Hubei Polytechnic Institute

The permutation flow shop scheduling problem (PFSP) is one of the hot issues in current research, and its production methods are widely used in steel, medicine, semiconductor, and other industries. Due to the characteristics of permutation flow (optimize the production process through the principle of symmetry to achieve efficient allocation and balance of resources), its task processes only need to be sorted on the first machine, and the subsequent machines are completely symmetrical with the first machine. This paper proposes an enhanced particle swarm optimization algorithm (EPSO) for the PFSP. Firstly, in order to enhance the diversity of the algorithm, a new dynamic inertia weight method was introduced to dynamically adjust the search range of particles. Secondly, a new speed update strategy was proposed, which makes full use of the information of high-quality solutions and further improves the convergence speed of the algorithm. Subsequently, an interference strategy based on individual mutations was designed, which improved the universality of the model’s global search. Finally, to verify the effectiveness of the EPSO algorithm, six benchmark functions were tested, and the results proved the superiority of the EPSO algorithm. In addition, the average relative error of the improved algorithm is at least 21.6% higher than that of the unimproved algorithm when solving large-scale PFSPs.

Flocculants are indispensable in water and wastewater treatment, enabling the aggregation and removal of suspended particles, colloids, and emulsions. However, the conventional development and application of flocculants rely heavily on empirical methods, which are time-consuming, resource-intensive, and environmentally problematic due to issues such as sludge production and chemical residues. Recent advances in machine learning (ML) have opened transformative avenues for the design, optimization, and intelligent application of flocculants. This review systematically examines the integration of ML into flocculant research, covering algorithmic approaches, data-driven structure–property modeling, high-throughput formulation screening, and smart process control. ML models—including random forests, neural networks, and Gaussian processes—have successfully predicted flocculation performance, guided synthesis optimization, and enabled real-time dosing control. Applications extend to both synthetic and bioflocculants, with ML facilitating strain engineering, fermentation yield prediction, and polymer degradability assessments. Furthermore, the convergence of ML with IoT, digital twins, and life cycle assessment tools has accelerated the transition toward sustainable, adaptive, and low-impact treatment technologies. Despite its potential, challenges remain in data standardization, model interpretability, and real-world implementation. This review concludes by outlining strategic pathways for future research, including the development of open datasets, hybrid physics–ML frameworks, and interdisciplinary collaborations. By leveraging ML, the next generation of flocculant systems can be more effective, environmentally benign, and intelligently controlled, contributing to global water sustainability goals.

<p>This paper explores reflections on the application of the story-based teaching method in college English grammar classes, aiming to address the long-standing issues of monotonous teaching and low student engagement. This paper analyzes the advantages of story-based teaching method such as enhancing immersive learning experiences, reinforcing grammatical understanding through meaningful contexts, and fostering students’ cultural awareness. It also delves into practical strategies for overcoming challenges, emphasizing the importance of customized story design and interactive classroom activities. Ultimately, the story-based teaching method holds great promise for revolutionizing college English grammar instruction, but continuous exploration and improvement are essential to maximizing its value.</p>

Depression and anxiety are prevalent mental health issues among older adult widowed adults. However, the symptom-level relationships between these conditions remain unclear. Due to the high correlations and complex relationships among various symptoms, this study employs network analysis to explore differences in the network structures of depression and anxiety symptoms between widowed and non-widowed older adults. Propensity score matching was used to identify widowed older adults with similar demographic characteristics. Data from 1,736 widowed and 1,736 matched controls were analyzed using the Chinese Longitudinal Healthy Longevity Survey (2017-2018). Depression and anxiety were measured by the Center for Epidemiologic Studies Depression Scale-10 (CESD-10) and the seven-item Generalized Anxiety Disorder Scale (GAD-7), respectively. Central and bridge symptoms were evaluated using expected influence (EI) and bridge expected influence (BEI), respectively. Network analysis revealed similarities in central symptoms between widowed and non-widowed older adults, with both groups exhibiting "Feeling depressed or down" (CESD3), "Feeling tense and having difficulty relaxing" (GAD4), and "Being unable to stop or control worrying" (GAD2) as core symptoms. However, differences emerged in bridge symptoms. In the widowed group, "Feeling anxious, worried, or distressed" (GAD1) was most strongly connected to "Felt lonely" (CESD8); "Worrying too much about various things" (GAD3) was strongly linked to "Feeling increasingly exhausted and useless with age" (CESD4); and "Feeling depressed or down" (CESD3) had a strong association with "Becoming easily annoyed or irritable" (GAD6). In the non-widowed group, "Feeling anxious, worried, or distressed" (GAD1) exhibited the strongest association with "Having good sleep quality" (CESD10); "Getting upset over small matters" (CESD1) was closely connected to "Feeling anxious, worried, or distressed" (GAD1); and "Worrying too much about various things" (GAD3) was most strongly connected to "Feeling depressed or down" (CESD3). Common central and bridge symptoms highlight universal intervention targets. Addressing "Feeling depressed or down" in widowed and "Getting upset over small matters" in non-widowed older adults may help prevent depression-anxiety comorbidity. These findings support targeted interventions to improve mental health outcomes. Future research should evaluate tailored intervention effectiveness.

