Search

Twin support vector regression (TSVR) has been widely applied in regression problems. TSVR seeks a pair of ε -insensitive proximal planes by solving two support vector machine type problems. TSVR assumes that the matrices appearing in the dual formulation are positive definite. However, in real-world scenarios, such an assumption may not be fulfilled and, hence, leads to suboptimal performance. ε -Twin support vector regression (ε -TSVR) improved the TSVR by introducing the regularisation term to avoid the singularity issues. Most of the twin support vector machine models involve the computation of matrix inverses. Also, TSVR implements the empirical risk minimization principle. In this paper, we propose an improved twin support vector regression (ITSVR) for brain age estimation by introducing different Lagrangian functions for the primal problems of the TSVR. The proposed ITSVR implements the structural risk minimization principle and avoids the computation of the matrix inverses. To solve the optimization problem more efficiently, we used successive overrelaxation (SOR) technique. We evaluated the proposed ITSVR on cognitively healthy subjects, mild cognitive impairment subjects and Alzheimer's disease subjects. The experimental results demonstrate that the proposed ITSVR has superior performance compared to the baseline models for brain age estimation. [ABSTRACT FROM AUTHOR]

Simulation models are often employed for guiding compressor prototype development, particularly for novel devices like the spool compressor. The spool compressor is a novel compressor technology that can provide competitive performance for low-pressure refrigerants (like R1234ze(E)) with a compact design. A parametric study is presented to find the optimum geometric aspect ratio for five refrigerants (CO 2 , R134a, R454B, R468B and R1234ze(E)) and a range of cooling capacities between 1-100 RT. A pseudo-optimum geometry is explored by varying the aspect ratio, defined by the eccentricity ratio (rotor diameter to bore diameter), and the compressor L/D ratio (axial length to bore diameter), varying from 0.75-0.8 and 0.4-3, respectively. A scaling model is developed to vary the compressor geometry and ports. A spool compressor model, developed by Bradshaw and Groll (2013), is extended and by validating the model using data from 30 RT and 40 RT prototype compressors using R134a and R1234ze(E). The model is then used to predict the performance of a spool compressor with the various geometric inputs and refrigerants. The results suggest that the volumetric and isentropic efficiencies can be maximized by using an eccentricity ratio of 0.75 and L/D ratios from 1-1.5 for various displacement volumes. The results showed that the optimum isentropic efficiency increases asymtoptically from 1 to 100 RT for most working fluids and it increases linearly for CO 2. Additionally, the compressor performance becomes insensitive to the aspect ratio for large compressor sizes. [ABSTRACT FROM AUTHOR]

Retinal image analysis is an integral and fundamental step towards the identification and classification of ocular diseases like glaucoma, diabetic retinopathy, macular edema, and cardiovascular diseases through computer-aided diagnosis systems. Various abnormalities are observed through retinal image modalities like fundus, fluorescein angiography, and optical coherence tomography by ophthalmologists, and computer science professionals. Retinal image analysis has gained a lot of importance in recent years due to advances in computational, storage, and image acquisition technologies. Better computational capabilities lead to a rise in the implementation of deep learning-based methods for ocular disease detection. Although deep learning promises better performance in this field, some issues like lack of well-labeled datasets, unavailability of large enough datasets, class imbalance, and model generalizability are yet to be addressed. Also, the real-time implementation of detection methods on new devices or existing hardware is an untouched area. This article highlights the development of retinal image analysis and related issues due to the introduction of AI-based methods. The methods are analyzed in terms of standard performance metrics on various publicly and privately available datasets. [ABSTRACT FROM AUTHOR]

Electroencephalogram (EEG) have been widely used for the diagnosis of neurological diseases like epilepsy and sleep disorders. Support vector machines (SVMs) are widely used classifiers for the classification of EEG signals due to their better generalization performance. However, SVM suffers due to high computational complexity. To reduce the computations, twin support vector machines (TWSVM) solved smaller size quadratic optimization problems. To enhance the performance of the SVM and TWSVM models, prior information known as universum data has been incorporated in the universum SVM (USVM) and universum twin (UTSVM) models. Both SVM and UTSVM employ hinge loss which results in sensitivity to noise and instability. To overcome these issues and incorporate the prior information of the EEG signals, we propose a novel universum twin support vector machine with pinball loss function (Pin-UTSVM) for the classification of EEG signals. The proposed Pin-UTSVM is more stable for resampling and is noise insensitive. Furthermore, the computational complexity of proposed Pin-UTSVM model is similar to the standard UTSVM model. In the proposed approach, we used the interictal EEG signal as the universum data. Numerical experiments at varying level of noise show that the proposed Pin-UTSVM is more robust to noise compared to standard models. To show the efficiency of the proposed Pin-UTSVM model, we used multiple feature extraction techniques for the classification of the EEG signal. Experimental results reveal that the proposed Pin-UTSVM model is performing better compared to the existing models. Moreover, statistical tests show that the proposed Pin-UTSVM model is significantly better in comparison with the existing baseline models. [ABSTRACT FROM AUTHOR]

Over the years, Machine Learning models have been successfully employed on neuroimaging data for accurately predicting brain age. Deviations from the healthy brain aging pattern are associated with the accelerated brain aging and brain abnormalities. Hence, efficient and accurate diagnosis techniques are required to elicit accurate brain age estimations. Several contributions have been reported in the past for this purpose, resorting to different data-driven modeling methods. Recently, deep neural networks (also referred to as deep learning) have become prevalent in manifold neuroimaging studies, including brain age estimation. In this review, we offer a comprehensive analysis of the literature related to the adoption of deep learning for brain age estimation with neuroimaging data. We detail and analyze different deep learning architectures used for this application, pausing at research works published to date quantitatively exploring their application. We also examine different brain age estimation frameworks, comparatively exposing their advantages and weaknesses. Finally, the review concludes with an outlook towards future directions that should be followed by prospective studies. The ultimate goal of this paper is to establish a common and informed reference for newcomers and experienced researchers willing to approach brain age estimation by using deep learning models. • We categorize brain age estimation models based on the deep learning architectures. • We classify deep learning architectures based on the slice/voxel-based input data. • We examine the modalities, size of data, performance and the datasets used. • We enumerate several challenges and trace directions that can be explored further. [ABSTRACT FROM AUTHOR]

