Important Data Processing Research Articles

Email spam detection by deep learning models using novel feature selection technique and BERT

Due to the influx of advancements in technology and the increased simplicity of communication through emails, there has been a severe threat to the global economy and security due to upsurge in volume of unsolicited During the training of models, high-dimensional and redundant datasets may reduce the classification results of the model due to high memory costs and high computation. An important data processing technique is feature selection which helps in selecting relevant features and subsets of information from the dataset. Therefore, choosing efficient feature selection techniques is very important for the best performance of classification of a model. Moreover, most of the research has been performed using traditional machine learning techniques, which are not enough to deal with the huge amount of data and its variations. Also,spammers are becoming smarter with technological advancement. Therefore, there is a need for hybrid techniques consisting of deep learning and conventional algorithms to cope with these problems. We have proposed a novel scheme in this paper for email spam detection, which will result in an improved feature selection approach from the original dataset and increase the accuracy of the classifier as well. The literature has been studied to explore the efficient machine learning models that have been applied by different researchers for email spam detection and feature selection to acquire the best results. Our method, GWO-BERT, has given remarkable results with deep learning techniques such as CNN, biLSTM and LSTM. We have compared our models with RF and LSTM and used dataset: “Lingspam,” which is a publicly available dataset. With different experiments, our technique, GWO-BERT, obtained 99.14% accuracy, which is almost equal to 100 percent.

Study on Key Technologies of Cancer Surveillance and Early Warning based on Data Mining

Early detection and accurate judgment are crucial during cancer diagnosis and treatment. Hence, it is of great significance to establish an effective cancer early warning system. However, the arrival of big data provides new opportunities for cancer surveillance and early warning, and data mining technology, as an important data processing method, is being widely used in the field of cancer surveillance and early warning. By analyzing a large number of medical images and medical records, the author identifies some potential risk factors which can improve the early diagnosis rate and treatment effect. Moreover, this paper compares the current status and trends of research on data mining, analyzes the key technologies of cancer surveillance and early warning based on data mining, and summarizes the related research results with the evaluation of each method.

Sequential Seismic Anisotropic Inversion for VTI Media with Simulated Annealing Algorithm Aided by Adaptive Setting of Optimization Parameters

As an important geophysical data processing technique, seismic inversion estimates subsurface rock properties with seismic observations. However, anisotropic inversion, intended for a vertical transverse isotropy (VTI) media that primarily describes shale gas/oil resources, suffers from high nonlinearity. Simulated annealing is a widely used global optimization algorithm for solving nonlinear seismic inverse problems, but it involves multiple optimization parameters (e.g., initial temperature, search limit, and perturbation range). The importance of such parameters has been proven whilst the relevant analysis is limited in seismic inversion studies. This work hereby proposes a sequential anisotropic inversion method for VTI media, wherein we combine Bayesian linear and simulated annealing nonlinear inversion schemes. The simulated annealing is featured by adaptive optimization parameters aided by the linear result. Rather than the conventional method, the adaptive setting can be implemented trace by trace for complex reservoirs, which endows the method with enhanced stability and extended applicability. Synthetic tests and practical application demonstrate the validity of the method, wherein the obtained stiffness parameters facilitate the characterization of potential shale reservoirs with an improved accuracy.

Trainable quantization for Speedy Spiking Neural Networks.

Spiking neural networks are considered as the third generation of Artificial Neural Networks. SNNs perform computation using neurons and synapses that communicate using binary and asynchronous signals known as spikes. They have attracted significant research interest over the last years since their computing paradigm allows theoretically sparse and low-power operations. This hypothetical gain, used from the beginning of the neuromorphic research, was however limited by three main factors: the absence of an efficient learning rule competing with the one of classical deep learning, the lack of mature learning framework, and an important data processing latency finally generating energy overhead. While the first two limitations have recently been addressed in the literature, the major problem of latency is not solved yet. Indeed, information is not exchanged instantaneously between spiking neurons but gradually builds up over time as spikes are generated and propagated through the network. This paper focuses on quantization error, one of the main consequence of the SNN discrete representation of information. We argue that the quantization error is the main source of accuracy drop between ANN and SNN. In this article we propose an in-depth characterization of SNN quantization noise. We then propose a end-to-end direct learning approach based on a new trainable spiking neural model. This model allows adapting the threshold of neurons during training and implements efficient quantization strategies. This novel approach better explains the global behavior of SNNs and minimizes the quantization noise during training. The resulting SNN can be trained over a limited amount of timesteps, reducing latency, while beating state of the art accuracy and preserving high sparsity on the main datasets considered in the neuromorphic community.

