Adaptive Weight Research Articles

Adaptive similarity-guided self-merging network for few-shot semantic segmentation

Few-shot Semantic Segmentation (FSS) attempts to segment the new category with only a few labeled samples, presenting a significant challenge. Existing approaches primarily focus on leveraging category information from the support set to identify objects of the new category in the query image. However, these models often struggle when confronted with substantial differences between paired images. To address issues stemming from scenario differences and intra-class diversity, this paper proposes an adaptive similarity-guided self-merging network. Firstly, style differences of multi-level features are introduced to alleviate the network's sensitivity to scenario variations and learn an adaptive weight for the K-shot scheme. Secondly, a feature-mask bi-aggregation module is designed to learn an enhanced feature and an initial mask for the query image. Within this module, dynamic correlations cover all the spatial locations, providing global information crucial for feature and mask aggregation. Subsequently, a self-merging module is proposed to alleviate prototype bias. It merges a self-prototype derived from the initial mask with an adaptive weighted support prototype obtained from K support images. Finally, the target object is segmented using the enhanced feature and merging prototype, and segmentation results are further refined by predictions of base categories and an adjustment factor derived from multi-level style differences. The proposed method achieves 69.1% (1-shot) and 72.3% (5-shot) mIoU on the PASCAL-5i dataset, and 47.4% (1-shot) and 52.1% (5-shot) mIoU on the COCO-20i dataset. These results demonstrate state-of-the-art segmentation performance compared to mainstream methods.© 2017 Elsevier Inc. All rights reserved.

Optimizing microseismic monitoring: a fusion of Gaussian–Cauchy and adaptive weight strategies

Abstract In mining mineral resources, it is vital to monitor the stability of the rock body in real time, reasonably regulate the area of ground pressure concentration, and guarantee the safety of personnel and equipment. The microseismic signals generated by monitoring the rupture of the rock body can effectively predict the rock body disaster, but the current microseismic monitoring technology is not ideal. In order to address the issue of microseismic monitoring in deep wells, this research suggests a machine learning-based model for predicting microseismic phenomena. First, this work presents the random spare, double adaptive weight, and Gaussian–Cauchy fusion strategies as additions to the multi-verse optimizer (MVO) and suggests an enhanced MVO algorithm (RDGMVO). Subsequently, the RDGMVO-Fuzzy K-Nearest Neighbours (RDGMVO-FKNN) microseismic prediction model is presented by combining it with the FKNN classifier. The experimental section compares 12 traditional and recently enhanced algorithms with RDGMVO, demonstrating the latter’s excellent benchmark optimization performance and remarkable improvement effect. Next, the FKNN comparison experiment, the classical classifier experiment, and the microseismic dataset feature selection experiment confirm the precision and stability of the RDGMVO-FKNN model for the microseismic prediction problem. According to the results, the RDGMVO-FKNN model has an accuracy above 89%, indicating that it is a reliable and accurate method for classifying and predicting microseismic occurrences. Code has been available at https://github.com/GuaipiXiao/RDGMVO.

Federated regressive learning: Adaptive weight updates through statistical information of clients

Federated learning is a method for training models in a distributed environment where each client utilizes its local dataset to train a model and shares it with a server to create a global model. This approach offers various advantages, such as eliminating the need for local clients to directly transfer their data to the server. However, it also has limitations, including the potential for limited global model performance due to imbalanced local datasets. In this study, we propose a new model that evaluates the quality of each client’s local dataset based on its probability distribution and quantity. Based on this evaluation, the contribution of locally trained models to the global model is adjusted accordingly. Unlike previous studies, our proposed method addresses the issue of low-quality local models degrading the performance of the global model. This allows for the improvement of the global model’s performance without the need for complex processes, such as adding specially designed loss functions to local models or employing data augmentation techniques to enhance the quality of the dataset. Furthermore, the method of calculating the contribution of local models proposed in this study allows for the quantitative assessment of the performance of clients participating in federated learning based on their data collection capabilities, making it an industry-friendly approach. We conducted experiments using various benchmark datasets, simulating different scenarios that could occur in the real world. In most scenarios, except a few, our method showed superior performance on all evaluation metrics compared to existing studies reviewed in the paper.

