Coordination Modulation Research Articles

Modulating Coordination of Iron Atom Clusters on N,P,S Triply-Doped Hollow Carbon Support towards Enhanced Electrocatalytic Oxygen Reduction.

Constructing atom-clusters (ACs) with in situ modulation of coordination environment and simultaneously hollowing carbon support are critical yet challenging for improving electrocatalytic efficiency of atomically dispersed catalysts (ADCs). Herein, a general diffusion-controlled strategy based on spatial confining and Kirkendall effect is proposed to construct metallic ACs in N,P,S triply-doped hollow carbon matrix (MACs /NPS-HC, M=Mn, Fe, Co, Ni, Cu). Thereinto, FeACs /NPS-HC with the best catalytic activity for oxygen reduction reaction (ORR) is thoroughly investigated. Unlike the benchmark sample of symmetrical N-surrounded iron single-atoms in N-doped carbon (FeSAs /N-C), FeACs /NPS-HC comprises bi-/tri-atomic Fe centers with engineered S/N coordination. Theoretical calculation reveals that proper Fe gathering and coordination modulation could mildly delocalize the electron distribution and optimize the free energy pathways of ORR. In addition, the triple doping and hollow structure of carbon matrix could further regulate the local environment and allow sufficient exposure of active sites, resulting in more enhanced ORR kinetics on FeACs /NPS-HC. The zinc-air battery assembled with FeACs /NPS-HC as cathodic catalyst exhibits all-round superiority to Pt/C and most Fe-based ADCs. This work provides an exemplary method for establishing atomic-cluster catalysts with engineered S-dominated coordination and hollowed carbon matrix, which paves a new avenue for the fabrication and optimization of advanced ADCs.

Modulating Coordination of Iron Atom Clusters on N,P,S Triply‐Doped Hollow Carbon Support towards Enhanced Electrocatalytic Oxygen Reduction

AbstractConstructing atom‐clusters (ACs) with in situ modulation of coordination environment and simultaneously hollowing carbon support are critical yet challenging for improving electrocatalytic efficiency of atomically dispersed catalysts (ADCs). Herein, a general diffusion‐controlled strategy based on spatial confining and Kirkendall effect is proposed to construct metallic ACs in N,P,S triply‐doped hollow carbon matrix (MACs/NPS−HC, M=Mn, Fe, Co, Ni, Cu). Thereinto, FeACs/NPS−HC with the best catalytic activity for oxygen reduction reaction (ORR) is thoroughly investigated. Unlike the benchmark sample of symmetrical N‐surrounded iron single‐atoms in N‐doped carbon (FeSAs/N−C), FeACs/NPS−HC comprises bi‐/tri‐atomic Fe centers with engineered S/N coordination. Theoretical calculation reveals that proper Fe gathering and coordination modulation could mildly delocalize the electron distribution and optimize the free energy pathways of ORR. In addition, the triple doping and hollow structure of carbon matrix could further regulate the local environment and allow sufficient exposure of active sites, resulting in more enhanced ORR kinetics on FeACs/NPS−HC. The zinc‐air battery assembled with FeACs/NPS−HC as cathodic catalyst exhibits all‐round superiority to Pt/C and most Fe‐based ADCs. This work provides an exemplary method for establishing atomic‐cluster catalysts with engineered S‐dominated coordination and hollowed carbon matrix, which paves a new avenue for the fabrication and optimization of advanced ADCs.

Review of Carbon Support Coordination Environments for Single Metal Atom Electrocatalysts (SACS).

