Malignant melanomas are the most deadly type of skin cancer, yet detected early have high chances of successful treatment. In the last twenty years, the interest in automatic recognition and classification of melanoma dynamically increased, partly because of appearing public datasets with dermatoscopic images of skin lesions. Automated computer-aided skin cancer detection in dermatoscopic images is a very challenging task due to uneven sizes of datasets, huge intra-class variation with small interclass variation, and the existence of many artifacts in the images. One of the most recognized methods of melanoma diagnosis is the ABCD method. In the paper, we propose an extended version of this method and an intelligent decision support system based on neural networks that uses its results in the form of hand-crafted features. Automatic determination of the skin features with the ABCD method is difficult due to the large diversity of images of various quality, the existence of hair, different markers and other obstacles. Therefore, it was necessary to apply advanced methods of pre-processing the images. The proposed system is an ensemble of ten neural networks working in parallel, and one network using their results to generate a final decision. This system structure enables to increase the efficiency of its operation by several percentage points compared with a single neural network. The proposed system is trained on over 5000 and tested afterwards on 200 skin moles. The presented system can be used as a decision support system for primary care physicians, as a system capable of self-examination of the skin with a dermatoscope and also as an important tool to improve biopsy decision making.
To solve the problem of large deformation soft rock roadway with complicated stress condition in Baluba copper mine, the characteristics of roadway deformation and failure modes are analyzed deeply on the basis of geological survey. Combined with the theoretical analysis and numerical simulation, the new reinforcement technology with floor mudsill and grouting anchor cable is proposed. Moreover, the three dimension numerical simulation model is established by the software FLAC-3D, the support parameter is optimized by it. The results show that the optical array pitch of the U-steel shelf arch is 0.8 m, and the optical array pitch of the grouting anchor cable is 2.4 m. At last, the field experiments are done all over the soft rock roadway. Engineering practice shows that the deformation of soft rock roadway in Baluba copper mine is effectively controlled by adopting the new reinforcement technology, which can provide certain references for similar engineering.
The paper analyses the distorted data of an electronic nose in recognizing the gasoline bio-based additives. Different tools of data mining, such as the methods of data clustering, principal component analysis, wavelet transformation, support vector machine and random forest of decision trees are applied. A special stress is put on the robustness of signal processing systems to the noise distorting the registered sensor signals. A special denoising procedure based on application of discrete wavelet transformation has been proposed. This procedure enables to reduce the error rate of recognition in a significant way. The numerical results of experiments devoted to the recognition of different blends of gasoline have shown the superiority of support vector machine in a noisy environment of measurement.
Correct incipient identification of an analog circuit fault is conducive to the health of the analog circuit, yet very difficult. In this paper, a novel approach to analog circuit incipient fault identification is presented. Time responses are acquired by sampling outputs of the circuits under test, and then the responses are decomposed by the wavelet transform in order to generate energy features. Afterwards, lower-dimensional features are produced through the kernel entropy component analysis as samples for training and testing a one-against-one least squares support vector machine. Simulations of the incipient fault diagnosis for a Sallen-Key band-pass filter and a two-stage four-op-amp bi-quad low-pass filter demonstrate the diagnosing procedure of the proposed approach, and also reveal that the proposed approach has higher diagnosis accuracy than the referenced methods.
Accurate flatness measurement of silicon wafers is affected greatly by the gravity-induced deflection (GID) of the wafers, especially for large and thin wafers. The three-point-support method is a preferred method for the measurement, in which the GID uniquely determined by the positions of the supports could be calculated and subtracted. The accurate calculation of GID is affected by the initial stress of the wafer and the positioning errors of the supports. In this paper, a finite element model (FEM) including the effect of initial stress was developed to calculate GID. The influence of the initial stress of the wafer on GID calculation was investigated and verified by experiment. A systematic study of the effects of positioning errors of the support ball and the wafer on GID calculation was conducted. The results showed that the effect of the initial stress could not be neglected for ground wafers. The wafer positioning error and the circumferential error of the support were the most influential factors while the effect of the vertical positioning error was negligible in GID calculation.
