Mathematical optimization of multilinear and artificial neural network regressions for mineral composition of different tea types infusions.

The objective of this study was to investigate the change in mineral composition depending on tea variety, tea concentration, and steeping time. Four different tea varieties, black Ceylon (BC), black Turkish (BT), green Ceylon (GC), and green Turkish (GT), were used to produce teas at concentrations of 1, 2, and 3%, respectively. These teas were produced using 7 different steeping times: 2, 5, 10, 20, 30, 45, and 60 min. It was also aimed to optimize the regression equations utilizing these factors to identify parameters conducive to maximizing Zn, K, Cu, Mg, Ca, Na, and Fe levels; minimizing Al content, and maintaining Mn level at 5.3 mg/L. The optimal conditions for achieving a Mn content of 5.3 mg/L in black Turkish tea entailed steeping at a concentration of 1.94% for 11.4 min. Variations in K and Mg levels across teas were inconsistent with those observed for other minerals, whereas variations in Al, Cu, Fe, Mn, Na, and Zn levels exhibited a close relationship. Overall, mineral levels in tea can be predicted through regression analysis, and by mathematically optimizing the resultant equations, the requisite conditions for tea production can be determined to achieve maximum, minimum, or target mineral values.

Comparative analysis of the chimpanzee and human brain superficial structural connectivities.

Diffusion MRI tractography (dMRI) has fundamentally transformed our ability to investigate white matter pathways in the human brain. While long-range connections have extensively been studied, superficial white matter bundles (SWMBs) have remained a relatively underexplored aspect of brain connectivity. This study undertakes a comprehensive examination of SWMB connectivity in both the human and chimpanzee brains, employing a novel combination of empirical and geometric methodologies to classify SWMB morphology in an objective manner. Leveraging two anatomical atlases, the Ginkgo Chauvel chimpanzee atlas and the Ginkgo Chauvel human atlas, comprising respectively 844 and 1375 superficial bundles, this research focuses on sparse representations of the morphology of SWMBs to explore the little-understood superficial connectivity of the chimpanzee brain and facilitate a deeper understanding of the variability in shape of these bundles. While similar, already well-known in human U-shape fibers were observed in both species, other shapes with more complex geometry such as 6 and J shapes were encountered. The localisation of the different bundle morphologies, putatively reflecting the brain gyrification process, was different between humans and chimpanzees using an isomap-based shape analysis approach. Ultimately, the analysis aims to uncover both commonalities and disparities in SWMBs between chimpanzees and humans, shedding light on the evolution and organization of these crucial neural structures.

Toward Unbiased High-Quality Portraits through Latent-Space Evaluation.

Images, texts, voices, and signals can be synthesized by latent spaces in a multidimensional vector, which can be explored without the hurdles of noise or other interfering factors. In this paper, we present a practical use case that demonstrates the power of latent space in exploring complex realities such as image space. We focus on DaVinciFace, an AI-based system that explores the StyleGAN2 space to create a high-quality portrait for anyone in the style of the Renaissance genius Leonardo da Vinci. The user enters one of their portraits and receives the corresponding Da Vinci-style portrait as an output. Since most of Da Vinci's artworks depict young and beautiful women (e.g., "La Belle Ferroniere", "Beatrice de' Benci"), we investigate the ability of DaVinciFace to account for other social categorizations, including gender, race, and age. The experimental results evaluate the effectiveness of our methodology on 1158 portraits acting on the vector representations of the latent space to produce high-quality portraits that retain the facial features of the subject's social categories, and conclude that sparser vectors have a greater effect on these features. To objectively evaluate and quantify our results, we solicited human feedback via a crowd-sourcing campaign. Analysis of the human feedback showed a high tolerance for the loss of important identity features in the resulting portraits when the Da Vinci style is more pronounced, with some exceptions, including Africanized individuals.

Neural networks based linear (PCA) and nonlinear (ISOMAP) feature extraction for soil swelling pressure prediction (North East Algeria).

