High-dimensional Data Research Articles

Advanced power quality monitoring with dilated convolutional neural networks for smart nanogrids

This study presents the development of an advanced power quality monitoring (PQM) system using dilated convolutional deep neural networks (DCDNN) for smart nanogrids. Traditional convolutional neural networks (CNNs) face challenges in efficiently handling high-dimensional data and identifying nuanced features due to their limited receptive field. To overcome these limitations, our DCDNN model employs a novel use of dilated convolutions to expand the receptive field without increasing network complexity, enabling the capture of long-range dependencies essential for accurate classification of power quality disturbances (PQDs). In addition, the integration of multi-channel time-series data processing, including voltage, current, and frequency measurements, is unique to our approach. The model processes multi-channel time-series data, including voltage, current, and frequency measurements, achieving an average accuracy of 98.9% across 29 PQD classes and 100% accuracy in 6 main classes, with a reduced detection time of 47 µs per segment. This approach not only improves real-time disturbance detection but also enhances the reliability and efficiency of electrical systems. The results demonstrate significant improvements over existing methods, underscoring the potential of DCDNNs in advancing PQM practices. Future work will focus on validating the model in real-world conditions and optimizing its computational efficiency.

Hyperspectral image classification with token fusion on GPU

Hyperspectral images capture material nuances with spectral data, vital for remote sensing. Transformer has become a mainstream approach for tackling the challenges posed by high-dimensional hyperspectral data with complex structures. However, a major challenge they face when processing hyperspectral images is the presence of a large number of redundant tokens, which leads to a significant increase in computational load, adding to the model’s computational burden and affecting inference speed. Therefore, we propose a token fusion algorithm tailored to the operational characteristics of the hyperspectral image and pure transformer network, aimed at enhancing the final accuracy and throughput of the model. The token fusion algorithm introduces a token merging step between the attention mechanism and the multi-layer perceptron module in each Transformer layer. Experiments on four hyperspectral image datasets demonstrate that our token fusion algorithm can significantly improve inference speed without any training, while only causing a slight decrease in the pure transformer network’s classification accuracy.

C-ziptf: stable tensor factorization for zero-inflated multi-dimensional genomics data.

In the past two decades, genomics has advanced significantly, with single-cell RNA-sequencing (scRNA-seq) marking a pivotal milestone. ScRNA-seq provides unparalleled insights into cellular diversity and has spurred diverse studies across multiple conditions and samples, resulting in an influx of complex multidimensional genomics data. This highlights the need for robust methodologies capable of handling the complexity and multidimensionality of such genomics data. Furthermore, single-cell data grapples with sparsity due to issues like low capture efficiency and dropout effects. Tensor factorizations (TF) have emerged as powerful tools to unravel the complex patterns from multi-dimensional genomics data. Classic TF methods, based on maximum likelihood estimation, struggle with zero-inflated count data, while the inherent stochasticity in TFs further complicates result interpretation and reproducibility. Our paper introduces Zero Inflated Poisson Tensor Factorization (ZIPTF), a novel method for high-dimensional zero-inflated count data factorization. We also present Consensus-ZIPTF (C-ZIPTF), merging ZIPTF with a consensus-based approach to address stochasticity. We evaluate our proposed methods on synthetic zero-inflated count data, simulated scRNA-seq data, and real multi-sample multi-condition scRNA-seq datasets. ZIPTF consistently outperforms baseline matrix and tensor factorization methods, displaying enhanced reconstruction accuracy for zero-inflated data. When dealing with high probabilities of excess zeros, ZIPTF achieves up to better accuracy. Moreover, C-ZIPTF notably enhances the factorization's consistency. When tested on synthetic and real scRNA-seq data, ZIPTF and C-ZIPTF consistently uncover known and biologically meaningful gene expression programs. Access our data and code at: https://github.com/klarman-cell-observatory/scBTF and https://github.com/klarman-cell-observatory/scbtf_experiments .

