2025/09/24

比較 Tableau 與 Power BI 在公司內部「雲端報表共享」上的應用差異

 這是一個很實用的問題 👍 我來幫你比較 Tableau 與 Power BI 在公司內部「雲端報表共享」上的應用差異:


🌐 部署與雲端平台

  • Tableau

    • 提供 Tableau Server(自建伺服器)與 Tableau Online(SaaS 雲端服務)。

    • 適合需要跨國、多部門協作的大型企業。

    • 能與多種雲端數據平台(AWS、Google Cloud、Azure)高度整合。

  • Power BI

    • 原生整合在 Microsoft Azure 與 Office 365 生態系統

    • 更適合已經使用 Microsoft Teams、SharePoint、Outlook 的公司。

    • 共享體驗相對平順,尤其對於已經在 Microsoft 生態系的組織。


👥 使用者共享與協作

  • Tableau

    • 透過 Tableau Server / Online 分配「Viewer、Explorer、Creator」不同角色。

    • 擅長處理跨部門、大規模共享,能提供使用者 互動式探索(下鑽、過濾)。

    • 對非技術人員可能需要額外培訓,因為報表操作相對專業化。

  • Power BI

    • 與 Microsoft 365 帳號直接綁定,授權和群組控制容易。

    • 使用者可以在 Teams、Outlook 直接嵌入報表,協作流暢。

    • 適合一般商務人員快速查看與互動,學習曲線較低


📊 報表設計與互動

  • Tableau

    • 可建立高度自訂的可視化,設計靈活度高,支援複雜的分析需求。

    • 適合數據科學、商業分析部門,做 深度視覺化探索

  • Power BI

    • 視覺化元件雖然少一些,但足以應付大多數商務情境。

    • 側重於 標準化報表、即時儀表板,適合經理層快速決策。


🔐 安全性與治理

  • Tableau

    • 提供強大的存取控制、資料治理與審計功能。

    • 適合需要嚴格合規(如金融、醫療)的大型組織。

  • Power BI

    • 繼承 Azure Active Directory (AAD) 的權限控管,與公司現有的 AD 整合容易。

    • 更適合 Microsoft 生態內的資訊安全政策。


💲 成本與授權

  • Tableau

    • 計費較高,以使用者角色(Viewer/Explorer/Creator)收費。

    • 適合預算充足、需要高彈性分析的企業。

  • Power BI

    • 價格相對便宜,Pro 訂閱每人每月約 10 美元,Premium 提供更大規模與雲端運算能力。

    • 成本效益高,特別適合中小企業或已經購買 Microsoft 365 的公司。


📌 總結

  • Tableau → 適合 數據驅動文化濃厚、跨部門合作、需要高度自訂視覺化的大型企業

  • Power BI → 適合 已使用 Microsoft 生態系(Teams、SharePoint、Office 365)的公司,追求成本效益與快速部署


2025/09/23

電力驅動的垃圾熱處理

 簡短結論:目前幾乎沒有公開的「以核反應爐的熱,直接拿來焚燒一般市政垃圾(MSW)」的實證專案。各國與國際機構評估核能多用在工業供熱、區域供暖、海水淡化、製氫等;垃圾處理則仍以「自燃焚燒/氣化(自身做燃料)」或「以電力驅動的等離子處理」為主(電力來源可含核電)。以下把「誰評估/測試過、結論如何」整理給你:

1) 「核能用於工業熱/供暖」的系統性評估(非特定於焚燒垃圾)

  • OECD-NEA(核能署):評估高溫氣冷堆(HTGR)供工業熱的可行性與限制,重點是化工、煉油、氫能、區域供熱等應用;文件把「焚燒垃圾」列為主要耦合場景。結論:在中高溫(多數 <~750 °C)工業熱需求上技術可行,但實施取決於經濟與在地條件。Nuclear Energy Agency (NEA)

  • MIT Energy Initiative(麻省理工)《限碳世界中的核能》(2018/2019):總結核能供工業熱的潛力與溫度邊界,建議優先導入低到中溫工藝與區域供熱;未提到用核熱來焚燒MSW。Main

