Benchmark Methods Research Articles

Daily runoff prediction based on lightweight Mamba with partial normalization

ABSTRACT Runoff prediction serves as the cornerstone for the effective management, allocation, and utilization of water resources, playing a key role in hydrological research. This study employs a newly reported deep learning model, Mamba, to forecast river daily runoff and compared the proposed model with various benchmark methods, including statistical models, machine learning methods, recurrent neural networks, and attention-based models. Application of these models is implemented on three hydrological stations situated along the middle and lower reaches of the Mississippi River. Daily runoff from 1983 to 2023 were used to build the model for 7-day prediction. Findings demonstrate the superiority of the Mamba model over its counterparts, showcasing its potential as a backbone model. In response to the necessity for a more lightweight approach, a refined variant of the Mamba model is proposed, called LightMamba. LightMamba incorporates partial normalization and MPM (Multi-Path-Mamba) to enhance its efficacy in discerning nonlinear trends and capturing long-term dependencies within the streamflow data. Notably, LightMamba achieves commendable performance with an average NSE of 0.904, 0.907, and 0.900 on the three stations. This study introduces an innovative backbone model for time series forecasting, which offers a novel approach to hybrid modeling for future daily runoff prediction.

Jointly Embedding Protein Structures and Sequences through Residue Level Alignment

The relationships between protein sequences, structures, and functions are determined by complex codes that scientists aim to decipher. While structures contain key information about proteins' biochemical functions, they are often experimentally difficult to obtain. In contrast, protein sequences are abundant but are a step removed from function. In this paper, we propose residue level alignment (RLA)—a self-supervised objective for aligning sequence and structure embedding spaces. By situating sequence and structure encoders within the same latent space, RLA enriches the sequence encoder with spatial information. Moreover, our framework enables us to measure the similarity between a sequence and structure by comparing their RLA embeddings. We show how RLA similarity scores can be used for binder design by selecting true binders from sets of designed binders. RLA scores are informative even when they are calculated given only the backbone structure of the binder and no binder sequence information, which simulates the information available in many early-stage binder design libraries. RLA performs similarly to benchmark methods and is orders of magnitude faster, making it a valuable new screening tool for binder design pipelines. Published by the American Physical Society 2024

Benchmarking for a New Railway Accident Classification Methodology and Its Database: A Case Study in Mexico, the United States, Canada, and the European Union

Rail accidents have decreased in recent years, although not significantly if measured by train accidents recorded in the last six years. Therefore, it is essential to identify weaknesses in the implementation of security and prevention systems. This research aims to study the trend and classification of railway accidents, as well as analyze public databases. Using the business management method of benchmarking, descriptive statistics, and a novel approach to the Ishikawa diagram, this study demonstrates best practices and strategies to reduce accidents. Unlike previous studies, this research specifically examines public databases and provides a framework for developing the standardization of railway accident causes and recommendations. The main conclusion is that the proposed classification of railway accident causes, and its associated database, ensures that agencies, researchers, and the government have accessible, easily linkable, and usable data references to enhance their analysis and support the continued reduction of accidents.

A Local-level App vs A National-level App: Evaluation of M-Grocery Apps From The UX and The Service Performance Perspective

In Indonesia, the increase in internet users, reaching 215.63 million in 2022-2023, has facilitated the growth of mobile shopping applications like Sayurbox and Beceran, which cater to daily needs such as groceries and fresh food items. Despite receiving high user ratings, these applications face technical issues that could impact user satisfaction and company revenue. This study aims to evaluate the service quality and user experience of the Sayurbox and Beceran applications using the M-S-QUAL and UX Benchmarking methods. The M-S-QUAL method assesses service quality across nine dimensions, while UX Benchmarking evaluates user satisfaction, ease of use, error counts, success rates, and task completion times. The results of UX Benchmarking reveal that Sayurbox has fewer errors and higher user satisfaction compared to Beceran, which has faster loading times but more errors. The M-S-QUAL analysis indicates that both applications have negative gap values in most service attributes, with Sayurbox performing slightly better than Beceran. Sayurbox received a score of -0.25 for the value gap on the M-S-QUAL scale, while Beceran received a score of -0.41 for the value gap.

