Extraction Ability Research Articles

Detection of pedestrians and vehicles on foggy roads based on improved YOLOv7

Abstract Nowadays, object detection technology plays an indispensable role in the direction of automatic vehicle driving. However, inclement weather, such as fog and haze, poses severe challenges to the ability to understand visual perception and scene understanding of automatic driving technology, making it extremely difficult. Therefore, this paper proposes an improved YOLOv7 algorithm. Firstly, Gaussian blur and Gaussian noise are used to process the original data set, reducing the sensitivity of our model to image information, improving the ability to adapt to changing environments and tasks, and enhancing the generalization performance. Then, using the SIOU loss function, we optimize the algorithm to accelerate the convergence speed while considering the vector angle problem. Add Coordinate Attention integrates accurate position information into the coding network, optimizes the recognition accuracy of the model for a specific position, significantly improves its overall feature extraction ability, and captures key features more accurately, thereby improving the overall performance, capturing key information, and reducing the possibility of missed detection. The introduction of CoordConv into ELAN in the backbone allows for a more sensitive perception of the position of objects during image processing, thus improving the accuracy of its recognition and positioning. The RepGhostNet structure is introduced into the neck to realize the implicit reuse of features. According to the experiments in this paper, our improved YOLOv7 algorithm achieves 87.3% map in the RTTS data set and partial synthetic fog KITTI data set, which improves by 3.9% based on the original model.

Bearing fault diagnosis method based on recurrence plot and improved EfficientNetV2-S

The non-linear and non-stationary characteristics of vibration signals in rolling bearings make it difficult to accurately extract fault features. In addition, traditional fault diagnosis methods cannot fully explore the correlation characteristics between time-series of fault signals. To address the aforementioned issues, this paper introduces a recurrence plot (RP) coding technique into the field of fault diagnosis and proposes a bearing fault diagnosis method based on RP and the improved EfficientNetV2-S. Firstly, the method uses the RP coding technique to convert one-dimensional vibration signals into two-dimensional time-frequency images as inputs to the neural network. Then, the number of layers in the EfficientNetV2-S network is optimised by a non-linear attenuation strategy to reduce network parameters and improve the recognition speed. Finally, the attention mechanism is modified and the variable load dataset is constructed for training to improve the feature extraction ability and generalisation performance of the model. To verify the effectiveness of the proposed method, experiments are conducted based on the bearing datasets provided by Case Western Reserve University (CWRU). The experimental results show that the bearing fault diagnosis method based on RP and the improved EfficientNetV2-S cannot only realise accurate identification of bearing faults but also accurately identify the degree of bearing fault with an accuracy of 99.85%.

Investigation on antibacterial ability of acetone extract from leaves of Avicennia alba Blume growing in the Can Gio Mangrove Biosphere Reserve, Vietnam

Investigation on antibacterial ability of acetone extract from leaves of Avicennia alba Blume growing in the Can Gio Mangrove Biosphere Reserve, Vietnam

Prediction of Network Security Situation Based on Attention Mechanism and Convolutional Neural Network–Gated Recurrent Unit

Network-security situation prediction is a crucial aspect in the field of network security. It is primarily achieved through monitoring network behavior and identifying potential threats to prevent and respond to network attacks. In order to enhance the accuracy of situation prediction, this paper proposes a method that combines a convolutional neural network (CNN) and a gated recurrent unit (GRU), while also incorporating an attention mechanism. The model can simultaneously handle the spatial and temporal features of network behavior and optimize the weight allocation of features through the attention mechanism. Firstly, the CNN’s powerful feature extraction ability is utilized to extract the spatial features of the network behavior. Secondly, time-series features of network behavior are processed through the GRU layer. Finally, to enhance the model’s performance further, we introduce attention mechanisms, which can dynamically adjust the importance of different features based on the current context information; this enables the model to focus more on critical information for accurate predictions. The experimental results show that the network-security situation prediction method, which combines a CNN and a GRU and introduces an attention mechanism, performs well in terms of the fitting effect and can effectively enhance the accuracy of situation prediction.