Integrating Canonical Correlation Analysis with Random Forest for Heart Disease Prediction

Heart disease, a leading global cause of death over the past several decades, encompasses a range of disorders affecting the heart. Researchers use various data mining and machine learning techniques to analyze complex medical data, aiding healthcare professionals in predicting cardiac conditions. Despite these advances, existing models often struggle with effectively modelling non-linear relationships, maximizing feature correlation, and addressing challenges related to dimensionality and overfitting. This research paper introduces the Hybrid CCRF model for heart disease prediction, which integrates Canonical Correlation Analysis (CCA) with Random Forest. The proposed model generates polynomial features to capture non-linear relationships and applies Canonical Correlation Analysis to identify canonical variables that maximize correlations between heart disease features and chronic condition features. By combining these canonical variables into a single feature set, the model enhances prediction accuracy. The objectives of the Hybrid CCRF model are threefold: 1) To capture complex non-linear relationships between heart disease and chronic condition features by integrating polynomial feature generation with Canonical Correlation Analysis, thereby improving the model’s ability to represent intricate data patterns; 2) To use CCA to identify and integrate canonical variables that enhance feature correlation, creating a more informative feature set; and 3) To address high-dimensional data and overfitting issues by combining canonical variables with polynomial features in a Random Forest model, balancing complexity and performance for improved generalization and robustness across various datasets. The proposed model achieved an accuracy of 99.45%, with a sensitivity of 98.53%, specificity of 99.54%, precision of 95.73%, and an F1 Score of 0.9711, outperforming all existing models.

Analyzing the Impact of Scientific and Technological Innovations on Financial Performance: A PCA-Based Study of an AI Healthcare Startup

This study explores the relationship between scientific and technological innovations and the financial performance of startups, focusing on a representative Artificial Intelligence (AI) healthcare startup. Utilizing Principal Component Analysis (PCA), the research aims to dissect the complex interplay between innovation-related metrics—such as R&D spending, patent counts, and technology adoption rates—and financial outcomes like revenue growth, profitability, and market share. The PCA methodology enabled the reduction of high-dimensional data into PCA, which clearly illustrates how several dimensions of innovation impact financial metrics. The approach used in the investigation helps people comprehend more thoroughly how development benefits business viability in several different manners and provides startups with practical advice to use when preparing their revolutionary investments. This paper aims to assist the ecosystem of startup consumers (including investors, business owners, and policymakers) in making better decisions that balance technological progress with economic objectives.

Cluster partition-fuzzy broad learning-based fast detection and localization framework for false data injection attack in smart distribution networks

The distributed renewable energy generations, as accessible and easily targets for attackers, introduce an extra false data injection attack (FDIA) threat in the smart distribution networks. Scattered attack points and complex attack features hinder the elimination of potential threats. In this context, an FDIA fast detection and pinpoint localization framework is proposed. This framework identifies abnormal signals and attacked nodes from the unique topology structure and status contiguity of smart distribution networks, namely, spatial-temporal correlations of power grids, by using a cluster partition-fuzzy broad learning system (CP-FBLS). Unlike most existing FDIA detection methods, which are dedicated to high accuracy but neglect the urgent need for rapid detection in smart distribution networks, the proposed CP-FBLS framework maintains the fast computational nature of a fuzzy broad learning system (FBLS), while avoiding the accuracy degradation caused by high-dimension of data in large-scale smart distribution networks. Moreover, the multi-layer structure of the proposed framework recognizes the location of FDIA, bridging the research gap of attack localization. To comprehensively evaluate the proposed strategy, datasets containing various FDIA types are constructed. Numerical simulations based on the above datasets in modified IEEE 34-bus and 123-bus distribution systems are implemented. The results of the case studies showed that the proposed method can achieve 98.43 % accuracy with 0.34 ms detection time, realizing rapid detection and localization of various FDIAs with satisfactory accuracy.

