Search

Background Factors affecting response to SARS-CoV-2 mRNA vaccine in allogeneic hematopoietic stem cell transplantation (allo-HCT) recipients remain to be elucidated. Methods Forty allo-HCT recipients were included in a study of immunization with BNT162b2 mRNA vaccine at days 0 and 21. Binding antibodies (Ab) to SARS-CoV-2 receptor binding domain (RBD) were assessed at days 0, 21, 28, and 49 while neutralizing Ab against SARS-CoV-2 wild type (NT50) were assessed at days 0 and 49. Results observed in allo-HCT patients were compared to those obtained in 40 healthy adults naive of SARS-CoV-2 infection. Flow cytometry analysis of peripheral blood cells was performed before vaccination to identify potential predictors of Ab responses. Results Three patients had detectable anti-RBD Ab before vaccination. Among the 37 SARS-CoV-2 naive patients, 20 (54%) and 32 (86%) patients had detectable anti-RBD Ab 21 days and 49 days postvaccination. Comparing anti-RBD Ab levels in allo-HCT recipients and healthy adults, we observed significantly lower anti-RBD Ab levels in allo-HCT recipients at days 21, 28 and 49. Further, 49% of allo-HCT patients versus 88% of healthy adults had detectable NT50 Ab at day 49 while allo-HCT recipients had significantly lower NT50 Ab titers than healthy adults ( P = 0.0004). Ongoing moderate/severe chronic GVHD ( P 0.5, P, info:eu-repo/semantics/published

Emerging single-cell technologies profile multiple types of molecules within individual cells. A fundamental step in the analysis of the produced high-dimensional data is their visualization using dimensionality reduction techniques such as t-SNE and UMAP. We introduce j-SNE and j-UMAP as their natural generalizations to the joint visualization of multimodal omics data. Our approach automatically learns the relative contribution of each modality to a concise representation of cellular identity that promotes discriminative features but suppresses noise. On eight datasets, j-SNE and j-UMAP produce unified embeddings that better agree with known cell types and that harmonize RNA and protein velocity landscapes. Supplementary Information The online version contains supplementary material available at (10.1186/s13059-021-02356-5).

Background Due to continued advances in sequencing technology, the limitation in understanding biological systems through an “-omics” lens is no longer the generation of data, but the ability to analyze it. Importantly, much of this rich -omics data is publicly available waiting to be further investigated. Although many code-based pipelines exist, there is a lack of user-friendly and accessible applications that enable rapid analysis or visualization of data. Results GECO (Gene Expression Clustering Optimization; http://www.theGECOapp.com) is a minimalistic GUI app that utilizes non-linear reduction techniques to rapidly visualize expression trends in many types of biological data matrices (such as bulk RNA-seq or proteomics). The required input is a data matrix with samples and any type of expression level of genes/protein/other with a unique ID. The output is an interactive t-SNE or UMAP analysis that clusters genes (or proteins/other unique IDs) based on their expression patterns across the multiple samples enabling visualization of expression trends. Customizable settings for dimensionality reduction, data normalization, along with visualization parameters including coloring and filters, ensure adaptability to a variety of user uploaded data. Conclusion This local and cloud-hosted web browser app enables investigation of any -omic data matrix in a rapid and code-independent manner. With the continued growth of available -omic data, the ability to quickly evaluate a dataset, including specific genes of interest, is more important than ever. GECO is intended to supplement traditional statistical analysis methods and is particularly useful when visualizing clusters of genes with similar trajectories across many samples (ex: multiple cell types, time course, dose response). Users will be empowered to investigate -omic data with a new lens of visualization and analysis that has the potential to uncover genes of interest, cohorts of co-regulated genes programs, and previously undetected patterns of expression.

Content-Centric Networking (CCN) is regarded as a promising network architecture which has received the distinct interest from many global research communities thanks to its friendly structure, especially its caching technology has attracted the most widespread attention. However, the current caching strategies have some limitations, such as redundant content copies, low cache utilization rate and unbalanced node load. In order to further optimize cache, this paper investigates the classical cache allocation problem, i.e., distributing the cache capacity across some Content Routers (CRs) under a constrained and fixed total cache budget. At first, both topology information and traffic characteristics as two factors to determine the importance of CR, where the evaluation of network topology depends on degree centrality, betweenness centrality and closeness centrality while that of traffic characteristics depends on node load and interest preference. In particular, given the data redundancy due to the high-dimensional feature, increasing the complexity of computation, t-distributed Stochastic Neighbor Embedding (t-SNE) is used to reduce the dimensions of data. Then, for the CR with cache capacity, its Content Store (CS) is divided into collaborative region and non-collaborative region by a heuristic algorithm to facilitate the optimal performance, and the CS with collaboration needs to interact the cached information with its neighborhoods. Finally, the performance evaluation is driven by the real dataset over GTS-CE topology. The experimental results reveal that the proposed collaboration-supported cache allocation strategy is more efficient than two baselines, i.e., increasing cache hit ratio by 7.79%, increasing cache utilization rate by 11.31%, decreasing routing delay by 49.38% and decreasing load balance by 50.98%.

This paper presents an approach towards word recognition based on embedded prototype subspace classification.The purpose of this paper is three-fold. Firstly, a new dataset for word recognition is presented, which is extractedfrom the Esposalles database consisting of the Barcelona cathedral marriage records. Secondly, different clusteringtechniques are evaluated for Embedded Prototype Subspace Classifiers. The dataset, containing 30 different classesof words is heavily imbalanced, and some word classes are very similar, which renders the classification task ratherchallenging. For ease of use, no stratified sampling is done in advance, and the impact of different data splits isevaluated for different clustering techniques. It will be demonstrated that the original clustering technique based onscaling the bandwidth has to be adjusted for this new dataset. Thirdly, an algorithm is therefore proposed that findskclusters, striving to obtain a certain amount of feature points in each cluster, rather than finding some clustersbased on scaling the Silverman’s rule of thumb. Furthermore, Self Organising Maps are also evaluated as both aclustering and embedding technique.

This paper proposes a novel fault classification method with application to induction motors, which is based on integrating and combining with receiver operating characteristic (ROC) curve and t-distribution stochastic neighbor embedding (t-SNE). According to the feature selection methods of ReliefF, symmetrical uncertainty (SU), and fast correlation-based filter (FCBF), the significant features were verified. Additionally, support vector machine (SVM), k-nearest neighbor (KNN), and decision tree (DT) are also considered as classifiers to identify the simulation results. To begin with, the current signals obtained from distinctive four topologies of working conditions of the motor, which includes healthy, bearing damage, broken rotor bar, and short circuit in stator windings, respectively. The potential feature set is extracted by using Hilbert-Huang transform (HHT) technique. Then, three feature selection methods are adopted to select three optimal feature subsets from the original feature set. Finally, the classification accuracy (ACC) and ROC curve are used to demonstrate the capability of classifiers’ recognition. The results showed that the optimal feature subsets significantly reduce the number of selected features and improve the classification ACC and area under the curve (AUC) compared with the original feature set. In conclusion, the proposed method can downgrade the data, demonstrate the scatter plot more intuitively, and identify various types of faults, unlike with other fault diagnosis literature.