Toward compound fault diagnosis via EMAGAN and large kernel augmented few-shot learning

Bearings are essential in machinery. Damage to them can cause financial losses and safety risks at industrial sites. Therefore, it is necessary to design an accurate diagnostic model. Although many bearing fault diagnosis methods have been proposed recently, they still cannot meet the requirements of high-accurate prediction of bearing faults. There are several challenges in this: 1) In practical settings, gathering sufficient and balanced sample data for training diagnostic network models proves challenging. 2) The damage to bearings in real industrial production sites is not singular, and compound faults are also a huge challenge for diagnostic networks. To address these issues, this study introduces a novel fault diagnosis model called EMALKNet that integrates DCGAN with Efficient Multi-Scale Attention (EMAGAN) and RepLKNet-XL, enhancing the detection and analysis of bearing faults in industrial machinery. This model employs EMAGAN to explore the underlying distribution of raw data, thereby enlarging the fault sample pool and enhancing the model’s diagnostic capabilities; The large kernel structure of RepLKNet-XL is different from the current mainstream small kernel and has stronger representation extraction ability. The proposed method has been validated on the Paderborn University dataset and the Huazhong University of Science and Technology dataset.

Unsupervised domain adaptive building semantic segmentation network by edge-enhanced contrastive learning

Unsupervised domain adaptation (UDA) is a weakly supervised learning technique that classifies images in the target domain when the source domain has labeled samples, and the target domain has unlabeled samples. Due to the complexity of imaging conditions and the content of remote sensing images, the use of UDA to accurately extract artificial features such as buildings from high-spatial-resolution (HSR) imagery is still challenging. In this study, we propose a new UDA method for building extraction, the contrastive domain adaptation network (CDANet), by utilizing adversarial learning and contrastive learning techniques. CDANet consists of a single multitask generator and dual discriminators. The generator employs a region and edge dual-branch structure that strengthens its edge extraction ability and is beneficial for the extraction of small and densely distributed buildings. The dual discriminators receive the region and edge prediction outputs and achieve multilevel adversarial learning. During adversarial training processing, CDANet aligns the cross-domain of similar pixel features in the embedding space by constructing the regional pixelwise contrastive loss. A self-training (ST) strategy based on pseudolabel generation is further utilized to address the target intradomain discrepancy. Comprehensive experiments are conducted to validate CDANet on three publicly accessible datasets, namely the WHU, Austin, and Massachusetts. Ablation experiments show that the generator network structure, contrastive loss and ST strategy all improve the building extraction accuracy. Method comparisons validate that CDANet achieves superior performance to several state-of-the-art methods, including AdaptSegNet, AdvEnt, IntraDA, FDANet and ADRS, in terms of F1 score and mIoU.

UV-A treatment of phenolic extracts impacts colour, bioactive compounds and antioxidant activity.

The unintended co-extraction of chlorophylls during the recovery of polyphenols from plant sources yields green-coloured phenolic extracts with limited use in colour-sensitive foods. This study aimed at decolourizing the ethanolic extracts of sugar beet leaves using a UV-A treatment (390 nm). Exposure of the phenolic extracts to 30 UV-A LEDs at 8.64 J m-2 radiation dose decreased the total chlorophyll content by 69.23% and reduced the greenness parameter (-a*) significantly (P < 0.05) from 27.33 ± 0.32 to 8.64 ± 0.16. Additionally, UV-A treatment increased the content of most individual phenolic compounds (e.g. gallic acid, ferulic acid, etc.) significantly, resulting in an increase in the overall phenolic content in the extracts from 900.56 ± 14.11 μg g-1 fresh weight (FW) to a maximum of 975.09 ± 9.62 μg g-1 FW at 0.67 J m-2. However, rutin content had a significant decrease at the highest radiation dose (8.64 J m-2). The soluble sugar content (i.e. glucose and fructose) increased simultaneously with phenolic compounds after the UV-A treatment. Although the UV treatment reduced the 2,2-diphenyl-1-picrylhydrazyl radical scavenging activity, it had no significant effect on the ferrous chelating activity and the extract's ability to delay lipid oxidation in corn oil. The antioxidant activity index of the treated extract was comparable to that of butylated hydroxytoluene, a synthetic antioxidant. Key findings of this study include successful decolourization of the extract, decomposition of bound polyphenols to their free form, and maintaining the antioxidant activity of the extract in the oil system after UV-A exposure. © 2024 The Author(s). Journal of the Science of Food and Agriculture published by John Wiley & Sons Ltd on behalf of Society of Chemical Industry.