Intelligent fatigue damage tracking and prognostics of composite structures utilizing raw images via interpretable deep learning

In recent years, prognostics gained attention in various industries by optimizing maintenance, boosting operational efficiency, and preventing costly downtime. Central to prognostics is the Remaining Useful Life (RUL), representing the critical time before system failure. Deep learning advancements facilitate RUL forecasting by extracting features from diverse data formats such as time series, images, or sequences thereof, in one, two, or three dimensions, respectively. Yet, predicting RUL from image sequences often relies heavily on resource-intensive techniques like digital image correlation, complicating data acquisition. To address challenges with high-dimensional data and unreliable models, this study introduces ISTRUST, an innovative Transformer-based architecture. ISTRUST (Interpretable Spatiotemporal TRansformer for Understanding STructures) tackles the dual challenges posed by high-dimensional data and the black-box nature of existing models. Leveraging Transformers’ attention mechanism, ISTRUST breaks down the spatiotemporal domain, effectively realizing interpretable RUL predictions under uncertainty using only sparse raw image sequences as input. Evaluated on fatigue-loaded composite samples showcasing crack propagation, ISTRUST interprets the relation between cracks and RUL via the attention mechanism. The results substantiate its capacity to interpret and clarify instances in which predictions may exhibit variability in accuracy. Through the attention mechanism, a strong correlation between the model’s spatiotemporal focus and the RUL predictions is established, making it, to the best of our knowledge, the first model to provide interpretable stochastic RUL predictions directly from sequential images of this nature.

Temporal Autoregressive Matrix Factorization for High-Dimensional Time Series Prediction of OSS.

Open-source software (OSS) plays an increasingly significant role in modern software development tendency, so accurate prediction of the future development of OSS has become an essential topic. The behavioral data of different open-source software are closely related to their development prospects. However, most of these behavioral data are typical high-dimensional time series data streams with noise and missing values. Hence, accurate prediction on such cluttered data requires the model to be highly scalable, which is not a property of traditional time series prediction models. To this end, we propose a temporal autoregressive matrix factorization (TAMF) framework that supports data-driven temporal learning and prediction. Specifically, we first construct a trend and period autoregressive model to extract trend and period features from OSS behavioral data, and then combine the regression model with a graph-based matrix factorization (MF) to complete the missing values by exploiting the correlations among the time series data. Finally, use the trained regression model to make predictions on the target data. This scheme ensures that TAMF can be applied to different types of high-dimensional time series data and thus has high versatility. We selected ten real developer behavior data from GitHub for case analysis. The experimental results show that TAMF has good scalability and prediction accuracy.

Integrating granular computing with density estimation for anomaly detection in high-dimensional heterogeneous data

Detecting anomalies in complex data is crucial for knowledge discovery and data mining across a wide range of applications. While density-based methods are effective for handling varying data densities and diverse distributions, they often struggle with accurately estimating densities in heterogeneous, uncertain data and capturing interdependencies among features in high-dimensional spaces. This paper proposes a fuzzy granule density-based anomaly detection algorithm (GDAD) for heterogeneous data. Specifically, GDAD first partitions high-dimensional attributes into subspaces based on their interdependencies and employs fuzzy information granules to represent data. The core of the method is the definition of fuzzy granule density, which leverages local neighborhood information alongside global density patterns and effectively characterizes anomalies in data. Each object is then assigned a fuzzy granule density-based anomaly factor, reflecting its likelihood of being anomalous. Through extensive experimentation on various real-world datasets, GDAD has demonstrated superior performance, matching or surpassing existing state-of-the-art methods. GDAD's integration of granular computing with density estimation provides a practical framework for anomaly detection in high-dimensional heterogeneous data.

