Classification Approach Research Articles

Retraction Note to: Leakage detection and localization on water transportation pipelines: a multi-label classification approach

Retraction Note to: Leakage detection and localization on water transportation pipelines: a multi-label classification approach

Categorising hybrid material microfluidic devices

Microfluidic devices are useful tools for a wide range of biomedical, industrial, and environmental applications. Hybrid microfluidic devices utilising more than two materials are increasingly being used for their capacity to produce unique structures and perform novel functions. However, an analysis of publications across the field shows that whilst hybrid microfluidic devices have been reported, there remains no system of classifying hybrid devices which could help future researchers in optimising material selection. To resolve this issue, we propose a system of classifying hybrid microfluidic devices primarily as containing either hybrid structural, chemical, or electrical components. This is expanded upon and developed into a hierarchy, with combinations of different primary components categorised into secondary or tertiary hybrid device groupings. This classification approach is useful as it describes materials that can be combined to create novel hybrid microfluidic devices.

Simultaneous Three-Degrees-of-Freedom Prosthetic Control Based on Linear Regression and Closed-Loop Training Protocol

Machine learning-based controllers of prostheses using electromyographic signals have become very popular in the last decade. The regression approach allows a simultaneous and proportional control of the intended movement in a more natural way than the classification approach, where the number of movements is discrete by definition. However, it is not common to find regression-based controllers working for more than two degrees of freedom at the same time. In this paper, we present the application of the adaptive linear regressor in a relatively low-dimensional feature space with only eight sensors to the problem of a simultaneous and proportional control of three degrees of freedom (left–right, up–down and open–close hand movements). We show that a key element usually overlooked in the learning process of the regressor is the training paradigm. We propose a closed-loop procedure, where the human learns how to improve the quality of the generated EMG signals, helping also to obtain a better controller. We apply it to 10 healthy and 3 limb-deficient subjects. Results show that the combination of the multidimensional targets and the open-loop training protocol significantly improve the performance, increasing the average completion rate from 53% to 65% for the most complicated case of simultaneously controlling the three degrees of freedom.

Advancements in skin cancer classification: a review of machine learning techniques in clinical image analysis

AbstractEarly detection of skin cancer from skin lesion images using visual inspection can be challenging. In recent years, research in applying deep learning models to assist in the diagnosis of skin cancer has achieved impressive results. State-of-the-art techniques have shown high accuracy, sensitivity and specificity compared with dermatologists. However, the analysis of dermoscopy images with deep learning models still faces several challenges, including image segmentation, noise filtering and image capture environment inconsistency. After making the introduction to the topic, this paper firstly presents the components of machine learning-based skin cancer diagnosis. It then presents the literature review on the current advance in machine learning approaches for skin cancer classification, which covers both the traditional machine learning approaches and deep learning approaches. The paper also presents the current challenges and future directions for skin cancer classification using machine learning approaches.

Fine-resolution estimation for urban surface water pollution susceptibility with multi-modal earth observation data

Abstract The sustainability and suitability of water resources are of great importance for maintaining urban populations. The landscapes and environment around urban waters have always been the main focus of maintaining water quality for sustainable water supplies. Early-stage field investigations recognized the influence of land use/land cover (LULC) on water quality. To extend the research scope in spatial and temporal dimensions, remote sensing techniques have been utilized to discover the relationships between LULC and water quality. However, these remote sensing datasets generally had a medium spatial resolution, making them unable to support the fine-detailed land classifications that are critical to explore the water quality in an urban area. Moreover, although more details regarding the land surface are available from the currently-generated high-resolution and very-high-resolution remote sensing images, this land surface information is too complex for the state-of-the-art deep learning approaches and benchmark datasets. This manuscript reports our efforts on developing a framework to explore the fine-resolution relationship between surface water pollution and LULC. To address the cost of computing time and limitations of well-labelled datasets, we employ a foundation model-enhanced approach for water extraction and water-surrounded LULC classification. We propose an estimator of surface water pollution susceptibility to main pollutants based on the surrounding LULCs. Selecting the Future City of Beijing as the study area, based on very-high-resolution remote sensing images, the experiment proved that our proposed approach could effectively map the susceptibility of surface water pollution caused by its surrounding land use and land cover. To our knowledge, the relationship of LULCs and water quality have not been investigated using 0.5m spatial resolution data. We hope our work can provide a prospective fine-detailed water quality analysis in the community of water environment of remote sensing.

