Dimensionality Of Information Research Articles

Manifold-based sparse representation for opinion mining

What the consumer thinks about an organization's products, services, and events is a crucial performance indicator for businesses. The brief opinion pieces were quickly published on websites and social media platforms and have been analyzed by machine learning methods. The classical text feature representation methods suffer from high dimensionality, sparsity, noisy, irrelevant and redundant information. This paper focuses on how to enhance feature representation for opinion mining. Some nonlinear feature selection methods based on manifold assumption have been exploited to resolve these problems. The inherent manifold configuration was commonly ascertained through a nearest neighbor graph, whereby the neighbors in the current techniques may exhibit diverse polarities. To alleviate this burden, it is proposed to exploit both manifold assumption and sparse property as prior knowledge for opinion representation to learn intrinsic structure from data. First, the graph representation of user reviews based on the mentioned prior knowledge is learned. Then, the spectral properties of the learned graph are exploited to present data in a new feature space. The proposed algorithm is applied to four various common input features on two benchmark datasets, the Internet Movie Database (IMDB) and the Amazon review dataset. Our experiments reveal that the proposed algorithm yields considerable enhancements in terms of F-measure, accuracy, and other standard performance measures compared to the combination of state-of-the-art features with various classifiers. The highest classification accuracies of 99.15 and 91.97 are obtained in the proposed method on IMDB and Amazon using a linear SVM classifier, respectively. The impact of the parameters of the proposed algorithm is also investigated in this paper. The incorporation of a sparse manifold-based representation has led to noteworthy advancements beyond the baseline, and this success serves to validate the underlying assumptions.

Investigation on Intelligent Early Warning of Rock Burst Disasters Using the PCA-PSO-ELM Model

In order to conduct an intelligent early warning assessment of stope rock burst disasters in mining areas, and effectively prevent and control them, the principal component analysis (PCA) method was embraced to perform dimensionality reduction and feature information extraction from 10 main factors that affect the occurrence of rock bursts. On this basis, six principal component elements of the influencing factors of rock bursts have been obtained as the input vectors for an extreme learning machine (ELM). In the meantime, the parameter optimization ability of the PSO algorithm was adopted, the input weight values of the ELM and the threshold values of the hidden layer were optimized, and the functions of the three models were completely combined. Therefore, an early warning model of rock bursts based on the PCA-PSO-ELM combined algorithm was creatively proposed and the risk rank of rock bursts in the Yanshitai Coal Mine was predicted and evaluated. Consequently, the research results indicated that the prediction accuracy of the PCA-PSO-ELM model improved the prediction performance and generalization ability and reached a 100% contrast with the three models, namely the BP neural network, the radial basis function, and the extreme learning machine, which presented an updated method for the early warning investigation of rock burst disasters and had favorable engineering significance.

Complexity analysis of VMAT prostate plans: insights from dimensionality reduction and information theory techniques

Abstract Introduction: Volumetric Modulated Arc Therapy (VMAT) is a state-of-the-art prostate cancer treatment, defined by high dose gradients around targets. Its unique dose shaping incurs hidden complexity, impacting treatment deliverability, carcinogenesis, and machine strain. This study compares various aperture-based VMAT complexity indices in prostate cases using principal component and mutual information analyses. It suggests essential properties for an ideal complexity index from an information-theoretic viewpoint. Material and methods: The following ten complexity indices were calculated in 217 VMAT prostate plans: circumference over area (CoA), edge metric (EM), equivalent square field (ESF), leaf travel (LT), leaf travel modulation complexity score for VMAT (LTMCSV), mean-field area (MFA), modulation complexity score (standard MCS and VMAT variant MCSV), plan irregularity (PI), and small aperture score (SAS5mm). Principal component analysis (PCA) was applied to explore the correlations between the metrics. The differential entropy of all metrics was also calculated, along with the mutual information for all 45 metric pairs. Results: Whole-pelvis plans had greater complexity across all indices. The first three principal components explained 96.2% of the total variance. The complexity metrics formed three groups with similar conceptual characteristics, particularly ESF, LT, MFA, PI, and EM, SAS5mm. The differential entropy varied across the complexity metrics (PI having the smallest vs. EM the largest). Mutual information analysis (MIA) confirmed some metrics’ interdependence, although other pairs, such as LTMCSV/SAS5mm, LT/MCSV, and EM/SAS5mm, were found to share minimal MI. Conclusions: There are many complexity indices for VMAT described in the literature. PCA and MIA analyses can uncover significant overlap among them. However, this is not entirely reducible through dimensionality reduction techniques, suggesting that there also exists some reciprocity. When designing predictive models of quality assurance metrics, PCA and MIA may prove useful for feature engineering.