Coronaviruses infect many animals, including humans, due to interspecies transmission. Three of the known human coronaviruses: MERS, SARS-CoV-1, and SARS-CoV-2, the pathogen for the COVID-19 pandemic, cause severe disease. Improved methods to predict host specificity of coronaviruses will be valuable for identifying and controlling future outbreaks. The coronavirus S protein plays a key role in host specificity by attaching the virus to receptors on the cell membrane. We analyzed 1238 spike sequences for their host specificity. Spike sequences readily segregate in t-SNE embeddings into clusters of similar hosts and/or virus species. Machine learning with SVM, Logistic Regression, Decision Tree, Random Forest gave high average accuracies, F1 scores, sensitivities and specificities of 0.95–0.99. Importantly, sites identified by Decision Tree correspond to protein regions with known biological importance. These results demonstrate that spike sequences alone can be used to predict host specificity., Highlights • Coronavirus spike protein sequences can predict host specificity. • Machine learning had accuracies of >0.98 for classification of human vs non-human hosts. • Decision Tree classifier identified spike regions with important biological roles . • Clustering with t-SNE embeddings correctly segregated sequences by virus genus and host .

Traumatic brain injury (TBI) causes a profound inflammatory response within the central nervous system and peripheral immune system, which contributes to secondary brain injury and further morbidity and mortality. Preclinical investigations have demonstrated that treatments that downregulate microglia activation and polarize them toward a reparative/anti‐inflammatory phenotype have improved outcomes in preclinical models. However, no therapy to date has translated into proven benefits in human patients. Regulatory T cells (Treg) have been shown to downregulate pathologic immune responses of the innate and adaptive immune system across a variety of pathologies. Furthermore, cellular therapy has been shown to augment host Treg responses in preclinical models; yet, studies investigating the use of Treg as a therapeutic for TBI are lacking. In a rodent TBI model, we demonstrate that human umbilical cord blood Treg modulate the central and peripheral immune response after injury in vitro and in vivo., A rat model of traumatic brain injury was used to determine whether regulatory T cells (Treg) could be used to treat neuroinflammation associated with severe central nervous system trauma. We utilized multicolor flow cytometry 30d after injury to rapidly assess the changes in the phenotype of microglia, which were visualized using a dimensional reduction algorithm (t‐distributed stochastic neighbor embedding). This method clearly maps populations that change as a result of injury but respond to Treg treatment. Further analysis demonstrates that these particular populations express microglia markers that change in expression levels in response to injury, including CD11bc (pictured here). This response is ameliorated by Treg treatment 24 hours after injury.

Ecoacoustics needs sophisticated acoustic monitoring tools to extract a wide level of features from an observed mixture of sounds. We have developed a portable acoustic monitoring system called ‘HARKBird’ which consists of a laptop PC and an inexpensive commercial microphone array with the robot audition software HARK. HARKBird can extract acoustic events in a recording, and we can obtain the begin and end timings, the spatial information (e.g., position or direction from the microphone array), and the spectrogram of the sound separated from the original recording. In this study, we report how robot audition techniques contribute to monitoring spatio‐spectro‐temporal dynamics of bird behaviors, using an extended and minimal system based on multiple microphone arrays. The dimension reduction of separated sounds is important to integrate the information from multiple microphone arrays. As a dimension reduction algorithm, we use t‐SNE to help manual annotation of each sound and to generate the vocalization distribution automatically. We conduct playback experiments to Spotted Towhee (Pipilo maculatus) to simulate different cases of territorial intrusions (song/call/no playback). Our hypothesis in playback experiments is that playback of conspecific vocalizations would invoke aggressive responses of males against song playbacks and the effects would be more prominent than those of call playbacks. Our primary aim is to test whether our system can extract the necessary information on the aggressiveness of target individuals to examine our hypothesis. We show the system with manual annotation of vocalizations can extract their different spatio‐spectro‐temporal dynamics in different conditions, which supported our hypothesis. We also consider the spectral affinity‐based automatic matching of localized sounds from different microphone arrays. The relative number of localized songs depending on the playback conditions reflected a similar trend to those in the manual approach, implying that we can grasp the long‐term dynamics of vocalizations without costly annotations.

The rapid development of learning technologies has enabled online learning paradigm to gain great popularity in both high education and K-12, which makes the prediction of student performance become one of the most popular research topics in education. However, the traditional prediction algorithms are originally designed for balanced dataset, while the educational dataset typically belongs to highly imbalanced dataset, which makes it more difficult to accurately identify the at-risk students. In order to solve this dilemma, this study proposes an integrated framework (LVAEPre) based on latent variational autoencoder (LVAE) with deep neural network (DNN) to alleviate the imbalanced distribution of educational dataset and further to provide early warning of at-risk students. Specifically, with the characteristics of educational data in mind, LVAE mainly aims to learn latent distribution of at-risk students and to generate at-risk samples for the purpose of obtaining a balanced dataset. DNN is to perform final performance prediction. Extensive experiments based on the collected K-12 dataset show that LVAEPre can effectively handle the imbalanced education dataset and provide much better and more stable prediction results than baseline methods in terms of accuracy and F1.5 score. The comparison of t-SNE visualization results further confirms the advantage of LVAE in dealing with imbalanced issue in educational dataset. Finally, through the identification of the significant predictors of LVAEPre in the experimental dataset, some suggestions for designing pedagogical interventions are put forward.

We demonstrate the use of a convolutional neural network to perform neutron-gamma pulse shape discrimination, where the only inputs to the network are the raw digitised SiPM signals from a dual scintillator detector element made of 6LiF:ZnS(Ag) scintillator and PVT plastic. A realistic labelled dataset was created to train the network by exposing the detector to an AmBe source, and a data-driven method utilsing a separate PMT was used to assign labels to the recorded signals. This approach is compared to the charge integration and continuous wavelet transform methods and is found to provide superior levels of discrimination, achieving an AUC of 0.995 +/- 0.003. We find that the neural network is capable of extracting interpretable features directly from the raw data. In addition, by visualising the high-dimensional representations of the network with the t-SNE algorithm, we discover that not only is this method robust to minor mislabeling of the training dataset but that it is possible to identify an underlying substructure within the signals that goes beyond the original labelling. This technique could be utilised to explore and cluster complex, raw detector data in a novel way that may reveal more insights than standard analysis methods., 13 pages, 8 figures, submitted to Nucl. Instr. Meth. A

Understanding students’ learning processes and education-related phenomena by extracting knowledge from educational data sets represents a continuous interest in the educational data mining domain. Due to an accelerated expansion of online learning and digitalisation in education, there is a growing interest in understanding the impact of online learning on the academic performance of students. In this study, we comparatively investigate traditional and synchronous online learning methods to assess students’ performance through the use of deep autoencoders. Experiments performed on real data sets collected in both online and traditional learning environments showed that autoencoders are able to detect hidden patterns in academic data sets unsupervised, these patterns are valuable for the prediction of students’ performance. The obtained results emphasized that, for the considered case studies, traditional evaluations are a little more accurate than online evaluations. Still, after applying a one-tailed paired Wilcoxon signed-rank test, no statistically significant difference between the traditional and online evaluations was observed.

