Sammon Mapping Research Articles

Using machine learning to improve anaphylaxis case identification in medical claims data.

Anaphylaxis is a severe life-threatening allergic reaction, and its accurate identification in healthcare databases can harness the potential of "Big Data" for healthcare or public health purposes. This study used claims data obtained between October 1, 2015 and February 28, 2019 from the CMS database to examine the utility of machine learning in identifying incident anaphylaxis cases. We created a feature selection pipeline to identify critical features between different datasets. Then a variety of unsupervised and supervised methods were used (eg, Sammon mapping and eXtreme Gradient Boosting) to train models on datasets of differing data quality, which reflects the varying availability and potential rarity of ground truth data in medical databases. Resulting machine learning model accuracies ranged from 47.7% to 94.4% when tested on ground truth data. Finally, we found new features to help experts enhance existing case-finding algorithms. Developing precise algorithms to detect medical outcomes in claims can be a laborious and expensive process, particularly for conditions presented and coded diversely. We found it beneficial to filter out highly potent codes used for data curation to identify underlying patterns and features. To improve rule-based algorithms where necessary, researchers could use model explainers to determine noteworthy features, which could then be shared with experts and included in the algorithm. Our work suggests machine learning models can perform at similar levels as a previously published expert case-finding algorithm, while also having the potential to improve performance or streamline algorithm construction processes by identifying new relevant features for algorithm construction.

Links of atmospheric circulation to cold days in simulations of EURO-CORDEX climate models for central Europe

Despite ongoing climate change and warming, extreme cold events still negatively affect human society. Since cold air incursions are related to specific circulation patterns, the main aims of this study are (1) to validate how well current EURO-CORDEX regional climate models (RCMs) reproduce these synoptic links and (2) to assess possible future changes in atmospheric circulation conducive to cold events. Using anomalies of daily minimum temperature, we define cold days (CDs) in central Europe and analyse their characteristics over the historical (1979−2020) and future (2070−2099) periods. We classify wintertime atmospheric circulation by applying a novel technique based on Sammon mapping to the state-of-the-art ERA5 reanalysis output. We discover that circulation types (CT) conducive to CDs are characterised by easterly advection and/or clear-sky anticyclonic conditions. While the RCM ensemble generally reproduces these synoptic links relatively well, we observe biases in the occurrence of CDs in individual simulations. These biases can be attributed to inadequately reproduced frequencies of CTs conducive to CDs (primarily propagating from driving data), as well as to deviations in the conduciveness within these CTs (primarily originating in the RCMs). Interestingly, two competing trends are identified for the end of the twenty-first century: (1) most RCMs project an increased frequency of CTs conducive to CDs, suggesting more frequent CDs, while (2) the same CTs are projected to warm faster compared to their counterparts, suggesting weaker CDs. The interplay between these opposing trends contributes to the overall uncertainty surrounding the recurrence and severity of future winter extremes in central Europe.

Using machine learning to improve anaphylaxis case identification in medical claims data.

Anaphylaxis is a severe life-threatening allergic reaction, and its accurate identification in healthcare databases can harness the potential of "Big Data" for healthcare or public health purposes. This study used claims data obtained between October 1, 2015 and February 28, 2019 from the CMS database to examine the utility of machine learning in identifying incident anaphylaxis cases. We created a feature selection pipeline to identify critical features between different datasets. Then a variety of unsupervised and supervised methods were used (eg, Sammon mapping and eXtreme Gradient Boosting) to train models on datasets of differing data quality, which reflects the varying availability and potential rarity of ground truth data in medical databases. Resulting machine learning model accuracies ranged between 47.7% and 94.4% when tested on ground truth data. Finally, we found new features to help experts enhance existing case-finding algorithms. Developing precise algorithms to detect medical outcomes in claims can be a laborious and expensive process, particularly for conditions presented and coded diversely. We found it beneficial to filter out highly potent codes used for data curation to identify underlying patterns and features. To improve rule-based algorithms where necessary, researchers could use model explainers to determine noteworthy features, which could then be shared with experts and included in the algorithm. Our work suggests machine learning models can perform at similar levels as a previously published expert case-finding algorithm, while also having the potential to improve performance or streamline algorithm construction processes by identifying new relevant features for algorithm construction.