The evolution of computer resources paved the way for numerical models to substitute extensive experimental campaigns to develop and optimize compressors for the HVAC&R industry. A particular class of compressor models referred to as mechanistic (or deterministic) chamber model is well-known to be computationally efficient and has reasonable model fidelity for performance prediction and extrapolation. The overall model architecture requires inputs from various sub-models, including the mass flow, heat transfer and valve models. The accuracy of the overall model depends on the fidelity and accuracy of the individual sub-models. This article provides a comprehensive review of the different approaches available in literature which were used to model the geometry, mass flow, valves, and heat transfer processes in the compressor. The article aims to help researchers identify suitable approaches for their analysis. Additionally, it was found that there are opportunities for additional research to develop analytical correlations for discharge coefficients for the mass flow model, explore solubility in leakage gaps, develop effective flow/force area estimation for valve models, and develop instantaneous heat transfer coefficients for specific compressor architectures and thermal conductance models for multi-lumped network models. [ABSTRACT FROM AUTHOR]

Random Forest is an ensemble of decision trees based on the bagging and random subspace concepts. As suggested by Breiman, the strength of unstable learners and the diversity among them are the ensemble models' core strength. In this paper, we propose two approaches known as oblique and rotation double random forests. In the first approach, we propose rotation based double random forest. In rotation based double random forests, transformation or rotation of the feature space is generated at each node. At each node different random feature subspace is chosen for evaluation, hence the transformation at each node is different. Different transformations result in better diversity among the base learners and hence, better generalization performance. With the double random forest as base learner, the data at each node is transformed via two different transformations namely, principal component analysis and linear discriminant analysis. In the second approach, we propose oblique double random forest. Decision trees in random forest and double random forest are univariate, and this results in the generation of axis parallel split which fails to capture the geometric structure of the data. Also, the standard random forest may not grow sufficiently large decision trees resulting in suboptimal performance. To capture the geometric properties and to grow the decision trees of sufficient depth, we propose oblique double random forest. The oblique double random forest models are multivariate decision trees. At each non-leaf node, multisurface proximal support vector machine generates the optimal plane for better generalization performance. Also, different regularization techniques (Tikhonov regularization, axis-parallel split regularization, Null space regularization) are employed for tackling the small sample size problems in the decision trees of oblique double random forest. The proposed ensembles of decision trees produce trees with bigger size compared to the standard ensembles of decision trees as bagging is used at each non-leaf node which results in improved performance. The evaluation of the baseline models and the proposed oblique and rotation double random forest models is performed on benchmark 121 UCI datasets and real-world fisheries datasets. Both statistical analysis and the experimental results demonstrate the efficacy of the proposed oblique and rotation double random forest models compared to the baseline models on the benchmark datasets. [ABSTRACT FROM AUTHOR]

Class imbalance and noise present significant challenges in numerous real-world classification tasks. The prevalence of an uneven distribution of samples typically results in a bias towards the majority class in Support Vector Machine (SVM) classifiers, compounded by the often inherent noise within these samples. Addressing both class imbalance and noise, we introduce two fuzzy-based methodologies. The first method employs intuitionistic fuzzy membership, resulting in the development of the Robust Energy-based Intuitionistic Fuzzy Least Squares Twin Support Vector Machine (IF-RELSTSVM), a model specifically designed for class imbalance learning. The IF-RELSTSVM model is distinguished by its use of intuitionistic fuzzy scores for both classes, significantly attenuating the detrimental effects of noise and outliers. A distinctive attribute of IF-RELSTSVM is its proficiency in processing noisy data points, whether proximate to or distant from the hyperplane. Additionally, we introduce a novel concept of hyperplane-based fuzzy membership, calculating fuzzy memberships through a projection-based approach. This foundation supports the formulation of a Robust Energy-based Fuzzy Least Squares Twin Support Vector Machine (F-RELSTSVM), also aimed at class imbalance learning. The efficacy of the proposed IF-RELSTSVM and F-RELSTSVM algorithms is rigorously evaluated across several benchmark and synthetic datasets, employing the Area Under the ROC Curve (AUC) as a performance metric. Experimental findings indicate that these algorithms surpass baseline models in the majority of datasets tested. Statistical analyses further validate the significance of our proposed methods, demonstrating their suitability for application in environments characterized by noise and class imbalance. A case study in credit card fraud detection showcases the F-RELSTSVM algorithm achieving an impressive average AUC of 90.84%, thereby outperforming comparable algorithms and highlighting the practical applicability of our approaches in tackling challenging datasets. [ABSTRACT FROM AUTHOR]

Cd x Zn 1-x Mg 0.25 Fe 1.75 O 4 (where x = 0.00, 0.25, 0.50, 0.75, 1.00) have been successfully produced by a facile hydrothermal technique for a thorough comparison of structural, optical, and photocatalytic properties (degradation of Rhodamine B -RhB dye under visible light irradiation). X-ray Diffraction (XRD), Scanning Electron Microscopy (SEM) and Transmission Electron Microscopy (TEM) confirmed the formation of cubic spinel structure for all of the samples. Fourier transform infrared (FTIR) spectroscopy verified the presence of metal-oxygen (M–O) bonding in the prepared samples with two frequency bands corresponding to phonon vibrational stretching in both the octahedral and tetrahedral lattice positions. UV–Visible Spectrophotometer and photoluminescence (PL) spectroscopy investigated the bandgap variation (2.7 eV-1.7 eV) and emission spectrum peaks appearing in the range of 405–471 nm region. The comparison in the photo-degradation of Rhodamine B (RhB) revealed the superior performance (98% degradation of RhB dye in 80 min having a K value of 0.04966 with excellent reusability) of Cd 0.50 Zn 0.50 Mg 0.25 Fe 1.75 O 4 sample having 50/50 dopant ratio of Cd and Zn in the parent Mg Ferrite, attributed to the lowest bandgap, longer lifetime of charge carriers, active octahedral lattice site, electron/hole pair recombination preventions, and the least value of ohmic impedance at higher frequency. [ABSTRACT FROM AUTHOR]