Hybrid random projection: Integrating dense and sparse techniques for enhanced representation in high-dimensional data

This paper introduces a novel hybrid random projection method (HRP) that effectively combines the strengths of normal random projection (NRP) and plus-minus one random projection (PMRP). By incorporating a blending parameter, HRP optimises the contributions of the NRP and PMRP, reducing the dimensions of the data while ensuring that the structure of the data is preserved. Conventional methods, such as NRP and PMRP, are recognised for their benefits; however, they also have limitations. NRP is generally accurate but can encounter difficulties with certain data types or noise. The PMRP is simple, but occasionally fails to capture complex relationships within the data. The performance of HRP is investigated through comprehensive evaluations, including simulations and real-world data analyses from key machine learning datasets, such as period change, toxicity, MNIST, and human activity recognition (HAR). We examine various factors such as sample size, dimensions of the original and reduced data, and sparsity. Distance distortion is the primary metric utilised to measure performance, and indicates how well the dataset structure is maintained after dimension reduction. In every test, HRP consistently demonstrates the least distance distortion, performing superiorly to the NRP and PMRP. This is true for a range of scenarios and datasets. HRP represents a significant advancement in dimension reduction techniques. Its ability to minimise information loss during the reduction process demonstrates its potential as a powerful tool for managing complex high-dimensional data in practical applications. This renders HRP an important development in the fields of machine learning, intelligent systems, and artificial intelligence, offering improved efficiency and precision in data analyses.

Support vector machine based on the quadratic unconstrained binary optimization model

Abstract Support vector machine (SVM) is a powerful supervised machine learning model that is often used in binary classification algorithms. As Moore’s Law approaches its theoretical limits and the demand for machine learning to handle large-scale, high-dimensional data analysis intensifies, the necessity of adopting non-traditional computational approaches becomes evident. Quantum computing, in particular, emerges as a vital solution for the effective training of SVM models, providing capabilities beyond those of classical computing systems. To solve the above problems, a QUBO (quadratic unconstrained binary optimization) model is proposed to transform the SVM machine learning model into a quadratic unconstrained binary optimization problem so that they can be effectively trained on the D-Wave platform using adiabatic quantum computer. The results show that the QUBO model can transform the SVM model into a simple quadratic programming problem, which makes it suitable for adiabatic quantum computer processing. When processing large-scale and high-dimensional data, this transformation shows a natural advantage and significantly improves computational efficiency. The application potential of this transformation technology is huge in the medical field.

Enhancing classification in high-dimensional data with robust rMI-SVM feature selection

Enhancing classification in high-dimensional data with robust rMI-SVM feature selection

NEAT Based Approach for Cognitive Covert Communication Assisted by UAV-IRS

Abstract To address the security vulnerabilities inherent in cognitive radio technology amidst extensive control information and data exchanges, this paper introduces the use of unmanned aerial vehicle equipped with intelligent reflecting surfaces (UAV-IRS) as relay nodes to facilitate covert communications for cognitive users. Given the complexities and dynamics of the electromagnetic environment, which involve multiple interconnected and constantly changing communication resources, as well as high-dimensional data, we propose the NeuroEvolution of Augmenting Topologies based Resource Optimisation Algorithm Method (NEAT-ROAM). This advanced algorithm continuously optimizes and adapts the network structure in response to the external environment, ensuring robust and secure communication in dynamic and challenging scenarios. The algorithm not only provides superior covert communication performance but also exhibits fast convergence, which can be applied to the problem of assisting covert communication under mobile conditions using UAV-IRS.

