Insufficient Ability Research Articles

Exploration & Exploitation: A Unified Framework for Data Purification & Augmentation in Recommendation Systems

In the context of recommendation scenarios, the utilization of data purification and data augmentation methodologies has demonstrated their efficiency in enhancing the quality of representations. Nevertheless, within an open environment, the constrained nature of interaction data and the diverse range of interaction intentions present formidable challenges, giving rise to insufficient generalization ability and generalization bias in these methodologies. To address this issue, in this paper we introduce Exploitation & Exploration: A Unified Framework for Data Purification & Augmentation in Recommendation Systems, which not only ensures the precise purification of current data but also delves into potential noisy data for further exploration. To be specific, based on the traditional collaborative filtering method calculating user-item correlation, we first implement an efficient multi-head SENet block to remove potential noise from the interaction data. After this, we deploy a diffusion module to remove the added adversarial noise based on its ability to denoise all kinds of noise. And finally we use mutual-learning method to coordinate two parts' learning. We conducted experiments on three publicly available datasets, evaluating our model against current state-of-the-art algorithms in recommendation robustness tasks. The experimental results validate the effectiveness of our model.

Prediction of Native Liver Survival in Patients With Biliary Atresia 20 Years After the Kasai Procedure.

To establish risk models for long-term native liver survival (NLS) in patients with biliary atresia. In this retrospective study, we analyzed data from 1792 patients registered in the Japanese Biliary Atresia Registry. Using multivariate logistic regression, we created predictive models for NLS at 1, 5, 10, 15, and 20 years postoperatively. Variables at the first year of age and those at 1 and 5 years postoperatively were used. The variables used in this model were selected using a forward-backward stepwise selection method. The models were further assessed using C-statistics of internal validation with 1000 bootstrapping resamples. The models using only variables at the first year of age showed insufficient predictive ability. The variables used in the model for NLS at 20 years postoperatively included the age at Kasai procedure, high levels of gamma-glutamyltranspeptidase at 1 year postoperatively, and low levels of cholinesterase at 5 years postoperatively. The models with internally validated C-statistics greater than 0.8 were as follows: NLS at 5 years postoperatively based on the variables at 1 year postoperatively (internally validated C-statistics: 0.88), at 10 years postoperatively based on the variables at 1 year postoperatively (0.86), and at 20 years postoperatively based on the variables at 1 year (0.81) and 5 years (0.83) postoperatively. Overall, we developed satisfactory risk models for NLS up to 20 years postoperatively using variables up to 5 years postoperatively.

A Hybrid Food Recommendation System Based on MOEA/D Focusing on the Problem of Food Nutritional Balance and Symmetry

With the improvement of people’s living standards, the issue of dietary health has received extensive attention. In order to simultaneously meet people’s demands for dietary preferences and nutritional balance, we have conducted research on the issue of personalized food recommendations. For this purpose, we have proposed a hybrid food recommendation model, which can provide users with scientific, reasonable, and personalized dietary advice. Firstly, the collaborative filtering (CF) algorithm is adopted to recommend foods to users; then, the improved Multi-Objective Evolutionary Algorithm Based on Decomposition (MOEA/D) is used to adjust the nutritional balance and symmetry of the recommended foods. In view of the existing problems in the current nutritional balance algorithm, such as slow convergence speed and insufficient local search ability, the autonomous optimization (AO) adjustment strategy, the self-adaptive adjustment strategy, and the two-sided mirror principle to optimize boundary strategy are introduced in the MOEA/D. According to the characteristics of the food nutrition regulation problem, an adaptive food regulation (AFR) adjustment strategy is designed to achieve more accurate nutritional regulation. Based on the above improvements, a food nutritional recommendation algorithm based on MOEA/D (FNR-MOEA/D) is proposed. Experiments show that compared with MOPSO, MOABC, and RVEA, FNR-MOEA/D performs more superiorly in solving the problem of nutritional balance in food recommendation.