Behavioral systems, understanding it as an emergent system comprising the environment and organism subsystems, include spatial dynamics as a primary dimension in natural settings. Nevertheless, under the standard approaches, the experimental analysis of behavior is based on the single response paradigm and the temporal distribution of discrete responses. Thus, the continuous analysis of spatial behavioral dynamics has been a scarcely studied field. The technological advancements in computer vision have opened new methodological perspectives for the continuous sensing of spatial behavior. With the application of such advancements, recent studies suggest that there are multiple features embedded in the spatial dynamics of behavior, such as entropy, and that they are affected by programmed stimuli (e.g., schedules of reinforcement), at least, as much as features related to discrete responses. Despite the progress, the characterization of behavioral systems is still segmented, and integrated data analysis and representations between discrete responses and continuous spatial behavior are exiguous in the Experimental Analysis of Behavior. Machine Learning advancements, such as t-SNE, variable ranking, provide invaluable tools to crystallize an integrated approach for analyzing and representing multidimensional behavioral data. Under this rationale, the present work: 1) proposes a multidisciplinary approach for the integrative and multilevel analysis of behavioral systems, 2) provides sensitive behavioral measures based on spatial dynamics and helpful data representations to study behavioral systems, and 3) reveals behavioral aspects usually ignored under the standard approaches in the experimental analysis of behavior. To exemplify and evaluate our approach, the spatial dynamics embedded in phenomena relevant to behavioral science, namely water-seeking behavior, and motivational operations, are examined, showing aspects of behavioral systems hidden until now. Keywords: Behavioral systems; spatial-behavioral dynamics; time-based schedules; water-seeking behavior; motivational operations; Machine Learning; t-SNE; entropy

This work deals with the presentation of a spiking neural network as a means for efficiently solving the reduction of dimensionality of data in a nonlinear manner. The underneath neural model, which can be integrated as neuromorphic hardware, becomes suitable for intelligent processing in edge computing within Internet of Things systems. In this sense, to achieve a meaningful performance with a low complexity one-layer spiking neural network, the training phase uses the metaheuristic Artificial Bee Colony algorithm with an objective function from the principals in the machine learning science, namely, the modified Stochastic Neighbor Embedding algorithm. To demonstrate this fact, complex benchmark data were used and the results were compared with those generated by a reference network with continuous-sigmoid neurons. The goal of this work is to demonstrate via numerical experiments another method for training spiking neural networks, where the used optimizer comes from metaheuristics. Therefore, the key issue is defining the objective function, which can relate optimally the information at both sides of the spiking neural network. Certainly, machine learning techniques have advanced in defining efficient loss functions that can become suitable objective function candidates in the metaheuristic training phase. The practicality of these ideas is shown in this article. We use MSE values for evaluating the relative quality of the results and also co-ranking matrices.

Transcriptome profiling and differential gene expression constitute a ubiquitous tool in biomedical research and clinical application. Linear dimensionality reduction methods especially principal component analysis (PCA) are widely used in detecting sample-to-sample heterogeneity in bulk transcriptomic datasets so that appropriate analytic methods can be used to correct batch effects, remove outliers and distinguish subgroups. In response to the challenge in analysing transcriptomic datasets with large sample size such as single-cell RNA-sequencing (scRNA-seq), non-linear dimensionality reduction methods were developed. t-distributed stochastic neighbour embedding (t-SNE) and uniform manifold approximation and projection (UMAP) show the advantage of preserving local information among samples and enable effective identification of heterogeneity and efficient organisation of clusters in scRNA-seq analysis. However, the utility of t-SNE and UMAP in bulk transcriptomic analysis has not been carefully examined. Therefore, we compared major dimensionality reduction methods (linear: PCA; nonlinear: multidimensional scaling (MDS), t-SNE, and UMAP) in analysing 71 bulk transcriptomic datasets with large sample sizes. UMAP was found superior in preserving sample level neighbourhood information and maintaining clustering accuracy, thus conspicuously differentiating batch effects, identifying pre-defined biological groups and revealing in-depth clustering structures. We further verified that new clustering structures visualised by UMAP were associated with biological features and clinical meaning. Therefore, we recommend the adoption of UMAP in visualising and analysing of sizable bulk transcriptomic datasets.

Malware has become a major threat to cyberspace security, not only because of the increasing complexity of malware itself, but also because of the continuously created and produced malicious code. In this paper, we propose two novel methods to solve the malware identification problem. One is to solve to malware classification. Different from traditional machine learning, our method introduces the ensemble models to solve the malware classification problem. The other is to solve malware family clustering. Different from the classic malware family clustering algorithm, our method introduces the t-SNE algorithm to visualize the feature data and then determines the number of malware families. The two proposed novel methods have been extensively tested on a large number of real-world malware samples. The results show that the first one is far superior to the existed individual models and the second one has a good adaptation ability. Our methods can be used for malicious code classification and family clustering, also with higher accuracy.

Unsupervised learning is applicable to classification that does not know the number of specific categories in advance, and sparse auto-encoders (SAE) are widely used for feature extraction of unsupervised learning. Therefore, this paper proposes an electromagnetic signal classification system based on SAE which is combined with the machine learning clustering algorithm. In particular, we propose to perform feature preprocessing on signals using STFT. Then, the features extracted by SAE training are clustered by t-SNE and DBSCAN to obtain clustering results. Finally, we prove the feasibility of this method classification by comparing with traditional clustering methods. Because of the feature extraction, SAE not only learns the key feature information but also effectively compresses the data content, which greatly reduces the data dimension that the clustering algorithm needs to deal with and improves the clustering accuracy. As the experimental results show, the evaluation indicators of the result obtained by our method are significantly improved compared with the traditional clustering algorithms, the compactness (CP) index decreases by 73.76%; the Davies-Bouldin Index (DB) decreases by 18.50%; the Dunn Validity Index (DVI) increases by 6.24%; and the Rand Index (RI) increases by 43.14%.

Today, a lot of different materials are used in human activity. These materials are distinguished by their mechanical properties, colour, and chemical composition. A wide variety of materials raises the problem of keeping information about them and about their visualization. A database of materials and an online application that provides access to information on various types of metals and their alloys, as well as to find the nearest analogues with the help of intelligent search function is created in the work. To create the database, MySQL database management system is used. Filling of this database is done by developing a special parser program. This program scanned pages from the Internet and highlighted the properties of the materials and stored them in the database. Dimensional reduction algorithms are used to visualize the data. These algorithms are aimed at finding such a projection of high-dimensional data into low-dimensional space. When using this projection, all internal relationships between the data are stored. This made it possible to construct and visualize large-dimensional data on a plane. To do this, the isomap, mds, t-sne algorithms are used. Thus, the database of materials was developed in the work. Access to the database provided through a web application. The web application provides the ability to use it from all devices that have access to the Internet and eliminates the need to install additional software. The web application uses a python programming language and a special framework Flask for creating web applications. This technology choice greatly simplifies the creation of web applications and allows us to quickly and flexibly manage your data. Visualizations are built for the collected data. To visualize data, one of the main tasks is to reduce the dimension of data. Reducing dimensionality requires accessible visualization methods that work effectively in two or three dimensional spaces. According to the results of the visualization, clusters of materials that correspond to already known classes of materials are revealed. This confirms the correctness of constructing visualization models and reducing the dimensionality, as well as the correctness of the information gathered.