K -nearest neighbor (KNN) based weighted multi-class twin support vector machines (KWMTSVM) is a novel multi-class classification method. In this paper, we propose a novel least squares version of KWMTSVM called LS-KWMTSVM by replacing the inequality constraints with equality constraints and minimized the slack variables using squares of 2-norm instead of conventional 1-norm. This simple modification leads to a very fast algorithm with much better results. The modified primal problems in the proposed LS-KWMTSVM solves only two systems of linear equations whereas two quadratic programming problems (QPPs) need to solve in KWMTSVM. The proposed LS-KWMTSVM, same as KWMTSVM, employed the weight matrix in the objective function to exploit the local information of the training samples. To exploit the inter class information, we use weight vectors in the constraints of the proposed LS-KWMTSVM. If any component of vectors is zero then the corresponding constraint is redundant and thus we can avoid it. Elimination of redundant constraints and solving a system of linear equations instead of QPPs makes the proposed LS-KWMTSVM more robust and faster than KWMTSVM. The proposed LS-KWMTSVM, commensurate as the KWMTSVM, all the training data points into a "1-versus-1-versus-rest" structure, and thus our LS-KWMTSVM generate ternary output { - 1 , 0 , + 1 } which helps to deal with imbalance datasets. Numerical experiments on several UCI and KEEL imbalance datasets(with high imbalance ratio) clearly indicate that the proposed LS-KWMTSVM has better classification accuracy compared with other baseline methods but with remarkably less computational time. [ABSTRACT FROM AUTHOR]

• Method to scale the scroll compressor for different cooling capacities and refrigerants. • Validation of scroll compressor model in PDSim. • Performance evaluation of low-GWP refrigerants in scroll compressor. Performance evaluation of low-GWP refrigerants in scroll compressor is carried out to aid the selection of suitable refrigerant for different applications. The open-source modeling platform PDSim, used for this study, is based on the mechanistic chamber model that has the accuracy comparable to the heuristic methods. A scaling model is developed to design and select the scroll geometry for 1–100 ton range of cooling capacity and seven refrigerants. This method is based on manufacturing constraints and minimization of leakage. Additionally, the ports and the bearings are scaled to make their effect fair for a range of capacities and refrigerants. The simulation model is validated using two example scroll compressors. The predicted mass flow rate and power are within 3% MAE while the isentropic efficiency is within 4% mean absolute error. A validated model and standard AHRI conditions are used for the performance evaluation of the refrigerants over a range of 1 to 100 tons of refrigeration capacity. Seven refrigerants are studied including low-pressure refrigerants, R1234ze(E) and R1234yf, medium-pressure refrigerants, R410A, R32, R454B, and R452B and high-pressure R744. The results suggest that an optimum range exists for each refrigerant to achieve good compressor performance. The leakage area is the primary contributor to the scroll compressor performance. [ABSTRACT FROM AUTHOR]

The proposed study was designed to assess the phytotherapic potential of locally cultivated fennel seeds against certain lifestyle associated disarrays. Fennel seed powder was subjected to conventional solvent extraction (CSE) and supercritical fluid extraction (SFE), followed by evaluation of health improving perspectives of fennel extracted phytoconstituents. The in vivo phase comprised of five studies with three groups in each based upon the diets i.e. control (D0), nutraceuticalCSE (D1), and nutraceuticalSFE (D2). The five studies included in the experiment were control, ulcerogenic, inflammatory, hepatotoxicity, and nephrotoxicity. NutraceuticalSFE showed highest decline in gastric juice volume, gastric juice acidity and ulcer index (63.54, 47.33, and 51.65%, respectively) followed by nutraceuticalCSE (41.09, 27.63, and 38.71%, respectively) in ulcerogenic study. Likewise, the maximum decline in paw edema was observed in inflammatory study, as 30.43% and 24.54%, in D2 and D1, respectively. For study IV, the maximum decline in ALT, ALP, AST and bilirubin value was recorded during hepatotoxic study among all other studies i.e. 10.90 & 18.49%, 11.94 & 20.37%, 9.49 & 13.49% and 12.39 & 16.57% for D1 and D2, respectively. A maximum reduction in urea, uric acid and creatinine was found in study V i.e. 20.57 & 28.40%, 20.74 & 33.60% and 14.18 & 23.88%, in D1 and D2 groups, respectively, among all studies. From the findings of the current study, it can by concluded that fennel-based extracts (nutraceuticalCSE and nutraceuticalSFE) are effectual to alleviate from the burden of lifestyle related disorders. [ABSTRACT FROM AUTHOR]

• 0-D/1-D compressor model. • PDSim. • Programming platforms evaluation. Several regulatory measures aimed to mitigate climate change are forcing compressor manufacturers to replace current refrigerants to those with low Global Warming Potential (GWP). New refrigerants need to be evaluated to ensure adequate efficiency for use in modern products. Evaluation can be done heuristically, which is expensive and time-consuming, while a carefully designed simulation model can provide similar outcomes for a significantly reduced cost. This paper presents a comparison between various user-developed and existing reciprocating compressor models to assist in the selection of a suitable modeling platform for a wide-ranging study. The reciprocating compressor is selected because of the simplicity of the model to ensure consistency across different platforms. The user-developed models are developed in MATLABTM and ModelicaTM for the reciprocating compressor. The same compressor is also modeled using existing compressor modeling platforms, PDSim and GT-SuiteTM. The compressor model includes three main components; geometry, compression process and frictional losses. Other sub-models, like valve model and heat transfer model, are also part of the compression process. These platforms are evaluated based on both quantitative and qualitative criteria. ModelicaTM is found to be computationally efficient while GT-SuiteTM took maximum time for simulation among the compared platforms. On a qualitative basis, PDSim is potentially a better platform for compressor optimization; which is also readily available to end user due to its open-source nature and prospects for future model development. [ABSTRACT FROM AUTHOR]

This paper aims to evaluate the base–emitter forward characteristics of In0.52Al0.48As/In0.53Ga0.47As heterojunction bipolar transistors using numerical simulations in Silvaco while comparing results with fabricated devices. Analysis drawn from simulations reveals that in addition to doping, thickness of emitter and spacer region also plays an important role in determining the operational behaviour of device. The thickness of spacer region strongly influences the nature of heterojunction barrier formed that in turn controls the injection efficiency and dictates various recombination mechanisms. Even a few angstroms added to a spacer layer can cause considerable shift in DC characteristics. Methodology of device modelling is first validated by matching simulated results with the experimental measurements of two different structures. Spacer thickness and emitter doping is then varied in each of the structures to comprehensively study the effect of these variations onto important DC figures of merit. [ABSTRACT FROM AUTHOR]

