Decomposition Approach Research Articles

Separating cognitive and motor processes in the behaving mouse.

The cognitive processes supporting complex animal behavior are closely associated with movements responsible for critical processes, such as facial expressions or the active sampling of our environments. These movements are strongly related to neural activity across much of the brain and are often highly correlated with ongoing cognitive processes. A fundamental issue for understanding the neural signatures of cognition and movements is whether cognitive processes are separable from related movements or if they are driven by common neural mechanisms. Here we demonstrate how the separability of cognitive and motor processes can be assessed and, when separable, how the neural dynamics associated with each component can be isolated. We designed a behavioral task in mice that involves multiple cognitive processes, and we show that dynamics commonly taken to support cognitive processes are strongly contaminated by movements. When cognitive and motor components are isolated using a novel approach for subspace decomposition, we find that they exhibit distinct dynamical trajectories and are encoded by largely separate populations of cells. Accurately isolating dynamics associated with particular cognitive and motor processes will be essential for developing conceptual and computational models of neural circuit function.

Photovoltaic solar energy prediction using the seasonal-trend decomposition layer and ASOA optimized LSTM neural network model

As the global energy demand continues to produce, photovoltaic (PV) solar energy has emerged as a key Renewable Energy Source (RES) due to its sustainability and potential to reduce dependence on fossil fuels. However, accurate forecasting of Solar Energy (SE) output remains a significant challenge due to the inherent variability and intermittency of solar irradiance (SI), which is affected by factors such as weather conditions, geographic location, and seasonal patterns. Reliable prediction models are crucial for optimizing energy management, ensuring grid stability, and minimizing operational costs. To address these challenges, this research introduces an innovative method that integrates Robust Seasonal-Trend Decomposition (RSTL) with an Adaptive Seagull Optimisation Algorithm (ASOA)-optimized Long Short-Term Memory (LSTM) neural network. Using RSTL to differentiate between time series data into development, seasonal in nature, and residual factors, this methodology addresses SI’s unpredictable nature and intermittent operation and provides the basis for accurate predictions. ASOA improves LSTM features by constantly finding and exploiting resources and adopting motivation from seagulls’ collecting and migration behaviours. Parameter standardization employing ASOA, the RSTL decomposition approach, and the conceptual model of LSTM networks are all presented in this research work. The proposed method has been contrasted with conventional methods by applying a testing environment incorporating essential Meteorological Factors (MF) and historical SE datasets. The study of performance measurements (RMSE, MAE, and R2) demonstrates significant improvements in the accuracy of predictions. The research results highlight significant implications regarding subsequent studies and real-world uses in SE prediction, accentuating the positive impacts of incorporating accurate data decomposition and adaptive optimized performance.

Noisy Non‐Negative Tucker Decomposition With Sparse Factors and Missing Data

ABSTRACTTensor decomposition is a powerful tool for extracting physically meaningful latent factors from multi‐dimensional non‐negative data, and has been an increasing interest in a variety of fields such as image processing, machine learning, and computer vision. In this paper, we propose a sparse non‐negative Tucker decomposition and completion approach for the recovery of underlying non‐negative data under incompleted and generally noisy observations. Here the underlying non‐negative tensor data is decomposed into a core tensor and several factor matrices with all entries being non‐negative and the factor matrices being sparse. The loss function is derived by the maximum likelihood estimation of the noisy observations, and the norm is employed to enhance the sparsity of the factor matrices. We establish the error bound of the estimator of the proposed model under generic noise scenarios, which is then specified to the observations with additive Gaussian noise, additive Laplace noise, and Poisson observations, respectively. Our theoretical results are better than those by existing tensor‐based or matrix‐based methods. Moreover, the minimax lower bounds are shown to be matched with the derived upper bounds up to logarithmic factors. Numerical experiments on both synthetic data and real‐world data sets demonstrate the superiority of the proposed method for non‐negative tensor data completion.

Blind Source Separation Using Time-Delayed Dynamic Mode Decomposition

Blind Source Separation (BSS) is a significant field of study in signal processing, with many applications in various fields such as audio processing, speech recognition, biomedical signal analysis, image processing and communication systems. Traditional methods, such as Independent Component Analysis (ICA), often rely on statistical independence assumptions, which may limit their performance in systems with significant temporal dynamics. This paper introduces an extension of the dynamic mode decomposition (DMD) approach by using time-delayed coordinates to implement BSS. Time-delay embedding enhances the capability of the method to handle complex, nonstationary signals by incorporating their temporal dependencies. We validate the approach through numerical experiments and applications, including audio signal separation, image separation and EEG artifact removal. The results demonstrate that modification achieves superior performance compared to conventional techniques, particularly in scenarios where sources exhibit dynamic coupling or non-stationary behavior.

