Neighborhood Component Analysis Research Articles

Deep Learning-Based Acoustic Emission Signal Filtration Model in Reinforced Concrete

AbstractAcoustic emission is a nondestructive testing (NDT) technique, widely used to monitor the condition of structures for safety reasons especially in real time. The method utilizes the electrical signals generated by the elastic waves in a material under load to detect and locate damage in structures. However, identifying the sources of AE signals in concrete or composite materials can be challenging due to the anisotropic properties of materials and interpreting a large amount of AE data, leading to data misinterpretation and inaccurate detection of damage. Hence, the need for filtering out noise-induced signals from recorded data and emphasizing the actual AE source is crucial for monitoring and source localization of damage in real time. This study proposed a one-dimensional convolutional neural network (1D-CNN) deep learning approach to filter around 22,000 AE data in a reinforced concrete (RC) beam. The model utilizes significant AE parameters identified through neighborhood component analysis (NCA) to classify true AE signals from noise-induced signals. By using the optimized network parameters, a high classification accuracy of 97% and 96.29% was achieved during the training and testing phases, respectively. To check the reliability of the proposed AE filtering model in the real world, it was evaluated and verified using source location AE activities collected during a four-point bending test on a shear-deficient beam. The outcomes suggest that the proposed AE filtration model has the potential to accurately classify AE signals with an accuracy of 92.8% and proved that the filtration model provides accurate and valuable insight into source location determination.

Study on Temperature Cascade ELM Inversion Method for 110 kV Single-Core Cable Intermediate Joints

The accurate calculation of the hotspot temperature of the cable intermediate joint can effectively guarantee the safe operation of the transmission and distribution network. This paper addresses the limitations of the current method of estimating hotspot temperature solely from surface temperature measurements. Specifically, we focus on a 110 kV single-core cable as our subject of study. We started by establishing a simulation model for the temperature field at the intermediate joint to generate data samples. Subsequently, the NCA (neighborhood component analysis) algorithm was employed to select the optimal measurement points on the cable’s surface. This allowed determination of the quantity and location of characteristic points. Finally, we developed a cascading inversion model, which consists of a radial inversion model and an axial inversion model, based on the extreme learning machine algorithm. The example results show that the mean squared error of hotspot temperature obtained by cascade inversion and direct inversion is 6.95 and 24.71, respectively, indicating that cascade inversion can effectively improve the inversion accuracy.

Novel hybrid classifier based on fuzzy type-III decision maker and ensemble deep learning model and improved chaos game optimization

AbstractThis paper presents a unique hybrid classifier that combines deep neural networks with a type-III fuzzy system for decision-making. The ensemble incorporates ResNet-18, Efficient Capsule neural network, ResNet-50, the Histogram of Oriented Gradients (HOG) for feature extraction, neighborhood component analysis (NCA) for feature selection, and Support Vector Machine (SVM) for classification. The innovative inputs fed into the type-III fuzzy system come from the outputs of the mentioned neural networks. The system’s rule parameters are fine-tuned using the Improved Chaos Game Optimization algorithm (ICGO). The conventional CGO’s simple random mutation is substituted with wavelet mutation to enhance the CGO algorithm while preserving non-parametricity and computational complexity. The ICGO was evaluated using 126 benchmark functions and 5 engineering problems, comparing its performance with well-known algorithms. It achieved the best results across all functions except for 2 benchmark functions. The introduced classifier is applied to seven malware datasets and consistently outperforms notable networks like AlexNet, ResNet-18, GoogleNet, and Efficient Capsule neural network in 35 separate runs, achieving over 96% accuracy. Additionally, the classifier’s performance is tested on the MNIST and Fashion-MNIST in 10 separate runs. The results show that the new classifier excels in accuracy, precision, sensitivity, specificity, and F1-score compared to other recent classifiers. Based on the statistical analysis, it has been concluded that the ICGO and propose method exhibit significant superiority compared to the examined algorithms and methods. The source code for ICGO is available publicly at https://nimakhodadadi.com/algorithms-%2B-codes. Graphical abstract

