Heart failure is a common heart disease whose incidence and mortality rate are increasing year by year. In order to predict heart failure accurately, three models, LightGBM, adaboost and XGBoost, were used for training and evaluated in this paper. After data preprocessing, the data was divided into training and test sets in the ratio of 7:3 and the models were evaluated using parameters such as precision, accuracy, recall and F1 score. The results showed that the best performer in terms of prediction accuracy was the LightGBM model, which achieved 88.4% accuracy, followed by the adaboost model with 87.7% accuracy, and the XGBoost model, which also achieved 87.3% prediction accuracy. In conclusion, all three prediction models achieved more than 85% accuracy and could accurately predict a patient's heart failure. Confusion matrix results showed that each model was able to effectively identify both positive and negative samples in the test set with high sensitivity and specificity. These results indicate that these models are highly reliable and practical in practical applications, and can provide important reference information for doctors to help them better diagnose and treat heart failure patients, thus improving treatment outcomes and survival rates.

The electric power system is one of the indispensable infrastructures in modern society, and its stable operation is crucial for guaranteeing economic development and social security. By calculating the correlation coefficient and drawing the correlation heat map, we find that there is a correlation between the voltage at each location and the occurrence of electrical faults, and at the same time, there is also a certain correlation between various types of electrical faults and the voltage at each location. These results indicate that there are complex and close interrelationships between different locations and between different types in the power system. In order to better identify and classify different types of electrical faults, we used the random forest model for prediction. The model is used to classify whether an electrical fault occurs or not and to determine its category. The prediction results show that the Random Forest achieved 99.63% in classifying whether an electrical fault occurred or not, and 91.26% in classifying the category of electrical faults. This shows that the Random Forest algorithm model is able to detect electrical faults well, as well as judge the category of electrical faults. In summary, this paper provides insight into the operation of the power system by studying the correlation between the voltage at various locations in the power system and the different types of electrical faults and using the random forest model to make predictions. These findings are of great significance in ensuring the stable operation of power systems.

Advancements in autonomous driving have been achieved due to the increasing use of artificial intelligence. The existing autonomous driving technology is insufficient to handle intricate traffic conditions. In autonomous driving, the world model is a crucial and innovative technology. Utilizing sensors and pre-existing knowledge, a world model can enhance the autonomous driving system's comprehension of the surroundings, offer essential data for future judgments, and enhance the system's resilience. The paper employs literature analysis and review methods to investigate the research and implementation of world models in autonomous driving, including environment perception and modeling, path planning, decision-making, and safety. This study examines the use of artificial intelligence technology in autonomous driving and analyzes the research and application of the world model in this field. It offers new insights for addressing challenging scenarios in autonomous driving and enhancing the safety of the system.

Semantic segmentation, crucial in computer vision, differentiates objects within images and finds applications in autonomous vehicles, medical imaging, and assistive technology. It typically employs neural networks for pixel-wise image classification. Key advancements in this field are attributed to Fully Convolutional Networks (FCN) and DeepLab models, known for their high performance with extensive datasets. However, the challenge arises when these models are applied to smaller datasets. Our research presents a concise overview of seminal work in machine learning and semantic segmentation, followed by an exploration of FCN and DeepLab architectures. The study primarily focuses on evaluating these models’ efficacy on a smaller dataset. Results, summarized in tables and figures, indicate that FCN-16 outperforms others in limited-data scenarios, while DeepLab shows reduced effectiveness. This finding is significant for applications with constrained data resources, providing a direction for future research in semantic segmentation under such conditions.

Assisted driving is a necessary way to realize autonomous driving, in which bird's-eye-view (BEV) is an ideal solution to perceive the targets around the body, i.e., the information acquired by the sensors of the body is extracted and semantic features are integrated into the BEV plane for downstream tasks such as target detection, scene segmentation, and path planning, etc. BEV-based pure vision target detection refers to the use of ordinary cameras without relying on other sensors to perceive the targets around the body. BEV-based pure visual target detection, on the other hand, refers to the use of ordinary cameras to perceive targets around the body without relying on other sensors, and Lift Splat Shoot (LSS) is a more typical solution among the existing schemes. Since the information obtained by each camera in assisted driving is always continuous, incorporating the temporal information into the model can achieve better detection results. We design the model (Sequential and Single Target based LSS) SSTL, and the experiment proves that our model has a certain performance improvement based on the original model.

