Extraction Ability Research Articles

Submarine Landslide Identification Based on Improved DeepLabv3 with Spatial and Channel Attention

As one of the most destructive, hazardous, and frequent marine geohazards, correctly recognizing submarine landslides holds substantial importance for regional risk assessment, disaster prevention, and marine resource development. Many conventional approaches to prediction and mapping necessitate the involvement of expert insights, oversight, and extensive field investigations, which can result in significant time and effort invested in the prediction process. This paper focuses on employing a deep neural network semantic segmentation technique to detect submarine landslides to replace previous methods, such as numerical analysis and physical modeling, to predict and identify the landslide areas quickly. The peripheral zone of the western Iberian Sea is selected as the study area. Since the neural network image recognition task usually requires RGB images as input data, factors such as slope, hillshade, and elevation extracted from digital elevation model (DEM) data are used to synthesize RGB images through band synthesis methods, and the number and diversity of data are increased utilizing data enhancement. Based on the classical semantic segmentation model DeepLabV3, this paper proposes an improved deep learning method, which strengthens the ability of model feature extraction for complex situations by adding an attention mechanism module, improving the spatial pyramid pooling module, and improving the landslide intersection over union metric from 0.4257 to 0.5219 and the F1-score metric from 0.609 to 0.6631 to achieve effective identification of submarine landslides.

A model for suppressing stray light in astronomical images based on deep learning.

Wide-Field Small Aperture Telescopes (WFSAT) are widely used for surveilling space objects. Due to their wide-field of view (FOV) characteristics, these telescopes can cover a large areas of the sky at once, improving observation efficiency. However, a wide-field optical telescope is highly sensitive to external stray light (such as moonlight and thin clouds), which can significantly reduce the quality of observation data. In severe cases, it can cause the telescope to malfunction and inaccurately position the object. In response to this problem, this paper proposes a model for suppressing stray light in astronomical images based on deep learning: the Pyramid Deformable Large Kernel Attention (PD-LKA) Model. This model expands the receptive field through a pyramid structure, captures multi-scale features, and improves the model's robustness to various scales of stray light interference. Meanwhile, through the Deformable Large Kernel Attention (D-LKA), the model can more accurately locate and enhance the feature extraction ability in areas affected by stray light interference, thereby better suppressing stray light.Using simulated astronomical image pairs to train the model, the tests achieved a PSNR of up to 32.540 and an SSIM of up to 0.938. Finally, the model is applied to a image sequence with real stray light interference. The restored images undergo astronomical positioning and orbital association processing. The results show that the positioning accuracy of the object is better than 5 arcseconds. This indicates that the model proposed in this paper not only recovers the object and background stars but also effectively preserves their gray values, shapes, and positional information.

Efficient separation of methyl ethyl ketone and water azeotrope using hydrophobic amino acid ester ionic liquids

BackgroundMethyl ethyl ketone (MEK), an essential organic solvent, is commonly produced via the n-butene method, where water emerges as the principal impurity. The conventional distillation processes, which are necessitated by the azeotropic behavior between MEK and water, result in a substantial expenditure of energy. As a result, liquid-liquid extraction represents a promising alternative for energy-efficient separation. MethodsIn this work, three hydrophobic amino acid ester ionic liquids L-phenylalanine ethyl ester bis(trifluoromethylsulfonyl) imide ([Phe][NTf2]), L-leucine ethyl ester bis(trifluoromethylsulfonyl) imide ([Leu][NTf2]) and L-valine ethyl ester bis(trifluoromethylsulfonyl) imide ([Val][NTf2]) were utilized as extractants for separation of the binary azeotrope methyl ethyl ketone and water. The effects of extraction time, extraction temperature, mass ratio of MEK-water mixture to ionic liquid and initial concentration of MEK on extraction efficiency were investigated. Significant findingsThe results demonstrate that the ionic liquid [Phe][NTf2] exhibits superior extraction ability for the separation of the azeotrope methyl ethyl ketone and water. The maximum extraction yield of 99.86 % was achieved with the optimum extraction conditions of extraction time, 10 min, extraction temperature, 293.15 K, mass ratio of mixture to ionic liquid, 1:1 and initial concentration of MEK, 20 %. In addition, the relationship between the structure of ionic liquids and their extraction performance was revealed by quantum chemical calculations of ionic liquids with MEK and water. These ionic liquids were positioned as promising environmentally friendly alternatives to traditional organic solvents for the recovery of MEK from aqueous solutions, providing valuable insights for industrial applications.

