Tag » Matlab

Scalable nonparametric inference for random graphs

This paper by Emily Fox and François Caron has been on arXiv for a while, but a fortnight ago it was read at an ordinary meeting of the RSS. 780 kata lagi

MCMC

1x01 - Pilot

At some point, Physicist became curious about the real world. And that changed everything:

  • Tim Berners Lee invented the Internet
  • Kip Thorne helped producing the movie ‘Interstellar’
  • 623 kata lagi
Data Science

Some Image and Video Processing: Motion Estimation with Block-Matching in Videos, Noisy and Motion-blurred Image Restoration with Inverse Filter in Python and OpenCV

The following problems appeared in the exercises in the coursera course Image Processing (by Northwestern University). The following descriptions of the problems are taken directly from the exercises’ descriptions. 824 kata lagi

Python

Tài liệu Tutorials Matlab dịch

Trích trong tài liệu:

Chào bạn đã đến với Các bài thực hành về điều khiển cho MATLAB và Simulink (Control Tutorials for MATLAB and Simulink). 1.716 kata lagi

Maple

Compute Laplacian in Matlab

Here’s how to find the Laplacian of function , i.e. , in Matlab using Symbolic Toolbox. Note that we can also take the divergence of the gradient to give us the Laplacian… 23 kata lagi

Matlab

2017年海洋科學年會

2017/5/4-5 @ 國立中山大學

聆聽海洋的訊息:應用深度學習分析海洋聲景之變動

林子皓、曹昱
中央研究院 資訊科技創新研究中心

被動式聲學監測已被廣泛應用在海洋環境與生態研究中,長期錄音中的各種環境音與動物音增加了我們對海洋生態環境的了解,許多研究也深入探討人為噪音對海洋生態的影響。然而,過去針對海洋聲景的分析大多著重噪音的時頻譜特性,並透過設定規則的偵測器尋找海洋動物的聲音。但海洋聲景受到地形、氣候、生物群聚與人為活動的高度影響,時頻譜分析可能無法有效描述同時出現的多種聲源,偵測器效能也隨著噪音變動而改變。為了有效分離海洋聲景中的各種聲源,本研究應用非負矩陣分解法 (non-negative matrix factorization) 及其變形方法分析長期時頻譜圖,將輸入資料拆解為特徵矩陣與編碼矩陣。雖然單層的非負矩陣分解法在多次疊代後,能夠在特徵矩陣與編碼矩陣約略學習到各種聲源的頻譜特徵與時域上的強度,但仍難以分離重疊的多種聲源。本研究將多層學習器分別預訓練後堆疊成深度學習架構,並在各層之間逐漸減少特徵矩陣之基底數量,藉由最末層回傳後之重建資料和輸入資料的誤差,在多次疊代中自行修正各層模型參數以達到最佳的聲源分離成果。本研究針對各地具有不同環境噪音特性的海洋聲景進行分析,結果顯示在不需要辨識樣本與資料標籤的情況下,深度學習能夠有效分離海洋中的各種主要聲源:魚群鳴唱、槍蝦脈衝聲、船隻噪音與環境音。學習到的特徵矩陣也能夠作為辨識樣本,透過半監督式學習分析大量的線上資料。透過深度學習分離聲源,未來將能夠更有效評估海洋聲景的複雜結構,並藉此探討海洋環境與生態的變動,以及人為開發的影響。

Passive Acoustic Monitoring