Revisiting the Fundamentals of Untargeted Data Analysis with Comprehensive Two-Dimensional Gas Chromatography (GC×GC): With Great Peak Capacity, There Must Also Come Great Responsibility

This article provides a general overview of untargeted analysis using comprehensive two-dimensional gas chromatography (GC×GC), while revisiting some fundamental aspects of method development. The original definition of chemometrics is also revised according to the latest developments of the field. We discuss how GC×GC has become an important backbone for new strategies in separation science, especially in multivariate data analysis. The concept of pixel is also revisited, as an important pixel-based data processing method, namely the Fisher ratio proposed by Synovec and coworkers, has been successfully implemented in important software for GC×GC.

Comparison of Methods to Segment Variable-Contrast XCT Images of Methane-Bearing Sand Using U-Nets Trained on Single Dataset Sub-Volumes

Methane (CH4) hydrate dissociation and CH4 release are potential geohazards currently investigated using X-ray computed tomography (XCT). Image segmentation is an important data processing step for this type of research. However, it is often time consuming, computing resource-intensive, operator-dependent, and tailored for each XCT dataset due to differences in greyscale contrast. In this paper, an investigation is carried out using U-Nets, a class of Convolutional Neural Network, to segment synchrotron XCT images of CH4-bearing sand during hydrate formation, and extract porosity and CH4 gas saturation. Three U-Net deployments previously untried for this task are assessed: (1) a bespoke 3D hierarchical method, (2) a 2D multi-label, multi-axis method and (3) RootPainter, a 2D U-Net application with interactive corrections. U-Nets are trained using small, targeted hand-annotated datasets to reduce operator time. It was found that the segmentation accuracy of all three methods surpass mainstream watershed and thresholding techniques. Accuracy slightly reduces in low-contrast data, which affects volume fraction measurements, but errors are small compared with gravimetric methods. Moreover, U-Net models trained on low-contrast images can be used to segment higher-contrast datasets, without further training. This demonstrates model portability, which can expedite the segmentation of large datasets over short timespans.

Spatio-Temporal Quality Indicators for Differential Interferometric Synthetic Aperture Radar Data

Satellite-based interferometric synthetic aperture radar (InSAR) is an invaluable technique in the detection and monitoring of changes on the surface of the earth. Its high spatial coverage, weather friendly and remote nature are among the advantages of the tool. The multi-temporal differential InSAR (DInSAR) methods in particular estimate the spatio-temporal evolution of deformation by incorporating information from multiple SAR images. Moreover, opportunities from the DInSAR techniques are accompanied by challenges that affect the final outputs. Resolving the inherent ambiguities of interferometric phases, especially in areas with a high spatio-temporal deformation gradient, represents the main challenge. This brings the necessity of quality indices as important DInSAR data processing tools in achieving ultimate processing outcomes. Often such indices are not provided with the deformation products. In this work, we propose four scores associated with (i) measurement points, (ii) dates of time series, (iii) interferograms and (iv) images involved in the processing. These scores are derived from a redundant set of interferograms and are calculated based on the consistency of the unwrapped interferometric phases in the frame of a least-squares adjustment. The scores reflect the occurrence of phase unwrapping errors and represent valuable input for the analysis and exploitation of the DInSAR results. The proposed tools were tested on 432,311 points, 1795 interferograms and 263 Sentinel-1 single look complex images by employing the small baseline technique in the PSI processing chain, PSIG of the geomatics division of the Centre Tecnològic de Telecomunicacions de Catalunya (CTTC). The results illustrate the importance of the scores—mainly in the interpretation of the DInSAR outputs.

An enhanced black widow optimization algorithm for feature selection

Feature selection is an important data processing method to reduce dimension of the raw datasets while preserving the information as much as possible. In this paper, an enhanced version of Black Widow Optimization Algorithm called SDABWO is proposed to solve the feature selection problem. The Black Widow Optimization Algorithm (BWO) is a new population-based meta-heuristic algorithm inspired by the evolution process of spider population. Three main improvements were included into the BWO to overcome the shortcoming of low accuracy, slow convergence speed and being easy to fall into local optima. Firstly, a novel strategy for selecting spouses by calculating the weight of female spiders and the distance between spiders is proposed. By applying the strategy to the original algorithm, it has faster convergence speed and higher accuracy. The second improvement includes the use of mutation operator of differential evolution at mutation phase of BWO which helps the algorithm escape from the local optima. And then, three key parameters are set to adjust adaptively with the increase of iteration times. To confirm and validate the performance of the improved BWO, other 10 algorithms are used to compared with the SDABWO on 25 benchmark functions. The results show that the proposed algorithm enhances the exploitation ability, improves the convergence speed and is more stable when solving optimization problems. Furthermore, the proposed SDABWO algorithm is employed for feature selection. Twelve standard datasets from UCI repository prove that SDABWO-based method has stronger search ability in the search space of feature selection than the other five popular feature selection methods. These results confirm the capability of the proposed method simultaneously improve the classification accuracy while reducing the dimensions of the original datasets. Therefore, SDABWO-based method was found to be one of the most promising for feature selection problem over other approaches that are currently used in the literature.