Giant Centella asiatica, a novel cultivar rich in madecassoside and asiaticoside, suppresses α‑melanocyte‑stimulating hormone‑induced melanogenesis through MC1R binding.

The present study investigated the anti‑melanogenesis effects of Giant Centella asiatica (GCA), a new cultivator of Centella asiatica (CA) cataloged by the Korea Forest Service in 2022, and compared its efficacy with that of traditional CA. GCA has a high yield per unit area and enhanced antioxidant properties. The anti‑melanogenic effects of GCA were investigated using B16F10 melanoma cells and a 3D human skin‑equivalent model. Key molecular mechanisms were elucidated through western blotting, cAMP assays and molecular docking studies. Focus was addressed on the effect of GCA on skin whitening by comparing the ability of a GCA extract to inhibit melanin production in B16F10 melanoma cells and a 3D human skin‑equivalent model to that of CA. The results showed that the GCA extracts more effectively reduced melanin production, which was attributed to their higher content of two active components, madecassoside and asiaticoside. Further investigation revealed that GCA primarily inhibited melanogenesis through the PKA‑cAMP response element‑binding (CREB)‑microphthalmia‑associated transcription factor (MITF) axis, a key regulatory pathway in melanin synthesis. Notably, the present study, to the best of our knowledge, is the first to demonstrate that madecassoside and asiaticoside, the two principal compounds in GCA, directly bound to MC1R, which contributed to the significant skin‑whitening effects. Moreover, GCA reduced melanin production in a 3D human skin‑equivalent model, showing efficacy within a complex skin environment. These results demonstrated the superior effectiveness of GCA to that of CA for skin anti‑melanogenesis, indicating its potential as a promising natural material for targeting pigmentation disorders.

Synergistic Impact of Passivation and Efficient Hole Extraction on Phase Segregation in Mixed Halide Perovskites

AbstractThe interface between the hole transport layer (HTL) and perovskite in p‐i‐n perovskite solar cells (PSCs) plays a vital role in the device performance and stability. However, the impact of this interface on the vertical phase segregation of mixed halide perovskite remains insufficiently understood. This work systematically investigates the impact of chemical and electronic properties of HTL on vertical halide segregation of mixed‐halide perovskites. This work shows that incorporating a poly[bis(4‐phenyl) (2,4,6‐trimethylphenyl) amine] (PTAA)/CuIxBr1‐x bilayer as the HTL significantly suppresses light‐induced vertical phase segregation in MAPb(I0.7Br0.3)3. This work uses grazing‐incidence X‐ray diffraction (GIXRD) to capture the depth‐resolved composition change of MAPb(I0.7Br0.3)3 at the interface and within the bulk under illumination. By changing the illumination direction and the electronic properties of HTL, this work elucidates the roles of charge carrier extraction and interfacial defects on vertical phase segregation. The PTAA/CuIxBr1‐x bilayer, with its synergistic passivation and efficient hole extraction ability, stabilizes the interface and bulk of the mixed halide perovskite layer and prevents phase segregation. This work underscores that synergetic passivation and efficient hole extraction pack a more powerful punch for arresting the vertical phase segregation in mixed‐halide perovskite.

