Preprocessing Strategies Research Articles

Stain Color Adaptive Normalization (SCAN) algorithm: Separation and standardization of histological stains in digital pathology

Background and objectiveThe diagnosis of histopathological images is based on the visual analysis of tissue slices under a light microscope. However, the histological tissue appearance may assume different color intensities depending on the staining process, operator ability and scanner specifications. This stain variability affects the diagnosis of the pathologist and decreases the accuracy of computer-aided diagnosis systems. In this context, the stain normalization process has proved to be a powerful tool to cope with this issue, allowing to standardize the stain color appearance of a source image respect to a reference image. MethodsIn this paper, novel fully automated stain separation and normalization approaches for hematoxylin and eosin stained histological slides are presented. The proposed algorithm, named SCAN (Stain Color Adaptive Normalization), is based on segmentation and clustering strategies for cellular structures detection. The SCAN algorithm is able to improve the contrast between histological tissue and background and preserve local structures without changing the color of the lumen and the background. ResultsBoth stain separation and normalization techniques were qualitatively and quantitively validated on a multi-tissue and multiscale dataset, with highly satisfactory results, outperforming the state-of-the-art approaches. SCAN was also tested on whole-slide images with high performances and low computational times. ConclusionsThe potential contribution of the proposed standardization approach is twofold: the improvement of visual diagnosis in digital histopathology and the development of powerful pre-processing strategies to automated classification techniques for cancer detection.

Missing Air Pollution Data Recovery Based on Long-Short Term Context Encoder

Air pollution has become a global challenge, and obtaining real-time air quality information is urgently needed. Although the governments have been trying their best in delivering accurate air quality reports, missing air pollution data remains a key challenge. Based on the temporal-spatial correlation of the data, we propose a novel long-short term context encoder (LSCE) structure for recovering missing air pollution data. The original context encoder approach based on image completion focuses on reconstructing rectangular missing regions. Differing from traditional methods, our fully convolutional neural network architecture enjoys the following novelties. First, LSCE can recover irregular missing data patterns. Second, we devise two data pre-processing strategies to produce two types of context encoders, namely, the long-short term cutting context encoder (LSCCE) and the long-short term sliding context encoder (LSSCE). Compared with LSCCE, LSSCE increases the number of training data matrixes. Finally, we investigate the significance of adaptive training in addressing different types of missing data. Our simulation results have demonstrated that our approach, especially, LSSCE, can outperform existing missing data recovery methods. Besides, our techniques can be widely applicable for recovering other temporally and spatially correlated missing data, such as vehicular traffic or meteorology data.

Multidocument Arabic Text Summarization Based on Clustering and Word2Vec to Reduce Redundancy

Arabic is one of the most semantically and syntactically complex languages in the world. A key challenging issue in text mining is text summarization, so we propose an unsupervised score-based method which combines the vector space model, continuous bag of words (CBOW), clustering, and a statistically-based method. The problems with multidocument text summarization are the noisy data, redundancy, diminished readability, and sentence incoherency. In this study, we adopt a preprocessing strategy to solve the noise problem and use the word2vec model for two purposes, first, to map the words to fixed-length vectors and, second, to obtain the semantic relationship between each vector based on the dimensions. Similarly, we use a k-means algorithm for two purposes: (1) Selecting the distinctive documents and tokenizing these documents to sentences, and (2) using another iteration of the k-means algorithm to select the key sentences based on the similarity metric to overcome the redundancy problem and generate the initial summary. Lastly, we use weighted principal component analysis (W-PCA) to map the sentences’ encoded weights based on a list of features. This selects the highest set of weights, which relates to important sentences for solving incoherency and readability problems. We adopted Recall-Oriented Understudy for Gisting Evaluation (ROUGE) as an evaluation measure to examine our proposed technique and compare it with state-of-the-art methods. Finally, an experiment on the Essex Arabic Summaries Corpus (EASC) using the ROUGE-1 and ROUGE-2 metrics showed promising results in comparison with existing methods.

