Yuhao's Blog

Introduction

Many previous studies have shown the importance of basic features such as transaction amount and the previous price in predicting the bitcoin price. Moreover, as already observed in previous studies that reveal the relationship between the transaction amount, and market price with the underlying graph structure, the topological data analysis (TDA) can capture these higher-order interactions\cite{abay2019chainnet}. However, in 2020, due to the rapid development of the cryptocurrency market, the market price of Bitcoin transactions has increased over sixfold, and massive large-scale international capital has poured into this market. In addition, blockchain technology based on Bitcoin has been gradually optimized, and a variety of new cryptocurrencies with different characteristics are constantly being introduced to the market, such as Ethereum, Litecoin, and Dogecoin. Therefore, the general strength of TDA in the analysis of various cryptocurrency transactions urgently needs to be further verified.

In contrast, different research has shown the high performance of vanilla Machine Learning algorithms such as Random forest, Gaussian Process, and ElasticNet in the long-term bitcoin price prediction. However, the latest efficient deep learning model in time series data prediction like RNN, LSTM, and other neural networks did not significantly improve\cite{abay2019chainnet}. Since 2017 with the introduction of the attention mechanism in neural networks, the vanilla transformer’s performance has achieved satisfactory results in many research fields \cite{vaswani2017attention}. Then in 2020, based on the vanilla Transformer, Haoyi Zhou proposed a more efficient model, Informer, which successfully enhanced the prediction capacity in the LSTM problem and used the ProbSparse Self-attention mechanism to replace the canonical self-attention for the reduction of the time complexity and memory usage\cite{zhou2020informer}.

In this research, we focus on topological properties on the dynamics graph of cryptocurrencies of Bitcoin and Ethereum and use the latest attention neural network model Informer to improve the price prediction of cryptocurrencies. At last, we will also explore the different influences of the topological properties on the various cryptocurrency datasets based on their characteristics.

You are trying to use relative imports in python, but you encounter one of the exceptions ImportError: attempted relative import with no known parent package. Yes, relative imports can be confusing from time to time. In this article, we see the method used by python interpreter to resolve the relative imports and how we can fix this issue.

InfluxDB

Attention:

1. How to use DataFrame Client

1

client = DataFrameClient('localhost', 8086, user, password, dbname)

1.If you can not use alphadin.bst in your TexStudio:

save alphadin.bst file from here to your local device, and keep it with the same file with your .tex file.

1. Install mysql on Ubuntu 18.04

1
2

$ sudo apt update
$ sudo apt install mysql-server 

1. update

db.collection.update(criteria, objNew, upset, multi)
criteria: The search condition of update,
objNew: The object or operator of update, like $set, $inc, $setOnInsert
upsert: If the criteria doesn’t exist, if insert objNew, true is insert, default[false], not insert.
multi: default[false], just update the first record of the founded result, if this argument is true, update all founded records.

Motivation

Due to the recent interview at the Sony research department in Stuttgart, so have to explore deeper in GAN. This blog will introduce more details of adversarial examples resarch and more state-of-the-art solutions.

(Draft)

Introduction(说明):

Recently the computer was broken, so all study resources were lost, and before I didn’t like backup files, I had to learn to build a personal blog with Hexo and Github. Write this file, so last time will not waste too much time to redo the same things as today.