Wound-Healing Activity of Solvent Fractions and Antiinflammatory Activity of Crude Extract and Solvent Fractions of Acokanthera schimperi Schweinf (Apocynaceae) Leaves in Mice Model

BackgroundIn Ethiopia, Acokanthera schimperi is frequently used to treat wounds and other conditions. Nothing has been published to date on the anti-inflammatory properties of A. schimperi leaves or the wound-healing effects of solvent fractions, despite a report on the crude extract's ability to heal wounds being available in the literature. PurposeTherefore, this experiment has been initiated to look into the solvent fractions' ability to heal wounds and the anti-inflammatory properties of the A. schimperi leaf 80% methanol extract and its fractions in mice. Study designThe experimental study design was conducted to evaluate wound healing and the anti-inflammatory properties of the A. schimperi leaf 80% methanol extract and its fractions in mice. MethodsThe plant's leaf crude extract was fractionated using ethyl acetate, chloroform, and distilled water. The resulting fractions were then combined with a simple ointment base to make an ointment at 5% and 10% w/w. Next, using excision and incision wound models, the ointments' ability to promote wound healing was assessed. The excision model was utilised to estimate wound contraction and epithelization time, whereas the incision model was utilised to measure tensile strength. By dissolving 1% carrageenan in 0.9% saline (w/v) and giving oral dosages of the crude extract and solvent fractions (100, 200, and 400 mg/kg), the anti-inflammatory efficacy of the leaves was assessed concurrently with a carrageenan-induced hind paw edema model. ResultsSignificant wound healing activity was seen in both models in wounds treated with 5% and 10% (w/w) solvent fraction ointment, as shown by higher tissue breaking strength (with 51.38% maximum effect by 10% (w/w) ethyl acetate fraction ointment), shorter epithelization times (within 15.92 days by ethyl acetate fraction ointment 10%), and increased wound contraction (99.40% by ethyl acetate fraction ointment 10%). The extract (hydromethanolic) and solvent fractions also showed notable dose-related decreases in inflammation. ConclusionThe study's findings supported A. schimperi's traditional use as a wound healing agent by showing that the solvent fractions of the plant's leaves promoted wound healing, at least in part, through their anti-inflammatory effect.

A two-dimensional magnetotelluric deep learning inversion approach based on improved Dense Convolutional Network

Magnetotelluric (MT) inversion is an important means of MT data interpretation. The use of deep learning technology for MT inversion has attracted much attention because it is not limited to the initial model, avoids falling into local optimal solutions, and has the strong ability to process large amounts of data. However, obtaining highly reliable deep learning inversion results remains a challenge. In this paper, we have proposed a two-dimensional (2-D) MT inversion method based on the improved Dense Convolutional Network (DenseNet), with the aim of improving the reliability of the 2-D deep learning MT inversion results. First, the MARE2DEM is used to compute the 2-D MT forward responses when establishing the sample set. Then, an improved DenseNet is proposed by incorporating depthwise separable convolution in lieu of standard convolution within dense connection blocks, and embedding the attention mechanism. Depthwise separable convolution splits the standard convolution operation into depthwise and pointwise convolution, effectively capturing spatial features of input data and correlations between channels. Meanwhile, attention mechanism allows the network to assign varying degrees of importance (or attention) to different elements in a sequence of data, thus enhancing its ability of key feature extraction. This design not only retains the inherent feature reuse and alleviates gradient vanishing of DenseNet but also further enhances network performance. The optimized network parameters for the improved DenseNet are obtained by training on the training set, while the validation set is used to adjust hyperparameters and evaluate model performance. Finally, the proposed 2-D deep learning approach is verified by using both synthetic and field data. Experimental results with synthetic data show that the reliability of inversion results obtained by using the proposed algorithm is improved, and the inversion results obtained by using both TE- and TM-mode data is more accurate than those obtained by using the single mode data. The inversion results of field data show that the proposed 2-D MT deep learning inversion approach can effectively detect the subsurface resistivity structure and has a good application prospect.

Improvement of visual servo system of industrial robot based on sliding mode control and deep reinforcement learning

Abstract. Visual servo system is more and more widely used in the field of industrial robots because it allows robots to sense external signals through sensors to convey control commands to themselves and complete tasks. However, the traditional visual servo has many limitations in the design of controller and image feature extraction, such as insufficient robustness and image extraction accuracy. This research focuses on the optimization of controller and image feature extraction, which can improve the overall performance and autonomy of the system by combining sliding mode control and Convolutional Neural Network (CNN). Sliding mode control performs well in terms of robustness and response speed, while CNN has excellent ability for image feature extraction. The research results show that the combination of the two and the visual servo has better performance in a variety of application scenarios, so this is also the development direction that industrial robots can adopt in the future.

