Ideal Feature Research Articles

Camera-aware graph multi-domain adaptive learning for unsupervised person re-identification

Recently, unsupervised person re-identification (Re-ID) has gained much attention due to its important practical significance in real-world application scenarios without pairwise labeled data. A key challenge for unsupervised person Re-ID is learning discriminative and robust feature representations under cross-camera scene variation. Contrastive learning approaches treat unsupervised representation learning as a dictionary look-up task. However, existing methods ignore both intra- and inter-camera semantic associations during training. In this paper, we propose a novel unsupervised person Re-ID framework, Camera-Aware Graph Multi-Domain Adaptive Learning (CGMAL), which can conduct multi-domain feature transfer with semantic propagation for learning discriminative domain-invariant representations. Specifically, we treat each camera as a distinct domain and extract image samples from every camera domain to form a mini-batch. A heterogeneous graph is constructed for representing the relationships between all instances in a mini-batch. Then a Graph Convolutional Network (GCN) is employed to fuse the image samples into a unified space and implement promising semantic transfer for providing ideal feature representations. Subsequently, we construct the memory-based non-parametric contrastive loss to train the model. In particular, we design an adversarial training scheme for transferring the knowledge learned by GCN to the feature extractor. Experimental experiments on three benchmarks validate that our proposed approach is superior to the state-of-the-art unsupervised methods.

True Random Number Generator Based on Chaotic Oscillation of a Tunable Double-Well MEMS Resonator.

Chaotic systems have aroused interest across various scientific disciplines such as physics, biology, chemistry, and meteorology. The deterministic but unpredictable nature of a chaotic system is an ideal feature for random number generation. Microelectromechanical systems (MEMS) are a promising technology that effectively harnesses chaos, offering advantages such as a compact footprint, scalability, and low power consumption. This paper presents a true random number generator (TRNG) based on a double-well MEMS resonator integrated with an actuator and position sensor. The potential energy landscape of the proposed MEMS resonator is actively tunable with a direct current voltage. Experimental demonstrations of tunable bistability and chaotic resonance are reported in this paper. A chaotic time sequence is generated through piezoresistive sensing of the position of the MEMS resonator once it is driven into the chaotic regime. Subsequently, the randomness of the bit sequence, achieved by applying the exclusive or function to a digital chaotic sequence and its delayed differential is confirmed to meet the National Institute of Standards and Technology specifications. Moreover, the throughput and energy efficiency of the proposed MEMS-based TRNG can be adjusted from 50 kb s-1 and 0.44 pJ per bit at a low energy barrier to 167 kb s-1 and 6.74 pJ per bit at a high energy barrier by changing the MEMS device's potential well. The tunability of the proposed double-well MEMS resonator not only offers continuous adjustments in the energy efficiency of TNRG but also unveils vast and diverse research opportunities in analog computing, encryption, and secure communications.

Classification and Analysis of HIV Neurocognitive MRI Images using Support Vector Machine

Medical imaging has expanded thanks to advances in processing power and advanced image analysis techniques, especially with magnetic resonance imaging (MRI), which offers comprehensive body scans for diagnosis. This work proposes a simple yet efficient method to use a support vector machine (SVM) to classify HIV neurocognitive MRI pictures into normal and pathological categories. The model consists of four steps: data pre-processing, feature extraction, SVM classification, and model evaluation. To separate desired and undesired elements, such as the scalp and skull, pre-processed images were converted from grayscale to colour using support vector machines. The discrete wavelet transform (DWT) was used in the feature extraction stage to extract image properties. Colour moments (CMs) were then used to optimize the feature collection. Afterwards, the SVM classifier was used to determine the ideal feature set to classify images. For example, a dataset is used for training and testing, with a split ratio of 75% to 25% respectively. The experimental results show that the proposed model has a high classification accuracy of 94.4%

The Extraction of Roof Feature Lines of Traditional Chinese Village Buildings Based on UAV Dense Matching Point Clouds