Mitigating Missing Rate and Early Cyberattack Discrimination Using Optimal Statistical Approach with Machine Learning Techniques in a Smart Grid

In the Industry 4.0 era of smart grids, the real-world problem of blackouts and cascading failures due to cyberattacks is a significant concern and highly challenging because the existing Intrusion Detection System (IDS) falls behind in handling missing rates, response times, and detection accuracy. Addressing this problem with an early attack detection mechanism with a reduced missing rate and decreased response time is critical. The development of an Intelligent IDS is vital to the mission-critical infrastructure of a smart grid to prevent physical sabotage and processing downtime. This paper aims to develop a robust Anomaly-based IDS using a statistical approach with a machine learning classifier to discriminate cyberattacks from natural faults and man-made events to avoid blackouts and cascading failures. The novel mechanism of a statistical approach with a machine learning (SAML) classifier based on Neighborhood Component Analysis, ExtraTrees, and AdaBoost for feature extraction, bagging, and boosting, respectively, is proposed with optimal hyperparameter tuning for the early discrimination of cyberattacks from natural faults and man-made events. The proposed model is tested using the publicly available Industrial Control Systems Cyber Attack Power System (Triple Class) dataset with a three-bus/two-line transmission system from Mississippi State University and Oak Ridge National Laboratory. Furthermore, the proposed model is evaluated for scalability and generalization using the publicly accessible IEEE 14-bus and 57-bus system datasets of False Data Injection (FDI) attacks. The test results achieved higher detection accuracy, lower missing rates, decreased false alarm rates, and reduced response time compared to the existing approaches.

Impacts of Feature Selection on Predicting Machine Failures by Machine Learning Algorithms

In the context of Industry 4.0, managing large amounts of data is essential to ensure informed decision-making in intelligent production environments. It enables, for example, predictive maintenance, which is essential for anticipating and identifying causes of failures in machines and equipment, optimizing processes, and promoting proactive management of human, financial, and material resources. However, generating accurate information for decision-making requires adopting suitable data preprocessing and analysis techniques. This study explores the identification of machine failures based on synthetic industrial data. Initially, we applied the feature selection techniques Principal Component Analysis (PCA), Minimum Redundancy Maximum Relevance (mRMR), Neighborhood Component Analysis (NCA), and Denoising Autoencoder (DAE) to the collected data and compared their results. In the sequence, a comparison among three widely known machine learning classifiers, namely Random Forest (RF), Support Vector Machine (SVM), and Multilayer Perceptron neural network (MLP), was conducted, with and without considering feature selection. The results showed that PCA and RF were superior to the other techniques, allowing the classification of failures with rates of 0.98, 0.97, and 0.98 for the accuracy, precision, and recall metrics, respectively. Thus, this work contributes by solving an industrial problem and detailing techniques to identify the most relevant variables and machine learning algorithms for predicting machine failures that negatively impact production planning. The findings provided by this study can assist industries in giving preference to employing sensors and collecting data that can contribute more effectively to machine failure predictions.

Gold cyanide leaching recovery prediction model based on neighbourhood component analysis and artificial intelligence technique

Gold cyanide leaching recovery prediction model based on neighbourhood component analysis and artificial intelligence technique

Lattice 123 pattern for automated Alzheimer’s detection using EEG signal

AbstractThis paper presents an innovative feature engineering framework based on lattice structures for the automated identification of Alzheimer's disease (AD) using electroencephalogram (EEG) signals. Inspired by the Shannon information entropy theorem, we apply a probabilistic function to create the novel Lattice123 pattern, generating two directed graphs with minimum and maximum distance-based kernels. Using these graphs and three kernel functions (signum, upper ternary, and lower ternary), we generate six feature vectors for each input signal block to extract textural features. Multilevel discrete wavelet transform (MDWT) was used to generate low-level wavelet subbands. Our proposed model mirrors deep learning approaches, facilitating feature extraction in frequency and spatial domains at various levels. We used iterative neighborhood component analysis to select the most discriminative features from the extracted vectors. An iterative hard majority voting and a greedy algorithm were used to generate voted vectors to select the optimal channel-wise and overall results. Our proposed model yielded a classification accuracy of more than 98% and a geometric mean of more than 96%. Our proposed Lattice123 pattern, dynamic graph generation, and MDWT-based multilevel feature extraction can detect AD accurately as the proposed pattern can extract subtle changes from the EEG signal accurately. Our prototype is ready to be validated using a large and diverse database.

