A hybrid multiple feature construction approach for classification using Genetic Programming

The purpose of feature construction is to create new higher-level features from original ones. Genetic Programming (GP) was usually employed to perform feature construction tasks due to its flexible representation. Filter-based approach and wrapper-based approach are two commonly used feature construction approaches according to their different evaluation functions. In this paper, we propose a hybrid feature construction approach using genetic programming (Hybrid-GPFC) that combines filter’s fitness function and wrapper’s fitness function, and propose a multiple feature construction method that stores top excellent individuals during a single GP run. Experiments on ten datasets show that our proposed multiple feature construction method (Fcm) can achieve better (or equivalent) classification performance than the single feature construction method (Fcs), and our Hybrid-GPFC can obtain better classification performance than filter-based feature construction approaches (Filter-GPFC) and wrapper-based feature construction approaches (Wrapper-GPFC) in most cases. Further investigations on combinations of constructed features and original features show that constructed features augmented with original features do not improve the classification performance comparing with constructed features only. The comparisons with three state-of-art methods show that in majority of cases, our proposed hybrid multiple feature construction approach can achieve better classification performance.     

Structure and phase-composition of Ti-doped gas atomized Raney-type Ni catalyst precursor alloys

Raney-type Ni precursor alloys containing 75 at.% Al and doped with 0, 0.75, 1.5 and 3.0 at.% Ti have been produced by a gas atomization process. The resulting powders have been classified by size fraction with subsequent investigation by powder XRD, SEM and EDX analysis. The undoped powders contain, as expected, the phases Ni₂Al₃, NiAl₃ and an Al-eutectic. The Ti-doped powders contain an additional phase with the TiAl₃ DO₂₂ crystal structure. However, quantitative analysis of the XRD results indicate a far greater fraction of the TiAl₃ phase is present than could be accounted for by a simple mass balance on Ti. This appears to be a (Ti_xNi_1−x)Al₃ phase in which higher cooling rates favour small x (low Ti-site occupancy by Ti atoms). SEM and EDX analysis reveal that virtually all the available Ti is contained within the TiAl₃ phase, with negligible Ti dissolved in either the Ni₂Al₃ or NiAl₃ phases.     

Usability of a cloud-based collaborative learning framework to improve learners’ experience

Computer-Supported Collaborative Learning (CSCL) is concerned with how Information and Communication Technology (ICT) might facilitate learning in groups which can be co-located or distributed over a network of computers such as Internet. CSCL supports effective learning by means of communication of ideas and information among learners, collaborative access of essential documents, and feedback from instructors and peers on learning activities. As the cloud technologies are increasingly becoming popular and collaborative learning is evolving, new directions for development of collaborative learning tools deployed on cloud are proposed. Development of such learning tools requires access to substantial data stored in the cloud. Ensuring efficient access to such data is hindered by the high latencies of wide-area networks underlying the cloud infrastructures. To improve learners’ experience by accelerating data access, important files can be replicated so a group of learners can access data from nearby locations. Since a cloud environment is highly dynamic, resource availability, network latency, and learner requests may change. In this paper, we present the advantages of collaborative learning and focus on the importance of data replication in the design of such a dynamic cloud-based system that a collaborative learning portal uses. To this end, we introduce a highly distributed replication technique that determines optimal data locations to improve access performance by minimizing replication overhead (access and update). The problem is formulated using dynamic programming. Experimental results demonstrate the usefulness of the proposed collaborative learning system used by institutions in geographically distributed locations.     

A miniature triaxial apparatus for investigating the micromechanics of granular soils with in situ X-ray micro-tomography scanning

The development of a miniature triaxial apparatus is presented. In conjunction with an X-ray micro-tomography (termed as X-ray μCT hereafter) facility and advanced image processing techniques, this apparatus can be used for in situ investigation of the micro-scale mechanical behavior of granular soils under shear. The apparatus allows for triaxial testing of a miniature dry sample with a size of \mathrm{8}\hspace{0.17em}\mathrm{mm}\times \mathrm{16}\hspace{0.17em}\mathrm{mm} (diameter \times height). In situ triaxial testing of a 0.4–0.8 mm Leighton Buzzard sand (LBS) under a constant confining pressure of 500 kPa is presented. The evolutions of local porosities (i.e., the porosities of regions associated with individual particles), particle kinematics (i.e., particle translation and particle rotation) of the sample during the shear are quantitatively studied using image processing and analysis techniques. Meanwhile, a novel method is presented to quantify the volumetric strain distribution of the sample based on the results of local porosities and particle tracking. It is found that the sample, with nearly homogenous initial local porosities, starts to exhibit obvious inhomogeneity of local porosities and localization of particle kinematics and volumetric strain around the peak of deviatoric stress. In the post-peak shear stage, large local porosities and volumetric dilation mainly occur in a localized band. The developed triaxial apparatus, in its combined use of X-ray μCT imaging techniques, is a powerful tool to investigate the micro-scale mechanical behavior of granular soils.     

