Search

In the recent time, enviromental sound classification has received much popularity. This area of research comes under domain of non-speech audio classification. In this work, we have proposed a dilated Convolutional Neural Network approch to classify urban sound. We have carried out feature extraction, data augmentation techniques to carry out our experimental strategy smoothly. We also found out the activation maps of each layers of dilated convolution neural network. An increamental dilation rate has exploited Overall we achieved 84.16% of accuracy from the proposed dilated convolutional method. The gradual increaments of dilation rate has exploited the worse effect of grindding and has lowered down the computational cost. Also, overall classification performance, precision, recall,overall truth and kappa value have been obtained from our proposed method. We have considered 10 fold cross validation for the implementation of the dilated CNN model. [ABSTRACT FROM AUTHOR]

Virtual maps are becoming more and more widespread, with the role of navigation in a virtual space. A virtual map must have a unitary structure, which means that although the map contains a multitude of multimedia elements, it must be designed as a standalone structure. The technologies which are used for the virtual maps creation are constantly developing. Creating such a map is done using programs that process images, sketches to create the 3D environment and graphic design. The paper proposes a virtual map for a building with many bodies. For the physical realization of the map of the building the Autodesk 3ds Max package is used. In order to navigate in this space Adobe Flash is the chosen solution, and the route between two locations (points) is calculated using artificial intelligence techniques. [ABSTRACT FROM AUTHOR]

The event driven systems cannot be modelled and simulated with discrete time systems analysis methods. Petri nets are dedicated to event driven system analysis. The advantage of studying a system as an event driven system is that simulating it with an event driven system instrument makes possible qualitative analysis, the analysis of resource distribution and chaining of system states, even in the case the system is not yet physically implemented. This kind of analysis makes possible the correction of conflict situations in the design stage of the system. This is the case presented in the paper which discusses the improvements made after performing Petri nets analysis for rubber fabrication process. [ABSTRACT FROM AUTHOR]

The paper presents a system developed for monitoring the processes parameters from a Romanian industrial wastewater treatment plant, respectively the parameters monitoring at the plant Parshall input and chemical step output. Due to a large number of analyzed parameters, using different statistical techniques (principal components analysis, correlation) were identified the main parameters that characterizes the processes from the studied plant and the dependencies among them. Also, using data mining (decision trees) and artificial intelligence (adaptive neuro-fuzzy inference systems) techniques were deducted the rules that compose the proposed monitoring system software. In addition, it is proposed a block diagram of an extended system that for monitoring uses the interface of the developed system. [ABSTRACT FROM AUTHOR]

Modern requirements dictate the need for sustainable transportation systems, given the substantial growth in transportation activities over recent years that is predicted to persist. This surge in transportation has brought about environmental concerns such as air pollution and noise. To deal with this crisis, municipal administrations are investing in sustainable, reliable, economical, and environmentally friendly transportation systems. This review examines the latest developments in fuzzy decision systems for sustainable transport supplements. By reviewing the literature, we assess the serviceability of the entire supply chain to maintain transport quality, remove degradation, and meet customer demands. The link between fuzzy decision systems and supply chain serviceability may not be immediately obvious, but there are many reasons why putting them together can be a valuable focus for companies. By leveraging the capabilities of fuzzy decision systems to optimize supply chain processes and improve service levels, companies can gain a competitive advantage and better meet customer demand. [ABSTRACT FROM AUTHOR]

In this paper, a fuzzy controller is designed based on operating mode knowledge and it is implemented in a tank level control system. The mathematical model of the plant is experimentally obtained. An important feature of the plant is its nonlinearity. To control the level of water in the tank over the whole range, one must use three tuning parameters pairs for the PI controller that work around three different operating points. The design of a fuzzy controller that uses the plant information works within the whole range, making it more suitable for this level control. [ABSTRACT FROM AUTHOR]