It was meaningful to predict the customers' decision-making behavior in the field of market. However, due to individual differences and complex, non-linear natures of the electroencephalogram (EEG) signals, it was hard to classify the EEG signals and to predict customers' decisions by using traditional classification methods. To solve the aforementioned problems, a recurrent t-distributed stochastic neighbor embedding (t-SNE) neural network was proposed in current study to classify the EEG signals in the designed brand extension paradigm and to predict the participants' decisions (whether to accept the brand extension or not). The recurrent t-SNE neural network contained two steps. In the first step, t-SNE algorithm was performed to extract features from EEG signals. Second, a recurrent neural network with long short-term memory (LSTM) layer, fully connected layer, and SoftMax layer was established to train the features, classify the EEG signals, as well as predict the cognitive performance. The proposed network could give a good prediction with accuracy around 87%. Its superior in prediction accuracy as compared to a recurrent principal component analysis (PCA) network, a recurrent independent component correlation algorithm [independent component analysis (ICA)] network, a t-SNE support vector machine (SVM) network, a t-SNE back propagation (BP) neural network, a deep LSTM neural network, and a convolutional neural network were also demonstrated. Moreover, the performance of the proposed network with different activated channels were also investigated and compared. The results showed that the proposed network could make a relatively good prediction with only 16 channels. The proposed network would become a potentially useful tool to help a company in making marketing decisions and to help uncover the neural mechanisms behind individuals' decision-making behavior with low cost and high efficiency.

Objective To visualize the encoding capability of magnetic resonance fingerprinting (MRF) dictionaries. Materials and methods High-dimensional MRF dictionaries were simulated and embedded into a lower-dimensional space using t-distributed stochastic neighbor embedding (t-SNE). The embeddings were visualized via colors as a surrogate for location in low-dimensional space. First, we illustrate this technique on three different MRF sequences. We then compare the resulting embeddings and the color-coded dictionary maps to these obtained with a singular value decomposition (SVD) dimensionality reduction technique. We validate the t-SNE approach with measures based on existing quantitative measures of encoding capability using the Euclidean distance. Finally, we use t-SNE to visualize MRF sequences resulting from an MRF sequence optimization algorithm. Results t-SNE was able to show clear differences between the color-coded dictionary maps of three MRF sequences. SVD showed smaller differences between different sequences. These findings were confirmed by quantitative measures of encoding. t-SNE was also able to visualize differences in encoding capability between subsequent iterations of an MRF sequence optimization algorithm. Discussion This visualization approach enables comparison of the encoding capability of different MRF sequences. This technique can be used as a confirmation tool in MRF sequence optimization.

International audience; From state-of-the-art visualization algorithms, we distill six working principles which are, by hypothesis, sufficient to produce visual projections qualitatively similar to those obtained with these state-of-the-art algorithms. These working principles are presented through the geometrical reasoning of the classical Multidimensional Scaling algorithm, and their effectiveness is illustrated through a novel straightforward algorithm for data visualization. We show, using several datasets originated from various applications, that our algorithm can produce visual projections qualitatively similar to those obtained with these state-of-the-art algorithms. Besides, under the same motivation (of simplification), the problem of visualizing large datasets is tackled through a companion algorithm which is able to embed new input patterns.

As a data-driven dimensionality reduction and visualization tool, t-distributed stochastic neighborhood embedding (t-SNE) has been successfully applied to a variety of fields. In recent years, it has also received increasing attention for classification and regression analysis. This study presented a t-SNE based classification approach for compositional microbiome data, which enabled us to build classifiers and classify new samples in the reduced dimensional space produced by t-SNE. The Aitchison distance was employed to modify the conditional probabilities in t-SNE to account for the compositionality of microbiome data. To classify a new sample, its low-dimensional features were obtained as the weighted mean vector of its nearest neighbors in the training set. Using the low-dimensional features as input, three commonly used machine learning algorithms, logistic regression (LR), support vector machine (SVM), and decision tree (DT) were considered for classification tasks in this study. The proposed approach was applied to two disease-associated microbiome datasets, achieving better classification performance compared with the classifiers built in the original high-dimensional space. The analytic results also showed that t-SNE with Aitchison distance led to improvement of classification accuracy in both datasets. In conclusion, we have developed a t-SNE based classification approach that is suitable for compositional microbiome data and may also serve as a baseline for more complex classification models.

The recurrent use of databases with categorical variables in different applications demands new alternatives to identify relevant patterns. Classification is an interesting approach for the recognition of this type of data. However, there are a few amount of methods for this purpose in the literature. Also, those techniques are specifically focused only on kernels, having accuracy problems and high computational cost. For this reason, we propose an identification approach for categorical variables using conventional classifiers (LDC-QDC-KNN-SVM) and different mapping techniques to increase the separability of classes. Specifically, we map the initial features (categorical attributes) to another space, using the Chi-square (C-S) as a measure of dissimilarity. Then, we employ the (t-SNE) for reducing dimensionality of data to two or three features, allowing a significant reduction of computational times in learning methods. We evaluate the performance of proposed approach in terms of accuracy for several experimental configurations and public categorical datasets downloaded from the UCI repository, and we compare with relevant state of the art methods. Results show that C-S mapping and t-SNE considerably diminish the computational times in recognitions tasks, while the accuracy is preserved. Also, when we apply only the C-S mapping to the datasets, the separability of classes is enhanced, thus, the performance of learning algorithms is clearly increased.

PurposeTo extract texture features from magnetic resonance imaging (MRI) scans of patients with brain tumors and use them to train a classification model for supporting an early diagnosis.MethodsTwo groups of regions (control and tumor) were selected from MRI scans of 40 patients with meningioma or glioma. These regions were analyzed to obtain texture features. Statistical analysis was conducted using SPSS (version 20.0), including the Shapiro–Wilk test and Wilcoxon signed-rank test, which were used to test significant differences in each feature between the tumor and healthy regions. T-distributed stochastic neighbor embedding (t-SNE) was used to visualize the data distribution so as to avoid tumor selection bias. The Gini impurity index in random forests (RFs) was used to select the top five out of all features. Based on the five features, three classification models were built respectively with three machine learning classifiers: RF, support vector machine (SVM), and back propagation (BP) neural network.ResultsSixteen of the 25 features were significantly different between the tumor and healthy areas. Through the Gini impurity index in RFs, standard deviation, first-order moment, variance, third-order absolute moment, and third-order central moment were selected to build the classification model. The classification model trained using the SVM classifier achieved the best performance, with sensitivity, specificity, and area under the curve of 94.04%, 92.3%, and 0.932, respectively.ConclusionTexture analysis with an SVM classifier can help differentiate between brain tumor and healthy areas with high speed and accuracy, which would facilitate its clinical application.