Traditional Chinese buildings serve as a carrier for the inheritance of traditional culture and national characteristics. In the context of rural revitalization, achieving the 3D reconstruction of traditional village buildings is a crucial technical approach to promoting rural planning, improving living environments, and establishing digital villages. However, traditional algorithms primarily target urban buildings, exhibiting limited adaptability and less ideal feature extraction performance for traditional residential buildings. As a result, guaranteeing the accuracy and reliability of 3D models for different types of traditional buildings remains challenging. In this paper, taking Jingping Village in Western Hunan as an example, we propose a method that combines multiple algorithms based on the slope segmentation of the roof to extract feature lines. Firstly, the VDVI and CSF algorithms are used to extract the building and roof point clouds based on the MVS point cloud. Secondly, according to roof features, village buildings are classified, and a 3D roof point cloud is projected into 2D regular grid data. Finally, the roof slope is segmented via slope direction, and internal and external feature lines are obtained after refinement through Canny edge detection and Hough straight line detection. The results indicate that the CSF algorithm can effectively extract the roofs of I-shaped, L-shaped, and U-shaped traditional buildings. The accuracy of roof surface segmentation based on slope exceeds 99.6%, which is significantly better than the RANSAC algorithm and the region segmentation algorithm. This method is capable of efficiently extracting the characteristic lines of roofs in low-rise buildings within traditional villages. It provides a reference method for achieving the high-precision modeling of traditional village architecture at a low cost and with high efficiency.

Nanoemulsions a Delivery System in the Making for Tumor Targeting Therapeutics: Evaluation and Characterization to Meet Clinical Challenges.

Cancer is a complex disease characterized by the uncontrolled and unregulated growth of cells followed by invasion and proliferation from the site of origin to other sites of the body. Conventional chemotherapy largely kills rapidly expanding and dividing cancer cells by impairing DNA synthesis and mitosis. It is associated with various types of adverse effects ranging from simple nausea and appetite loss to serious ones like bone marrow depression and compromised immunity etc., due to their non-selectivity and inability to differentiate. The ideal feature of a delivery system is delivering the drug to the target place to achieve the most therapeutic impact while having the least toxicity. With the advent of novel drug delivery systems, it has been easier to deliver the drug to the target site. Utilizing new techniques and technology makes it a feasible approach to target cancer cells. Nanoemulsions are isotropic mixtures of transparent or translucent oil globules dispersed in an aqueous phase that is kinetically stable and supported by an interfacial coating of surfactant and co-surfactant molecules with droplet sizes in the nanometre range. Nanoemulsions are the delivery system of choice in case of cancer because of certain key attributes, including biodegradability, biocompatibility, large surface area nonimmunogenicity, and release behavior control. At the same time, nanoemulsions have been engineered for various reasons, including enhanced biological half-life, target-specific binding ability, and imaging capability at different therapy levels by modifying the characteristics of nanoemulsions. This review focuses on current cancer treatment challenges and the role of nanoemulsions in treating cancer with their production methods, characterization methods, application, and quality attributes, which would help them make it to the clinics where cancer treatment is going on.

Facile fabrication of polymeric-inorganic hybrid coated membrane with super-hydrophilic and underwater super-oleophobic properties for highly efficient crude oil-in-water emulsion separation