A Standardized Project Gutenberg Corpus for Statistical Analysis of Natural Language and Quantitative Linguistics.

The use of Project Gutenberg (PG) as a text corpus has been extremely popular in statistical analysis of language for more than 25 years. However, in contrast to other major linguistic datasets of similar importance, no consensual full version of PG exists to date. In fact, most PG studies so far either consider only a small number of manually selected books, leading to potential biased subsets, or employ vastly different pre-processing strategies (often specified in insufficient details), raising concerns regarding the reproducibility of published results. In order to address these shortcomings, here we present the Standardized Project Gutenberg Corpus (SPGC), an open science approach to a curated version of the complete PG data containing more than 50,000 books and more than word-tokens. Using different sources of annotated metadata, we not only provide a broad characterization of the content of PG, but also show different examples highlighting the potential of SPGC for investigating language variability across time, subjects, and authors. We publish our methodology in detail, the code to download and process the data, as well as the obtained corpus itself on three different levels of granularity (raw text, timeseries of word tokens, and counts of words). In this way, we provide a reproducible, pre-processed, full-size version of Project Gutenberg as a new scientific resource for corpus linguistics, natural language processing, and information retrieval.

A Novel CNN-GRU-Based Hybrid Approach for Short-Term Residential Load Forecasting

Electric energy forecasting domain attracts researchers due to its key role in saving energy resources, where mainstream existing models are based on Gradient Boosting Regression (GBR), Artificial Neural Networks (ANNs), Extreme Learning Machine (ELM) and Support Vector Machine (SVM). These models encounter high-level of non-linearity between input data and output predictions and limited adoptability in real-world scenarios. Meanwhile, energy forecasting domain demands more robustness, higher prediction accuracy and generalization ability for real-world implementation. In this paper, we achieve the mentioned tasks by developing a hybrid sequential learning-based energy forecasting model that employs Convolution Neural Network (CNN) and Gated Recurrent Units (GRU) into a unified framework for accurate energy consumption prediction. The proposed framework has two major phases: (1) data refinement and (2) training, where the data refinement phase applies preprocessing strategies over raw data. In the training phase, CNN features are extracted from input dataset and fed in to GRU, that is selected as optimal and observed to have enhanced sequence learning abilities after extensive experiments. The proposed model is an effective alternative to the previous hybrid models in terms of computational complexity as well prediction accuracy, due to the representative features' extraction potentials of CNNs and effectual gated structure of multi-layered GRU. The experimental evaluation over existing energy forecasting datasets reveal the better performance of our method in terms of preciseness and efficiency. The proposed method achieved the smallest error rate on Appliances Energy Prediction (AEP) and Individual Household Electric Power Consumption (IHEPC) datasets, when compared to other baseline models.

Strength Check of Aircraft Parts Based on Multi-GPU Clusters for Fast Calculation of Sparse Linear Equations

In order to improve the cost-effectiveness ratio, the next-generation vehicle needs to meet the requirements of reuse, while adopting a lighter structural weight, so it is necessary to realize the strength calculation and condition monitoring of key components in the digital twin. Most of the current monitoring methods are based on the characteristics of various data acquisition systems, but they need the support of a large number of flight data. The disadvantages of the above strategy can be avoided by reducing the structure of aircraft components to a finite element model and quickly checking the key components in the health management system. In order to solve the problem of fast calculation of the finite element model of the key components of the aircraft, a parallel algorithm and framework of large-scale sparse matrix preprocessing conjugate gradient method based on CUDA(Compute Unified Device Architecture) technology is proposed in the multi GPU(Graphics Processing Unit) workstation cluster environment. Once the sparse matrix is too large to be processed in a single workstation, this paper discusses how to realize the optimized data segmentation in the distributed multi-GPU computing environment. For the problem of iterative solution of matrix preprocessing, two preprocessing strategies of matrix bandwidth reduction parallelization and incomplete Cholesky decomposition are proposed, and asynchronous task concurrency and load balancing strategies are designed on the architecture. The calculation of some examples in the standard sparse matrix database shows that the algorithm and architecture proposed in this paper have the ability to solve large-scale sparse matrix quickly and efficiently, and can complete the fast strength verification of vehicle components.