This topical review focuses on the distinct role of carbon support coordination environment of single-atom catalysts (SACs) for electrocatalysis. The article begins with an overview of atomic coordination configurations in SACs, including a discussion of the advanced characterization techniques and simulation used for understanding the active sites. A summary of key electrocatalysis applications is then provided. These processes are oxygen reduction reaction (ORR), oxygen evolution reaction (OER), hydrogen evolution reaction (HER), nitrogen reduction reaction (NRR), and carbon dioxide reduction reaction (CO2 RR). The review then shifts to modulation of the metal atom-carbon coordination environments, focusing on nitrogen and other non-metal coordination through modulation at the first coordination shell and modulation in the second and higher coordination shells. Representative case studies are provided, starting with the classic four-nitrogen-coordinated single metal atom (MN4 ) based SACs. Bimetallic coordination models including homo-paired and hetero-paired active sites are also discussed, being categorized as emerging approaches. The theme of the discussions is the correlation between synthesis methods for selective doping, the carbon structure-electron configuration changes associated with the doping, the analytical techniques used to ascertain these changes, and the resultant electrocatalysis performance. Critical unanswered questions as well as promising underexplored research directions are identified.

Chemical Reagent Localization and Recognition Algorithm for Robot Chemists Based on YOLOv5 and CRNN

Artificial intelligence and robotics are increasingly used in chemical experiments for reagent preparation, but it is still a challenge to accurately grasp the reagent bottle in small and dense scenarios. Therefore, precise positioning and identification of the reagent bottles are crucial. However, the different kinds of chemical reagents create complexity in target detection, making the task difficult. Therefore, we propose a model, named TA-YOLOv5, based on YOLOv5 for the task of chemical reagent localization. To enrich our dataset and prevent single-background overfitting, we employed Mosaic and Mix-Up data augmentation during dataset processing. Furthermore, Transformer Encoder and Coordinate Attention modules are utilized to enhance the feature expressive ability for both small target objects and global information during model training. Finally, the CIoU-NMS algorithm is utilized to optimize prediction box filtering in dense scenarios. In addition, for the task of chemical reagent classification, this paper uses the CRNN (Convolutional Recurrent Neural Network) algorithm to identify character information on the label of the reagent bottle, enabling the successful classification of the reagent bottle. The experimental results illustrate that TA-YOLOv5 achieves 98.49% precision on the self-made reagent bottles dataset, which is 4.12% higher than the YOLOv5 network model. Moreover, the CRNN network reached 97.6% accuracy on IIIT 5k dataset.

An underwater image enhancement model combining physical priors and residual network

AbstractDeep learning‐based methods have achieved notable performance for underwater image enhancement. However, previous studies are mostly focused on pursuing high similarity between the original image and the target, which incurs performance drop when the models are used for real‐world images. A new framework for underwater image enhancement is proposed to improve the generalization performance of enhancement. First, the coordinate attention module is integrated into the backbone network, which serves as a pre‐trained model, to strengthen the feature extraction capability of the network. Second, the backbone is finetuned by physical prior knowledge and real‐world images, in an unsupervised manner, to realize generalization from artificial images to real‐world images. Furthermore, a model protection mechanism is designed to guarantee the successful execution of the training. The experimental results indicate that the proposed method provides a powerful pre‐trained backbone network and the finetuning strategy can further solve the color distortion and improve the image sharpening, especially in the harsh real environment. Compared with relevant methods, the UCIQE and NIQE are, respectively, 0.525 and 4.149, with a 0.009–0.095 increase in UCIQE and a 0.256–1.032 decrease in NIQE compared to other methods.

Phosphorescence Enzyme-Mimics for Time-Resolved Sensitive Diagnostics and Environment-Adaptive Specific Catalytic Therapeutics.

Enzyme mimics (EMs) with intrinsic catalysis activity have attracted enormous interest in biomedicine. However, there is a lack of environmentally adaptive EMs for sensitive diagnosis and specific catalytic therapeutics in simultaneous manners. Herein, the coordination modulation strategy is designed to synthesize silicon-based phosphorescence enzyme-mimics (SiPEMs). Specifically, the atomic-level engineered Co-N4 structure in SiPEMs enables the environment-adaptive peroxidase, oxidase, and catalase-like activities. More intriguingly, the internal Si-O networks are able to stabilize the triplet state, exhibiting long-lived phosphorescence with lifetime of 124.5 ms, suitable for millisecond-range time-resolved imaging of tumor cells and tissue in mice (with high signal-to-background ratio values of ∼60.2 for in vitro and ∼611 for in vivo). Meanwhile, the SiPEMs act as an oxidative stress amplifier, allowing the production of ·OH via cascade reactions triggered by the tumor microenvironment (∼136-fold enhancement in peroxidase catalytic efficiency); while the enzyme-mimics can scavenge the accumulation of reactive oxygen species to alleviate the oxidative damage in normal cells, they are therefore suitable for environment-adaptive catalytic treatment of cancer in specific manners. We innovate a systematic strategy to develop high-performance enzymemics, constructing a promising breakthrough for replacing traditional enzymes in cancer treatment applications.

