Weight Assignment Research Articles

Assessing Climate Change Resilience in Central Indian Agriculture: A Regional Indicators-based Approach and Agro-climatic Zone Mapping

Climate change has adversely hampered the agricultural economy of India, especially central India. To get insight into the present level of climate change resilience in Central India (Madhya Pradesh, Maharashtra, Chhattisgarh, Southern UP) a composite climate change resilience capacity index (CCRCI) was developed for selected 102 districts using 50 climatic, soil, crop, livestock and socio-economic indicators in agriculture. Mann- Kendall non-parametric trend analysis was employed to evaluate long-term climatic trends (kharif 1981- summer 2023) for key climatic indicators like daily average temperature, precipitation, relative humidity and root zone soil wetness. Standard methodologies of index development like normalisation and principal component analysis (PCA) for weight assignment were executed. After developing CCRCI, agro-climatic zone-wise mapping was done for all the selected districts. Results revealed that Maharashtra had the largest number of high climate-resilience districts, followed by Madhya Pradesh with a mix of resilience levels in Chhattisgarh and Southern UP showing significant gaps in climate preparedness. The findings underscore the need for targeted interventions in low-resilience districts, particularly in agro-climatic Zones VII (Eastern Plateau and Hills Region) and IX (Western Plateau and Hills Region), where climate exposure and limited adaptability pose significant risks to agriculture. This mapping highlights the diversity of challenges and opportunities in central India, offering a framework for region-specific climate change resilience planning.

A DA-STCM Dual-channel Short Text Classification Method Based on Attention Mechanism

Short text classification is an important and challenging task in NLP. Compared with long text, short text suffers from insufficient semantic information. Based on a lot of theoretical and experimental analysis, a two-channel short text classification method, DA-STCM, is proposed. This method implements word correction by introducing the Aliyun service and introduces an attention mechanism in the channels to achieve weight assignment. Experimental results show that our proposed method is feasible in short text classification, and the classification accuracy is significantly improved.

IF-EDAAN: An information fusion-enhanced domain adaptation attention network for unsupervised transfer fault diagnosis

Unlike domain adaptation methods that rely on single-source information for transfer diagnosis, multi-source information-based domain adaptation methods can leverage the extensive diagnostic features derived from multiple sources of data. However, the issues of potential feature conflicts, the critical fault information loss, and high computational burdens still hinder effective applications of multi-source information domain adaptation for transfer diagnosis. For resolving these issues, this study proposes an unsupervised multi-source information domain adaptation approach for transfer fault diagnosis, which utilizes an information fusion-enhanced domain adaptation attention network (IF-EDAAN). Firstly, an information fusion method that converts multi-source information into a fused image using principal component analysis and signal-to-image conversion is employed to enhance and compress data from both the source and target domains. Then, a parameter-free attention mechanism (PFAM) module is proposed to adaptively focus on the domain-invariant temporal and spatial features of information fusion samples. Subsequently, the weight assignment module and joint maximum mean discrepancy metric strategy are proposed to mitigate negative transfer, thus enabling the effective extraction and alignment of domain-invariant temporal and spatial features. Finally, experiment validations on two rotating machinery datasets have been comprehensively elaborated to verify the efficacy and advantages of our proposed IF-EDAAN approach for transfer fault diagnosis across different working conditions. Experiment results have proved that our proposed IF-EDAAN approach can rapidly adapt to new transfer diagnostic scenarios with impressive performance and outperform several mainstream unsupervised domain adaptation approaches.

Multi-Label Learning with Distribution Matching Ensemble: An Adaptive and Just-In-Time Weighted Ensemble Learning Algorithm for Classifying a Nonstationary Online Multi-Label Data Stream