Textual emotion classification using MPNet and cascading broad learning

As one of the most important tasks of natural language processing, textual emotion classification (TEC) aims to recognize and detect all emotions contained in texts. However, most existing methods are implemented using deep learning approaches, which may suffer from long training time and low convergence. Motivated by these challenges, in this paper, we provide a new solution for TEC by using cascading broad learning (CBL) and sentence embedding using a masked and permuted pre-trained language model (MPNet), named CBLMP. Texts are input into MPNet to generate sentence embedding containing emotional semantic information. CBL is adopted to improve the ability of feature extraction in texts and to enhance model performance for general broad learning, by cascading feature nodes and cascading enhancement nodes, respectively. The L-curve model is adopted to ensure the balance between under-regularization and over-regularization for regularization parameter optimization. Extensive experiments have been carried out on datasets of SMP2020-EWECT and SemEval-2019 Task 3, and the results show that CBLMP outperforms the baseline methods in TEC.

DFW-YOLO: YOLOv5-based algorithm using phased array ultrasonic testing for weld defect recognition

ABSTRACT Although phased array ultrasonic testing (PAUT) technology has been widely employed in pipeline weld defect recognition, current defect recognition still relies on manual operation, which limits its efficiency. By combining deep learning with PAUT, this paper presents a new neural architecture based on YOLOv5 called DFW-YOLO that can call defect indications automatically. To address redundant defect feature maps, the FasterNet backbone is introduced to enhance the model’s feature extraction ability. Additionally, partial dilated convolution (PDConv) and partial convolution (PConv) with an atrous convolution branch are designed to extend the receptive field of the backbone network, mitigating the chance of feature loss. Furthermore, a weighted generalised feature pyramid network (WGFPN) structure is proposed as the neck network. This structure combines the reparameterized generalised feature pyramid network (RepGFPN) with the weighted aggregated concatenation (WAC) structure and eliminates inefficient branches to enhance the model’s feature fusion ability. The experimental results demonstrated that DFW-YOLO outperforms the original YOLOv5 in terms of detection performance. The precision, recall, mean average precision (mAP)@0.5, and mAP@0.5:0.95 are indicators for DFW-YOLO and reach 97.4%, 97.5%, 98.3%, and 68.2%, respectively, marking 4.8%, 5%, 2.7%, and 22.5% improvement compared to the original YOLOv5.

Sequential action-induced invariant representation for reinforcement learning

How to accurately learn task-relevant state representations from high-dimensional observations with visual distractions is a realistic and challenging problem in visual reinforcement learning. Recently, unsupervised representation learning methods based on bisimulation metrics, contrast, prediction, and reconstruction have shown the ability for task-relevant information extraction. However, due to the lack of appropriate mechanisms for the extraction of task information in the prediction, contrast, and reconstruction-related approaches and the limitations of bisimulation-related methods in domains with sparse rewards, it is still difficult for these methods to be effectively extended to environments with distractions. To alleviate these problems, in the paper, the action sequences, which contain task-intensive signals, are incorporated into representation learning. Specifically, we propose a Sequential Action–induced invariant Representation (SAR) method, which decouples the controlled part (i.e., task-relevant information) and the uncontrolled part (i.e., task-irrelevant information) in noisy observations through sequential actions, thereby extracting effective representations related to decision tasks. To achieve it, the characteristic function of the action sequence’s probability distribution is modeled to specifically optimize the state encoder. We conduct extensive experiments on the distracting DeepMind Control suite while achieving the best performance over strong baselines. We also demonstrate the effectiveness of our method at disregarding task-irrelevant information by applying SAR to real-world CARLA-based autonomous driving with natural distractions. Finally, we provide the analysis results of generalization drawn from the generalization decay and t-SNE visualization. Code and demo videos are available at https://github.com/DMU-XMU/SAR.git.

