraction. In order to reach real-time reconstruction a 3D ECT computational subsystem has to be able to transform capacitance data into image in fractions of seconds. By assuming, that many of the computations can be performed in parallel using modern, fast graphics processor and by altering the algorithms time to achieve high quality image reconstruction will be shortened significantly. The research conducted while analysing ECT algorithms has also shown that, although dynamic development of GPU computational capabilities and its recent application for image reconstruction in ECT has significantly improved calculations time, in modern systems a single GPU is not enough to perform many tasks. Distributed Multi-GPU solutions can reduce reconstruction time to only a fraction of what was possible on pure CPU systems. Nevertheless performed tests clearly illustrate the need for developing a new distributed platform, which would be able to fully utilize the potential of the hardware. It has to take into account specific nature of computations in Multi-GPU systems.

The paper describes a new method using Hopfield artificial neural network combined with technical analysis fractal analysis and feed-forward artificial neural networks for predicting share prices for a next day on a Stock Exchange. The developed method and networks are implemented in an Expert System, which is proposed as a valuable comprehensive, analytical tool. A new algorithm for artificial neural networks training and testing is also presented. It automatically chooses the best network structure, and the most important input parameters.

Article describes, the use of Artificial Neural Networks (ANN) for predicting values of Stock Exchange shares. Rules of Stock Exchange functioning, principles of technical analysis and the most important stock market indices are described, which support investors, who plan to make transactions. ANN of Multi-Layer Perceptron (MLP) type, and a moving window method are applied. A hybrid method is also proposed, in which time series of CLOSE values as a function of the following trading days are used to stock market indices calculation, such as moving averages and oscillators, which are applied to ANN inputs. Research was conducted for 80 companies, selected from the 1218 companies functioning on Stock Exchange. The achieved maximum error in one day ahead CLOSE value prediction is 1,31%.

Yarn hairiness is one of the key parameters influencing fabric quality. In this paper image processing and analysis algorithms developed for an automatic determination of yarn hairiness are presented. The main steps of the proposed algorithms are as follows: image preprocessing, yarn core extraction using graph cut method, yarn segmentation using high pass filtering based method and fibres extraction. The developed image analysis algorithms quantify yarn hairiness by means of the two proposed measures such as hair area index and hair length index, which are compared to the USTER hairiness index—the popular hairiness measure, used nowadays in textile science, laboratories and industry. The detailed description of the proposed approach is given. The developed method is verified experimentally for two distinctly different yarns, produced by the use of different spinning methods, different fibres types and characterized by totally different hairiness. The proposed algorithms are compared with computer methods previously used for yarn properties assessment. Statistical parameters of the hair length index (mean absolute deviation, standard deviation and coefficient of variation) are calculated. Finally, the obtained results are analyzed and discussed. The proposed approach of yarn hairiness measurement is universal and the presented algorithms can be successfully applied in different vision systems for yarn quantitative analysis.

The new method is proposed for the numerical solution of a class of shape inverse problems. The size and the location of a small opening in the domain of integration of an elliptic equation is identified on the basis of an observation. The observation includes the finite number of shape functionals. The approximation of the shape functionals by using the so-called topological derivatives is used to perform the learning process of an artificial neural network. The results of computations for 2D examples show, that the method allows to determine an approximation of the global solution to the inverse problem, sufficiently closed to the exact solution. The proposed method can be extended to the problems with an opening of general shape and to the identification problems of small inclusions. However, the mathematical theory of the proposed approach still requires futher research. In particular, the proof of global convergence of the method is an open problem.

A new method to solve the inverse problem of electrical capacitance tomography is proposed. Our method is based on artificial neural network to estimate the radius of an object present inside a pipeline. This information is useful to predict the distribution of material inside the pipe. The capacitance data used to train and test the neural network is simulated on Matlab using the electrical capacitance tomography toolkit ECTsim. The provided accuracy is promising and shows efficiency to solve the inverse problem in a simple manner and on reduced computational time about 120 times when compared to the existing Landweber iterative algorithm for tomographic image reconstruction that can be encouraging for dynamic industrial applications.

The paper describes a new method of combining Artificial Neural Networks (ANN), technical analysis and fractal analysis for predicting share prices on the Warsaw Stock Exchange. The proposed hybrid model consists of two consecutive modules. In the first step share prices are preprocessed and calculated into moving averages and oscillators. Then, in the next step, they are given to the ANN inputs, which provides the closing values of the asset for the next day. ANN of Multi-Layer Perceptron (MLP) type, and fractal analysis are applied. The hybrid model combining ANN with technical and fractal analysis is compared with hybrid model combining ANN with technical analysis. The obtained results indicate that hybrid model combined with fractal analysis is more accurate and stable in the long run than the hybrid model.