Machine learning methods are extensively used for processing and analysing speech signals by virtue of their performance gains over multiple domains. Deep learning and ensemble learning are the two most commonly used techniques, which results in benchmark performance across different downstream tasks. Ensemble deep learning is a recent development which combines these two techniques to result in a robust architecture having substantial performance gains, as well as better generalization performance over the individual techniques. In this paper, we extensively review the use of ensemble deep learning methods for different speech signal related tasks, ranging from general objectives such as automatic speech recognition and voice activity detection, to more specific areas such as biomedical applications involving the detection of pathological speech or music genre detection. We provide a discussion on the use of different ensemble strategies such as bagging, boosting and stacking in the context of speech signals, and identify the various salient features and advantages from a broader perspective when coupled with deep learning architectures. The main objective of this study is to comprehensively evaluate existing works in the area of ensemble deep learning, and highlight the future directions that may be explored to further develop it as a tool for several speech related tasks. To the best of our knowledge, this is the first review study which primarily focuses on ensemble deep learning for speech applications. This study aims to serve as a valuable resource for researchers in academia and in industry working with speech signals, supporting advanced novel applications of ensemble deep learning models towards solving challenges in existing speech processing systems. [ABSTRACT FROM AUTHOR]

For classification problems, twin support vector machine with pinball loss (Pin-GTSVM) is noise insensitive and has better performance than twin support vector machine (TWSVM). However, it lacks sparsity in comparison to TWSVM. In this article, to maintain a trade-off between the noise insensitivity and sparsity of the model along with preserving the theoretical properties of pinball loss, we propose universum twin support vector machine with truncated pinball loss (Tpin-UTWSVM). The proposed Tpin-UTWSVM considers universum data which gives prior information about the distribution of the data, thus improves the generalization performance of the proposed model. Further, the proposed optimization problem is non-convex and non-differentiable which is solved by concave–convex procedure. We employed the SOR approach to train the proposed model effectively with minimum training time. We conducted numerical experiments on 19 UCI binary datasets with different noise levels to validate the noise insensitivity of the proposed Tpin-UTWSVM model. We also conducted numerical experiments for electroencephalogram (EEG) signal classification and Alzheimer's disease (AD) detection. The overall experimental outcomes and statistical tests demonstrate the superiority of the proposed Tpin-UTWSVM model in comparison to the baseline models. The source code for the proposed Tpin-UTWSVM is available at https://github.com/mtanveer1/Universum-twin-SVM-with-truncated-pinball-loss. [ABSTRACT FROM AUTHOR]

SUMMARY: The article presents the experimental evaluation of an integrated approach for path following and obstacle avoidance, implemented on wheeled robots. Wheeled robots are widely used in many different contexts, and they are usually required to operate in partial or total autonomy: in a wide range of situations, having the capability to follow a predetermined path and avoiding unexpected obstacles is extremely relevant. The basic requirement for an appropriate collision avoidance strategy is to sense or detect obstacles and make proper decisions when the obstacles are nearby. According to this rationale, the approach is based on the definition of the path to be followed as a curve on the plane expressed in its implicit form f (x, y) = 0, which is fed to a feedback controller for path following. Obstacles are modeled through Gaussian functions that modify the original function, generating a resulting safe path which – once again – is a curve on the plane expressed as f ′(x, y) = 0: the deformed path can be fed to the same feedback controller, thus guaranteeing convergence to the path while avoiding all obstacles. The features and performance of the proposed algorithm are confirmed by experiments in a crowded area with multiple unicycle-like robots and moving persons. [ABSTRACT FROM AUTHOR]

Support vector machine (SVM) has been used widely for classification of electroencephalogram (EEG) signals for the diagnosis of neurological disorders such as epilepsy and sleep disorders. SVM shows good generalization performance for high dimensional data due to its convex optimization problem. The incorporation of prior knowledge about the data leads to a better optimized classifier. Different types of EEG signals provide information about the distribution of EEG data. To include prior information in the classification of EEG signals, we propose a novel machine learning approach based on universum support vector machine (USVM) for classification. In our approach, the universum data points are generated by selecting universum from the EEG dataset itself which are the interictal EEG signals. This removes the effect of outliers on the generation of universum data. Further, to reduce the computation time, we use our approach of universum selection with universum twin support vector machine (UTSVM) which has less computational cost in comparison to traditional SVM. For checking the validity of our proposed methods, we use various feature extraction techniques for different datasets consisting of healthy and seizure signals. Several numerical experiments are performed on the generated datasets and the results of our proposed approach are compared with other baseline methods. Our proposed USVM and proposed UTSVM show better generalization performance compared to SVM, USVM, Twin SVM (TWSVM) and UTSVM. The proposed UTSVM has achieved highest classification accuracy of 99% for the healthy and seizure EEG signals. [ABSTRACT FROM AUTHOR]

Among different Water Sensitive Urban Design options, constructed wetlands (CWs) are used to protect and restore downstream water quality by attenuating nutrients generated by stormwater runoff. This research compared the nutrient attenuation ability during a diverse population of storm events of two CWs: (a) a hybrid CW with multiple alternating surface flow (SF) and laterite-based subsurface flow (SSF) compartments, and (b) a single stage SF CW. Within-storm variability, nutrient concentrations were assessed at 2 to 3-h intervals at both the main inlet and outlet of each CW. Dissolved oxygen concentrations of the surface waters were also monitored at 10-min intervals using high frequency in situ sensors. Nutrient loads into the CWs were observed to be higher when a high rainfall event occurred, particularly after longer antecedent dry conditions. Longer hydraulic retention times promoted higher attenuation at both sites. However, the relative extent of nutrient attenuation differed between the CW types; the mean total nitrogen (TN) attenuation in the hybrid and SF CW was 45 and 48%, respectively. The hybrid CW attenuated 67% total phosphorus (TP) loads on average, while the SF CW acted as a net TP source. Periodic storm events transitioned the lentic CW into a lotic CW and caused riparian zone saturation; it was therefore hypothesized that such saturation of organic matter rich-riparian zones led to release of TP in the system. The hybrid CW attenuated the released TP in the downstream laterite-based SSF compartments. Diel oxygen metabolism calculated before and after the storm events was found to be strongly correlated with water temperature, solar exposure and antecedent dry condition during the pre-storm conditions. Furthermore, the SF CW showed a significant relationship between overall nutrient load attenuation and the change in oxygen metabolism during the storm perturbation, suggesting oxygen variation could be a useful proxy indicator of CW function. [ABSTRACT FROM AUTHOR]