  • EPRI(美國電力研究院):盤點核電廠對區域供熱的現況與歷史案例(東歐、北歐等地),顯示核電可穩定輸出熱能到城市熱網;但文獻中沒有核熱直接服務於垃圾焚化廠的實例。restservice.epri.com

2) 「電力驅動的垃圾熱處理」(核電可做電源)的實證與結果

  • 等離子氣化(Plasma Gasification)

    • MIT 新聞報導 InEnTec 等公司以等離子氣化把各類垃圾轉為合成氣與可用的玻璃渣,已有多處部署;技術可行但經濟性與放大規模是難點。MIT News

    • 美國俄勒岡 Columbia Ridge 的示範(S4 Energy / Waste Management 參與):展示把家戶垃圾轉成可用合成氣與玻璃渣;媒體與技術文獻指出技術能跑、商轉擴張困難WIRED

    • 學術面:高溫蒸汽氣化可把塑膠/MSW 轉為清潔氣體燃料;多篇研究驗證路線可行,但仍受原料雜質、經濟性所限。ACS Publications

    • IEA Bioenergy(任務組33)總結:垃圾氣化可產能,但落地常受政策、經濟與供料穩定度影響。IEA Bioenergy
      ⮕ 以上流程用「電」驅動,理論上核電可提供低碳、穩定電力,但現有示範並未強調「必須使用核電」。

  • 傳統焚燒—評估/設計趨勢:多國把重點放在效率與超低排放改造與監管(非核能供熱)。例如:

    • 中國大陸生態環境部的《生活垃圾焚燒發電廠現場監督檢查技術指南》(2022)與浙江省的超低排放評估監測技術指南(2025),推動焚燒廠的達標與改造評估。Ministry of Ecology and Environment+1

    • 美DOE(EERE)報告:MSW 作為能源原料含水率高、熱值低且成分異質,是經濟與技術整合的主要挑戰;當前主流仍是焚燒與厭氧消化。The Department of Energy's Energy.gov

3) 「核領域自身廢棄物」的等離子焚化/玻璃化測試

  • 放射性廢棄物(非一般垃圾):早在 1990s 就有等離子焚化+玻璃化的研究與示範,能顯著減容並把無機殘渣玻璃化以便長期穩定處置。這類測試多發生在核能/研究單位或其承包商。ScienceDirect

4) 為何「核能+燒垃圾」少見?

  • 垃圾本身就是燃料:現代焚化設計是用垃圾的熱值自給自足;額外用高品級外部熱源(如核熱)經濟誘因不強,還可能推高 NOx 生成風險(過高爐溫)。NCBI

  • 佈署與監管:把大量混合垃圾運到核電廠附近不具社會與監管可行性;核電更常被用來供熱給城市或工業,而不是反過來服務焚化爐。restservice.epri.com+1

  • 技術聚焦不同:國際路線圖把核熱優先用在區域供暖、海淡、製氫與中溫工藝熱;焚燒垃圾不是主要耦合案例。Nuclear Energy Agency (NEA)+1

  • MSW 端的優先事項:各國在排放監測/超低排放改造與熱網整合上下功夫,而非尋找外部高品級熱源來「幫忙燒」。Ministry of Ecology and Environment+1

可以落地的「折衷方案」

如果目標是「用核能幫垃圾處理降低碳排」,比較務實的是:

  • 核電(含SMR)→ 穩定低碳電力 → 等離子氣化/電鍋爐/CCS等單元:利用核電穩定性來提高等離子氣化碳捕集的可用率。MIT News+1

  • 核電供區域熱網,焚化爐與核熱共用熱網:兩者各自發熱,但在熱網層面做調度與備援(北歐與東歐已有核供熱與焚化供熱的成熟案例,但多為各自入網而非直接耦合)。restservice.epri.com

2025/09/20

Desktop Media Cleanup App — Requirements v1.0

Desktop Media Cleanup App — Requirements v1.0

1) Overview & Goals

A desktop utility that helps users quickly triage photos and videos by assigning scores and bulk‑deleting low‑scored media. The app indexes media in a chosen root folder, previews items one‑by‑one, lets users adjust a per‑file score via mouse clicks, and automates deletion of files that were marked for removal.