Machine learning based classification of excessive smartphone users via neuronal cue reactivity

Excessive Smartphone Use (ESU) poses a significant challenge in contemporary society, yet its recognition as a distinct disorder remains ambiguous. This study aims to address this gap by leveraging functional magnetic resonance imaging (fMRI) data and machine learning techniques to classify ESU and non-excessive smartphone users (n-ESU) based on their neural Cue-Reactivity (CR) signatures. By conducting a CR task and analyzing brain activation patterns, we identified spatial similarities between addictive smartphone use and established addictive disorders. Our approach involved employing Support Vector Machines (SVM) for classification, enhanced with feature selection methods such as Recursive Feature Elimination (RFE) and Model-based Selection and dimensionality reduction methods such as and Principal Component Analysis (PCA) to mitigate the challenges posed by limited dataset size and high dimensionality of fMRI data. The results demonstrate the effectiveness of our classification model, achieving accuracies of up to 79.9 %. Furthermore, we observed region-specific activations contributing significantly to classification accuracy, highlighting the potential biomarkers associated with ESU. External validation on longitudinal data revealed the necessity for larger training datasets to improve model generalizability. Additionally, feature selection techniques proved crucial for optimizing model performance, particularly in datasets with combined information from multiple sources. Our findings underscore the importance of incorporating more data to enhance model stability and generalizability, with implications for advancing the understanding and treatment of ESU and related disorders. Overall, our study demonstrates the promise of machine learning approaches in elucidating neural correlates of ESU and informing targeted interventions for affected individuals.

MADE: Multicurvature Adaptive Embedding for Temporal Knowledge Graph Completion.

Temporal knowledge graphs (TKGs) are receiving increased attention due to their time-dependent properties and the evolving nature of knowledge over time. TKGs typically contain complex geometric structures, such as hierarchical, ring, and chain structures, which can often be mixed together. However, embedding TKGs into Euclidean space, as is typically done with TKG completion (TKGC) models, presents a challenge when dealing with high-dimensional nonlinear data and complex geometric structures. To address this issue, we propose a novel TKGC model called multicurvature adaptive embedding (MADE). MADE models TKGs in multicurvature spaces, including flat Euclidean space (zero curvature), hyperbolic space (negative curvature), and hyperspherical space (positive curvature), to handle multiple geometric structures. We assign different weights to different curvature spaces in a data-driven manner to strengthen the ideal curvature spaces for modeling and weaken the inappropriate ones. Additionally, we introduce the quadruplet distributor (QD) to assist the information interaction in each geometric space. Ultimately, we develop an innovative temporal regularization to enhance the smoothness of timestamp embeddings by strengthening the correlation of neighboring timestamps. Experimental results show that MADE outperforms the existing state-of-the-art TKGC models.

Predictive modeling using Copula Particle Filter and Adaptive Network-Based Fuzzy Inference

This paper introduces a novel prediction algorithm, CPF-ANFIS, designed to overcome the challenges posed by high-dimensional input data in Adaptive Neuro-Fuzzy Inference Systems (ANFIS). ANFIS's performance deteriorates with increasing input dimensionality due to the distortion of its membership functions. To address this limitation, CPF-ANFIS leverages a two-stage approach: A Copula Particle Filter (CPF) for robust state estimation and ANFIS for nonlinear mapping. By incorporating copulas, CPF effectively addresses the impoverishment and degeneracy problems commonly encountered in traditional particle filters. This enhanced robustness allows for more accurate state estimation, which in turn improves the overall performance of the CPF-ANFIS algorithm. By decoupling state estimation from nonlinear modeling, CPF-ANFIS effectively mitigates the curse of dimensionality. The proposed method is evaluated on real-world applications, such as hybrid PV-wind systems and SLAM. Experimental results demonstrate that CPF-ANFIS consistently outperforms ANFIS and the Copula Particle Filter individually, as well as previously proposed methods such as ANFIS-PF, highlighting its effectiveness in achieving accurate predictions under challenging conditions. The results show that the CPF-ANFIS algorithm increases prediction accuracy by at least 5% compared to using each algorithm separately.