Self-assembly, structure and catalytic activity of Ni3 on TiO2: A triple-atom catalyst for hydrogen evolution

Triple-atom catalysts (TACs), structurally derived from single-atom catalysts (SACs) but beyond SACs in the active sites, have received increasing attention but are still in their infant stage. Using density functional theory, we study the self-assembly of the Ni3 trimer on TiO2 (Ni3/TiO2) by atom-by-atom deposition. Coordinatively unsaturated sites on the TiO2 surface are responsible for this self-assembly, resulting in different configurations of Ni3. According to the orientation relationship and lattice mismatch, an embryo of Ni crystal is thought to be born of triangle Ni3 trimer on TiO2. The hydrogen evolution reaction activity and mechanism of Ni3/TiO2 with different H coverages are evaluated using thermochemistry and kinetics calculations. Only at high H coverage would Ni3/TiO2 TACs exhibit a hydrogen production activity higher than that of Ni1/TiO2 SACs, indicating the matching relationship between multiple active sites and multi-step reaction intermediates for the active-site utilization. The quantum confinement effect throughout Nin/TiO2 (n = 1–3) is evidenced by the localization of metallic states of Nin. Our results not only open the possibility for synthesizing multimers on oxides by self-assembly, but also enrich the quantum control toolbox in few-atom catalysts by coordination modulation.

DEVELOPMENT OF A CARTESIAN COORDINATE MODULE TO IMPROVE THE ABILITY TO UNDERSTAND MATHEMATICAL CONCEPTS

Mathematics is very important in everyday life, because human mathematics can think logically and argue. Many students think that mathematics is learning that is not fun and results in students being less able to understand mathematical concepts so that the level of student learning decreases, plus the source material presented is lacking. So that researchers conduct research on module development that can support students in learning mathematics and improve students' abilities in understanding concepts. This study aims to develop a module that refers to increasing the ability to understand mathematical concepts, with the material presented is Cartesian coordinate material. The module development procedure in this study is the 4-D development model. Data collection techniques used are student learning outcomes tests and questionnaires. The instruments used were validation sheets, student response questionnaires and pretest-posttest validation sheets. Based on the validity test, the results of the research show that the Cartesian coordinate module is very valid with a validity level of 86.4%. The results of the practicality test in the limited trial with a total of 16 students obtained a very practical Cartesian coordinate module with a percentage of 90.3%, and a field trial with a total of 22 students obtained a very practical Cartesian coordinate module with a practicality level percentage of 85.2%. . The module has met the effectiveness criteria based on the results of limited trials with the acquisition of a learning completeness score of 0.60 in the medium category, the results of field trials with the acquisition of a learning completeness score of 0.73 in the high category. This shows that the developed module is valid, practical and effective. The researcher hopes that this module can be used in learning, especially Cartesian coordinate material to improve students' conceptual understanding abilities.

A Method for Detecting Key Points of Transferring Barrel Valve by Integrating Keypoint R-CNN and MobileNetV3

Industrial robots need to accurately identify the position and rotation angle of the handwheel of chemical raw material barrel valves during the process of opening and closing, in order to avoid interference between the robot gripper and the handwheel. This paper proposes a handwheel keypoint detection algorithm for fast and accurate acquisition of handwheel position and rotation pose. The algorithm is based on the Keypoint R-CNN (Region-based Convolutional Neural Network) keypoint detection model, which integrates the lightweight mobile network MobileNetV3, the Coordinate Attention module, and improved BiFPN (Bi-directional Feature Pyramid Network) structure to improve the detection speed of the model, enhance the feature extraction performance of the handwheel, and improve the expression capability of small targets at keypoint locations. Experimental results on a self-built handwheel dataset demonstrate that the proposed algorithm outperforms the Keypoint R-CNN model in terms of detection speed and accuracy, with a speed improvement of 54.6%. The detection accuracy and keypoint detection accuracy reach 93.3% and 98.7%, respectively, meeting the requirements of the application scenario and enabling accurate control of the robot’s rotation of the valve handwheel.