A complex model of mechanically ventilated ARDS lungs is proposed in the paper. This analogue is based on a combination of four components that describe breathing mechanics: morphology, mechanical properties of surfactant, tissue and chest wall characteristics. Physical-mathematical formulas attained from experimental data have been translated into their electrical equivalents and implemented in MultiSim software. To examine the adequacy of the forward model to the properties and behaviour of mechanically ventilated lungs in patients with ARDS symptoms, several computer simulations have been performed and reported in the paper. Inhomogeneous characteristics observed in the physical properties of ARDS lungs were mapped in a multi-lobe model and the measured outputs were compared with the data from physiological reports. In this way clinicians and scientists can obtain the knowledge on the moment of airway zone reopening/closure expressed as a function of pressure, volume or even time. In the paper, these trends were assessed for inhomogeneous distributions (proper for ARDS) of surfactant properties and airway geometry in consecutive lung lobes. The proposed model enables monitoring of temporal alveolar dynamics in successive lobes as well as those occurring at a higher level of lung structure organization, i.e. in a point P0 which can be used for collection of respiratory data during indirect management of recruitment/de-recruitment processes in ARDS lungs. The complex model and synthetic data generated for various parametrization scenarios make possible prospective studies on designing an indirect mode of alveolar zone management, i.e. with
Fault detection and location are important and front-end tasks in assuring the reliability of power electronic circuits. In essence, both tasks can be considered as the classification problem. This paper presents a fast fault classification method for power electronic circuits by using the support vector machine (SVM) as a classifier and the wavelet transform as a feature extraction technique. Using one-against-rest SVM and one-against-one SVM are two general approaches to fault classification in power electronic circuits. However, these methods have a high computational complexity, therefore in this design we employ a directed acyclic graph (DAG) SVM to implement the fault classification. The DAG SVM is close to the one-against-one SVM regarding its classification performance, but it is much faster. Moreover, in the presented approach, the DAG SVM is improved by introducing the method of Knearest neighbours to reduce some computations, so that the classification time can be further reduced. A rectifier and an inverter are demonstrated to prove effectiveness of the presented design.
This paper presents a novel strategy of fault classification for the analog circuit under test (CUT). The proposed classification strategy is implemented with the one-against-one Support Vector Machines Classifier (SVC), which is improved by employing a fault dictionary to accelerate the testing procedure. In our investigations, the support vectors and other relevant parameters are obtained by training the standard binary support vector machines. In addition, a technique of radial-basis-function (RBF) kernel parameter evaluation and selection is invented. This technique can find a good and proper kernel parameter for the SVC prior to the machine learning. Two typical analog circuits are demonstrated to validate the effectiveness of the proposed method.
A novel VC (voice conversion) method based on hybrid SVR (support vector regression) and GMM (Gaussian mixture model) is presented in the paper, the mapping abilities of SVR and GMM are exploited to map the spectral features of the source speaker to those of target ones. A new strategy of F0 transformation is also presented, the F0s are modeled with spectral features in a joint GMM and predicted from the converted spectral features using the SVR method. Subjective and objective tests are carried out to evaluate the VC performance; experimental results show that the converted speech using the proposed method can obtain a better quality than that using the state-of-the-art GMM method. Meanwhile, a VC method based on non-parallel data is also proposed, the speaker-specific information is investigated using the SVR method and preliminary subjective experiments demonstrate that the proposed method is feasible when a parallel corpus is not available.
Active acoustics offers potential benefits in music halls having acoustical short-comings and is a relatively inexpensive alternative to physical modifications of the enclosures. One critical benefit of active architecture is the controlled variability of acoustics. Although many improvements have been made over the last 60 years in the quality and usability of active acoustics, some problems still persist and the acceptance of this technology is advancing cautiously. McGill's Virtual Acoustic Technology (VAT) offers new solutions in the key areas of performance by focusing on the electroacoustic coupling between the existing room acoustics and the simulation acoustics. All control parameters of the active acoustics are implemented in the Space Builder engine by employing multichannel parallel mixing, routing, and processing. The virtual acoustic response is created using low-latency convolution and a three-way temporal segmentation of the measured impulse responses. This method facilitates a sooner release of the virtual room response and its radiation into the surrounding space. Field tests are currently underway at McGill University involving performing musicians and the audience in order to fully assess and quantify the benefits of this new approach in active acoustics.