SMDE: Unsupervised representation learning for time series based on signal mode decomposition and ensemble

Time series data pervades multiple domains, yet in real-world applications, there frequently exists a deficiency of labels to ascertain effective representations and enable efficient classification. In this work, we introduce SMDE, a unique time series contrastive learning framework, diverging from conventional techniques that predominantly concentrate on instance-level contrast. SMDE leverages signal decomposition and ensemble methodologies, enhancing our focus on localized mode alterations, within time series signals. We further introduce the global signal consistency and intrinsic mode consistency mechanisms to promote the robust learning of global and local attributes. To ensure more efficient convergence, we present the DE Circle loss furnished with an adaptive weighting mechanism, founded on global signal consistency and intrinsic mode consistency principles. The SMDE framework is designed to be applicable to both univariate and multivariate time series analysis, indicating its potential for a wide range of temporal data applications. Experiments on 128 univariate UCR datasets reveal that SMDE improves the average accuracy by 4.73% over existing techniques. Additionally, our experiments on 29 multivariate UEA datasets demonstrate an average accuracy improvement of 7.42% compared to current methodologies. Moreover, through extensive semi-supervised experimentation, SMDE demonstrates superior performance in 15 disparate semi-supervised configurations, attaining an equivalent performance level to supervised training with 100% labeled data, even with a minimal portion of the labels. The code is publicly available at https://github.com/haobinlaosi/smde.

Post-Processing Maritime Wind Forecasts from the European Centre for Medium-Range Weather Forecasts around the Korean Peninsula Using Support Vector Regression and Principal Component Analysis

Accurate wind data are crucial for successful search and rescue (SAR) operations on the sea surface in maritime accidents, as survivors or debris tend to drift with the wind. As maritime accidents frequently occur outside the range of wind stations, SAR operations heavily rely on wind forecasts generated by numerical models. However, numerical models encounter delays in generating results due to spin-up issues, and their predictions can sometimes exhibit inherent biases caused by geographical factors. To overcome these limitations, we reviewed the observations for the first 24 h of the 72-hour forecast from the ECMWF and then post-processed the forecast for the remaining 48 h. By effectively reducing the dimensionality of input variables comprising observation and forecast data using principal component analysis, we improved wind predictions with support vector regression. Our model achieved an average RMSE improvement of 16.01% compared to the original forecast from the ECMWF. Furthermore, it achieved an average RMSE improvement of 5.42% for locations without observation data by employing a model trained on data from the nearest wind station and then applying an adaptive weighting scheme to the output of that model.

Adaptive pessimism via target Q-value for offline reinforcement learning

Offline reinforcement learning (RL) methods learn from datasets without further environment interaction, facing errors due to out-of-distribution (OOD) actions. Although effective methods have been proposed to conservatively estimate the Q-values of those OOD actions to mitigate this problem, insufficient or excessive pessimism under constant constraints often harms the policy learning process. Moreover, since the distribution of each task on the dataset varies among different environments and behavior policies, it is desirable to learn an adaptive weight for balancing constraints on the conservative estimation of Q-value and the standard RL objectives depending on each task. To achieve this, in this paper, we point out that the quantile of the Q-value is an effective metric to refer to the Q-value distribution of the fixed data set. Based on this observation, we design Adaptive Pessimism via a Target Q-value (APTQ) algorithm that balances between the pessimism constraint and the RL objective; this leads the expectation of Q-value to stably converge to a given target Q-value from a reasonable quantile of the Q-value distribution of the dataset. Experiments show that our method remarkably improves the performance of the state-of-the-art method CQL by 6.20% on the D4RL-v0 and 1.89% on the D4RL-v2.