Primary goals

  • Fast, keyboard/mouse‑driven triage of large media libraries.

  • Clear progress feedback and a definitive “clean up completed” state.

  • Safe, reversible (optional) delete flow, per user confirmation.

Out of scope (v1): Cloud sync integrations, facial recognition, deduplication, format conversion, editing.


2) Platforms & Tech Assumptions

  • Target OS: Windows 10+, macOS 12+, (optional) Linux (Ubuntu LTS).

  • Packaging: Native installers (MSIX/EXE, DMG/PKG, AppImage/Snap optional).

  • Media preview: use OS codecs or a cross‑platform library (e.g., ffmpeg/AVFoundation/DirectShow) for thumbnails and playback.

  • Index store: single file per root (SQLite recommended; JSON allowed for MVP).


3) Core Concepts & Definitions

  • Root Folder: The folder the user chooses to clean; includes all subfolders.

  • Index: On‑disk database of discovered media and their scores/metadata.

  • Score: Integer 1..51..5, default 3 for each indexed file.

    • 1 = reject (to delete), 5 = keep (locked), 2/3/4 = undecided.

  • todelete folder: Destination subfolder under each file’s current parent for files scored 1.


4) User Stories

  1. As a user, I can pick a folder and immediately see its subfolders in a tree with file counts.

  2. As a user, I can preview photos/videos in sequence and change their score quickly with the mouse.

  3. As a user, I can skip items already at score 1 or 5 and focus only on undecided ones.

  4. As a user, I can finish triage and bulk‑delete the 1‑scored files after a clear confirmation.

  5. As a user, I see a "clean up completed" message when every file is either 1 or 5.


5) Functional Requirements

FR-1 Folder Navigation & Tree

  • FR-1.1 The app shows a collapsible folder tree rooted at the selected folder.

  • FR-1.2 Users can toggle among folders and subfolders; selecting a node filters the item list/preview scope.

  • FR-1.3 Each node displays the total media file count (photos + videos) within that folder including all nested subfolders.

FR-2 Indexing

  • FR-2.1 On selecting a root, the app creates/updates an index of photos and videos (configurable extensions: jpg/jpeg/png/heic/webp/mp4/mov/avi/mkv, etc.).

  • FR-2.2 Each discovered file is added with initial score = 3.

  • FR-2.3 The index stores: absolute path, file size, modified time, hash (optional), duration (video), orientation + EXIF date (photo), and current score.

  • FR-2.4 Index updates are incremental on subsequent launches (detect adds/removes/moves).

  • FR-2.5 Index file is stored at the root as .media_index.sqlite (or .json for MVP).

FR-3 Preview & Scoring

  • FR-3.1 The app starts previewing media from the current selection/folder.

  • FR-3.2 Right‑click on preview adds +1 to the current file’s score (max 5).

  • FR-3.3 Left‑click on preview deducts −1 from the current file’s score (min 1).

  • FR-3.4 Keyboard shortcuts (optional but recommended): = +1, = −1, Space = next, Backspace = previous.

  • FR-3.5 The preview loop auto‑skips any item with score 1 or 5.

  • FR-3.6 When the current pass ends, the app circles back to files that are still score 2/3/4 until all files are 1 or 5.

  • FR-3.7 Video preview defaults to the first 5 seconds (toggle to full playback); photo preview fits to window with zoom/pan.

FR-4 Move & Delete

  • FR-4.1 Whenever a file’s score becomes 1, the app moves it to a sibling folder named todelete under its original parent (create if missing). Preserve subfolder structure relative to the root.

  • FR-4.2 When all files within the selected scope are either 1 or 5, show “clean up completed”.

  • FR-4.3 Prompt: “Delete all files scored 1?” If the user confirms, permanently delete those files (see Safety below), then delete the index file.

  • FR-4.4 After deletion, recursively remove empty folders (folders with no files in them or any of their subfolders).

FR-5 Progress & Status

  • FR-5.1 Show counts: total, scored 1, scored 5, remaining (2/3/4).