Deep Anomaly Detection: A Linear One-Class SVM Approach for High-Dimensional and Large-Scale Data

Deep Anomaly Detection: A Linear One-Class SVM Approach for High-Dimensional and Large-Scale Data

Cascaded capsule twin attentional dilated convolutional network for malicious URL detection

Malware is one of the most popular cyber-attacks, and it is becoming more common on the network every day. In contrast to benign transmission, which typically exhibits symmetrical patterns, malware communication often shows asymmetrical behaviours, making detection a complex challenge. Fortunately, malware can be distinguished and identified for actual activities utilizing a variety of artificial intelligence methods. However, insufficient work has been allocated to the problem of handling high-dimensional and huge data. This paper proposes a novel deep learning-based approach to identify malicious Uniform Resource Locators (URLs) specifically designed to handle the challenges posed by large-scale and complex data. Initially, input data is sourced from a comprehensive Kaggle dataset, which includes diverse and large-scale URL samples. The URLs are then transformed into vector representations using a Vector Embedding Module, which employs a character-level word embedding technique to capture intricate patterns within the URLs. To further refine the data, the Chaotic Kookaburra Efficient-Bo Network (CKEBO-Net) is applied to extract the most significant features from these vectors, effectively reducing the dimensionality and computational burden. Subsequently, the Cascaded Capsule Twin Attentional Dilated Convolutional Network (C2TA_DiCN) model is introduced to classify and identify malicious URLs with high precision. This model leverages the unique strengths of capsule networks and attentional mechanisms, enhancing its capability to capture subtle dependencies within the data. Furthermore, the Lyrebird Meta-heuristic Optimization (LMO) algorithm is used to fine-tune the model parameters appropriately, ensuring that the training process is efficient and robust. The proposed approach is implemented using Python and rigorously evaluated on the Kaggle dataset. Simulation results demonstrate that the proposed method significantly outperforms existing models, achieving a malicious URL detection accuracy of 99.7%.

Identifying Crop Distress and Stress-Induced Plant Diseases Using Hyper Spectral Image Analysis

The purpose of this study is to determine whether hyper spectral images can be used to identify plant diseases and crop pressure from aerial photographs. With extensive research on the prevalent methods used closer to the problem, this study offers a potent strategy for identifying crop distress and illnesses using this efficient imaging technique. To identify the spectral fingerprints of common indications and symptoms of plant diseases and crop strains, this study evaluates the available hyper spectral photo datasets. After that, the data are examined using two learning algorithms—the highly randomized trees and the Random Woodland set of rules—to create predictions that are entirely dependent on the results that are discovered. In the end, a benchmarked set of test statistics is used to assess the prediction accuracy. The results of this study show that hyper spectral photo evaluation has a strong and promising utility for crop stress and disease identification. Hyper spectral light evaluation is a method for identifying plant diseases caused by strain on crops. By gathering and evaluating high-dimensional spectral reflection data from satellite or aircraft structures, details regarding the physiological homes of flowers can be identified. The health of plants, illnesses brought on by stress, and agricultural productivity predictions can all be made using these facts. Hyper spectral recordings can also be used to create actions that reduce agricultural losses and enhance the health of plants that are prone to disease.

A remaining useful life prediction method based on DATCN-PSOSEN for turbofan engines

Abstract Turbofan engine is a crucial operational component of aircraft. Remaining useful life (RUL) prediction is important for the stable and reliable operation of the turbofan engine. High-dimensional and large-capacity monitoring data of turbofan engines pose a considerable challenge to accurate RUL prediction. A novel approach based on dual-attention temporal convolutional network (DATCN) and particle swarm optimization with selective ensemble (PSOSEN) is proposed in this paper. In the first stage, DATCN is utilized to explore the internal correlations among various input features and different time steps in monitoring data, highlighting the degradation information from two dimensions. In the second stage, PSOSEN is developed to prune base models, excluding the ones with poor performance and assigning varying weights to the others, leading to selectively ensembled prediction results. The experimental results on the C-MAPSS aero-engine degradation dataset validate the effectiveness of the proposed DATCN-PSOSEN method and show improvements of RUL prediction accuracy by 14.2% compared with other methods.