Optical Machine Learning Using Time-Lens Deep Neural NetWorks

As a high-throughput data analysis technique, photon time stretching (PTS) is widely used in the monitoring of rare events such as cancer cells, rough waves, and the study of electronic and optical transient dynamics. The PTS technology relies on high-speed data collection, and the large amount of data generated poses a challenge to data storage and real-time processing. Therefore, how to use compatible optical methods to filter and process data in advance is particularly important. The time-lens proposed, based on the duality of time and space as an important data processing method derived from PTS, achieves imaging of time signals by controlling the phase information of the timing signals. In this paper, an optical neural network based on the time-lens (TL-ONN) is proposed, which applies the time-lens to the layer algorithm of the neural network to realize the forward transmission of one-dimensional data. The recognition function of this optical neural network for speech information is verified by simulation, and the test recognition accuracy reaches 95.35%. This architecture can be applied to feature extraction and classification, and is expected to be a breakthrough in detecting rare events such as cancer cell identification and screening.

Multiobjective Particle Swarm Optimization for Feature Selection With Fuzzy Cost.

Feature selection (FS) is an important data processing technique in the field of machine learning. There have been various FS methods, but all assume that the cost associated with a feature is precise, which restricts their real applications. Focusing on the FS problem with fuzzy cost, a fuzzy multiobjective FS method with particle swarm optimization, called PSOMOFS, is studied in this article. The proposed method develops a fuzzy dominance relationship to compare the goodness of candidate particles and defines a fuzzy crowding distance measure to prune the elitist archive and determine the global leader of particles. Also, a tolerance coefficient is introduced into the proposed method to ensure that the Pareto-optimal solutions obtained satisfy decision makers' preferences. The developed method is used to tackle a series of the UCI datasets and is compared with three fuzzy multiobjective evolutionary methods and three typical multiobjective FS methods. Experimental results show that the proposed method can achieve feature sets with superior performances in approximation, diversity, and feature cost.

Feature selection using bare-bones particle swarm optimization with mutual information

Feature selection (FS) is an important data processing method in pattern recognition and data mining. Due to not considering characteristics of the FS problem itself, traditional particle update mechanisms and swarm initialization strategies adopted in most particle swarm optimization (PSO) limit their performance on dealing with high-dimensional FS problems. Focused on it, this paper proposes a novel feature selection algorithm based on bare bones PSO (BBPSO) with mutual information. Firstly, an effective swarm initialization strategy based on label correlation is developed, making full use of the correlation between features and class labels to accelerate the convergence of swarm. Then, in order to enhance the exploitation performance of the algorithm, two local search operators, i.e., the supplementary operator and the deletion operator, are developed based on feature relevance-redundancy. Furthermore, an adaptive flip mutation operator is designed to help particles jump out of local optimal solutions. We apply the proposed algorithm to typical datasets based on the K-Nearest Neighbor classifier (K-NN), and compare it with eleven state-of-the-art algorithms, SFS, PTA, SGA, BPSO, PSO(4-2), HPSO-LS, Binary BPSO, NaFA, IBFA, KPLS-mRMR and SMBA-CSFS. The experimental results show that the proposed algorithm can achieve a feature subset with better performance, and is a highly competitive FS algorithm.

Identification of Comprehensive Energy Consumption Feature Based on Rough Set Bayesian Classification Algorithm

Mining of valuable information from user energy consumption data efficiently and accurately has always been a research hotspot in the power industry. Bayesian classification method is one of the important data processing methods in the field of machine learning and data mining research. It has the advantages of simplicity, high efficiency and stable classification effect, and it provides an effective solution to the user’s comprehensive energy consumption feature identification. A model describing energy consumption data to predict trends is built, training data set is analyzed, a classification model is constructed, and the data records in the database to a given category are maped, which can be applied to data prediction. By studying incomplete information systems, expanding rough sets, constructing extended models, Bayesian classification algorithms based on rough sets theory is designed, and user comprehensive energy consumption feature identification is realized. Experiments show that the user comprehensive energy consumption feature identification algorithm based on rough set Bayesian classification can greatly improve the classification accuracy.