3-WAY Secured WSN with CSDSM-DNN based Intrusion Detection Model

In Wireless Sensor Networks (WSNs), intrusion aims indegrading or even eliminating the capacity of these networks for providing their functions. Thus, in recent years, several ideas are brought and employed. However, these techniques still did not fulfill their requirements in attaining better classification accuracy. This paper proposes a novel Cosine Similarity Distance integrated Sammon Mapping learning layer-Deep Neural Network (CSDSM-DNN)-centricIntrusion Detection Model (IDM) in WSNfor attaining better outcomes. Initially, the nodes are clustered; after that, utilizing Binomial Distribution based Dwarf Mongoose Optimization (BD-DMO), the cluster heads are selected. Then, theIdentity Matrix Function-Kalman Filter (IMF-KF) identified the optimal route. Subsequently, the data is transferred via the secured route. The transferred data is pre-processed and then, the important features are selected. Lastly, to classify whether the data is attacked or non-attacked, the selected features are given into the CSDSM-DNN. Therefore, with the prevailing approaches, the experiential outcomes are evaluated and analogized and it exhibits the proposed model’s higher reliability and efficacy.

Evaluation of Mutual Information and Feature Selection for SARS-CoV-2 Respiratory Infection.

This study aims to develop a predictive model for SARS-CoV-2 using machine-learning techniques and to explore various feature selection methods to enhance the accuracy of predictions. A precise forecast of the SARS-CoV-2 respiratory infections spread can help with efficient planning and resource allocation. The proposed model utilizes stochastic regression to capture the virus transmission's stochastic nature, considering data uncertainties. Feature selection techniques are employed to identify the most relevant and informative features contributing to prediction accuracy. Furthermore, the study explores the use of neighbor embedding and Sammon mapping algorithms to visualize high-dimensional SARS-CoV-2 respiratory infection data in a lower-dimensional space, enabling better interpretation and understanding of the underlying patterns. The application of machine-learning techniques for predicting SARS-CoV-2 respiratory infections, the use of statistical measures in healthcare, including confirmed cases, deaths, and recoveries, and an analysis of country-wise dynamics of the pandemic using machine-learning models are used. Our analysis involves the performance of various algorithms, including neural networks (NN), decision trees (DT), random forests (RF), the Adam optimizer (AD), hyperparameters (HP), stochastic regression (SR), neighbor embedding (NE), and Sammon mapping (SM). A pre-processed and feature-extracted SARS-CoV-2 respiratory infection dataset is combined with ADHPSRNESM to form a new orchestration in the proposed model for a perfect prediction to increase the precision of accuracy. The findings of this research can contribute to public health efforts by enabling policymakers and healthcare professionals to make informed decisions based on accurate predictions, ultimately aiding in managing and controlling the SARS-CoV-2 pandemic.

Lancaster Stem Sammon Projective Feature Selection based Stochastic eXtreme Gradient Boost Clustering for Web Page Ranking

Web content mining retrieves the information from web in more structured forms. The page rank plays an essential part in web content mining process. Whenever user searches for any information on web, the relevant information is shown at top of list through page ranking. Many existing page ranking algorithms were developed and failed to rank the web pages in accurate manner through minimum time feeding. In direction to address the above mentioned issues, Lancaster Stem Sammon Projective Feature Selection based Stochastic eXtreme Gradient Boost Clustering (LSSPFS-SXGBC) Approach is introduced for page ranking based on user query. LSSPFS-SXGBC Approach has three processes for performing efficient web page ranking, namely preprocessing, feature selection and clustering. LSSPFS-SXGBC Approach in account of the numeral of operator request by way of an input. Lancaster Stemming Preprocessed Analysis is carried out in LSSPFS-SXGBC Approach for removing the noisy data from the input query. It eradicates the stem words, stop words and incomplete data for minimizing the time and space consumption. Sammon Projective Feature Selection Process is carried out in LSSPFS-SXGBC Approach to select the relevant features (i.e., keywords) based on user needs for efficient page ranking. Sammon Projection maps the high-dimensional space to lower dimensionality space to preserve the inter-point distance structure. After feature selection, Stochastic eXtreme Gradient Boost Page Rank Clustering process is carried out to cluster the similar keyword web pages based on their rank. Gradient Boost Page Rank Cluster is an ensemble of several weak clusters (i.e., X-means cluster). X-means cluster partitions the web pages into ‘x’ numeral of clusters where each reflection goes towards the cluster through adjacent mean value. For every weak cluster, selected features are considered as the training samples. Subsequently, all weak clusters are joined to form the strong cluster for attaining the webpage ranking results. By this way, an efficient page ranking is carried out through higher accurateness and minimum time consumption. The practical validation is carried out in LSSPFS-SXGBC Approach on factors such ranking accurateness, false positive rate, ranking time and space complexity with respect to numeral of user query.