Video Anomaly Detection with Hyperbolic Graph Embedding and Masked Normalizing Flows

Video anomaly detection plays a vital role in intelligent video monitoring systems. It has found extensive applications in the fields of public safety and social security. Nevertheless, the area of video anomaly detection continues to be a formidable task because of the intricate nature of actual data and the challenge of precisely identifying anomalies. Current anomaly detection approaches suffer from overpowered generalization ability, weak spatio-temporal feature extraction capability, and insufficient global information aggregation ability. Therefore, an unsupervised Hyperbolic Graph-based Normalizing Flows (HGNF) model is proposed in this paper, which is constructed with a Spatio-temporal Encoder (STEncoder) and stacked normalizing flows to reduce the overgeneralization of auto-encoder-based anomaly detection models. STEncoder consists of spatio-temporal attention and inter-frame feature aggregation. In normalizing flows, a Poincaré ball graph extractor is developed to improve the representation ability of the dynamic changes of the input data, and a masked affine coupling block is established to improve the performance of this model in global information aggregation. According to the experimental results obtained on four public datasets, HGNF achieves excellent performance and the best AUC (Area Under the Curve) score of 74.5% on the UBnormal dataset.

A Qualitative Study on the Experiences of Patients with Pulmonary Hypertension Undergoing Polypharmacy.

Aims/Background Pulmonary hypertension (PH) is a severe progressive disease characterized by elevated blood pressure in the lungs. Medications are a critical form of treatment for patients with PH. This study aims to explore the experiences of patients with PH undergoing polypharmacy, thereby providing a more concrete foundation for formulating targeted intervention measures. Methods A purposive sampling method was used to select 13 PH patients treated in a grade III hospital in Zhejiang Province from December 2023 to February 2024 as the research subjects. This study is a descriptive qualitative research design, where the patients were interviewed face-to-face in a semi-structured manner. The data were analyzed, summarized and extracted using the traditional content analysis method. Results There were five themes and ten sub-themes surrounding the polypharmacy experiences of the PH patients: (1) Negative emotional experience of multidrug use, including lack of disease-related medication knowledge and insufficient ability to obtain medication information; (2) Complex physical testing of multiple drugs, including adverse reactions and complex dose titration; (3) Economic burden; (4) Coping difficulties, including insufficient drug safety, excessive reliance on medical personnel, and lack of opportunities for deep participation; (5) Desire for supports, including professional and social support, as well as those from family, colleagues and classmates. Conclusion Disease, treatment, psychological factors, and social customs affect PH patients' drug use post-diagnosis, with varying experiences and degrees. Healthcare providers must offer tailored care and practical strategies for managing multiple drug use, considering patients' unique experiences and needs.

A General "Two-Lock" Strategy to Enhance Drug Loading and Lysosomal Escape in Intelligent Boronate Ester Polymer Nanoparticles for Improved Chemotherapy.

Boronate ester can be used to prepare intelligent polymer nanoparticles (NPs). However, the traditional boronate ester polymer NPs made of boronic acid and diols using a "single-lock" strategy (B-O NPs) exhibit low drug loading capacity (DLC) and insufficient lysosomal escape ability, resulting in limited antitumor efficacy. We develop a "two-lock" strategy that combines dodecanamine and boronic acid using boron-nitrogen (B ← N) coordination to enhance the formation of a boronate ester polymer. Through this strategy, amphiphilic dextran and poly(vinyl alcohol) are synthesized through conjugation with the phenylboronic acid (PBA)/dodecanamine complex. The amphiphilic dextran encapsulates paclitaxel (PTX) to form B-N-O NPs with a higher DLC than their "single-lock" compartments due to enhanced boronate ester stability and improved hydrophobic drug-polymer interactions. Moreover, the B-N-O NPs release more PTX under acidic conditions compared with the B-O NPs. To demonstrate the generality of this "two-lock" strategy, eight polymer prodrug B-N-O NPs employing poly(vinyl alcohol) or dextran, along with PBA-modified gemcitabine, fluorouracil, and 7-ethyl-10-hydroxycamptothecin, or boronic acid-containing bortezomib and dodecanamine, are prepared, showing overall enhanced DLC and higher responsive drug release efficiency compared to B-O NPs. Importantly, B-N-O NPs with a combination of dodecanamine and boronic acid show a better lysosomal escape capability than B-O NPs. Moreover, B-N-O NPs exhibit stronger cytotoxicity compared to B-O NPs and free drugs in vitro. Their enhanced drug loading, responsive drug release, and lysosomal escape abilities contribute to enhanced antitumor efficacy in vivo. This "two-lock" strategy can be a general and convenient method to prepare responsive polymer NPs with enhanced anticancer efficacy.