Load Recognition in Home Energy Management Systems Based on Neighborhood Components Analysis and Regularized Extreme Learning Machine.

Efficient energy management in residential environments is a constant challenge, in which Home Energy Management Systems (HEMS) play an essential role in optimizing consumption. Load recognition allows the identification of active appliances, providing robustness to the HEMS. The precise identification of household appliances is an area not completely explored. Gaps like improving classification performance through techniques dedicated to separability between classes and models that achieve enhanced reliability remain open. This work improves several aspects of load recognition in HEMS applications. In this research, we adopt Neighborhood Component Analysis (NCA) to extract relevant characteristics from the data, seeking the separability between classes. We also employ the Regularized Extreme Learning Machine (RELM) to identify household appliances. This pioneering approach achieves performance improvements, presenting higher accuracy and weighted F1-Score values-97.24% and 97.14%, respectively-surpassing state-of-the-art methods and enhanced reliability according to the Kappa index, i.e., 0.9388, outperforming competing classifiers. Such evidence highlights the promising potential of Machine Learning (ML) techniques, specifically NCA and RELM, to contribute to load recognition and energy management in residential environments.

ECG Feature Importance Rankings: Cardiologists vs. Algorithms.

Feature importance methods promise to provide a ranking of features according to importance for a given classification task. A wide range of methods exist but their rankings often disagree and they are inherently difficult to evaluate due to a lack of ground truth beyond synthetic datasets. In this work, we put feature importance methods to the test on real-world data in the domain of cardiology, where we try to distinguish three specific pathologies from healthy subjects based on ECG features comparing to features used in cardiologists' decision rules as ground truth. We found that the SHAP and LIME methods and Chi-squared test all worked well together with the native Random forest and Logistic regression feature rankings. Some methods gave inconsistent results, which included the Maximum Relevance Minimum Redundancy and Neighbourhood Component Analysis methods. The permutation-based methods generally performed quite poorly. A surprising result was found in the case of left bundle branch block, where T-wave morphology features were consistently identified as being important for diagnosis, but are not used by clinicians.

CNN‐based defect detection in manufacturing

AbstractThis research introduces an advanced algorithm based on convolutional neural networks for the detection and categorization of surface defects in manufacturing processes. At its core, the algorithm employs a deep learning model that integrates residual networks and attention mechanisms to effectively extract features. Additionally, we have developed a novel feature selection method, named NR, which synergistically combines neighborhood component analysis and ReliefF techniques. This approach enables the selection of more representative deep features for subsequent analysis. For the classification task, we utilize the support vector machine technique, which demonstrates versatility in handling both binary and multi‐class classification scenarios. The reliability and superiority of our algorithm are further validated through a comparative analysis using a dataset specifically tailored for this context. The results indicate that our approach outperforms existing algorithms in accurately identifying manufacturing defects.

FLP: Factor lattice pattern-based automated detection of Parkinson's disease and specific language impairment using recorded speech