The attenuation of urban stormwater nutrient is essential for maintaining ecological health of downstream waterways. Constructed wetlands (CWs) are widely used for stormwater management due to the economic and environmental benefits they create by attenuating nutrients. This research assessed stormwater nutrient attenuation in a surface flow CW located in Western Australia, by assessing data spanning decadal, seasonal and diurnal time-scales. The study site was built in 2004 and restored in 2010, and the significance of such restoration was also assessed in this research. The CW designed to minimize nutrient loads to downstream sensitive waterways despite experiencing Mediterranean climates with strong hydrological seasonality including prolonged low or no flow conditions during the dry summer periods and nutrient-rich pulses during the wet winter periods. Furthermore, seasonal ungauged water inputs and macrophytes senescence made the system complex to optimize nutrient attenuation. The annual average attenuation of nitrogen (N) and phosphorus (P) based nutrients were 2–4 times higher during the post-restoration periods than that observed during the pre-restoration periods. The attenuation of inorganic, organic, dissolved and total N was higher during the dry periods of the post-restoration regimes, while P species showed higher attenuation during the wet periods of the post-restoration regimes. Inorganic N showed greater attenuation than attenuation of inorganic P throughout the year. Baumea articulata and Schoenoplectus validus were the dominant macrophyte species across the site; B. articulata was estimated to store about 3 and 2 times higher N and P pools, respectively than that stored in S. validus . Low dissolved oxygen (DO) occurred in the site and DO showed a decreasing trend over the decade and a distinct diurnal signature of day-time peaks and night-time anoxia. Diurnal pattern in aquatic metabolism, defined as the daily fluctuation of DO levels within the water column of CW, was related to solar radiation and nutrient concentrations, and could be considered as a proxy of CW function. [ABSTRACT FROM AUTHOR]

Among different Water Sensitive Urban Design (WSUD) options, constructed wetlands (CWs) are widely used to protect and support downstream urban waterways from stormwater nutrients. This analysis assessed the nutrient attenuation ability of a novel CW in Western Australia that combined multiple alternating surface flow (SF) and laterite-based subsurface flow (SSF) compartments within a parkland context to improve the urban landscape and amenity. The CW was designed to maximise nutrient reduction despite experiencing a large range of hydrologic conditions, from low transit time nutrient-rich pulses during the wet periods to prolonged low to zero flow conditions during the dry periods. The CW design was further complicated by the possibility of ungauged water inputs after wet antecedent conditions, seasonal macrophyte senescence and a recirculation system to maintain flow during the dry periods. From analysis of data over a range of time scales, we determined that overall the CW attenuated up to 62% total nitrogen (TN) and 99% total phosphorus (TP) loads during dry weather conditions, and 54–76% TN and 27–68% TP during episodic flow pulses. N species attenuation was dominant in the SF compartments, while P species were attenuated mostly within the SSF compartments. Nutrient accumulation in the sediments, and above and below ground biomass of the macrophytes were found to increase during the early stages of operation, suggesting the system reached equilibrium within four years. Further, by comparing trends in nutrient attenuation within the context of diel changes in high frequency oxygen data from different compartments, it was demonstrated that changes in dissolved oxygen were related to changes in nutrient concentration across the CW, although interpretation of this was complicated by changing hydro-climatological conditions. The implementation of this CW concept in a highly seasonal Mediterranean climate demonstrates that urban liveability and environmental health can both be improved through careful design. [ABSTRACT FROM AUTHOR]

In general, pattern classification and regression tasks do not take into consideration the variation in the importance of the training samples. For twin support vector regression (TSVR), this implies that all the training samples play the same role on the bound functions. However, the number of close neighboring samples near to each training sample has an effect on the bound functions. In this paper, we formulate a regularized version of the KNN-based weighted twin support vector regression (KNNWTSVR) called RKNNWTSVR which is both efficient and effective. By introducing the regularization term and replacing 2-norm of slack variables instead of 1-norm, our RKNNWTSVR only needs to solve a simple system of linear equations with low computational cost, and at the same time, it improves the generalization performance. Particularly, we compare four implementations of RKNNWTSVR with existing approaches. Experimental results on several synthetic and benchmark datasets indicate that, comparing to SVR, WSVR, TSVR and KNNWTSVR, our proposed RKNNWTSVR has better generalization ability and requires less computational time. [ABSTRACT FROM AUTHOR]

This study was conducted for evaluating a natural source to treat inflammation and pain, to avoid the severe side effects of currently used agents for these ailments. Thuja Orientalis (More Pankh) is commonly used for the treatment of pain and inflammatory disorders in traditional medicine. Carrageenan induced inflammatory model, acetic acid induced writhing test and hot plate methods were used to evaluate anti-inflammatory, peripheral and central analgesic properties of aqueous methanolic extract of Thuja Orientalis fruit (To-Cr) in albino rats. Completely randomized design (CRD) was constructed for the study and one way ANOVA was applied to compare means. The results showed that TO-Cr has significant anti-inflammatory and analgesic properties. [ABSTRACT FROM AUTHOR]

Global climate change mostly impacts river ecosystems by affecting microbial biodiversity and ecological functions. Considering the high functional redundancy of microorganisms, the unknown relationship between biodiversity and ecosystem functions obstructs river ecological research, especially under the influence of increasing weather extremes, such as in intermittent rivers and ephemeral streams (IRES). Herein, dry–wet alternation experiments were conducted in artificial stream channels for 25 and 90 days of drought, both followed by 20 days of rewetting. The dynamic recovery of microbial biodiversity and ecosystem functions (represented by ecosystem metabolism and denitrification rate) were determined to analyse biodiversity–ecosystem–function (BEF) relationships after different drought durations. There was a significant difference between bacterial and eukaryotic biodiversity recovery after drought. Eukaryotic biodiversity was more sensitive to drought duration than bacterial, and the eukaryotic network was more stable under dry–wet alternations. Based on the establishment of partial least squares path models, we found that eukaryotic biodiversity has a stronger effect on ecosystem functions than bacteria after long‐term drought. Indeed, this work represents a significant step forward for further research on the ecosystem functions of IRES, especially emphasizing the importance of eukaryotic biodiversity in the BEF relationship. [ABSTRACT FROM AUTHOR]

