Extraction Ability Research Articles

UViT: Efficient and lightweight U-shaped hybrid vision transformer for human pose estimation

Pose estimation plays a crucial role in human-centered vision applications and has advanced significantly in recent years. However, prevailing approaches use extremely complex structural designs for obtaining high scores on the benchmark dataset, hampering edge device applications. In this study, an efficient and lightweight human pose estimation problem is investigated. Enhancements are made to the context enhancement module of the U-shaped structure to improve the multi-scale local modeling capability. With a transformer structure, a lightweight transformer block was designed to enhance the local feature extraction and global modeling ability. Finally, a lightweight pose estimation network— U-shaped Hybrid Vision Transformer, UViT— was developed. The minimal network UViT-T achieved a 3.9% improvement in AP scores on the COCO validation set with fewer model parameters and computational complexity compared with the best-performing V2 version of the MobileNet series. Specifically, with an input size of 384×288, UViT-T achieves an impressive AP score of 70.2 on the COCO test-dev set, with only 1.52 M parameters and 2.32 GFLOPs. The inference speed is approximately twice that of general-purpose networks. This study provides an efficient and lightweight design idea and method for the human pose estimation task and provides theoretical support for its deployment on edge devices.

Few-Shot Learning for Misinformation Detection Based on Contrastive Models

With the development of social media, the amount of fake news has risen significantly and had a great impact on both individuals and society. The restrictions imposed by censors make the objective reporting of news difficult. Most studies use supervised methods, relying on a large amount of labeled data for fake news detection, which hinders the effectiveness of the detection. Meanwhile, the focus of these studies is on the detection of fake news in a single modality, either text or images, but actual fake news is more often in the form of text–image pairs. In this paper, we introduce a self-supervised model grounded in contrastive learning. This model facilitates simultaneous feature extraction for both text and images by employing dot product graphic matching. Through contrastive learning, it augments the extraction capability of image features, leading to a robust visual feature extraction ability with reduced training data requirements. The model’s effectiveness was assessed against the baseline using the COSMOS fake news dataset. The experiments reveal that, when detecting fake news with mismatched text–image pairs, only approximately 3% of the data are used for training. The model achieves an accuracy of 80%, equivalent to 95% of the original model’s performance using full-size data for training. Notably, replacing the text encoding layer enhances experimental stability, providing a substantial advantage over the original model, specifically on the COSMOS dataset.

Convolutional neural network intelligent fault diagnosis method for rotating machinery based on discriminant correlation analysis multi-domain feature fusion strategy

Aiming at solving the problems of limited training data, single input information, and limited diagnostic accuracy under the influence of strong background noise in fault diagnosis of rotating machinery, this paper proposes a fault diagnosis method based on the combination of discriminant correlation analysis (DCA) and convolutional neural network (CNN). Firstly, the original vibration signal is divided into several segments in the time domain, and the training data is directly processed by one CNN branch to extract multi-scale time domain features. Simultaneously, the divided data is subjected to discrete wavelet transform (DWT), and processed by another branch of CNN to extract multi-scale time-frequency features. Then, the DCA feature fusion mechanism is adopted to fuse the two-domain features extracted in the parallel branches to improve the model’ detection ability. Finally, the fused features are input into the deep CNN for training and learning to extract new features and output the classification results. Through the experimental analysis of two different types of data, the results show that the proposed method can be used for fault diagnosis of rotating machinery effectively. Compared with the single CNN network, the proposed method combines the multi-domain multi-scale feature extraction module with the DCA feature fusion module to enrich the feature information extraction ability. At the same time, the network performance is improved to get higher fault classification accuracy higher.

Coupling video vision transformer (ViVit) into land change simulation: a comparison with three-dimensional convolutional neural network (3DCNN)

ABSTRACT To enhance land use/cover change (LUCC) simulation accuracy, we introduced ViViT-ANN-CA, blending video vision transformer’s spatio-temporal features extraction ability, artificial neural network‘s (ANN) non-linearity computing ability, and CA’s spatial computing. Compared to 3DCNN-ANN-CA, ViViT-ANN-CA showed higher accuracy in simulating water bodies and vegetation, with overall improvements in Hailing District and Wuxi City. ViViT demonstrates comparable spatio-temporal feature extraction ability to three-dimensional convolutional neural network (3DCNN), promising for future ynamic LUCC simulations.