Learning from a nonstationary data stream is challenging, as a data stream is generally considered to be endless, and the learning model is required to be constantly amended for adapting the shifting data distributions. When it meets multi-label data, the challenge would be further intensified. In this study, an adaptive online weighted multi-label ensemble learning algorithm called MLDME (multi-label learning with distribution matching ensemble) is proposed. It simultaneously calculates both the feature matching level and label matching level between any one reserved data block and the new received data block, further providing an adaptive decision weight assignment for ensemble classifiers based on their distribution similarities. Specifically, MLDME abandons the most commonly used but not totally correct underlying hypothesis that in a data stream, each data block always has the most approximate distribution with that emerging after it; thus, MLDME could provide a just-in-time decision for the new received data block. In addition, to avoid an infinite extension of ensemble classifiers, we use a fixed-size buffer to store them and design three different dynamic classifier updating rules. Experimental results for nine synthetic and three real-world multi-label nonstationary data streams indicate that the proposed MLDME algorithm is superior to some popular and state-of-the-art online learning paradigms and algorithms, including two specifically designed ones for classifying a nonstationary multi-label data stream.

Surrogate-based model parameter optimization in simulations of the West African monsoon

Abstract. The West African monsoon (WAM) system is a critical climatic phenomenon with significant socio-economic impacts on millions of people. Despite many advancements in numerical weather and climate models, accurately representing the WAM remains a challenge due to its intricate dynamics and inherent uncertainties. Building upon our previous work utilizing the ICON (icosahedral nonhydrostatic) numerical model to construct statistical surrogate models for quantities of interest (QoIs) characterizing the WAM, this paper focuses on the optimization of the three uncertain model parameters of entrainment rate, fall speed of ice, and soil moisture evaporation fraction through innovative multi-objective optimization (MOO) techniques. The problem is approached in two distinct ways: (1) optimization of 15 designated QoIs, such as the latitude and magnitude of the African rain belt or African easterly jet, using existing surrogate models and (2) optimization of twelve 2D meteorological output fields, such as precipitation, cloud cover, and pressure, using new surrogate models that employ principal component analysis. The objectives subject to minimization in the MOO process are defined as the difference between the surrogate model and reference data for each QoI or output field. As reference data, Integrated Multi-satellitE Retrievals for the Global Precipitation Measurement (GPM IMERG) mission are used for precipitation, and the ERA5 reanalysis data from the European Centre for Medium-Range Weather Forecasts are used for all other quantities. The multi-objective optimization problems are tackled through two strategies: (1) assignment of weights with uncertainties to the objectives based on expert opinion and (2) variation in these weights in order to assess their influence on the optimal values of the uncertain model parameters. Results show that the ICON model is already generally well-tuned for the WAM system. However, a lower entrainment parameter would lead to a more accurate simulation of accumulated precipitation, averaged 2 m dew point temperature, and mean sea level pressure over the considered domain (15° W to 15° E, 0 to 25° N). An improvement in 2D output fields instead of QoIs is barely possible with the considered parameters, which confirms meaningful default values of the model parameters for the region. Nevertheless, optimal model parameters strongly depend on the assigned weights for the objectives. To further enhance the accuracy of climate simulations and potentially improve weather predictions, it is crucial to prioritize the refinement of the overall physical models, including the reduction in inherent structural errors, rather than solely adjusting the uncertain parameters in existing model parametrizations. Nevertheless, our methodology demonstrates the potential of integrating statistical and expert-driven approaches to assess and improve the simulation accuracy of the WAM. The findings underscore the importance of considering uncertainties in MOO and the need for a holistic understanding of the WAM's dynamics to enhance prediction skills.

A robust image watermarking framework based on U2-net encoder and loss function weight assignment

A robust image watermarking framework based on U2-net encoder and loss function weight assignment

TCN-Transformer Deep Network with Random Forest for Prediction of the Chemical Synthetic Ammonia Process.

It is of great significance to realize the accurate prediction of the key output response of the chemical synthetic ammonia process for optimizing system performance and operation monitoring. Because many key intermediate variables of complex systems are difficult to measure comprehensively, there are great difficulties and errors in mechanism analysis and identification modeling techniques. Based on random forest (RF) variable selection, a deep neural network combining temporal convolutional network (TCN) and transformer is proposed to predict the output variables of the synthetic ammonia process. The RF technique is used to select the principal input variables to increase the computational efficiency and the generalization ability of the network. A self-attention mechanism is used to assign biased weights to the data of the key feature variables. A TCN-Transformer network with encoding and decoding techniques is first designed to enhance the correlation of information between variable data, which can extract features of input variables and achieve dynamic modeling of multivariate feature sequences. The network is optimized using a multihead attention mechanism, and the key features are enhanced by probabilistic weight assignment to improve the prediction accuracy. Finally, by comparing with existing methods, the merit and applicability of the proposed network, R 2 = 0.8233, RMSE = 0.0032, and MAE = 0.0024, are verified for predicting the key output of carbon monoxide using offline data generated.