Three-dimensional lumbar spine generation using variational autoencoder.

The disease analysis of the lumbar spine often requires a large number of three-dimensional (3D) models. Currently, there is a lack of 3D model of the lumbar spine for research, especially for the diseases such as scoliosis where it is difficult to collect sufficient data in a short period of time. To solve this problem, we develop an end-to-end network based on 3D variational autoencoder for randomly generating 3D lumbar spine model. In this network, the dual path encoder structure is used to fit two individual variables, i.e., mean and variance. Spatial coordinate attention modules are added to the encoder to improve the learning ability of the network to the 3D spatial structure of the lumbar spine. To enhance the power of the network to reconstruct the lumbar spine, a regularization loss is added to constrain the distribution loss. Additionally, Gaussian noise layers are added to the decoder to improve the authenticity and diversity of generated model. The experiments were conducted on the data of the entire lumbar spine and the individual lumbar vertebra, respectively. The results showed that the voxel intersection over union was 0.588 and 0.684, the voxel Dice coefficient was 0.739 and 0.811, the average surface distance was 0.807 and 1.189, and the Hausdorff distance was 2.615 and 3.710, for the entire lumbar spine and individual lumbar vertebra, respectively. The developed approach is comparable to the most commonly used model generation method of statistical shape model (SSM) in both visual and objective indicators, while the developed approach does not require the landmarks that is needed in the SSM method. Therefore, this fully automatic method can be easily used for population-based modeling of the lumbar spine which has the potential to be a powerful clinical tool.

Integrating Care Coordination and Mental Health Research Into Dialysis Practice: Stakeholder Perspectives, Methods, and Outcomes

Despite many studies suggesting beneficial innovations for patients, few make it into clinical practice. This study aims to enhance patient care by facilitating effective dissemination of patient-centered outcomes research to health care workers in outpatient dialysis facilities, aided by the Patient-Centered Outcomes Research Institute's (PCORI) dissemination and implementation framework. Dissemination and implementation project. Outpatient hemodialysis facilities in the United States. We brought together panels of key stakeholders, which included researchers, patient subject matter experts, and dialysis personnel. Their role was to provide guidance on the content and methods for disseminating research findings. With a focus on 2 critical patient safety areas-care coordination or care transitions and mental or behavioral health-we developed virtual education modules. These modules were then made available to outpatient dialysis facilities by the national 5-Diamond Patient Safety Program. In 2022, the training was used by more than 2,500 dialysis facilities and approximately 40,000 dialysis staff in the care coordination module, and by more than 300 dialysis facilities and 5,000 staff for the mental health module. Cumulatively, the modules affected more than 179,000 patients. Evidence of efficacy was the significant increase in trainee knowledge of research findings and implementation considerations (P≤0.05). Potential selection bias because dialysis facilities that did not participate in the program may differ significantly from those that did, which may affect generalizability. In addition, variable timing in release of the different modules may have influenced uptake by facilities. By using key stakeholder guidance and accessible virtual education modules, the implementation framework shows promise in effectively disseminating research findings within outpatient dialysis settings. This method potentially carries implications for broader health care settings as well. Our study addresses a common health care challenge-many promising ideas for improving patient care never actually reach the patients. We aimed to bridge the dissemination gap by sharing research with health care workers in outpatient dialysis, promoting evidence-based practice. We collaborated with experts, patients, and dialysis personnel to develop easy-to-understand educational materials focused on 2 critical topics: care coordination and mental health. In 2022, our training benefited more than 2,500 facilities and 40,000 staff for care coordination, and 300 facilities with 5,000 staff for mental health, positively affecting more than 179,000 patients. We found that the training significantly increased knowledge among staff. Our approach shows promise for sharing research effectively in dialysis centers and potentially in other health care settings.

