In construction project management, accurate cost forecasting is critical for ensuring informed decision making. In this article, a construction cost prediction method based on an improved bidirectional long- and short-term memory (BiLSTM) network is proposed to address the high interactivity among construction cost data and difficulty in feature extraction. Firstly, the correlation between cost-influencing factors and the unilateral cost is calculated via grey correlation analysis to select the characteristic index. Secondly, a BiLSTM network is used to capture the temporal interactions in the cost data at a deep level, and the hybrid attention mechanism is incorporated to enhance the model’s feature extraction capability to comprehensively capture the interactions among the features in the cost data. Finally, a hyperparameter optimisation method based on the improved particle swarm optimisation algorithm is proposed using the prediction accuracy as the fitness function of the algorithm. The MAE, RMSE, MPE, MAPE, and coefficient of determination of the simulated prediction results of the proposed method on the dataset are 7.487, 8.936, 0.236, 0.393, and 0.996%, respectively, where MPE is a positive coefficient. This avoids the serious consequences of underestimating the cost. Compared with the unimproved BiLSTM, the MAE, RMSE, and MAPE are reduced by 15.271, 18.193, and 0.784%, respectively, which reflects the superiority and effectiveness of the method and can provide technical support for project cost estimation in the construction field.

The configuration of the hyperparameters in convolutional neural networks (CNN) is crucial for determining their performance. However, traditional methods for hyperparameter configuration, such as grid searches and random searches, are time consuming and labor intensive. The optimization of CNN hyperparameters is a complex problem involving multiple local optima that poses a challenge for traditional particle swarm optimization (PSO) algorithms, which are prone to getting stuck in the local optima and achieving suboptimal results. To address the above issues, we proposed an adaptive dimensional Gaussian mutation PSO (ADGMPSO) to efficiently select the optimal hyperparameter configurations. The ADGMPSO algorithm utilized a cat chaos initialization strategy to generate an initial population with a more uniform distribution. It combined the sine-based inertia weights and an asynchronous change learning factor strategy to balance the global exploration and local exploitation capabilities. Finally, an elite particle adaptive dimensional Gaussian mutation strategy was proposed to improve the population diversity and convergence accuracy at the different stages of evolution. The performance of the proposed algorithm was compared to five other evolutionary algorithms, including PSO, BOA, WOA, SSA, and GWO, on ten benchmark test functions, and the results demonstrated the superiority of the proposed algorithm in terms of the optimal value, mean value, and standard deviation. The ADGMPSO algorithm was then applied to the hyperparameter optimization for the LeNet-5 and ResNet-18 network models. The results on the MNIST and CIFAR10 datasets showed that the proposed algorithm achieved a higher accuracy and generalization ability than the other optimization algorithms, such as PSO-CNN, LDWPSO-CNN, and GA-CNN.

Here we proposed a grape disease identification model based on improved YOLOXS (GFCD-YOLOXS) to achieve real-time detection of grape diseases in field conditions. We build a dataset of 11,056 grape disease images in 15 categories, based on 2566 original grape disease images provided by the State Key Laboratory of Plant Pest Biology data center after pre-processing. To improve the YOLOXS algorithm, first, the FOCUS module was added to the backbone network to reduce the lack of information related to grape diseases in the convolution process so that the different depth features in the backbone network are fused. Then, the CBAM (Convolutional Block Attention Module) was introduced at the prediction end to make the model focus on the key features of grape diseases and mitigate the influence of the natural environment. Finally, the double residual edge was introduced at the prediction end to prevent degradation in the deep network and to make full use of the non-key features. Compared with the experimental results of relevant authoritative literature, GFCD-YOLOXS had the highest identification accuracy of 99.10%, indicating the superiority of the algorithm in this paper.

Grape leafhoppers (Erythroneura spp.) are major pests in grape cultivation, leading to significant economic losses. Accurate and efficient damage level assessment is crucial for effective pest management and reducing financial impact. In this study, we categorized damage into uninfested leaves and five damage levels (I–V) and constructed a grape leafhopper damage dataset. Based on this dataset, we developed a lightweight detection model for grape leafhopper damage levels, incorporating improvements to the YOLOv8n architecture. The model employs FasterNet as the backbone network to enhance computational efficiency and reduce model complexity. It substitutes for the nearest-neighbor upsampling with CARAFE to improve small target detection capabilities. Additionally, the SE attention mechanism is integrated to optimize leaf feature extraction, thereby enhancing recognition accuracy in complex vineyard environments. The experimental results demonstrate that CSF-YOLO achieves a mAP of 90.15%, which is 1.82% higher than the baseline model, YOLOv8n. Additionally, the model’s inference results can be accessed via mobile devices, demonstrating the feasibility of real-time vineyard pest monitoring. This study provides a solid technical foundation for advancing intelligent pest monitoring systems in vineyards and the development of smart agriculture.

As the primary means of modern enterprise management, business process management (BPM) technology has become the mainstream development trend of modern enterprise management. The efficient and accurate establishment of business processes is essential for effective BPM. However, the traditional manual-based modeling approach is time-consuming and error-prone. To overcome this, process recommendation technology can improve the intelligence and efficiency of modeling to a certain extent. However, existing process modeling recommendation methods suffer from the problem of low accuracy and neglecting short-process models. Therefore, a novel process modeling recommendation method that integrates disjoint paths and sequential patterns was proposed. This method uses edge-disjoint paths for the first time to represent the behavioral semantics of processes, and an improved contiguous sequential pattern mining algorithm was proposed to mine the contiguous path sequential patterns (CPSPs) of edge-disjoint paths. In the process modeling recommendation stage, the k CPSPs with the highest matching degree with the current reference model process were calculated, and the last node in these CPSPs was used as the set of recommendation nodes. In cases with CPSPs with the same matching degree, the one with the higher value was recommended according to their corresponding lift, confidence, and support degrees. Through experimental evaluation and comparison, it was shown that the proposed method effectively improved the accuracy of the recommendation of both short-process and long-process models while ensuring effectiveness and time efficiency.

Given the wide application of container technology, the accurate prediction of container CPU usage has become a core aspect of optimizing resource allocation and improving system performance. The high volatility of container CPU utilization, especially the uncertainty of extreme values of CPU utilization, is challenging to accurately predict, which affects the accuracy of the overall prediction model. To address this problem, a container CPU utilization prediction model, called ExtremoNet, which integrates the isolated forest algorithm, and classification sub-models are proposed. To ensure that the prediction model adequately takes into account critical information on the CPU utilization’s extreme values, the isolated forest algorithm is introduced to compute these anomalous extreme values and integrate them as features into the training data. In order to improve the recognition accuracy of normal and extreme CPU utilization values, a classification sub-model is used. The experimental results show that, on the AliCloud dataset, the model has an R² of 96.51% and an MSE of 7.79. Compared with the single prediction models TCN, LSTM, and GRU, as well as the existing combination models CNN-BiGRU-Attention and CNN-LSTM, the model achieves average reductions in the MSE and MAE of about 38.26% and 23.12%, proving the effectiveness of the model at predicting container CPU utilization, and provides a more accurate basis for resource allocation decisions.