A detection based on particle filtering and multivariate time-series anomaly detection via graph attention network for automatic voltage control attack in smart grid

The Automatic Voltage Control (AVC) attack is a novel attack that targets voltage control instructions sent to generators from the dispatching center. A successful AVC attack can manipulate reactive power or terminal voltage of generators without being detected, causing the voltages of pilot buses to deviate from the reference values received from the dispatching center. This poses a threat to the safe and stable operation of power systems. This paper proposed a detection based on Particle Filtering (PF) and multivariate time-series anomaly detection via graph attention network (MTAD-GAT). Although each method can detect AVC attacks independently, the coordination of the two methods can be more effective. PF and MTAD are utilized to predict the voltage changes of the pilot bus in the next moment. To combine them, adaptive weights are employed, and an adaptive hybrid prediction can be calculated. The moment can be identified as attacked if the absolute value of the difference between the pilot bus voltage and the reference value exceeds a threshold automatically chosen by Peaks Over Thresholds (POT) theory. The proposed method has been validated through simulations on the IEEE 39-bus 6-partition Coordinated Secondary Voltage Control (CSVC) system and has shown to be effective.

Multi-order graph clustering with adaptive node-level weight learning

Current graph clustering methods emphasize individual node and edge connections, while ignoring higher-order organization at the level of motif. Recently, higher-order graph clustering approaches have been designed by motif-based hypergraphs. However, these approaches often suffer from hypergraph fragmentation issue seriously, which degrades the clustering performance greatly. Moreover, real-world graphs usually contain diverse motifs, with nodes participating in multiple motifs. A key challenge is how to achieve precise clustering results by integrating information from multiple motifs at the node level. In this paper, we propose a multi-order graph clustering model (MOGC) to integrate multiple higher-order structures and edge connections at node level. MOGC employs an adaptive weight learning mechanism to automatically adjust the contributions of different motifs for each node. This not only tackles hypergraph fragmentation issue but enhances clustering accuracy. MOGC is efficiently solved by an alternating minimization algorithm. Experiments on seven real-world datasets illustrate the effectiveness of MOGC.

To be global or personalized: Generalized federated learning with cooperative adaptation for data heterogeneity

As federated learning (FL) continues to advance, research has branched into two major directions: enhancing the individual global model and developing multiple personalized models. However, few studies took both orientations into consideration in parallel. The underlying reason lies in the objective heterogeneity between global and personalized models, where the former emphasizes generalization, while the latter focuses on specialization. The dilemma of sacrificing the personalized deviation in exchange for stable global enhancement, or forsaking the global model for personalization, is particularly acute in highly heterogeneous data scenarios (as a curse). To establish the coexistence of global and personalized models in highly heterogeneous data scenarios, we propose FedAKD, a generalized federated learning framework with adaptive knowledge distillation to optimizes both global and personalized models. Specifically, based on the similarity of predictive distributions over a reference dataset, two distinct adaptive weighting strategies are employed to match the divergent focuses of global and personalized optimization, leveraging data heterogeneity to foster cooperative adaptation and establish their coexistence (as a blessing). The client-side strategy through cluster-oriented optimization to facilitate the domain adaptation in local tasks. Meanwhile, the server-side strategy adjusts the global model to accommodate varying optimization directions from diverse implicit clusters. Experiments in label and feature shift settings demonstrate that our method outperforms state-of-the-art methods in both global and personalized performance with faster convergence [e.g. the accuracy improvements on the physical activity monitoring dataset (PAMAP2) for global and personalized models exceed 26.51% and 11.00%, respectively]. Furthermore, our method is equally applicable to real-world healthcare scenarios.

Adaptive Visual Control for Robotic Manipulators with Consideration of Rigid-Body Dynamics and Joint-Motor Dynamics

A novel cascade visual control scheme is proposed to tailor for electrically driven robotic manipulators that operate under kinematic and dynamic uncertainties, utilizing an uncalibrated stationary camera. The proposed control approach incorporates adaptive weight radial basis function neural networks (RBFNNs) to learn the behaviors of the uncertain dynamics of the robot and the joint actuators. The controllers are designed to nullify the approximation error and mitigate unknown disturbances through an integrated robust adaptive mechanism. A major advantage of the proposed approach is that prior knowledge of the dynamics of the robotic manipulator and its actuator is no longer required. The controller autonomously assimilates the robot and actuator dynamics online, thereby obviating the need for fussy regression matrix derivation and advance dynamic measurement to establish the adaptive dynamic parameter update algorithm. The proposed scheme ensures closed-loop system stability, bounded system states, and the convergence of tracking errors to zero. Simulation results, employing a PUMA manipulator as a testbed, substantiate the viability of the proposed control policy.