On becoming a commodity, Microgrids (MGs) have started gaining ground in various sizes (e.g., nanogrids, homegrids, etc.) and forms (e.g., local energy communities) leading an exponential growth in the respective sector. From demanding deployments such as military bases and hospitals, to tertiary and residential buildings and neighborhoods, MG systems exploit renewable and conventional generation assets, combined with various storage capabilities to deliver a completely new set of business opportunities and services in the context of the Smart Grid. As such systems involve economic, environmental and technical aspects, their performance is quite difficult to evaluate, since there are not any standards that cover all of these aspects, especially during operational stages. Towards allowing an holistic definition of a MG performance, for both design and operational stages, this paper first introduces a complete set of Key Performance Indicators to measure holistically the performance of a MG&rsquo, s life cycle. Following, focusing on the MG&rsquo, s day-to-day operation, a data-driven assessment is proposed, based on dynamic metrics, custom made reference models, and smart meter data, in order to be able to extract its operational performance. Two different algorithmic implementations (i.e., Dynamic Time Warping and t-distributed Stochastic Neighbor Embedding) are used to support the methodology proposed, while real-life data are used from a small scale MG to provide the desired proof-of-concept. Both algorithms seem to correctly identify days and periods of not optimal operation, hence presenting promising results for MG performance assessment, that could lead to a MG Performance Classification scheme.

Objectives By deploying a novel combination of machine learning approaches, we aim to investigate the contributions of each local and systemic risk factors in multi-etiology of knee osteoarthritis (KOA) to disease onset and deterioration. Methods A machine-learning-based KOA progression prediction model is developed using the data from the National Institute of Health Osteoarthritis Biomarkers Consortium. According to Kellgren-Lawrence (KL) grade of plain radiographs at baseline, the subjects are divided into either KOA onset or deterioration study groups. The disease progression is defined as the changes in both joint space width (JSW) and WOMAC pain score. In addition to radiographic and symptomatic data, the anthropological particulars, history of the knee injury and surgery, metabolic syndrome and living habits were deployed in a multi-layer perceptron (MLP) to predict disease progression in each study group. The relative contributions of each risk factors were weighted via DeepLIFT gradient. Additionally, statistical interactions among risk factors were identified compared. Results Our model achieved AUC of 0.843 (95% CI 0.824, 0.862) and 0.765 (95% CI 0.756, 0.774) in prediction of KOA onset and deterioration, respectively. For KOA onset prediction, history of injury has attained the highest DeepLIFT gradient except medial joint space narrowing; while for KOA deterioration prediction, diabetes and habit of smoking obtained second and third highest gradients respectively aside from medial joint space narrowing, surpassing the impact of the injury. Conclusion We developed a machine learning workflow which effectively dissects the risk factors’ contributions and their mutual interactions for onset and deterioration of KOA respectively.

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.

Despite the remarkable evolution of flow cytometers, fluorescent probes, and flow cytometry analysis software, most users still follow the same ways for data analysis. Conventional flow cytometry analysis relies on the creation of dot plot sequences, based on two fluorescence parameters at a time, to evidence phenotypically distinct populations. Thus, reaching conclusions about the biological characteristics of the samples is a fragmented and challenging process. We present here the MCTA (Multiparametric Color Tendency Analysis), a method for data analysis that considers multiple labelings simultaneously, extending and complementing conventional analysis. The MCTA method executes the background fluorescence exclusion, spillover compensation, and a user-defined gating strategy for subpopulation analysis. The results are then presented in conventional FSC x SSC dot plots with statistical data. For each event, the method converts each of the multiple fluorescence colors under analysis into a vector, with longer vectors being attributed to more intense labelings. Then, the MCTA generates a resultant vector, which is therefore mostly influenced by predominant labelings. The radial position of this resultant vector corresponds to a resultant color, making it easy to visualize phenotypic modulations among cellular subpopulations. Besides, it is a deterministic method that quickly assigns a resulting color to all events that obey the gating strategy, with no polymeric regions defined by the user or downsampling. The MCTA application generates a single dot plot showing all events in the FCS file, but a resultant color is attributed only to those that obey the gating strategy. Therefore, it can also help to evidence rare events or unpredicted subpopulations naturally excluded from the regions defined by the user. We believe that the MCTA method adds a new perspective over multiparametric flow cytometry analysis while evidencing modulations of molecular labeling profiles based on multiple fluorescences. Availability and implementation: The instructions for the MCTA application is freely available at https://github.com/flowcytometry/MCTA.

For a suspected forgery that involves the falsification of a document or its contents, the investigator will primarily analyze the document&rsquo, s paper and ink in order to establish the authenticity of the subject under investigation. As a non-destructive and contactless technique, Hyperspectral Imaging (HSI) is gaining popularity in the field of forensic document analysis. HSI returns more information compared to conventional three channel imaging systems due to the vast number of narrowband images recorded across the electromagnetic spectrum. As a result, HSI can provide better classification results. In this publication, we present results of an approach known as the t-Distributed Stochastic Neighbor Embedding (t-SNE) algorithm, which we have applied to HSI paper data analysis. Even though t-SNE has been widely accepted as a method for dimensionality reduction and visualization of high dimensional data, its usefulness has not yet been evaluated for the classification of paper data. In this research, we present a hyperspectral dataset of paper samples, and evaluate the clustering quality of the proposed method both visually and quantitatively. The t-SNE algorithm shows exceptional discrimination power when compared to traditional PCA with k-means clustering, in both visual and quantitative evaluations.

In the field of supervised machine learning, the quality of a classifier model is directly correlated with the quality of the data that is used to train the model. The presence of unwanted outliers in the data could significantly reduce the accuracy of a model or, even worse, result in a biased model leading to an inaccurate classification. Identifying the presence of outliers and eliminating them is, therefore, crucial for building good quality training datasets. Pre-processing procedures for dealing with missing and outlier data, commonly known as feature engineering, are standard practice in machine learning problems. They help to make better assumptions about the data and also prepare datasets in a way that best expose the underlying problem to the machine learning algorithms. In this work, we propose a multistage method for detecting and removing outliers in high-dimensional data. Our proposed method is based on utilising a technique called t-distributed stochastic neighbour embedding (t-SNE) to reduce high-dimensional map of features into a lower, two-dimensional, probability density distribution and then use a simple descriptive statistical method called interquartile range (IQR) to identifying any outlier values from the density distribution of the features. t-SNE is a machine learning algorithm and a nonlinear dimensionality reduction technique well-suited for embedding high-dimensional data for visualisation in a low-dimensional space of two or three dimensions. We applied this method on a dataset containing images for training a convolutional neural network model (ConvNet) for an image classification problem. The dataset contains four different classes of images: three classes contain defects in construction (mould, stain, and paint deterioration) and a no-defect class (normal). We used the transfer learning technique to modify a pre-trained VGG-16 model. We used this model as a feature extractor and as a benchmark to evaluate our method. We have shown that, when using this method, we can identify and remove the outlier images in the dataset. After removing the outlier images from the dataset and re-training the VGG-16 model, the results have also shown that the accuracy of the classification has significantly improved and the number of misclassified cases has also dropped. While many feature engineering techniques for handling missing and outlier data are common in predictive machine learning problems involving numerical or categorical data, there is little work on developing techniques for handling outliers in high-dimensional data which can be used to improve the quality of machine learning problems involving images such as ConvNet models for image classification and object detection problems.