A novel multi-level data fusion and anomaly detection approach for infrastructure damage identification and localisation

In this paper, a new damage identification and localisation framework utilising multi-level data fusion and anomaly detection techniques is introduced. The performance of the framework is presented via case studies of a simply supported bridge and a continuous bridge, whose data were numerically generated through a surrogate model. Accelerations, deflections and bending moments obtained at multiple sensor locations when the bridge was subjected to a moving vehicle were used as the input. A damage-sensitive feature was established via coupling principal component analysis and Mahalanobis distance, allowing for initial data dimensionality reduction and information integration. Anomaly detection using a deep convolutional autoencoder was performed to identify the presence of single and multiple damages on the bridge. It is demonstrated that the proposed approach is independent of the mass and speed of moving vehicles, and is applicable to different types of bridges (i.e. simply supported bridge and continuous bridge) with only minor modifications to the data augmentation/preparation processes. The accuracy of damage identification for the simply supported bridge is shown to be consistently greater than 93%, even for extremely small damage severity (e.g. 1% reduction in local stiffness), and multiple damages. While the damage identification accuracy for the continuous bridge is greater than 94.9% for the majority of the tested cases. The proposed damage localisation approach can accurately determine damage location(s) for both single and multiple damage cases. It is shown how the proposed framework can be adopted for early damage detection to enable reliable decision-making and maximise structural safety.

Designing a Fuzzy Adaptive Neural Network Leveraging a Feature Self-Enhancement Unit and Statistical Selection Methods

In this study, we propose an advanced category of a fuzzy adaptive neural network (FANN) based on a feature self-enhancement unit (FSU) and statistical selection methods (SSMs). Undoubtedly, the raw data contain a large amount of information with varying importance. One of the most important tasks for regression model design is to avoid losing these important details. However, the raw data cannot participate in the whole training process due to the data fuzzification unit in the structure of conventional fuzzy neural networks (FNNs). Meanwhile, the polynomial-based neuron also has its limitations as a common node in FNNs. For example, in the polynomial neuron, the complexity of the neurons increases exponentially with the increase in network size. Consequently, overfitting and insufficient raw data information are two primary drawbacks in the structure of conventional FNNs. To address these limitations, we designed the FSU and the SSM as effective vehicles to reduce data dimensionality and select significant raw information. The proposed FANN also demonstrates the capability to improve modeling accuracy in neural networks. Moreover, this is the first instance of integrating statistical methods and feature self-enhancement techniques into a fuzzy model. To validate and showcase the superiority of the proposed FANN, the model is applied to 16 machine learning datasets, outperforming other comparative models in 81.25% of the datasets utilized. Additionally, the proposed FANN model outperformed the latest FNN models, achieving an average 5.1% increase in modeling accuracy. The comparison experiment section not only includes classical machine learning models but also references the experimental results from two recent related studies.