BackgroundTimely detection of neurodevelopmental and neurological conditions is crucial for early intervention. Specific Language Impairment (SLI) in children and Parkinson's disease (PD) manifests in speech disturbances that may be exploited for diagnostic screening using recorded speech signals. We were motivated to develop an accurate yet computationally lightweight model for speech-based detection of SLI and PD, employing novel feature engineering techniques to mimic the adaptable dynamic weight assignment network capability of deep learning architectures. Materials and methodsIn this research, we have introduced an advanced feature engineering model incorporating a novel feature extraction function, the Factor Lattice Pattern (FLP), which is a quantum-inspired method and uses a superposition-like mechanism, making it dynamic in nature. The FLP encompasses eight distinct patterns, from which the most appropriate pattern was discerned based on the data structure. Through the implementation of the FLP, we automatically extracted signal-specific textural features. Additionally, we developed a new feature engineering model to assess the efficacy of the FLP. This model is self-organizing, producing nine potential results and subsequently choosing the optimal one. Our speech classification framework consists of (1) feature extraction using the proposed FLP and a statistical feature extractor; (2) feature selection employing iterative neighborhood component analysis and an intersection-based feature selector; (3) classification via support vector machine and k-nearest neighbors; and (4) outcome determination using combinational majority voting to select the most favorable results. ResultsTo validate the classification capabilities of our proposed feature engineering model, designed to automatically detect PD and SLI, we employed three speech datasets of PD and SLI patients. Our presented FLP-centric model achieved classification accuracy of more than 95% and 99.79% for all PD and SLI datasets, respectively. ConclusionsOur results indicate that the proposed model is an accurate alternative to deep learning models in classifying neurological conditions using speech signals.

Enhancing lane changing trajectory prediction on highways: A heuristic attention-based encoder-decoder model

Accurate prediction of lane changing (LC) trajectories plays a vital role in ensuring safe and efficient traffic flow on highways. This paper proposes a LC trajectory prediction model based on encoder-decoder architecture to address low long-term prediction accuracy problem and to gain insight into the underlying motivations of LC behavior. Three specific enhancements were proposed to improve the performance of encoder-decoder. The first enhancement involves the utilization of Neighborhood Component Analysis (NCA) to identify the most relevant input features from driving environment. The second enhancement involves the introduction of heuristic attention to capture intricate time-dependent and environment-dependent patterns of input data. Finally, a trajectory check module was proposed to supervise and adjust the prediction outputs based on vehicle dynamics constraints. The proposed model was trained and evaluated using the HighD dataset. Experimental results demonstrated that the proposed model outperforms improved encoder-decoder architectures designed by previous studies in terms of prediction accuracy in long-term prediction, which the lateral and longitude MAE were 0.041 m and 1.842 m in 5 s prediction duration, respectively. Additionally, it was observed that preceding vehicles in the current and target lane, and following vehicle in the target lane, exert a significantly influential effect on LC maneuvers, which represents the underlying motivations behind LC behavior. The findings of this study contribute to the advancement of intelligent transportation systems (ITS) and autonomous vehicles (AVs) by providing an effective LC trajectory prediction.

Projector deep feature extraction-based garbage image classification model using underwater images

AbstractMarine and ocean pollution is one of the most serious environmental problems in the world. Marine plastics pose a significant threat to the marine ecosystem due to their negative effects. After passing through various processes, plastic waste accumulates on the seafloor and fragments into very small pieces known as microplastics. These microplastics are to blame for the extinction and death of aquatic life. This study obtained a hybrid underwater dataset containing 13,089 images, sized 300 × 300, including garbage and sea animals. In the proposed method, this dataset is used to develop our example projector deep feature generator. In this study, using the Resnet101 network in a sample projector build, the feature generator creates 6,000 features. Using NCA (Neighborhood Component Analysis), the best 1000 features from a pool of 6,000 are selected. The kNN (k-nearest neighbor) algorithm is then used to classify the resulting feature vectors. As validation techniques, both tenfold cross-validations were used. The hybrid dataset's best accuracy was calculated to be 99.35%. Our recommendation is successful based on the comparisons and calculated performance measures.

Automatic detection of knee osteoarthritis grading using artificial intelligence‐based methods

AbstractOsteoarthritis (OA) means that the slippery cartilage tissue that covers the bone surfaces in the joints and allows the joint to move easily loses its properties and wears out. Knee OA is the wear and tear of the cartilage in the knee joint. Knee OA is a disease whose incidence increases especially after a certain age. Knee OA is difficult and costly to be detected by specialists using traditional methods and may lead to misdiagnosis. In this study, computer‐aided systems were used to prevent errors in traditional methods of detecting knee OA, shorten the diagnosis time, and accelerate the treatment process. In this study, a hybrid model was developed by using Darknet53, Histogram of Directional Gradients (HOG), Local Binary Model (LBP) methods for feature extraction, and Neighborhood Component Analysis (NCA) for feature selection. Our dataset used in experiments contains 1650 knee joint images and consists of five classes: Normal, Doubtful, Mild, Moderate, and Severe. In the experimental studies performed, the performance of the proposed method was compared with eight different Convolutional Neural Networks (CNN) Models. The developed model achieved better performance metrics than the eight different models used in the study and similar studies in the literature. The accuracy value of the developed model is 83.6%.