The swelling pressure (SP) of expansive soils is crucial for both geotechnical studies as well as practitioners. Multiple attempts have been made to correlate the SP with the properties of soil due to the difficulty of determining it in the laboratory. However, the large number of environmental and physical governing parameters makes accurate SP predictions difficult. In this paper, Artificial Neural Networks (ANNs) are used to assess accurate prediction of SP of soil. Dimension reduction techniques are intensely required for ANNs inputs. Feature extraction (FE) based dimension reduction (DR) methods map original multidimensional space into a space of reduced dimensionality. This paper presents a comparative study of linear FE using Principal Component Analysis (PCA) and nonlinear FE using ISOmetric MAPping (ISOMAP) for feed forward neural models to predict SP. Results showed that FE technique improves ANNs models compared to multiple linear regression (MLR) and ANNs model without DR. Moreover, nonlinear ISOMAP based DR technique has proven its effectiveness regarding performance metrics for five dimensions inputs (Dims), Determination coefficient (R2 = 0.923), Mean absolute percentage error (MAPE = 0.072), and Root mean square error (RMSE = 54.937) and Root relative squared error (RRSE = 0.383). Therefore, ISOMAP-ANN models can be adopted to solve geotechnical problems specially those of expansive soils which have a very complex and nonlinear structure.

Role of proliferation COVID-19 media chatter in predicting Indian stock market: Integrated framework of nonlinear feature transformation and advanced AI.

The outbreak of the COVID-19 pandemic has transpired the global media to gallop with reports and news on the novel Coronavirus. The intensity of the news chatter on various aspects of the pandemic, in conjunction with the sentiment of the same, accounts for the uncertainty of investors linked to financial markets. In this research, Artificial Intelligence (AI) driven frameworks have been propounded to gauge the proliferation of COVID-19 news towards Indian stock markets through the lens of predictive modelling. Two hybrid predictive frameworks, UMAP-LSTM and ISOMAP-GBR, have been constructed to accurately forecast the daily stock prices of 10 Indian companies of different industry verticals using several systematic media chatter indices related to the COVID-19 pandemic alongside several orthodox technical indicators and macroeconomic variables. The outcome of the rigorous predictive exercise rationalizes the utility of monitoring relevant media news worldwide and in India. Additional model interpretation using Explainable AI (XAI) methodologies indicates that a high quantum of overall media hype, media coverage, fake news, etc., leads to bearish market regimes.

A machine learning strategy with clustering under sampling of majority instances for predicting drug target interactions.

Drug Target Interactions (DTIs) are crucial in drug discovery as it reduces the range of candidate searches, speeding up the drug screening process. Considering in vitro and in vivo experimentations are time and cost-expensive, there has been a surge in computational techniques, especially ML methods for DTIs prediction. Therefore, this study aims to present a methodology that uses molecular structures and amino acid sequences for generating PSSM and PubChem fingerprints for drugs and targets respectively. The proposed work uses a novel technique NearestCUS for handling the class imbalance problem of the benchmark datasets. We use Isomap Embedding to extract features from PSSMs. Feature selection is performed using ANOVA. CatBoost is used for predicting the interaction between drugs and targets for the first time. To quantify the efficacy of NearestCUS, we compared it with other sampling techniques. We found that the proposed methodology performed better than state-of-the-art approaches.

Application of KNN-based isometric mapping and fuzzy c-means algorithm to predict short-term rockburst risk in deep underground projects.

The rockburst phenomenon is the major source of the high number of casualties and fatalities during the construction of deep underground projects. Rockburst poses a severe hazard to the safety of employees and equipment in subsurface mining operations. It is a hot topic in recent years to examine and overcome rockburst risks for the safe installation of deep urban engineering designs. Therefore, for a cost-effective and safe underground environment, it is crucial to determine and predict rockburst intensity prior to its occurrence. A novel model is presented in this study that combines unsupervised and supervised machine learning approaches in order to predict rockburst risk. The database for this study was built using authentic microseismic monitoring occurrences from the Jinping-II hydropower project in China, which consists of 93 short-term rockburst occurrences with six influential features. The prediction process was succeeded in three steps. Firstly, the original rockburst database's magnification was reduced using a state-of-the-art method called isometric mapping (ISOMAP) algorithm. Secondly, the dataset acquired from ISOMAP was categorized using the fuzzy c-means algorithm (FCM) to reduce the minor spectral heterogeneity impact in homogenous areas. Thirdly, K-Nearest neighbor (KNN) was employed to anticipate different levels of short-term rockburst datasets. The KNN's classification performance was examined using several performance metrics. The proposed model correctly classified about 96% of the rockbursts events in the testing datasets. Hence, the suggested model is a realistic and effective tool for evaluating rockburst intensity. Therefore, the proposed model can be employed to forecast the rockburst risk in the early stages of underground projects that will help to minimize casualties from rockburst.