Electrocatalytic gas sensors belong to the family of electrochemical solid state sensors. Their responses are acquired in the form of I-V plots as a result of application of cyclic voltammetry technique. In order to obtain information about the type of measured gas the multivariate data analysis and pattern classification techniques can be employed. However, there is a lack of information in literature about application of such techniques in case of standalone chemical sensors which are able to recognize more than one volatile compound. In this article we present the results of application of these techniques to the determination from a single electrocatalytic gas sensor of single concentrations of nitrogen dioxide, ammonia, sulfur dioxide and hydrogen sulfide. Two types of classifiers were evaluated, i.e. linear Partial Least Squares Discriminant Analysis (PLS-DA) and nonlinear Support Vector Machine (SVM). The efficiency of using PLS-DA and SVM methods are shown on both the raw voltammetric sensor responses and pre-processed responses using normalization and auto-scaling
In order to make the analog fault classification more accurate, we present a method based on the Support Vector Machines Classifier (SVC) with wavelet packet decomposition (WPD) as a preprocessor. In this paper, the conventional one-against-rest SVC is resorted to perform a multi-class classification task because this classifier is simple in terms of training and testing. However, this SVC needs all decision functions to classify the query sample. In our study, this classifier is improved to make the fault classification task more fast and efficient. Also, in order to reduce the size of the feature samples, the wavelet packet analysis is employed. In our investigations, the wavelet analysis can be used as a tool of feature extractor or noise filter and this preprocessor can improve the fault classification resolution of the analog circuits. Moreover, our investigation illustrates that the SVC can be applicable to the domain of analog fault classification and this novel classifier can be viewed as an alternative for the back-propagation (BP) neural network classifier.
The purpose of the work was to predict the selected product parameters of the dry separation process using a pneumatic sorter. From the perspective of application of coal for energy purposes, determination of process parameters of the output as: ash content, moisture content, sulfur content, calorific value is essential. Prediction was carried out using chosen machine learning algorithms that proved to be effective in forecasting output of various technological processes in which the relationships between process parameters are non-linear. The source of data used in the work were experiments of dry separation of coal samples. Multiple linear regression was used as the baseline predictive technique. The results showed that in the case of predicting moisture and sulfur content this technique was sufficient. The more complex machine learning algorithms like support vector machine (SVM) and multilayer perceptron neural network (MPL) were used and analyzed in the case of ash content and calorific value. In addition, k-means clustering technique was applied. The role of cluster analysis was to obtain additional information about coal samples used as feed material. The combination of techniques such as multilayer perceptron neural network (MPL) or support vector machine (SVM) with k-means allowed for the development of a hybrid algorithm. This approach has significantly increased the effectiveness of the predictive models and proved to be a useful tool in the modeling of the coal enrichment process.
Cross-docking is a strategy that distributes products directly from a supplier or manufacturing plant to a customer or retail chain, reducing handling or storage time. This study focuses on the truck scheduling problem, which consists of assigning each truck to a door at the dock and determining the sequences for the trucks at each door considering the time-window aspect. The study presents a mathematical model for door assignment and truck scheduling with time windows at multi-door cross-docking centers. The objective of the model is to minimize the overall earliness and tardiness for outbound trucks. Simulated annealing (SA) and tabu search (TS) algorithms are proposed to solve large-sized problems. The results of the mathematical model and of meta-heuristic algorithms are compared by generating test problems for different sizes. A decision support system (DSS) is also designed for the truck scheduling problem for multi-door cross-docking centers. Computational results show that TS and SA algorithms are efficient in solving large-sized problems in a reasonable time.