The oily wastewater is a huge wastewater stream that can potentially serve as an enormous source of clean water for water reuse applications such as groundwater recharge or irrigation. Given the huge potential of cleaning oily wastewater, we have developed an amino-functionalized nickel oxide nanoparticles coated inorganic-polymeric hybrid membrane with superhydrophilic and underwater superoleophobic properties for excellent crude oil-in-water (O/W) emulsion separation potential using a cross-flow filtration system. The use of ceramic alumina (Al2O3) support offers increased chemical, thermal, and mechanical stability while nickel oxide (NiO) decoration equips the membrane with special surface wettability to avoid membrane fouling. Moreover, the amino-functionalized NiO-coated polyamide network (F-NiO/PA) offers an active layer dense enough to separate the oil from water when the surfactant-stabilized crude oil-in-water emulsion was used as feed during separation experiments. Hence fabricated F-NiO/PA@Alumina membrane was studied by using different membrane characterization techniques to explore the features and understand the structure of F-NiO/PA@Alumina membrane. The F-NiO/PA@Alumina membrane possessed a superhydrophilic (water contact angle; θW, A = 0°) and underwater superoleophobic (oil contact angle; θO, W = 161°) surface wettability which is an ideal feature required for O/W emulsion separation. The F-NiO/PA@Alumina membrane demonstrated a high O/W emulsion separation efficiency of >99 % even with crude oil concentrations as high as 200 ppm using a cross-flow filtration system. The stability test of the separation performance of the F-NiO/PA@Alumina membrane also revealed a separation performance of >99 % for the duration of the test using a cross-flow filtration system.

G-ACP: a machine learning approach to the prediction of therapeutic peptides for gastric cancer

Conventional Gastrointestinal (GI) cancer treatments are quite expensive and have major hazards. Nowadays, a different strategy places more emphasis on creating tiny biologically active peptides that do not cause severe poisoning. Anticancer peptides (ACPs) are found through experimental screening, which is time-dependent and frequently fraught with difficulties. Gastric ACPs are emerging as a promising GI cancer treatment in the current day. It is crucial to identify novel gastric ACPs to have an improved knowledge of their functioning processes and treatment of gastric cancer. As a result of the post-genomic era’s massive production of peptide sequences, rapid and effective ACPs using a computational method are essential. Several adaptive statistical techniques for distinguishing ACPs and non-ACPs have recently been developed. A variety of adapted statistically significant methods have been developed to differentiate between ACPs and non-ACPs. Despite significant progress, there is no specific model for the prediction of gastric ACPs because the specific model will predict a particular type of peptide more accurately and quickly. To overcome this, an initiative is taken for the creation of a reliable framework for the accurate identification of gastric ACPs. The current technique in particular contains four possible features along with one hybrid feature encoding mechanisms which are the target-class motif previously indicated by Amino Acid Composition, Dipeptide Composition, Tripeptide Composition (TPC), Pseudo Amino Acid Composition (PAAC), and their Hybrid. Machine Learning algorithms make high-performance and accurate prediction tools. Moreover, highly variable and ideal deep feature selection is done using an ANOVA-based F score for feature pruning. Experiments on a range of algorithms are carried out to identify the optimal operating strategy due to the diverse nature of learning. Following analysis of the empirical results, Naïve Bayes with TPC and Hybrid feature space outperforms other methods with 0.99 accuracy score on the testing dataset. To find the model generalization an external validation is carried out. In external datasets, the Extra Trees with PAAC features outperforms with the accuracy of 0.94. The comparison study shows that our suggested model will predict gastric ACPs more accurately and will be useful in drug development and gastric cancer. The predictive model can be freely accessed at https://github.com/humeraazad10/G-ACP.git. Communicated by Ramaswamy H. Sarma

A Study of the Aesthetic Application of Machine Learning to Five Education in Classical Music Interpretation

Abstract With the application of machine learning to the teaching of classical music in the context of five education as the research objective, this study first tested the feature extraction performance and classification of classical music with specific classical music data. Secondly, it explored the changes in the three elements of song aesthetics before and after machine learning five-education music teaching in two academic periods and analyzed the teaching effect it had on the task completion time and rhythmic accuracy of the songs. The use of audio analysis software in terms of task completion time, rhythmic accuracy, and pitch accuracy dimensions produces quantitative teaching effect ratings. The results show that the method in this paper obtains ideal classical music classification and feature extraction results and the ratings of the music feature extraction algorithms are in line with the real level of teachers and students. The experimental group and the control group, after teaching music using machine learning, took a similar time to learn the task, but the difference in rhythmic accuracy was large. The highest IOI value of the experimental group is only 0.07439, and the overall average of the group’s satisfaction with the teaching effect has increased by 0.842. This paper’s method is conducive to the development and innovation of music teaching.

