欢迎使用我们的GitHub汽车价格预测系统存储库！该机器学习项目利用随机森林、梯度提升和支持向量回归等算法，根据变速器类型、车主历史、年龄等特征预测汽车价格。深入研究我们的代码库，并为增强
Welcome to our GitHub repository for the Car Price Prediction System! This machine learning project utilizes algorithms such as Random Forest, Gradient Boosting, and Support Vector Regression to predict car prices based on features like transmission type, ownership history, age, and more. Dive in to explore our codebase and contribute to enhancing (2024-04-28, Jupyter Notebook, 0KB, 下载0次)
该GitHub存储库提供了一个实现，使用Simulink演示给定地图上两个位置之间的无障碍路径规划。它采用概率路线图（PRM）规划算法（mobileRobotPRM）生成路径，并利用Pure Pursuit控制器块生成导航控制命令
This GitHub repository provides an implementation demonstrating obstacle-free path planning between two locations on a given map using Simulink . It employs a probabilistic road map (PRM) planning algorithm (mobileRobotPRM) to generate the path and utilizes the Pure Pursuit controller block to generate control commands for navigation (2024-04-17, Jupyter Notebook, 0KB, 下载0次)
本项目旨在利用昂贵的肺循环PDE血液动力学模型的数据集，使用高斯过程（GP）构建仿真器。随后，利用马尔可夫链蒙特卡罗（MCMC）方法，根据真实对象的真实测量数据推断PDE模型的参数。
This project aims to utilize a dataset from an expensive PDE hemodynamics model of pulmonary circulation to construct an emulator using Gaussian Process (GP). Subsequently, it employs Markov Chain Monte Carlo (MCMC) to infer the parameters of the PDE model based on the true measured data from a real subject. (2024-03-23, Jupyter Notebook, 0KB, 下载0次)
这个进化模拟器是一个基于Python的创新项目，结合了神经网络、遗传算法和Q学习的概念。代理（生物）在迷宫中导航以达到指定的目标，通过神经网络决策和强化学习策略的独特混合来学习和适应。
This Evolution Simulator is an innovative Python-based project combining concepts from neural networks, genetic algorithms, and Q-learning. Agents (creatures) navigate through a maze to reach a specified goal, learning and adapting over time through a unique blend of neural network decisions and reinforcement learning strategies. (2024-03-20, Jupyter Notebook, 0KB, 下载0次)
本项目的目的是通过从EEG信号中提取拓扑特征来比较强ASMR响应器和预松弛状态，以了解ASMR对拓扑特征的影响。我们的目标是为这两种情况创建持久图，并使用Wasserstein距离了解它们之间的差异。
Purpose of this project is comparing StrongASMR responders with PreRelaxed state by extracting topological features from EEG signals, to see how ASMR affects on topological features . Our goal is to create persistent diagram for both cases and using Wasserstein distance understand the difference between them. (2024-03-16, Jupyter Notebook, 0KB, 下载0次)
泰坦尼克号生存预测概述：开发了一个机器学习模型来预测泰坦尼克上的乘客生存。分析乘客数据、可视化模式，并选择相关特征。训练各种分类器，包括SVM、随机森林和梯度提升。在验证数据集上实现了XX%的最大精度。
Titanic Survival Prediction Overview: Developed a machine learning model to predict passenger survival on the Titanic. Analyzed passenger data, visualized patterns, and selected relevant features. Trained various classifiers including SVM, Random Forest, and Gradient Boosting. Achieved a maximum accuracy of XX% on the validation dataset. (2024-03-11, Jupyter Notebook, 0KB, 下载0次)
這是一份和企業甲級排球聯賽(以下簡稱企排)合作的研究,旨在為企排 YouTube 直播留言建立一個主題模型以量化分析觀眾的討論話題,進而達到了解各主題隨時間的熱度 分佈及掌握觀眾的注意力,以利後續開發更多的商業用途。本文所使用的所有資料均源自於 企排 18 年所有直播場次的留言資料,資料分別透過五個預處理方式以評估模型表現。分類模型由三個分類器所構成,分別用來分類主要主題(閒聊、比賽、加油、轉播)、次要主題(將比賽細分為球員、球隊、裁判、教練、戰術)以及情緒分析,三者的量化評估分數 Area Under ROC Curve 高達 99.55 99.73 99.99,單句留言平均計算時間(計算於 Nvidia T4 GPU)為 0.044 seconds sentence。