Exploration and Performance Assessment of Efficient Histopathology Image Pre-Processing and Segmentation Techniques for Breast Cancer Prediction

Evaluation of features after segmentation is a significant process in image processing, especially in the medical field. Medical imaging technologies are widely utilized in clinical diagnosis to guide therapeutic and surgical decisions and to monitor disease advancement, understanding occurrence and re-occurrence of infection and view treatment response. Among all cancer kinds, Breast Cancer (BC) now-a-days has turn out to be a common form of cancer amongst ladies around the world and is the second common cause of most cancers deaths. At present, there aren't any powerful methods to save you and remedy breast cancer, because its cause is not absolutely known. Early detection is the most effective way to enhance breast cancer survivals and might deliver a better hazard of full healing. The main motive of this paper is to implement various efficient image segmentation techniques after preprocessing histopathology BC images of different magnification level and exhaustively compare them to achieve best results. We analyze the outcomes of widely used edge detection based image segmentation methods such as Adaptive K-Means, Multi Class Fuzzy C-Means, Canny, Gabor filter and Homogeneity based PSO and evaluate them via metrics which includes accuracy, precision, recall and F-degree. Various preprocessing strategies like histogram equalization (HE), Adaptive equalization (AE) and Contrast Stretching (CS) are compared and used to enhance the performance of above segmentation methods. Contrast Improvement Index (CII) is chosen as a selection criteria for preprocessed image. Finally one vs. all multiclass SVM classifier is used for BC image classification. Our implementation uses breast cancer dataset having two classes as benign and malignant each in turn having four sub-classes. Images of different magnification levels such as 40x, 100x, 200x and 400x, are considered for BC detection.

Predicting the occurrence of surgical site infections using text mining and machine learning.

In this study we propose the use of text mining and machine learning methods to predict and detect Surgical Site Infections (SSIs) using textual descriptions of surgeries and post-operative patients’ records, mined from the database of a high complexity University hospital. SSIs are among the most common adverse events experienced by hospitalized patients; preventing such events is fundamental to ensure patients’ safety. Knowledge on SSI occurrence rates may also be useful in preventing future episodes. We analyzed 15,479 surgery descriptions and post-operative records testing different preprocessing strategies and the following machine learning algorithms: Linear SVC, Logistic Regression, Multinomial Naive Bayes, Nearest Centroid, Random Forest, Stochastic Gradient Descent, and Support Vector Classification (SVC). For prediction purposes, the best result was obtained using the Stochastic Gradient Descent method (79.7% ROC-AUC); for detection, Logistic Regression yielded the best performance (80.6% ROC-AUC).

On Low-Complexity Lattice Reduction Algorithms for Large-Scale MIMO Detection: The Blessing of Sequential Reduction

Lattice reduction is a popular preprocessing strategy in multiple-input multiple-output (MIMO) detection. In a quest for developing a low-complexity reduction algorithm for large-scale problems, this paper investigates a new framework called sequential reduction (SR), which aims to reduce the lengths of all basis vectors. The performance upper bounds of the strongest reduction in SR are given when the lattice dimension is no larger than 4. The proposed new framework enables the implementation of a hash-based low-complexity lattice reduction algorithm, which becomes especially tempting when applied to large-scale MIMO detection. Simulation results show that, compared to other reduction algorithms, the hash-based SR algorithm exhibits the lowest complexity while maintaining comparable error performance.