The Impact of Criteria Weights on Medical Equipment Selection

Selecting optimal medical equipment is a complex decision involving multiple criteria. This study aimed to assess the sensitivity of equipment selection outcomes to variations in both offer parameters and criteria weights in the context of a magnetic resonance imaging scanner selection where the analytic hierarchy process was used. The analysis involves a 2-pronged approach: (1) systematically modifying parameters of the winning offer to assess rank stability and (2) conducting a Monte Carlo simulation to evaluate the impact of varying criteria weights on the final ranking. Results indicated that although the winning offer generally maintained its rank, weight assignment, parameters variability, data preprocessing, and threshold definition exerted significant influence. These findings underscore the importance of conducting comprehensive sensitivity analyses to mitigate decision risks in medical equipment selection.

Natural or man-made disaster? Lessons from the extreme rain and flood disaster in Zhengzhou, China on "2021.7.20"

Driven by extreme weather events, precipitation-induced flood disasters are occurring more frequently, posing substantial threats to both economic development and public safety. Increased human production activities have further intensified the impact of flood disasters. However, understanding of the factors influencing flood disasters and their associated risk assessments remains limited. To better formulate flood prevention and disaster reduction strategies suited to local conditions, this paper takes the "7.20" extreme rainfall event in the main urban area of Zhengzhou, Henan Province, China, on July 20, 2021, as a case study and uses geographic detectors to incorporate human activities into the quantitative analysis of influencing factor contributions. Based on the three aspects of disaster incubation, disaster causation, and disaster bearing, this study proposes using the influence values obtained from geographic detectors as objective weight assignments for risk assessment, thereby conducting a locally adapted risk assessment of Zhengzhou's main urban area. Research results indicate that the "7.20" heavy rainstorm in Zhengzhou's main urban area involved a superposition of natural and human factors. Impervious surfaces had the highest explanatory power, followed by population density, confirming that this flood disaster arose from the interaction of multiple factors. The flood disaster risk assessment for Zhengzhou's main urban area shows higher risk levels in the central area and relatively lower levels in peripheral areas. The central area features flat terrain, with high population density and a large proportion of impervious surfaces. Among these, 22 subdistricts are located in extremely high-risk flood zones, while 6 subdistricts, classified as low-risk, account for over 60% of the low-risk area, making them relatively lower-risk communities. Comparison with flood waterlogging point data verifies the accuracy of the risk assessment through statistical analysis, allowing for further analysis of the spatial differentiation of flood risk. The findings of this study offer valuable insights for preventing and managing urban extreme rainfall disasters.

Ensembled Pretrained Model-Based Adaptive Sequential Trace Recognition for Moving Objects

In this paper, we propose an adaptive continuous trajectory recognition method for badminton sports scenarios. First, we adopt an integrated pre-training model with high generality and expressive ability as the infrastructure. By pre-training large-scale badminton game data, the model can learn the features of badminton sports from rich and diverse trajectory data. Second, to adapt to the trajectory differences in different scenarios, we introduce an adaptive mechanism. By extracting and encoding features from real-time acquired badminton motion trajectories, the model can adjust its own parameters and weight assignments according to the changes in the current scene to optimally recognize and track the motion targets. The algorithm also employs the Kalman filter aggregation Enhanced Correlation Coefficient (ECC) method of the motion model to improve the prediction accuracy. Finally, a series of experiments and comparisons are conducted to validate the effectiveness of the approach. The results show that our proposed adaptive continuous trajectory recognition method for badminton achieves better performance in different scenarios and various complexities, and has higher accuracy and robustness than the traditional method. The FDA-SSD model operates at 28.7[Formula: see text]fps, which is about 16.5% faster than the traditional SSD. In the target tracking experiments, the target tracking mean squared error is about 1.0%. In the target tracking experiments based on the FDA and geometrically constrained localization method, the root-mean-square error of the target tracking is less than 4.72[Formula: see text]cm.