The article presents a concept of using an audience response system (ARS) or ”clickers”, which can run on a mobile, tablet, PDA or PC for enhancing interaction between a lecturer and students in large classrooms. The developed interactive audio response software is based on Joomla! content management system (CMS) and its JVoteSystem component. The article compares results of students’ learning outcomes for the students taught with and without question based learning methodology and also with and without using clickers software.

Proposals for a simplified dynamic model for a Resistance Thermometer Detector, or RTD, which is based upon a priori and a posteriori knowledge, are made. A new self-heating method of in situ sensor testing is presented. Experimentation using Multifrequency Binary Signals for both this new self-heating and the traditional external input immersion tests are described. Different transfer functions were obtained for these two testing methods. Mathematical relationships between them were determined from the laws of thermokinetics.

This paper describes the design of a system providing room occupancy information in a university campus. The system and its possible influence on the human environment are designed to enhance the work environment through pervasive information delivery. The work is motivated by recent advances in the domain of ubiquitous computing. The authors describe a case study of delivering a solution to university students informing them where they can find free spaces in rooms designated for quiet study. The data is available on the web and through ambient displays. The proof-of-concept study presents the methodology applied, discusses the design issues that were encountered by the project team and reflects on the devices and techniques used in the implementation. An application of standard image processing techniques to provide a contextualized, pervasive user-centered service is also depicted.

Audience response systems (ARS) or “clickers” are becoming more and more popular tools for managing audience response or voting feedback for certain questions. Currently, they are more commonly used in education, mostly to engage students during lectures in large classrooms and give the lecturer prompt anonymous response from the audience. The article presents a concept of using a clickers software, which can run on a mobile, tablet, PDA or PC. Such a solution offers flexible student-lecturer interaction. The article compares results of students' learning outcomes for the students taught with and without question based learning methodology.

The paper presents new methods for modelling of temperature sensors' dynamics by means of Artificial Neural Networks (ANN) and hybrid analytical-neural approach. Feedforward multilayer ANN and a moving window method, as well as Recurrent Neural Networks (RNN) are applied. The proposed modelling techniques were evaluated experimentally for two small platinum Resistance Temperature Detectors (RTDs) immersed in oil. Experiments were performed in temperature range, for which the sensors characteristics are nonlinear. The proposed ANN-based and hybrid analytical-neural models were validated by means of computer simulations on the basis of the quality of dynamic errors correction. It was shown that in the process conditions for which classical methods and linear models fail, the application of ANNs and hybrid techniques which combine soft and hard computing paradigms can significantly improve modelling quality.

In this article structural aspects of two different vision systems were described. The systems automatically measures respectively: surface properties of metals and yarn hairiness. Despite of so different fields of science there are common stages in all these measurements processes. Having this in mind, in the article authors defined main stages of the considered' measurement processes including image acquisition, image enhancement, image segmentation and image analysis.

The article describes the algorithm of the edge detection in the computer application of the assessment of yarn quality. The proposed algorithm and the measurement method allows the real setting of the length and number of the protruding fibres. That solution introduces a new quality to the measurement of yarn hairiness.

We consider the problem of locating small openings inside the domain of definition of elliptic equation using as the observation data the values of finite number of integral functionals. Application of neural networks requires a great number of training sets. The approximation of these functionals by means of topological derivative allows to generate training data very quickly. The results of computations for 2D examples show, that the method allows to determine an approximation of the global solution to the inverse problem, sufficiently closed to the exact solution.

The paper presents a new method for modelling of non-linear temperature sensor and correction of its dynamic errors by means of Artificial Neural Networks (ANNs). Feedforward multilayer ANNs with a moving window method and recurrent ANNs were applied. In the proposed correction technique an inverse dynamic model of the sensor is implemented by means of a neural corrector. ANN based modelling and correction technique has been evaluated experimentally for small platinum RTD immersed in oil. Recurrent ANN was used as a simulator for modelling sensor’s non-linear dynamics and to validate the correction technique.

The article presents a new approach that combines two separate fields of stock exchange analysis. The aim of proposed solution is to support investors in their decisions and recommend to buy the assets which provide the greatest profits. To achieve this goal, decisive algorithms have been developed using artificial neural networks and technical analysis, which were used along with statistics that refer to the occurrence of single words in the fundamental analysis. Based on this, a model was prepared that in response gives a recommendation for future increases. The system consists of two algorithms. The first of them uses the LSTM (Long Short-Term Memory) artificial neural network. As inputs, information about the current closing price as well as technical analysis indicators along with the value of the current volume were used. The output has been specified as the closing price on the following day. In order to improve the response from the ANN (Artificial Neural Network), statistics of the occurrence of words in publications from last week were used. Subsequent signals gained much more importance if the volume of all transactions was much larger than the moving average of the last 15 periods and if the words that appeared in the last publication caused earlier increases. Additional information for the system are also data that come from Google Trends. This allows to verify the trend of interest and whether the published messages are important.