Laser-Induced Breakdown Spectroscopy Combined with Nonlinear Manifold Learning for Improvement Aluminum Alloy Classification Accuracy.

Laser-induced breakdown spectroscopy (LIBS) spectra often include many intensity lines, and obtaining meaningful information from the input dataset and condensing the dimensions of the original data has become a significant challenge in LIBS applications. This study was conducted to classify five different types of aluminum alloys rapidly and noninvasively, utilizing the manifold dimensionality reduction technique and a support vector machine (SVM) classifier model integrated with LIBS technology. The augmented partial residual plot was used to determine the nonlinearity of the LIBS spectra dataset. To circumvent the curse of dimensionality, nonlinear manifold learning techniques, such as local tangent space alignment (LTSA), local linear embedding (LLE), isometric mapping (Isomap), and Laplacian eigenmaps (LE) were used. The performance of linear techniques, such as principal component analysis (PCA) and multidimensional scaling (MDS), was also investigated compared to nonlinear techniques. The reduced dimensions of the dataset were assigned as input datasets in the SVM classifier. The prediction labels indicated that the Isomap-SVM model had the best classification performance with the classification accuracy, the number of dimensions and the number of nearest neighbors being 96.67%, 11, and 18, respectively. These findings demonstrate that the combination of nonlinear manifold learning and multivariate analysis has the potential to classify the samples based on LIBS with reasonable accuracy.

The relation of integrated psychological therapy to resting state functional brain connectivity networks in patients with schizophrenia.

Functional brain dysconnectivity measured with resting state functional magnetic resonance imaging (rsfMRI) has been linked to cognitive impairment in schizophrenia. This study investigated the effects on functional brain connectivity of Integrated Psychological Therapy (IPT), a cognitive behavioral oriented group intervention program, in 31 patients with schizophrenia. Patients received IPT or an equal intensity non-specific psychological treatment in a non-randomized design. Evidence of improvement in executive and social functions, psychopathology and overall level of functioning was observed after treatment completion at six months only in the IPT treatment group and was partially sustained at one-year follow up. Independent Component Analysis and Isometric Mapping (ISOMAP), a non-linear manifold learning algorithm, were used to construct functional connectivity networks from the rsfMRI data. Functional brain dysconnectivity was observed in patients compared to a group of 17 healthy controls, both globally and specifically including the default mode (DMN) and frontoparietal network (FPN). DMN and FPN connectivity were reversed towards healthy control patterns only in the IPT treatment group and these effects were sustained at follow up for DMN but not FPN. These data suggest the use of rsfMRI as a biomarker for accessing and monitoring the therapeutic effects of cognitive remediation therapy in schizophrenia.

ISOMAP and machine learning algorithms for the construction of embedded functional connectivity networks of anatomically separated brain regions from resting state fMRI data of patients with Schizophrenia.

We construct Functional Connectivity Networks (FCN) from resting state fMRI (rsfMRI) recordings towards the classification of brain activity between healthy and schizophrenic subjects using a publicly available dataset (the COBRE dataset) of 145 subjects (74 healthy controls and 71 schizophrenic subjects). First, we match the anatomy of the brain of each individual to the Desikan-Killiany brain atlas. Then, we use the conventional approach of correlating the parcellated time series to construct FCN and ISOMAP, a nonlinear manifold learning algorithm to produce low-dimensional embeddings of the correlation matrices. For the classification analysis, we computed five key local graph-theoretic measures of the FCN and used the LASSO and Random Forest (RF) algorithms for feature selection. For the classification we used standard linear Support Vector Machines. The classification performance is tested by a double cross-validation scheme (consisting of an outer and an inner loop of "Leave one out" cross-validation (LOOCV)). The standard cross-correlation methodology produced a classification rate of 73.1%, while ISOMAP resulted in 79.3%, thus providing a simpler model with a smaller number of features as chosen from LASSO and RF, namely the participation coefficient of the right thalamus and the strength of the right lingual gyrus.