Adaptive Forecasting of Nuclear Power Plant Operational Status Under Sensor Concept Drift Using a Bridging Distribution Adaptive Network.

A large number of sensors are required to collect information during the operation of nuclear power plants to ensure their absolutely safe operation. However, because of the unique nature of nuclear reactions, the physical environment of nuclear power production is prone to changes, leading to concept drift in the data collected by the sensors. Concept drift describes the phenomenon of sample distribution changing over time, which typically negatively impacts the model's training and inference processes. We found that nongradual distribution changes could be guided by generating transitional intermediary distributions within the distribution, thereby achieving a gradual change process. Based on this, we designed a bridging distribution adaptive network (BDAN), which consisted of identical-depth TDoA (time difference of arrival) homomorphic backbone neural networks on both sides with a latent adaptive bridging module in the middle. By calculating the distribution differences over multiple timesteps, a series of bridge distributions were generated to guide the gradients in the latent space, updating the parameters of the latent adaptive guiding module in a directional manner and enabling the model to perceive nongradual distribution changes in the time domain. Experimental results showed that the BDAN outperformed the previous state-of-the-art benchmark methods by 5.6% in terms of mean squared error in the nuclear power data prediction task under concept drift, achieving the best fault prediction performance.

Multisource representation learning for pediatric knowledge extraction from electronic health records

Electronic Health Record (EHR) systems are particularly valuable in pediatrics due to high barriers in clinical studies, but pediatric EHR data often suffer from low content density. Existing EHR code embeddings tailored for the general patient population fail to address the unique needs of pediatric patients. To bridge this gap, we introduce a transfer learning approach, MUltisource Graph Synthesis (MUGS), aimed at accurate knowledge extraction and relation detection in pediatric contexts. MUGS integrates graphical data from both pediatric and general EHR systems, along with hierarchical medical ontologies, to create embeddings that adaptively capture both the homogeneity and heterogeneity between hospital systems. These embeddings enable refined EHR feature engineering and nuanced patient profiling, proving particularly effective in identifying pediatric patients similar to specific profiles, with a focus on pulmonary hypertension (PH). MUGS embeddings, resistant to negative transfer, outperform other benchmark methods in multiple applications, advancing evidence-based pediatric research.

An Autotuning Hybrid Method with Bayesian Optimization for Road Edge Extraction in Highway Systems from Point Clouds

In transportation infrastructure systems, feature images and spatial characteristics are generally utilized as complementary elements derived from point clouds for road edge extraction, but the involvement of one or more hyperparameters in each makes the extraction complicated. This study proposes an autotuning hybrid method with Bayesian optimization for road edge extraction in highway systems. The hybrid method combines the strengths of 2D feature images and 3D spatial characteristics while also automatically tuning the hyperparameter combination using Bayesian optimization. The hyperparameters encompass high and low pixel gradient thresholds, neighborhood radius, and normal vector threshold. Later, the point cloud dataset of national highways in Henan Province, China, is taken as the case study to evaluate the performance of the proposed method against three benchmark methods in two typical road scenarios: straight and curved edges. Experimental results show that the proposed method outperforms the benchmarks in detection quality and accuracy. It can serve as a decision-making tool to complement traditional manual road surveying, enabling efficient and automated road edge extraction in highway systems.

SRPNet: stroke risk prediction based on two-level feature selection and deep fusion network.