A Multiscale Adaptive Fusion Network for Modular Multilevel Converter Fault Diagnosis

Modular Multilevel Converters (MMCs) play a crucial role in new energy grid connection and renewable energy conversion systems due to the significant merits of good modularity, flexible scalability, and lower operating loss. However, reliability is a significant challenge for MMCs, which consist of a large number of Insulated Gate Bipolar Transistors (IGBTs). Failures of the IGBTs in submodules (SMs) are a critical issue that affect the performance and operation of MMCs. The insufficient ability of convolutional neural networks to learn key fault features affects the accuracy of MMC fault diagnosis. To resolve this issue, this paper proposes a novel deep fault diagnosis framework named the Multiscale Adaptive Fusion Network (MSAFN) for MMC fault diagnosis. In the proposed MSAFN, the fault features of the raw current in an MMC are extracted by employing multiscale convolutional neural networks (CNNs) firstly, and then a channel attention mechanism is added to adaptively select the channel containing key features, so as to improve the fault diagnosis ability of the MMC in a noisy environment. Finally, the adaptive size of a one-dimensional CNN is adopted to adjust the weight of the feature channels of different scales, which are adaptively fused for fault diagnosis. Experimental validation is performed on two different MMC datasets. Experimental results confirm that the introduction of an attention mechanism of the multiscale feature adaptive fusion channel improves the recognition accuracy of the model by an average of 15.6%. Moreover, comparative experiments under different signal-to-noise ratios (SNRs) demonstrate that the MSAFN maintains accuracy levels above 96.7%, highlighting its excellent performance, particularly under noisy conditions.

Self-Assembled Peptide-Derived Proteolysis-Targeting Chimera (PROTAC) Nanoparticles for Tumor-Targeted and Durable PD-L1 Degradation in Cancer Immunotherapy.

Proteolysis-targeting chimeras (PROTACs) are a promising technique for the specific and durable degradation of cancer-related proteins via the ubiquitin-proteasome system in cancer treatment. However, the therapeutic efficacy of PROTACs is restricted due to their hydrophobicity, poor cell permeability and insufficient tumor-targeting ability. Herein, we develop the self-assembled peptide-derived PROTAC nanoparticles (PT-NPs) for precise and durable programmed death-ligand 1 (PD-L1) degradation in targeted tumors. The PT-NPs with an average size of 211.8 nm are formed through the self-assembly of amphiphilic peptide-derived PROTAC (CLQKTPKQC-FF-ALAPYIP), comprising a PD-L1-targeting 'CLQKTPKQC', self-assembling linker 'FF' and E3 ligase recruiting 'ALAPYIP'. Particularly, PT-NPs strongly bind to tumor cell surface PD-L1 to form PD-L1/PT-NPs complex, then internalized through receptor-mediated endocytosis and degraded in lysosomes. Second, free PROTACs released from PT-NPs to the cytoplasm further induce the durable proteolysis of cytoplasmic PD-L1 via the ubiquitin-proteasome system. In colon tumor models, intravenously injected PT-NPs accumulate significantly at targeted tumor tissues through nanoparticle-derived passive and active targeting. At the targeted tumor tissues, PT-NPs promote durable PD-L1 degradation and ultimately trigger a substantial antitumor immune response. Collectively, this study provides valuable insights into the rational design of self-assembled peptide-derived PROTAC nanoparticles to ensure noticeable accuracy and enhanced efficacy in cancer treatment.

Identification of marine oil spill types based on multi-source remote sensing data using multi-scale dynamic convolution model