Auxiliary input-enhanced siamese neural network: A robust tool wear prediction framework with improved feature extraction and generalization ability

Tool wear monitoring is essential for automated and resilient manufacturing, as it can prevent catastrophic failures caused by severe wear on cutting edges during machining. The conventional tool wear monitoring approaches depend on features extracted from signals, which require sensitive signals and consistent tool wear. In practical scenarios, however, neither the sensitivity of collected signals to the tool wear status nor the consistency of the actual tool wear evolution is hard to meet the requirement of the tool condition monitoring algorithm, which greatly limit the wide spread of its industrial applications. To overcome this challenge, we propose an Auxiliary Input-enhanced Siamese Neural Network (AISNN) framework by incorporating a Siamese structure into the feature extraction part of a convolutional neural network (CNN), and introducing an auxiliary input to its nonlinear regression part. The Siamese structure, instead of extracting features directly from signals, distinguishes the difference between the features extracted from signals of the examined cut and the first cut, and uses this difference as the indicator of tool wear status. Moreover, the auxiliary input provides an additional feature that has heavy dependence on the tool wear, which enables the model learning the general wear evolution of the examined cutting tool. The effectiveness of the proposed AISNN framework is verified in a set of milling experiments where input signal is insensitive to the flank wear of cutting tool and different tools’ wear evolution exhibits obvious inconsistency. Compared to the traditional CNN, the proposed AISNN significantly improves the accuracy on the verification set from 63% to 95% and on the testing set from 50% to 81%. The results demonstrate that the AISNN framework achieves significant improvement in feature extraction and generalization ability. The proposed AISNN, as a universal framework, can empower most existing deep learning-based tool wear prediction methods, enhancing their robustness in handling insensitive signals and inconsistent wear evolution and thereby promoting more industrial applications.

The Antioxidant, Antibacterial and Cell-Protective Properties of Bioactive Compounds Extracted from Rowanberry (Sorbus aucuparia L.) Fruits In Vitro.

Considering that Sorbus aucuparia fruits have been underutilized despite their tremendous potential, this study aimed to correlate the in vitro antioxidant, antibacterial and cell-protective abilities of fruit extracts derived from Sorbus aucuparia Romanian cultivars with their phytochemical composition. Therefore, following the preparation of ethanolic and carotenoid extracts, phytochemical screening was performed using UV-Vis and HPLC-DAD-ESI-MS methods. The antioxidant activity was analyzed using DPPH and FRAP tests. As the results revealed high contents of bioactive compounds (polyphenols 1.11 mg GAE/g DM, flavonoids 430.06 µg QE/g DM and carotenoids 95.68 µg/g DM) and an important antiradical action (DPPH 24.51 mg/mL and FRAP 0.016 µM TE/mL), we chose to further examine the fruits' biological properties. The antibacterial capacity was assessed employing agar well diffusion and broth microdilution techniques, with fruits displaying an intense activity against MSSA, MRSA and Enterococcus faecalis, but also E. coli and Pseudomonas aeruginosa. The cell-protective activity was analyzed on gentamicin-stressed renal cells, through MTT and Annexin V-FITC assays. Importantly, a significant increase in viability was registered on stressed cells following extract administration in low doses; nevertheless, viability was noticed to decline when exposed to elevated concentrations, potentially due to the cumulative actions of the extract and gentamicin. These findings offer novel light on the antibacterial activity of Sorbus aucuparia Romanian cultivars, as well as their cell-protective ability in renal cell injury.