Rolling stock rescheduling in high-speed railway networks via a nested Benders decomposition approach

Rolling stock rescheduling in high-speed railway networks via a nested Benders decomposition approach

Tomato plant disease prediction system with a new framework SSMAN using advanced deep learning techniques

Agriculture plays a pivotal role in India's economy, and the timely detection of plant infections is essential to safeguard crops and prevent further spread of diseases. The conventional approach involves manual inspection of plant leaves to identify the specific type of disease, a task typically carried out by farmers or plant pathologists. In previous studies, you only look once (YOLO) and faster region-based convolutional neural network (R-CNN), machine learning algorithms were applied to datasets for detecting objects on tomato leaves which includes a total of images 2403 and got accuracies of 86 and 82 percent. In this paper, a deep convolutional neural network (DCNN) model proposed with a new framework separate, shift, and merge based AlexNet50 algorithm (SSMAN) is used to predict the disease at an earlier stage with higher accuracy. Among various pre-trained deep models, AlexNet emerges as the top performer, achieving the highest accuracy in disease classification. SSMAN can address anomalies in images by employing a class decomposition approach to scrutinize class boundaries. AlexNet exhibits a notable accuracy of 98.30% in successfully identifying tomato leaf diseases from images, with pre-trained new framework, superior to the original AlexNet architecture as well as traditional classification methods with other algorithms.

Spatial single-cell maps reveal ST6GAL1 promoting ovarian cancer metastasis.

In this study, spatial and single-cell transcriptome techniques were used to investigate the role of beta-galactoside alpha-2,6-sialyltransferase 1 (ST6GAL1) in promoting peritoneal metastasis in ovarian cancer epithelial cells. We collected single-cell transcriptomic (GSE130000) and spatial transcriptomic datasets (GSE211956) from the Gene Expression Omnibus and RNA-sequencing data from The Cancer Genome Atlas. The Robust Cell Type Decomposition (RCTD) approach was implemented to integrate spatial and single-cell transcriptomic data. In addition, pseudo-time trajectory analysis, cell-cell communication networks, transcription factor activity profiling, spatial interaction mapping, and prognostic significance of gene expression were assessed. A significant enrichment of ST6GAL1 was observed in the epithelial cells of ovarian cancer, particularly in peritoneal metastases, which exhibited elevated metabolic activity compared to primary tumors. The levels of ST6GAL1 were significantly high in peritumoral and adjacent non-tumorous tissues, with increased metabolic activity, while the tumor core demonstrated ST6GAL1-negative epithelial cells. Extensive cell-cell communication and transcription factor networks were unraveled, potentially influencing vascular permeability and intracellular signaling. Clinically, high expression of ST6GAL1 in epithelial cells is associated with diminished progression-free survival, indicating its prognostic potential. In conclusion, ST6GAL1 is likely to significantly impact the progression and metastasis of ovarian cancer.

Research on Physically Constrained VMD-CNN-BiLSTM Wind Power Prediction

Accurate forecasting of wind power is crucial for addressing energy demands, promoting sustainable energy practices, and mitigating environmental challenges. In order to improve the prediction accuracy of wind power, a VMD-CNN-BiLSTM hybrid model with physical constraints is proposed in this paper. Initially, the isolation forest algorithm identifies samples that deviate from actual power outputs, and the LightGBM algorithm is used to reconstruct the abnormal samples. Then, leveraging the variational mode decomposition (VMD) approach, the reconstructed data are decomposed into 13 sub-signals. Each sub-signal is trained using a CNN-BiLSTM model, yielding individual prediction results. Finally, the XGBoost algorithm is introduced to add the physical penalty term to the loss function. The predicted value of each sub-signal is taken as the input to get the predicted result of wind power. The hybrid model is applied to the 12 h forecast of a wind farm in Zhangjiakou City, Hebei province. Compared with other hybrid forecasting models, this model has the highest score on five performance indicators and can provide reference for wind farm generation planning, safe grid connection, real-time power dispatching, and practical application of sustainable energy.