Robust multi-view clustering via structure regularization concept factorization

Recently, many concept factorization-based multi-view clustering methods have been proposed and achieved promising results on text multi-view data. However, existing methods are limited in the following two aspects. (1) The Frobenius norm used in these methods is sensitive to noise and outliers; (2) These methods ignore the global structural information of the data. To address the above problems, we propose a robust concept factorization framework for multi-view clustering, which not only improves the robustness but also fully exploits the available information of multi-view data. Specifically, L2,1-norm is used to evaluate the error of the factorization, thus eliminating the effect of outliers and improving robustness. In addition, to retain more structure information of the original data, the global and local structure information are taken into consideration simultaneously, which makes the learned low-dimensional matrix more discriminative. Further, to make use of the complementary information of the different views, we introduce an adaptive weight learning strategy to assign weights for different views. An iterative updating algorithm is proposed to solve the proposed optimization problem. We compare the proposed method with state-of-the-art alternative methods on benchmark multi-view data sets. The extensive experimental results show the effectiveness and superiority of the proposed method.

Research on thermal runaway early warning algorithm of lithium battery based on improved particle swarm algorithm optimized BP neural network

Abstract In response to the issues of false alarms and missed alarms in traditional fire alarm systems for energy storage station fire prevention and control, this study proposes a fire alarm approach employing improved PSO-BP neural networks. Firstly, we set adaptive inertial weights and asymmetric learning factors on the PSO algorithm that are automatically optimized as fitness changes to improve the optimization accuracy and convergence speed of the algorithm. Secondly, the thresholds or weights are mapped to random particles for training to obtain the optimal value. Finally, utilizing the Pyrosim software, a model of the battery cabinet was established, and the thermal runaway data samples were input into the neural network model for training. The test consequence indicates that the improved PSO-BP model achieved a 5% and 3.75% rise in precision relative to the neural network and PSO-BP model, respectively, while the frequency of iterations declined by 55% relative to the PSO-BP.

Bushing fault diagnosis based on SVM and the improved sparrow search algorithm

Abstract In order to address the issue of low precision in traditional bushing fault diagnosis, a bushing fault diagnosis method based on an improved sparrow search algorithm (ISSA) and support vector machine (SVM) is proposed in this paper. Firstly, the bushing vibration signals are extracted by wavelet packet, and the feature vectors are used as inputs for the SVM. In view of the impact of support vector machine parameters on the model, a sparrow search algorithm is proposed for intelligent optimization. To prevent reaching a local optimum, adaptive inertia weight is added based on the original approach. The final bushing fault diagnosis model is established by training. Comparison experiments with three fault diagnosis models, SSA-SVM, PSO-SVM, and SVM, found that the proposed method achieves complete diagnosis in a shorter time, and the diagnostic accuracy rate is 96.5%, which verifies the feasibility and effectiveness of the model.

An Effective Local Search Algorithm for Flexible Job Shop Scheduling in Intelligent Manufacturing Systems

As one of the most classical scheduling problems, flexible job shop scheduling problems (FJSP) find widespread applications in modern intelligent manufacturing systems. However, the majority of meta-heuristic methods for solving FJSP in the literature are population-based evolutionary algorithms, which are complex and time-consuming. In this paper, we propose a fast effective single-solution based local search algorithm with an innovative adaptive weighting technique (AWLS) for solving FJSP. The adaptive weighting technique assigns weights to each operation and adaptively updates them during the exploration. AWLS integrates a Tabu Search strategy and the adaptive weighting technique to smooth the landscape of the search space and enhance the exploration diversity. Computational experiments on 313 well-known benchmark instances demonstrate that AWLS is highly competitive with state-of-the-art algorithms in terms of both solution quality and computational efficiency, despite of its simplicity. Specifically, AWLS improves the previous best-known results in the literature on 33 instances and match the best-known results on the remaining ones except for only one under the same time limit of up to 300 s. As a strongly Non-deterministic Polynomia (NP)-hard problem which has been extensively studied for nearly half a century, breaking the records on these classic instances is an arduous task. Nevertheless, AWLS establishes new records on 8 challenging instances whose previous best records were established by a state-of-the-art meta-heuristic algorithm and a famous industrial solver.