Abstract Debris flow is one of the most common types of geological disasters in China. Owing to the influence of topography, geomorphology, geological conditions, human activity, and rainfall debris flow disasters frequently occur in the mountainous areas of Beijing. The research on debris flow in the Beijing area focuses on rainfall and risk evaluation, material sources, and early warning and prevention of debris flow. However, there are few studies on the development characteristics of single-gully debris flow and the prediction of hazardous areas in the Beijing area. Therefore, we chose the debris flow of Bangou Village in Yanqing District of Beijing as the research object. We analyzed the recharge conditions in the ditch domain and predicted the extent of the hazardous area around the gully, providing suggestions for control measures. The dynamic reserves of the loose deposits in the debris flow gully, currently in the development stage, were estimated as 15.48 × 104 m3, representing four supply sources: artificial deposits, alluvium and diluvium, residual slope deposits, and collapse. The peak flow is 24.49 m3/s for a 10-year rainfall event, 27.64 m3/s for a 20-year rainfall event, 31.79 m3/s for a 50-year rainfall event, and 34.93 m3/s for a 100-year rainfall event. The total amounts of solids washed out by a debris flow from the preceding events are 0.70 × 104 m3, 0.79 × 104 m3, 0.91 × 104 m3, and 1.00 × 104 m3, respectively. The size of the debris flow is small, with a maximum hazardous area of 0.2810 km2. We conclude that a small debris flow outbreak in the Bangou Village gully is possible. We expect that the results of this study will provide basic information and help improve debris flow research in Beijing.

This project aims to solve the problem that the high dependence of conventional extended Kalman filter (EKF) in accurate modeling conflicts with the inaccurate acquisition of battery dynamics modeling accuracy, and researches a new method for estimating state of charge (SOC) over the lifetime based on the fully data-driven modified EKF algorithm. This algorithm can effectively overcome the accumulation errors in traditional algorithms, while maintaining the dynamic performance of the system. At the same time, the traditional method over relies on the deficiency of the unit, and maintains the good robust performance of the unit. A black box system with internal voltage serves as output and battery internal impedance as time-varying parameter. Through dynamic identification, the actual operating status of the power battery is obtained, and its accurate and dynamic changes are ensured to achieve SOC estimation over the entire life cycle. Finally, the effectiveness of the proposed algorithm is verified by computer simulation.

The goal of aspect-based multimodal sentiment analysis (ABMSA) is to classify the sentiment associated with aspect words in a given context. Most current ABMSA models focus only on general inter-modal information interactions without considering both intra-modal and inter-modal information interactions and ignoring image noise. To address these issues, this paper proposes an Interactive Attention Mechanism Fusion Network (IAMFN) model. The model first designs an image-text fusion module based on the attention, which applies the attention mechanism to a recurrent neural network to fuse text and images while filtering the noise in the images, and finally adds the fused information to the aspect information step by step to obtain the dynamic inter-modal representation. In addition, this paper proposes an aspect-text fusion module based on the attention, which learns the intra-modal contextual representation by calculating the weights of each aspect word in the context. Finally, this paper stitches the information obtained from the two modules and feeds it into the fully connected softmax layers to predict sentiment polarity. We have conducted extensive experiments on two benchmark datasets and the experimental results show that our model achieves state-of-the-art performance.

The status of English education has always been very important. In our country, English is one of the compulsory education activities during high school, university and junior college. High school entrance examination, English CET4, CET6, entrance examination, higher education, postgraduate and other examinations, English scores occupy a place, the scale is very important, so it is really very important to learn English well. The main purpose of this paper is to study college English grades under big data through DM algorithms, including the prediction of grades and the countermeasures for subsequent improvement. This paper deals with the theoretical and technical aspects of data mining (DM) and ML, and describes related technologies, including mining processes and related algorithms. Experiments show that more than 70% of students take the initiative to seek opportunities to learn English and speak English occasionally. At the same time, the proportion of girls who actively seek to learn English is higher than that of boys.