A Novel Hyperspectral Image Classification Model Using Bole Convolution With Three-Direction Attention Mechanism: Small Sample and Unbalanced Learning

Currently, the use of rich spectral and spatial information of hyperspectral images (HSIs) to classify ground objects is a research hotspot. However, the classification ability of existing models is significantly affected by its high data dimensionality and massive information redundancy. Therefore, we focus on the elimination of redundant information and the mining of promising features and propose a novel Bole convolution (BC) neural network with a tandem three-direction attention (TDA) mechanism (BTA-Net) for the classification of HSI. A new BC is proposed for the first time in this algorithm, whose core idea is to enhance effective features and eliminate redundant features through feature punishment and reward strategies. Considering that traditional attention mechanisms often assign weights in a one-direction manner, leading to a loss of the relationship between the spectra, a novel three-direction (horizontal, vertical, and spatial directions) attention mechanism is proposed, and an addition strategy and a maximization strategy are used to jointly assign weights to improve the context sensitivity of spatial–spectral features. In addition, we also designed a tandem TDA mechanism module and combined it with a multiscale BC output to improve classification accuracy and stability even when training samples are small and unbalanced. We conducted scene classification experiments on four commonly used hyperspectral datasets to demonstrate the superiority of the proposed model. The proposed algorithm achieves competitive performance on small samples and unbalanced data, according to the results of comparison and ablation experiments. The source code for BTA-Net can be found at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/vivitsai/BTA-Net</uri> .

A CNN-LSTM-PSO tool wear prediction method based on multi-channel feature fusion

In order to achieve predictive maintenance of CNC machining tools and to be able to change tools intelligently before tool wear is at a critical threshold, a CNN-LSTM tool wear prediction model based on particle swarm algorithm (PSO) optimization with multi-channel feature fusion is proposed. Firstly, the raw signals of seven channels of the machining process are collected using sensor technology and processed for noise reduction; secondly, the time-domain, frequency-domain and time-frequency-domain features of each channel signal are extracted, and a sample data set of spatio-temporal correlation of traffic flow is constructed by dimensionality reduction processing and information fusion of the above features; finally, the data set is input to the CNN-LSTM-PSO model for training and testing. The results show that the CNN-LSTM-PSO model can effectively predict tool wear with an average absolute error MAE value of 0.5848, a root mean square error RMSE value of 0.7281, and a coefficient of determination R2 value of 0.9964; and compared with the BP model, CNN model, LSTM model and CNN-LSTM model, its tool wear prediction accuracy improved by 7.56%, 2.60%, 2.98%, and 1.63%, respectively.

Improving Quantitative EDS Chemical Analysis of Alloy Nanoparticles by PCA Denoising: Part II. Uncertainty Intervals.

Analytical studies of nanoparticles (NPs) are frequently based on huge datasets derived from hyperspectral images acquired using scanning transmission electron microscopy. These large datasets require machine learning computational tools to reduce dimensionality and extract relevant information. Principal component analysis (PCA) is a commonly used procedure to reconstruct information and generate a denoised dataset; however, several open questions remain regarding the accuracy and precision of reconstructions. Here, we use experiments and simulations to test the effect of PCA processing on data obtained from AuAg alloy NPs a few nanometers wide with different compositions. This study aims to address the reliability of chemical quantification after PCA processing. Our results show that the PCA treatment mitigates the contribution of Poisson noise and leads to better quantification, indicating that denoised results may be reliable from the point of view of both uncertainty and accuracy for properly planned experiments. However, the initial data need to be of sufficient quality: these results can only be obtained if the signal-to-noise ratio of input data exceeds a minimal value to avoid the occurrence of random noise bias in the PCA reconstructions.

Deep Learning for Radiotherapy Outcome Prediction Using Dose Data – A Review

Artificial intelligence, and in particular deep learning using convolutional neural networks, has been used extensively for image classification and segmentation, including on medical images for diagnosis and prognosis prediction. Use in radiotherapy prognostic modelling is still limited, however, especially as applied to toxicity and tumour response prediction from radiation dose distributions. We review and summarise studies that applied deep learning to radiotherapy dose data, in particular studies that utilised full three-dimensional dose distributions. Ten papers have reported on deep learning models for outcome prediction utilising spatial dose information, whereas four studies used reduced dimensionality (dose volume histogram) information for prediction. Many of these studies suffer from the same issues that plagued early normal tissue complication probability modelling, including small, single-institutional patient cohorts, lack of external validation, poor data and model reporting, use of late toxicity data without taking time-to-event into account, and nearly exclusive focus on clinician-reported complications. They demonstrate, however, how radiation dose, imaging and clinical data may be technically integrated in convolutional neural networks-based models; and some studies explore how deep learning may help better understand spatial variation in radiosensitivity. In general, there are a number of issues specific to the intersection of radiotherapy outcome modelling and deep learning, for example translation of model developments into treatment plan optimisation, which will require further combined effort from the radiation oncology and artificial intelligence communities.