Triple bottom line analysis of the decline in foreign tourist demand in Japan due to the COVID‐19 pandemic: Counterfactual structural decomposition approach

AbstractThis study developed a consumption‐endogenous input–output analysis framework and a novel counterfactual structural decomposition analysis (SDA) framework to assess the economic, social, and environmental effects of the 2020 decline in foreign tourists due to the COVID‐19 pandemic. The results show a pandemic‐induced loss of 33 million tourists, resulting in 3.44 trillion JPY in value‐added losses, employment declines for 868,976 people, and environmental benefits of an 11.6 Mt‐CO2 emissions reduction. Sectors hit the hardest include hotels, eating and drinking services, and wholesale and retail trade. The deterioration revealed a 100% reduction in value added from foreign visitors, whereas shifts in production contributed to a 3.6% increase in CO2 emissions. This study recommends government intervention, focusing on stipends for sectors with the highest value‐added losses and employment declines, as well as support funds for sectors that reduce environmental impact.

How Important are Carer Tasks in Determining Carer Quality of Life? Evidence from a Shapley Decomposition Approach

Abstract While there is a large literature that examines the determinants of carer quality of life, there is a dearth of research that focuses on the usual activities that carers perform and how they are related to carer-specific measures of quality of life. We use data from the Survey of Adult Carers in England to investigate the role that the tasks that carers perform play in determining carer quality of life. We model the relationship between the variables through a series of simple linear regressions, multiple linear regressions, and a Shapley decomposition. We find that all of the individual tasks that we have information on are statistically significant predictors of carer quality of life. In addition, the Shapley decomposition shows that, when taken together, carer tasks explain a higher proportion of variance in carer quality of life than any other group of determinants. These results are largely robust to different measures of carer tasks, different measures of carer quality of life, and different subgroups. We also find that there is evidence of a causal link between carer tasks and carer quality of life as carers report that their caring responsibilities have affected tangible health outcomes such as illnesses and GP visits. From a policy perspective, local government services that are used to support carers should know that policies designed to help carers with their tasks could have a large impact on carer quality of life.

Sub‐Tree Scheduling for Wireless Sensor Networks With Partial Coverage: Complexity and Polynomial‐Size Formulations

ABSTRACTGiven an undirected graph whose edge weights change over time slots, the sub‐tree scheduling for wireless sensor networks with partial coverage asks to partition the vertices of in non‐empty trees such that the total weight of the trees is minimized. In this article, we show that the problem is NP‐hard in both the cases where is part of the input and is a fixed instance parameter. In both our proofs we reduce the cardinality of the Steiner tree problem. Then, in order to provide easy‐to‐implement and effective computational tools to benchmark heuristics, we introduce new polynomial‐size integer linear programming formulations for the problem. Being defined by a polynomial number of variables and constraints, the formulations can be used to address instances of the problem by means of off‐the‐shelf mixed‐integer linear programming solvers with minimum implementation efforts. All proposed formulations share the property that the integrality requirement can be relaxed on subsets of variables. This enables several algorithmic choices to solve the models, including Benders' decomposition approaches and branch‐and‐bound with specific branching priorities. We experimentally identify the best resolution method for each formulation. Moreover, the experimental results obtained on benchmark instances of the problem, compared against those reported in the literature, support the effectiveness arising from using the new proposed formulations.

Inequality in COVID-19 vaccine acceptance and uptake: A repeated cross-sectional analysis of COVID vaccine acceptance and uptake in 13 countries.

Background COVID-19 vaccine hesitancy was a key barrier to ending the pandemic via mass immunisation. Objectives Assess magnitudes and differences in socioeconomic inequality in stated COVID-19 vaccine acceptance (hesitancy) and uptake. Methods Online surveys were conducted in 13 countries, collecting data from 15,337 and 18,189 respondents respectively. The investigation compares socioeconomic inequality in reported vaccine acceptance, measured in 2020-21 and subsequent uptake of vaccination in 2022. Inequalities are quantified using differences, ratios and the Erreygers adjusted concentration index. A regression decomposition approach is used to identify factors associated with inequality. Results Mean uptake levels were 87 %, while acceptance was lower at 77 %. The difference between the richest and the poorest quintile was as large as 23 percentage points in acceptance and 30 p.p. in uptake, both observed in France. Acceptance and uptake were pro-rich (regressive) in most countries. Nine countries reported pro-rich inequality in acceptance, and eight in uptake. Uptake was significantly less regressive than acceptance in Australia, China, India, and USA. Australia and Colombia were the only countries where vaccination uptake was pro-poor (progressive). Age, marital status and political ideology were correlated with socioeconomic inequalities in several countries in both waves, while gender and education were associated with acceptance, and health levels with uptake. Conclusion We found significant inequalities in vaccination acceptance and uptake across countries but inequality was generally lower in vaccine uptake than in acceptance. This suggests that inequalities can be reduced over time if adequate policies are in place to overcome hesitancy and reduce inequalities.