Sensitive Properties of Power Spectral Density Transmissibility (PSDT) to Moving Vehicles and Structural States in Bridge Health Monitoring

Bridge health monitoring confronts a critical challenge in extracting meaningful features that are sensitive to structural damage while remaining nonsensitive to operational environments and loads. Most of structural response features such as power spectral density (PSD) in the long‐term monitored bridge are influenced by operational vehicle loads. The power spectral density transmissibility (PSDT), defined as the power spectral density ratio of two measured output responses at two different structural locations with the same reference output response, converges independently at the system poles of the applied excitations and transferring outputs. Capitalizing on such a unique property of PSDT around the system poles, the PSDT‐based spectral moment is proposed in the paper to establish a robust structural feature in bridge health monitoring taking into account the time‐varying characteristics under operational vehicle loads. Numerical simulations and comparisons with PSD‐based spectral moment analysis reveal that the PSDT‐based spectral moment exhibits an enhanced robustness to traffic flow excitations and heightened sensitivity to changes in structural parameters. Further laboratory experimental results on the beam under moving vehicle confirm that the PSDT‐based spectral moment is less affected by moving vehicle loads, but it demonstrates higher sensitivity to structural parameter changes. Given its robust properties of low sensitivity to operational vehicle loads and sensitivity to changes in structural parameters, the proposed PSDT‐based spectral moment emerges as an ideal structural feature suitable for the effective applications in the long‐term bridge health monitoring, such as structural damage identification, model updating, condition assessment, and safety warning.

Numerical analysis of the thin film solar cell modelled based on In doped CdS semiconductor

In this study, pure and 1%, 2% and %3 In-doped CdS thin films were produced by spray pyrolysis method. CdS is an n-type (II-VI group) semiconductor material and used as a buffer layer in solar cells. By doping In into CdS thin film, it was investigated how optical and crystalline behavior of thin film are changed. Using Moss and Herve&Vandamme and Ravindra relations, refractive indices and dielectric coefficients were investigated depending on the band gap of the obtained CdS sample. It has been observed that In element decreases the band gap of CdS thin film, improved its crystal structure and reduced its roughness. Therefore, 3% In doped CdS has gained a more ideal feature for use as an n-type semiconductor in solar cells. CIGS/In doped CdS solar cell was modelled and analysed by SCAPS-1D simulation program by using the physical parameters of the semiconductor layers that make up solar cells as imputs of program. Photovoltaic parameters of solar cell based on donor defect density, the neutral interface defect density and Auger electron/hole capture coefficient which were calculated by using In %3 doped CdS thin film, which has the most ideal n-type semiconductor properties.

DETECTION OF CHRONIC VENOUS INSUFFICIENCY CONDITION USING TRANSFER LEARNING WITH CONVOLUTIONAL NEURAL NETWORKS BASED ON THERMAL IMAGES

Chronic Venous Insufficiency (CVI) is a venous incompetence condition that leads to improper blood circulation from the lower limbs towards the heart. This occurs as a result of blood pooling in the veins of the leg, resulting in twisted, dilated, and tortuous veins. Aging, obesity, prolonged standing or sitting, and lack of mobility are all important causes of the occurrence of this chronic disease. The cost of CVI diagnosis and treatment is extremely high. Infrared thermographic image analysis is used for early detection and reduces the cost of diagnosis. Deep learning (DL) techniques play an important role in early prediction and may aid clinicians in diagnosing CVI. An automated classification model will assist the physician in making a precise diagnosis of the abnormal vein and treating the patient according to the severity of the condition. There is a need for a model that can perform successful classification without the need for pre-processing when compared to the traditional machine learning (ML) methods that depend on ideal manual feature extraction to achieve optimal outcomes. In this research, we recommend the customized DenseNet-121 architecture for CVI detection and compare it with other advanced DL models to determine its efficacy. DenseNet-121 and other pre-trained convolutional neural network models, including EfficientNetB0 and Inception_v3, were trained using a transfer learning strategy. The experimental findings indicate that the proposed modified DenseNet-121 model outperformed other classical methods. The reported results provide evidence of the robustness of the suggested method in addition to the high accuracy that it possessed, as shown by the overall testing accuracy of 97.4%. Thus, this study can be considered as a non-invasive and cost-effective approach for diagnosing chronic venous insufficiency condition in lower extremity.