Adaptive Performance Evaluation of Container Terminals Through Normalization and Parameter Analysis

Background: Container terminals are a pivotal part of global logistics networks, influencing supply chain reliability and port competitiveness. Traditional performance evaluation methods, such as KPI-based assessments or multi-criteria analyses, often fail in dynamic operational conditions with inherent uncertainty and variability. Methods: This study proposes a normalization-based framework to evaluate container terminal performance by standardizing operational parameters, including availability, non-productive operations, operation time, energy consumption, and throughput. The methodology involves parameter definition, normalization, weight assignment, index calculation, and performance classification. Results: The findings demonstrate that normalization ensures a transparent and adaptable evaluation framework. Sample calculations show how parameter weights influence terminal assessments across varied scenarios, confirming the robustness of the proposed method in capturing dynamic operational changes. Conclusions: Normalization offers a practical tool for enhancing container terminal efficiency and competitiveness. It enables decision-makers to adapt strategies to changing priorities, such as throughput maximization or energy efficiency, ensuring comprehensive and reliable performance assessments.

MEREC-Based Combined Framework for Multiple-Attribute Group Decision-Making in Probabilistic Linguistic Environment

The deployment of our country's innovation driven strategy has been implemented, and transforming the economic development mode has become an important content. It is particularly important to use finance to serve technological innovation and promote economic development. The efficiency evaluation of technology finance development is multiple-attribute group decision-making (MAGDM). Presently, the utilization of Logarithmic TODIM (LogTODIM) and CoCoSo approach was implemented to address the MAGDM challenges. To effectively evaluate the development of technology finance, the application of probabilistic linguistic term sets (PLTSs) has been illustrated as a method to characterize uncertain information. This research introduces the probabilistic linguistic LogTODIM-CoCoSo (PL-LogTODIM-CoCoSo) approach to address MAGDM concerns within PLTSs. Additionally, the MEREC approach is illustrated to handle the weight assignment process under PLTSs. Finally, numerical example for efficiency evaluation of technology finance development is put forward to validate the LogTODIM-CoCoSo approach.

STANet: A Novel Spatio-Temporal Aggregation Network for Depression Classification with Small and Unbalanced FMRI Data.

Background: Early diagnosis of depression is crucial for effective treatment and suicide prevention. Traditional methods rely on self-report questionnaires and clinical assessments, lacking objective biomarkers. Combining functional magnetic resonance imaging (fMRI) with artificial intelligence can enhance depression diagnosis using neuroimaging indicators, but depression-specific fMRI datasets are often small and imbalanced, posing challenges for classification models. New Method: We propose the Spatio-Temporal Aggregation Network (STANet) for diagnosing depression by integrating convolutional neural networks (CNN) and recurrent neural networks (RNN) to capture both temporal and spatial features of brain activity. STANet comprises the following steps: (1) Aggregate spatio-temporal information via independent component analysis (ICA). (2) Utilize multi-scale deep convolution to capture detailed features. (3) Balance data using the synthetic minority over-sampling technique (SMOTE) to generate new samples for minority classes. (4) Employ the attention-Fourier gate recurrent unit (AFGRU) classifier to capture long-term dependencies, with an adaptive weight assignment mechanism to enhance model generalization. Results: STANet achieves superior depression diagnostic performance, with 82.38% accuracy and a 90.72% AUC. The Spatio-Temporal Feature Aggregation module enhances classification by capturing deeper features at multiple scales. The AFGRU classifier, with adaptive weights and a stacked Gated Recurrent Unit (GRU), attains higher accuracy and AUC. SMOTE outperforms other oversampling methods. Additionally, spatio-temporal aggregated features achieve better performance compared to using only temporal or spatial features. Comparison with existing methods: STANet significantly outperforms traditional classifiers, deep learning classifiers, and functional connectivity-based classifiers. Conclusions: The successful performance of STANet contributes to enhancing the diagnosis and treatment assessment of depression in clinical settings on imbalanced and small fMRI.