Dissemination of fake news on Twitter is a rapidly growing problem, mostly due to the increasing number of bots. Hence, automatic bot detection is becoming an important area of research. In this work, we present the BERT- based bot detection model along with exploratory data analysis of tweets written by bots and humans. We statistically prove that including additional features alongside contextualized embeddings boosts model performance. Furthermore, we develop a gender prediction model using derived features and compare the difficulties of the two tasks. Finally, we demonstrate how Logistic Regression outperforms Deep Neural Network on both tasks.

Summary Untargeted metabolomics is used to refine the development of biomarkers for the diagnosis of cardiovascular disease. Myocardial infarction (MI) has major individual and societal consequences for patients, who remain at high risk of secondary events, despite advances in pharmacological therapy. To monitor their differential response to treatment, we performed untargeted plasma metabolomics on 175 patients from the platelet inhibition and patient outcomes (PLATO) trial treated with ticagrelor and clopidogrel, two common P2Y12 inhibitors. We identified a signature that discriminates patients, which involves polyunsaturated fatty acids (PUFAs) and particularly the omega-3 fatty acids docosahexaenoate and eicosapentaenoate. The known cardiovascular benefits of PUFAs could contribute to the efficacy of ticagrelor. Our work, beyond pointing out the high relevance of untargeted metabolomics in evaluating response to treatment, establishes PUFA metabolism as a pathway of clinical interest in the recovery path from MI., Graphical abstract, Highlights We detect an extreme metabolomic signature of myocardial infarction (MI) in plasma Polyunsaturated fatty acids (PUFAs) are upregulated in patients taking ticagrelor PUFA metabolism is a pathway of clinical interest in the recovery path from MI Data science methods detect biologically meaningful patterns in metabolite signals, Samman et al. present a metabolomics study of 350 samples from participants hospitalized for acute coronary syndrome. The analyses reveal that polyunsaturated fatty acids levels are upregulated in patients taking ticagrelor compared to clopidogrel, highlighting a pathway of potential clinical interest in the recovery path from myocardial infarction.

It is crucial to effectively and accurately diagnose the faults of rotating machinery. However, the high-dimensional characteristic of the features, which are extracted from the vibration signals of rotating machinery, makes it difficult to accurately recognize the fault mode. To resolve this problem, t-distributed stochastic neighbor embedding (t-SNE) is introduced to reduce the dimensionality of the feature vector in this paper. Therefore, the article describes a proposed method for fault diagnosis of rotating machinery based on local characteristic decomposition-sample entropy (LCD-SampEn), t-SNE and random forest (RF). First, the original vibration signals of rotating machinery are decomposed to a number of intrinsic scale components (ISCs) by the LCD. Next, the feature vector is obtained through calculating SampEn of each ISC. Subsequently, t-SNE is used to reduce the dimension of the feature vectors. Finally, the reconstructed feature vectors are applied to the RF for implementing the classification of the fault patterns. Two cases are studied based on the experimental data of the fault diagnoses of a bearing and a hydraulic pump. The proposed method can achieve a diagnosis rate of 98.22 % and 98.75 % for the bearing and the hydraulic pump, respectively. Compared with the other methods, the proposed approach exhibits the best performance. The results validate the effectiveness and superiority of the proposed method.

The main challenge of fault diagnosis is to extract excellent fault feature, but these methods usually depend on the manpower and prior knowledge. It is desirable to automatically extract useful feature from input data in an unsupervised way. Hence, an automatic feature extraction method is presented in this paper. The proposed method first captures fault feature from the raw vibration signal by sparse filtering. Considering that the learned feature is high-dimensional data which cannot achieve visualization, t-distributed stochastic neighbor embedding (t-SNE) is further selected as the dimensionality reduction tool to map the learned feature into a three-dimensional feature vector. Consequently, the effectiveness of the proposed method is verified using gearbox and bearing experimental datas. The classification results show that the hybrid method of sparse filtering and t-SNE can well extract discriminative information from the raw vibration signal and can clearly distinguish different fault types. Through comparison analysis, it is also validated that the proposed method is superior to the other methods.

Background Molecular space visualization can help to explore the diversity of large heterogeneous chemical data, which ultimately may increase the understanding of structure-activity relationships (SAR) in drug discovery projects. Visual SAR analysis can therefore be useful for library design, chemical classification for their biological evaluation and virtual screening for the selection of compounds for synthesis or in vitro testing. As such, computational approaches for molecular space visualization have become an important issue in cheminformatics research. The proposed approach uses molecular similarity as the sole input for computing a probabilistic surface of molecular activity (PSMA). This similarity matrix is transformed in 2D using different dimension reduction algorithms (Principal Coordinates Analysis ( PCooA), Kruskal multidimensional scaling, Sammon mapping and t-SNE). From this projection, a kernel density function is applied to compute the probability of activity for each coordinate in the new projected space. Results This methodology was tested over four different quantitative structure-activity relationship (QSAR) binary classification data sets and the PSMAs were computed for each. The generated maps showed internal consistency with active molecules grouped together for all data sets and all dimensionality reduction algorithms. To validate the quality of the generated maps, the 2D coordinates of test molecules were computed into the new reference space using a data transformation matrix. In total sixteen PSMAs were built, and their performance was assessed using the Area Under Curve (AUC) and the Matthews Coefficient Correlation (MCC). For the best projections for each data set, AUC testing results ranged from 0.87 to 0.98 and the MCC scores ranged from 0.33 to 0.77, suggesting this methodology can validly capture the complexities of the molecular activity space. All four mapping functions provided generally good results yet the overall performance of PCooA and t-SNE was slightly better than Sammon mapping and Kruskal multidimensional scaling. Conclusions Our result showed that by using an appropriate combination of metric space representation and dimensionality reduction applied over metric spaces it is possible to produce a visual PSMA for which its consistency has been validated by using this map as a classification model. The produced maps can be used as prediction tools as it is simple to project any molecule into this new reference space as long as the similarities to the molecules used to compute the initial similarity matrix can be computed.

Dimensionality reduction using the t-Distributed Stochastic Neighbor Embedding (t-SNE) algorithm has emerged as a popular tool for visualizing high-parameter single-cell data. While this approach has obvious potential for data visualization it remains unclear how t-SNE analysis compares to conventional manual hand-gating in stratifying and quantitating the frequency of diverse immune cell populations. We applied a comprehensive 38-parameter mass cytometry panel to human blood and compared the frequencies of 28 immune cell subsets using both conventional bivariate and t-SNE-guided manual gating. t-SNE analysis was capable of stratifying every general cellular lineage and most sub-lineages with high correlation between conventional and t-SNE-guided cell frequency calculations. However, specific immune cell subsets delineated by the manual gating of continuous variables were not fully separated in t-SNE space thus causing discrepancies in subset identification and quantification between these analytical approaches. Overall, these studies highlight the consistency between t-SNE and conventional hand-gating in stratifying general immune cell lineages while demonstrating that particular cell subsets defined by conventional manual gating may be intermingled in t-SNE space.