PV-YOLO: A lightweight pedestrian and vehicle detection model based on improved YOLOv8

With the frequent occurrence of urban traffic accidents, fast and accurate detection of pedestrian and vehicle targets has become one of the key technologies for intelligent assisted driving systems. To meet the efficiency and lightweight requirements of smart devices, this paper proposes a lightweight pedestrian and vehicle detection model based on the YOLOv8n model, named PV-YOLO. In the proposed model, receptive-field attention convolution (RFAConv) serves as the backbone network because of its target feature extraction ability, and the neck utilizes the bidirectional feature pyramid network (BiFPN) instead of the original path aggregation network (PANet) to simplify the feature fusion process. Moreover, a lightweight detection head is introduced to reduce the computational burden and improve the overall detection accuracy. In addition, a small target detection layer is designed to improve the accuracy for small distant targets. Finally, to reduce the computational burden further, the lightweight C2f module is utilized to compress the model. The experimental results on the BDD100K and KITTI datasets demonstrate that the proposed PV-YOLO can achieve higher detection accuracy than YOLOv8n and other baseline methods with less model complexity.

Factors affected housing prices: taking Boston as an example

Abstract. Real estate price prediction plays a vital role in urban planning, investment decision-making, and risk management. However, existing prediction models often show problems such as insufficient generalization ability and susceptibility to outliers when faced with complex nonlinear relationships, multidimensional features, and noisy data. Therefore, choosing a model that can accurately capture complex patterns and has strong robustness has become the focus of research. This paper introduces the random forest model and compares it with multivariate linear regression, XGBoost, and support vector machine (SVM). Compared with the traditional regression model, the random forest model combines the flexibility of decision trees and the multi-level feature extraction ability of deep learning, and can better handle the complex nonlinear relationships in the Boston housing price dataset. The experimental results show that the random forest model has achieved excellent performance in all evaluation indicators, and the model accuracy indicators are distributed as MSE=8.2502, RMSE=2.8723, MAE=2.0668, and R^2=0.8875. These results show that the random forest model not only outperforms other models in prediction accuracy but also shows significant advantages in dealing with data complexity and improving generalization ability. Therefore, the random forest model provides an efficient and reliable tool for future real estate price prediction research and applications.

An Attention-Based Spatial-Spectral Joint Network for Maize Hyperspectral Images Disease Detection

Maize is susceptible to pest disease, and the production of maize would suffer a significant decline without precise early detection. Hyperspectral imaging is well-suited for the precise detection of diseases due to its ability to capture the internal chemical characteristics of vegetation. However, the abundance of redundant information in hyperspectral data poses challenges in extracting significant features. To overcome the above problems, in this study we proposed an attention-based spatial-spectral joint network model for hyperspectral detection of pest-infected maize. The model contains 3D and 2D convolutional layers that extract features from both spatial and spectral domains to improve the identification capability of hyperspectral images. Moreover, the model is embedded with an attention mechanism that improves feature representation by focusing on important spatial and spectral-wise information and enhances the feature extraction ability of the model. Experimental results demonstrate the effectiveness of the proposed model across different field scenarios, achieving overall accuracies (OAs) of 99.24% and 97.4% on close-up hyperspectral images and middle-shot hyperspectral images, respectively. Even under the condition of a lack of training data, the proposed model performs a superior performance relative to other models and achieves OAs of 98.29% and 92.18%. These results proved the validity of the proposed model, and it is accomplished efficiently for pest-infected maize detection. The proposed model is believed to have the potential to be applied to mobile devices such as field robots in order to monitor and detect infected maize automatically.