Exogenous variable driven deep learning models for improved price forecasting of TOP crops in India

Accurately predicting agricultural commodity prices is crucial for India's economy. Traditional parametric models struggle with stringent assumptions, while machine learning (ML) approaches, though data-driven, lack automatic feature extraction. Deep learning (DL) models, with advanced feature extraction and predictive abilities, offer a promising solution. However, their application to agricultural price data ignored the exogenous factors. Hence, the study explored advanced versions of the well-known univariate models, NBEATSX and TransformerX. The research employed price data for essential crops like Tomato, Onion, and Potato (TOP) from major Indian markets and complemented it with corresponding weather data (precipitation and temperature). To provide a comprehensive analysis, the study also evaluated traditional statistical methods (ARIMAX and MLR) and a suite of ML algorithms (ANN, SVR, RFR, and XGBoost). The performance of these models was rigorously evaluated using error metrics like RMSE, MAE, sMAPE, MASE and QL. The findings were significant indicating DL models, particularly when augmented with exogenous variables, consistently outshone other methods with NBEATSX and TransformerX showing an average RMSE of 110.33 and 135.33, MAE of 60.08 and 74.92, sMAPE of 22.14 and 24.00, MASE of 1.02 and 1.32 and QL of 30.04 and 34.07, respectively. They exhibited lower error metrics, as compare to the statistical and ML models underscoring their effectiveness and potential in agricultural crop price forecasting. This study not only bridged a crucial research gap but also highlighted the robust potential of DL models in enhancing the accuracy of agricultural commodity price predictions in India.

Online_XKD: An online knowledge distillation model for underwater object detection

Underwater object detection in the field of computer vision faces unique challenges such as color distortion, reduced visibility, and blurred edges caused by aquatic conditions, which decrease the efficiency of traditional methods. Furthermore, the limited memory and computational power of underwater equipment necessitate the development of lightweight and efficient real-time monitoring algorithms. To address these issues, this paper designs an online knowledge distillation(KD) framework based on mutual knowledge transfer, named Online-XKD, which aims to enhance the efficiency and generalizability of knowledge distillation through mutual knowledge exchange while maintaining model lightweightness. The core idea of Online-XKD is an internally designed mutual knowledge transfer structure for online distillation within the detection head, which enhances learning outcomes by optimizing distillation efficiency and broadening generalizability. Additionally, we introduce a mask generation feature knowledge distillation architecture based on the backbone network, which significantly enhances the feature extraction capability of the student model by integrating mask masking and feature generation techniques. Moreover, by incorporating PSA and AUGFPN attention modules, the feature extraction capability in complex underwater environments is further enhanced without adding extra parameters, thereby improving detection accuracy. Experimental results on the URPC2020 dataset demonstrate that Online-XKD enhances the detection accuracy of the student model by 3.6 mAP, exceeding initial KD models by 3.3 mAP, and outperforming most existing KD methods in underwater detection tasks. These results confirm the effectiveness and superiority of Online-XKD in applications of underwater object detection, proving its practical significance and effectiveness in enhancing the feature extraction and generalization abilities of lightweight models.

Advances in using artificial intelligence for predicting protein-ligand binding affinity

The binding of proteins and ligands is a crucial aspect of life processes. The calculation of the protein-ligand binding affinity (PLBA) offers valuable insights into protein function, drug screening targets protein receptors, and enzyme modifications. In recent years, artificial intelligence (AI) has experienced rapid advancements, becoming widely used in PLBA prediction. This is attributed to its robust feature extraction ability, superior algorithm accuracy, and speedy calculations. Our paper aims to provide a comprehensive overview of AI predication process, associated resources, application scenarios, challenges, and potential solutions, serving as a valuable reference for the relevant research endeavors.

Energy fluctuation pattern recognition coupled with decomposition-integration: A novel ocean tidal energy forecasting system

Ocean tidal energy is a new energy source which is recognized and utilized earlier by human beings. For the complexity of tidal generation and the singleness of tidal prediction, this paper proposes a multi-factor forecasting system for ocean tidal energy based on energy fluctuation pattern recognition with confluent ReliefF-density-based spatial clustering of applications with noise (ReliefF-DBSCAN), improved symplectic geometric mode decomposition (ISGMD) and convolutional neural network−bidirectional long short-term memory (CNN-BiLSTM) with temporal pattern attention (TPA), named ReliefF-DBSCAN-ISGMD-TPA-CNN-BiLSTM. Precisely, ReliefF-DBSCAN can extract effective features and fluctuation patterns, and reduce the forecasting difficulty. ISGMD significantly improves the endpoint effect and false components of the decomposition results, and heightens the stability and correlation of each component. TPA-CNN-BiLSTM method have strong feature extraction ability, memory ability and recognition ability. In the evaluation stage, this study introduces some indicators such as root mean square error (RMSE) and Diebold Mariano (DM) test to evaluate the forecasting system comprehensively. To highlight the effect of the developed system, use actual data collected from Port SanLuis and Port Chicago as experimental data and compare with five contrastive models. The experimental result shows that the predicted value for the developed system is the closest to the real value, and the RMSE, mean absolute error (MAE) and goodness of fit (R2) of Port Chicago are 0.3152, 0.2900 and 0.9964, respectively, indicating that the prediction ability is better than all contrastive models. In addition, the result proves that the decomposition-integration system is beneficial to improve forecasting accuracy. This study can make a meaningful improvement and innovation for the forecasting of ocean tidal energy.

