Large Language Models (LLMs) have demonstrated strong capabilities across diverse tasks under the example-driven learning paradigm. However, in high-stakes domains such as emergency response and industrial safety, historical incidents are scarce, confidential, or both, while concise rule books are abundant. We formalize this underexplored setting as rule knowledge-driven reasoning and ask: Can LLMs reason reliably when rules are plentiful but examples are nearly absent? To study this question, we introduce RULER, an automatic benchmark that generates 32K rigorously verified questions from 1K expert-curated emergency response rules to probe three core abilities: rule memorization, single-rule application, and multi-rule complex reasoning. RULER is further equipped with a hallucination-aware evaluation suite and novel relational metrics. A comprehensive empirical study of five representative LLMs and five enhancement strategies shows that, even when models achieve reliable performance on rule memorization and single-rule application, multi-rule complex reasoning plateaus at 5.4 on a 10-point scale. To address this limitation, we propose RAMPS, a Rule knowledge-Aware Monte Carlo Tree Search Process-reward Supervision framework. RAMPS injects rule knowledge priors into MCTS, distills 12K step-level traces without human annotation, and trains an advantage-based reward model that scores candidate reasoning paths during beam search inference. Experimental results show that RAMPS significantly improves multi-rule complex reasoning performance to 7.7.

With the rapid development of software systems, logs have become essential data for monitoring the security and stability of computer systems. Current log anomaly detection methods usually rely on large volumes of labeled data, which can lead to class imbalance and fail to fully leverage the features of log sequences. To address these problems, we propose a novel anomaly detection model LogMT, which performs anomaly detection based on multiple self-supervised tasks. LogMT uses Transformer encoder to extract feature vectors from log event sequences and trains the model through self-supervised tasks for anomaly detection. To better capture the bidirectional context information of log sequences, we introduce the dynamic masked log templates prediction task, which enhances the contextual understanding of the model through predicting masked log templates in the log sequence. In the minimization of outlier factor task, we map log sequence features to a high-dimensional space and cluster similar normal log sequences together, improving the model's capability to distinguish anomaly features. Finally, we conducted extensive experiments on three public datasets, and the experimental results demonstrate the effectiveness and superiority of LogMT.

With the development of artificial intelligence, artificial intelligence technology is widely used in robots. For example, emotional computing robots need to be able to complete the function of facial expression analysis. The multi-task deep learning model MCAN proposed in this paper is designed to complete facial expression analysis for robots which can predict discrete expressions and dimensional measures. The class center loss function proposed in this paper can increase the inter-class distance while reducing the intra-class distance. In addition, multi-head attention network was improved to focus on different areas of the input image. Finally, feature pyramid network allows information exchange and fusion between feature maps at different levels. Experiments have proven that MCAN achieves excellent results on both the AffectNet dataset and the AFEW-VA dataset, and also speeds up inference.

Particle Swarm Optimization (PSO) is a swarm intelligence method which is employed frequently for solving real-world problems. After its inception, many variants of PSO devote to improving its performance by modifying the behavior of each particle, in which the population topologies of the particle swarm may alter. This paper investigates how population topology influences the performance of PSO. A random topology generation algorithm that adopts both the greedy strategy and randomized algorithm is proposed in the paper. The randomly generated topologies are applied in PSO-w, which introduces no modification to the population topology of the original PSO. Experimental results demonstrate that algorithms using topologies with more edges tend to converge faster and generally obtain a more accurate solution. Another major result in this paper is that how clustering coefficient affects PSO largely depends on the sparsity of the topology. A lower clustering coefficient in sparse topology conduces to faster convergence and a more precise result, but a higher clustering coefficient is preferred when the topology is dense.

Weather prediction is one of the hot topics in artificial intelligence. In this paper, three new temperature prediction models based on historical data are proposed for two important meteorological indexes, the maximum temperature and the minimum temperature. The first model is to construct SVM model to predict the residual error of LSTM model, then add the prediction results of the two models to get the final prediction result. The second model is to use empirical mode decomposition (EMD) to decompose the original data, then use the combination forecasting model to predict the subsequences, and finally summarize the prediction results. The third model is to combine the advantages of the first and second models. First, EMD is used to decompose the original sequence. Then, the first model is used to predict each subsequence. Finally, the predicted values of all subsequences are superimposed to obtain the final predicted value. Based on the temperature data of Washington and Los Angeles, the three models are tested and analyzed in this paper. The experimental results show that the third model proposed in this paper, which is based on EMD and residual prediction SVM-LSTM model, has better prediction accuracy than other models.