Modified multiscale weighted permutation entropy and optimized support vector machine method for rolling bearing fault diagnosis with complex signals.

The rolling bearing vibration signals are complex, non-linear, and non-stationary, it is difficult to extract the sensitive features and diagnose faults by conventional signal processing methods. This paper focuses on the sensitive features extraction and pattern recognition for rolling bearing fault diagnosis and proposes a novel intelligent fault-diagnosis method based on generalized composite multiscale weighted permutation entropy (GCMWPE), supervised Isomap (S-Iso), and marine predators algorithm-based support vector machine (MPA-SVM). Firstly, a novel non-linear technology named GCMWPE was presented, allowing the extraction of bearing features from multiple scales and enabling the construction of a high-dimensional feature set. The GCMWPE uses the generalized composite coarse-grained structure to overcome the shortcomings of the original structure in multiscale weighted permutation entropy and obtain more stable entropy values. Subsequently, the S-Iso algorithm was introduced to obtain the main features and reduce the GCMWPE set dimensionality. Finally, a combination of GCMWPE and S-Iso set was input to the MPA-SVM for diagnosis and identification. The marine predators algorithm (MPA) was used to obtain the optimal SVM parameters. The effectiveness of the proposed fault diagnosis method was confirmed through two bearing fault diagnosis experiments. The results have shown that the proposed method can be used to correctly diagnose bearing states with high diagnostic accuracy.

Nonlinear Feature Extraction Through Manifold Learning in an Electronic Tongue Classification Task.

A nonlinear feature extraction-based approach using manifold learning algorithms is developed in order to improve the classification accuracy in an electronic tongue sensor array. The developed signal processing methodology is composed of four stages: data unfolding, scaling, feature extraction, and classification. This study aims to compare seven manifold learning algorithms: Isomap, Laplacian Eigenmaps, Locally Linear Embedding (LLE), modified LLE, Hessian LLE, Local Tangent Space Alignment (LTSA), and t-Distributed Stochastic Neighbor Embedding (t-SNE) to find the best classification accuracy in a multifrequency large-amplitude pulse voltammetry electronic tongue. A sensitivity study of the parameters of each manifold learning algorithm is also included. A data set of seven different aqueous matrices is used to validate the proposed data processing methodology. A leave-one-out cross validation was employed in 63 samples. The best accuracy (96.83%) was obtained when the methodology uses Mean-Centered Group Scaling (MCGS) for data normalization, the t-SNE algorithm for feature extraction, and k-nearest neighbors (kNN) as classifier.

Collective Pulsing in Xeniid Corals: Part I-Using Computer Vision and Information Theory to Search for Coordination.

Xeniid corals (Cnidaria: Alcyonacea), a family of soft corals, include species displaying a characteristic pulsing behavior. This behavior has been shown to increase oxygen diffusion away from the coral tissue, resulting in higher photosynthetic rates from mutualistic symbionts. Maintaining such a pulsing behavior comes at a high energetic cost, and it has been proposed that coordinating the pulse of individual polyps within a colony might enhance the efficiency of fluid transport. In this paper, we test whether patterns of collective pulsing emerge in coral colonies and investigate possible interactions between polyps within a colony. We video recorded different colonies of Heteroxenia sp. in a laboratory environment. Our methodology is based on the systematic integration of a computer vision algorithm (ISOMAP) and an information-theoretic approach (transfer entropy), offering a vantage point to assess coordination in collective pulsing. Perhaps surprisingly, we did not detect any form of collective pulsing behavior in the colonies. Using artificial data sets, however, we do demonstrate that our methodology is capable of detecting even weak information transfer. The lack of a coordination is consistent with previous work on many cnidarians where coordination between actively pulsing polyps and medusa has not been observed. In our companion paper, we show that there is no fluid dynamic benefit of coordinated pulsing, supporting this result. The lack of coordination coupled with no obvious fluid dynamic benefit to grouping suggests that there may be non-fluid mechanical advantages to forming colonies, such as predator avoidance and defense.