Global Optimization of Offshore Wind Farm Collection Systems

A mathematical program for global optimization of the cable layout of Offshore Wind Farms (OWFs) is presented. The model consists on a Mixed Integer Linear Program (MILP). Modern branch-and-cut solvers are able to solve large-scale instances, defined by more than hundred Wind Turbines (WTs), and a reasonable number of Offshore Substations (OSSs). In addition to the MILP model to optimize total cable length or initial investment, a pre-processing strategy is proposed in order to incorporate total electrical power losses into the objective function. High fidelity models are adapted to calculate cables current capacities, spatial currents. The MILP model is embedded in an iterative algorithmic framework, solving a sequence of problems with increasing search space size. The search space is defined as a set of underlying candidate arcs. The applicability of the method is illustrated through 10 case studies of real-world large-scale wind farms. Results show that: (i) feasible points are obtained in seconds, (ii) points with an imposed maximum tolerance near the global optimum are calculated in a reasonable computational time in the order of hours, and (iii) the proposed method compares favorably against state-of-the-art method available in literature.

Comparing convolutional neural networks and preprocessing techniques for HEp-2 cell classification in immunofluorescence images

Autoimmune diseases are the third highest cause of mortality in the world, and the identification of an anti-nuclear antibody via an immunofluorescence test for HEp-2 cells is a standard procedure to support diagnosis. In this work, we assess the performance of six preprocessing strategies and five state-of-the-art convolutional neural network architectures for the classification of HEp-2 cells. We also evaluate enhancement methods such as hyperparameter optimization, data augmentation, and fine-tuning training strategies. All experiments were validated using a five-fold cross-validation procedure over the training and test sets. In terms of accuracy, the best result was achieved by training the Inception-V3 model from scratch, without preprocessing and using data augmentation (98.28%). The results suggest the conclusions that most CNNs perform better on non-preprocessed images when trained from scratch on the analyzed dataset, and that data augmentation can improve the results from all models. Although fine-tuning training did not improve the accuracy compared to training the CNNs from scratch, it successfully reduced the training time.

Different preprocessing strategies lead to different conclusions: A [11C]DASB-PET reproducibility study

Positron emission tomography (PET) neuroimaging provides unique possibilities to study biological processes in vivo under basal and interventional conditions. For quantification of PET data, researchers commonly apply different arrays of sequential data analytic methods (“preprocessing pipeline”), but it is often unknown how the choice of preprocessing affects the final outcome. Here, we use an available data set from a double-blind, randomized, placebo-controlled [11C]DASB-PET study as a case to evaluate how the choice of preprocessing affects the outcome of the study. We tested the impact of 384 commonly used preprocessing strategies on a previously reported positive association between the change from baseline in neocortical serotonin transporter binding determined with [11C]DASB-PET, and change in depressive symptoms, following a pharmacological sex hormone manipulation intervention in 30 women. The two preprocessing steps that were most critical for the outcome were motion correction and kinetic modeling of the dynamic PET data. We found that 36% of the applied preprocessing strategies replicated the originally reported finding (p < 0.05). For preprocessing strategies with motion correction, the replication percentage was 72%, whereas it was 0% for strategies without motion correction. In conclusion, the choice of preprocessing strategy can have a major impact on a study outcome.

Unsupervised Manifold Alignment for Cross-Domain Classification of Remote Sensing Images

The original manifold alignment (MA) approach is for semisupervised domain adaptation. Since the target prior information is difficult to obtain, we conduct it in an unsupervised manner, resulting in an unsupervised MA (UMA) method. This approach utilizes the probabilistic prediction results of target data to construct the cross-domain similarity matrix, which characterizes the relationships between domains and is used for alignment. Due to the spectral drift, the prediction results may not be accurate, and thus affect the alignment. We employed spatial filtering and overall centroid alignment method as two preprocessing strategies to improve the prediction results. Furthermore, per-class maximum mean discrepancy (MMD) constraint is introduced to the UMA to further improve the alignment performance. The proposed UMA_MMD algorithm is applied for the classification of remote sensing images, and the experimental results using hyperion multitemporal remote sensing images demonstrated the effectiveness of the proposed approach.