Improve the spectral clustering by integrating a new modularity similarity index and out-of-sample extension

Spectral clustering is one of the most important data processing methods which has been wildly applied to machine learning, computer vision, pattern recognition and image processing. However, one of the main drawbacks of spectral clustering is the fact that the clustering model is defined only for primal data without clear extension to out-of-sample data. To improve its efficiency, in this paper, we proposed a new modularity-based method for spectral clustering with out-of-sample extension. First, kernel independent component analysis is used to solve the demixing matrix on Stiefel manifold in order to extract high-order irrelevant data feature. Then, a new modularity similarity measure-based spectral mapping algorithm is proposed, which allows the clustering model to be directly extended to out-of-sample data. Based on above analysis, we present a spectral clustering algorithm with out-of-sample extension. Experimental results show our method has better performance compared with other related algorithms in different datasets.

Development of Web Based Courseware for Artificial Neural Networks

Artificial Neural Networks (ANN) are important data processing algorithms which are used for solving nonlinear problems. Through classical approaches, mathematical infrastructure and complex equations in ANN are difficult to understand. Interactive and multimedia-based courseware has the potential to overcome these difficulties. In this study, a web based educational courseware for ANN was developed to provide an effective and efficient learning environment so that the difficulties can be overcome. This interactive courseware was also enriched with animations and text-based course contents. In addition to this, the effects of ANN parameters’ changes were observed directly through graphical results. In this way, users can easily understand the fundamentals and working mechanism of ANN. Without using any commercial libraries, the courseware was developed with ASP.NET, an object-oriented programming language. The courseware supports file formats such as XML, TXT, and CSV so that it can co-operate with other software. “Balance and Scale” data set was used to evaluate the performance of the courseware. 0.9918 accuracy, 1 specificity and 1 sensitivity values were achieved. When this study is compared to previous studies, improvements in terms of visuality, understandability and interactivity can clearly be identified.

A Modified RLS Algorithm for ICA with Weighted Orthogonal Constraint

Independent component analysis (ICA), as an important data processing technique, is widely employed in many areas. The objective of the ICA is to recover independent components from observed signals. Several algorithms, such as equivariant adaptive separation via independence algorithm, least-mean-square (LMS)-type algorithms and recursive least-squares (RLS)-type learning rules, are proposed to solve the ICA problem. In the present paper, a modified RLS algorithm for ICA with weighted orthogonal constraint is developed to implement source separation based on the local convergence analysis of the available algorithm. Comparative experiment results demonstrate that the proposed algorithm is better than existing learning rules in the aspect of the accuracy of separation and stability.

The Kalman Filter Uncertainty Concept in the Possibility Domain

The Kalman filter (KF) is one of the most important and common optimal recursive data processing algorithms in many applications characterized by linear dynamical behavior and affected by random zero-mean white Gaussian noise. However, when measurement processes are considered, inaccuracy is not only due to noise but also to several contributions to uncertainty that can be due to both random and uncompensated systematic effects. Therefore, when the KF is used on experimental data, all uncertainty contributions should be considered. While several proposals are available in the literature to modify the KF in order to consider different probability distributions and systematic effects, represented both in probability and possibility domains, they are not fully compliant with the uncertainty concept adopted in metrology. The aim of this paper is, hence, to reformulate the KF theory within the possibility domain in compliance with the measurement uncertainty concept, in order to be able to consider both the random and systematic contributions to uncertainty (regardless of their distribution) that may affect the measurement process. An experimental setup is considered and the results obtained under different assumptions are reported.

Kronecker least angle regression for unsupervised unmixing of hyperspectral imaging data