Comparative analysis of 2D-PCA based dimensionality reduction and feature extraction

The complex spectral and spatial characteristics of hyperspectral remote sensing images (HSI) lead to higher time-consuming in classification task. To address this question, we introduced the 2D-PCA dimensionality reduction method of linear mapping in the two-dimensional spatial domain on the basis of linear dimensionality reduction in the spectral domain, thereby compressing the complex spatial structure information of HSI into a limited low-dimensional space, and realizing space-spectrum dimensionality reduction and information fusion. The experimental results on three classic data sets of Salinas, Tea Farm, and Indian Pines show that 2D-PCA has a strong ability to condense and compress spatial structure characteristics. Compared with popular deep learning frameworks such as CNN and Mixer-MLP, conventional machine learning models based on 2D-PCA have significant advantages in terms of computing time under the premise of controllable accuracy loss, which makes 2D-PCA a promising method for dimensionality reduction and feature expression in hyperspectral pixel-wise classification.

Integrating Information Visualization and Dimensionality Reduction: A pathway to Bridge the Gap between Natural and Artificial Intelligence

By importing some natural abilities from human thinking into the design of computerized decision support systems, a cross-cutting trend of intelligent systems has emerged, namely, the synergetic integration between natural and artificial intelligence. While natural intelligence provides creative, parallel, and holistic thinking, its artificial counterpart is logical, accurate, able to perform complex and extensive calculations, and tireless. In the light of such integration, two concepts are important: controllability and interpretability. The former is defined as the ability of computerized systems to receive feedback and follow users’ instructions, while the latter refers to human-machine communication. A suitable alternative to simultaneously involve these two concepts—and then bridging the gap between natural and artificial intelligence—is bringing together the fields of dimensionality reduction (DimRed) and information visualization (InfoVis).

Ship velocity estimation via images acquired by an unmanned aerial vehicle-based hyperspectral imaging sensor

Remote sensing technology is an important means of ocean exploration. Unmanned aerial vehicle (UAV) remote sensing is widely used in small observation areas because of its flexible operation, timely data transmission, and high spatial resolution. According to these characteristics, we propose a ship attribute inversion algorithm based on the wake characteristics. First, a band selection method is used to reduce the data dimensionality and remove redundant information from UAV remote sensing data. Then, the ship wake is detected by extracting the shear wave (S-wave) characteristics. Finally, the ship’s motion parameters are inverted according to the S-wave attributes. The experimental results show that the method proposed can detect the wakes effectively and estimate ship velocity accurately using the UAV-obtained hyperspectral images.

Dynamical Analysis of the Dow Jones Index Using Dimensionality Reduction and Visualization.

Time-series generated by complex systems (CS) are often characterized by phenomena such as chaoticity, fractality and memory effects, which pose difficulties in their analysis. The paper explores the dynamics of multidimensional data generated by a CS. The Dow Jones Industrial Average (DJIA) index is selected as a test-bed. The DJIA time-series is normalized and segmented into several time window vectors. These vectors are treated as objects that characterize the DJIA dynamical behavior. The objects are then compared by means of different distances to generate proper inputs to dimensionality reduction and information visualization algorithms. These computational techniques produce meaningful representations of the original dataset according to the (dis)similarities between the objects. The time is displayed as a parametric variable and the non-locality can be visualized by the corresponding evolution of points and the formation of clusters. The generated portraits reveal a complex nature, which is further analyzed in terms of the emerging patterns. The results show that the adoption of dimensionality reduction and visualization tools for processing complex data is a key modeling option with the current computational resources.