Suspension Type Base Isolation: For Seismic Impact Mitigation in High-Rise Buildings

Suspension Type Base Isolation (STBI) is a system where the base of a structure is literally suspended using suspenders. With STBI innovative design and construction, significant reduction in seismic impact could be achieved in all heights of structures from low-rise, mid-rise, to high-rise ones. The significant reduction in impact can be observed in reduced structure’s displacement, acceleration, and base shear of structure during earthquake events. The structural and mechanical design of the STBI is especially suited for high-rise structures. This new innovative system can handle uplift forces on columns caused by relatively large overturning moments in high-rise structures during seismic events. Most seismic isolators in use presently are not applicable for high-rise buildings. STBI is capable of mitigating seismic impact as could be observed in reduced structural displacement and acceleration by around 88% as compared to fixed-base structure even in strong earthquake events. Simply stated, if the earthquake intensity, for instance, is around 9, the structure will “feel” around intensity 5 only. Another ideal feature of STBI is its ability to allow the structure to sway back to its original position after every seismic event. This is called auto-centering which is initiated by the pull of gravity.

Peptide nucleic acid-zirconium coordination nanoparticles

Ideal drug carriers feature a high loading capacity to minimize the exposure of patients with excessive, inactive carrier materials. The highest imaginable loading capacity could be achieved by nanocarriers, which are assembled from the therapeutic cargo molecules themselves. Here, we describe peptide nucleic acid (PNA)-based zirconium (Zr) coordination nanoparticles which exhibit very high PNA loading of >,94% w/w. This metal-organic hybrid nanomaterial class extends the enormous compound space of coordination polymers towards bioactive oligonucleotide linkers. The architecture of single- or double-stranded PNAs was systematically varied to identify design criteria for the coordination driven self-assembly with Zr(IV) nodes at room temperature. Aromatic carboxylic acid functions, serving as Lewis bases, and a two-step synthesis process with preformation of Zr_{6} O_{4} (OH)_{4} turned out to be decisive for successful nanoparticle assembly. Confocal laser scanning microscopy confirmed that the PNA-Zr nanoparticles are readily internalized by cells. PNA-Zr nanoparticles, coated with a cationic lipopeptide, successfully delivered an antisense PNA sequence for splicing correction of the beta-globin intron mutation IVS2-705 into a functional reporter cell line and mediated splice-switching via interaction with the endogenous mRNA splicing machinery. The presented PNA-Zr nanoparticles represent a bioactive platform with high design flexibility and extraordinary PNA loading capacity, where the nucleic acid constitutes an integral part of the material, instead of being loaded into passive delivery systems.

Linear and Non-Linear Predictive Models in Predicting Motor Assessment Scale of Stroke Patients Using Non-Motorized Rehabilitation Device

Various predictive models, both linear and non-linear, such as Multiple Linear Regression (MLR), Partial Least Squares (PLS), and Artificial Neural Network (ANN), were frequently employed for predicting the clinical scores of stroke patients. Nonetheless, the effectiveness of these predictive models is somewhat impacted by how features are selected from the data to serve as inputs for the model. Hence, it's crucial to explore an ideal feature selection method to attain the most accurate prediction performance. This study primarily aims to evaluate the performance of two non-motorized three-degree-of-freedom devices, namely iRest and ReHAD using MLR, PLS and ANN predictive models and to examine the usefulness of including a hand grip function with the assessment device. The results reveal that ReHAD coupled with non-linear model (i.e. ANN) has a better prediction performance compared to iRest and at once proving that by including the hand grip function into the assessment device may increase the prediction accuracy in predicting Motor Assessment Scale (MAS) score of stroke subjects. Furthermore, these findings imply that there is a substantial association between kinematic variables and MAS scores, and as such the ANN model with a feature selection of twelve kinematic variables can predict stroke patients' MAS scores.