Spectral unmixing is an important data processing task that is commonly applied to hyperspectral imaging data. It uses a set of spectral pixels, i.e., multichannel data, to separate each spectral pixel, a multicomponent signal comprised of a linear mixture of pure spectral signatures, into its individual spectral signatures commonly known as endmembers. When no prior information about the required endmembers is available, the resulting unsupervised unmixing problem will be underdetermined, and additional constraints become necessary. A recent approach to solving this problem required that these endmembers be sparse in some dictionary. Sparse signal recovery is commonly solved using a basis pursuit optimization algorithm that requires specifying a data-dependent regularization parameter. Least angle regression (LARS) is a very efficient method to simultaneously solve the basis pursuit optimization problem for all relevant regularization parameter values. However, despite this efficiency of LARS, it has not been applied to the spectral unmixing problem before. This is likely because the application of LARS to large multichannel data could be very challenging in practice, due to the need for generation and storage of extremely large arrays (~ 1010 bytes in a relatively small area of spectral unmixing problem). In this paper, we extend the standard LARS algorithm, using Kronecker products, to make it suitable for practical and efficient recovery of sparse signals from large multichannel data, i.e., without the need to construct or process very large arrays, or the need for trial and error to determine the regularization parameter value. We then apply this new Kronecker LARS (K-LARS) algorithm to successfully achieve spectral unmixing of both synthetic and AVIRIS hyperspectral imaging data. We also compare our results to ones obtained using an earlier basis pursuit-based spectral unmixing algorithm, generalized morphological component analysis (GMCA). We show that these two results are similar, albeit our results were obtained without trial and error, or arbitrary choices, in specifying the regularization parameter. More important, our K-LARS algorithm could be a very valuable research tool to the signal processing community, where it could be used to solve sparse least squares problems involving large multichannel data.

Geoinformation Sharing System for East and Southeast Asia Using SDI, OGC Web Services and FOSS

This paper presents an innovative, cost-effective and efficient web-based sharing system for geoscience information among the countries in East and Southeast Asia. The information system’s main components are organized following the Spatial Data Infrastructure (SDI) model. It also uses the Open Geospatial Consortium (OGC) Web Map Service (WMS) and Web Processing Service (WPS) for online spatial data rendition and processing, respectively. Free and Open Source Software (FOSS) are also used for other important spatial data processing functions. The geospatial contents of the information system are stored and managed using the open source software PostgreSQL and its PostGIS extension. The information system makes spatial data sharing more efficient and organized by formulating a hierarchical information content classification scheme and the option for the users to put up their own customized WebGIS portals. These give users the option to show their chosen geospatial contents on their own web-based platform. The information system also makes spatial data sharing more flexible by providing data owners the choice to determine the data access privileges for each user or group of users. It also provides module for processing, rendering and sharing Japan’s ASTER satellite images. The information system is called GSi for Geoinformation Sharing Infrastructure for East and Southeast Asia. The URL of the web-based information system is https://ccop-gsi.org/main/index.html.

Mobile Application and a Web-Based Geographic Information System for Sharing Geological Hazards Information in East and Southeast Asia

This paper presents a mobile application and a web-based geographic information system for an efficient and cost-effective sharing of geological hazards information in East and Southeast Asia. The information system uses the Open Geospatial Consortium (OGC), Web Map Service (WMS) and Web Processing Service (WPS) for spatial data rendition and processing online. Free and Open Source Software (FOSS) is also used for other important spatial data processing and sharing operations. WMS and WPS are formulated to access and view the geological hazard data in the system’s database. The mobile application is developed to access and share the system’s geospatial contents by sending requests to these web services. The application also makes geological hazard mitigation measures more effective by incorporating the mobile device’s GPS location information with geological hazard data. Information like the distance from the nearest active fault, active volcano and earthquake hypocenter can be easily determined using the application. The mobile application provides an interface for the users to easily access geological hazard information such as active fault, active volcanoes, shorelines inundated by tsunamis, and historical and real time seismic events. The widespread use of mobile devices with Internet connection makes geological hazard information dissemination very efficient using the application. The mobile application is called G-EVER Mobile. G-EVER stands for Asia Pacific Region Global Earthquake and Volcanic Eruption Risk Management consortium. The application can be accessed at https://ccop-geoinfo.org/gever-mo/index.php.

Toward a new approach for sorting extremely large data files in the big data era

The extensive amount of data and contents generated today will require a paradigm shift in processing and management techniques for these data. One of the important data processing operations is the data sorting. Using multiple passes in external merge sort has a great influence on speeding up the sorting of extremely large data files. Since in large files, the swapping time is dominant in many applications, algorithms that minimize the swapping operations are normally superior to those which only focus on CPU time optimizations. In sorting extremely large files, external algorithms, such as the merge sort, are normally used. It is shown that using multiple passes over the data set, as proposed in our algorithm, has resulted in a great improvement in the number of swaps, thus, reducing the overall sorting time. Moreover, the proposed technique is suitable to be used with the emerging parallelization techniques such as GPUs. The reported results show the superiority of the proposed technique for “CPU only” and hybrid CPU–GPU implementations.