A hybrid BiLSTM-CNN deep learning model for Chinese sentiment analysis of online car reviews

Although sentiment analysis with datasets in English has achieved significant progress, there are still relatively few studies on sentiment analysis in the area of Chinesecar review texts. In addition, the existing Chinese text sentiment analysis methods cannot simultaneously extract the contextual features and the local semantic information from the review texts. To address the above issues, a hybrid deep learning model namely BiLSTM-CNN was designed and validated with Chinese car review texts. We trained word vectors with the CBOW model by combining the Chinese Wikipedia corpus with other open-source car-related corpora. Such word vectors include car-specific vocabulary, which improves sentimental classification accuracy. Experimental results show that the performance indices of the deep learning models (CNN, LSTM, BiLSTM) are much better than the KNN, SVM, Naïve Bayes, and RF model, which is attributed to deep learning's powerful feature extraction ability and nonlinear fitting ability. Furthermore, when compared to deep learning models such as CNN, LSTM, BiLSTM, and LSTM-CNN, the suggested hybrid BiLSTM-CNN model outperformed the others. The results may provide references for consumers to buy a car and for car companies to optimize their products.

An improved YOLOv8n-IRP model for natural rubber tree tapping surface detection and tapping key point positioning.

Aiming at the problem that lightweight algorithm models are difficult to accurately detect and locate tapping surfaces and tapping key points in complex rubber forest environments, this paper proposes an improved YOLOv8n-IRP model based on the YOLOv8n-Pose. First, the receptive field attention mechanism is introduced into the backbone network to enhance the feature extraction ability of the tapping surface. Secondly, the AFPN structure is used to reduce the loss and degradation of the low-level and high-level feature information. Finally, this paper designs a dual-branch key point detection head to improve the screening ability of key point features in the tapping surface. In the detection performance comparison experiment, the YOLOv8n-IRP improves the D_mAP50 and P_mAP50 by 1.4% and 2.3%, respectively, over the original model while achieving an average detection success rate of 87% in the variable illumination test, which demonstrates enhanced robustness. In the positioning performance comparison experiment, the YOLOv8n-IRP achieves an overall better localization performance than YOLOv8n-Pose and YOLOv5n-Pose, realizing an average Euclidean distance error of less than 40 pixels. In summary, YOLOv8n-IRP shows excellent detection and positioning performance, which not only provides a new method for the key point localization of the rubber-tapping robot but also provides technical support for the unmanned rubber-tapping operation of the intelligent rubber-tapping robot.

СОВЕРШЕНСТВОВАНИЕ СПОСОБА ПОЛУЧЕНИЯ УСНИНОВОЙ КИСЛОТЫ ИЗ РАСТИТЕЛЬНОГО СЫРЬЯ ИСЛАНДСКОГО МХА

Relevance. Contemporary pharmaceutical industry requires constant search and development of new technologies for the production of pharmacological products. At the same time, the processing of plants, which contain substances with a therapeutic effect, is a promising direction. Their use in terms of economic and therapeutic effectiveness is sometimes very beneficial. It has been proven that lichen plants contain substances that have a therapeutic effect. Organisms of the genus Cladonia, which synthesize usnic acid, among them have a special significance and application. The extraction of usnic acid from lichen biomass is carried out using various organic solvents. At the same time, it is preferable to use techniques with the lowest cost with a high quantitative yield of extractives. In addition, extracts containing bioactive substances should exhibit significant biological activity. The aim is improving the technology of extraction of usnic acid from the vegetable raw materials of Cladonia rangiferina Hoff by determining the optimal components for its extraction. Materials and methods. The material for the study is raw material of Yagel (Deer Moss)/Cladonia rangiferina Hoff. The extractive properties of the most commonly used solvents (purified water, ethyl alcohol 40, 70 and 95%) were studied, among which the most effective was identified. The content of extractive substances was determined by the gravimetric analysis method. The results of the study. According to the results of a series of experiments to study extractive capabilities, of all solvents, the maximum extractive ability of extractive substances from Cladonia rangiferina Hoff was noted for 95% ethyl alcohol (7.38%). Ethyl alcohol 70% was produced with a high extraction capacity, however, it turned out to be less effective. The conclusion was made about these methods can be used to detect biologically active substances obtained from the raw materials of Cladonia rangiferina Hoff. The obtained developments create prerequisites for the development of regulatory documentation on the procedure and position of the relevant standard or a temporary pharmacopoeia article.

