Aggregation Method Research Articles

OPTIMAL HARVEST CONTROL OF PREDATOR–PREY SYSTEMS IN FISHERIES WITH STAGE STRUCTURE AND ADDITIONAL FOOD SUPPLY

In this paper, we consider a fishery predator–prey system with stage structure and additional food incorporating fluctuations in resource prices influenced by supply and demand. The fishery system can be regarded as a slow–fast system under some suitable assumptions. Through variable aggregation methods, we derive a simplified four-dimensional model governing the density of prey fish, the juvenile and adult predator densities, and fishing effort in the fishery. We perform a stability analysis of the simplified system and give the optimal harvesting policy by using Pontryagin’s maximum principle. In our analysis, we find that the catastrophe equilibrium point corresponding to overfishing leading to fish extinction is unstable, which indicates that the predator stage structure has an impact on the stability of the system. Moreover, we find that due to the additional food item the system appears to have prey-free equilibrium points, which indicates that the system does not collapse due to the extinction of one prey item. We also give thresholds for the amount of additional food needed to maintain the balance of the system under different circumstances.

Diversification in Business Valuation

Abstract The importance of the diversification and the related diversification factor in business valuation has not been studied in depth. In CAPM, due to the model assumptions, it is implied that an investor holds a perfectly diversified portfolio, which answers the question of diversification. The objective of this paper is to clarify the definition of diversification and to show how diversification effects can be incorporated into business valuation. Our research contribution entails demonstrating methods to capture the risk situation of an investor based on its asset allocation and then deriving the diversification effect from this assessment. As a methodological approach, we have opted for one that encompasses the most diverse degrees of diversification. Our analysis shows that this approach captures all non-hedged risks and thus performs a stand-alone valuation without diversification effects. If the diversification effect of a specific portfolio is to be included in the valuation, the analyst must shift from a stand-alone approach to a portfolio based approach, where the diversification factor cannot simply be equated with the correlation coefficient but must be calculated using various aggregation methods. Given that the conventional variance-covariance method excludes extreme risks, we propose the use of the copula approach. This approach can enhance risk modeling and yield more accurate results in diversification effect calculations. Our analysis demonstrates that it is possible to effectively model different diversification effects in business valuation. However, this entails substantial data expenses and demands a high degree of methodological expertise from the analyst.

Pothole detection‐you only look once: Deformable convolution based road pothole detection

AbstractThe detection of road potholes plays a crucial role in ensuring passenger comfort and the structural safety of vehicles. To address the challenges of pothole detection in complex road environments, this paper proposes a model focusing on shape features (pothole detection you only look once, PD‐YOLO). The model aims to overcome the limitations of multi‐scale feature learning caused by the use of fixed convolutional kernels in the baseline model, by constructing a feature extraction module that better adapts to variations in the shape of potholes. Subsequently, a cross‐stage partial network was designed using a one‐time aggregation method, simplifying the model while enabling the network to fuse information between feature maps at different stages. Additionally, a dynamic sparse attention mechanism is introduced to select relevant features, reducing redundancy and suppressing background noise. Experiments conducted on the VOC2007 and GRDDC2020_Pothole datasets reveal that compared to the baseline model YOLOv8, PD‐YOLO achieves improvements of 3.9% and 2.8% in mean average precision, with a frame rate of approximately 290 frames per second, effectively meeting the accuracy and real‐time requirements for pothole detection. The code and dataset for this paper are located at: https://github.com/woyijiankou/PD‐YOLO.

Reinforced Concrete Columns with Treated Recycled Concrete Aggregate: An Experimental and Theoretical Study

Six Reinforced Concrete (RC) columns composed of Treated Recycled Concrete Aggregate (TRCA) and Natural Aggregate (NA) were subjected to experimental and theoretical analyses to ascertain their axial compressive behavior. The method of soaking recyclable aggregate in a NAOH solution was then employed to treat it. The TRCA was subjected to replacement ratios of 20%, 40%, 60%, 80%, and 100% relative to the total weight of NA. The dimensions of the column were 700 mm, 150 mm, and 150 mm, respectively. The column was reinforced with steel of varying diameters. The transverse reinforcement was 6 mm in diameter, whereas the longitudinal reinforcement was 8 mm in diameter. To examine the axial compressive behavior of the columns, the final load values obtained from the static tests were revealed. The measured axial capacity of the columns was then compared with the theoretical values derived from the ACI codes. The incorporation of TRCA contents was observed to enhance the columns' axial capacity, as evidenced by the experimental results. However, the computed theoretical values were found to be more conservative than the experimental observations. This suggests that there is no risk involved in using TRCA and NA-TRCA columns in construction.