D-MGDCN-CLSTM: A Traffic Prediction Model Based on Multi-Graph Gated Convolution and Convolutional Long-Short-Term Memory.

Real-time and accurate traffic forecasting aids in traffic planning and design and helps to alleviate congestion. Addressing the negative impacts of partial data loss in traffic forecasting, and the challenge of simultaneously capturing short-term fluctuations and long-term trends, this paper presents a traffic forecasting model, D-MGDCN-CLSTM, based on Multi-Graph Gated Dilated Convolution and Conv-LSTM. The model uses the DTWN algorithm to fill in missing data. To better capture the dual characteristics of short-term fluctuations and long-term trends in traffic, the model employs the DWT for multi-scale decomposition to obtain approximation and detail coefficients. The Conv-LSTM processes the approximation coefficients to capture the long-term characteristics of the time series, while the multiple layers of the MGDCN process the detail coefficients to capture short-term fluctuations. The outputs of the two branches are then merged to produce the forecast results. The model is tested against 10 algorithms using the PeMSD7(M) and PeMSD7(L) datasets, improving MAE, RMSE, and ACC by an average of 1.38% and 13.89%, 1% and 1.24%, and 5.92% and 1%, respectively. Ablation experiments, parameter impact analysis, and visual analysis all demonstrate the superiority of our decompositional approach in handling the dual characteristics of traffic data.

Time to break up? The case for tailor-made digital platform regulation based on platform-governance standard types

The rise of hybrid-conglomerate platforms like Google, Apple, Microsoft, Amazon, and Meta (GAMAM) has led to significant market power concentration and negative competition implications, right down to calls for their potential breakups. To expand dominance, these platforms leverage extensive ecosystems with strategic control over resources and customer relationships, often at the expense of others. We conduct a qualitative meta-analysis of 87 empirical platform-governance problem cases from a regulatory perspective. Using a decomposition approach, we develop a taxonomy of competition problems induced by platform governance and identify four governance standard types (i.e., growth, consolidation, extension, and protect and capture), representing platform lifecycle phases from a regulatory perspective. Each standard type describes the platform owner’s governance strategy, consequent competition problems, and potential remedies. Our findings show how lack of regulation of digital platforms’ governance design has contributed to their growing market power and that effective regulatory intervention requires making platform governance more open and neutral. Moreover, we emphasize the need for platform governance regulation that shifts the burden of proof for regulatory compliance from regulators to platform owners.

Real-time modal decomposition of fiber laser beams using a spatial mode multiplexer.

A novel, to the best of our knowledge, approach for the modal decomposition of a fiber laser beam is demonstrated using a spatial mode multiplexer. Since the modal decomposition is carried out optically, this approach is able to obtain the modal content at speeds up to the GHz level. In order to demonstrate such performance, we have applied this approach to the modal analysis of a Q-switched pulse generated in a multimode fiber with alternating intra-pulse mode content.

Chinese import dominance and structural transformation in Africa

ABSTRACT This study analyzes the effect of China’s import dominance on Africa’s structural transformation, measured through the Shapley decomposition approach. A pooled mean group Autoregressive Distributed Lag (PMG-ARDL) model is analyzed using panel data from 1995–2018 for 21 countries. We find that Chinese imports of goods and services, like those from the rest of the world, increase Africa’s structural transformation in the long-run. However, the magnitude of the coefficient for China is larger than that of the rest of the world for both goods and services (total). The Chinese impact on Africa’s structural transformation is mainly through capital goods and other commercial services (such as ICT, financial, and construction), whose coefficients are larger than those of the rest of the world. Imposing barriers on Chinese imports is not a viable option for African countries. Instead, they should pursue policies that enrich the manufacturing sector, including adopting an Africa-wide trade agreement.