ABSTRACT The identification of marine oil spill types is closely related to source tracing and pollution treatment. At present, most of the remote sensing monitoring of sea surface oil spill is conducted based on a single technical means, which has certain limitations. At the same time, the classification methods used have insufficient ability to extract hyperspectral image features, and the classification results cannot meet the needs of accurate monitoring. In this paper, a multi-scale dynamic convolution algorithm (MDCM) for oil types identification based on airborne hyperspectral data was constructed, and the ability to improve the identification of hyperspectral oil spill types by adding thermal infrared and SAR features was explored. The method application experiments were carried out based on the measured airborne hyperspectral, thermal infrared and SAR remote sensing data of different oil spill types obtained from outdoor oil spill simulation experiment. The experimental results show that: 1) The MDCM model exhibited good classification performance, with an identification accuracy of 88.95% for oil spill types based on hyperspectral image, which was 18.24%, 7.28% and 2.56% higher than those of Support Vector Machine, Random Forest and Convolutional Neural Network, respectively. 2) The combination of hyperspectral, thermal infrared, and SAR data can effectively improve the identification accuracy of oil spill types, with an average improvement of 7.6% compared to that of single hyperspectral features. The improvement effect of thermal infrared features was more significant, while the improvement effect of single SAR features on hyperspectral identification results was not significant.

A hydraulic motor fault diagnosis method based on weighted multi-channel information fusion

Abstract In response to the limitations of the existing single-sensor hydraulic motor fault diagnosis model, which includes significant fluctuations in fault identification accuracy, low data utilization, poor reliability, and insufficient generalization ability under variable working conditions, a novel hydraulic motor fault diagnosis method based on weighted fusion of multi-channel data and migration learning is proposed. Firstly, in order to fully extract the fault information in the multi-channel data set of the hydraulic motor, a multi-channel fusion method based on information entropy weighting is proposed. The information entropy method is employed to calculate the fusion weight of each channel of data, and the sampled data of each channel is weighted and fused. Subsequently, the fusion data from the source domain is employed to pre-train the deep transfer model, with the model parameters obtained from this pre-training serving as the initialization parameters for the target domain model. Further, the parameters of the target domain model’s feature extractor are fixed, and the parameters of its classifier are fine-tuned using the target domain’s fusion data. The distance between the source and target domains is reduced by incorporating an attention mechanism and constructing a loss function. The migration from the source domain to the target domain is achieved, which enables the classifier to adapt to the novel target sample recognition task. Ultimately, the experimental results of hydraulic motor migration diagnosis under variable operating conditions demonstrate that the proposed method is efficacious for hydraulic motor fault diagnosis. In comparison to conventional models such as CNN, LSTM and ResNet, the proposed method exhibits superior migration diagnosis accuracy and strong generalization and robustness under variable operating conditions.

Enhancing the reliability of CSP solder joints under thermal cycling conditions through particle swarm optimization of an improved BP neural network

The packaging of chip-scale (CSP) devices plays a pivotal role in enhancing the reliability of CSP under thermal cycling conditions, largely due to the intricate structure and the recurrent alterations in the actual operating environment. The objective of this study is to enhance the reliability of solder joints by optimising the structural parameters of CSP packaging in order to reduce the strain values at the solder joints. In order to enhance the design efficiency and accuracy of the computational model, the Anand model is adopted in order to define the solder joint parameters, and finite element simulations are conducted using Ansys software. This paper puts forward a novel intelligent algorithm that fuses response surface methodology with a neural network-particle swarm optimization algorithm, thereby enhancing the precision of the system. The method is capable of identifying the combination with the minimum strain value using limited data, thereby addressing the issue of insufficient generalisation ability in conventional methods. The implementation of this method into the model resulted in a minimum strain value of 4.071 × 10−3, representing a 37.6 % reduction compared to the original CSP structure. Furthermore, the optimized lifespan is approximately 3.24 times longer than that observed prior to optimization. The approach presented in this paper has the potential to significantly enhance design efficiency and increase the lifespan of components. It offers a novel perspective for optimising the structural parameters of CSP packaging.

A novel electrochemiluminescent cytosensor using dual-target magnetic probe recognition and nanozymes-catalyzed cascade signal amplification for precise phenotypic enumeration of CTCs.