Efficient classification of kidney disease detection using Heterogeneous Modified Artificial Neural Network and Fruit Fly Optimization Algorithm

Chronic kidney disease (CKD), a significant issue for public health, affects millions of individuals globally. The course of end-stage renal disease must be stopped or reversed, hence it is crucial to find chronic kidney disease early in order to receive therapy. Prediction of CKD is a second source of treatment, as machine learning techniques, with their high classification accuracy, are becoming increasingly significant in medical diagnosis. To learn about CKD and associated issues in this situation, deep learning is used. The sole inputs used to construct the three distinct types of models were the retinal fundus image alone (test model), the covariate only (the reference model), and the retinal fundus image plus covariate (hybrid model). To maintain the accuracy of contemporary classification systems, feature selection techniques must be applied correctly in order to reduce data size. Here, recommend the Fruit fly optimisation algorithm (FFOA) and the heterogeneous artificial neural network (HMANN) in this paper for efficient disease categorization. An Internet of Medical Things (IoMT) platform is presented for the early detection, segmentation, and diagnosis of chronic renal failure using a heterogeneous modified artificial neural network (HMANN). The Multilayer Perceptron (MLP) and Support Vector Machine (SVM) algorithms are used to classify the suggested HMANN. The ideal feature is chosen using an FFOA from a large pool of candidate features. The proposed method uses ultrasound pictures as its foundation and, as a first step in processing, slices a region of interest in the kidney in the ultrasound image. The accuracy, sensitivity, specificity, positive predictive power, negative predictive power, false positive rate, and false negative rate of the suggested CKD classification system were all taken into consideration when evaluating its performance.

Enhancing feature selection with GMSMFO: A global optimization algorithm for machine learning with application to intrusion detection

Abstract The paper addresses the limitations of the Moth-Flame Optimization (MFO) algorithm, a meta-heuristic used to solve optimization problems. The MFO algorithm, which employs moths' transverse orientation navigation technique, has been used to generate solutions for such problems. However, the performance of MFO is dependent on the flame production and spiral search components, and the search mechanism could still be improved concerning the diversity of flames and the moths' ability to find solutions. The authors propose a revised version called GMSMFO, which uses a Novel Gaussian mutation mechanism and shrink MFO to enhance population diversity and balance exploration and exploitation capabilities. The study evaluates the performance of GMSMFO using the CEC 2017 benchmark and 20 datasets, including a high-dimensional intrusion detection system dataset. The proposed algorithm is compared to other advanced metaheuristics, and its performance is evaluated using statistical tests such as Friedman and Wilcoxon rank-sum. The study shows that GMSMFO is highly competitive and frequently superior to other algorithms. It can identify the ideal feature subset, improving classification accuracy and reducing the number of features used. The main contribution of this research paper includes the improvement of the exploration/exploitation balance and the expansion of the local search. The ranging controller and Gaussian mutation enhance navigation and diversity. The research paper compares GMSMFO with traditional and advanced metaheuristic algorithms on 29 benchmarks and its application to binary feature selection on 20 benchmarks, including intrusion detection systems. The statistical tests (Wilcoxon rank-sum and Friedman) evaluate the performance of GMSMFO compared to other algorithms. The algorithm source code is available at https://github.com/MohammedQaraad/GMSMFO-algorithm.