  • FR-5.2 Status bar indicates current folder, preview position (e.g., 120/3,482), and pass number.

FR-6 Settings

  • FR-6.1 Configure included file extensions.

  • FR-6.2 Toggle confirm‑before‑move (default off) and confirm‑before‑delete (default on, cannot be disabled in v1).

  • FR-6.3 Option to send deletes to OS Trash/Recycle Bin instead of hard delete (recommended default).


6) Non‑Functional Requirements

  • Performance: Index 50k files in ≤ 5 minutes on SSD; preview latency ≤ 150 ms for images, ≤ 500 ms to start video.

  • Reliability: Crash‑safe index writes (transactional); resume last session state.

  • Security: No network access by default; operates only on local paths with explicit user selection.

  • Accessibility: All actions available via keyboard; high‑contrast option.


7) UX & Screens

  • Main layout: Left = folder tree with counts; center = preview; right = metadata + score display; bottom = controls & status.

  • Contextual HUD: Big overlay briefly shows new score after click (e.g., “Score: 4”).

  • Completion dialog: Summary of items to be deleted; irreversible‑action warning.


8) Data Model (SQLite Suggestion)

TABLE media (
  id INTEGER PRIMARY KEY,
  path TEXT UNIQUE NOT NULL,
  rel_path TEXT NOT NULL,
  folder_id INTEGER NOT NULL,
  type TEXT CHECK(type IN ('photo','video')),
  score INTEGER NOT NULL DEFAULT 3 CHECK(score BETWEEN 1 AND 5),
  size_bytes INTEGER,
  mtime_utc TEXT,
  duration_ms INTEGER,
  exif_datetime TEXT,
  hash TEXT,
  FOREIGN KEY(folder_id) REFERENCES folders(id)
);

TABLE folders (
  id INTEGER PRIMARY KEY,
  path TEXT UNIQUE NOT NULL,
  rel_path TEXT NOT NULL,
  total_count INTEGER NOT NULL DEFAULT 0
);

INDEX idx_media_folder ON media(folder_id);
INDEX idx_media_score ON media(score);

9) Scoring & Preview Algorithm (Reference)

function triageLoop(scope):
  queue = all media in scope where score IN (2,3,4)
  while queue not empty:
    item = queue.popNext()
    showPreview(item)
    action = waitForUserClick()
    if action == RIGHT_CLICK: item.score = min(5, item.score + 1)
    if action == LEFT_CLICK:  item.score = max(1, item.score - 1)
    persistScore(item)
    if item.score == 1: moveToToDelete(item)
    if item.score in (2,3,4): queue.enqueue(item) // circle back later
  if all items in scope have score in (1,5):
    showCleanupCompleted()
    if confirm("Delete all files scored 1?"):
      deleteAllScoreOne(scope)
      deleteIndex()
      pruneEmptyFolders(scope.root)

10) File Operations & Safety

  • Moves and deletes must be atomic where possible; fall back with clear error messages.

  • During delete: if setting is “send to OS Trash,” use platform APIs; otherwise perform hard delete after confirmation.

  • Skip/record failures (e.g., permission denied, locked file) and continue; show a completion report.


11) Module Breakdown (Modularization)

  • app/

    • main (bootstrap, window, routing)

    • config (settings load/save)

    • i18n (strings)

  • indexer/

    • scanner (walk filesystem)

    • metadata (EXIF/video probes)

    • store (SQLite/JSON abstraction)

  • preview/

    • image_viewer (render, zoom, pan)

    • video_player (playback, scrub)

  • scoring/

    • controller (event handling, queue policy)

    • state (session state, resume)

  • ui/

    • folder_tree (counts, toggles)

    • status_bar, hud, dialogs

  • ops/

    • mover (to todelete)

    • deleter (trash/hard delete, prune empty dirs)

    • reporter (summary & logs)

Each module ships in a separate source file (or cohesive files) with narrow interfaces to ease updates and feature additions.


12) Acceptance Criteria

  • AC‑1: Selecting a root shows a tree with accurate counts (children included).