Runtime Analysis of Typical Decomposition Approaches in MOEA/D for Many-Objective Optimization Problems.

Decomposition-based multi-objective evolutionary algorithms (MOEAs) are popular methods utilized to address many-objective optimization problems (MaOPs). These algorithms decompose the original MaOP into several scalar optimization subproblems, and solve them to obtain a set of solutions to approximate the Pareto front (PF). The decomposition approach is an important component in them. This paper presents a runtime analysis of a MOEA based on the classic decomposition framework using the typical weighted sum (WS), Tchebycheff (TCH), and penalty-based boundary intersection (PBI) approaches to obtain an optimal solution for any subproblem of two pseudo-Boolean benchmark MaOPs, namely mLOTZ and mCOCZ. Due to the complexity and limitation of the theoretical analysis techniques, the analyzed algorithm employs one-bit mutation to generate offspring individuals. The results indicate that when using WS, the analyzed algorithm can consistently find an optimal solution for every subproblem, which is located in the PF, in polynomial expected runtime. In contrast, the algorithm requires at least exponential expected runtime (with respect to the number of objectives m) for certain subproblems when using TCH or PBI, even though the landscapes of all objective functions in the two benchmarks are strictly monotone. Moreover, this analysis reveals a drawback of using WS: the optimal solutions obtained by solving subproblems are more easily mapped to the same point in the PF, compared to the case of using TCH. When using PBI, a smaller value of the penalty parameter is a good choice for faster convergence to the PF but may compromise diversity. To further understand the impact of these approaches in practical algorithms, numerical experiments on using bit-wise mutation to generate offspring individuals are conducted. The findings of this study may be helpful for designing more efficient decomposition approaches for MOEAs in future research.

A Hybrid Data Decomposition and Deep Learning Approach for Solana Price Prediction Incorporating Market Factors

In this study, a hybrid data decomposition model for predicting the Solana (SOL) price is proposed, integrated by advanced signal processing and machine learning techniques. The model utilizes Variational Mode Decomposition (VMD) to decompose the Solana price series into 10 intrinsic modes, each representing different frequency components of the data. These 10 decomposed modes are then used as features, along with other relevant market factors, including Solana volume, halving index, Solana trend, and Bitcoin closing price. Then, the Bidirectional Long Short-Term Memory (BiLSTM) network is chosen to capture the complex temporal dependencies in these features and forecast future prices. To evaluate the efficacy of the approach, this study compares the hybrid models performance with a baseline LSTM model, which uses only raw historical price data. The results demonstrate that the hybrid model outperforms the benchmark model, showing higher predictive accuracy and robustness. A trading simulation for models was then conducted, and the findings indicate a significant potential for the experiment model to function as an effective trading support system, reinforcing its applicability in practical market environments. This work contributes to the field of cryptocurrency price prediction by offering a more sophisticated methodology that combines time series decomposition with deep learning techniques, providing valuable insights for traders and investors.

Leader-following privacy-preserving consensus control of nonlinear multi-agent systems: a state decomposition approach

This paper focuses on a nonlinear multi-agent system (MAS) in the presence of unknown dynamics and eavesdroppers. An output consensus control strategy is proposed based on an extended state observer, which achieves leader-following privacy-preserving consensus in a backstepping framework. Different from existing distributed average consensus approaches that require each follower to exchange and expose state information to its neighbours, our strategy avoids the requirement for communication during information interaction by decomposing each follower's state information into two sub-states. The status information is leaked, thereby achieving privacy preservation. Furthermore, for this class of MAS with unknown dynamics, we use an extended state observer to estimate the unknown dynamics and design an auxiliary system. The auxiliary variables generated by this auxiliary system combined with the back-stepping method can effectively compensate for dynamics. By combining graph theory knowledge and techniques such as Lyapunov functions, it is proven that the output-consensus tracking error of an MAS is ultimately bounded. Finally, the effectiveness of the control strategy is verified via an example.

Asymmetric autocorrelation in the crude oil market at multiple scales based on a hybrid approach of variational mode decomposition and quantile autoregression

Asymmetric autocorrelation in the crude oil market at multiple scales based on a hybrid approach of variational mode decomposition and quantile autoregression