Effect of spatial constraints on the phase evolution of YFeO3-based nanopowders under heat treatment of glycine-nitrate combustion products

Formation and structural transformations of yttrium orthoferrite crystals have been studied using X-ray diffractometry, Mössbauer spectroscopy and transmission electron microscopy combined with electron microdiffraction. Said processes have been studied under heat treatment of glycine-nitrate combustion products. There have been identified formations of three structural yttrium orthoferrite modifications – amorphized hexagonal <h₁>-YFeO₃ (P6₃cm) and nanocrystalline hexagonal h₂-YFeO₃ (P6₃/mmc), as well as nanocrystalline orthorhombic o-YFeO₃ (Pbnm), which are selectively formed depending on available three-dimensional confinements. Based on the analysis of changes in the fluid and size composition formulation, it has been proposed mechanism for formation and transformation of YFeO₃ nanocrystals, including growth stage of h₂-YFeO₃ crystals due to amorphized phase of <h₁>-YFeO₃ up to critical size of about 15?nm and their subsequent transformation into orthorhombic form o-YFeO₃.     

Operational time-series data modeling via LSTM network integrating principal component analysis based on human experience

Today’s information technologies involve increasingly intelligent systems, which come at the cost of increasingly complex equipment. Modern monitoring systems collect multi-measuring-point and long-term data which make equipment health prediction a “big data” problem. It is difficult to extract information from such condition monitoring data to accurately estimate or predict health statuses. Deep learning is a powerful tool for big data processing that is widely utilized in image and speech recognition applications, and can also provide effective predictions in industrial processes. This paper proposes the Long Short-term Memory Integrating Principal Component Analysis based on Human Experience (HEPCA-LSTM), which uses operational time-series data for equipment health prognostics. Principal component analysis based on human experience is first conducted to extract condition parameters from the condition monitoring system. The long short-term memory (LSTM) framework is then constructed to predict the target status. Finally, a dynamic update of the prediction model with incoming data is performed at a certain interval to prevent any model misalignment caused by the drifting of relevant variables. The proposed model is validated on a practical case and found to outperform other prediction methods. It utilizes a powerful deep learning analysis method, the LSTM, to fully process big condition monitoring series data; it effectively extracts the features involved with human experience and takes dynamic updates into consideration.     

Precipitating spinel into precursor glass and its assistance in crystallization

The crystallization phenomena of spinel in CaO-MgO-Al₂O₃-SiO₂-Fe₂O₃ glass have received much attention due to the particular role in preparation of glass-ceramic materials, which represent an effective option to manage hazardous waste. In this study, both preliminary spinel and secondary spinel were precipitated in the precursor glass. The formation of these spinel was meticulously assessed by a combination of X-ray diffractometry and scanning electron microscopy. The structure of the microenvironment in the precursor glass was characterized by Raman spectrums. These advanced techniques highlight the potential for one-step crystallization of the glass. The investigation, which focused on one-step crystallization, demonstrated the growth of pyroxene on spinel accompanying a migration of chromium. The results also show the microstructure of the obtained glass-ceramic was very dependent on the heat-treat temperature. This study not only unambiguously reveals the precipitation mechanisms of spinel but also provides more documentation for one-step crystallization in the glass-ceramics field.     

Ions motion algorithm for solving optimization problems

This paper proposes a novel optimization algorithm inspired by the ions motion in nature. In fact, the proposed algorithm mimics the attraction and repulsion of anions and cations to perform optimization. The proposed algorithm is designed in such a way to have the least tuning parameters, low computational complexity, fast convergence, and high local optima avoidance. The performance of this algorithm is benchmarked on 10 standard test functions and compared to four well-known algorithms in the literature. The results demonstrate that the proposed algorithm is able to show very competitive results and has merits in solving challenging optimization problems.     

Restructuring bank networks after mergers and acquisitions: A capacitated delocation model for closing and resizing branches

During restructuring processes, due to mergers and acquisitions, banks frequently face the problem of having redundant branches competing in the same market. In this work, we introduce a new Capacitated Branch Restructuring Model which extends the available literature in delocation models. It considers both closing down and long term operations׳ costs, and addresses the problem of resizing open branches in order to maintain a constant service level. We consider, as well, the presence of competitors and allow for ceding market share whenever the restructuring costs are prohibitively expensive.We test our model in a real life scenario, obtaining a reduction of about 40% of the network size, and annual savings over 45% in operation costs from the second year on. We finally perform a sensitivity analysis on critical parameters. This analysis shows that the final design of the network depends on certain strategic decisions concerning the redundancy of the branches, as well as their proximity to the demand nodes and to the competitor׳s branches. At the same time, this design is quite robust to changes in the parameters associated with the adjustments on service capacity and with the market reaction.     

Producing fully-lamellar microstructure for wrought beta-gamma TiAl alloys without single α-phase field

Fine-grained fully-lamellar (FL) microstructure is desired for TiAl components to serve as compressor/turbine blades and turbocharger turbine wheels. This study deals with the process and phase transformation to produce FL microstructure for Mo stabilized beta-gamma TiAl alloys without single α-phase field. Unlike the α + γ two-phased TiAl or beta-gamma TiAl with single α-phase field, the wrought multi-phase TiAl–4/6Nb–2Mo–B/Y alloys exhibit special annealing process to obtain FL microstructure. Short-term annealing at temperatures slightly above β-transus is recommended to produce the desired FL microstructure. The related mechanism is to guarantee the sufficient diffusion homogenization of β stabilizers during single β-phase annealing, and further avoid α decomposition by α → γ + β when cooling through α + β + γ phase field. The colony boundary β phase contributes to fine-grained nearly FL microstructure, by retarding the coarsening of the α phase grains.