Fuzzy-HLSTM (Hierarchical Long Short-Term Memory) for Agricultural Based Information Mining

This research proposes a machine learning approach using fuzzy logic to build an information retrieval system for the next crop rotation. In case-based reasoning systems, case representation is critical, and thus, researchers have thoroughly investigated textual, attribute-value pair, and ontological representations. As big databases result in slow case retrieval, this research suggests a fast case retrieval strategy based on an associated representation, so that, cases are interrelated in both either similar or dissimilar cases. As soon as a new case is recorded, it is compared to prior data to find a relative match. The proposed method is worked on the number of cases and retrieval accuracy between the related case representation and conventional approaches. Hierarchical Long Short-Term Memory (HLSTM) is used to evaluate the efficiency, similarity of the models, and fuzzy rules are applied to predict the environmental condition and soil quality during a particular time of the year. Based on the results, the proposed approaches allows for rapid case retrieval with high accuracy.     

Dynamic Bayesian networks and variable length genetic algorithm for designing cue-based model for dialogue act recognition

The automatic recognition of dialogue act is a task of crucial importance for the processing of natural language dialogue at discourse level. It is also one of the most challenging problems as most often the dialogue act is not expressed directly in speaker’s utterance. In this paper, a new cue-based model for dialogue act recognition is presented. The model is, essentially, a dynamic Bayesian network induced from manually annotated dialogue corpus via dynamic Bayesian machine learning algorithms. Furthermore, the dynamic Bayesian network’s random variables are constituted from sets of lexical cues selected automatically by means of a variable length genetic algorithm, developed specifically for this purpose. To evaluate the proposed approaches of design, three stages of experiments have been conducted. In the initial stage, the dynamic Bayesian network model is constructed using sets of lexical cues selected manually from the dialogue corpus. The model is evaluated against two previously proposed models and the results confirm the potentiality of dynamic Bayesian networks for dialogue act recognition. In the second stage, the developed variable length genetic algorithm is used to select different sets of lexical cues to constitute the dynamic Bayesian networks’ random variables. The developed approach is evaluated against some of the previously used ranking approaches and the results provide experimental evidences on its ability to avoid the drawbacks of the ranking approaches. In the third stage, the dynamic Bayesian networks model is constructed using random variables constituted from the sets of lexical cues generated in the second stage and the results confirm the effectiveness of the proposed approaches for designing dialogue act recognition model.     

Multimodal fusion for multimedia analysis: a survey

This survey aims at providing multimedia researchers with a state-of-the-art overview of fusion strategies, which are used for combining multiple modalities in order to accomplish various multimedia analysis tasks. The existing literature on multimodal fusion research is presented through several classifications based on the fusion methodology and the level of fusion (feature, decision, and hybrid). The fusion methods are described from the perspective of the basic concept, advantages, weaknesses, and their usage in various analysis tasks as reported in the literature. Moreover, several distinctive issues that influence a multimodal fusion process such as, the use of correlation and independence, confidence level, contextual information, synchronization between different modalities, and the optimal modality selection are also highlighted. Finally, we present the open issues for further research in the area of multimodal fusion.     

Numerical study of asymmetric laminar flow of micropolar fluids in a porous channel

A numerical study is presented for the two-dimensional flow of a micropolar fluid in a porous channel. The channel walls are of different permeability. The fluid motion is superimposed by the large injection at the two walls and is assumed to be steady, laminar and incompressible. The micropolar model due to Eringen is used to describe the working fluid. The governing equations of motion are reduced to a set of non-linear coupled ordinary differential equations (ODEs) in dimensionless form by using an extension of Berman’s similarity transformations. A numerical algorithm based on finite difference discretization is employed to solve these ODEs. The results obtained are further improved by Richardson’s extrapolation for higher order accuracy. Comparisons with the previously published work are performed and are found to be in a good agreement. It has been observed that the velocity and microrotation profiles change from the most asymmetric shape to the symmetric shape across the channel as the parameter R or the permeability parameter A are varied between their extreme values. The results indicate that larger the injection velocity at a wall relative to the other is, smaller will be the shear stress at it than that at the other. The position of viscous layer has been found to be more sensitive to the permeability parameter A than to the parameter R. The micropolar fluids reduce shear stress and increase couple stress at the walls as compared to the Newtonian fluids.     

Real-Time Natural Disasters Detection and Monitoring from Smart Earth Observation Satellite

Current remote sensing satellites with multispectral sensors capture high-resolution images and produce vast quantities of data. The size and volume of this information has dramatically increased in the last decade as sensor resolution and capabilities have significantly improved, without a similar improvement on the satellite system capacity to accommodate these changes. Remote sensing satellites currently operate on a “store and forward” paradigm, where data is stored on the satellite until the satellite is in view of the ground station. Low Earth orbit satellites may only see a ground station for a 10–15 min window per pass, in which time all the collected information must be telemetered to the ground. This process requires large and expensive onboard storage resources and places tremendous stress on communication channels. Hence, a complete image may not be successfully telemetered in one pass causing a significant delay between capture and analysis and limiting the benefits of these images. Smart satellites are more technologically advanced, require less ground station support and data storage, and are capable of transmitting required information quickly and easily to ground stations. With onboard reconfigurable data processing, these satellites have faster data product turnaround, less communication requirements, and provide more useful information. The high performance computing (HPC-I) payload on board the Australian satellite FedSat, launched in December 2002, is a demonstration device of the feasibility of reconfigurable computing technology in space. This device is small in size, requires low power, and has the processing capacity to handle large data volumes. Using this device in conjunction with a high-resolution imaging sensor, such as the bispectral infrared detection (BIRD) sensor, smart dedicated satellites become a feasible and cost effective solution to remote sensing needs. This paper elaborates on the system level design of a real-time fire observation system in the context of a smart satellite mission for detecting and monitoring natural disasters. The proposed system is built upon flight tested field programmable gate arrays based HPC-I technology, and would be capable of producing useful information about natural disasters directly broadcasted to interested parties within rapid timeframes. The algorithms for onboard real-time detection of direction, intensity, and location of fires are discussed, and reliable algorithms for detecting and verifying these fires using smoke plume detection are presented. Further work is described including fire-front analysis and the tracking of fire movement.     