Efficient Multi-View Clustering via Unified and Discrete Bipartite Graph Learning.

Although previous graph-based multi-view clustering (MVC) algorithms have gained significant progress, most of them are still faced with three limitations. First, they often suffer from high computational complexity, which restricts their applications in large-scale scenarios. Second, they usually perform graph learning either at the single-view level or at the view-consensus level, but often neglect the possibility of the joint learning of single-view and consensus graphs. Third, many of them rely on the k -means for discretization of the spectral embeddings, which lack the ability to directly learn the graph with discrete cluster structure. In light of this, this article presents an efficient MVC approach via u nified and d iscrete b ipartite g raph l earning (UDBGL). Specifically, the anchor-based subspace learning is incorporated to learn the view-specific bipartite graphs from multiple views, upon which the bipartite graph fusion is leveraged to learn a view-consensus bipartite graph with adaptive weight learning. Furthermore, the Laplacian rank constraint is imposed to ensure that the fused bipartite graph has discrete cluster structures (with a specific number of connected components). By simultaneously formulating the view-specific bipartite graph learning, the view-consensus bipartite graph learning, and the discrete cluster structure learning into a unified objective function, an efficient minimization algorithm is then designed to tackle this optimization problem and directly achieve a discrete clustering solution without requiring additional partitioning, which notably has linear time complexity in data size. Experiments on a variety of multi-view datasets demonstrate the robustness and efficiency of our UDBGL approach. The code is available at https://github.com/huangdonghere/UDBGL.

A Model Predictive Control Method With Adaptive Weighting Factors for Enhancing Performance of Modular Multilevel Converters

A Model Predictive Control Method With Adaptive Weighting Factors for Enhancing Performance of Modular Multilevel Converters

A FDA-based multi-robot cooperation algorithm for multi-target searching in unknown environments

Target search using a swarm of robots is a classic research topic that poses challenges, particularly in conducting multi-target searching in unknown environments. Key challenges include high communication cost among robots, unknown positions of obstacles, and the presence of multiple targets. To address these challenges, we propose a novel Robotic Flow Direction Algorithm (RFDA), building upon the modified Flow Direction Algorithm (FDA) to suit the characteristics of the robot’s motion. RFDA efficiently reduces the communication cost and navigates around unknown obstacles. The algorithm also accounts for scenarios involving isolated robots. The pipeline of the proposed RFDA method is outlined as follows: (1). Learning strategy: a neighborhood information based learning strategy is adopted to enhance the FDA’s position update formula. This allows swarm robots to systematically locate the target (the lowest height) in a stepwise manner. (2). Adaptive inertia weighting: An adaptive inertia weighting mechanism is employed to maintain diversity among robots during the search and avoid premature convergence. (3). Sink-filling process: The algorithm simulates the sink-filling process and moving to the aspect slope to escape from local optima. (4). Isolated robot scenario: The case of an isolated robot (a robot without neighbors) is considered. Global optimal information is only required when the robot is isolated or undergoing the sink-filling process, thereby reducing communication costs. We not only demonstrate the probabilistic completeness of RFDA but also validate its effectiveness by comparing it with six other competing algorithms in a simulated environment. Experiments cover various aspects such as target number, population size, and environment size. Our findings indicate that RFDA outperforms other methods in terms of the number of required iterations and the full success rate. The Friedman and Wilcoxon tests further demonstrate the superiority of RFDA.