Linear feature projective geometric damped convolutional deep belief network for indoor floor planning

Wireless localization or positioning is essential for delivering location-based services for designing location tracking systems. Traditional indoor floor planning system employs wireless signals for accurate position estimation. But these positioning schemes failed to perform position estimation effectively and accurately through many obstacles or objects. The novel technique called Linear Features Projective Geometric Damped Convolutional Deep Belief Network (LFPGDCDBN) is introduced to improve the position estimation accuracy with minimum error. The proposed LFPGDCDBN technique includes two major processes namely dimensionality reduction and position estimation. First, the dimensionality reduction process is performed by projecting the principle features using Linear Helmert–Wolf blocked Sammon projection. After the feature selection, Geometric Levenberg–Marquardt Convolutional deep belief network is employed to estimate the position of the devices with higher accuracy and minimum error. The Convolutional deep belief network uses the triangulation geometric method to identify the position of the device in an indoor positioning system. Then the Levenberg–Marquardt function is a Damped least square method to minimize the squares of the deviations between the expected and observed results at the output unit. As a result, the LFPGDCDBN increases the positioning accuracy and minimizes the error rate. Experimental MATLAB assessment is carried out with various factors such as computational time, Computational space, positioning accuracy, and positing error. The experimental results and discussion indicate that the proposed LFPGDCDBN provides improved performance in terms of achieving higher positioning accuracy and minimum error as well as computational time when compared to the existing methods. The experimental results and discussion indicate that the proposed LFPGDCDBN increases the positioning accuracy by 47% and computational time, computational complexity, and reduces the positioning error by 45%, 29%, and 74% as compared to state-of-the-art works.

Iterative Reflect Perceptual Sammon and Machine Learning-Based Bagging Classification for Efficient Tumor Detection

A tumor is an abnormal development of cells in the human body. A tumor develops when cells divide without any control. Tumors change their size from a small to large lump. Tumors appear anywhere in the body. The early stage of diagnosis is an essential one in disease treatment. Many researchers carried out their research on different tumor detection methods. However, the tumor detection accuracy level was not improved and tumor detection time consumption not minimized. In order to address these problems, an Iterative Reflect Perceptual Sammon Bagging Classification (IRPS-BAC) Method is introduced. The aim is to accurately detect brain tumors as early as possible and make the method suitable for real-time applications. The IRPS-BAC Method comprises two processes, namely, feature selection and classification using the iterative reflect perceptual sammon feature selection process and bagging classification process. In the IRPS-BAC Method, an input of medical data are gathered from the Epileptic Seizure Recognition Data Set and Cervical Cancer Risk Classification database. After that, iterative reflect perceptual sammon feature selection process is carried out to select the relevant features. Iterative reflect perceptual divergence computes the variation between two features. After that, sammon mapping projects the similar and dissimilar features into feature space. By this manner, the relevant features get selected using the IRPS-BAC Method. With the help of selected relevant features, bagging classification process is carried out. In bagging classification process, internal node processes the selected features and leaf node to make the tumor decision as normal or cancerous one based on information gain. This, in turn, helps to reduce the time complexity and error rate. The performance of the proposed IRPS-BAC Method is determined by two benchmark datasets through comparing the parameter such as tumor detection time, tumor detection accuracy and error rate with the existing approaches. In the Epileptic Seizure Recognition Data Set, the proposed IRPS-BAC Method improves tumor detection accuracy by 16%, with minimum time period and the error rate of 41 ms and 58% for tumor detection as compared to existing methods. By using Cervical Cancer Risk Classification, the proposed IRPS-BAC Method exhibited higher classification performance measures, including accuracy (14%), time (46 ms), and error rate (61%), than the current conventional approaches.