Mobile Internet user credit assessment is an important way for communication operators to establish decisions and formulate measures, and it is also a guarantee for operators to obtain expected benefits. However, credit evaluation methods have long been monopolized by financial industries such as banks and credit. As supporters and providers of platform network technology and network resources, communication operators are also builders and maintainers of communication networks. Internet data improves the user’s credit evaluation strategy. This paper uses the massive data provided by communication operators to carry out research on the operator’s user credit evaluation model based on the fusion LightGBM algorithm. First, for the massive data related to user evaluation provided by operators, key features are extracted by data preprocessing and feature engineering methods, and a multi-dimensional feature set with statistical significance is constructed; then, linear regression, decision tree, LightGBM, etc. The machine learning algorithm builds multiple basic models to find the best basic model; finally, integrates Averaging, Voting, Blending, Stacking and other integrated algorithms to refine multiple fusion models, and finally establish the most suitable fusion model for operator user evaluation.

On December 19, 2023, the Chinese Ministry of Education's press conference once again emphasized the continued expansion of undergraduate professional degree enrollment. Nowadays, under the influence of the expanding enrollment scale of colleges and universities, the reasonable allocation of limited educational resources has become the primary task of educators, and college students' course choice and course arrangement will directly determine their school life quality. However, the number of students is large, so the research topic of this paper is to use greedy algorithms to design a more efficient course selection and scheduling system. The course selection and scheduling system based on the greedy algorithm can save the resources required by manual scheduling to the maximum extent and directly improve the work efficiency of educators. The system designed and practiced in this paper is effective to a certain extent, and the effective use of the algorithm can avoid many problems in course selection and course arrangement.

This paper provides a comprehensive review of the state-of-the-art in humanoid robotics, discussing the latest advancements, challenges,and potential future trends in the field. Through an analysis of relevant literature, this paper highlights the importance of humanoid robots in various applications, including service, entertainment, and industrial sectors. Furthermore, this paper also identifies the main research questions and technical challenges that need to be addressed to enable the full potential of humanoid robots to be realized. The research on humanoid robots originated from the simulation of human behavior and morphology. The original intention of this simulation is to improve the adaptability, efficiency, and safety of robots in specific environments. For example, in a home environment, humanoid robots can mimic human actions and behaviors, completing tasks such as household chores, taking care of the elderly and children. On industrial production lines, humanoid robots can mimic the actions of workers and complete complex tasks such as assembly and handling. In addition, research on humanoid robots also involves multiple fields such as human-computer interaction, artificial intelligence, computer vision, etc., providing strong technical support for the application of robots in various environments.

This article delves into the systematic analysis of Hyperspectral Imaging Technology (HSI) and Intelligent Sensor Systems in the context of multiscale agriculture, showcasing their critical role in enhancing efficiency and sustainability in agricultural production amid the challenges posed by global population growth. It highlights the pressing need to optimize agricultural processes through advanced technologies to tackle issues such as resource scarcity and environmental pollution. By presenting case studies, the article illustrates the effective integration of HSI and intelligent sensors in key agricultural processes—soil analysis, crop monitoring, and pest detection—underscoring their significance in advancing precision agriculture. The discussion extends to the potentials of data fusion and decision support systems in elevating crop yield and quality. Concluding, the paper emphasizes that despite facing hurdles like technical barriers and maintenance costs, the application of these technologies not only boosts production efficiency and precision but also contributes to agricultural sustainability, underlining the importance of continued research and innovation for a more sustainable and efficient agricultural future.

Medical image segmentation is crucial in the fields of computer vision and medical image processing. Its difficulty lies in precisely extracting regions of interest from images, such as blood vessels, tumors, or other anatomical structures, which is especially important in retinal images and skin pathology images. However, factors like noise, low contrast, and the complexity of target structures in medical images severely affect the accuracy of segmentation.Despite significant progress made by deep learning models such as U-Net in medical image segmentation, their performance still needs improvement when dealing with medical images with complex contexts and long-range dependencies. To tackle these challenges, we introduce a new deep learning model named GSANet.The GSANet model retains the advantages of U-Net while incorporating two innovative modules to enhance its performance in handling challenging medical image segmentation tasks. We assess the GSANet model's performance on two demanding medical image segmentation tasks, DRIVE and ISIC2018. Experimental findings illustrate that the GSANet model achieves significant performance enhancements on these tasks, surpassing the current state-of-the-art methods.The success of the GSANet model can be attributed to its effective design and implementation. GSANet excels in handling medical image segmentation tasks with complex contexts and long-range dependencies, leading to superior performance. Our research highlights the superiority of the GSANet model in medical image segmentation tasks, opening up new possibilities for further improvements in the performance and accuracy of medical image segmentation.