In society, the mutual influence and interaction between individuals constitute a social network, and opinion dynamics studies the generation, diffusion and aggregation of thoughts or behaviors in social networks. This paper introduces the idea of evolution in opinion dynamics models into particle swarm optimization algorithm, and proposes a social opinion dynamics-guided particle swarm optimization algorithm (SODPSO). Firstly, in the process of population evolution, the idea of dynamic bounded confidence is used to select the learning object (the best individual in the confidence bound) for each particle to update, and for the individual whose learning object is itself, a difference operator is introduced to update it. Secondly, when the population stagnation reaches a certain threshold, the concepts of individual differences and acceptance are introduced. The particles are sorted and classified according to the fitness value, and different evolution strategies are used to update them in order to jump out of the current optimal solution. Finally, this paper compares SODPSO with the other five PSO variants on part of cec'17 benchmark functions. The experimental results demonstrate that the SODPSO proposed in this paper has greater advantages in functions with certain specific characteristics.

As one of the most important renewable energy sources in the world, wind energy has been widely studied and applied. When using wind energy to generate electricity, it will be of great help to the safety and stability of power supply, if the wind speed in the future can be accurately known. In this paper, a new short-term wind speed prediction method based on historical data is proposed. Firstly, the wind speed is pre-processed through variational mode decomposition (VMD) of which the parameters are optimized using a multi-objective optimization method in this paper, owing to the effect of VMD is greatly affected by parameters. Then, the combined forecasting method combining support vector machine improved by particle swarm optimization algorithm (PSO-SVM), back propagation neural network (BP) and long short-term memory network (LSTM) is used to predict each wind speed component. This paper takes data sets available at the US Virgin Islands Bovoni measurement station as an example, conducting experiments and performing analysis. Compared with other prediction models, it is demonstrated that the model proposed in this paper significantly improves the prediction accuracy. Also, the wind speed in January, April, July and October are forecasted respectively to test the stability of models, and the result shows that the proposed model has the best adaptability.

An important objective of wireless sensor network is to prolong the network life cycle, and topology control is of great significance for extending the network life cycle. Based on previous work, for cluster head selection in hierarchical topology control, we propose a solution based on fuzzy clustering preprocessing and particle swarm optimization. More specifically, first, fuzzy clustering algorithm is used to initial clustering for sensor nodes according to geographical locations, where a sensor node belongs to a cluster with a determined probability, and the number of initial clusters is analyzed and discussed. Furthermore, the fitness function is designed considering both the energy consumption and distance factors of wireless sensor network. Finally, the cluster head nodes in hierarchical topology are determined based on the improved particle swarm optimization. Experimental results show that, compared with traditional methods, the proposed method achieved the purpose of reducing the mortality rate of nodes and extending the network life cycle.

The community structure is one of the most common and important attributes in complex networks. Community detection in complex networks has attracted much attention in recent years. As an effective evolutionary computation technique, particle swarm optimization (PSO) algorithm has become a candidate for many optimization applications. However, PSO algorithm was originally designed for continuous optimization. In this paper, an improved simple discrete particle swarm optimization (ISPSO) algorithm and a discrete particle swarm optimization with redefined operator (IDPSO-RO) algorithm are proposed in the discrete context of community detection problem. Furthermore, a community correcting strategy is used to optimize the results. The performance of the two algorithms is tested on three real networks with known community structures. The experiment results show that ISPSO and IDPSO-RO algorithms using community correcting strategy can detect community structures more efficiently without prior knowledge about the size of communities and the number of communities.

Robot path planning is a complicated problem which needs to balance many factors. In pathfinding, the robot has to find the shortest path to the destination and avoid the obstacles. Ant colony optimization is a heuristic algorithm which has many excellent features in pathfinding. This paper proposed a heterogeneous feature ant colony optimization (HFACO) algorithm to solve the robot path planning problem. In the proposed method, two kinds of ants with different features are designed to influence the convergence rate of the algorithm by controlling the number of them. We also applied some other novel strategies that enhance the solving quality and the performance. The experiment results show that HFACO can find a better path in a shorter period of time compared to the classical ACO algorithms.