On using self‐organizing maps and discretized Sammon maps to study links between atmospheric circulation and weather extremes

AbstractClassifications by self‐organizing maps (SOMs) have been used to study links between extreme weather events and atmospheric circulation. However, SOMs may often provide a too generalized image of circulation, which is too coarse to properly resolve meteorological extremes. Several approaches have been used to circumvent this limitation, including an increase in the number of nodes and/or relaxation of the stress on topological ordering of nodes, through adjusting the neighbourhood radius. Here, we (1) test whether weighting of training fields based on extremity of their circulation could lead to SOMs that would better represent circulation extremes without impairing the topological ordering of nodes, and (2) we investigate whether Sammon maps (SM), which have so far been limited to validation of SOMs in climatology, could provide a viable alternative to SOMs in studying weather extremes. We show that removing a certain percentage of circulation fields closest to the climatological mean has a greater effect on the representation of circulation extremes than more than doubling the SOM array size. Additionally, this step allows for decreasing the neighbourhood radius, the parameter responsible for topological ordering, which would not otherwise be possible without impairing the topology of the map. The SOMs are compared with two newly developed methods that discretize SMs based on arbitrarily chosen and distribution‐based bins. We demonstrate the usefulness of both methods in climate model validation and show that both methods are able to capture circulation variability in its extremes in more detail than the SOMs. The distribution‐based method does not suffer from sample‐size issues and outperforms all other classifications in extracting ERA5 patterns leading to extreme temperature minima over central Europe. Our results suggest that classifications based on SM could be a viable alternative to SOMs when SOMs lack the ability to discriminate circulation outliers leading to temperature extremes.

A multiparametric calcium signal screening platform using iPSC-derived cortical neural spheroids.

Discovery of therapeutics for neurological diseases is hampered by the lack of predictive in vitro and in vivo models. Traditionally, in vitro assays rely on engineered cell lines grown two-dimensionally (2D) outside a physiological tissue context, which makes them very amenable for large scale drug screening but reduces their relevance to in vivo neurophysiology. In recent years, three-dimensional (3D) neural cell culture models derived from human induced pluripotent stem cells (iPSCs) have been developed as an in vitro assay platform to investigate brain development, neurological diseases, and for drug screening. iPSC-derived neural spheroids or organoids can be developed to include complex neuronal and glial cell populations and display spontaneous, synchronous activity, which is a hallmark of in vivo neural communication. In this report we present a proof-of-concept study evaluating 3D iPSC-derived cortical neural spheroids as a physiologically- and pharmacologically-relevant high-throughput screening (HTS) platform and investigate their potential for use for therapeutic development. To this end, a library of 687 neuroactive compounds were tested in a phenotypic screening paradigm which measured calcium activity as a functional biomarker for neural modulation through fluctuations in calcium fluorescence. Pharmacological responses of cortical neural spheroids were analyzed using a multi-parametric approach, whereby seven peak characteristics from the calcium activity in each well were quantified and incorporated into principal component analysis and Sammon mapping to measure compound response. Here, we describe the implementation of the 687-compound library screen and data analysis demonstrating that iPSC-derived cortical spheroids are a robust and information-rich assay platform for HTS.

Early fault identification for operating circuit breaker based on classifier model system

One of the most important switchgear in a substation is the circuit breaker (CB); it is used either in the transmission or distribution sections. Currently, the maintenance of a CB is done by capturing the trip time using a handheld device; the trip time is the time from trip initiation to the moment of current flow cessation in the load side of the CB. For the maintenance staff of the Iraqi National Power Board (INPB), their decision is mainly aimed to pinpoint the specific problem of the CB, the breaker parameters, such as latch, buffer, mcon, acon, and end which can be analysed using data mining methods such as K-means clustering and Sammon mapping (KCSM). The advantages of this approach include early identification of faults and saving more cost and time of repairing and replacing damaged CBs as the number of damaged CBs can be decreased. The problem with this method is the prolonged time of testing the conventional trip as it requires removing the CBs from service and planned outage. Furthermore, the CB may not capture the crucial information that causes slow tripping. Hence, the main objectives of this work are to analyse CB trip coil current data and study the effect and relationship between two different analytical approaches to analyse the data. The result of this technique showed excellent identification of the switch faults.