This is a research on cooperation with the Enterprise First Class Volleyball League (hereinafter referred to as the Enterprise Volleyball League), which aims to establish a theme model for the Enterprise Volleyball League YouTube live message to quantitatively analyze the discussion topics of the audience, so as to understand the heat distribution of each theme over time and grasp the attention of the audience, so as to facilitate the subsequent development of more commercial uses. All the data used in this paper are derived from the message data of all the live broadcast sessions of the enterprise platoon in 18 years. The data are represented by the evaluation model through five pre-processing methods. The classification model consists of three classifiers, which are used to classify the main themes (chat, match, cheer, broadcast), secondary themes (divide the game into players, teams, referees, coaches, and tactics), and emotional analysis. The quantitative evaluation score of the th (2024-02-27, Jupyter Notebook, 0KB, 下载0次)
实体链接是一个涉及使用Inferess中开发的基于规则的规范化方法来创建正负数据集对的项目。然后，使用这些数据集来训练能够将公司名称映射到384个向量的对比编码器。使用Faiss算法执行匹配过程。
Entity linking is a project that involves using rule-based normalization methods developed in Inferess to create pairs of positive and hard negative datasets. These datasets are then used to train a contrastive encoder capable of mapping company names into 384 vectors. The matching process is performed using the Faiss Algorithm. (2024-02-25, Jupyter Notebook, 0KB, 下载0次)
我开发了一个高级垃圾邮件检测系统，可以准确地将电子邮件分类为垃圾邮件或非垃圾邮件。该项目的核心涉及实现朴素贝叶斯分类器，并辅以用于增强文本分析的单词嵌入，从而在垃圾邮件检测中实现显著的准确性。
I developed an advanced spam detection system that accurately categorizes emails as spam or not spam. The core of the project involved implementing a Naive Bayes classifier, complemented by word embeddings for enhanced text analysis, achieving significant accuracy in spam detection. (2024-02-10, Jupyter Notebook, 0KB, 下载0次)
1.导入libries.加载数据集csv文件，清除数据s 3，字符转换为数字s 4.拆分数据s x和y变量5。训练模型6.使用随机森林分类器算法7.测试数据8.预先引用的输出人员是否存活9.检查nlp预测的准确性
1.import libries2.load dataset csv file, clean data s 3,character convert to numeric s 4.split data s x and y variables 5. training models 6.usings Random Forest Classifier algorithm 7.testing datas8.predcited output person survived or not 9.check accuracy nlp prediction (2024-02-01, Jupyter Notebook, 0KB, 下载0次)
使用该疾病预测机器学习模型精确地预测疾病。该项目采用三种强大的机器学习模型支持向量分类器（SVC）、高斯朴素贝叶斯（GaussianNB）和随机森林，根据用户输入的症状准确预测多达40种不同的疾病。
Predict diseases with precision using this Disease Prediction Machine Learning Model. This project employs three powerful machine learning models—Support Vector Classifier (SVC), Gaussian Naive Bayes (GaussianNB), and Random Forest—to accurately predict up to 40 different diseases based on user-entered symptoms. (2024-01-26, Jupyter Notebook, 0KB, 下载0次)
本研究的目的是识别不同驾驶员的模式，并基于轴方向、坐标、年龄、性别等对其进行分类。Rash驱动模式检测器使用广泛的机器学习算法，包括决策树、随机森林、K-最近邻（KNN）、高斯朴素贝叶斯和SVM。
The aim of this study is to identify patterns of different drivers and classify them based on Axis orientation, Coordinates, age, gender and others. The Rash Driving Pattern Detector uses a wide range of machine learning algorithms, including Decision Tree, Random Forest, K-Nearest Neighbors (KNN), Gaussian Naive Bayes, and SVM. (2024-01-03, Jupyter Notebook, 0KB, 下载0次)
使用Python实现了一个垃圾邮件检测项目，采用了数据清理、探索性数据分析和文本预处理技术。训练和评估朴素贝叶斯模型，使用贝努利朴素贝叶分类器实现了显著的97%准确性和97.35%精度。
Implemented a spam detection project using Python, employing data cleaning, exploratory data analysis, and text preprocessing techniques. Trained and evaluated Naive Bayes models, achieving a notable 97% accuracy and 97.35% precision with the Bernoulli Naive Bayes classifier. (2024-01-02, Jupyter Notebook, 0KB, 下载0次)
3D声学房间模式分析：Jupyter笔记本电脑在Mathematica中实现有限元方法（FEM）解算器，用于基于3D模型计算和可视化房间的声学模式。它提供了对房间声学特性的详细见解，如模式频率、能量、衰减时间和最大振幅。
3D Acoustic Room Modes Analysis: A Jupyter notebook implementing a Finite Element Method (FEM) solver in Mathematica for calculating and visualizing the acoustic modes of a room based on a 3D model. It provides detailed insights into the acoustic properties of the room such as mode frequencies, energies, decay times, and maximum amplitudes. (2023-12-31, Jupyter Notebook, 0KB, 下载0次)