Stroke is one of the major chronic non-communicable diseases (NCDs) with high morbidity, disability and mortality. The key to preventing stroke lies in controlling risk factors. However, screening risk factors and quantifying stroke risk levels remain challenging. A novel prediction model for stroke risk based on two-level feature selection and deep fusion network (SRPNet) is proposed to solve the problem mentioned above. First, the two-level feature selection method is used to screen comprehensive features related to stroke risk, enabling accurate identification of significant risk factors while eliminating redundant information. Next, the deep fusion network integrating Transformer and fully connected neural network (FCN) is utilized to establish the risk prediction model SRPNet for stroke patients. We evaluate the performance of the SRPNet using screening data from the China Stroke Data Center (CSDC), and further validate its effectiveness with census data on stroke collected in affiliated hospital of Jining Medical University. The experimental results demonstrate that the SRPNet model selects features closely related to stroke and achieves superior risk prediction performance over benchmark methods. SRPNet can rapidly identify high-quality stroke risk factors, improve the accuracy of stroke prediction, and provide a powerful tool for clinical diagnosis.

Low Computational Cost for Multiple Waypoints Trajectory Planning: A Time‐Optimal‐Based Approach

In the field of mobile robots, achieving minimum time in executing trajectories is crucial for applications like delivery, inspection, and search and rescue. In this article, a novel time‐optimal planner based on optimization methods is introduced. Despite the high computational cost associated with such methods, the solution calculates time‐optimal multi‐waypoint trajectories, achieving results in the order of milliseconds. The proposed method formulates a time‐optimal trajectory using the Pontryagin's maximum principle as a policy. By utilizing a point mass model, the planner generates trajectories that are adaptable to different robot models. The approach incorporates a definition of a search space to guarantee convergence while considering the system limits. Simulation and real‐world experiments are performed to validate the feasibility of our method with different configurations. Simulation results compared to a benchmark method demonstrate our approach's superior performance in terms of computational time, achieving near‐optimal solutions. In addition, in the real‐world experiments, the integration of the method into practical applications is validated.

Heterogeneous graph neural network with hierarchical attention for group-aware paper recommendation in scientific social networks

In recent years, the academic groups established in Scientific Social Networks (SSNs) have not only facilitated collaboration among researchers but also enriched the relations in SSNs, providing valuable information for paper recommendation tasks. However, existing paper recommendation methods rarely consider group information and they fail to fully leverage the group information due to the heterogeneous and complex relations between researchers, papers, and groups. In this paper, a heterogeneous graph neural network with hierarchical attention, named HHA-GPR, is proposed for group-aware paper recommendation. Firstly, a heterogeneous graph is constructed based on the interactions of researchers, papers, and groups in SSNs. Secondly, a random walk-based sampling strategy is utilized to sample highly correlated heterogeneous neighbors for researchers and papers. Thirdly, a hierarchical attention network with intra-type and inter-type attention mechanisms is designed to aggregate the sampled neighbors and comprehensively model the complex relations among the heterogeneous neighbors. More specifically, an intra-type attention mechanism is introduced to aggregate the neighbors of the same type, and an inter-type attention mechanism is employed to combine the embeddings of different types to form the ultimate node embedding. Extensive experiments are conducted on the real-world CiteULike and AMiner datasets, and the experimental results demonstrate that our proposed method outperforms other benchmark methods with an average improvement of 5.3 % in Precision, 5.6 % in Recall, and 5.1 % in Normalized Discounted Cumulative Gain (NDCG) across both datasets.

Prediction of Lithium-Ion Battery Health Using GRU-BPP

Accurate prediction of lithium-ion batteries’ (LIBs) state-of-health (SOH) is crucial for the safety and maintenance of LIB-powered systems. This study addresses the variability in degradation trajectories by applying gated recurrent unit (GRU) networks alongside principal component analysis (PCA), Granger causality, and K-means clustering to analyze the relationships between operating conditions—such as temperature and load profiles—and battery performance degradation. This paper uses a publicly accessible dataset derived by aging three prismatic LIB cells under a realistic forklift operation profile. First, we identify the features that are relevant to driving variance, then we employ the winning algorithm of K-means clustering for the classification of operational states. Granger causality later investigates the inter-group relationships. Our GRU-BPP model achieves an RMSE value of 0.167 and an MAE of 0.129 for the reference performance testing (RPT) dataset and an RMSE of 0.032 with an MAE of 0.025 for the aging dataset, thus outperformed benchmark methods such as GRU, LME, and XGBoost. These results further enhance the predictiveness and robustness of this approach and yield a holistic solution to the conventional challenges in battery management and their remaining useful life (RUL) predictions.

