Explore the vast range of titles available.

Modern urban centers have one of the most critical challenges of congestion. Traditional electronic toll collection systems attempt to mitigate this issue through pre-defined static congestion pricing methods; however, they are inadequate in addressing the dynamic fluctuations in traffic demand. Dynamic congestion pricing has been identified as a promising approach, yet its implementation is hindered by the computational complexity involved in optimizing long-term objectives and the necessity for coordination across the traffic network. To address these challenges, we propose a novel dynamic traffic congestion pricing model utilizing multi-agent reinforcement learning with a transformer architecture. This architecture capitalizes on its encoder-decoder structure to transform the multi-agent reinforcement learning problem into a sequence modeling task. Drawing on insights from research on graph transformers, our model incorporates agent structures and positional encoding to enhance adaptability to traffic flow dynamics and network coordination. We have developed a microsimulation-based environment to implement a discrete toll-rate congestion pricing scheme on actual urban roads. Our extensive experimental results across diverse traffic demand scenarios demonstrate substantial improvements in congestion metrics and reductions in travel time, thereby effectively alleviating traffic congestion.

Detecting small objects is a challenging task. We focus on a special case: the detection and classification of traffic signals in street views. We present a novel framework that utilizes a visual attention model to make detection more efficient, without loss of accuracy, and which generalizes. The attention model is designed to generate a small set of candidate regions at a suitable scale so that small targets can be better located and classified. In order to evaluate our method in the context of traffic signal detection, we have built a traffic light benchmark with over 15,000 traffic light instances, based on Tencent street view panoramas. We have tested our method both on the dataset we have built and the Tsinghua–Tencent 100K (TT100K) traffic sign benchmark. Experiments show that our method has superior detection performance and is quicker than the general faster RCNN object detection framework on both datasets. It is competitive with state-of-the-art specialist traffic sign detectors on TT100K, but is an order of magnitude faster. To show generality, we tested it on the LISA dataset without tuning, and obtained an average precision in excess of 90%.

Investigating the spatio-temporal trends in agricultural green production level and proposing pathways to improve it can offer valuable insights for promoting the green, low-carbon, and sustainable development of China’s agriculture, as well as contributing to the achievement of the United Nations’ Sustainable Development Goals by 2030. Therefore, in order to investigate the spatio-temporal variations in agricultural green production level and its driving factors, and explore pathways to improve it in the major grain-producing areas of China, a new multi-dimensional framework for estimating the agricultural green production level was proposed, and based on the OLS regression and scenario prediction, the agricultural green production levels from 2012 to 2030 were estimated. The findings indicate that from 2012 to 2021, the agricultural green production level in the major grain-producing areas experienced a consistent annual increase. The average annual value for the agricultural green production level was recorded at 0.443. At a spatial scale, the agricultural green production level exhibited a pronounced regional pattern, showing higher levels in the central and eastern areas, while lower levels were noted in the northeastern and western regions. The actual utilization of foreign capital and the per capita disposable income of farmers positively influenced the agricultural green production level. In contrast, factors such as the proportion of the secondary industry, the proportion of the tertiary industry, and the urbanization rate negatively affected this level. From 2022 to 2030, the agricultural green production level is expected to demonstrate a gradual growth trend under the baseline scenario, although the rate of growth is expected to decrease over time. Conversely, under the green and sustainable development scenario, a notably significant growth trend in agricultural green production level is projected. However, under the rapid economic development scenario, it is estimated that the agricultural green production level will initially increase slowly before peaking in 2026 and then experiencing a decline. With the aim of ensuring the ongoing enhancement of agricultural green production level objectives, the major grain-producing areas should proactively encourage inter-provincial collaboration in agricultural green production, vigorously attract foreign investment to facilitate the advancement of green production technologies, promote the harmonious integration of primary, secondary, and tertiary industries in rural regions, and improve farmers’ income.