Historical Window-Enhanced Transfer Gaussian Process for Production Optimization

Summary As a crucial step of reservoir management, production optimization aims to make the optimal scheme for maximal economic benefit measured by net present value (NPV) according to reservoir states. Despite the remarkable success, more advanced methods that can get higher NPV with less time consumed are still in urgent need. One main reason for limiting the optimization performance of existing methods is that historical data cannot be fully used. For a practical reservoir, production optimization is generally implemented in multiple stages, and substantial historical data are accumulated. These hard-won data obtained with lots of time encapsulate beneficial optimization experience and in-depth knowledge of the reservoir. However, when encountered with an unsolved optimization task in new stages, most methods discard these historical data, optimize from scratch, and gradually regain the knowledge of the reservoir with massive time for “trial and error” to find the right optimization direction, which is time-consuming and affects their practical application. Motivated by this, a novel method named historical window-enhanced transfer Gaussian process (HWTGP) for production optimization is proposed in this paper. Each optimization stage is regarded as a time window, and the data in historical windows are adopted as a part of training data to construct the transfer Gaussian process (TGP), which guides the whole optimization process. To solve the high-dimensional feature of practical problems, the prescreening framework based on a dimension-reduction method named Sammon mapping is introduced. The main innovation of HWTGP is that like experienced engineers, it can extract beneficial reservoir knowledge from historical data and transfer it to the target production-optimization problem, avoiding massive time for “trial and error” and getting superior performance. Besides, HWTGP has a self-adaptive mechanism to avoid harmful and ineffective experience transfer when tasks in historical and current windows are unrelated. To verify the effectiveness of HWTGP, two reservoir models are tested 10 times independently and results are compared with those obtained by differential evolution (DE) and a surrogate-based method. Experimental results show that HWTGP can achieve the optimal well controls that can get the highest NPV, and has significantly enhanced convergence speed with excellent stability, proving the effectiveness of transferring historical data.

Immunoassay platform with surface-enhanced resonance Raman scattering for detecting trace levels of SARS-CoV-2 spike protein

The early diagnosis of Coronavirus disease (COVID-19) requires either an accurate detection of genetic material or a sensitive detection of viral proteins. In this work, we designed an immunoassay platform for detecting trace levels of SARS-CoV-2 spike (S) protein. It is based on surface-enhanced resonance Raman scattering (SERRS) of methylene blue (MB) adsorbed onto spherical gold nanoparticles (AuNPs) and coated with a 6 nm silica shell. The latter shell in the SERRS nanoprobe prevented aggregation and permitted functionalization with SARS-CoV-2 antibodies. Specificity of the immunoassay was achieved by combining this functionalization with antibody immobilization on the cover slides that served as the platform support. Different concentrations of SARS-CoV-2 antigen could be distinguished and the lack of influence of interferents was confirmed by treating SERRS data with the multidimensional projection technique Sammon's mapping. With SERRS using a laser line at 633 nm, the lowest concentration of spike protein detected was 10 pg/mL, achieving a limit of detection (LOD) of 0.046 ng/mL (0.60 pM). This value is comparable to the lowest concentrations in the plasma of COVID-19 patients at the onset of symptoms, thus indicating that the SERRS immunoassay platform may be employed for early diagnosis.

Sammon Quadratic Recurrent Multilayer Deep Classifier for Legal Document Analytics

In recent years, machine learning algorithms and in particular deep learning has shown promising results when used in the field of legal domain. The legal field is strongly affected by the problem of information overload, due to the large amount of legal material stored in textual form. Legal text processing is essential in the legal domain to analyze the texts of the court events to automatically predict smart decisions. With an increasing number of digitally available documents, legal text processing is essential to analyze documents which helps to automate various legal domain tasks. Legal document classification is a valuable tool in legal services for enhancing the quality and efficiency of legal document review. In this paper, we propose Sammon Keyword Mapping-based Quadratic Discriminant Recurrent Multilayer Perceptive Deep Neural Classifier (SKM-QDRMPDNC), a system that applies deep neural methods to the problem of legal document classification. The SKM-QDRMPDNC technique consists of many layers to perform the keyword extraction and classification. First, the set of legal documents are collected from the dataset. Then the keyword extraction is performed using Sammon Mapping technique based on the distance measure. With the extracted features, Quadratic Discriminant analysis is applied to perform the document classification based on the likelihood ratio test. Finally, the classified legal documents are obtained at the output layer. This process is repeated until minimum error is attained. The experimental assessment is carried out using various performance metrics such as accuracy, precision, recall, F-measure, and computational time based on several legal documents collected from the dataset. The observed results validated that the proposed SKM-QDRMPDNC technique provides improved performance in terms of achieving higher accuracy, precision, recall, and F-measure with minimum computation time when compared to existing methods.