The inability of surgical biopsy to monitor the dynamic evolution of cancer cells hampers its capacity to reflect real-time tumor heterogeneity. Circulating tumor cells (CTCs), as a crucial target in liquid biopsy, offer a novel approach for accurate monitoring of tumors. However, the rarity and complex phenotype resulting from epithelial-mesenchymal transition pose challenges for conventional methods such as CellSearch and immunohistochemistry, which have insufficient ability for simultaneous phenotyping and enumeration of CTCs. The enumeration of a single phenotype CTCs is insufficient for accurately assessing disease progression. Herein, we propose a strategy to address this issue by fabricating an electrochemiluminescence cytosensor via the integration of dual-target enrichment and nanozymes-catalyzed cascade signal amplification. The graphene oxide@hollow mesoporous Prussian blue/Pt (GO@HMPB/Pt) complex, possessing a large specific surface area and exceptional catalytic activity, is employed for loading a substantial amount of luminol as the signal probe. Dual-target magnetic PPy@Fe3O4/Au-antibody/aptamer is utilized for the magnetic capture of both epithelial and interstitial CTCs. Glutathione (GSH) can disrupt theAu-S bond on aptamer by a thiol exchange reaction and selectively releases a specific subset of phenotypic CTCs, thereby facilitating the efficient capture, accurate classification, and ultrasensitive detection of CTCs in peripheral blood. Using the epithelial MCF-7 and mesenchymal Hela cells as models, the ECL cytosensor demonstrates excellent performance in identifying cells spiked into whole blood. This study presents a novel approach for early detection of metastasis, tracking tumor recurrence, and monitoring therapeutic efficacy.

The ability of changes in oct angiography values to predict visual field and retinal nerve layer tomography progression in patients with glaucoma progression: A prospective study

IntroductionTo investigate whether changes in optical coherence tomography angiography (OCTA) values can predict progression in the visual field (VF) and retinal nerve fiber layer (RNFL) in patients with glaucoma progression. MethodsAll patients in the glaucoma outpatient clinic of SBU Gulhane Medicine Faculty between 2021 and 2023 underwent RNFL, 24:2 VF, and simultaneous peripapillary OCTA. 130 eyes that progressed were included in the study. Thinning of more than 5 μ in any quadrant in the RNFL or a decrease of more than 1 dB in the MD value in the visual field within 6 months was accepted as a progression criterion. The ability of changes in OCTA thickness values and OCTA radial peripapillary capillary plexus (RPCP) analysis to predict progression in RNFL and VF was prospectively investigated. ResultsThe mean age of the patients was 66.9 ± 11.8 years. There was progression in VF in 70 eyes and RNFL in 89 eyes between baseline and 6-month controls. The change in OCTA thickness values had insufficient ability to predict the progression of RNFL in the superior, inferior, nasal, temporal and total quadrants (p = 0.55, 0.40, 0.84, 0.91, 0.39, respectively). The changes in OCTA thickness values failed to predict VF MD progression in the superior, inferior,nasal,temporal,and total quadrants (p = 0.40, 0.11, 0.24, 0.44, 0.10, respectively). The changes in OCTA RPCP values ​​did not show superiority in the ability to predict RNFL progression in superior, inferior, nasal, temporal, and total quadrants (p = 0.21, 0.53, 0.39, 0.39, 0.29, respectively). The changes in OCTA RPCP values ​​did not show superiority in the ability to predict VF progression in superior, inferior, nasal, temporal, and total quadrants (p = 0.96, 0.29, 0.77, 0.42, 0.21, respectively). ConclusionAlthough OCTA is a non-invasive imaging test whose use and popularity have been increasing in recent years, our study could not show superiority compared to RNFL and VF tests in demonstrating glaucoma progression.

Development of a New Media Marketing and Planning Course Based on Project-Based Learning combined with Outcome-Based Education Concept to enhance Problem-Solving Ability in Advertising at Xi'an University