A novel self-supervised sentiment classification approach using semantic labeling based on contextual embeddings

AbstractSentiment Analysis (SA) is a domain or context-oriented task since the sentiment words convey different sentiments in various domains. As a result, the domain-independent lexicons cannot correctly recognize the sentiment of domain-dependent words. To address this problem, this paper proposes a novel self-supervised SA method based on semantic similarity, contextual embedding, and Deep Learning Techniques. It introduces a new Pseudo-label generator that estimates the pseudo-labels of samples using semantic similarity between the samples and their sentiment words. It proposes two new concepts to calculate semantic similarity: The Soft-Cosine Similarity of a sample with its Positive words (SCSP) and the Soft-Cosine Similarity of a document with its Negative words (SCSN). Then, the Pseudo-label generator uses these concepts and the number of sentiment words to estimate the label of each sample. Later on, a novel method is proposed to find the samples with highly accurate pseudo-labels. Finally, a hybrid classifier, composed of a Convolutional Neural Network (CNN) and a Gated Recurrent Unit (GRU), is trained using these highly accurate pseudo-labeled data to predict the label of unseen data. The comparison of the proposed method with the lexicons and other similar existing methods demonstrates that the proposed method outperforms them in terms of accuracy, precision, recall, and F1 score.

Schizencephaly: Etiopathogenesis, Classification, Therapeutic, and Rehabilitative Approach

AbstractSchizencephaly is an uncommon anomaly in neuronal migration characterized by complete clefts that extend from the pia mater to the ependymal surface of the ventricular system. These clefts are encompassed by displaced gray matter and filled with cerebrospinal fluid. Typically, they are found most often in the frontal lobe or the area around the lateral sulcus and can occur on one or both sides. The size, location, and type of these clefts carry significant clinical and prognostic implications. Moreover, they are frequently associated with other central nervous system malformations, including the absence of the septum pellucidum, septo-optic dysplasia, optic nerve hypoplasia, pachygyria, polymicrogyria, cortical dysplasia, heterotopia, and dysplasia of the corpus callosum. Occurrence of schizencephaly is almost always sporadic but its etiopathogenesis is yet to be fully understood. Most likely environmental factors, including exposure to teratogens, viral infections, and maternal factors, operate jointly with genetic defects. To date COL4A1, EMX2, SHH, and SIX3 are the genes identified as possible pathogenetic target. It is interesting to notice that schizencephaly is commonly seen in abandoned or adopted children, as proof of causative effect of intrautero insults. Clinical presentations widely vary and symptoms include a spectrum of cognitive impairment, limb paresis/tetraparesis, and epileptic seizures either with early or late onset; anyway, none of these symptoms is ever-present and patients with schizencephaly can also have normal neurocognitive and motor development. Diagnostic gold standard for schizencephaly is magnetic resonance imaging, which allows to identify and characterize typical clefts. Treatment of schizencephaly is symptomatic and supportive and depends on the severity of morbidity resulting from the malformation. Therapy includes antiepileptic drugs, psychomotor rehabilitation, and in selected cases surgical approach.