FA-MSVNet: multi-scale and multi-view feature aggregation methods for stereo 3D reconstruction

FA-MSVNet: multi-scale and multi-view feature aggregation methods for stereo 3D reconstruction

Comparative analysis of single-machine equivalent methods for heterogeneous PMSG-based wind farm with the VSC-HVDC system

This paper presents a comparative study of four single-machine equivalent methods used to simplify the analysis of small-signal stability (SSS) in grid-connected wind farms composed of multiple wind turbine generators (WTGs), particularly focusing on heterogeneous permanent magnet synchronous generator (PMSG)-based wind farms with a VSC-HVDC system. The four methods compared are (1) the dynamic aggregation method, (2) the average power or average control parameter method, (3) the weighted average method, and (4) the covering theorem method. The comparative analysis highlights the connections and differences among those four methods that help to gain a better understanding of their strengths and limitations as follows: (1) When the dynamic characteristics of individual PMSGs are different, the dynamic aggregation method may result in errors in assessing system SSS. (2) The average power and weighted average methods are accurate in assessing the system's SSS when a linear relationship exists between the system's oscillation modes and the PMSG output or control parameters. However, both methods may give erroneous SSS assessments when this linearity does not hold. (3) The weighted average method can accurately assess SSS when wind speeds differ across PMSGs, while the average wind speed method produces errors. (4) The covering theorem method is found to be conservative in SSS assessment. Finally, the methods are validated through simulations on two PMSG-based wind farm topologies connected to the grid with a VSC-HVDC system.

360 Layout Estimation via Orthogonal Planes Disentanglement and Multi-View Geometric Consistency Perception.

Existing panoramic layout estimation solutions tend to recover room boundaries from a vertically compressed sequence, yielding imprecise results as the compression process often muddles the semantics between various planes. Besides, these data-driven approaches impose an urgent demand for massive data annotations, which are laborious and time-consuming. For the first problem, we propose an orthogonal plane disentanglement network (termed DOPNet) to distinguish ambiguous semantics. DOPNet consists of three modules that are integrated to deliver distortion-free, semantics-clean, and detail-sharp disentangled representations, which benefit the subsequent layout recovery. For the second problem, we present an unsupervised adaptation technique tailored for horizon-depth and ratio representations. Concretely, we introduce an optimization strategy for decision-level layout analysis and a 1D cost volume construction method for feature-level multi-view aggregation, both of which are designed to fully exploit the geometric consistency across multiple perspectives. The optimizer provides a reliable set of pseudo-labels for network training, while the 1D cost volume enriches each view with comprehensive scene information derived from other perspectives. Extensive experiments demonstrate that our solution outperforms other SoTA models on both monocular layout estimation and multi-view layout estimation tasks.

DeepMulticut: Deep Learning of Multicut Problem for Neuron Segmentation From Electron Microscopy Volume.

Superpixel aggregation is a powerful tool for automated neuron segmentation from electron microscopy (EM) volume. However, existing graph partitioning methods for superpixel aggregation still involve two separate stages-model estimation and model solving, and therefore model error is inherent. To address this issue, we integrate the two stages and propose an end-to-end aggregation framework based on deep learning of the minimum cost multicut problem called DeepMulticut. The core challenge lies in differentiating the NP-hard multicut problem, whose constraint number is exponential in the problem size. With this in mind, we resort to relaxing the combinatorial solver-the greedy additive edge contraction (GAEC)-to a continuous Soft-GAEC algorithm, whose limit is shown to be the vanilla GAEC. Such relaxation thus allows the DeepMulticut to integrate edge cost estimators, Edge-CNNs, into a differentiable multicut optimization system and allows a decision-oriented loss to feed decision quality back to the Edge-CNNs for adaptive discriminative feature learning. Hence, the model estimators, Edge-CNNs, can be trained to improve partitioning decisions directly while beyond the NP-hardness. Also, we explain the rationale behind the DeepMulticut framework from the perspective of bi-level optimization. Extensive experiments on three public EM datasets demonstrate the effectiveness of the proposed DeepMulticut.