Background and aim: At present, the phenomenon of insufficient problem-solving ability of college students in China is more prominent. The project-based learning（PBL) combined with the outcome-based education (OBE) concept provides new ideas and methods for addressing the problem of insufficient problem-solving ability among college students. The PBL combined with OBE teaching offers effective ways and means to enhance problem-solving ability. Outcome-based education concept (OBE) emphasizes student learning outcomes and focuses on the ability and qualities students acquire during the learning process. While project-based learning (PBL) enables students to participate in solving actual projects, clarifying their learning goals and outcomes, and enhancing their learning motivation and enthusiasm. This teaching model emphasizes practical ability. It focuses on cultivating students' practical ability by having them apply learned knowledge and ability in actual projects, thus improving their problem-solving and practical operation ability, which aligns with the requirements for practical ability in the advertising field. It promotes cooperation and innovation. PBL usually requires students to complete projects in groups, helping to cultivate their cooperation ability and team spirit. At the same time, during the project implementation process, students need to continuously propose innovative solutions, which also helps cultivate their innovation consciousness and innovation ability. This study aims to develop and evaluate the effectiveness of a new media marketing and planning course based on PBL combined with OBE teaching to enhance problem-solving ability in advertising students. Materials and approaches: The study employed a three-phase research design involving phase 1 was studying the background information through reviewing documents and interviewing experts and students, phase 2 was constructing and verifying the developed course by 5 experts, and phase 3 was implementing the course with the sample of 40 junior Advertising students at Xi'an University which were derived by cluster random sampling. The research instruments used to collect data in this phase were as follows:1) scoring rubric of students' problem-solving ability with reliability of 0.84. 2) questionnaire for students' satisfaction with the reliability of 0.75. Data collection was relevant to test papers and scales, and data were analyzed by using statistics including; means, standard deviations, t-test for dependent samples, and one sample t-test. Results: After implementation of a new media marketing and planning course based on project-based learning combined with outcome-based education concept, it revealed that 1) posttest scores of students' problem-solving ability is greater than pretest at.01 levels of statistical significance (t39= 16.01, p = 0.001). 2) students' satisfaction after implementing the course was statistically greater than the criterion of 70% at a.01 level of statistical significance (t39 =19.51, p = 0.001). Conclusion: The PBL combined with OBE teaching provides effective ways and methods for improving college students' problem-solving abilities. By clarifying learning outcomes, emphasizing practical ability, and promoting cooperation and innovation, the PBL teaching methods model can better meet the requirements for problem-solving ability in modern education and the advertising field.

CTIFTrack: Continuous Temporal Information Fusion for object track

In visual tracking tasks, researchers usually focus on increasing the complexity of the model or only discretely focusing on the changes in the object itself to achieve accurate recognition and tracking of the moving object. However, they often overlook the significant contribution of video-level linear temporal information fusion and continuous spatiotemporal mapping to tracking tasks. This oversight may lead to poor tracking performance or insufficient real-time ability of the model in complex scenes. Therefore, this paper proposes a real-time tracker, namely Continuous Temporal Information Fusion Tracker (CTIFTrack). The key of CTIFTrack lies in its well-designed Temporal Information Fusion (TIF) module, which cleverly performs a linear fusion of the temporal information between the (t-1)-th and the t-th frames and completes the spatiotemporal mapping. This enables the tracker to better understand the overall spatiotemporal information and contextual spatiotemporal correlations within the video, thereby having a positive impact on the tracking task. In addition, this paper also proposes the Object Template Feature Refinement (OTFR) module, which effectively captures the global information and local details of the object, and further improves the tracker’s understanding of the object features. Extensive experiments are conducted on seven benchmarks, such as LaSOT, GOT-10K, UAV123, NFS, TrackingNet, VOT2018 and OTB-100. The experimental results validate the significant contribution of the TIF module and OTFR module to the tracking task, as well as the effectiveness of CTIFTrack. It is worth noting that while maintaining excellent tracking performance, CTIFTrack also shows outstanding real-time tracking speed. On the Nvidia Tesla T4-16GB GPU, the FPS of CTIFTrack reaches 71.98. The code and demo materials will be available at https://github.com/vpsg-research/CTIFTrack.

Pulse eddy current testing of corrosion defects in pipelines with insulation layer based on U-shaped sensors

Abstract In response to the insufficient detection ability of CUI in pipelines, based on U-shaped sensors, combined with the wide spectrum and non-contact characteristics of pulse eddy current detection technology, the area and depth of corrosion defects on the outer wall of pipelines can be effectively detected without removing the insulation. Simulation and experimental research are conducted on the outer wall defects of carbon steel test tubes with insulation layers. The simulation results show that the excitation magnetic field generated by the U-shaped sensor can effectively penetrate the inner wall of the pipeline, and the two signal-receiving coils of the U-shaped sensor will generate significant characteristic signals when passing through defects. The detection voltage position curve is obtained by applying the voltage distribution analysis method, and the characteristic signal length is the defect length. The experimental results show that when the detection sensor passes through and leaves the defect, the detection voltage distribution curve will generate a significant voltage drop characteristic signal, and the distance between the measurement points is consistent with the length of the defect. The experimental results are highly consistent with the simulation results.