Automated Brain Tumor Detection in MRI Images Using Efficient Deep Learning Methods

Brain tumor is an unusual intensification of cells inside the skull. The brain MRI scanned images is segmented to extract brain tumor to analyze type and depth of tumor. In order to reduce the time consumption of brain tumor extraction, an automatic method for detection of brain tumor is highly recommended. Deep machine learning methods are used for automatic detection of the brain tumor in soft tissues at an early stage which involves the following stages namely: image pre-processing, clustering and optimization. This paper addresses previously adduced pre-processing (Skull stripping, Contrast stretching, clustering (k-Means, Fuzzy c-means) and optimization (Cuckoo search optimization, Artificial Bee Colony optimization) strategies for abnormal brain tumor detection from MRI brain images. Performance evaluation is done based on computational time of clustering output and optimization algorithms are analyzed in terms of sensitivity, specificity, and accuracy.

Pre-processing nonlinear output regulation with non-vanishing measurements

The paper deals with the output regulation problem of linear and nonlinear systems in the presence of measurements that, besides the regulation error, might include also extra outputs non-vanishing in steady state. We first show that, for linear systems, any “pre-processing” internal model-based solution solving the problem in a robust way necessarily relies on a stabilizer blocking the steady state effect of the extra measurements through properly located zeros. Motivated by this, a nonlinear pre-processing design strategy, relying on a “washout filter” processing the non-vanishing measurements and generating a new output having zero steady state, is presented for nonlinear systems in a semiglobal setting. A new nonlinear non-resonance condition, underlying the stabilizability by output feedback of the cascade of the plant and the filter, is introduced.

Hyperspectral Endmember Extraction Using Spatially Weighted Simplex Strategy

Spatial information is increasingly becoming a vital factor in the field of hyperspectral endmember extraction, since it takes into consideration the spatial correlation of pixels, which generally involves jointing spectral information for preprocessing and/or endmember extraction in hyperspectral imagery (HSI). Generally, simplex-based endmember extraction algorithms (EEAs) identify endmembers without considering spatial attributes, and the spatial preprocessing strategy is an independently executed module that can provide spatial information for the endmember search process. Despite this interest, to the best of our knowledge, no one has studied the integration framework of the spatial information-embedded simplex for hyperspectral endmember extraction. In this paper, we propose a spatially weighted simplex strategy, called SWSS, for hyperspectral endmember extraction that investigates a novel integration framework of the spatial information-embedded simplex for identifying endmember. Specifically, the SWSS generates the spatial weight scalar of each pixel by determining its corresponding spatial neighborhood correlations for weighting itself within the simplex framework to regularize the selection of the endmembers. The SWSS could be implemented in the traditional simplex-based EEAs, such as vertex component analysis (VCA), to introduce spatial information into the data simplex framework without the computational complexity excessively increasing or endmember extraction accuracy loss. Based on spectral angle distance (SAD) and root-mean-square-error (RMSE) evaluation criteria, experimental results on both synthetic and C u p r i t e real hyperspectral datasets indicate that the simplex-based EEA re-implemented by the SWSS has a significant improvement on endmember extraction performance over the techniques on their own and without re-implementing.

Comparison of Pre-Processing and Variable Selection Strategies in Group-Based GC×GC-TOFMS Analysis

Chemometric analysis of comprehensive two-dimensional chromatography coupled to time-of-flight mass spectrometry (GC×GC-TOFMS) data has been reported with various workflows, yet little effort has been devoted to evaluating the impacts of workflow variation on study conclusions. The report presented herein aims to investigate the effects of different pre-processing and variable selection strategies on the scores’ plot outputs from GC×GC-TOFMS data acquired from lavender and tea tree essential oils. Our results suggest that pre-processing, such as applying log transformation to the data set, can result in significant differentiation of sample clustering when compared to only mean centering. Additionally, exploring differences between analysis of variance, Fisher-ratio, and partial least squares-discriminant analysis feature selection resulted in little variation in scores plots. This work highlights the effects different chemometric workflows can have on results to help facilitate harmonization efforts.