Nondestructive Inspection of Reinforced Concrete Utility Poles with ISOMAP and Random Forest.

Reinforced concrete poles are very popular in transmission lines due to their economic efficiency. However, these poles have structural safety issues in their service terms that are caused by cracks, corrosion, deterioration, and short-circuiting of internal reinforcing steel wires. Therefore, they must be periodically inspected to evaluate their structural safety. There are many methods of performing external inspection after installation at an actual site. However, on-site nondestructive safety inspection of steel reinforcement wires inside poles is very difficult. In this study, we developed an application that classifies the magnetic field signals of multiple channels, as measured from the actual poles. Initially, the signal data were gathered by inserting sensors into the poles, and these data were then used to learn the patterns of safe and damaged features. These features were then processed with the isometric feature mapping (ISOMAP) dimensionality reduction algorithm. Subsequently, the resulting reduced data were processed with a random forest classification algorithm. The proposed method could elucidate whether the internal wires of the poles were broken or not according to actual sensor data. This method can be applied for evaluating the structural integrity of concrete poles in combination with portable devices for signal measurement (under development).

Fault Detection of Bearing Systems through EEMD and Optimization Algorithm.

This study proposes a fault detection and diagnosis method for bearing systems using ensemble empirical mode decomposition (EEMD) based feature extraction, in conjunction with particle swarm optimization (PSO), principal component analysis (PCA), and Isomap. First, a mathematical model is assumed to generate vibration signals from damaged bearing components, such as the inner-race, outer-race, and rolling elements. The process of decomposing vibration signals into intrinsic mode functions (IMFs) and extracting statistical features is introduced to develop a damage-sensitive parameter vector. Finally, PCA and Isomap algorithm are used to classify and visualize this parameter vector, to separate damage characteristics from healthy bearing components. Moreover, the PSO-based optimization algorithm improves the classification performance by selecting proper weightings for the parameter vector, to maximize the visualization effect of separating and grouping of parameter vectors in three-dimensional space.

Classification of collective behavior: a comparison of tracking and machine learning methods to study the effect of ambient light on fish shoaling.

Traditional approaches for the analysis of collective behavior entail digitizing the position of each individual, followed by evaluation of pertinent group observables, such as cohesion and polarization. Machine learning may enable considerable advancements in this area by affording the classification of these observables directly from images. While such methods have been successfully implemented in the classification of individual behavior, their potential in the study collective behavior is largely untested. In this paper, we compare three methods for the analysis of collective behavior: simple tracking (ST) without resolving occlusions, machine learning with real data (MLR), and machine learning with synthetic data (MLS). These methods are evaluated on videos recorded from an experiment studying the effect of ambient light on the shoaling tendency of Giant danios. In particular, we compute average nearest-neighbor distance (ANND) and polarization using the three methods and compare the values with manually-verified ground-truth data. To further assess possible dependence on sampling rate for computing ANND, the comparison is also performed at a low frame rate. Results show that while ST is the most accurate at higher frame rate for both ANND and polarization, at low frame rate for ANND there is no significant difference in accuracy between the three methods. In terms of computational speed, MLR and MLS take significantly less time to process an image, with MLS better addressing constraints related to generation of training data. Finally, all methods are able to successfully detect a significant difference in ANND as the ambient light intensity is varied irrespective of the direction of intensity change.

Modeling the shape hierarchy for visually guided grasping.

The monkey anterior intraparietal area (AIP) encodes visual information about three-dimensional object shape that is used to shape the hand for grasping. We modeled shape tuning in visual AIP neurons and its relationship with curvature and gradient information from the caudal intraparietal area (CIP). The main goal was to gain insight into the kinds of shape parameterizations that can account for AIP tuning and that are consistent with both the inputs to AIP and the role of AIP in grasping. We first experimented with superquadric shape parameters. We considered superquadrics because they occupy a role in robotics that is similar to AIP, in that superquadric fits are derived from visual input and used for grasp planning. We also experimented with an alternative shape parameterization that was based on an Isomap dimension reduction of spatial derivatives of depth (i.e., distance from the observer to the object surface). We considered an Isomap-based model because its parameters lacked discontinuities between similar shapes. When we matched the dimension of the Isomap to the number of superquadric parameters, the superquadric model fit the AIP data somewhat more closely. However, higher-dimensional Isomaps provided excellent fits. Also, we found that the Isomap parameters could be approximated much more accurately than superquadric parameters by feedforward neural networks with CIP-like inputs. We conclude that Isomaps, or perhaps alternative dimension reductions of visual inputs to AIP, provide a promising model of AIP electrophysiology data. Further work is needed to test whether such shape parameterizations actually provide an effective basis for grasp control.