Dense Pedestrian Detection Based on GR-YOLO.

In large public places such as railway stations and airports, dense pedestrian detection is important for safety and security. Deep learning methods provide relatively effective solutions but still face problems such as feature extraction difficulties, image multi-scale variations, and high leakage detection rates, which bring great challenges to the research in this field. In this paper, we propose an improved dense pedestrian detection algorithm GR-yolo based on Yolov8. GR-yolo introduces the repc3 module to optimize the backbone network, which enhances the ability of feature extraction, adopts the aggregation-distribution mechanism to reconstruct the yolov8 neck structure, fuses multi-level information, achieves a more efficient exchange of information, and enhances the detection ability of the model. Meanwhile, the Giou loss calculation is used to help GR-yolo converge better, improve the detection accuracy of the target position, and reduce missed detection. Experiments show that GR-yolo has improved detection performance over yolov8, with a 3.1% improvement in detection means accuracy on the wider people dataset, 7.2% on the crowd human dataset, and 11.7% on the people detection images dataset. Therefore, the proposed GR-yolo algorithm is suitable for dense, multi-scale, and scene-variable pedestrian detection, and the improvement also provides a new idea to solve dense pedestrian detection in real scenes.

A real-time and high-accuracy railway obstacle detection method using lightweight CNN and improved transformer

With the sustained development of railway transportation, the urgent necessity to improve train operation safety makes obstacle detection become the research focus. However, existing railway obstacle detectors still face challenges in balancing detection accuracy and speed during the shunting process. In addition, they are not robust enough in real-world railway environments, especially in complex scenes involving small obstacles. To address these problems, this paper presents a real-time and high-accuracy railway obstacle detection model using lightweight CNN and improved transformer (RH-Net) for detecting railway obstacles efficiently to guarantee traffic safety. First, the Lightweight Feature Extraction Module (LEM) is designed to minimize the model’s computational load while maintaining its feature extraction ability. Then, the Improved Transformer Module (IFM) is developed to boost the model’s ability about stably extract global contextual information. Finally, the Enhanced Multi-Scale Feature Fusion Module (EFM) is proposed to optimize the detection of obstacles with different sizes, especially small objects. In the experiments on railway dataset, RH-Net achieves optimal detection performance on GeForce GTX 1080Ti (96.99% mAP and 135 FPS) and Jetson Xavier NX (97.02% mAP and 43 FPS), which is significantly superior to the existing detection models. Experimental results show that RH-Net has excellent detection ability, which can accurately and efficiently detect obstacles in complicated railway environments. Moreover, the experiments on MS COCO indicate that RH-Net can achieve more satisfactory detection performance than existing state-of-the-art methods. Therefore, the proposed model can be well-applied to more complex real-world scenes for multiple object detection.

Short-Term Photovoltaic System Output Power Prediction Based on Integrated Deep Learning Algorithms in the Clean Energy Sector

Photovoltaic power generation system plays an important role in renewable energy. Therefore, accurately predicting the short-term output power of photovoltaic system has become a key challenge for real-time power grid management. This study focuses on Yingli's green energy photovoltaic system, and uses the convolution neural network and long-term and short-term memory network fusion model (CNN-LSTM) to predict the short-term power. The model integrates CNN's data feature extraction and LSTM's time series prediction ability, showing high accuracy and stability. The experimental results show that CNN-LSTM model has a low mean and variance of prediction error, and the prediction is stable and reliable, and it is consistent in different scenarios. This provides theoretical support for the output power prediction of photovoltaic system based on deep learning.