Measuring everyday creativity: A Rasch model analysis of the Biographical Inventory of Creative Behaviors (BICB) scale

Research on everyday creativity—the “little c” creative activities people do in their everyday lives—commonly uses self-report scales to assess people’s engagement in different activities. The present research presents a detailed psychometric analysis of the Biographical Inventory of Creative Behaviors (BICB), a 34-item yes/no checklist of common creative activities that has become one of the most popular self-report measures of everyday creative behaviors. Based on a sample of 2,359 adults, the reliability, dimensionality, item fit, item difficulty, and test information were evaluated from a Rasch model perspective. Overall, the BICB shows good evidence for score reliability and appears essentially unidimensional; a small cluster of misfitting and locally dependent items were flagged for impairing unidimensionality. The items’ difficulty level was generally moderate and suitable for the scale’s intended populations and purposes. Differential item functioning (DIF) based on gender and age, estimated via Rasch tree recursive partitioning methods, found notable gender-based DIF (generally reflecting culturally gendered qualities of some creative activities) but little age-based DIF. Taken together, the BICB has many psychometric strengths. Some opportunities for future scale refinement are discussed.

Performing sequential forward selection and variational autoencoder techniques in soil classification based on laser-induced breakdown spectroscopy.

The feasibility and accuracy of several combination classification models, i.e., quadratic discriminant analysis (QDA), random forest (RF), Bernoulli naïve Bayes (BNB), and support vector machine (SVM) classification models combined with either sequential feature selection (SFS) or dimensionality reduction methods, for classifying soil with laser-induced breakdown spectroscopy (LIBS) had been explored in this study. Each algorithm combination was compared to assess their classification performance. After eliminating the irrelevant features of the data using sequential feature selection (SFS), the performances were all improved for the studied four classification models, and the best accuracy reached 97.88% by SFS-SVM. The dimensions of the data were then reduced using variational autoencoder (VAE), truncated singular value decomposition (TSVD), and isometric mapping (Isomap), respectively. The classification accuracy improved for all combination models with dimensionality reduction, and impressive accuracies of 98.12% from TSVD-SVM and 98.24% from VAE-SVM were obtained. These results demonstrate an effective way to reduce uncorrelated features, high dimensionality, and redundant information in the LIBS dataset. In addition, coupling classification models with feature selection and dimensionality reduction techniques could significantly optimize the classification performance of LIBS.

Image Compression Technology Based on Wavelet Transform

Image compression based on wavelet transform is to apply wavelet algorithm to multi-resolution decomposition of the image, and to achieve image compression by encoding the obtained wavelet coefficients. First, multi-level wavelet decomposition is performed on the image to obtain the corresponding wavelet coefficients. Then, each layer of wavelet coefficients is quantized to obtain quantized coefficient objects. Finally, the quantized coefficient objects are encoded to obtain compression results. This paper uses Haar wavelet as the wavelet base, selects the 2-level decomposition scale, performs wavelet transform, compresses the reconstructed image by setting a threshold, and calculates the file size ratio and PSNR value before and after compression. The wavelet reconstruction function uses the coefficient matrix, dimensionality information and wavelet base type obtained by wavelet decomposition to perform wavelet reconstruction. The global threshold setting method is selected, and the wavelet high-frequency coefficients are threshold filtered to achieve compression before the reconstruction operation, and then the compressed image is obtained through wavelet reconstruction. After the image has undergone wavelet transformation with a specified scale, most of the energy is concentrated in the fractional part of the wavelet decomposition coefficients. The coefficients of other parts are set to constants by setting a threshold, and only a few decomposition coefficients are retained to represent the entire image.The experimental results show that the storage space of the compressed image is greatly saved and the compressed image does not change significantly from the original image visually.