[Display omitted] The novel study of Cd-Zn co-doped Magnesium ferrites Cd x Zn 1-x Mg 0.25 Fe 1.75 O 4 (where x = 0, 0.25, 0.75, 0.50, and 1.00) has been made successfully by adopting a facile sol-gel extended hydrothermal pathway. Structural, optical, and magnetic behavior of the Cd-Zn co-doped Magnesium ferrites were systematically analyzed. From the X-ray Diffraction (XRD) patterns it was confirmed that the prepared samples have a cubic spinel structure. Scanning electron microscopic (SEM) study revealed the agglomerated and irregular shape of Cd-Zn co-doped Magnesium ferrites nanoparticles. Fourier transforms infrared (FTIR) spectroscopy has been studied for the confirmation of the presence of (M-O) bonding in the synthesized samples. Furthermore, the synthesized samples showed two frequency bands related to phonon vibrational stretching in both octahedral and tetrahedral lattice positions. The PL spectrum revealed the strong emission peaks in the ultraviolet to the visible region of all the synthesized samples. Raman spectroscopy showed the formation of four active modes due to the cubic spinel structure of all samples. Finally, the magnetic characteristics are calculated by using a vibrating sample magnetometer (VSM) showing ferrimagnetic and soft magnetic behavior of all the Magnesium ferrite samples. As the Cd and Zn co-doping in Mg ferrites was increased, the H c was decreased. The magnetic studies revealed that the maximum H c of 576 Oe and maximum saturation magnetization (M s) appeared for the sample Cd 0.50 Zn 0.50 Mg 0.25 Fe 1.75 O 4 , carrying Cd/Zn in 50/50 ratio. It is envisaged that the novel preparation of Cd-Zn co-doped Magnesium ferrite would be suitable for several applications, for example, magnetic recording devices, actuators, high-density data storage devices sensors, and biomedical equipments. [ABSTRACT FROM AUTHOR]

In real world problems, imbalance of data samples poses major challenge for the classification problems as the data samples of a particular class are dominating. Problems like fault and disease detection involve imbalance data and hence need attention to avoid the bias towards a particular class. The classification models like support vector machines (SVM) get biased to majority class samples and hence results in misclassification of the minority class samples. SVM suffers as no prior information related to the data is involved in the generation of hyperplanes. Also, local information of the neighbourhood is ignored in SVM samples and thus treats each sample equally for generating the hyperplanes. However, the data points may be contaminated and may mislead the generation of hyperplanes. Inspired by the idea of prior data information and local neighbourhood information, we propose K -nearest neighbour based weighted reduced universum twin SVM for class imbalance learning (KWRUTSVM-CIL). The proposed KWRUTSVM-CIL embodies the local neighbourhood information and uses universum data to balance the classes in class imbalance problems. Local neighbourhood information is incorporated via weight matrix in the objective function. In proposed KWRUTSVM-CIL model, weight vectors are used in the corresponding constraints of the objective functions to exploit the interclass information. The oversampling and undersampling approaches are followed to balance the data in class imbalance problems. Universum data gives prior information of the data. Twin SVM, universum twin SVM, and reduced universum twin SVM for class imbalance implement empirical risk minimization principle and thus may lead to overfitting. However, the proposed KWRUTSVM-CIL model embodies regularization term to maximize the margin and implement the structural risk minimization principle which is the marrow of statistical learning and overcomes the issues of overfitting. Experimental results and the statistical analysis signify that the generalization ability of proposed KWRUTSVM-CIL model is superior in comparison to other twin SVM based models. As an application, we use the proposed KWRUTSVM-CIL model for the diagnosis of Alzheimer's disease and breast cancer disease. The proposed KWRUTSVM-CIL model showed better generalization performance compared to other twin SVM based models in biomedical datasets. • To incorporate the local neighbourhood information, K nearest neighbourbased weights are used in the proposed KWRUTSVM-CIL. • Unlike RUTSVM-CIL, UTSVM, TSVM and FTWSVM models which implement the empirical risk minimization principle, the proposed KWRUTSVM-CIL model implements the structural risk minimization principle. • Similar to RUTSVM-CIL, the proposed KWRUTSVM-CIL model incorporates prior information about the data (universum data) to handle the class imbalance problem. • The matrices appearing in the Wolfe dual of the proposed KWRUTSVM-CIL are positive definite, while as the matrices in the Wolfe dual of RUTSVM-CIL, UTSVM, TSVM and FTWSVM are positive semi-definite. • Experimental results and statistical analysis show the efficacy of the proposed KWRUTSVM-CIL model. As an application, we use the proposed KWRUTSVM-CIL model for the classification of Alzheimer's disease and breast cancer subjects. [ABSTRACT FROM AUTHOR]

Twin support vector machine (TWSVM) and twin support vector regression (TSVR) are newly emerging efficient machine learning techniques which offer promising solutions for classification and regression challenges respectively. TWSVM is based upon the idea to identify two nonparallel hyperplanes which classify the data points to their respective classes. It requires to solve two small sized quadratic programming problems (QPPs) in lieu of solving single large size QPP in support vector machine (SVM) while TSVR is formulated on the lines of TWSVM and requires to solve two SVM kind problems. Although there has been good research progress on these techniques; there is limited literature on the comparison of different variants of TSVR. Thus, this review presents a rigorous analysis of recent research in TWSVM and TSVR simultaneously mentioning their limitations and advantages. To begin with, we first introduce the basic theory of support vector machine, TWSVM and then focus on the various improvements and applications of TWSVM, and then we introduce TSVR and its various enhancements. Finally, we suggest future research and development prospects. [ABSTRACT FROM AUTHOR]