Construction Environment Noise Suppression of Ground-Penetrating Radar Signals Based on an RG-DMSA Neural Network

Ground-penetrating radar (GPR) is often used to detect targets in a construction environment. Due to the different construction environments, the noise exhibits different characteristics on the GPR signal. When the noise is widely distributed on the GPR signal, and its spectrum and the spectrum of the active signal are aliased, it is difficult to separate and suppress the noise by traditional filtering methods. In this paper, we propose a deep learning GPR image noise suppression method based on a recursive guided and dual multi-scale self-attention mechanism neural network (RG-DMSA-NN), which uses a recursive guidance module and a dual multi-scale self-attention mechanism module to improve the feature extraction ability of the image and enhance the robustness and generalization ability in image noise suppression. Through the application of noise suppression on the synthesized test data and the GPR data actually collected by the Macao Science and Technology Museum, the advantages of this method over the traditional filtering, DnCNN and UNet noise suppression methods are demonstrated.

Genus Sambucus: Exploring Its Potential as a Functional Food Ingredient with Neuroprotective Properties Mediated by Antioxidant and Anti-Inflammatory Mechanisms.

The genus Sambucus, mainly Sambucus nigra, has emerged as a valuable source of bioactive compounds with potential neuroprotective properties. This review explores the antioxidant, anti-inflammatory, and neuroregenerative effects of Sambucus-derived compounds and their implications for brain health and cognitive function. In vitro studies have demonstrated the ability of Sambucus extracts to mitigate oxidative stress, modulate inflammatory responses, and promote neural stem cell proliferation and differentiation. In vivo studies using animal models of neurodegenerative diseases, such as Alzheimer's and Parkinson's, have shown that Sambucus compounds can improve cognitive function, motor performance, and neuronal survival while attenuating neuroinflammation and oxidative damage. The neuroprotective effects of Sambucus are primarily attributed to its rich content of polyphenols, particularly anthocyanins, which exert their benefits through multiple mechanisms, including the modulation of signaling pathways involved in inflammation, apoptosis, mitochondrial function, and oxidative stress. Furthermore, the potential of Sambucus as a functional food ingredient is discussed, highlighting its application in various food products and the challenges associated with the stability and bioavailability of its bioactive compounds. This review provides a comprehensive overview of the current state of research on the neuroprotective potential of Sambucus and its derivatives, offering valuable insights for the development of dietary strategies to promote brain health and prevent age-related cognitive decline.

Substituent effects of Phenanthroline-Derived Phosphine-Oxide extractants on extraction and separation performance towards U(VI)/Th(IV)

Designing and selecting extractants with high selectivity between uranium and thorium, and developing the relevant separation process is one of the key points to realize efficient utilization of nuclear resources in the thorium-uranium nuclear fuel cycle. In this work, we used four phenanthroline-derived phosphine-oxide extractants with different substituents and studied their extraction ability and separation effect on U(VI)/Th(IV) under different conditions. The Et2-BPPhen and Ph2-BPPhen extractants show weak and strong extraction abilities for U(VI) and Th(IV), respectively. The Et-Ph-BPPhen(R,R) and Et-Ph-BPPhen(R,S) extractants could co-extract U(VI) and Th(IV) under high acidity (DU(VI) > 300, DTh(IV) > 40, SFU(VI)/ Th(IV) < 7, 4 M HNO3), and show high selectivity towards U(VI) over Th(IV) at low acidity (SFU(VI)/ Th(IV) > 200, 0.1 M HNO3). Most Th(IV) can be stripped by adjusting the acidity of the aqueous phase, while U(VI) still remains in the organic phase (STh(IV) ＞ 95 %, SU(VI) < 5 %), so as to achieve the step-by-step process for co-extraction and selective separation. Then, the slope analysis and NMR titration (1H and 31P) determined BPPhen ligands could form ML-type complex with U(VI), and can simultaneously form M/L = 1:1 and 1:2 complexes with Th(IV). The stability constants of the metal–ligand complexes were fitted by UV–Vis spectroscopic titration to estimate coordination abilities of four ligands. Finally, the single-crystals of complexes with the structures of [UO2(L)(NO3)2], [Th(L)(NO3)4] and [Th(L)(H2O)2]·4(ClO4), (L = Et2-BPPhen/Et-Ph-BPPhen(R,R)/Et-Ph-BPPhen(R,S)/Ph2-BPPhen) were produced, and their coordination and packing mode were analyzed. This work contributes to revealing the structure–activity relationship of phenanthroline phosphine-oxide extractants and providing a reference for designing new extractants with high U(VI)/Th(IV) separation efficiency.