Air quality has always been one of the most important environmental concerns for the general public and society. Using machine learning algorithms for Air Quality Index (AQI) prediction is helpful for the analysis of future air quality trends from a macro perspective. When conventionally using a single machine learning model to predict air quality, it is challenging to achieve a good prediction outcome under various AQI fluctuation trends. In order to effectively address this problem, a genetic algorithm-based improved extreme learning machine (GA-KELM) prediction method is enhanced. First, a kernel method is introduced to produce the kernel matrix which replaces the output matrix of the hidden layer. To address the issue of the conventional limit learning machine where the number of hidden nodes and the random generation of thresholds and weights lead to the degradation of the network learning ability, a genetic algorithm is then used to optimize the number of hidden nodes and layers of the kernel limit learning machine. The thresholds, the weights, and the root mean square error are used to define the fitness function. Finally, the least squares method is applied to compute the output weights of the model. In order to verify the predictive ability of GA-KELM, based on the collected basic data of long-term air quality forecast at a monitoring point in a city in China, the optimized kernel extreme learning machine is applied to predict air quality ( SO ₂ , NO ₂ , _{PM 10} , CO , O ₃ , PM _2.5 concentration and AQI), with comparative experiments based on convolutional neural networks, recurrent neural networks and long short-term memory. The results show that the proposed model trains faster and makes more accurate predictions.

In ground-based bearing-only tracking of multiple maneuvering targets, there are difficulties in data association due to the reliance solely on azimuth information, making it challenging to distinguish and identify multiple targets. This problem is particularly pronounced when targets are close or overlapping, leading to disassociation or target loss. Moreover, bearing-only information struggles to accurately capture the dynamic changes in maneuvering targets, significantly affecting tracking accuracy. To address these issues, this paper proposes an Improved Maneuver Detection-Based Multiple Hypothesis Bearing-Only Target Tracking (IMD-MHRPCKF) algorithm. To begin with, the observation range is segmented into multiple sub-intervals through a distance parameterization technique, and within each sub-interval, a Cubature Kalman Filter (CKF) is applied. The Multiple Hypothesis Tracking (MHT) algorithm is then used for data association, solving the measurement ambiguity problem. To detect target maneuvers, the sliding window average of the innovation sequence is calculated. When a target maneuver is detected, the sub-filter parameters are reinitialized to ensure filter stability. In contrast, if no maneuver is detected, the filter parameters remain unchanged. Finally, simulations are used to compare this algorithm with various other algorithms. The results show that the proposed algorithm significantly improves system robustness, reduces tracking errors, and effectively tracks bearing-only multiple maneuvering targets.

The safety performance function (SPF) is an extensively employed tool in road safety assessment. However, traditional modeling methods often fall short of effectively capturing the intricate interdependencies among diverse traffic variables. To address this limitation, a feature importance analyzable resilient deep neural network (RDNN) is proposed as an alternative approach. This model begins with an explainable autoencoder that delineates the relationship between observed collisions and road characteristics. Subsequently, it introduces a priori unsupervised feature importance analysis process that enriches the original input data. The enhanced input is then processed by a novel RDNN, featuring an automated Gaussian transfer function and resilient supervised learning, both meticulously designed for precise modeling. Ultimately, the efficacy of the proposed framework is demonstrated through several case studies on real-world applications, utilizing data collected from highways in Canada and the U.S.

Accurately predicting the turning traffic flow at urban intersections is crucial for optimizing traffic management strategies and alleviating congestion. Existing traffic flow prediction models often fail to effectively capture the inherent complexity and dynamic variability of intersections, particularly the nonlinear characteristics of turning movements. To address these limitations, this paper proposes a novel parallel quadruple neural networks (PNNs4) model that leverages deep learning and multi-source data feature fusion techniques in a parallel architecture, enabling comprehensive processing of multi-source traffic data. The innovative feature fusion technology enhances the learning capabilities and accuracy in predicting complex traffic patterns. The fusion process involves an innovative combination of spatial and temporal feature extraction, effectively synchronized through element-wise multiplication, enriching the model's input representation and robustness. Experimental validation across 49 intersections in Milton, Ontario, Canada, demonstrates that the PNNs4 model outperforms existing state-of-the-art methods in terms of both accuracy and stability.

Ordered-risk assessment is a safety-critical learning problem in which delayed or biased risk estimation can affect prioritization and response planning. Existing expert-knowledge and data-driven approaches face a trade-off among transparent indicator design, nonlinear representation capability, and stable optimization when reliable labeled data are scarce. To address this gap, we developed a two-stage adaptive differential evolution-optimized extreme learning machine framework (TA-DE-ELM) for six-level ordered-risk assessment and evaluated it in a controlled physics-informed synthetic simulation benchmark. The benchmark encodes kinematic, capability, sensing/interference, and resilience priors as explicit scoring rules for model evaluation, rather than as an application simulator. The method combines transparent risk-logic specification, a stage-wise exploration–refinement optimizer with stagnation-triggered restart, and a validation objective that jointly considers cross-entropy, macro-F1, ordinal error, and accuracy. Under a unified finite budget, TA-DE-ELM ranked first among all tested ELM-family baselines for accuracy, macro-F1, quadratic weighted kappa, and ordinal mean absolute error, with paired tests indicating improvements over the closest competitor ($p<0.013$). These results show that TA-DE-ELM can recover an expert-rule-induced ordered-risk mapping more effectively than the tested baselines under controlled finite-sample conditions. Further validation with higher-fidelity simulators, externally collected datasets, and richer temporal perturbation protocols remains necessary before application-specific use.