Fairness in online vehicle-cargo matching: An intuitionistic fuzzy set theory and tripartite evolutionary game approach

This paper explores the concept of fairness and equitable matching in an on-line vehicle-cargo matching setting, addressing the varying degrees of satisfaction experienced by shippers and carriers. Relevant indicators for shippers and carriers in the on-line matching process are categorized as attributes, expectations, and reliability, which are subsequent quantified to form satisfaction indicators. Employing the intuitionistic fuzzy set theory, we devise a transformed vehicle-cargo matching optimization model by combining the fuzzy set’s membership, non-membership, and uncertainty information. Through an adaptive interactive algorithm, the matching scheme with fairness concerns is solved using CPLEX. The effectiveness of the proposed matching mechanism in securing high levels of satisfaction is established by comparison with three benchmark methods. To further investigate the impact of considering fairness in vehicle-cargo matching, a shipper-carrier-platform tripartite evolutionary game framework is developed under the waiting response time cost (WRTC) sharing mechanism. Simulation results show that with fairness concerns in vehicle-cargo matching, all stakeholders are better off: The platform achieves positive revenue growth, and shippers and carriers receive positive subsidy. This study offers both theoretical insights and practical guidance for the long-term and stable operation of the on-line freight stowage industry.

Oxygen‐Stable Electrochemical CO2 Capture using Redox‐Active Heterocyclic Benzodithiophene Quinone

AbstractElectrochemical carbon capture offers a promising alternative to thermal amine technology, which serves as the traditional benchmark method for CO2 capture. Despite its technological maturity, the widespread deployment of thermal amine technologies is hindered by high energy consumption and sorbent degradation. In contrast, electrochemical methods, with their inherently isothermal operation, address these challenges, offering enhanced energy efficiency and robustness. Among emerging strategies, electrochemical carbon capture systems using redox‐active materials such as quinones stand out for their potential to capture CO2. However, their practical application is currently limited by their low stability in the presence of oxygen. We demonstrate that benzodithiophene quinone (BDT‐Q), a heterocyclic quinone, exhibits high stability in electrochemical carbon capture processes with oxygen‐containing feed gas. Conducted in a cyclic flow system with a simulated flue gas mixture containing 13 % CO2 and 3.5 % O2 for over 100 hours, the process demonstrates high oxygen stability with an electron utilization of 0.83 without significant degradation, indicating a promising approach for real world applications. Our study explores the potential of new heterocyclic quinone compounds in the context of carbon capture technologies.

Oxygen-Stable Electrochemical CO2 Capture using Redox-Active Heterocyclic Benzodithiophene Quinone.

Electrochemical carbon capture offers a promising alternative to thermal amine technology, which serves as the traditional benchmark method for CO2 capture. Despite its technological maturity, the widespread deployment of thermal amine technologies is hindered by high energy consumption and sorbent degradation. In contrast, electrochemical methods, with their inherently isothermal operation, address these challenges, offering enhanced energy efficiency and robustness. Among emerging strategies, electrochemical carbon capture systems using redox-active materials such as quinones stand out for their potential to capture CO2. However, their practical application is currently limited by their low stability in the presence of oxygen. We demonstrate that benzodithiophene quinone (BDT-Q), a heterocyclic quinone, exhibits high stability in electrochemical carbon capture processes with oxygen-containing feed gas. Conducted in a cyclic flow system with a simulated flue gas mixture containing 13 % CO2 and 3.5 % O2 for over 100 hours, the process demonstrates high oxygen stability with an electron utilization of 0.83 without significant degradation, indicating a promising approach for real world applications. Our study explores the potential of new heterocyclic quinone compounds in the context of carbon capture technologies.