Bearing defect detection based on the improved YOLOv5 algorithm.

In the field of bearing defect detection, Aiming at the problem of low efficiency in manual inspection and prone to missed detections in scenarios with small target defects, and overlapping targets, an improved YOLOv5-based object detection method is proposed. Firstly, in terms of feature extraction, the C3 modules in the original backbone of YOLOv5 are replaced with the finer-grained Res2Block modules to improve the model's feature extraction ability. Secondly, in terms of feature fusion, a Bidirectional Feature Pyramid Network (BiFPN) is added to the original neck of YOLOv5 to enhance the fusion ability of shallow graphic features and deep semantic features. Finally, the performance of the improved YOLOv5 algorithm is validated through ablation experiments and comparative experiments with other defect detection algorithms, including the Small_obj algorithm the existing method of adding a small target detection head for identifying small target defects. The experimental results demonstrate that the improved YOLOv5 algorithm exhibits high mAP and accuracy in bearing defect detection, enabling more precise identification the types of small target defects on bearings in complex scenarios with multiple coexisting defects and overlapping detection targets, thereby providing valuable reference for practical bearing defect detection.

Airfoil Shape Generation and Feature Extraction Using the Conditional VAE-WGAN-gp

A machine learning method was applied to solve an inverse airfoil design problem. A conditional VAE-WGAN-gp model, which couples the conditional variational autoencoder (VAE) and Wasserstein generative adversarial network with gradient penalty (WGAN-gp), is proposed for an airfoil generation method, and then, it is compared with the WGAN-gp and VAE models. The VAEGAN model couples the VAE and GAN models, which enables feature extraction in the GAN models. In airfoil generation tasks, to generate airfoil shapes that satisfy lift coefficient requirements, it is known that VAE outperforms WGAN-gp with respect to the accuracy of the reproduction of the lift coefficient, whereas GAN outperforms VAE with respect to the smoothness and variations of generated shapes. In this study, VAE-WGAN-gp demonstrated a good performance in all three aspects. Latent distribution was also studied to compare the feature extraction ability of the proposed method.

Numerical investigation of the effective receptive field and its relationship with convolutional kernels and layers in convolutional neural network

The receptive field (RF) plays a crucial role in convolutional neural networks (CNNs) because it determines the amount of input information that each neuron in a CNN can perceive, which directly affects the feature extraction ability. As the number of convolutional layers in CNNs increases, there is a decay of the RF according to the two-dimensional Gaussian distribution. Thus, an effective receptive field (ERF) can be used to characterize the available part of the RF. The ERF is calculated by the kernel size and layer number within the neural network architecture. Currently, ERF calculation methods are typically applied to single-channel input data that are both independent and identically distributed. However, such methods may result in a loss of effective information if they are applied to more general (i.e., multi-channel) datasets. Therefore, we proposed a multi-channel ERF calculation method. By conducting a series of numerical experiments, we determined the relationship between the ERF and the convolutional kernel size in conjunction with the layer number. To validate the new method, we used the recently published global wave surrogate model for climate simulation (GWSM4C) and its accompanying dataset. According to the newly established relationship, we refined the kernel size and layer number in each neural network of the GWSM4C to produce the same ERF but lower RF attenuation rates than those of the original version. By visualizing the gradient map at several points in West African and East Pacific areas, the high gradient value regions confirmed the known swell sources, which indicated effective feature extraction in these areas. Furthermore, the new version of the GWSM4C yielded better prediction accuracy for significant wave height in global swell pools. The root mean square errors in the West African and East Pacific regions reduced from approximately 0.3 m, in the original model to about 0.15 m, in the new model. Moreover, these improvements were attributed to the higher efficiency of the newly modified neural network structure that allows the inclusion of more historical winds while maintaining acceptable computational consumption.