Diesel engine fault diagnosis for multiple industrial scenarios based on transfer learning

Fault diagnosis based on data-driven intelligence has recently attracted extensive interest owing to the rapid development of big data and deep-learning algorithms. However, when the amount of faulty data is limited, deep learning training is prone to overfitting. When the application scenario is changed, the generalization ability of the trained network is affected. In this study, a fault diagnosis architecture based on deep transfer learning is proposed to work with limited data and transfer between multiple scenarios. A wide convolution kernel convolutional long short-term memory neural network (WCL) was used to improve the feature extraction ability of fault data from a diesel engine with a low signal-to-noise ratio. A multiple transfer learning scheme based on WCL was further adopted to transfer the well-trained diagnostic knowledge of large-scale labeled source domain data to the target domain with limited samples. In addition, for diesel engines for various purposes, the knowledge transferability between different scenarios was studied. The algorithm evaluates the transfer performance of four different domains when the sample is insufficient, including the cross-fault type, cross-equipment type, cross-fault degree, and cross-working conditions. The results show the proposed method is proven with high noise immunity improves the accuracy of small sample cross-domain diagnosis and provides an optimal transfer scheme suitable for diesel engine fault signals.

Detection of Coal and Gangue Based on Improved YOLOv8.

To address the lightweight and real-time issues of coal sorting detection, an intelligent detection method for coal and gangue, Our-v8, was proposed based on improved YOLOv8. Images of coal and gangue with different densities under two diverse lighting environments were collected. Then the Laplacian image enhancement algorithm was proposed to improve the training data quality, sharpening contours and boosting feature extraction; the CBAM attention mechanism was introduced to prioritize crucial features, enhancing more accurate feature extraction ability; and the EIOU loss function was added to refine box regression, further improving detection accuracy. The experimental results showed that Our-v8 for detecting coal and gangue in a halogen lamp lighting environment achieved excellent performance with a mean average precision (mAP) of 99.5%, was lightweight with FLOPs of 29.7, Param of 12.8, and a size of only 22.1 MB. Additionally, Our-v8 can provide accurate location information for coal and gangue, making it ideal for real-time coal sorting applications.

Exothermic, sluggish biphasic extraction of uranyl through polygonal bipyramidal chloroacetamide complexes in ionic liquid

An exothermic, spontaneous, highly efficient, sluggish biphasic extractive mass transfer of uranyl ion have been reported from aqueous acidic solution using chloroacetamide ligands into highly viscous ionic liquid involving UO2(NO3)(Chloroacetamide)2+ species predominantly following diffusion controlled ‘cation exchange’ mechanism. The O-donor of chloroacetamide monodentate ligand and O-donor of the bidentate NO3− were coordinated to the UO22+ ion. The average U−OUO2 bond distance is found to be the shortest (1.788 Å), followed by U−Ochloroacetamide (2.439 Å and 2.446 Å for L1 and L2) and U–ONO3 (2.511 Å). The donation of electron density from the O-donors to the central U atom was evidenced by lowering of positive charge (∼0.28) on U atom from [UO2(H2O)5]2+ to UO2(NO3)(Chloroacetamide)2+ complexes. In these uranyl complexes, the contributions from the electrostatic and orbital interaction were found to be ∼73.7–75.2 % and 22.4–23.9 %, respectively of the total contribution, which was estimated as −518.9 and −582.2 kcal mol−1. The ionic liquid based solvent systems exhibited moderate radiolytic stability and good back extract ability using aqueous carbonate complex. The regeneration ability has been clearly demonstrated for five consecutive cycles consisting of one extraction and three back extraction cycles without much compromise on the performance (reduction in DU values were within 5–10 %).

SeqCorr-EUNet: A sequence correction dual-flow network for segmentation and quantification of anterior segment OCT image

The accurate segmentation of AS-OCT images is a prerequisite for the morphological details analysis of anterior segment structure and the extraction of clinical biological parameters, which play an essential role in the diagnosis, evaluation, and preoperative prognosis management of many ophthalmic diseases. Manually marking the boundaries of the anterior segment tissue is time-consuming and error-prone, with inherent speckle noise, various artifacts, and some low-quality scanned images further increasing the difficulty of the segmentation task. In this work, we propose a novel model called SeqCorr-EUNet with a dual-flow architecture based on convolutional gated recursive sequence correction for semantic segmentation and quantification of AS-OCT images. An EfficientNet encoder is employed to enhance the intra-slice features extraction ability of semantic segmentation flow. The sequence correction flow based on ConvGRU is introduced to extract inter-slice features from consecutive adjacent slices. Spatio-temporal information is fused to correct the morphological details of pre-segmentation results. And the channel attention gate is inserted into the skip-connection between encoder and decoder to enrich the contextual information and suppress the noise of irrelevant regions. Based on the segmentation results of the anterior segment structures, we achieved automatic extraction of essential clinical parameters, 3D reconstruction of the anterior chamber structure, and measurement of anterior chamber volume. The proposed SeqCorr-EUNet has been evaluated on the public AS-OCT dataset. The experimental results show that our method is competitive compared with the existing methods and significantly improves the segmentation and quantification performance of low-quality imaging structures in AS-OCT images.