Industrial loads (ILs), characterized by their large scale and high automation levels, offer significant potential to mitigate supply-demand imbalances in smart grids with high penetration of renewable energy generation. However, research on modeling the controllable characteristics of industrial loads remains relatively limited. Existing models are often overly simplistic, failing to account for transient processes—which are non-negligible during regulation—as well as potential parameter variations, leading to substantial regulation errors and an inability to meet precision requirements. This paper focuses on adjustable industrial loads and establishes precise regulation response models based on their production characteristics and transient processes, including continuously adjustable industrial load models, discrete parameter-fixed adjustable industrial load models, and discrete parameter-variable adjustable industrial load models. Building on these models, an improved approximate dynamic programming (IADP) algorithm is proposed, which transforms the traditional iteration-based value function approximation method into a numerical fitting approach. This method is utilized to derive a day-ahead optimal scheduling strategy. Finally, the effectiveness of the proposed approach is validated through multiple case studies, where comparisons with optimal scheduling strategies from other modeling approaches and optimization techniques further demonstrate its superiority.

Data stream clustering is integral to contemporary big data applications. However, addressing the ongoing influx of data streams efficiently and accurately remains a primary challenge in current research. This paper aims to elevate the efficiency and precision of data stream clustering, leveraging the TEDA (Typicality and Eccentricity Data Analysis) algorithm as a foundation, we introduce improvements by integrating a nearest neighbor search algorithm to enhance both the efficiency and accuracy of the algorithm. The original TEDA algorithm, grounded in the concept of “Typicality and Eccentricity Data Analytics”, represents an evolving and recursive method that requires no prior knowledge. While the algorithm autonomously creates and merges clusters as new data arrives, its efficiency is significantly hindered by the need to traverse all existing clusters upon the arrival of further data. This work presents the NS-TEDA (Neighbor Search Based Typicality and Eccentricity Data Analysis) algorithm by incorporating a KD-Tree (K-Dimensional Tree) algorithm integrated with the Scapegoat Tree. Upon arrival, this ensures that new data points interact solely with clusters in very close proximity. This significantly enhances algorithm efficiency while preventing a single data point from joining too many clusters and mitigating the merging of clusters with high overlap to some extent. We apply the NS-TEDA algorithm to several well-known datasets, comparing its performance with other data stream clustering algorithms and the original TEDA algorithm. The results demonstrate that the proposed algorithm achieves higher accuracy, and its runtime exhibits almost linear dependence on the volume of data, making it more suitable for large-scale data stream analysis research.

Sepsis remains a significant clinical challenge. Ferroptosis is involved in the pathogenesis of sepsis. Ferroptosis is associated with oxidative stress, and excessive oxidative stress is suppressed by milk fat globule epidermal growth factor 8 (MFG-E8) under various conditions. However, the role of MFG-E8 in sepsis-induced ferroptosis and oxidative stress is still unclear. First, we collected blood samples from patients with sepsis and detected the expression of serum MFG-E8. Then, the relationship between serum concentrations of MFG-E8 and disease severity was detected. Finally, the effects of MFG-E8 treatment on ferroptosis and oxidative stress in the livers of septic mice were determined. The expression of serum MFG-E8 in healthy subjects was notably higher than that in septic patients. In addition, when nonsurvivors and survivors of sepsis were compared, MFG-E8 levels were considerably lower in the former. The ROC curve for MFG-E8 was also generated. The area under the curve for MFG-E8 was 0.768 (95% confidence interval [CI] 0.627–0.909, p = 0.003). The patients were separated into two groups based on the MFG-E8 cut-off value of 3.86 ng/mL. According to the Kaplan‒Meier survival analysis, patients with low MFG-E8 levels had a significantly decreased 28-day survival rate compared with patients with high MFG-E8 levels. High MFG-E8 levels were substantially related to a decreased risk of death, as demonstrated by the Cox proportional hazard model that we utilized. In addition, compared with sham mice, septic mice exhibited liver and kidney damage, and MFG-E8 may have protective effects. The survival study indicated that MFG-E8 could effectively improve the survival rate of septic mice. Treatment with MFG-E8 suppresses oxidative stress and ferroptosis in the livers of septic mice. Serum MFG-E8 levels are lower in septic patients and are negatively related to disease severity. Treatment with MFG-E8 suppresses oxidative stress and ferroptosis in the livers of septic mice, contributing to significantly improved survival in septic mice. These findings showed that MFG-E8 could be a new sepsis predictive biomarker. MFG-E8 may have therapeutic potential in the treatment of sepsis.