Congenital/Primitive Hydrocephalus: Classification, Clinical Aspects, and Rehabilitation Approach

AbstractHydrocephalus is a heterogeneous disorder of cerebrospinal fluid (CSF) flow that leads to abnormal enlargement of the brain ventricles. The prevalence of infant hydrocephalus is approximately one case per 1,000 births. Hydrocephalus occurs due to an imbalance between the production and the absorption of CSF. The causes of hydrocephalus secondary to CSF overproduction are papilloma of the choroid plexus and rarely diffuse hyperplasia of the villi. All the other hydrocephalus forms are secondary to obstruction to normal CSF reabsorption and are also known as obstructive hydrocephalus. According to the location of obstruction, obstructive hydrocephalus can be defined as communicating, when caused by extraventricular obstruction of the CSF flow or decreased resorption of CSF distal to the fourth ventricle in the cisterns of the base or in the subarachnoid spaces, or as not communicating, in case of intraventricular obstruction to fluid flow. There is a third category, common in preterm infants, called external hydrocephalus which is secondary to delayed development of arachnoid function. Hydrocephalus leads to an increase in intraventricular pressure because of the lack of the mechanism regulating the homeostasis of the CSF flow. Increased intraventricular pressure is responsible for the clinical symptoms in affected child. Clinical presentation varies with age. In the neonatal period, prolonged or frequent apneic or bradycardic events, increasing head circumference, presence of sunsetting eyes or upward gaze palsy, evidence of full or tense anterior/posterior fontanelle, and splayed cranial sutures are signs of increased intracranial pressure. In infants, the most common signs are progressive macrocephaly, irritability, nausea/vomiting, headache, gait changes, and regression of developmental milestones. The extent of brain damage depends on the cause that led to hydrocephalus, the patient's age, and the rapidity of onset. The surgical treatment modalities consist of endoscopic ventriculostomy of the third ventricle and ventriculoperitoneal or ventriculoatrial CSF shunt.

The Effect of Residence Time and Stream Restrictions on the Precursors’ Structure and Coke Morphology

AbstractIn this work, the precursors and intermediates of catalytic dehydrogenation of toluene, ethylbenzene, and styrene (TES) stream were detected, quantified, and classified at 750–800 °C. The classification approach for tracing the structural changes of the produced precursors was designed based on different residence times of intermediates, leading to the presentation of a morphology prediction model for precipitated coke according to the restriction of stream pass. The results revealed that the coke structure of encapsulating is formed by heavier precursors produced at a restricted direction of flow. On the other hand, the filamentous coke made from lighter precursors is formed at smooth streams with no restricted areas.

Hot rolled steel surface defect detection and classification using an automatic ensemble approach

Abstract This study introduces an ensemble-based Deep Neural Network (DNN) model for detecting defects on steel surfaces. The method suggested in this study classifies steel surface conditions into six possible fault categories, namely, crazing, inclusion, rolled in, pitted surface, scratches, and patches. The images undergo preprocessing and extraction of features in spatial and frequency domains using image segmentation techniques such as grey level difference method (GLDM), fast Fourier Transform (FFT), grey level co-occurrence matrix (GLCM), texture analysis and discrete wavelet transform (DWT). The ensembling of image features into a fused feature pool is carried out after the preprocessing of input images that are provided as input to a light-weight neural network model for training and testing. The performance of the model is comprehensively evaluated via an ablation study both before and after ensembling. In addition, the model capability is effectively analyzed using receiver operating characteristics (ROC) curve, confusion matrix from which classification accuracy of the model could be obtained and other parameters including precision and f1-score. It was observed that the proposed deep learning network presents phenomenally high accuracy of 99.72% for detection and classification of steel surface faults. This result was found to be superior when compared with the performance of the same neural network over each feature type individually. This study also compares the classification results of the model built based on the ensembled feature set with the results of various other classification approaches available in literature. The ensemble-based model could potentially be integrated into existing inspection systems for real-time, efficient and robust condition monitoring of steel surfaces.

