由上海對(duì)外經(jīng)貿(mào)大學(xué)人工智能與變革管理研究院聯(lián)合研究團(tuán)隊(duì)劉峰*、楊成意、孔德莉、齊佳音等撰寫(xiě)的學(xué)術(shù)論文“A hybrid with distributed pooling blockchain protocol for image storage”發(fā)表于Nature子刊《Scientific Reports》（IF：4.379，JCR Q1）。
區(qū)塊鏈網(wǎng)絡(luò)中缺乏存儲(chǔ)空間的問(wèn)題是分布式存儲(chǔ)研究領(lǐng)域長(zhǎng)期關(guān)注的研究重點(diǎn)，目前，有關(guān)降低區(qū)塊鏈存儲(chǔ)需求的算法和協(xié)議的研究相對(duì)較少，且現(xiàn)有的研究存在局限性，如以犧牲容錯(cuò)性能來(lái)提高時(shí)間成本等方案，有待進(jìn)一步完善。面對(duì)上述問(wèn)題，本研究提出了一種基于分布式圖像存儲(chǔ)的協(xié)議（DISP），InterPlanetary File System（IPFS）的幫助下，可以有效提高區(qū)塊鏈的存儲(chǔ)空間，降低計(jì)算成本。研究團(tuán)隊(duì)充分利用IPFS和分布式數(shù)據(jù)庫(kù)，設(shè)計(jì)了一個(gè)區(qū)塊鏈的模擬實(shí)驗(yàn)，驗(yàn)證了該協(xié)議的可行性。它包含DP算法和其逆運(yùn)算IDP算法，能夠適應(yīng)分布式場(chǎng)景。DP通過(guò)在每個(gè)池區(qū)按順序選擇像素，將高像素的圖像分解成若干低像素的圖像，每個(gè)節(jié)點(diǎn)保存的生成的圖像仍然可以識(shí)別。IDP將每個(gè)節(jié)點(diǎn)保存的分布式信息按照原來(lái)的順序進(jìn)行重組，這樣就可以實(shí)現(xiàn)對(duì)原始文件的無(wú)損還原。這些性能上的優(yōu)勢(shì)為大規(guī)模的工業(yè)和商業(yè)應(yīng)用創(chuàng)造了條件。
成果摘要
Abstract:
As a distributed storage scheme, the blockchain network lacks storage space has been a long-term concern in this field. At present, there are relatively few research on algorithms and protocols to reduce the storage requirement of blockchain, and the existing research has limitations such as sacrificing fault tolerance performance and raising time cost, which need to be further improved. Facing the above problems, this paper proposes a protocol based on Distributed Image Storage Protocol (DISP), which can effectively improve blockchain storage space and reduces computational costs in the help of InterPlanetary File System (IPFS). In order to prove the feasibility of the protocol, we make full use of IPFS and distributed database to design a simulation experiment for blockchain. Through distributed pooling (DP) algorithm in this protocol, we can divide image evidence into recognizable several small files and stored in several nodes. And these files can be restored to lossless original documents again by inverse distributed pooling (IDP) algorithm after authorization. These advantages in performance create conditions for large scale industrial and commercial applications.