FairDPFL-SCS: Fair Dynamic Personalized Federated Learning with strategic client selection for improved accuracy and fairness

Personalized federated learning (PFL) addresses the significant challenge of non-independent and identically distributed (non-IID) data across clients in federated learning (FL). Our proposed framework, “FairDPFL-SCS: Fair Dynamic Personalized Federated Learning with Strategic Client Selection”, marks a notable advancement in this domain. By integrating dynamic learning rate adjustments and a strategic client selection mechanism, our approach effectively mitigates the challenges posed by non-IID data while enhancing model personalization, fairness, and efficiency. We evaluated FairDPFL-SCS using standard datasets, including MNIST, FashionMNIST, and SVHN, employing architectures like VGG and CNN. Our model achieved impressive results, attaining 99.04% accuracy on MNIST, 89.19% on FashionMNIST, and 90.9% on SVHN. These results represent a substantial improvement over existing methods, including a highest increase of 16.74% in accuracy on SVHN when compared to the best-performing benchmark methods. In particular, our method also demonstrated lower fairness variance, presenting the importance of fairness in model personalization, a frequently overlooked aspect in FL research. Through extensive experiments, we validate the superior performance of FairDPFL-SCS compared to benchmark PFL approaches, highlighting significant improvements over state-of-the-art methods. This work represents a promising step forward in the field of federated learning, offering a comprehensive solution to the challenges presented by non-IID data while prioritizing fairness and efficiency in model personalization.

Attack-Defending Contrastive Learning for Volumetric Medical Image Zero-Watermarking

Zero-watermarking is an emerging distortion-free copyright protection method for volumetric medical images. However, achieving both robustness against various malicious attacks and distinguishability between individual images remains challenging. In this paper, we propose a novel attack-defending contrastive learning zero-watermarking scheme (ADCL-ZW) to tackle the above challenge using deep learning-based representations. In our approach, we design an attack-defending data enrichment mechanism to enhance the watermarking robustness by generating a large number of image samples under various watermarking attacks. Subsequently, features for both watermarking distinguishability and robustness are enhanced through application of a contrastive loss. In particular, we implement a dual-stream Siamese network architecture to effectively handle both signal attacks and geometric attacks in order to enhance the wartermarking performance. Experimental results demonstrate that ADCL-ZW achieves stronger watermarking robustness and a better tradeoff between watermarking robustness and distinguishability compared with state-of-the art zero-watermarking methods. One of the highlighted metrics the false negative rate of ADCL-ZW achieves 0.01 when a fixed false positive rate is set to 1%, which is more than 13.3 times better than the benchmark methods.

Patient-specific visual neglect severity estimation for stroke patients with neglect using EEG.

We aim to assess the severity of spatial neglect through detailing patients' field of view (FOV) using EEG. Spatial neglect, a prevalent neurological syndrome in stroke patients, typically results from unilateral brain injuries, leading to inattention to the contralesional space. Commonly used Neglect detection methods like the Behavioral Inattention Test - Conventional (BIT-C) lack the capability to assess the full extent and severity of neglect. Although the Catherine Bergego Scale (CBS) provides valuable clinical information, it does not detail the specific field of view affected in neglect patients. Building on our previously developed EEG-based Brain-Computer Interface (BCI) system, AREEN (AR-guided EEG-based Neglect Detection, Assessment, and Rehabilitation System), we aim to map neglect severity across a patient's field of view. We have demonstrated that AREEN can assess neglect severity in a patient-agnostic manner. However, its effectiveness in patient-specific scenarios, which is crucial for creating a generalizable plug-and-play system, remains unexplored. This paper introduces a novel EEG-based combined Spatio-Temporal Network (ESTNet) that processes both time and frequency domain data to capture essential frequency band information associated with spatial neglect. We also propose a field of view correction system using Bayesian fusion, leveraging AREEN's recorded response times for enhanced accuracy by addressing noisy labels within the dataset. Extensive testing of ESTNet on our proprietary dataset has demonstrated its superiority over benchmark methods, achieving 79.62% accuracy, 76.71% sensitivity, and 86.36% specificity. Additionally, we provide saliency maps to enhance model explainability and establish clinical correlations. These findings underscore ESTNet's potential combined with Bayesian fusion-based FOV correction as an effective tool for generalized neglect assessment in clinical setting.