Enhancing stability and flexibility of platoon control with an adaptive spacing policy

Connected and Automated Vehicles (CAVs) forming platoons have shown significant potential in enhancing traffic flow. This paper proposes a cooperative platoon control model using MPC integrated with the CTG spacing policy to improve both platoon stability and overall traffic performance. This integration offers greater flexibility and practicality compared to the CS-based model. Additionally, the control model includes a safety constraint with high flexibility to prevent collisions. We numerically analyse the asymptotic stability of the proposed control model to address its mathematical complexity. A wide range of parameter configurations and weight assignment schemes were tested to provide rigorous proof of the model's asymptotic stability. Numerical experiments show that the CTG-based model offers better stability than the CS-based model, though it leads to larger spacings at higher vehicle speeds. Moreover, traffic simulation results demonstrate that the CTG-based model outperforms the CS-based model in mitigating traffic oscillations and reducing congestion.

A footless stroll through Italian stress

Abstract Despite the fact that Italian has been studied intensely for many years, the intricate relationship between its syllable structure and its metrical facts (weight and stress assignment) still poses a very significant formal challenge to previously published theoretical accounts. In this paper, we provide a novel account of Italian stress within the framework of Strict CV Metrics. We show that this approach most accurately captures the empirical data of the language, while providing a formally simple analysis which does not require feet, binary or ternary. The analysis is computationally simple and derives the ‘three syllable’ window effect without arbitrarily stipulating the foot-size of the language or overgenerating forms.

A minimum cost and maximum fairness-driven multi-objective optimization consensus model for large-scale group decision-making

The rise of social media and e-democracy has driven a paradigm shift in decision-making, notably reflected in the changing ways of public participation and policymaking within decision-making processes. The increased focus on fairness and efficiency not only complicates the consensus-building process among diverse interests and perspectives, but also significantly adds to the complexity of decision-making and its implementation. In this context, balancing the interests of all parties while ensuring fairness and improving decision-making effectiveness becomes crucial. To address these challenges, this study develops a multi-objective optimization consensus framework for large-scale group decision-making (LSGDM) that integrates the interests of decision-makers (DMs) and a moderator, providing a more comprehensive tool. Specifically, this study first designs a DM weight determination method based on structural hole theory within fuzzy social networks. The proposed DM weight determination method effectively leverages the flexibility of fuzzy social networks and the comprehensiveness of structural hole theory to enhance the accuracy and reliability of weight assignment. Building on this, a novel clustering method based on the maximum group consensus level is developed, taking into account the varying importance of different DMs. Furthermore, a minimum cost and maximum fairness-driven multi-objective optimization LSGDM consensus model, referred to as MCMF-MO-LSGDM, is explored in this study. Finally, the utility and superiority of the constructed model are confirmed through comparative analysis and simulation experiments against existing related works.

Multi-criteria decision analysis using GIS in assessing suitability for a solar-powered biomass briquetting plant in the Gambella region, Ethiopia

Biomass briquetting presents a promising avenue for alternative cooking energy, enhancing livelihoods, and fostering sustainable development. This study underscores the abundant biomass resources in the Gambella region, primarily composed of savanna and woody savanna, which encompass 77 % of the land area, consisting mainly of forest and agricultural waste. Leveraging these resources can ensure a renewable and sustainable cooking energy supply, aligning with Sustainable Development Goals (SDGs) related to clean energy and environmental conservation. Consequently, this thesis endeavors to identify optimal sites for establishing solar-powered non-wooden biomass briquetting plants across the region. Various spatial and non-spatial datasets, including solar radiation, slope, land use/land cover (LULC), and proximity to roads, rivers, and towns, were utilized for area delineation and mapping. Parameters such as solar radiation, slope, and river streams were derived from 30 m resolution digital elevation models (DEMs). The Analytical Hierarchy Process (AHP) was employed to calculate criteria weights for overlay analysis, resulting in a suitable solar farm site map. The study reveals that land use/land cover exerts the most significant influence, with a weight of 46.58 %, followed by solar radiation strength (20.42 %), slope (15.52 %), proximity to roads (8.26 %), proximity to rivers (5.46 %), and proximity to towns (3.77 %). By integrating parameter suitability and weight assignment in ArcGIS spatial analysis, a suitability map was generated, highlighting highly suitable areas predominantly along the North-South axis through central Gambella. This area covers approximately 12,094.49 km², constituting 47 % of the study area. These findings have practical implications, as they can inform local policymakers and actors in strategically addressing the region's dire need for sustainable cooking energy. This contribution can support the development of localized renewable energy strategies and promote long-term energy security in line with local energy policies.