International audience; Marine mammals are found in every sea worldwide and are at the highest level of the marine food chain. They communicate among themselves through sounds. It is complicated to study and to characterize these populations because they spend most of their time below the surface. Nevertheless, it is possible to analyze, characterize and classify different cetacean species through the use of bioacoustics. Our study focuses on the Pantropical spotted dolphin (Stenella attenuata), in particular on the influence of nautical tourism, i.e. whale-watching boats, in the Caribbean Sea on dolphin communications. The objective of this study was to observe the correlation between dolphin behaviours and whistles. The most appropriate methods had to be implemented in order to analyze ethoacoustic data. To achieve this, we compared a manual method with an automatic whistle detector. Then, we used different methods of projection (ACP and t-SNE) to reduce the dimension of acoustic data. We concluded by clustering the sounds versus the behavioural classes. The results showed that our automatic method was effective as different clusters were identified : pantropical spotted dolphin do not communicate in the same manner when they are surrounded by whale-watching boats, or during socialization. Therefore, acoustic survey is an efficient non-intrusive way to characterize the form of communication and to evaluate impacts of noise on cetaceans. Our method is effective and provides opportunities for acoustic surveys of anthropophonic pollution.

In this paper, we develop a visualization tool to enhance the understanding of up to big data sets. Compared to classic data models which rely on the computing of the features (color, texture, etc.), this tool is fully feature free, as it processes directly on the data file. The Fast Compression Distance (FCD) and t-distributed Stochastic Neighbor Embedding (t-SNE) have been applied to visualize a large TerraSAR-X dataset which are annotated with up to three layers of hierarchical semantic labels, and a Sentinel-1 dataset with 10 annotated classes, in VV and VH polarization modes. We analyze the visualization results in manifold space, and try to understand and interpret them with the available semantic labels. The visualization interpretation is based on a vega-style interactive tool, which allows user zoom in, zoom out for processing large amount of data points.

Variety classification is an important step in seed quality testing. This study introduces t-distributed stochastic neighbourhood embedding (t-SNE), a manifold learning algorithm, into the field of hyperspectral imaging (HSI) and proposes a method for classifying seed varieties. Images of 800 maize kernels of eight varieties (100 kernels per variety, 50 kernels for each side of the seed) were imaged in the visible- near infrared (386.7–1016.7 nm) wavelength range. The images were pre-processed by Procrustes analysis (PA) to improve the classification accuracy, and then these data were reduced to low-dimensional space using t-SNE. Finally, Fisher’s discriminant analysis (FDA) was used for classification of the low-dimensional data. To compare the effect of t-SNE, principal component analysis (PCA), kernel principal component analysis (KPCA) and locally linear embedding (LLE) were used as comparative methods in this study, and the results demonstrated that the t-SNE model with PA pre-processing has obtained better classification results. The highest classification accuracy of the t-SNE model was up to 97.5%, which was much more satisfactory than the results of the other models (up to 75% for PCA, 85% for KPCA, 76.25% for LLE). The overall results indicated that the t-SNE model with PA pre-processing can be used for variety classification of waxy maize seeds and be considered as a new method for hyperspectral image analysis.

This article presents the analysis of the influence of household appliances on the quality of the energy consumed by the end-user. The results of the research, then, concern the final consumer (the lowest level of the power grid). The research was conducted on 120 combinations of electrical appliances connected into a grid. Each combination consisted of three devices working simultaneously in a micro-grid. The obtained and statistically analyzed data proved that there are several types of appliances that have a great influence on the power quality (PQ) parameters changes. The results of the conducted experiments indicate the devices which influenced significantly the total harmonic distortion of voltage (THDV), the voltage frequency (FREQ) and the voltage fluctuation (V). Specific features of particular devices were examined in terms of their significance for the power quality deviation. This showed the most important features which should be considered while working out the prediction model. The future of smart grids resides in data analysis, predictive models and real-time optimization. One of the key characteristics is the reducing energy consumption generated by renewable energy sources. This phenomenon, namely looking for problems connected with sustainable power quality and their appropriate solution, is described in this article. We performed an extended analysis of the smart home appliances influence of individual quantities on a real model. Furthermore, we explored devices with a high impact on chosen power quality indicators. In the end, we discuss their specific behavior and relevance to the above-described phenomenon to improve the predictive model utility. Web of Science 13 17 art. no. 4323

Low adoption of agricultural technology is among the main reasons for low farm productivity and high incidence of poverty and food insecurity in sub-Saharan countries including Tanzania. In this study, we examine the factors affecting adoption of improved sorghum varieties using data from 822 randomly selected sample households in northern and central Tanzania. We employ a multiple-hurdle Tobit model to assess the factors affecting adoption after controlling for both capital and information constraints. We also use t-distributed stochastic neighbor embedding to cluster farmers into homogeneous groups. The method allows to reduce the dimensionality while preserving the topology of the dataset, which increases the clustering accuracy. It also superiors for visualization of the clustering results. Results show that radio and other mass media outlets that create awareness will increase adoption among farmers who do not face capital constraint. Some farmers lack basic resources such as land and capital, and subsidies could have a high impact on these farmers. Other farmers simply need assurance on the performance of improved sorghum varieties. Field days, on-farm trials, and demonstration plots could be useful in supporting these farmers. A tailored support system, however, needs a sustained investment in both quantity and quality of services. There is therefore a need to develop a pluralistic research and extension systems that encourage the use of information technologies and community-based organizations to reach specific groups of farmers.

Traditionally Genetic algorithms are thought of as brute force approaches, aimed to arrive at solutions to problems which do not have a specific answer. In problems where the data is not structured for the general implementation of a specific idea, genetic algorithms are most useful. This paper proposes to mitigate the above problem of brute force approaches through elucidation of procedures ranging from exploratory analysis, followed by pattern analysis and classification. This novel conceptualization of the scheme and design will help in arriving at solutions through reduced iterations. Research conducted involves dropping of poorly performing hypotheses, controlled mutation, thereby adding a dimension of intelligence to evolutionary algorithms. The following paper describes the methodology used to solve the problem of addition of numbers using evolutionary algorithms of Neural Networks, whilst building intelligence into the system. The specific problem of addition has been dealt with in the following paper, however the same design philosophy can be extended for a paraphernalia of problems. The end goal is to obtain a generation of adroit and capable hypotheses to solve the problem in reduced number of iterations. The solution provided is generic and can be reused, it has been applied to a specific problem in the following paper.