A novel bifunctional ionic liquid [N1888][OOB] for the separation of rare earth and transition metal in NdFeB magnet

In this paper, a series of novel bifunctional ionic liquids with methyltrioctylammonium as the cation and o-alkoxybenzoic acetate as the anion were synthesized. Their extraction properties were investigated for the separation of rare earth and transition metal for NdFeB waste recycling. It was found that [methyltrioctyl ammonium][o-octyloxybenzoic acetate] ([N1888][OOB]) could preferentially extract rare earth while the extraction abilities of Fe and Co were weak. The extraction mechanism of rare earth with [N1888][OOB] was indicated to be ion association in a molar ratio of 2:1. The rare earth loaded by [N1888][OOB] could be selectively stripped with water. Based on the above research results, a novel separation process was developed to separate rare earth, Fe and Co with [N1888][OOB]. This study intensified the separation process of rare earth and transition metals. The novel separation strategy based on [N1888][OOB] has revealed the advantages of efficiency and sustainability for rare earth recovery.

A novel feature extraction method: iterative Ramanujan Fourier mixture spectrum

As a classical demodulation method, envelope spectrum (ES) has been used in rotating machinery fault diagnosis. However, for strong noise or multiple faults, the feature extraction ability of ES is not outstanding, even if it is unable to extract obvious fault features. Fourier transform (FT) in ES analysis is also not suitable for analyzing non-stationary signals. Considering the shortcomings of FT, this paper defines the Ramanujan Fourier mixture transform (RFMT). The RFMT has outstanding period feature extraction ability and can accurately extract the periodic features in the envelope signal. Based on this, this paper proposes the iterative Ramanujan Fourier mixture spectrum (IRFMS) method. The IRFMS enhances the fault features in the signal by iterative envelope and selects the envelope signals with obvious fault features by cyclic kurtosis. The results of signal analysis verify that IRFMS has excellent fault feature extraction ability, which is suitable for various fields of rotating machinery fault diagnosis.

Selective extraction of lithium ions by phosphoroxy-functionalized ionogels from the mother liquor of Li2CO3

Functionalized ionic liquids (FILs), as novel extractants, offer a promising way for the effective separation of Li+, but are limited by their high viscosity which increases the mass transfer resistance and hinders their practical application in industry. To overcome the above problem, this work develops a phosphoroxy-functionalized ionogels (PFIG) with a high specific surface area, hydroxyl-rich groups and porous structure, which was formed by introducing highly hydrophilic [N4444][DEHP] into a silica gel substrate via the sol–gel method. The PFIG can take advantage of the beneficial properties of each component, including the nature of the solid carrier and the Li+ selective extraction ability of [N4444][DEHP]. The high extraction rate of Li+ up to 80.4 % was attained when the content of [N4444][DEHP] in the PFIG composite was 7 mL, which may be due to the strong chelation between [N4444][DEHP] and Li+ and the excellent hydrophilicity of the substrate to increase the mass transfer. Moreover, the competitive extraction experiments indicated that PFIG-7 had excellent high selectivity. Therefore, PFIG-7 has great potential application for lithium recovery from the mother liquor of Li2CO3.

A Contraband Detection Scheme in X-ray Security Images Based on Improved YOLOv8s Network Model.