  • AC‑2: All files are assigned score 3 on first index.

  • AC‑3: Left/Right clicks adjust score exactly by −1/+1; scores clamp to 1..51..5.

  • AC‑4: Preview loop never shows items already at 1 or 5.

  • AC‑5: Files at score 1 are moved to todelete/ under their original parents.

  • AC‑6: When no items remain at 2/3/4, “clean up completed” appears.

  • AC‑7: On confirmation, all score‑1 files are deleted, the index file is removed, and empty folders are pruned.


13) Future Enhancements (Non‑blocking)

  • Duplicate detection (perceptual hash).

  • Sorting heuristics (by similarity, face detection, blurriness).

  • Multi‑root projects; exportable CSV reports.

  • Undo/redo stack and checkpoints.


14) Technology Options for a Windows App — Comparison

The app is Windows‑first with heavy filesystem work and image/video preview. Below is a pragmatic comparison of common stacks.

14.1 Quick Matrix (higher is better)

Tech Perf. Memory Dev Speed Native Win Integration Cross‑Platform Media Preview Maturity Packaging
.NET WPF (.NET 8) 5 4 4 5 2 5 MSIX/WiX/WinGet
.NET WinUI 3 (Windows App SDK) 5 4 3 5 2 5 MSIX/WinGet
.NET MAUI (Windows target) 4 4 3 4 4 3 MSIX
Avalonia UI (.NET) 4 4 4 3 5 3 MSIX/others
Qt (C++/QML) 5 5 3 4 5 5 MSI/WiX
Flutter (Windows) 4 4 3 3 5 3 MSIX
Electron (JS/TS) 3 2 5 3 5 4 Squirrel/MSIX
Tauri (Rust + WebView) 4 5 3 3 5 3 MSI/MSIX
Python (PySide/PyQt/PyInstaller) 3 3 4 3 5 3 EXE/MSI

Legend: 1–5 relative score. Memory = smaller footprint → higher score.

14.2 Notes & Pros/Cons

.NET WPF

  • Pros: Battle‑tested on Windows, excellent filesystem APIs, stable MVVM ecosystem, great tooling (Visual Studio, Rider). Easy thumbnails via WIC; video via Media Foundation or FFmpeg wrappers. Mature SQLite + EXIF libs.

  • Cons: Windows‑only; legacy XAML patterns but still first‑class.

  • Use when: You want the most stable Windows‑native path with top‑tier performance and full access to Windows codecs.

.NET WinUI 3 (Windows App SDK)

  • Pros: Modern WinUI controls, high‑DPI, fluent styling, future‑facing Windows stack. Deep integration with Windows features.

  • Cons: Some APIs/tooling still evolving; smaller community than WPF. Edge cases with third‑party controls vs WPF.

  • Use when: You want modern Windows look/feel and can accept newer‑stack tradeoffs.

.NET MAUI (Windows)

  • Pros: Same codebase can target Mac/iOS/Android; Windows layer sits on WinUI 3. Good for shared business logic.

  • Cons: Desktop maturity below WPF/WinUI; media preview/video plugins less polished for Windows.

  • Use when: Cross‑platform is a real requirement and you’re already in .NET.

Avalonia UI (.NET)

  • Pros: Cross‑platform WPF‑like XAML; good theming; solid desktop focus.

  • Cons: Fewer off‑the‑shelf media components; you’ll likely embed FFmpeg/LibVLC for video.

  • Use when: You want .NET + cross‑platform with a desktop‑first mindset.

Qt (C++/QML/QtQuick)

  • Pros: High performance, native feel, very mature multimedia (Qt Multimedia) and EXIF/DB tooling, excellent for large libraries.

  • Cons: C++ complexity; commercial licensing for some use cases; larger dev ramp.

  • Use when: You need top performance and true cross‑platform with robust media.

Flutter (Windows)

  • Pros: Single codebase; fast UI iteration; strong 2D GPU rendering.

  • Cons: Desktop plugins for advanced media/filesystem are still catching up vs native.

  • Use when: You have Flutter expertise and want cross‑platform UIs.