Principal components of hand kinematics and neurophysiological signals in motor cortex during reach to grasp movements.

A few kinematic synergies identified by principal component analysis (PCA) account for most of the variance in the coordinated joint rotations of the fingers and wrist used for a wide variety of hand movements. To examine the possibility that motor cortex might control the hand through such synergies, we collected simultaneous kinematic and neurophysiological data from monkeys performing a reach-to-grasp task. We used PCA, jPCA and isomap to extract kinematic synergies from 18 joint angles in the fingers and wrist and analyzed the relationships of both single-unit and multiunit spike recordings, as well as local field potentials (LFPs), to these synergies. For most spike recordings, the maximal absolute cross-correlations of firing rates were somewhat stronger with an individual joint angle than with any principal component (PC), any jPC or any isomap dimension. In decoding analyses, where spikes and LFP power in the 100- to 170-Hz band each provided better decoding than other LFP-based signals, the first PC was decoded as well as the best decoded joint angle. But the remaining PCs and jPCs were predicted with lower accuracy than individual joint angles. Although PCs, jPCs or isomap dimensions might provide a more parsimonious description of kinematics, our findings indicate that the kinematic synergies identified with these techniques are not represented in motor cortex more strongly than the original joint angles. We suggest that the motor cortex might act to sculpt the synergies generated by subcortical centers, superimposing an ability to individuate finger movements and adapt the hand to grasp a wide variety of objects.

Euclidean sections of protein conformation space and their implications in dimensionality reduction.

Dimensionality reduction is widely used in searching for the intrinsic reaction coordinates for protein conformational changes. We find the dimensionality-reduction methods using the pairwise root-mean-square deviation (RMSD) as the local distance metric face a challenge. We use Isomap as an example to illustrate the problem. We believe that there is an implied assumption for the dimensionality-reduction approaches that aim to preserve the geometric relations between the objects: both the original space and the reduced space have the same kind of geometry, such as Euclidean geometry vs. Euclidean geometry or spherical geometry vs. spherical geometry. When the protein free energy landscape is mapped onto a 2D plane or 3D space, the reduced space is Euclidean, thus the original space should also be Euclidean. For a protein with N atoms, its conformation space is a subset of the 3N-dimensional Euclidean space R(3N). We formally define the protein conformation space as the quotient space of R(3N) by the equivalence relation of rigid motions. Whether the quotient space is Euclidean or not depends on how it is parameterized. When the pairwise RMSD is employed as the local distance metric, implicit representations are used for the protein conformation space, leading to no direct correspondence to a Euclidean set. We have demonstrated that an explicit Euclidean-based representation of protein conformation space and the local distance metric associated to it improve the quality of dimensionality reduction in the tetra-peptide and ß-hairpin systems.

Supervised extensions of chemography approaches: case studies of chemical liabilities assessment.

Chemical liabilities, such as adverse effects and toxicity, play a significant role in modern drug discovery process. In silico assessment of chemical liabilities is an important step aimed to reduce costs and animal testing by complementing or replacing in vitro and in vivo experiments. Herein, we propose an approach combining several classification and chemography methods to be able to predict chemical liabilities and to interpret obtained results in the context of impact of structural changes of compounds on their pharmacological profile. To our knowledge for the first time, the supervised extension of Generative Topographic Mapping is proposed as an effective new chemography method. New approach for mapping new data using supervised Isomap without re-building models from the scratch has been proposed. Two approaches for estimation of model's applicability domain are used in our study to our knowledge for the first time in chemoinformatics. The structural alerts responsible for the negative characteristics of pharmacological profile of chemical compounds has been found as a result of model interpretation.