Transformer-guided Feature Pyramid Network for multi-view stereo

Feature Pyramid Network (FPN) is widely used in Multi-View Stereo (MVS) to extract multi-scale features, effectively enhancing both the quality and efficiency of reconstruction. However, the multi-scale features are simply fused by element-wise addition, ignoring the contextual relationship between them. To solve this problem, a Transformer-guided Feature Pyramid Network (TFPN-MVSNet) is proposed, which uses the self-attention mechanism to aggregate the long-range context information between multi-scale features. Firstly, the feature enhancement module is designed based on internal attention mechanism to calculate the importance of different parts within the feature sequence, which pays more attention to the features related to reconstruction. The feature aggregation module is designed based on cross attention mechanism to focus on the contextual information of multi-scale features. Secondly, the two modules are introduced into the multi-scale feature extraction network to enhance the three-stage features from coarse to fine. Finally, the Spatial Weighted Cost Volume Aggregation method (SWCA)uses the spatial attention mechanism to calculate the pixel weights at the same position in different views, which suppresses the negative impact of occluded pixels. Evaluated on the DTU dataset, the overall error is reduced by 0.062 mm compared to CasMVSNet, and by 0.012 mm and 0.019 mm compared to similar methods TransMVSNet and CostFormer, respectively. Our method also achieves competitive results on the Tanks & Temples and ETH3D datasets.

Sequential Manipulation Against Rank Aggregation: Theory and Algorithm.

Rank aggregation with pairwise comparisons is widely encountered in sociology, politics, economics, psychology, sports, etc. Given the enormous social impact and the consequent incentives, the potential adversary has a strong motivation to manipulate the ranking list. However, the ideal attack opportunity and the excessive adversarial capability cause the existing methods to be impractical. To fully explore the potential risks, we leverage an online attack on the vulnerable data collection process. Since it is independent of rank aggregation and lacks effective protection mechanisms, we disrupt the data collection process by fabricating pairwise comparisons without knowledge of the future data or the true distribution. From the game-theoretic perspective, the confrontation scenario between the online manipulator and the ranker who takes control of the original data source is formulated as a distributionally robust game that deals with the uncertainty of knowledge. Then we demonstrate that the equilibrium in the above game is potentially favorable to the adversary by analyzing the vulnerability of the sampling algorithms such as Bernoulli and reservoir methods. According to the above theoretical analysis, different sequential manipulation policies are proposed under a Bayesian decision framework and a large class of parametric pairwise comparison models. For attackers with complete knowledge, we establish the asymptotic optimality of the proposed policies. To increase the success rate of the sequential manipulation with incomplete knowledge, a distributionally robust estimator, which replaces the maximum likelihood estimation in a saddle point problem, provides a conservative data generation solution. Finally, the corroborating empirical evidence shows that the proposed method manipulates the results of rank aggregation methods in a sequential manner.

Reliable federated learning based on delayed gradient aggregation for intelligent connected vehicles

As an organic combination of the Internet of Vehicles and intelligent vehicles, Intelligent Connected Vehicles (ICVs) have very high research and application value. Traditional data application methods require the local aggregation of sensitive user data, which poses a threat to user data privacy. Federated learning (FL) is a promising machine learning method that leverages distributed, personalized datasets to enhance performance while preserving user privacy. However, in mobile environments, unreliable client data can degrade the global model, reducing accuracy. Additionally, the mobility of ICVs can destabilize the training process, prolonging model updates and diminishing aggregation accuracy. To address these challenges, this paper proposes a dynamic asynchronous aggregation method that improves both reliability and training efficiency in FL for mobile networks. Therefore, it becomes crucial to find reliable aggregation of mobile device participation in FL tasks. To this end, we propose a reliable FL scheme, which only selects reliable mobile devices to participate in model aggregation to improve the generalization ability of the model. In addition, we design a dynamic asynchronous aggregation method based on reputation scores without affecting the model. Reduce model training time without compromising performance. Through experimental analysis, it is proved that this method can improve the reliability and effectiveness of FL tasks in mobile networks.