Subpixel Component Analysis for Hyperspectral Image Classification

Land-cover classification with hyperspectral imagery has been an active topic in the remote sensing community. It aims at relating a unique class label to each pixel in the scene, so that it can be well defined by a given land cover type. In this paper, we explore the intrinsic characteristics of hyperspectral imagery from a subpixel-level perspective and propose a new subpixel component analysis (SCA) approach for feature extraction and land-cover classification. The core idea of SCA is that we extract a subpixel attribute component feature from the abundance maps. Compared with the abundance maps, the extracted subpixel feature image shows higher signal-to-noise level and clearer spatial distribution details. In order to deal with spectral variability, as well as obtain representative image endmember signatures and their corresponding abundance maps, we adopt a regional clustering-based spatial preprocessing (RCSPP) strategy for endmember identification, and a partial unmixing model based on mixture tuned matched filtering (MTMF) for abundance estimation. Furthermore, to highlight the spatial distribution details as well as eliminate the noise disturbance in the derived abundance maps, we perform sparse image decomposition on the obtained abundance maps, thus achieving a new subpixel feature representation for classification. Our experimental results reveal that the proposed SCA approach can obtain feature representation with explicit physical meaning, clear spatial distribution details, and better noise robustness, leading to state-of-the-art classification results.

Enhancement of fraternal K-median algorithm with CNN for high dropout probabilities to evolve optimal time-complexity

Machine learning era began to rule almost all the technologies, which influences the improvement of the performance due to its intelligent computing methodologies. Especially the Deep Learning algorithm plays a vital role in computing a human-like decision, which is considered to be the superior breakthrough technology of the century. Deep Learning algorithms generate a massive sum of features which is stacked and learned by many other neurons of the network in the term of links. Links initiated from the input and ends in the output of the network connecting many neurons on its path. The significant limitation of this network is its thirst towards the high computation power. This paper represents a methodology to make the system consume less computation requirement during its training or testing phase. In this process, an effective clustering algorithm (fraternal K-median clustering) is used as the preprocessing strategies, and as the second phase the dropout regularization procedure is implemented (in the Convolutional Neural Network, a type of Deep Learning algorithm) to eliminate most of the insignificant data. The dropout strategies used in the process helps in the improvement of accuracy by making the network overfit the decision of CNN, obtaining state-of-the-art results.

Classification of Under-Resourced Language Documents Using English Ontology

Automatic documents classification is an important task due to the rapid growth of the number of electronic documents, which aims automatically assign the document to a predefined category based on its contents. The use of automatic document classification has been plays an important role in information extraction, summarization, text retrieval, question answering, e-mail spam detection, web page content filtering, automatic message routing , etc.Most existing methods and techniques in the field of document classification are keyword based, but due to lack of semantic consideration of this technique, it incurs low performance. In contrast, documents also be classified by taking their semantics using ontology as a knowledge base for classification; however, it is very challenging of building ontology with under-resourced language. Hence, this approach is only limited to resourced language (i.e. English) support. As a result, under-resourced language written documents are not benefited such ontology based classification approach. This paper describes the design of automatic document classification of under-resourced language written documents. In this work, we propose an approach that performs classification of under-resourced language written documents on top of English ontology. We used a bilingual dictionary with Part of Speech feature for word-by-word text translation to enable the classification of document without any language barrier. The design has a concept-mapping component, which uses lexical and semantic features to map the translated sense along the ontology concepts. Beside this, the design also has a categorization component, which determines a category of a given document based on weight of mapped concept. To evaluate the performance of the proposed approach 20-test documents for Amharic and Tigrinya and 15-test document for Afaan Oromo in each news category used. In order to observe the effect of incorporated features (i.e. lemma based index term selection, pre-processing strategies during concept mapping, lexical and semantics based concept mapping) five experimental techniques conducted. The experimental result indicated that the proposed approach with incorporation of all features and components achieved an average F-measure of 92.37%, 86.07% and 88.12% for Amharic, Afaan Oromo and Tigrinya documents respectively. Keywords : under-resourced language, Multilingual, Documents or text Classification , knowledge base, Ontology based text categorization, multilingual text classification, Ontology. DOI : 10.7176/CEIS/10-6-02 Publication date :July 31 st 2019