Expert–Novice Level Classification Using Graph Convolutional Network Introducing Confidence-Aware Node-Level Attention Mechanism

In this study, we propose a classification method of expert–novice levels using a graph convolutional network (GCN) with a confidence-aware node-level attention mechanism. In classification using an attention mechanism, highlighted features may not be significant for accurate classification, thereby degrading classification performance. To address this issue, the proposed method introduces a confidence-aware node-level attention mechanism into a spatiotemporal attention GCN (STA-GCN) for the classification of expert–novice levels. Consequently, our method can contrast the attention value of each node on the basis of the confidence measure of the classification, which solves the problem of classification approaches using attention mechanisms and realizes accurate classification. Furthermore, because the expert–novice levels have ordinalities, using a classification model that considers ordinalities improves the classification performance. The proposed method involves a model that minimizes a loss function that considers the ordinalities of classes to be classified. By implementing the above approaches, the expert–novice level classification performance is improved.

The Attention-Based Autoencoder for Network Traffic Classification with Interpretable Feature Representation

Network traffic classification is crucial for identifying network applications and defending against network threats. Traditional traffic classification approaches struggle to extract structural features and suffer from poor interpretability of feature representations. The high symmetry between network traffic classification and its interpretable feature representation is vital for network traffic analysis. To address these issues, this paper proposes a traffic classification and feature representation model named the attention mechanism autoencoder (AMAE). The AMAE model extracts the global spatial structural features of network traffic through attention mechanisms and employs an autoencoder to extract local structural features and perform dimensionality reduction. This process maps different network traffic features into one-dimensional coordinate systems in the form of spectra, termed FlowSpectrum. The spectra of different network traffic represent different intervals in the coordinate system. This paper tests the interpretability and classification performance of network traffic features of the AMAE model using the ISCX-VPN2016 dataset. Experimental results demonstrate that by analyzing the overall distribution of attention weights and local weight values of network traffic, the model effectively explains the differences in the spectral representation intervals of different types of network traffic. Furthermore, our approach achieves the highest classification accuracy of up to 100% for non-VPN-encrypted traffic and 99.69% for VPN-encrypted traffic, surpassing existing traffic classification schemes.

Unsupervised multimodal modeling of cognitive and brain health trajectories for early dementia prediction

Predicting the course of neurodegenerative disorders early has potential to greatly improve clinical management and patient outcomes. A key challenge for early prediction in real-world clinical settings is the lack of labeled data (i.e., clinical diagnosis). In contrast to supervised classification approaches that require labeled data, we propose an unsupervised multimodal trajectory modeling (MTM) approach based on a mixture of state space models that captures changes in longitudinal data (i.e., trajectories) and stratifies individuals without using clinical diagnosis for model training. MTM learns the relationship between states comprising expensive, invasive biomarkers (β-amyloid, grey matter density) and readily obtainable cognitive observations. MTM training on trajectories stratifies individuals into clinically meaningful clusters more reliably than MTM training on baseline data alone and is robust to missing data (i.e., cognitive data alone or single assessments). Extracting an individualized cognitive health index (i.e., MTM-derived cluster membership index) allows us to predict progression to AD more precisely than standard clinical assessments (i.e., cognitive tests or MRI scans alone). Importantly, MTM generalizes successfully from research cohort to real-world clinical data from memory clinic patients with missing data, enhancing the clinical utility of our approach. Thus, our multimodal trajectory modeling approach provides a cost-effective and non-invasive tool for early dementia prediction without labeled data (i.e., clinical diagnosis) with strong potential for translation to clinical practice.