Black-white hole pattern: an investigation on the automated chronic neuropathic pain detection using EEG signals

AbstractElectroencephalography (EEG) signals provide information about the brain activities, this study bridges neuroscience and machine learning by introducing an astronomy-inspired feature extraction model. In this work, we developed a novel feature extraction function, black-white hole pattern (BWHPat) which dynamically selects the most suitable pattern from 14 options. We developed BWHPat in a four-phase feature engineering model, involving multileveled feature extraction, feature selection, classification, and cortex map generation. Textural and statistical features are extracted in the first phase, while tunable q-factor wavelet transform (TQWT) aids in multileveled feature extraction. The second phase employs iterative neighborhood component analysis (INCA) for feature selection, and the k-nearest neighbors (kNN) classifier is applied for classification, yielding channel-specific results. A new cortex map generation model highlights the most active channels using median and intersection functions. Our BWHPat-driven model consistently achieved over 99% classification accuracy across three scenarios using the publicly available EEG pain dataset. Furthermore, a semantic cortex map precisely identifies pain-affected brain regions. This study signifies the contribution to EEG signal classification and neuroscience. The BWHPat pattern establishes a unique link between astronomy and feature extraction, enhancing the understanding of brain activities.

MNPDenseNet: Automated Monkeypox Detection Using Multiple Nested Patch Division and Pretrained DenseNet201

Abstract Background Monkeypox is a viral disease caused by the monkeypox virus (MPV). A surge in monkeypox infection has been reported since early May 2022, and the outbreak has been classified as a global health emergency as the situation continues to worsen. Early and accurate detection of the disease is required to control its spread. Machine learning methods offer fast and accurate detection of COVID-19 from chest X-rays, and chest computed tomography (CT) images. Likewise, computer vision techniques can automatically detect monkeypoxes from digital images, videos, and other inputs. Objectives In this paper, we propose an automated monkeypox detection model as the first step toward controlling its global spread. Materials and method A new dataset comprising 910 open-source images classified into five categories (healthy, monkeypox, chickenpox, smallpox, and zoster zona) was created. A new deep feature engineering architecture was proposed, which contained the following components: (i) multiple nested patch division, (ii) deep feature extraction, (iii) multiple feature selection by deploying neighborhood component analysis (NCA), Chi2, and ReliefF selectors, (iv) classification using SVM with 10-fold cross-validation, (v) voted results generation by deploying iterative hard majority voting (IHMV) and (vi) selection of the best vector by a greedy algorithm. Results Our proposal attained a 91.87% classification accuracy on the collected dataset. This is the best result of our presented framework, which was automatically selected from 70 generated results. Conclusions The computed classification results and findings demonstrated that monkeypox could be successfully detected using our proposed automated model.

Use of psychoacoustic spectrum warping, decision template fusion, and neighborhood component analysis in newborn cry diagnostic systems.

Dealing with newborns' health is a delicate matter since they cannot express needs, and crying does not reflect their condition. Although newborn cries have been studied for various purposes, there is no prior research on distinguishing a certain pathology from other pathologies so far. Here, an unsophisticated framework is proposed for the study of septic newborns amid a collective of other pathologies. The cry was analyzed with music inspired and speech processing inspired features. Furthermore, neighborhood component analysis (NCA) feature selection was employed with two goals: (i) Exploring how the elements of each feature set contributed to classification outcome; (ii) investigating to what extent the feature space could be compacted. The attained results showed success of both experiments introduced in this study, with 88.66% for the decision template fusion (DTF) technique and a consistent enhancement in comparison to all feature sets in terms of accuracy and 86.22% for the NCA feature selection method by drastically downsizing the feature space from 86 elements to only 6 elements. The achieved results showed great potential for identifying a certain pathology from other pathologies that may have similar effects on the cry patterns as well as proving the success of the proposed framework.