Schizophrenia (SCZ) is a devastating mental condition with significant negative consequences for patients, making correct and prompt diagnosis crucial. The purpose of this study is to use structural magnetic resonance image (MRI) to better classify individuals with SCZ from control normals (CN) and to locate a region of the brain that represents abnormalities associated with SCZ. Deep learning (DL), which is based on the nervous system, could be a very useful tool for doctors to accurately predict, diagnose, and treat SCZ. Gray Matter (GM), Cerebrospinal Fluid (CSF), and White Matter (WM) brain regions are extracted from 99 MRI images obtained from the open-source OpenNeuro database to demonstrate SCZ's regional relationship. In this paper, we use a pretrained ResNet-50 deep network to extract features from MRI images and an ensemble deep random vector functional link (edRVFL) network to classify those features. By examining the results obtained, the edRVFL deep model provides the highest classification accuracy of 96.5% with WM and is identified as the best-performing algorithm compared to the traditional algorithms. Furthermore, we examined the GM, WM, and CSF tissue volumes in CN subjects and SCZ patients using voxel-based morphometry (VBM), and the results show 1363 significant voxels, 6.90 T-value, and 6.21 Z-value in the WM region of SCZ patients. In SCZ patients, WM is most closely linked to structural alterations, as evidenced by VBM analysis and the DL model. [ABSTRACT FROM AUTHOR]

Well controlled nanosheets-based hierarchical microspheres (NSHMS) of pure covellite phase CuS were synthesized using a facile PVP assisted solvothermal process. The reaction conditions were optimized using various amounts of PVP to develop unique hierarchical structured hollow microspheres. CuS hollow structures have a bandgap of ~1.97 eV. These mesoporous structures exhibit excellent photocatalytic activity in degradation of organic dyes (Methylene Blue) under natural light in comparison to other structures of copper sulphide. These photocatalysts show extraordinary reusability with over 96.5% degradation of organic dye after 6th cycle. A "bottom-up" assembly was successfully developed to synthesize hollow microspheres with unique and well defined architectures at large scale, which offer a good opportunity to understand the fundamental significance of unusual and complex hierarchical structures for their potential applications. [ABSTRACT FROM AUTHOR]

In the recent articles, Khan and Sumitra (Appl. Math. Sci., 5(29)(2011), 1421-1430) and Singh et al. (Int. J. Math. Anal., 5(27) (2011), 1301-1308) claim a fuzzy version of common fixed point theorem of Bouhadjera and Godet-Thobie [3]. The results of aforementioned articles contain flaws and are not correct in their present form. We provide some examples to demonstrate that this claim is false unless some additional conditions are imposed. Our note is desired to complete the interesting results in the quoted paper. [ABSTRACT FROM AUTHOR]

A new smoothing approach for the implicit Lagrangian twin support vector regression is proposed in this paper. Our formulation leads to solving a pair of unconstrained quadratic programming problems of smaller size than in the classical support vector regression and their solutions are obtained using Newton-Armijo algorithm. This approach has the advantage that a system of linear equations is solved in each iteration of the algorithm. Numerical experiments on several synthetic and real-world datasets are performed and, their results and training time are compared with both the support vector regression and twin support vector regression to verify the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

The article discusses how during the COVID-19 pandemic, personal protective equipment (PPE) has driven increased plastic pollution. In response to high PPE demand among the general public, health care workers, and service workers, single use face mask production in China soared to 116 million per day in February 2020, about 12 times the usual quantity.

In this paper, a simple and linearly convergent Lagrangian support vector machine algorithm for the dual of the twin support vector regression (TSVR) is proposed. Though at the outset the algorithm requires inverse of matrices, it has been shown that they would be obtained by performing matrix subtraction of the identity matrix by a scalar multiple of inverse of a positive semi-definite matrix that arises in the original formulation of TSVR. The algorithm can be easily implemented and does not need any optimization packages. To demonstrate its effectiveness, experiments were performed on well-known synthetic and real-world datasets. Similar or better generalization performance of the proposed method in less training time in comparison with the standard and twin support vector regression methods clearly exhibits its suitability and applicability. [ABSTRACT FROM AUTHOR]

The ground-state magnetic properties of free-standing Fe wires having linear, zigzag, and rectangular geometries are investigated in the framework of density-functional theory. The stability of various wires geometries and types of magnetic orders is analyzed as a function of the spin-density-wave (SDW) number q. In particular, we consider ferromagnetic (FM) and antiferromagnetic (AF) collinear states as well as periodic and alternating noncollinear (NC) states. The relaxed interatomic bond lengths d, frozen-magnon dispersion relations ΔE(q), local magnetic moments μi spin-polarized electronic densities of states ρdσ(ε), and effective exchange couplings Jij are determined. Iron zigzag chains show FM order (q = 0) at the equilibrium lattice parameter a with ΔE(q) increasing monotonously with q. In contrast, Diatomic rectangular ladders (RLs) develop spontaneously a spiral SDWs along the wire, keeping FM dimer couplings in the perpendicular direction. This NC order is further stabilized by compressing the wire. However, stretched RLs show FM order. In all cases, strong μi, are found within the Wigner-Seitz spheres, which decrease moderately with increasing q. The electronic structures of collinear and NC states are analyzed by comparing the density of states ρdσ(ε) for different representative values of q. Effective exchange-interaction parameters Jij between the local moments μi and μj are derived by fitting the ab initio magnon dispersion relation ΔE(q) to a classical Heisenberg model. The interplay between the various competing Jij is shown to depend decisively on the lattice parameter and wire geometry. Comparing the ab initio results within a model phase diagram provides useful insights on the magnetic order of Fe wires from a local perspective. [ABSTRACT FROM AUTHOR]

Abstract: NaIO4 oxidizes lithium bromide efficiently under acidic conditions to functionalize alkylbenzenes and alkanes and produce the corresponding bromo and acetoxy derivatives in excellent yields. The protocol also demonstrates the direct conversion of cyclohexane into trans-1,2-dibromocyclohexane in moderate yield. [Copyright &y& Elsevier]

• Deep convolutional neural networks show high performance for neonatal seizure classification. • Trained ensemble model show promising results for use in clinical settings. • Ensemble model shows higher performance than individual models. Neonatal seizures are a common occurrence in clinical settings, requiring immediate attention and detection. Previous studies have proposed using manual feature extraction coupled with machine learning, or deep learning to classify between seizure and non-seizure states. In this paper a deep learning based approach is used for neonatal seizure classification using electroencephalogram (EEG) signals. The architecture detects seizure activity in raw EEG signals as opposed to common state-of-art, where manual feature extraction with machine learning algorithms is used. The architecture is a two-dimensional (2D) convolutional neural network (CNN) to classify between seizure/non-seizure states. The dataset used for this study is annotated by three experts and as such three separate models are trained on individual annotations, resulting in average accuracies (ACC) of 95.6 %, 94.8 % and 90.1 % respectively, and average area under the receiver operating characteristic curve (AUC) of 99.2 %, 98.4 % and 96.7 % respectively. The testing was done using 10-cross fold validation, so that the performance can be an accurate representation of the architectures classification capability in a clinical setting. After training/testing of the three individual models, a final ensemble model is made consisting of the three models. The ensemble model gives an average ACC and AUC of 96.3 % and 99.3 % respectively. This study outperforms previous studies, with increased ACC and AUC results coupled with use of small time windows (1 s) used for evaluation. The proposed approach is promising for detecting seizure activity in unseen neonate data in a clinical setting. [ABSTRACT FROM AUTHOR]