On the SPH tensile instability in forming viscous liquid drops

Smoothed Particle Hydrodynamics (SPH) simulations of elastic solids and viscous fluids may suffer from unphysical clustering of particles due to the tensile instability. Recent work has shown that in simulations of elastic or brittle solids the instability can be removed by an artificial stress whose form is derived from a linear perturbation analysis of the full set of governing SPH equations. While a linear analysis cannot be used to derive the corresponding form of the artificial stress for a viscous fluid, here we show that the same construction which applies to elastic solids may also work for viscous fluids provided that the constant parameter ? entering in the definition of the artificial stress is properly chosen. As a suitable test case, we model the formation of a circular van der Waals liquid drop and show that the tensile instability is removed when an artificial viscous force and energy generation term are added to the standard SPH equations of motion and energy, respectively. The optimal value of the constant ? is constrained by the ability of the model simulation to reproduce both a sufficiently smoothed density profile and the van der Waals phase diagram.     

Recent developments in catalyst synthesis using DBD plasma for reforming applications

The catalyst has a significant role in gas processing applications such as reforming technologies for H₂ and syngas production. The stable catalyst is requisite for any industrial catalysis application to make it commercially viable. Several methods are employed to synthesize the catalysts. However, there is still a challenge to achieve a controlled morphology and pure catalyst which majorly influences the catalytic activity in reforming applications. The conventional methods are expansive, and the removal of the impurities are major challenges. Nevertheless, it is not straightforward to achieve the desired structure and stability. Therefore, significant interest has been developed on the advanced techniques to take control of the physicochemical properties of the catalyst through non-thermal plasma (NTP) techniques. In this review, the systematic evolution of the catalyst synthesis using NTP technique is elucidated. The emerging DBD plasma to synthesized and effective surface treatment is reviewed. DBD plasma synthesized catalyst performance in reforming application for H₂ and syngas production is summarised. Furthermore, the status of DBD plasma for catalyst synthesis and proposed future avenues to design environmentally suitable and cost-effective synthesis techniques are discussed.     

Polymer Membrane Electrodes for Sensitive Potentiometric Determination of β-blockers

ABSTRACT

The construction of PVC matrix-type β-blockers (sotalol, carvedilol, and betaxolol) ion selective electrodes and their use for direct potentiometry of their respective species are described. The proposed sensors are based on the complex ion associates of β-blockers with tungstophosphate (TP) and Ammonium Reineckate (Rein) ionophoris in poly vinyl chloride membrane (PVC) with Dioctylphthalate (DOP) plasticizer. The four electrodes (Beta-TP), (Sota-TP), (Carve-TP), and (Cave-Rein) show stable potential response with near Nernstian slope of 50.8, 33.7, 32.35, and 33 mv per decade, range of concentration 10?2–10?7 M β-blockers. Selectivity coefficients data obtained for 11 different organic and inorganic ions are presented. The electrodes have fast response time (30 and 40 s) and were used over wide range of pH 4.5–8.5. Validation of the method according to the quality assurance standers shows suitability of proposed sensors for use in the quality control assessment of these drugs. The results obtained for the determination of β-blockers with the proposed electrodes show average recoveries of 100.78% and a mean standard deviation of ±1.2. The nominal are obtained. The data agree well with those obtained by standard methods.     

Mathematical modelling of abrasive waterjet footprints for arbitrarily moving jets: Part I—single straight paths

It is notoriously well-known that abrasive waterjet milling (AWJM) is difficult to perform controlled-depth owing to variable geometries of the footprints that depends not only on jet energy and the exposure time upon the workpiece, but also on the orientation of the jet relative to the target surface. An attempt is made to develop a model that can be generally applied to different machine system and to predict individual jet footprints that are one of the key steps for controlled-depth AWJM. To address this, the paper breaks new ground in geometrical modelling of AWJM with the benefit of having few variables for predicting the footprints obtained under the following conditions: (i) any time exposures (i.e. V_f, jet feed speeds); (ii) jet orientations (θ) relative to the target surface; (iii) arbitrarily moving straight jet-paths (β). These conditions reflect the real industrial conditions under which the process is run. The geometrical model results in a non-linear partial differential equation, a method to evaluate the material specific erosion rate from the characteristics of a shallow trench obtained experimentally using high jet feed speeds. Under these conditions, the governing equations can be linearised and solved analytically.The model validation for full profile of trenches generated at various tilt angles (θ=70-90°), jet feed rates (V_f=500-1000 mm/min) and jet path directions (β=0-270°) indicates that a high degree of accuracy (mean of the residuals R_M<3% and root-mean-square error of residuals R_RMS<6%) has been achieved. This innovative footprint modelling approach has the key advantage of being independent of the properties of the workpiece material and/or machine setup, since it calibrates the specific etching rate. By considering any orientation of the jet plume vector relative to the target surface, this approach becomes a powerful tool for the development of advanced jet path strategies to enable AWJM of complex geometries.