Characterization of driving maneuvers or driving styles through motion sensors has become a field of great interest. Before now, this characterization used to be carried out with signals coming from extra equipment installed inside the vehicle, such as On-Board Diagnostic (OBD) devices or sensors in pedals. Nowadays, with the evolution and scope of smartphones, these have become the devices for recording mobile signals in many driving characterization applications. Normally multiple available sensors are used, such as accelerometers, gyroscopes, magnetometers or the Global Positioning System (GPS). However, using sensors such as GPS increase significantly battery consumption and, additionally, many current phones do not include gyroscopes. Therefore, we propose the characterization of driving style through only the use of smartphone accelerometers. We propose a deep neural network (DNN) architecture that combines convolutional and recurrent networks to estimate the vehicle movement direction (VMD), which is the forward movement directional vector captured in a phone&rsquo, s coordinates. Once VMD is obtained, multiple applications such as characterizing driving styles or detecting dangerous events can be developed. In the development of the proposed DNN architecture, two different methods are compared. The first one is based on the detection and classification of significant acceleration driving forces, while the second one relies on longitudinal and transversal signals derived from the raw accelerometers. The final success rate of VMD estimation for the best method is of 90.07%.

Background There is growing interest in utilizing artificial intelligence, and particularly deep learning, for computer vision in histopathology. While accumulating studies highlight expert-level performance of convolutional neural networks (CNNs) on focused classification tasks, most studies rely on probability distribution scores with empirically defined cutoff values based on post-hoc analysis. More generalizable tools that allow humans to visualize histology-based deep learning inferences and decision making are scarce. Results Here, we leverage t-distributed Stochastic Neighbor Embedding (t-SNE) to reduce dimensionality and depict how CNNs organize histomorphologic information. Unique to our workflow, we develop a quantitative and transparent approach to visualizing classification decisions prior to softmax compression. By discretizing the relationships between classes on the t-SNE plot, we show we can super-impose randomly sampled regions of test images and use their distribution to render statistically-driven classifications. Therefore, in addition to providing intuitive outputs for human review, this visual approach can carry out automated and objective multi-class classifications similar to more traditional and less-transparent categorical probability distribution scores. Importantly, this novel classification approach is driven by a priori statistically defined cutoffs. It therefore serves as a generalizable classification and anomaly detection tool less reliant on post-hoc tuning. Conclusion Routine incorporation of this convenient approach for quantitative visualization and error reduction in histopathology aims to accelerate early adoption of CNNs into generalized real-world applications where unanticipated and previously untrained classes are often encountered. Electronic supplementary material The online version of this article (10.1186/s12859-018-2184-4) contains supplementary material, which is available to authorized users.

Background To characterize the regional and national variation in prescribing patterns in the Medicare Part D program using dimensional reduction visualization methods. Methods Using publicly available Medicare Part D claims data, we identified and visualized regional and national provider prescribing profile variation with unsupervised clustering and t-distributed stochastic neighbor embedding (t-SNE) dimensional reduction techniques. Additionally, we examined differences between regionally representative prescribing patterns for major metropolitan areas. Results Distributions of prescribing volume and medication diversity were highly skewed among over 800,000 Medicare Part D providers. Medical specialties had characteristic prescribing patterns. Although the number of Medicare providers in each state was highly correlated with the number of Medicare Part D enrollees, some states were enriched for providers with > 10,000 prescription claims annually. Dimension-reduction, hierarchical clustering and t-SNE visualization of drug- or drug-class prescribing patterns revealed that providers cluster strongly based on specialty and sub-specialty, with large regional variations in prescribing patterns. Major metropolitan areas had distinct prescribing patterns that tended to group by major geographical divisions. Conclusions This work demonstrates that unsupervised clustering, dimension-reduction and t-SNE visualization can be used to analyze and visualize variation in provider prescribing patterns on a national level across thousands of medications, revealing substantial prescribing variation both between and within specialties, regionally, and between major metropolitan areas. These methods offer an alternative system-wide and pattern-centric view of such data for hypothesis generation, visualization, and pattern identification. Electronic supplementary material The online version of this article (10.1186/s12911-018-0670-2) contains supplementary material, which is available to authorized users.

We present a supervised dimensionality reduction technique suitable for visualizing multi-label images on a 2-D space. This method extends the use of the well-known t-distributed stochastic embedding (t-SNE) algorithm to the case of multi-labels instances, where the concept of partial relevance plays an important role. Furthermore, it is applicable straightaway for weakly annotated data. We apply our approach to generate 2-D representations of Mayan glyph-blocks, which are groups of individual glyph-signs expressing full sentences. The resulting representations are used to place visual instances in a 2-D space with the purpose of providing a browsable catalog for further epigraphic studies, where nearby instances are similar both in semantic and visual terms. We evaluate the performance of our approach quantitatively by performing classification and retrieval experiments. Our results show that this approach obtains high performance in both of these tasks.

Albeit automated classifiers offer a standard tool in many application areas, there exists hardly a generic possibility to directly inspect their behavior, which goes beyond the mere classification of (sets of) data points. In this contribution, we propose a general framework how to visualize a given classifier and its behavior as concerns a given data set in two dimensions. More specifically, we use modern nonlinear dimensionality reduction (DR) techniques to project a given set of data points and their relation to the classification decision boundaries. Furthermore, since data are usually intrinsically more than two-dimensional and hence cannot be projected to two dimensions without information loss, we propose to use discriminative DR methods which shape the projection according to given class labeling as is the case for a classification setting. With a given data set, this framework can be used to visualize any trained classifier which provides a probability or certainty of the classification together with the predicted class label. We demonstrate the suitability of the framework in the context of different dimensionality reduction techniques, in the context of different attention foci as concerns the visualization, and as concerns different classifiers which should be visualized.

The misalignment of the drive system is one of the important factors causing damage to gears and bearings on the high-speed output end of the gearbox in doubly-fed wind turbines. How to use the obtained information to determine the types of the faults accurately has always been a challenging problem for researchers. Under the restriction that only one kind of signal is used in the current wind turbine fault diagnosis, a new method based on heterogeneous information fusion is presented in this paper. The collected vibration signal, temperature signal, and stator current signal are used as original sources. Their time domain, frequency domain and time-frequency domain information are extracted as fault features. Taking into account the correlation between the features, t-distributed Stochastic Neighbor Embedding (t-SNE) is used to reduce the dimensionality of the original combinations. Then, the fusion features are put into the Least Square Support Vector Machine (LSSVM), which is optimized by artificial bee colony (ABC) algorithm. The simulation tests show that this method has higher diagnostic accuracy than other methods.

Sensors are increasingly part of our daily lives: motion detection, lighting control, and energy consumption all rely on sensors. Combining this information into, for instance, simple and comprehensive graphs can be quite challenging. Dimensionality reduction is often used to address this problem, by decreasing the number of variables in the data and looking for shorter representations. However, dimensionality reduction is often aimed at normal daily data, and applying it to events deviating from this daily data (so-called outliers) can affect such events negatively. In particular, outliers might go unnoticed. In this paper, we show that dimensionality reduction can indeed have a large impact on outliers. To that end we apply three dimensionality reduction techniques to three real-world datasets, and inspect how well they preserve outliers. We use several performance measures to show how well these techniques are capable of preserving outliers, and we discuss the results.

In the era of explosion in biological data, machine learning techniques are becoming more popular in life sciences, including biology and medicine. This research note examines the rise and fall of the most commonly used machine learning techniques in life sciences over the past three decades.