Can You Understand Why I Am Crying? A Decision-making System for Classifying Infants’ Cry Languages Based on DeepSVM Model

Scientific and therapeutic advances in perinatology and neonatology have improved the survival prospects of preterm and extremely-low-birth-weight infants. Infants’ cries are a valuable noninvasive tool for monitoring their neurologic health, especially if they are premature. Automatic acoustic analysis and data mining are employed in this study to determine the discriminative features of preterm and full-term infant cries. The use of machine learning for recognizing sounds in a newborn's cry language has received less attention than previous methods for analyzing the sounds. Moreover, to extract appropriate features from infant cries, adequate knowledge and appropriate signal descriptors are required. Accordingly, to analyze infant cry language, we propose an approach that uses fractal descriptors to extract discriminant features from spectrograms of windowed signals, followed by iterative neighborhood component analysis (iNCA) to select appropriate features. Additionally, the improved deep support vector machine (DeepSVM) is used to classify the infants’ crying types and their meanings. The proposed method is verified using a newborn sound dataset. According to the classification of five types of crying perception based on various characteristics, 98.34% of all crying perceptions have been recognized. Although there are many classes examined, the feature extraction method based on the fractal method and our optimal classification have a much higher diagnostic accuracy compared with similar methods for analyzing baby crying language. The proposed method can overcome many problems associated with analyzing babies’ crying sounds and understanding their language, such as uncertainty and unusual errors in classification.

Developing a robust two-step machine learning multiclassification pipeline to predict primary site in head and neck carcinoma from lymph nodes

This study aimed to develop a robust multiclassification pipeline to determine the primary tumor location in patients with head and neck carcinoma of unknown primary using radiomics and machine learning techniques. The dataset included 400 head and neck cancer patients with primary tumor in oropharynx, OPC (n = 162), nasopharynx, NPC (n = 137), oral cavity, OC (n = 63), larynx and hypopharynx, HL (n = 38). Two radiomic-based multiclassification pipelines (P1 and P2) were developed. P1 consisted in a direct identification of the primary sites, whereas P2 was based on a two-step approach: in the first step, the number of classes was reduced by merging the two minority classes which were reclassified in the second step. Diverse correlation thresholds (0.75, 0.80, 0.85), feature selection methods (sequential forwards/backwards selection, sequential floating forward selection, neighborhood component analysis and minimum redundancy maximum relevance), and classification models (neural network, decision tree, naïve Bayes, bagged trees and support vector machine) were assessed. P2 outperformed P1, with the best results obtained with the support vector machine classifier including radiomic and clinical features (accuracies of 75.3 % (HL), 75.4 % (OC), 71.3 % (OPC), 92.9 % (NPC)). These results indicate that the two-step multiclassification pipeline integrating radiomics and clinical information is a promising approach to predict the tumor site of unknown primary.

A no-reference image quality assessment model based on neighborhood component analysis and Gaussian process

In this paper, a human visual system (HVS) based no-reference image quality assessment model (NR-IQA) is proposed. This is an objective NR-IQA model that uses perceptual features such as structure and orientation to compute the loss of naturalness in the image. An adaptive feature extraction process is modeled to capture the underlying significant features of the images along with the noise. Moreover, the optimal subset of features is derived using the neighborhood component analysis and further used as inputs to the Gaussian process for regression. The various experimentations are carried out on LIVE, TID2008, and TID2013 databases to test the effectiveness of the proposed approach. It is observed that the presented model exhibits a competitive performance in comparison with the existing IQA approaches. Moreover, the computation complexity and run-time show the effectuality of the proposed approach. Further, the experiments show that the predicted score matches with human perceptions. Thus, the proposed model is more accurate, less complex, independent of distortions, and well-suited for real-time applications.