X-ray inspections of contraband are widely used to maintain public transportation safety and protect life and property when people travel. To improve detection accuracy and reduce the probability of missed and false detection, a contraband detection algorithm YOLOv8s-DCN-EMA-IPIO* based on YOLOv8s is proposed. Firstly, the super-resolution reconstruction method based on the SRGAN network enhances the original data set, which is more conducive to model training. Secondly, DCNv2 (deformable convolution net v2) is introduced in the backbone network and merged with the C2f layer to improve the ability of the feature extraction and robustness of the model. Then, an EMA (efficient multi-scale attention) mechanism is proposed to suppress the interference of complex background noise and occlusion overlap in the detection process. Finally, the IPIO (improved pigeon-inspired optimization), which is based on the cross-mutation strategy, is employed to maximize the convolutional neural network's learning rate to derive the optimal group's weight information and ultimately improve the model's detection and recognition accuracy. The experimental results show that on the self-built data set, the mAP (mean average precision) of the improved model YOLOv8s-DCN-EMA-IPIO* is 73.43%, 3.98% higher than that of the original model YOLOv8s, and the FPS is 95, meeting the deployment requirements of both high precision and real-time.

High Electrical Conductivity and Hole Transport in an Insightfully Engineered Columnar Liquid Crystal for Solution-Processable Nanoelectronics.

Discotic liquid crystals (DLCs) are widely acknowledged as a class of organic semiconductors that can harmonize charge carrier mobility and device processability through supramolecular self-assembly. In spite of circumventing such a major challenge in fabricating low-cost charge transport layers, DLC-based hole transport layers (HTLs) have remained elusive in modern organo-electronics. In this work, a minimalistic design strategy is envisioned to effectuate a cyanovinylene-integrated pyrene-based discotic liquid crystal (PY-DLC) with a room-temperature columnar hexagonal mesophase and narrow bandgap for efficient semiconducting behavior. Adequately combined photophysical, electrochemical, and theoretical studies investigate the structure-property relations, logically correlating them with efficient hole transport. With a low reorganization energy of 0.2eV, PY-DLC exhibits superior charge extraction ability from the contact electrodes at low values of applied voltage, achieving an electrical conductivity of 3.22 × 10-4 Sm-1, the highest reported value for any pristine DLC film in a vertical charge transport device. The columnar self-assembly, in conjunction with solution-processable self-healed films, results in commendably elevated values of hole mobility (≈10-3 cm2V-1s-1). This study provides an unprecedented constructive outlook toward the development of DLC semiconductors as practical HTLs in organic electronics.

Double-Branch Multi-Scale Contextual Network: A Model for Multi-Scale Street Tree Segmentation in High-Resolution Remote Sensing Images.

Street trees are of great importance to urban green spaces. Quick and accurate segmentation of street trees from high-resolution remote sensing images is of great significance in urban green space management. However, traditional segmentation methods can easily miss some targets because of the different sizes of street trees. To solve this problem, we propose the Double-Branch Multi-Scale Contextual Network (DB-MSC Net), which has two branches and a Multi-Scale Contextual (MSC) block in the encoder. The MSC block combines parallel dilated convolutional layers and transformer blocks to enhance the network's multi-scale feature extraction ability. A channel attention mechanism (CAM) is added to the decoder to assign weights to features from RGB images and the normalized difference vegetation index (NDVI). We proposed a benchmark dataset to test the improvement of our network. Experimental research showed that the DB-MSC Net demonstrated good performance compared with typical methods like Unet, HRnet, SETR and recent methods. The overall accuracy (OA) was improved by at least 0.16% and the mean intersection over union was improved by at least 1.13%. The model's segmentation accuracy meets the requirements of urban green space management.

Research on U-Net seismic signal denoising combined with residual dense blocks

Aiming to address the limited noise reduction capabilities of conventional methods for reducing noise in seismic signals, the paper proposes a noise reduction model based on the RDBU-Net network. This model utilizes a residual dense block (RDB) instead of conventional convolutional layers in the U-Net network to enhance the feature extraction capacity for same-band noise, thereby elevating the signal-to-noise ratio (SNR) of seismic signals. The RDBU-Net model is trained, validated, and tested using the global seismic dataset from Stanford University. In comparison with the wavelet threshold method, the denoising RDB model, and the U-Net model, the RDBU-Net model demonstrates an improvement in SNRs by 7.82 dB, 6.13 dB, and 2.9 dB, respectively. Additionally, the root mean square errors are reduced by 0.4812, 0.3736, and 0.1938, and the correlation coefficients are enhanced by 0.3818, 0.2714, and 0.1205. The RDBU-Net model proposed in this study effectively enhances the SNR of seismic signals and offers fresh insights into eliminating noise within the same frequency band of seismic signals.