A Stakeholder-Related Procedure Model for Social Sustainability Assessment

The importance of assessing the sustainability of companies and their activities is increasing. Especially since the implementation of the new Corporate Social Reporting Directive, even more companies are committed to reporting on the impacts of their businesses on sustainability. This is a challenge especially concerning the social dimension of sustainability. Some frameworks present various relevant social criteria that can be used as a basis for assessment. However, these do not provide detailed suggestions for handling the numerous methodological challenges of such a multi-criteria assessment: identification and selection of the relevant stakeholders, categories and indicators to measure the impacts on social sustainability, weighting and aggregation of these criteria, etc. Therefore, this paper contributes to the methodology of social sustainability assessment by presenting a procedure model for this specific assessment task. The novelty of the model results from its foundation by a review of methods for selection, normalisation, weighting and aggregation of social criteria, existing decision theory-based procedure models, as well as a stakeholder-oriented catalogue of criteria. The procedure model is structured hierarchically by subdividing the overall social sustainability-assessment task into different levels: stakeholders, categories, and indicators. Furthermore, appropriate methods are suggested for the single steps of the procedure model.

Durability of concrete containing carbonated recycled aggregates: A comprehensive review

The utilisation of carbonated recycled aggregates in concrete has been increasingly considered as an effective strategy for CO2 sequestration in the built environment and enhancement of concrete sustainability. Following up a pervious review on the role of carbonated recycled concrete aggregates in the mechanical properties of concrete, this paper presents a comprehensive review on the effects of carbonation treatment on the chemical compositions and physical properties of recycled concrete aggregates, as well as the role of carbonated recycled concrete aggregates in microstructure and durability-related properties including volume deformation, transport properties, chemical resistance, freeze-thaw resistance and fire resistance of concrete. A special focus is placed on the relationship between microstructure and durability-related properties of carbonated recycled aggregate concrete considering the effects of pre-treatment method, replacement level, curing age, water-to-binder ratio and quality of the original aggregates. The insights into the deterioration mechanism and strategies for improving the durability of carbonated recycled aggregate concrete are provided. This review summarises the recent advances in the field, followed by a discussion on the remaining challenges and opportunities for future research.

Scalable order dispatching through Federated Multi-Agent Deep Reinforcement Learning

Efficient order dispatching is crucial for online ride-hailing systems, directly influencing user experience and platform revenue. Traditional methods often focus on maximizing immediate revenue through local observations of individual vehicles, ignoring the long-term potential benefits, the dynamic nature of dispatching systems, and the importance of collaboration among distributed vehicles. This typically results in suboptimal performance. To address these issues, we propose FedMARL4OD, a novel Federated Multi-Agent Deep Reinforcement Learning framework designed to optimize order dispatching. This framework integrates local learning via Multi-Agent Reinforcement Learning (MARL) for individual vehicles and global learning via Federated Multi-Agent Reinforcement Learning (FedMARL) across all vehicles. Specifically, we introduce an innovative reward mechanism in local learning that considers both the current revenue of each order and the supply–demand dynamics of the system related to potential future revenue, thereby improving dispatching performance. Moreover, we introduce a scalable model aggregation method in global learning that explicitly models interactions among distributed vehicles to facilitate collaborative learning. By progressively integrating local and global insights through average parameter aggregation, this method not only reduces communication overhead and enhances the learning efficiency of agents, but also ensures system scalability and maintains data privacy. Extensive real-world simulations demonstrate that FedMARL4OD outperforms baseline methods, achieving a 9.17% increase in Accumulated Driver Income (ADI) and a 7.75% improvement in Order Response Rate (ORR). The ADI improvements demonstrate the framework’s effectiveness in boosting revenue, while the enhanced ORR indicates a quicker fulfillment of users’ requests, improving user experience.