On the Trail of Spatial Patterns of Genetic Variation

The accurate determination of the spatial trends on the variability of a species’ gene pool is essential to elucidate the underlying demographic-evolutionary events, thus helping to unravel the microevolutionary history of the population under study. Herein we present a new software called GenoCline, mainly addressed to detect genetic clines from allele, haplotype, and genome-wide data. This program package allows identifying the geographic orientation of clinal genetic variation through a system of iterative rotation of a virtual coordinate axis. Besides, GenoCline can perform complementary analyses to explore the potential origin of the genetic clines observed, including spatial autocorrelation, isolation by distance, centroid method, multidimensional scaling and Sammon projection. Among the advantages of this software is the ease in data entry and potential interconnection with other programs. Genetic and geographic data can be entered in spreadsheet table formatting (.xls), whereas genome-wide data can be imported in Eigensoft format. Genetic frequencies can also be exported in a format compatible with other programs dealing with population genetic and evolutionary biology analyses. All illustrations of results are saved in.svg format so that there will be high quality and easily editable vectorial graphs available for the researcher. Being implemented in Java, GenoCline is highly portable, thus working in different operating systems.

Sammon Projected Feature Selection Based Linear Support Vector Regression for Big Data Predictive Analytics

In big data analytics, classification is a key problem to be resolved for providing efficient prediction results. Recently, many research works have been designed for big data classification. However, accuracy was not increased with minimal time complexity when considering large dataset as input. In order to handle such issues, Sammon Projected Feature Selection based Linear Support Vector Regression (SPFS-LSVR) Method is introduced. The SPFS-LSVR method is developed to minimize the time and space complexity involved in the classification with better accuracy. At first, SPFS-LSVR method takes big dataset as input where it includes number of features and data for executing predictive analytics. Then theSammon Projection is employed in SPFS-LSVR methodfor performing the feature selection in high dimensional data. Sammon Projection helps in finding the relevant features by mapping the high-dimensional space to the lower-dimensionality space. This in turns, the time and space complexity occurred during the classification is reduced. After that, SPFS-LSVR method uses a Linear Support Vector Regression (LSVR) model for examining the selected features of input data with higher accuracy. The designed model uses hyperplane for producing the exact prediction result with higher accuracy. The LSVR model determines the relationship between independent data (i.e., features of input data) and the dependent data (i.e., prediction outcomes) with the help of Laplace kernel function. From that, the maximum relationship between the input features of data is classified into different classes. This helps in SPFS-LSVR method to enhance the performance of classification with maximum accuracy and minimal error rate. Through the efficient classification performance of big data, proposed SPFS-LSVR method improves the big data predictive analytics process as compared to state-of-the-art works. Experimental evaluation is carried out using big dataset on factors such as prediction time, prediction accuracy, false positive rate and space complexity with respect to number of data.

Classification of histopathological gastric images using a new method

The number of patients who die from stomach cancer is still very excessive. Early diagnosis of cancer patients is necessary to reduce the death rate. In this case, a molecular structure classification system can help carry out early diagnosis of cancer. The existing system has some problems. These problems are high cost, low accuracy rate and waste of time. To tackle this problem, this article presents a new method. This method consists of a new size reduction algorithm called as extending extract histogram of oriented gradients (EEHOG). A multimodality size reduction method is obtained by combining the new EEHOG method and other dimension reduction methods (ODRM). Other dimension reduction methods are multidimensional scaling (MDS), Sammon mapping, Isomap, local linear embedding (LLE), Laplacian eigenmaps, stochastic neighbor embedding (SNE) and t-distributed stochastic neighbor embedding (t-SNE). As well, extract histogram of oriented gradients (EHOG) features have been calculated in this article. Then, EEHOG + MDS, EEHOG + Sammon mapping, EEHOG + Isomap, EEHOG + LLE, EEHOG + Laplacian Eigenmaps, EEHOG + SNE and EEHOG + t-SNE methods have been used for the dimensional reduction of the EHOG features. Thus, the high dimension of these features has been reduced to lower dimensions with a multimodality size reduction method. These new nominal feature sizes have been given to multilayer perceptron neural networks (MLP) and random forest (RF) classifier entries for classification of the histopathological stomach images. The accuracy results established by using the EEHOG + ODRM size reduction method are higher than the accuracy results obtained by using only ODRM. The accuracy result obtained with the MLP classifier is found to be higher from the accuracy results obtained with the RF classifier, when the performance of the MLP classifier is compared with the performance of the RF classifier. The stomach cancer images used this article were obtained from Firat University Medical Faculty Pathology Department. It has been found that the highest accuracy results are obtained as 98.14% with EHOG_EEHOG + LLE_MLP method. The average of the accuracy results obtained with the MLP classifier has been found as 89.57%. However, the average of the accuracy results obtained with the RF classifier has been found as 84.49%. These results have been compared with previous studies. It has been proven that more high accuracy results than single solutions of the multimodality solutions are given.