All Roads Lead to Rome: Isomers with Divergent Cathode Modification Mechanisms toward Ohmic Contact.

Cathode interfacial layers (CILs) hold utmost importance for achieving ohmic contact at the organic semiconductor-cathode interface of organic photovoltaic devices. Delving deep into diverse design principles and working mechanisms is of great significance for designing novel CILs with high performance. Herein, two novel nonamine-based CILs are designed: one featuring a cyclopentadiene unit, designated as CIL-cp; while the other, lacking cyclopentadiene, is referred to as CIL-ph, which is an isomer of CIL-cp. The subtle changes in chemical structures result in distinct modification mechanisms toward ohmic contact. On one hand, the robust electron-withdrawing characteristic of cyclopentadiene endows CIL-cp with lower energy levels, resulting in an interfacial dipole at the active layer-CIL-cp interface due to electron transfer from D18 to CIL-cp. On the other hand, CIL-ph exhibits a strong interfacial dipole at the CIL-Ag interface, which significantly reduces the work function (WF) of the silver electrode. Both CIL-cp and CIL-ph demonstrate excellent interfacial modification capability, whereas CIL-cp possesses a stronger electron extraction ability, thus leading to a high power conversion efficiency of 19.31% in the D18:L8-BO system. Our results reveal the distinctive operational mechanism of cyclopentadiene-based CILs, thus offering innovative design ideas for CIL materials.

Pre-connected and trainable adjacency matrix-based GCN and neighbor feature approximation for industrial fault diagnosis

Industrial fault diagnosis methods based on graph convolution network (GCN) becomes a hot topic for its great feature extraction ability to multivariate time-series data. However, GCNs ignore inter-sample temporality when constructing the adjacency matrix (AM), leading to low prediction accuracy. A novel fault diagnosis method based on pre-connected and trainable AM-based GCN and neighbor feature approximation (PTGCN-FA) is proposed at the node-level task. Firstly, PTGCN-FA introduces the temporal nearest neighbors into spatial nearest neighbors to pre-connect and construct the AM. Then, the AM is trained only where the samples are connected, which makes the best weights obtained and reduces the time complexity of the model. Finally, after the GCN layers, the trained AM is introduced into the approximation of features, which are neighbors in the original sample space. Two process industry cases are carried out, and the simulation results including diagnosis accuracy, confusion matrix, study to the ratio of labeled data and an ablation experiment verify PTGCN-FA has more efficient and accurate diagnostic performance than related methods. Additionally, the analysis of the temporal neighborhood weight parameter shows that the performance of fault diagnosis can be improved by considering both temporal and spatial information between samples.

Enhanced Collaborative Filtering: Combining Autoencoder and Opposite User Inference to Solve Sparsity and Gray Sheep Issues

In recent years, the study of recommendation systems has become crucial, capturing the interest of scientists and academics worldwide. Music, books, movies, news, conferences, courses, and learning materials are some examples of using the recommender system. Among the various strategies employed, collaborative filtering stands out as one of the most common and effective approaches. This method identifies similar active users to make item recommendations. However, collaborative filtering has two major challenges: sparsity and gray sheep. Inspired by the remarkable success of deep learning across a multitude of application areas, we have integrated deep learning techniques into our proposed method to effectively address the aforementioned challenges. In this paper, we present a new method called Enriched_AE, focused on autoencoder, a well-regarded unsupervised deep learning technique renowned for its superior ability in data dimensionality reduction, feature extraction, and data reconstruction, with an augmented rating matrix. This matrix not only includes real users but also incorporates virtual users inferred from opposing ratings given by real users. By doing so, we aim to enhance the accuracy of predictions, thus enabling more effective recommendation generation. Through experimental analysis of the MovieLens 100K dataset, we observe that our method achieves notable reductions in both RMSE (Root Mean Squared Error) and MAE (Mean Absolute Error), underscoring its superiority over the state-of-the-art collaborative filtering models.