Multi-Vehicle Cooperative Decision-Making in Merging Area Based on Deep Multi-Agent Reinforcement Learning

In recent years, reinforcement learning (RL) methods have shown powerful learning capabilities in single-vehicle autonomous driving. However, few studies have focused on multi-vehicle cooperative driving based on RL, particularly in the dynamically changing traffic environments of highway ramp merge zones. In this paper, a multi-agent deep reinforcement learning (MARL) framework for multi-vehicle cooperative decision-making is proposed based on actor–critic, which categorizes vehicles into two groups according to their origins in the merging area. At the same time, the complexity of the network is reduced and the training process of the model is accelerated by utilizing mechanisms such as partial parameter sharing and experience playback. Additionally, a combination of global and individual rewards is adopted to promote cooperation in connected autonomous vehicles (CAVs) and balance individual and group interests. The training performance of the model is compared under three traffic densities, and our method is also compared with state-of-the-art benchmark methods. The simulation results show that the proposed MARL framework can have stronger policy learning capability and stability under various traffic flow conditions. Moreover, it can also effectively improve the speed of vehicles in the merging zone and reduce traffic conflicts.

Using Deep Reinforcement Learning (DRL) for minimizing power consumption in Video-on-Demand (VoD) storage systems

As video streaming services such as Netflix become popular, resolving the problem of high power consumption arising from both large data size and high bandwidth in video storage systems has become important. However, because various factors, such as the power characteristics of heterogeneous storage devices, variable workloads, and disk array models, influence storage power consumption, reducing power consumption with deterministic policies is ineffective. To address this, we present a new deep reinforcement learning (DRL)-based file placement algorithm for replication-based video storage systems, which aims to minimize overall storage power consumption. We first model the video storage system with time-varying streaming workloads as the DRL environment, in which the agent aims to find power-efficient file placement. We then propose a proximal policy optimization (PPO) algorithm, consisting of (1) an action space that determines the placement of each file; (2) an observation space that allows the agent to learn a power-efficient placement based on the current I/O bandwidth utilization; (3) a reward model that assigns a greater penalty for increased power consumption for each action; and (4) an action masking model that supports effective learning by preventing agents from selecting unnecessary actions. Extensive simulations were performed to evaluate the proposed scheme under various solid-state disk (SSD) models and replication configurations. Results show that our scheme reduces storage power consumption by 5% to 25.8% (average 12%) compared to existing benchmark methods known to be effective for file placement.

Meta-learning and proximal policy optimization driven two-stage emergency allocation strategy for multi-energy system against typhoon disasters

To achieve resilience improvement of the multi-energy system against typhoon disasters, this study designs a novel two-stage optimization framework that considers the emergency allocation of distributed resources under typhoon disasters to fully exploit the potential of distributed resources for resilience enhancement. Firstly, we formulate the emergency allocation of distributed resources as a Markov decision process. Then, a meta-learning-driven proximal policy optimization method is utilized to solve it. Different from that the existing reinforcement learning methods always ignore the unpredictable change caused by typhoon and keep multi-energy system dynamics invariant, limiting its control performance. The proposed method embeds meta-learning to fine-tune the pre-trained allocation policy to new tasks with high adaptability and few interactions. Finally, comparison results with other benchmark methods are carried out and shows that the proposed method can learn the appropriate resource allocation policy for multi-energy system and achieve better resilience enhancement, yielding fast application efficiency and good generalization ability for emergency fault conditions.