A Hybrid Fuzzy Evaluation Method for Quantitative Risk Classification of Barrier Lakes Based on an AHP Method Extended by D Numbers

The risk classification of barrier lakes is the key to conducting emergency treatment in a scientific manner. However, risk classification faces difficulties such as a short time for risk evaluation, complex evaluation indicators, difficulty in obtaining information quickly, and quantifying index weights. Based on this, this paper constructs a quantitative risk classification model for barrier lakes based on D-AHP. On the basis of studies on nearly 100 cases of barrier lakes, an eight-factor evaluation index system and quantitative classification are proposed. The methods of rapid calculation of reservoir capacity curve of barrier lakes and intelligent identification of particles on the surface of barrier bodies were developed, which realized the rapid acquisition of eight-factor evaluation index information in an emergency environment. The D-AHP method dealt with inconsistent weight assignment to evaluation factors by experts, which helped achieve weight quantification of eight factors. The risk assessment on 15 barrier lakes such as Tangjiashan barrier lake shows that the conclusions drawn for the risk classification method proposed in this paper are basically consistent with those of the traditional table-lookup method. However, the table-lookup method ignores cumulative loss impacts on the risk level of barrier lakes and considers the extremely severe loss of barrier lakes as a sufficient condition for the evaluation level to be grade I, and thus a deviation in the evaluation. The risk classification method proposed in this paper is more reasonable and reliable.

Evaluating China’s urbanization trajectory: an overextension or still in progress?

China’s urbanization has undergone a transformative journey since the initiation of the reform and opening-up policy in 1978, catalyzing economic growth while profoundly impacting its ecological and demographic landscapes. This study offers a systematic evaluation of China’s urbanization trajectory over the past 4 decades through the development of an indicator system encompassing three key dimensions: population urbanization, land urbanization, and economic urbanization. Using the entropy method for weight assignment, the analysis reveals a consistent upward trend in China’s comprehensive urbanization, with occasional sharp increases. Although population urbanization influences the overall index, land urbanization has outpaced both population and economic urbanization, indicating a pronounced dependence on land resources. This trend poses a potential risk of unsustainable urban growth if left unaddressed. The findings indicate that to achieve sustainable urban development, China must prioritize balancing the interplay between population and land, moving away from land-dependent strategies, and adopting a more balanced approach to urbanization. The quantitative analysis provides key insights into this imbalance, indicating that policies should integrate land use planning with population dynamics to promote holistic urban growth. Future research should investigate the long-term socio-economic and environmental impacts of land-centric urbanization and propose innovative strategies to guide China towards a sustainable urban future.

Dynamic multi teacher knowledge distillation for semantic parsing in KBQA

Knowledge base question answering (KBQA) is an important task of extracting answers from a knowledge base by analyzing natural language questions. Semantic parsing methods convert natural language questions into executable logical forms to obtain answers on the knowledge base. Conventional approaches often prioritize singular logical forms, overlooking the distinct strengths inherent in various logical frameworks for problem solving. Recognizing that different logical forms may excel in addressing specific types of questions, our aim is to harness these strengths. By integrating the strengths of different logical forms, we expect to achieve more comprehensive and effective semantic parsing solutions. In our paper, we propose a Dynamic Multi Teacher Knowledge Distillation for Semantic Parsing (DMTKD-SP). DMTKD-SP leverages a collection of teacher models, each mastering a unique logical form, to collaboratively guide a student model so that knowledge from different logical forms can be transferred into the student model. To achieve this, we employ a confidence-based weight assignment module to dynamically assign weights for each teacher model. Furthermore, we introduce a self-distillation mechanism to mitigate the confusion caused by simultaneous learning from multiple teachers. We evaluate DMTKD-SP across variants of the KQA Pro dataset, demonstrating an accuracy improvement of 0.35% on five types of questions, with a notable 0.75% improvement for Count questions.