Управление информационной инфраструктурой малого предприятия с учетом дизайна продукции

The relevance of managing the enterprise information infrastructure, including the introduction of new modules into the existing architecture, is governed by the necessity to ensure a high degree of information protection and to improve the business process efficiency. 
 The article discusses modelling and implementing a new product design coordination module at several levels of a small enterprise’s infrastructure. Specific methods for managing the built infrastructure include business process automation, vulnerability analysis, information security, monitoring and managing changes. Examples of infrastructure management at different levels are considered, as well as the methods for implementing a new module and controlling it based on standards. To create a new module, a model development was carried out at the hardware level, which made it possible to optimise the system structure and reduce the load on the servers. Such standards as GOST R ISO / IEC 27001-2013 and GOST R ISO / IEC 27002-2015 were used, which ensured the security and protection of company data, as well as the Meta Object Facility (MOF) standard was applied, which made it easy to integrate the new module into the existing infrastructure. The study results show that introducing a new module can improve the enterprise’s information infrastructure, reduce the time for approval and improve the product quality, as well as decrease the likelihood of errors and information leaks and diminish the enterprise’s costs. It is recommended to use ISO/IEC and ITIL standards for efficient management of the enterprise’s information infrastructure.

Surface defect detection method of wooden spoon based on improved YOLOv5 algorithm

The available surface defect detection methods for disposable wooden spoons still involve screening with the naked eye. This detection method is not only inefficient but also accompanied by problems such as false detection and missed detection. Therefore, this paper proposes a detection method based on an improved YOLOv5 network model (YOLOv5-TSPP). This method uses the K-Means ++ algorithm to cluster the target samples in the data set to obtain anchor frames that are more in line with different target scales. The Coordinate Attention module is added to the backbone network of the YOLOv5 network model to improve the feature extraction ability of the model. A new SPP module is added to the backbone network to increase the important features in the receptive field extraction network to improve the detection accuracy of small targets. The experimental results show: The YOLOv5-TSPP algorithm has better detection performance and the mAP of defect detection reaches 80.3%, which is 9.2% higher than that of the YOLOv5 algorithm. Among them, the detection accuracy of black knot defect reached 98.6%, the detection accuracy of back crack defect reached 92.1%, and the detection accuracy of mineral line defect reached 92.3%.

LE-YOLOv5: A Lightweight and Efficient Road Damage Detection Algorithm Based on Improved YOLOv5

Road damage detection is very important for road safety and timely repair. The previous detection methods mainly rely on humans or large machines, which are costly and inefficient. Existing algorithms are computationally expensive and difficult to arrange in edge detection devices. To solve this problem, we propose a lightweight and efficient road damage detection algorithm LE-YOLOv5 based on YOLOv5. We propose a global shuffle attention module to improve the shortcomings of the SE attention module in MobileNetV3, which in turn builds a better backbone feature extraction network. It greatly reduces the parameters and GFLOPS of the model while increasing the computational speed. To construct a simple and efficient neck network, a lightweight hybrid convolution is introduced into the neck network to replace the standard convolution. Meanwhile, we introduce the lightweight coordinate attention module into the cross-stage partial network module that was designed using the one-time aggregation method. Specifically, we propose a parameter-free attentional feature fusion (PAFF) module, which significantly enhances the model’s ability to capture contextual information at a long distance by guiding and enhancing correlation learning between the channel direction and spatial direction without introducing additional parameters. The K-means clustering algorithm is used to make the anchor boxes more suitable for the dataset. Finally, we use a label smoothing algorithm to improve the generalization ability of the model. The experimental results show that the LE-YOLOv5 proposed in this document can stably and effectively detect road damage. Compared to YOLOv5s, LE-YOLOv5 reduces the parameters by 52.6% and reduces the GFLOPS by 57.0%. However, notably, the mean average precision (mAP) of our model improves by 5.3%. This means that LE-YOLOv5 is much more lightweight while still providing excellent performance. We set up visualization experiments for multialgorithm comparative detection in a variety of complex road environments. The experimental results show that LE-YOLOv5 exhibits excellent robustness and reliability in complex road environments.