MIXED GEOGRAPHICALLY WEIGHTED REGRESSION (MGWR) WITH ADAPTIVE WEIGHTING FUNCTION IN POVERTY MODELING IN NTT PROVINCE

Poverty modeling is a crucial economic and social development issue in various regions, including in East Nusa Tenggara (NTT) Province. This research proposes using the Mixed Geographically Weighted Regression (MGWR) model with an adaptive Bisquare weighting function to analyze variables influencing poverty levels in NTT Province. The MGWR model is an extension of the Geographically Weighted Regression (GWR), which allows some variables in the model to have local effects while others have global effects. The adaptive weighting function in the MGWR model enhances the analysis by providing different weights at each location according to its local characteristics, thus making the results more accurate and representative for each area. The data includes economic, social, and infrastructure variables from 22 districts/cities in NTT Province for 2023. The MGWR model with an adaptive weighting function is applied to model the relationship between these variables and poverty levels. The analysis integrates statistical software to manage and analyze spatial data. The study findings show that the MGWR model with an adaptive weighting function offers better estimates than the global regression and GWR models. The results revealed the smallest AIC value for the MGWR model at 104.1888, compared to the global regression model at 140.1427 and the GWR model at 117.6174. This model successfully identifies significant local and global variables and shows variations in influence at different locations in NTT Province. These findings provide valuable insights for policymakers and practitioners in designing and implementing more effective poverty alleviation strategies tailored to local conditions in NTT Province.

A weighted time embedding transformer network for remaining useful life prediction of rolling bearing

Data-driven remaining useful life (RUL) prediction is of vital importance to industrial equipment prognostics health management (PHM). The transformer algorithms have been applied for RUL prediction recently. RUL prediction is a typically time-correlated task. However, in most transformer-based RUL prediction methods, one of the main procedures, patch embedding, is usually implemented by linear-based or convolution-based approaches, which lacks consideration for time correlation feature extraction. Moreover, the time correlation features at different degradation states may be variable, which will make different contributions to RUL prediction. To this end, in this paper, a novel framework for RUL prediction named weighted time embedding transformer (WTE-Trans) is proposed. A WTE module is designed to enhance the capacity of the model to extract more discriminative time correlation features and impose different weights automatically. Concretely, the peak-to-peak values are calculated from input and transformed firstly to provide prior knowledge information, and then multiplied by a learnable mask to generate an adaptive weight. Afterwards, the adaptive weight is used to impose constraints on the transformed input. Secondly, multiple 3D convolution (3D-conv) modules are designed to integrate the deep features through the time axis. Finally, the shifted-window transformer block is adopted to complete the RUL prediction task. Experiments are carried out on the widely used PHM 2012 bearing dataset and an actual industrial bearing full-lifecycle dataset to verify the effectiveness and application value. The results and analysis have shown that lower prediction error can be achieved by the proposed method.

An improved particle swarm optimisation algorithm for optimum placement and sizing of biogas-fuelled distributed generators for seasonal loads in a radial distribution network

Optimal allocation is critical for effective planning and operation of grid connected distributed generator(s) (DGs) subject to efficient optimisation approach(es). In this paper, an improved particle swarm optimisation (IPSO) algorithm based on weighted randomised acceleration coefficients and adaptive inertia weight for dynamic movement of the particles towards an optimal solution is proposed. The technique is expected to determine optimal placement, sizing and power factor of biogas-fuelled distributed generators (B-DGs such as internal combustion engine (ICE) and fuel cells (FC)) in a radial distribution network. The proposed IPSO is applied to simultaneously optimise three technical objectives namely total active power loss (TAPL), voltage deviation (VD) and voltage stability index (VSI) considering load growth and seasonal voltage dependence. The proposed IPSO is validated using an IEEE 33 bus radial distribution network to evaluate its effectiveness through various combinations of B-DGs for different scenarios and cases with a maximum of 3 B-DGs. Some of the key findings indicate that operating 3 ICEs at optimal power factor reduces TAPL by 93.52 %, reduces VD by 99.62 % and improves VSI by 23.32 % compared to 61.80 % TAPL reduction, 94.77 % VD reduction and 17.89 % VSI improvement for 3 FCs operating at unity power factor. The proposed IPSO gives better results than the standard PSO in terms of solution quality, convergence speed and statistical results. It is also perceived to be better compared to most of the recent state-of-the-art optimization algorithms found in literature.