Weight-Based Privacy-Preserving Asynchronous SplitFed for Multimedia Healthcare Data

Multimedia significantly enhances modern healthcare by facilitating the analysis and sharing of diverse data, including medical images, videos, and sensor data. Integrating AI for multimedia data classification shows promise in improving healthcare services, data analysis, and decision-making. However, ensuring privacy in AI-integrated healthcare systems remains a challenge, especially with data continuously transmitted over networks. Synchronous Federated Learning (FL) is designed to address these privacy concerns by allowing end devices to collaboratively train a machine learning model without sharing data. Nonetheless, FL alone does not fully resolve privacy issues and faces efficiency challenges, particularly with devices of varying computational capabilities. In this article, we introduce an Asynchronous Partial Privacy-preserving Split-Federated Learning (APP-SplitFed) approach for smart healthcare systems. This method reduces computational demands on resource-limited devices and uses a weight-based aggregation method to allow devices of differing computational power to contribute effectively, ensuring optimal model performance and rapid convergence. Additionally, we incorporate a secure aggregation method to prevent adversaries from identifying individual models owned by healthcare institutions.

Hypercube Pooling for Visual Semantic Embedding

Visual Semantic Embedding ( VSE ) is a primary model for cross-modal retrieval, wherein the global feature aggregator is a crucial component of the VSE model. In recent research, the General Pooling Operator ( GPO ) aggregator, which weighs the features reconstructed from the local feature set to aggregate, facilitates the related models to achieve good retrieval performance. However, the reason for the effectiveness remains to be explored. To enhance the rationality of aggregator designs, we analyze the reason from the perspective of feature space. Indeed, for each data, the local feature set forms a hypercube containing abundant data information, and the feature learned by GPO measures the hypercube, thereby representing the data. The geometric structure of the hypercube implies that the set containing all points within the hypercube is a convex set, so the feature learned by weighted aggregation is an interior point of the hypercube. However, using the interior point to measure the hypercube leads to some problems in feature representation and model optimization, as well as the reduction of retrieval efficiency caused by weight computation. For example, the related pair’s features may be far, while the unrelated ones may be close. To measure the hypercube more clearly and alleviate the problems mentioned above, we propose Hypercube Pooling ( HCP ) aggregator. Specifically, HCP concatenates the Max and Min Pooling features as the global features. This aggregation method has multiple advantages, e.g., the learned global feature represents all hyperplanes of the hypercube that contain critical information and hypercube geometric structure. Moreover, HCP adds normalization-before-concatenation and reduces the usual setting of margin in the loss function by half to avoid gradient loss caused by the difference in the feature value and dimensionality doubling. The experimental results on the Flickr30K and MSCOCO datasets show that the HCP model has excellent performance with high efficiency, confirming the correctness of the spatial analysis and the effectiveness of the HCP aggregator.

Data aggregation and routing in Mobile Ad hoc network: Introduction to Self-Adaptive Tasmanian Devil Optimization

Mobile Ad-Hoc Network (MANETs) is referred to as the mobile wireless nodes that make up ad hoc networks. The network topology may fluctuate on a regular basis due to node mobility. Each node serves as a router, passing traffic throughout the network, and they construct the network’s infrastructure on their own. MANET routing protocols need to be able to store routing information and adjust to changes in the network topology in order to forward packets to their destinations. While mobile networks are the main application for MANET routing techniques, networks with stationary nodes and no network infrastructure can also benefit from using them. In this paper, we proposed a Self Adaptive Tasmanian Devil Optimization (SATDO) based Routing and Data Aggregation in MANET. The first step in the process is clustering, where the best cluster heads are chosen according to a number of limitations, such as energy, distance, delay, and enhanced risk factor assessment on security conditions. In this study, the SATDO algorithm is proposed for this optimal selection. Subsequent to the clustering process, routing will optimally take place via the same SATDO algorithm introduced in this work. Finally, an improved kernel least mean square-based data aggregation method is carried out to avoid data redundancy. The efficiency of the suggested routing model is contrasted with the conventional algorithms via different performance measures.