We introduce a unified simulation framework that generates natural sensing environments and produces biosonar echoes under various sensing scenarios. This framework produces rich sensory data with environmental information completely known, thus can be used for the training of robotic algorithms for biosonar-based Unmanned Aerial Vehicles. The simulated environment consists of random trees with full geometry of the tree foliage. To simulate a single tree, we adopt the Lindenmayer system to generate the initial branching pattern and integrate that with the available measurements of the 3D computer-aided design object files to create natural-looking branches, sub-branches, and leaves. A forest is formed by simulating trees at random locations generated by using an inhomogeneous Poisson process. While our simulated environments can be generally used for testing other sensors and training robotic algorithms, in this study we focus on testing bat-inspired Unmanned Aerial Vehicles that recreate bat's flying behavior through biosonar sensors. To this end, we also introduce an foliage echo simulator that produces biosonar echoes while mimicking bat's biosonar system. We demonstrate the application of the proposed simulation framework by generating real-world scenarios with multiple trees and computing the resulting impulse responses under static or dynamic motions of an Unmanned Aerial Vehicle. [ABSTRACT FROM AUTHOR]

Alzheimer's disease (AD) is a degenerative neurological ailment that begins with memory loss and ultimately leads to a total loss of mental capacity. Researchers are interested in using magnetic resonance imaging (MRI) and positron emission tomography (PET) to find people with mild cognitive impairment (MCI), which is a stage before Alzheimer's disease (AD). Significant hippocampal loss and temporal lobe atrophy characterize the transition from MCI to AD, which can be visualized using T1-W structural MRI. PET visualizes brain glucose metabolism, which indicates neuronal activity, making it a viable neuroimaging method for AD diagnosis. The extraction and fusion of structural and metabolite information about brain alterations contained in multimodal data is crucial for achieving an appropriate classification result. Therefore, in this work a new end-to-end coupled-GAN (CGAN) architecture is introduced. The proposed CGANC network consists of two sub-models: a CGAN for extraction of fused features from multimodal data, and a CNN classifier to classify these features. The proposed CGAN model is trained to encode MRI and PET images into a shared latent space. The fused features are extracted from this shared latent space and then are classified according to particular stage of AD. In order to test the effectiveness of the suggested approach, experiments are done on the publicly available ADNI dataset and compared with state-of-the-art methods. The proposed method's source code will be made freely available at https://github.com/ChandrajitChoudhury/CGAN-AD. • MRI and PET images are fused to utilize structural and metabolic features for AD diagnosis. • An adversarial learning-based method is proposed to extract fused features. • A coupled adversarial subnetwork and a classification subnetwork have been designed. • Experiments are done on the publicly available ADNI dataset. [ABSTRACT FROM AUTHOR]

• A universum based algorithm is proposed for class imbalance learning. • Universum learning is used for the first time to solve class imbalance problem. • Reduced kernel is incorporated for reducing storage and computation cost. • Proposed approach is useful for large scale class imbalanced datasets. In most of the real world datasets, there is an imbalance in the number of samples belonging to different classes. Various pattern classification problems such as fault or disease detection involve class imbalanced data. The support vector machine (SVM) classifier becomes biased towards the majority class due to class imbalance. Moreover, in the existing SVM based techniques for class imbalance, there is no information about the distribution of data. Motivated by the idea of prior information about data distribution, a reduced universum twin support vector machine for class imbalance learning (RUTSVM-CIL) is proposed in this paper. For the first time, universum learning is incorporated with SVM to solve the problem of class imbalance. Oversampling and undersampling of data is performed to remove the imbalance in the classes. The universum data points are used to give prior information about the data. To reduce the computation time of our universum based algorithm, we use a small sized rectangular kernel matrix. The reduced kernel matrix needs less storage space, and thus applicable for large scale imbalanced datasets. Comprehensive experimentation is performed on various synthetic, real world and large scale imbalanced datasets. In comparison to the existing approaches for class imbalance, the proposed RUTSVM-CIL gives better generalization performance for most of the benchmark datasets. Also, the computation cost of RUTSVM-CIL is very less, making it suitable for real world applications. [ABSTRACT FROM AUTHOR]

• A novel approach is proposed to generate the oblique decision tree ensemble via TBSVM. • Structural risk minimization principle is implemented in the proposed models. • No explicit regularization techniques need to be applied in the proposed models. • Experimental results and statistical tests show the efficacy of the proposed models. Ensemble methods with "perturb and combine" strategy have shown improved performance in the classification problems. Recently, random forest algorithm was ranked one among 179 classifiers evaluated on 121 UCI datasets. Motivated by this, we propose a new approach for the generation of oblique decision trees. At each non-leaf node, the training data samples are grouped in two categories based on the Bhattachrayya distance with randomly selected feature subset. Then, twin bounded support vector machine (TBSVM) is used to get two clustering hyperplanes such that each hyperplane is closer to data points of one group and as far as possible from the data points of other group. Based on these hyperplanes, each non-leaf node is splitted to generate the decision tree. In this paper, we used different base models like random forest (RaF), rotation forest (RoF), random sub rotation forest (RRoF) to generate the different oblique decision tree forests named as TBRaF, TBRoF and TBRRoF, respectively. In earlier oblique decision trees, like multisurface proximal support vector machine (MPSVM) based oblique decision trees, matrices are semi-positive definite and hence different regularization methods are required. However, no explicit regularization techniques need to be applied to the primal problems as the matrices in the proposed TBRaF, TBRoF and TBRRoF are positive definite. We evaluated the performance of the proposed models (TBRaF, TBRoF and TBRRoF) on 49 datasets taken from the UCI repository and on some real-world biological datasets (not in UCI). The experimental results and statistical tests conducted show that TBRaF and TBRRoF outperform other baseline methods. [ABSTRACT FROM AUTHOR]