Wake structure of an array of cylinders in shallow flow

Although there is a range of approaches for classifying the wake structure behind an array of obstacles, these approaches provide inconsistent results across different array systems. This motivates the present study to integrate and reconcile these approaches into one that is consistent across different systems. This new, transferable classification approach is based on the dimensionless flow blockage of the array and the wake stability parameter. To demonstrate this approach, a series of laboratory experiments was conducted to characterise the wake structure behind an array of emergent cylinders across a practically relevant parameter space that has not previously been explored. Two arrays with the same values of flow blockage and wake stability parameters but different sizes display the same wake structure, demonstrating the controlling influence of these two parameters on the wake structure. This approach classifies four different wake structures, which are distinct in that they display differences in instantaneous and time-averaged flow fields, temporal velocity oscillations, shear layer growth and the length of the steady wake region. The dependence of the wake structure on the two parameters is a consequence of (i) the controlling influence of blockage on the fraction of incident flow passing through the array and (ii) the ability of shallowness to suppress wake instabilities and, to a lesser extent, also influence the velocity through the array. This paper provides a predictive framework for the wake structure based on knowledge of the array geometry, and the depth and velocity of incident flow across the entire relevant practical parameter space.

Mapping surface sediment characteristics in enclosed shallow‐marine environments using spatially balanced designs and the random forest algorithm

AbstractMapping the sedimentary character of the seafloor in large water‐filled basins is fundamental for understanding landform dynamics to inform research, management, intervention and conservation actions. Seabed mapping methods have undergone considerable development in the last two decades, including the uptake of machine learning approaches for sediment size prediction and classification. However, predictions of surficial sediment characteristics are often hindered by the availability of ground truthing data, their arrangement in space and the modelling approach chosen. Spatially informed sampling designs provide an opportunity to significantly improve the accuracy and uncertainty of predicted sediment distributions. In this study, we apply a machine learning algorithm to predict sediment distributions across Port Phillip Bay, a large (1930 km2) structurally controlled estuary on the southeast coast of Victoria, Australia. Surface sediment samples (n = 252) were collected using a spatially balanced design, ensuring that sampling effort was spread evenly within the embayment with increased sampling intensity placed in more heterogeneous areas. Surficial textural metrics were modelled using the random forest algorithm with bathymetric and hydrodynamic predictor variables. Models highlighted trends in sediment grain size, sorting and composition consistent with predicted wave‐ and current‐induced sediment mobilisation. Model predictions were accurate (normalised‐root mean squared error [NRMSE]: 0.14–0.16); however, standard error was not homogeneous across the study area. Uncertainty maps highlighted areas where additional sampling effort may be needed, including areas where transitional bathymetry impacted surficial sediment character and areas of anthropogenic modifications to the seabed. This study shows the benefits of undertaking spatially informed sample design, block cross‐validation during model fitting and quantifying spatial uncertainty in predictive maps to accurately quantify the fundamental boundary conditions of sediment size. The results of this study are intended to inform local coastal management, including beach renourishment activities. However, approaches outlined are applicable to any study where the seafloor grain size is a fundamental variable in understanding landscape change.

Membership Weight Salp Swarm Algorithm (MWSSA) based feature selection and deep learning approach for breast cancer classification of SNP genomics data

Membership Weight Salp Swarm Algorithm (MWSSA) based feature selection and deep learning approach for breast cancer classification of SNP genomics data

A dual-branch selective attention capsule network for classifying kiwifruit soft rot with hyperspectral images

Kiwifruit soft rot is highly contagious and causes serious economic loss. Therefore, early detection and elimination of soft rot are important for postharvest treatment and storage of kiwifruit. This study aims to accurately detect kiwifruit soft rot based on hyperspectral images by using a deep learning approach for image classification. A dual-branch selective attention capsule network (DBSACaps) was proposed to improve the classification accuracy. The network uses two branches to separately extract the spectral and spatial features so as to reduce their mutual interference, followed by fusion of the two features through the attention mechanism. Capsule network was used instead of convolutional neural networks to extract the features and complete the classification. Compared with existing methods, the proposed method exhibited the best classification performance on the kiwifruit soft rot dataset, with an overall accuracy of 97.08% and a 97.83% accuracy for soft rot. Our results confirm that potential soft rot of kiwifruit can be detected using hyperspectral images, which may contribute to the construction of smart agriculture.