Interactive Efficient Multi-Task Network for RGB-D Semantic Segmentation

Semantic segmentation is significant for robotic indoor activities. However, relying solely on RGB modality often leads to poor results due to limited information. Introducing other modalities can improve performance but also increases complexity and cost, making it unsuitable for real-time robotic applications. To address the balance issue of performance and speed in robotic indoor scenarios, we propose an interactive efficient multitask RGB-D semantic segmentation network (IEMNet) that utilizes both RGB and depth modalities. On the premise of ensuring rapid inference speed, we introduce a cross-modal feature rectification module, which calibrates the noise of RGB and depth modalities and achieves comprehensive cross-modal feature interaction. Furthermore, we propose a coordinate attention fusion module to achieve more effective feature fusion. Finally, an instance segmentation task is added to the decoder to assist in enhancing the performance of semantic segmentation. Experiments on two indoor scene datasets, NYUv2 and SUNRGB-D, demonstrate the superior performance of the proposed method, especially on the NYUv2, achieving 54.5% mIoU and striking an excellent balance between performance and inference speed at 42 frames per second.

Translated article] Consensus recommendations on the preventive treatment of migraine

ObjectiveThe objectives are to know the opinion of neurologists and hospital pharmacists on those aspects still under debate regarding the role of anti-Calcitonin Gene-related Peptide monoclonal antibodies in the preventive treatment of migraine. To identify those controversies that still exist. To propose agreed recommendations for improvement of care. And to promote access of clinicians and patients to these new treatments in the prevention of migraine with biological drugs, in order to improve patient care and follow-up. MethodologyRecommendations for the use of biological drugs in the prevention of migraine were identified and evaluated through the Delphi consensus methodology, proposing 88 statements grouped into 3 themes: a clinical module that deals with the management of biological treatments in migraine; a patient module that discusses patient education and adherence improvement strategies; and a coordination module that includes statements related to strategies to improve joint work between the two groups. The 9-point Likert ordinal scale was used to score these recommendations and, subsequently, the data was statistically analysed through different metrics. ResultsAfter both rounds of voting, consensus was reached in agreement on 71 of the 88 statements (80.7%), leaving 1 statement (1.1%) with consensus in disagreement and 16 remaining as indeterminate (18.2%). ConclusionsThe high degree of consensus indicates that the opinion of neurologists and hospital pharmacists on the role of anti-Calcitonin Gene-related Peptide monoclonal antibodies in the preventive treatment of migraine is very similar and allows identifying those controversies that still exist, to improve the care and follow-up of patients with migraine.

AFCANet: An adaptive feature concatenate attention network for multi-focus image fusion

For multi-focus image fusion, the existing deep learning based methods cannot effectively learn the texture features and semantic information of the source image to generate high-quality fused images. Thus, we develop a new adaptive feature concatenate attention network named AFCANet, which adaptively learns cross-layer features and retains the texture features and semantic information of images to generate visually appealing fully focused images. In AFCANet, the encoder-decoder network is used as the backbone network. In the unsupervised training stage, an adaptive cross-layer skip connection mode is designed, and a cross-layer adaptive coordinate attention module is built to acquire meaningful information from the image along with ignoring unimportant information to obtain a better image fusion effect. In addition, in the middle of the encoder-decoder network, we also introduce an effective channel attention module to fully learn the output of the encoder, and accelerate network convergence. In the inference stage, we apply the pixel-based spatial frequency fusion rules to fuse the adaptive features learned by the encoder, which can successfully combine the texture and semantic information of the image and produce a more precise decision map. Extensive experiments on public datasets and the HBU-CVMDSP dataset show that our AFCANet can effectively improve the accuracy of the decision map in the focus and defocus regions, as well as improve the ability to retain the abundant details and edge features of the source image.

Improved EfficientNet for corn disease identification.