Measurement and correlation of geological data is provided by depth sensors and transducers with which may be known with accuracy, at all times, the position of the drill bit into the well. This paper presents the types of depth sensors currently used in the drilling industry, associated transmitters that convert final digital data and the advantages and disadvantages of the presented types of transducers. [ABSTRACT FROM AUTHOR]

The proposed modelling approach will allow a thorough understanding of the interactions between different phenomena, human interactions and environmental factors constituting the real behaviour of manufacturing systems. Important industrial systems such as Tobacco Unloading Process Unit (TUPU) have inter-related internal process activities coexisting with external events and require a real time formalism to model them. This modelling framework is based on identifying the critical resources. The modelling goal is achieved by identifying the key points from the evolution of process states. The paper discusses the function and implementation of proposed modelling method as applicable to the industrial case of TUPU. [ABSTRACT FROM AUTHOR]

In this paper, a novel gain-scheduled sliding-mode-type (SM-type) iterative learning (IL) control approach is proposed for the high-precision trajectory tracking of mechanical systems subject to model uncertainties and disturbances. Based on the SM variable, the proposed controller is synthesized involving a feedback regulation item, a feedforward learning item, and a robust switching item. The feedback regulation item is adopted to regulate the position and velocity tracking errors, the feedforward learning item is applied to handle the model uncertainties and repetitive disturbance, and the robust switching item is introduced to compensate the nonrepetitive disturbance and linearization residual error. Moreover, the gain-scheduled mechanism is employed for both the feedback regulation item and feedforward learning item to enhance the convergence speed. Convergence analysis illustrates that the position and velocity tracking errors can eventually regulate to zero under the proposed controller. By combining the advantages of both SM control and IL control, the proposed controller has strong robustness against model uncertainties and disturbances. Lastly, simulations and comparisons are provided to evaluate the efficiency and excellent performance of the proposed control approach. [ABSTRACT FROM AUTHOR]

In this article, a neural integral sliding mode control strategy is presented for the finite-time fault-tolerant attitude tracking of rigid spacecraft subject to unknown inertia and disturbances. First, an integral sliding mode controller was developed by originally constructing a novel integral sliding mode surface to avoid the singularity problem. Then, the neural network (NN) was embedded into the integral sliding mode controller to compensate the lumped uncertainty and replace the robust switching term. In this way, the chattering phenomenon was significantly suppressed. Particularly, the mechanism of indirect neural approximation was introduced through inequality relaxation. Benefiting from this design, only a single learning parameter was required to be adjusted online, and the computation burden of the proposed controller was extremely reduced. The stability argument showed that the proposed controller could guarantee that the attitude and angular velocity tracking errors were regulated to the minor residual sets around zero in a finite time. It was noteworthy that the proposed controller was not only strongly robust against unknown inertia and disturbances, but also highly insensitive to actuator faults. Finally, the effectiveness and advantages of the proposed control strategy were validated using simulations and comparisons. [ABSTRACT FROM AUTHOR]

Computers have been used in different areas of medical technology and applications. Innovation in the field of tehnology has been considered as a fundamental consitutent of medical discipline. Advancement in the field of medical and health care results in an ease for disease diagnostic, reduction in risk of diseases and lessen pain which is eventually beneficial to human life. In this work, the designing and effect of skin puncturing of micro-needle was studied. The simulations for skin puncturing was performed in ANSYS and MATLAB fuzzy logic tool. The skin puncturing using needle based on human skin coatings including dermis, stratum corneum and viable epidermis was studied. Fuzzy logic analysis was use to study the effect of effect of applied stress and tip diameter of the needle on the three layers of skin. A 3D model of human skin layer and needle was created in ANSYS and studied for an applied force of 0.4 to 0.9 N. Thinner the tip diameter of the needle, more penetration and puncturing of skin will occur. Similarly, for applied skin, more stress is required for proper puncturing of stratum corneum layer of human skin. The microfluidic analysis performed in the CFX environment of ANSYS shows that at the driving pressure of 140 kPa, 415μL/min flow rate has been achieved. [ABSTRACT FROM AUTHOR]