The problem of portfolio selection in the field of financial engineering has received more attention in recent years. This paper presents a novel heterogeneous multiple population particle swarm optimization algorithm (HMPPSO) for solving a generalized Markowitz mean-variance portfolio selection model. The proposed HMPPSO is based on heterogeneous multiple population strategy, in which the whole population is divided into several sub-populations and all the sub-populations evolve with different PSO variants. The communication between the sub-populations is executed at regular intervals to maintain the information exchange inside the entire population and coordinate exploration and exploitation according to certain migration rules. The generalized portfolio selection model is classified as a quadratic mixed-integer programming model for which no computational efficient algorithms have been proposed. We employ the proposed HMPPSO to find the solution for the model and compare the performance of HMPPSO with several classic PSO variants. The test data set is the weekly prices from March, 1992 to September, 1997 including the following indices: Hang Seng in Hong Kong, DAX 100 in Germany, FTSE 100 in UK, S&P 100 in USA and Nikkei 225 in Japan. The computational results demonstrate that HMPPSO is much effective and robust, especially for problems with high dimensions, thus provides an effective solution for the portfolio optimization problem.

Recommendation algorithms in social networks have attracted much attention in recent years. Collaborative filtering recommendation algorithm is one of the most commonly used recommendation algorithms. Traditional user-based collaborative filtering recommendation algorithm recommends based on the user-item rating matrix, but the large amounts of data may cause low efficiency. In this paper, we propose an improved collaborative filtering recommendation algorithm based on community detection. Firstly, the user-item rating matrix is mapped into the user similarity network. Furthermore, a novel discrete particle swarm optimization algorithm is applied to find communities in the user similarity network, and finally Top-N items are recommend to the recommended user according to the communities. The experiments on a real dataset validate the effectiveness of the proposed algorithm for improving the precision, coverage and efficiency of recommendation.

Recommendation technology has experienced its great popularity for resource recommendation in web-based social networks. This paper proposed an effective recommendation model based on communities and trust network (CTNRM). In the proposed model, the neighbors of the recommended user are selected from the users in the same community with the recommended user, the users in the recommended user's circle of friends and the users in the recommended user's trusted community. Experiments on the Epinions dataset demonstrate the feasibility and effectiveness of CTNRM. The experimental results validate the effectiveness of our proposed recommendation model for improving the precision and rating coverage especially for inactive users.

Population topologies of Particle Swarm Optimization algorithm (PSO) have direct impacts on the information sharing amony particles during the evolution, and will influence the PSO algorithms' performance obviously. The canonical PSO algorithms usually use static population topologies, and the majority are the classic population topologies (such as fully connected topology and ring topology). In this paper, we present the strategies of dynamic random topology based on the random generation of population topologies. The basic idea is as follows: various random topologies are used at different stages of evolution in the population, and the solving performance of PSO algorithms is enhanced by improving the information exchange of population in different evolutionary stages. This provides a new way of thinking for the improvement of the PSO algorithm. Experimental results on a relatively new variant of dynamic probabilistic particle swarm optimization show that our strategies can achieve better performance compared with traditional static population topologies. Experimental data are analyzed and discussed in the paper, and the useful conclusions will provide a basis for further research.

The node localization in Wireless Sensor Network (WSN) presently plays an important role in the field of applications. Particle Swarm Optimization (PSO) algorithm is a typical swarm intelligence method. Researchers propose many PSO variants and try to apply PSO algorithm to the related problems in WSN. This paper focuses on the WSN node localization using PSO algorithm. This paper conducts the experiment simulation, comparison and evaluation work in the node localization using PSO algorithm. The performance of different PSO variants with different population topologies is analyzed. Experiment simulations show that WSN node localization using PSO algorithm can get good performance in ring topology and square topology. In particular, the two newly proposed PSO variants (GDPSO and LDPSO) have good performance on this problem. This paper proposes some useful conclusions, which will provide a valuable reference to WSN engineering field.