DOCSEARCHbyAlgolia
Submit Docs

Hirsun's Blog

website·Indexed 30 days ago

https://guomaimang.github.io

A personal knowledge base and blog by Hirsun (HAN Jiaming), featuring technical notes on Computer Science, Data Science (DS), and AI. Content covers Machine Learning with scikit-learn, Computer Organization, MIPS assembly, Operating Systems, SQL, Web Programming, and linguistics, alongside personal reflections and creative works.

Tokens
287.2K
Snippets
680
Records
2K
Agent score
75%

What's inside Hirsun's Blog

  1. Overview of SPSS for statistical analysis

    SPSS (Statistical Package for the Social Sciences) is a comprehensive and flexible statistical analysis and data management solution developed by IBM. It is widely used in social science for survey writing, data mining, text analysis, and complex statistical analysis. It is compatible with Windows, Linux, UNIX, and Mac operating systems.

  3. Overview of JavaScript's role and ecosystem

    JavaScript was originally designed specifically for web browsers but has since expanded to many other environments. It holds a unique position as the most widely used browser language and is fully integrated with HTML and CSS. Additionally, many other languages can be compiled into JavaScript to provide extended functionality; developers are encouraged to explore these languages after mastering core JavaScript.

  4. Overview of Clustering in Data Mining

    Clustering is an unsupervised learning method used to group a set of data objects into clusters. A cluster is defined as a collection of objects that are similar to each other within the same cluster and dissimilar to objects in other clusters. It is often used as a standalone tool for data distribution analysis or as a preprocessing step for other algorithms (such as classification or regression).

    Common applications include:

    • Spatial Data Analysis (GIS thematic maps)
    • Image Processing (e.g., face detection via skin-color pixel clustering)
    • Economic Sciences (market research and customer segmentation)
    • WWW (file classification and blog access pattern discovery)

  5. Overview of Association Rule Mining (ARM)

    Association Rule Mining (ARM) is a data mining technique used to discover interesting patterns, frequent itemsets, and association rules within large databases. It is commonly used in market basket analysis to identify items that frequently co-occur (e.g., customers who buy bread also buy milk). The process consists of two primary stages: 1. Frequent Itemset Mining (finding sets of items that appear together frequently) and 2. Rule Generation (creating rules based on those frequent itemsets).

  6. Overview of Seata Distributed Transaction Architecture

    Seata provides a high-performance distributed transaction solution for microservices (compatible with Spring Boot and SSM). It utilizes three primary roles to manage global transactions:

    1. TM (Transaction Manager): Defines the transaction boundary and decides whether to globally commit or rollback.
    2. TC (Transaction Coordinator): A middleware (Seata-Server) that coordinates and delivers commit/rollback instructions to the various services.
    3. RM (Resource Manager): Manages the specific database operations for each service.

  7. Overview of Blockchain Cryptographic Primitives

    Blockchain security and functionality rely on a variety of cryptographic tools. Key primitives include:

    • Hash Functions: Convert input data to fixed-length values for verification and encryption.
    • Authenticated Data Structures (e.g., Chain-of-Blocks): Use hash chains to ensure data integrity and immutability.
    • Digital Signatures (e.g., ECDSA): Verify the authenticity and integrity of messages.
    • Public-Key Cryptography: Uses public/private key pairs for secure encryption/decryption.
    • Elliptic Curve Cryptography (ECC): Provides efficient and secure encryption based on elliptic curve mathematics.
    • Advanced Privacy Tools: Blind Signatures (privacy for signees), Ring Signatures (group anonymity), and Zero-Knowledge Proofs (proving knowledge of a secret without revealing it).
    • Multi-Party Security: Multi-Sig (requires multiple signatures for a transaction) and Threshold Signatures (multiple signers required to generate a valid signature).
    • Post-Quantum Cryptography (PQC): Cryptographic methods designed to be secure against quantum computer attacks.

  8. Introduction to Pragmatics

    Pragmatics is the study of language use, focusing on how meaning is derived not only from the internal semantics of words but also from the speaker's identity, status, role, and the specific context of the conversation. While semantics studies the literal meaning of words and sentences, pragmatics studies meaning within a specific context.

  9. Overview of the Human Information Processor model

    The Human Information Processor model describes how humans perceive and respond to information through a three-stage pipeline:

    • Input: Perception (感知).
    • Throughput: Memory processing, categorized into sensory, short-term, and long-term memory. This stage involves problem-solving via reasoning and association.
    • Output: Motor response and performance evaluation.

  10. Overview of Wireless Personal Area Networks (WPAN)

    A Wireless Personal Area Network (WPAN) is a network centered around an individual where devices are connected wirelessly. Key characteristics include short communication ranges (from a few centimeters to several meters), low power consumption, low cost, and the use of ad hoc networking for self-discovery. Common applications include connecting laptops to printers, PDAs, wireless mice, digital cameras, headsets to mobile phones, and body sensors to medical devices.

  11. Overview of C++ Language Characteristics

    C++ is a compiled, general-purpose, statically typed, case-sensitive, and free-form programming language developed by Bjarne Stroustrup at Bell Labs. It is considered a middle-level language because it combines both imperative and object-oriented features. It supports procedural, object-oriented (including inheritance, polymorphism, encapsulation, and abstraction), and generic programming. C++ includes a rich standard library for file operations and data structure manipulation.

  12. Overview of Exploratory Data Analysis (EDA) philosophy

    Exploratory Data Analysis (EDA) is a data analysis philosophy that uses various techniques—primarily graphical—to understand a dataset without relying on preconceived model assumptions. The primary goals of EDA are to:

    1. Maximize understanding of a dataset.
    2. Reveal underlying structures.
    3. Extract important variables.
    4. Detect outliers and anomalies.
    5. Test basic hypotheses.
    6. Develop concise models.
    7. Determine optimal factor settings.