Corn is one of the world's essential crops, and the presence of corn diseases significantly affects both the yield and quality of corn. Accurate identification of corn diseases in real time is crucial to increasing crop yield and improving farmers' income. However, in real-world environments, the complexity of the background, irregularity of the disease region, large intraclass variation, and small interclass variation make it difficult for most convolutional neural network models to achieve disease recognition under such conditions. Additionally, the low accuracy of existing lightweight models forces farmers to compromise between accuracy and real-time. To address these challenges, we propose FCA-EfficientNet. Building upon EfficientNet, the fully-convolution-based coordinate attention module allows the network to acquire spatial information through convolutional structures. This enhances the network's ability to focus on disease regions while mitigating interference from complex backgrounds. Furthermore, the adaptive fusion module is employed to fuse image information from different scales, reducing interference from the background in disease recognition. Finally, through multiple experiments, we have determined the network structure that achieves optimal performance. Compared to other widely used deep learning models, this proposed model exhibits outstanding performance in terms of accuracy, precision, recall, and F1 score. Furthermore, the model has a parameter count of 3.44M and Flops of 339.74M, which is lower than most lightweight network models. We designed and implemented a corn disease recognition application and deployed the model on an Android device with an average recognition speed of 92.88ms, which meets the user's needs. Overall, our model can accurately identify corn diseases in realistic environments, contributing to timely and effective disease prevention and control.

Управление информационной инфраструктурой малого предприятия с учетом дизайна продукции

The relevance of managing the enterprise information infrastructure, including the introduction of new modules into the existing architecture, is governed by the necessity to ensure a high degree of information protection and to improve the business process efficiency. 
 The article discusses modelling and implementing a new product design coordination module at several levels of a small enterprise’s infrastructure. Specific methods for managing the built infrastructure include business process automation, vulnerability analysis, information security, monitoring and managing changes. Examples of infrastructure management at different levels are considered, as well as the methods for implementing a new module and controlling it based on standards. To create a new module, a model development was carried out at the hardware level, which made it possible to optimise the system structure and reduce the load on the servers. Such standards as GOST R ISO / IEC 27001-2013 and GOST R ISO / IEC 27002-2015 were used, which ensured the security and protection of company data, as well as the Meta Object Facility (MOF) standard was applied, which made it easy to integrate the new module into the existing infrastructure. The study results show that introducing a new module can improve the enterprise’s information infrastructure, reduce the time for approval and improve the product quality, as well as decrease the likelihood of errors and information leaks and diminish the enterprise’s costs. It is recommended to use ISO/IEC and ITIL standards for efficient management of the enterprise’s information infrastructure.

High-Resolution Remote Sensing Image Segmentation Algorithm Based on Improved Feature Extraction and Hybrid Attention Mechanism

Segmentation of high-resolution remote sensing images is one of the hottest topics in deep learning. Compared to ordinary images, high-resolution remote sensing images possess characteristics such as higher intra-class diversity and lower inter-class separability. Additionally, the objects in these images are complex and have smaller sizes. Aiming at the classical segmentation network in remote sensing images, there are some problems, such as inaccurate edge object segmentation, inconsistent segmentation of different types of objects, low detection accuracy, and a high false detection rate. This paper proposes a new hybrid attention model (S-CA), a new coordinate efficient channel attention module (C-ECA), and a new small-target feature extraction network (S-FE). The S-CA model enhances important spatial and channel features in shallow layers, allowing for more detailed feature extraction. The C-ECA model utilizes convolutional layers to capture complex dependencies between variations, thereby better capturing feature information at each position and reducing redundancy in feature channels. The S-FE network can capture the local feature information of different targets more effectively. It enhances the recognition and classification capabilities of various targets and improves the detection rate of small targets. The algorithm is used for segmentation in high-resolution remote sensing images. Experiments were conducted on the public dataset GID-15 based on Gaofen-2 satellite remote sensing images. The experimental results demonstrate that the improved DeepLabV3+ segmentation algorithm for remote sensing images achieved a mean intersection over union (mIoU), mean pixel accuracy (mPA), and mean precision (mP) of 91.6%, 96.1%, and 95.5%, respectively. The improved algorithm is more effective than current mainstream segmentation networks.