Co-Cultivation of Fusarium, Alternaria, and Pseudomonas on Wheat-Ears Affects Microbial Growth and Mycotoxin Production.

Mycotoxigenic fungal pathogens Fusarium and Alternaria are a leading cause of loss in cereal production. On wheat-ears, they are confronted by bacterial antagonists such as pseudomonads. Studies on these groups’ interactions often neglect the infection process’s temporal aspects and the associated priority effects. In the present study, the focus was on how the first colonizer affects the subsequent ones. In a climate chamber experiment, wheat-ears were successively inoculated with two different strains (Alternaria tenuissima At625, Fusarium graminearum Fg23, or Pseudomonas simiae Ps9). Over three weeks, microbial abundances and mycotoxin concentrations were analyzed and visualized via Self Organizing Maps with Sammon Mapping (SOM-SM). All three strains revealed different characteristics and strategies to deal with co-inoculation: Fg23, as the first colonizer, suppressed the establishment of At625 and Ps9. Nevertheless, primary inoculation of At625 reduced all of the Fusarium toxins and stopped Ps9 from establishing. Ps9 showed priority effects in delaying and blocking the production of the fungal mycotoxins. The SOM-SM analysis visualized the competitive strengths: Fg23 ranked first, At625 second, Ps9 third. Our findings of species-specific priority effects in a natural environment and the role of the mycotoxins involved are relevant for developing biocontrol strategies.

Sammon's mapping regression for the quantitative analysis of glucose from both mid infrared and near infrared spectra.

This paper proposes a novel regression method based on Sammon's mapping dimensionality reduction technique for the quantification of glucose from both near infrared and mid infrared spectra. The proposed regression model was validated to determine the concentration of glucose from the spectra of aqueous mixtures consisting of human serum albumin and glucose in phosphate buffer solution from both near infrared (NIR) and mid infrared (MIR) regions. The performance of the proposed prediction model has been analysed with traditional regression methods principal component regression (PCR) and partial least squares regression (PLSR) models. The results indicate that the proposed model yields improved prediction performance compared to PCR and PLSR methods. In detail, the proposed Sammon's mapping regression (SMR) model provides better prediction ability by reducing the root mean square error of prediction (RMSEP) from 35.74 mg dL-1 for PCR and 31.39 mg dL-1 for PLSR to 21.89 mg dL-1 for the proposed regression model in the MIR region and the RMSEP has been reduced from 38.15 mg dL-1 for the PCR model and 37.5 mg dL-1 for the PLSR model to 29.74 mg dL-1 for the SMR model in the NIR region.

A Decision-Making Tool Based on Exploratory Visualization for the Automotive Industry

In recent years, the digital transformation has been advancing in industrial companies, supported by the Key Enabling Technologies (Big Data, IoT, etc.) of Industry 4.0. As a consequence, companies have large volumes of data and information that must be analyzed to give them competitive advantages. This is of the utmost importance in fields such as Failure Detection (FD) and Predictive Maintenance (PdM). Finding patterns in such data is not easy, but cutting-edge technologies, such as Machine Learning (ML), can make great contributions. As a solution, this study extends Hybrid Unsupervised Exploratory Plots (HUEPs), as a visualization technique that combines Exploratory Projection Pursuit (EPP) and Clustering methods. An extended formulation of HUEPs is proposed, adding for the first time the following EPP methods: Classical Multidimensional Scaling, Sammon Mapping and Factor Analysis. Extended HUEPs are validated in a case study associated with a multinational company in the automotive industry sector. Two real-life datasets containing data gathered from a Waterjet Cutting tool are visualized in an intuitive and informative way. The obtained results show that HUEPs is a technique that supports the continuous monitoring of machines in order to anticipate failures. This contribution to visual data analytics can help companies in decision-making, regarding FD and PdM projects.