New Directions in the Applications of Rough Path Theory

This article provides a concise overview of some of the recent advances in the application of rough path theory to machine learning. Controlled differential equations (CDEs) are discussed as the key mathematical model to describe the interaction of a stream with a physical control system. A collection of iterated integrals known as the signature naturally arises in the description of the response produced by such interactions. The signature comes equipped with a variety of powerful properties rendering it an ideal feature map for streamed data. We summarise recent advances in the symbiosis between deep learning and CDEs, studying the link with RNNs and culminating with the Neural CDE model. We concluded with a discussion on signature kernel methods.

Employing FGP-3D, a Fully Gated and Anchored Methodology, to Identify Skeleton-Based Action Recognition

Recent years have seen an explosion in interest in and development of action recognition based on skeletal data. Contemporary methods using fully gated units can successfully extract characteristics from human skeletons by relying on the human topology that has been predefined. Despite advancements, fully gated unit-based techniques have trouble generalizing to other domains, particularly when dealing with various human topological structures. In this context, we introduce FGP-3D, a novel skeleton-based action recognition technique that can generalize across datasets while being effective at learning spatiotemporal features from human skeleton sequences. This is accomplished via a multi-head attention technique to learn an ideal dependence feature matrix from the uniform distribution. We next re-evaluate state-of-the-art techniques as well as the suggested novel descriptor FGP-3D in order to examine the cross-domain generalizability of skeleton-based action recognition in real-world video skeleton statistics. After being applied to commonly used action categorization datasets, experimental results demonstrate that the proposed FGP-3D, with pre-training, generalizes well and outperforms the state-of-the-art.

Application of Hybrid Model between the Technique for Order of Preference by Similarity to Ideal Solution and Feature Extractions for Bearing Defect Classification

This paper describes a development that offers new opportunities for detecting faulty bearings. Prioritization is based on the technique for order of preference by similarity to the ideal solution (TOPSIS) for the most discriminative features in the faulty bearing dataset. The proposed model is divided into three steps: feature extraction, feature selection, and classification. In feature extraction, variational mode decomposition (VMD) and fast Fourier transform (FFT) are used to extract features from the measured signal of the test motors and use the symmetrical uncertainty (SU) value for calculation, reducing the redundancy of data. In terms of feature selection, the TOPSIS method is used instead of the traditional filtering method, which is applied to analysis and decision making, and important features are selected from seven filtering methods. Finally, in order to validate the classification ability of the proposed model, k-nearest neighbors (KNN), support vector machine (SVM), and artificial neural networks (ANN) are used as independent classifiers. The effectiveness of the proposed model is evaluated by applying two bearing datasets, namely the current dataset of motor vibration signals and the dataset of bearing motors provided by Case Western Reserve University (CWRU). The results show that the comparison of the proposed model with other models shows the feasibility of this study.

One-Class Convolutional Neural Network (OC-CNN) Model for Rapid Bridge Damage Detection Using Bridge Response Data

This study proposes a numerical investigation for rapid bridge damage detection based on a semi-supervised deep learning (DL) model and a damage index (DI)-based Gaussian process. The proposed damage detection method uses bridge response data (acceleration and displacement data) from various damage scenarios within a simply supported girder bridge subjected to a two-axle moving vehicle load. As for semi-supervised learning, we used a one-class convolutional neural network (OC-CNN) model. This model combines a one-class (OC) classification algorithm with a simple one-dimensional convolutional neural network (1D CNN) configuration. The performance of the proposed OC-CNN model was evaluated through a numerical example of a vehicle-bridge coupling system. The proposed OC-CNN model trained using acceleration data showed promising results for different vehicle weights and speeds. These results offer confidence in using the prediction error loss of the proposed OC-CNN model as an ideal damage-sensitive feature for rapid bridge damage detection. In addition, the Gaussian process used in the DI can classify the prediction error losses resulting from the change induced by different damage severities (10%, 20%, and 30%) and different types of damage scenarios (single damage, double damages, and multiple damages). These results emphasize the potential of the proposed damage detection method to monitor the state of bridges in practical engineering.