Characterization of seismic-scale petrofacies variability in the Arbuckle Group using supervised machine learning: Wellington Field, Kansas

The Arbuckle Group in southern Kansas has been investigated for carbon geosequestration-related studies. In this study, we evaluated seismic-scale petrophysically defined facies variability of the Arbuckle Group at the Wellington Field, Kansas, using quantitative seismic interpretation and a supervised Random Forest classification approach. We first defined three petrophysics-based rock types (petrofacies) from core-derived porosity and permeability measurements using the flow-zone indicator (FZI) approach. Then, using the artificial neural network (ANN), we classified these petrofacies in non-cored intervals. We observed that petrofacies 1 corresponds to medium and coarse-grained dolomitic packstone, wackestone, and dolomitic breccia with up to 8% porosity and Darcy-scale permeability values. Whereas petrofacies 2 and 3 correspond to argillaceous and fine-grained micritic dolomites and dolomitic mudstones with lower permeability values for a given porosity, with respect to petrofacies 1. Using the common reflection-point gathers, we performed pre-stack seismic inversion and calculated various amplitude-versus-offset (AVO) attribute volumes. We used these elastic properties and AVO attribute volumes as input for estimating supervised seismic-scale 3D petrofacies and petrofacies probability volumes using the Random Forest algorithm. Results reveal the complex distribution of petrofacies in the candidate injection and baffle zones in the study area, where petrofacies 1 is mainly prevalent within the lower and upper portions of the Arbuckle group, while petrofacies 2 and 3 are mainly present in the middle Arbuckle interval. The workflow we present through this study provides spatial variability of facies distribution that is reflective of actual lithology and petrophysical properties of the Arbuckle group in the study area with limited well control.

Classification model for chlorophyll content using CNN and aerial images

Chlorophyll content is usually used as a quantitative measurement of plant health. The chlorophyll content is also a continuous number of data type, leading to a regression approach when developing the deep learning model. The regression model will predict the chlorophyll content in number format, which requires experts to analyse the outcome. Nevertheless, the analysis of the outcome could possibly lead to human error in diagnosing the plant’s health condition. Therefore, this study proposed a classification approach in developing a deep learning model to analyse the plant’s health condition without human intervention. The classification approach requires a discrete group for dependent variables instead of continuous numbers. When forming the chlorophyll content index groups in this study, which are low, optimum and high levels, two research studies were combined to form the groups, which were (1) the product of the standard range of nitrogen value in mango plant and (2) the correlation analysis between nitrogen value and chlorophyll content index. The classification model in this study used transfer learning algorithms, which were InceptionV3, DenseNet121 and ResNet50, with the canopy-scale level of mango plant RGB images with complex leaf structures in an uncontrolled and open area. Based on the findings, the classification model could classify the chlorophyll content index levels on both mango plant images, which were infected and not infected with black sooty mould. The finding also shows that a clearer distribution pattern of spectral information extracted from the mango plant images can influence the performance result of the classification model. Besides that, the starting point of the Digitization Footprint for this study site across the development stages of the classification model was 308.5756 MB/ha. Finally, the overall accuracy performances for the classification models that used the transfer learning algorithms, which were InceptionV3, DenseNet121, and ResNet50, and trained using the images of the mango plant infected with pest were 96.49 %, 92.98 %, and 89.47 %, respectively, and for using the images of the mango plant not infected with pest were 88.10 %, 78.57 %, and 69.05 %, respectively.

A Deep Learning Based Soil Type Classification and Recommendation of Crops to the Soil Type

Accurate classification of soil surface texture plays a pivotal role in agriculture, environmental management, and land-use planning. However, the classification of soil textures from RGB images obtained under uncontrolled field conditions remains a challenging task due to the inherent complexities of natural environments. In this study, we propose a novel approach for Soil Surface Texture Classification using Convolutional Neural Networks to address these challenges.