To compare brain activation in the dopaminergic reward system between 26 LPE patients and 16 normal controls (NCs) via glans penis electric stimulation task-fMRI and resting-state fMRI (rs-fMRI). The beta value, degree centrality (DC), and functional connectivity (FC) were calculated. The Pearson correlation was used to analyze the correlation between the fMRI measurements and disease severity. After task-fMRI, PE patients had significantly higher beta values in the dopaminergic reward system, including the bilateral thalamus and inferior frontal gyrus than NCs. In the rs-fMRI, higher DC values in the bilateral supplementary motor area (SMA) and lower DC values in the bilateral precuneus were found. Furthermore, our results showed enhanced FC between the right inferior frontal gyrus and the bilateral SMA and decreased FC between the bilateral precuneus and bilateral thalamus after electrical stimulation. The sensitivity was 80.77%, the specificity was 81.25%, and the AUC was 0.83 ( p  < 0.001) when differentiating the PE and NC using the FC between the inferior frontal gyrus and SMA. The sensitivity was 73.08%, the specificity was 75.00%, and the AUC was 0.82 ( P  = 0.002) when differentiating the two groups using the FC between the precuneus and thalamus.

Accurate estimation of Timber Product Output (TPO) is important for carbon budget accounting, since wood products can act as delayed release carbon pools. However, the existing timber harvest data in the US relies on Forest Service's TPO survey, and the survey does not happen every year. In this study, we proposed a methodological framework to produce annual TPO volume estimates for seven southeastern states (North Carolina, South Carolina, Alabama, Florida, Georgia, Mississippi, and Tennessee) of the US by integrating TPO survey data, Landsat Time Series Stacks (LTSS), and National Land Cover Database (NLCD). First, a forest disturbance product was derived based on Vegetation Change Tracker (VCT) algorithm using LTSS from 1985 to 2016. Then, by linking the predictor variables derived from the disturbance data and the TPO survey data, two regression algorithms were tested and compared, and Random Forest was selected to create TPO estimation models for different wood types. The results show that from 1986 to 2015, the region produced more than 5 × 10 9 m 3 wood products, including 3.7 × 10 9 m 3 softwood products and 1.6 × 10 9 m 3 hardwood products. The derived TPO estimates had large spatial variations among the counties within each state as well as large temporal variations across the study period. The TPO data derived through this study can provide an observational basis for calculating the amount of C transferred from the standing biomass to the wood products through logging and for partitioning of harvested C among different wood product pools.

Alzheimer’s disease (AD) is a prevalent form of dementia that affects an estimated 32 million individuals globally. Identifying early indicators is vital for screening at-risk populations and implementing timely interventions. At present, there is an urgent need for early and sensitive biomarkers to screen individuals at risk of AD. Among all sensory biomarkers, olfaction is currently one of the most promising indicators for AD. Olfactory dysfunction signifies a decline in the ability to detect, identify, or remember odors. Within the spectrum of AD, impairment in olfactory identification precedes detectable cognitive impairments, including mild cognitive impairment (MCI) and even the stage of subjective cognitive decline (SCD), by several years. Olfactory impairment is closely linked to the clinical symptoms and neuropathological biomarkers of AD, accompanied by significant structural and functional abnormalities in the brain. Olfactory behavior examination can subjectively evaluate the abilities of olfactory identification, threshold, and discrimination. Olfactory functional magnetic resonance imaging (fMRI) can provide a relatively objective assessment of olfactory capabilities, with the potential to become a promising tool for exploring the neural mechanisms of olfactory damage in AD. Here, we provide a timely review of recent literature on the characteristics, neuropathology, and examination of olfactory dysfunction in the AD continuum. We focus on the early changes in olfactory indicators detected by behavioral and fMRI assessments and discuss the potential of these techniques in MCI and preclinical AD. Despite the challenges and limitations of existing research, olfactory dysfunction has demonstrated its value in assessing neurodegenerative diseases and may serve as an early indicator of AD in the future.