Assimilation of Principal Component Analysis and Wavelet with Kernel Support Vector Regression for Medium-Term Financial Time Series Forecasting

Entities and institutional financiers have gained a lot of growth from financial time series forecasting in recent times. But the major challenges of financial time series data are the high noise and complexity of its nature. Researchers in recent times have successfully engaged the application of support vector regression (SVR) to conquer this challenge. In this study principal component analysis (PCA) is applied to extract the low dimensionality and efficient feature information, while wavelet is used to pre-process the extracted features in other to nu1llify the influence of the noise in the features with a KSVR based forecasting model. The analysis is carried out based on the quarterly tax revenue data of 39 years from the first quarter of 1981 to the last quarter of 2016. The forecasting is made for ten quarters ahead. The initial empirical result shows that the multicollinearity has been reduced to zero (0), and the analytic result reveals that the proposed model PCA-W-KSVR outperforms KSVR, PCA-KSVR, and W-KSVR in terms of MAE, MAPE, MSE and RMSE.

EnsemPseU: Identifying Pseudouridine Sites With an Ensemble Approach

Pseudouridine (Ψ) is the most prevalent RNA modification, which is formed from uridine through an isomerization reaction. With the increasing availability of genomic and proteomic samples, computer-aided pseudouridine-synthase-specific Ψ site recognition is becoming possible. In this paper, we propose an ensemble approach to identify pseudouridine sites, named EnsemPseU. First, five sequence-encoding strategies, namely, kmer, binary encoding, enhanced nucleic acid composition (ENAC), nucleotide chemical property (NCP), and nucleotide density (ND), were applied to extract sequence information. Then, chi-square feature selection was used to reduce the feature dimensionality and remove redundant information. Finally, an ensemble algorithm integrating support vector machine (SVM), extreme gradient boosting (XGBoost), naive Bayes (NB), k-nearest neighbor (KNN), and random forest (RF) was used to build our prediction model. Upon testing, the results showed that the accuracy improved 5.3% for H. sapiens, 6.09% for S. cerevisiae, and 5.55% for M. musculus after chi-square feature selection. Moreover, upon evaluation via 10-fold cross-validation and an independent test, our proposed model EnsemPseU outperformed the other best existing model. The source code and data sets are available at https://github.com/biyue1026/EnsemPseU.

A Comparison Between Support Vector Machine (SVM) and Convolutional Neural Network (CNN) Models For Hyperspectral Image Classification

This study presents a methodology model for the spectral classification of hyperspectral images. The applied methodology, first extracts neighbouring spatial regions via a suitable statistical support vector machine (SVM-Linear) architecture, support vector machine radial basis function (SVM-RBF) and Deep Learning (DL) architecture that comprises principal component analysis (PCA) and convolutional neural networks (CNN) and then applies a soft max classifier. PCA is introduced to reduce the high spectral dimensionality, noise, and redundant information of the input image. The SVM-Linear, SVM-RBF and CNN model is used to extract useful high-level features automatically given that it provides results comparable with each other, including hyperspectral image classification. However, because the CNN, SVM models alone may fail to extract features with different scales and to tolerate the large-scale variance of image objects, the presented methodology uses PCA optimization for spatial regions to construct features that can be then used by the SVM and CNN model to classify hyperspectral images. Experimental results obtained in the classification of the Hyperspec-VNIR Chikusei datasets show that the performance of the presented model is competitive with that of other DL and traditional machine-learning methods. The best overall accuracy of the presented methodology for the Hyperspec-VNIR Chikusei datasets is 98.84 % in SVM-RBF model.

A computational perspective of the periodic table of elements

This paper adopts dimensionality reduction, clustering and information visualization techniques to organize and map a set of 86 chemical elements (CE). Each CE is characterized through 17 properties and the dissimilarities between the CE are measured by different metrics, namely the arccosine, Canberra and Lorentzian distances. The dissimilarity information is then used as input to hierarchical clustering and multidimensional scaling algorithms. The two computational techniques yield 2- and 3-dim maps of the CE organized accordingly to their characteristics. The results can be visualized and interpreted not only under the light of the CE location, but also of the emerging clusters. The new representations constitute an alternative to the classic Cartesian-like 2-dimensional table and point towards advanced scientific visualization using present day computational resources.