BLSENet: A Novel Lightweight Bilinear Convolutional Neural Network Based on Attention Mechanism and Feature Fusion Strategy for Apple Leaf Disease Classification

Accurate identification of apple leaf diseases is of great significance for improving apple yield. The lesion area of the apple leaf disease image is small and vulnerable to background interference, which easily leads to low recognition accuracy. To solve this problem, a lightweight bilinear convolutional neural network (CNN) model named BLSENet based on attention mechanism is designed. The model consists of two subnetworks, and each subnetwork is embedded with a Squeeze-and-Excitation (SE) module. By using the feature extraction ability of the two subnetworks and combining the bilinear feature CONCAT operation, the multiscale features of the image are obtained. Compared with the unimproved model LeNet-5 (84.63%), BLSENet has higher accuracy in the test set, which indicates that SE module and bilinear feature fusion have a positive effect on the performance of the model, and BLSENet has the ability to identify apple leaf diseases. The model has achieved the expected goal and can provide technical support for accurate identification and real-time monitoring of apple disease images.

Molecular insights into dicationic versus monocationic ionic liquids as a high hydrophobic alternative for the separation of phenol from waters

The hydrophobic nature of an extractant is particularly critical in the treatment of wastewater. Considering that dicationic ionic liquids (DILs) are likely to be more hydrophobic, a comparative study of the separation of phenol from waters using [NTf2]– based monocationic ionic liquids (MILs) and DILs is carried out both from experimental and theoretical analysis perspectives. Experimental results revealed that DILs exhibited superior extraction ability compared to MILs, with extraction efficiencies of 93.7% and 97.4% using [BMIM][NTf2] and [C6(MIM)2][NTf2]2 as extractants, respectively. The microscopic examination through theoretical calculations elucidated the higher hydrophobicity and extraction efficiency of DILs over MILs. The results indicated that the DIL showed stronger hydrophobicity than the MIL because the hydrogen bond strength between the DIL and water was lower than that of the MIL. Although the hydrogen bond strength between the DIL and phenol was lower than that of the MIL, the stronger van der Waals forces existed between DIL and phenol, so DIL was more efficient in extracting phenol. In addition, the experimental parameters were optimized to provide basic data for application, such as mass ratio of ILs to water, extraction time and temperature, pH, and initial phenol content. Finally, the DILs were recovered using rotary evaporation apparatus, and the results demonstrated that DILs had good recovery and reuse performance. In brief, this work could provide an effective method for the treatment of phenol-containing wastewater. And the revelation of molecular mechanism is expected to positively impact the design of high-performance task-specific ILs.

Lotus toot extract: An investigation of its antioxidant and anticancer properties for potential application in functional foods

This study investigates the effects of lotus root extract (LRE) on antioxidants and cancer prevention to understand how lotus can be used as a natural ingredient in health-promoting foods. We tested the extract's ability to neutralize harmful molecules using the DPPH assay and found that its effectiveness increases with the amount of extract used. The concentration of 22.21 g/mL was key for the extract to show its protective effects. Additionally, our research showed that LRE is good at removing harmful substances like nitrite (21.14 µg/mL) and hydrogen peroxide (24.91 µg/mL). Importantly, lotus extracts were especially effective against human breast cancer cells. Through MTT analysis at 15.60 g/mL, we found LRE to be very effective in killing these cancer cells. This killing process involves the increase of certain proteins (p53, caspase 3, and 9) and the breaking up of DNA, which are signs of cancer cells being programmed to die. Our findings indicate that LRE could be a strong candidate for cancer prevention. This research sheds light on how lotus root extract could be used in health-promoting foods and suggests it might be worth exploring more as a treatment against cancer.