Factors affected housing prices: taking Boston as an example

Abstract. Real estate price prediction plays a vital role in urban planning, investment decision-making, and risk management. However, existing prediction models often show problems such as insufficient generalization ability and susceptibility to outliers when faced with complex nonlinear relationships, multidimensional features, and noisy data. Therefore, choosing a model that can accurately capture complex patterns and has strong robustness has become the focus of research. This paper introduces the random forest model and compares it with multivariate linear regression, XGBoost, and support vector machine (SVM). Compared with the traditional regression model, the random forest model combines the flexibility of decision trees and the multi-level feature extraction ability of deep learning, and can better handle the complex nonlinear relationships in the Boston housing price dataset. The experimental results show that the random forest model has achieved excellent performance in all evaluation indicators, and the model accuracy indicators are distributed as MSE=8.2502, RMSE=2.8723, MAE=2.0668, and R^2=0.8875. These results show that the random forest model not only outperforms other models in prediction accuracy but also shows significant advantages in dealing with data complexity and improving generalization ability. Therefore, the random forest model provides an efficient and reliable tool for future real estate price prediction research and applications.

Investigation of the effect of three parameters in the GEKO model on the calculation results for backward facing step flow

Abstract. Computational fluid dynamics (CFD) is a field which is attracting more and more focus today for its ability to simulate comprehensive conditions. Reynolds-Averaged Navier-Stokes (RANS), which needs low cost, is one of the most popular methods used in engineering. However, RANS method has insufficient ability to simulate separated flow, which is a major challenge at present. One reason for this is that the model parameters introduce uncertainty into the simulation. This research investigates the effect of three parameters in the Generalized k- (GEKO) two-equation turbulence model on the calculations in backward facing step flow. It is found that C_sep has the greatest influence on the calculation of pressure coefficient and friction coefficient. C_nw has the greatest influence on the reattachment calculation through eddy-viscosity. The calculation results of the three variables show that there is correlation between them. Besides, a better set of parameters is obtained, which will improve the calculation accuracy for these three variables.

Exploring the Mechanisms Driving Sense of Community in a Smart Society in Wuhan: A Mixed-Methods Multidimensional Comparative Study

In the context of China’s community governance, as a result of the insufficient willingness and ability of residents to participate, most communities have formed a “strong political–weak social” governance structure, which limits the effective expansion of social capital. To address this challenge and promote resident participation, achieving a “strong social and political” transformation in governance structure has become a core issue in current research. Meanwhile, “sense of community” serves as a crucial perspective in this research, which remains to be deepened in domestic studies and needs to consider the impact of emerging factors such as smart technologies. This study innovatively introduces affective events theory (AET), constructing a theoretical model and taking Wuhan as an example. By adopting quantitative and case comparison research methods, the paper delves into the factors influencing Wuhan residents’ sense of community in the context of a smart society and the promoting role of smart governance. On the basis of the findings, this paper presents the following conclusions: (1) Communities should attribute equal importance to the construction of both traditional and smart environments while reinforcing the leading and participatory roles of community administrators; (2) In the community’s daily governance processes, equal focus and importance must be attributed to both service delivery and engagement; (3) Communities must acknowledge the individual distinctions among residents and implement tailored governing strategies accordingly; (4) The government should prioritize the research and development of smart applications while boosting financial investments in the creation and operation of smart communities.

The Development Prospect of Prefabricated Dish Industry

Abstract: In recent years, prefabricated dishes is a rapidly developing emerging industry in China. With a long industrial chain, wide connections and high technical requirements, it has become an important productive force for the upgrading of agricultural industry and has great development potential. However, the development of China's prefabricated dish still faces problems such as non-standard industry standards, unstable quality, low consumer acceptance, and insufficient innovation ability. The purpose of studying prefabricated dish is to explore more market potential, promote the upgrading of prefabricated dish industry, and meet more consumer needs. This paper introduces the present situation of China's prefabricated dishes, analyzes the different characteristics of overseas mature prefabricated dishes, and provides a development path for reference. It is suggested that the future prefabricated dishes industry should pay attention to food safety, expand sales channels, innovate dishes, and establish brand and marketing system. It also provides new ideas and suggestions for the future development of predicted dishes.