An Equivalent Model for Frequency Dynamic Analysis of Large Power Grids Based on Regulation Performance Weighting Method

With the construction of the UHV (Ultra High Voltage) AC/DC hybrid power grid and the large-scale access to renewable energy such as wind power, frequency dynamic fluctuation has become a prominent problem affecting the safe and stable operation of large power grids. The expansion of the scale of the power system makes it impossible to use traditional fine modeling to analyze the power system. In order to reduce the calculation scale and storage capacity of power system frequency dynamic simulation, it is necessary to make appropriate equivalent simplification of the external system, so the appropriate dynamic equivalent method is of great significance. This paper mainly studies the equivalent model suitable for frequency dynamic analysis of large power grids. Firstly, the typical models of generator set and load are simplified, and the parameters that have a great influence on frequency in the simplified model are obtained through characteristic analysis. Then, a dynamic aggregation method of generator governor and prime mover parameters and load parameters based on regulation performance weighting (the parameters of the generator or load are weighted and summed according to its regulation ability on the system) is proposed. This method is applied to the simulation example of the East China Power Grid. The simulation proves that the frequency of the East China Power Grid before and after equivalence can be consistent under four different faults, which verifies the effectiveness of the equivalent method proposed in this paper in the frequency dynamic analysis of large power grids.

Laser Capture Microdissection of Tertiary Lymphoid Structures from Formalin-Fixed Paraffin-Embedded Sections of Canine Cutaneous and Subcutaneous Sarcomas for NanoString Direct RNA Counting.

Laser capture microdissection (LCM) of formalin-fixed, paraffin-embedded sections is a way to analyze gene expression of morphologically distinct areas of tissue, as microscopically visualized with stained tissue sections. Herein, I describe a method for laser dissecting lymphoid aggregates in canine cutaneous and subcutaneous sarcomas and their adjacent sarcoma tissue to determine the differential expression of RNA as determined by NanoString® nCounter technology. Canine soft tissue sarcomas (STS) are diversely derived mesenchymal neoplasms that, regardless of exact histogenesis, behave similarly and thus have been grouped together as a diagnostic entity. The risk of recurrence and/or metastasis depends on the extent of surgical excision and histologic grade. Lymphoid aggregates are described in these tumors but have not been characterized. In humans, lymphoid aggregates characterized as tertiary lymphoid structures (TLS) improve the prognosis of several tumors, including sarcomas. We sought to determine if RNA expressed by lymphoid aggregates in canine sarcomas was compatible with TLS RNA expression. This chapter describes tissue preparation, staining, laser capture microdissection, and RNA isolation in preparation for digital RNA counting.

Antibody Aggregation: A Problem Within the Biopharmaceutical Industry and Its Role in AL Amyloidosis Disease.

Due to the large size and rapid growth of the global therapeutic antibody market, there is major interest in understanding the aggregation of protein products as it can compromise efficacy, concentration, and safety. Various production and storage conditions have been identified as capable of inducing aggregation of polyclonal and monoclonal antibody (mAb) therapies such as low pH, freezing, light exposure, lyophilisation and increased ionic strength. The addition of stabilising excipients to these therapeutics helps to combat the formation of aggregates with future aggregation inhibition mechanisms involving the introduction of point mutations and glycoengineering within aggregation prone regions (APRs). Antibody aggregation also plays an integral role in the pathogenesis of a condition known as amyloid light chain (AL) amyloidosis which is characterised by the production of improperly folded and amyloidogenic immunoglobulin light chains (LCs). Current diagnostic tools rely heavily on histological staining with their future moving towards amyloid component identification and proteomic analysis. For many years, treatment options designed for multiple myeloma (MM) have been applied to AL amyloidosis patients by depleting plasma cell numbers. More recently, treatment strategies more specific to this condition have been developed with many designed to recognize amyloid fibrils and trigger their degradation without causing systemic plasma cell cytotoxicity. Amyloid fibrils in AL disease and aggregates in antibody therapeutics are both formed through the oligomerisation of misfolded / modified proteins attempting to reach a thermodynamically stable, free energy minimum that is lower than the respective monomers themselves. Although the final morphologies are different, by understanding the principles underlying such aggregation, we expect to find common insights that may contribute to the development of new and effective methods of antibody aggregation and/or amyloidosis management. We envision that this area of research will continue to be very relevant in both industry and clinical settings.