T h e a i m: The aim of the study is to present the initial experience with continuous flow left ventricle assist device (CF-LVAD) in pediatric patients with BSA below 1.5 m2. M a t e ri a l a n d M e t h o d s: Between 2016 and 2017, CF-LVAD (the Heartware System) have been implanted in three pediatric patients in the Department of Pediatric Cardiac Surgery, Jagiellonian University, Krakow, Poland. The indications for initiating CF-LVAD were end-stage congestive heart failure due to dilated cardiomyopathy in all children. R e s u l t s: Implanted patients have had BSA of 1.09, 1.42, 1.2 m2, and 37, 34, 34 kg of body weight and the age 12, 11, 12 years, respectively. The time of support was 550 days in two patients and 127 in another one, and is ongoing. The main complication has been driveline infection. C o n c l u s i o n: The outcomes from our single-center experience using the HeartWare CF-LVAD have been excellent with a low incidence of complication and no necessity to reoperation in our patients. Children could be successfully and safely discharged home.
This article presents a study on music genre classification based on music separation into harmonic and drum components. For this purpose, audio signal separation is executed to extend the overall vector of parameters by new descriptors extracted from harmonic and/or drum music content. The study is performed using the ISMIS database of music files represented by vectors of parameters containing music features. The Support Vector Machine (SVM) classifier and co-training method adapted for the standard SVM are involved in genre classification. Also, some additional experiments are performed using reduced feature vectors, which improved the overall result. Finally, results and conclusions drawn from the study are presented, and suggestions for further work are outlined.
This article presents a practical solution in the form of implementation of agent-based platform for the management of contracts in a network of foundries. The described implementation is a continuation of earlier scientific work in the field of design and theoretical system specification for cooperating companies . The implementation addresses key design assumptions - the system is implemented using multi-agent technology, which offers the possibility of decentralisation and distributed processing of specified contracts and tenders. The implemented system enables the joint management of orders for a network of small and medium-sized metallurgical plants, while providing them with greater competitiveness and the ability to carry out large procurements. The article presents the functional aspects of the system - the user interface and the principle of operation of individual agents that represent businesses seeking potential suppliers or recipients of services and products. Additionally, the system is equipped with a bi-directional agent translating standards based on ontologies, which aims to automate the decision-making process during tender specifications as a response to the request.
Complex structural engineering projects that involve information-gathering and decision-makingprocesses need to be approached with appropriate systems and tools. As transactional databasesare found to be insufficient for this purpose, engineers are adopting multidimensional informationsystems that have been successfully used in other areas of management, especially business.
The paper deals with possibilities of innovation projects financing in the Small and Medium Size Enterprises (SMEs) in the Czech Republic. It discusses, in the emphasis on SMEs, possible approaches to innovative company financing in dependence on company life cycle. Well established and functional models of innovative companies financing as FFF, Business angels, Private equity and Venture capital funding and mezzanine financing are discussed. Inasmuch SMEs are considered the key driving force of the Czech economy and the stabilizing feature of the regional development, the government places emphasis on the development of financial instruments which would ensure an ongoing financial support of innovation projects. But managements of SMEs insufficiently use all opportunities to obtain investment resources for the growth, future competitiveness and prosperity of their companies. According to researches performed in EU it was proven that financing constraints hinder innovation among SMEs. Maintaining regional balance through sustainable performance of SMEs is the common aim of municipalities as well. It is necessary for SMEs to form long-term relationships with their municipalities in the region. Programmes which arrange financial support for institutions are provided through private investors, grants, the EU funds and national budget. The paper evaluates pros and cons of various types of financial subsidies with respect to payback periods, risk exposure and availability. The paper includes the outputs of empirical research in SMEs carried out 2014 focused on steering innovation projects in SMEs. The aim of the research was to find out if SMEs can manage, evaluate and develop innovation projects. Moreover the authors examined the effectiveness of relationships established between SMEs and municipalities and problems which the SMEs are confronted by upon the ensurance of project innovation investments. The sources procurement is a very sophisticated topic and it is beneficial for the SMEs to establish a close cooperation not only with municipalities but also with universities.
Article present various forms of transfer of information available on the Internet. An attempt was made to show the possibility of such a selection of the knowledge sources that, taking into account user preferences, would arouse his interest, showing in parallel the intended substantive content. This commitment is shown in the context of the current assumptions of building a platform dedicated to support the needs of production processes in foundry and metallurgy.