Electron (JS/TS)

  • Pros: Web skills, rapid UI dev, rich ecosystem. Chromium can preview many image/video formats; Node for filesystem.

  • Cons: Larger memory footprint; packaging/signing friction; native OS feature gaps.

  • Use when: Team is web‑heavy and footprint isn’t critical.

Tauri (Rust + WebView)

  • Pros: Tiny binaries and memory; secure; Rust for native ops; modern WebView front‑end.

  • Cons: Media playback often requires native plugins/FFmpeg; fewer production examples for heavy media.

  • Use when: You want Electron‑style dev with an order‑of‑magnitude smaller footprint and can handle native media plumbing.

Python (PySide/PyQt)

  • Pros: Quick prototyping; rich libraries; Qt underneath.

  • Cons: Packaging size, startup time, and distribution quirks; perf below C#/C++.

  • Use when: You need rapid iteration and internal tooling; less ideal for mass distribution.

14.3 Media‑Specific Considerations for This App

  • Thumbnailing & EXIF: WIC + MetadataExtractor (.NET) or Qt’s QImageReader + Exiv2/QtEXIF are robust.

  • Video preview: Windows Media Foundation (native/.NET wrappers) or FFmpeg/LibVLC for broad codec coverage. Browser engines (Electron/Flutter WebView) support common codecs but may choke on edge formats.

  • Large library indexing: Prefer SQLite (system.data.sqlite/.NET; QtSql/SQLite; rusqlite for Rust). Use incremental scans and file hashing on demand.

14.4 Packaging & Updates

  • Windows‑native: MSIX (WinGet), or MSI/WiX; code‑signing cert required.

  • Web stacks: Electron → Squirrel/MSIX; Tauri → MSI/MSIX. Auto‑update channel recommended but must be code‑signed.

14.5 Recommendation

For Windows‑only and fastest path to a polished tool: .NET (WPF or WinUI 3).

  • Pick WPF if you want maximum stability and ecosystem breadth.

  • Pick WinUI 3 if you want a modern Fluent look and don’t mind a newer stack.

If small footprint and you’re comfortable binding native media: Tauri (Rust backend with FFmpeg/LibVLC + WebView UI).

If cross‑platform with strong media and you’re OK with C++: Qt (C++/QML).

14.6 Suggested Starter Kits

WPF (.NET 8)

  • Imaging: WIC via BitmapImage; EXIF: MetadataExtractor

  • Video: Media Foundation (MediaElement alternatives) or FFmpeg.AutoGen

  • DB: System.Data.SQLite

  • Packaging: MSIX + WinGet

WinUI 3

  • UI: Windows App SDK templates; MediaPlayerElement for video

  • Same EXIF/DB approach as WPF; MSIX packaging

Tauri

  • Backend: Rust (filesystem scan, SQLite, FFmpeg/LibVLC bindings)

  • Frontend: React/Svelte/Vue in WebView; invoke via Tauri commands

  • Installer: Tauri bundler → MSI/MSIX

Qt (C++/QML)

  • Media: QMediaPlayer / QVideoSink, thumbnails with QImageReader

  • EXIF: Exiv2; DB: QtSql + SQLite

  • Installer: WiX/MSI

2025/09/19

紅光療法(Red Light Therapy)的相關科學實驗證據整理

 ### 紅光療法(Red Light Therapy)的相關科學實驗證據整理


紅光療法(也稱光生物調節或低水平激光療法)使用紅光或近紅外光(波長約600-1000 nm)來刺激細胞功能,主要透過影響線粒體中的細胞色素c氧化酶來增加ATP產生,從而促進組織修復和生理調節。以下根據文獻中的隨機對照試驗(RCT)、meta分析和系統回顧,整理其對運動恢復、皮膚健康、抗炎作用及睡眠節律的證據。證據等級以GRADE系統評估(高、中、低),並聚焦人類研究。注意:雖然多數研究顯示正面效果,但樣本量有限,且需更多大型長期試驗確認。


#### 1. 運動後恢復(Boost recovery after workouts)

紅光療法可預先照射(pre-conditioning)或事後應用,減少肌肉損傷、氧化壓力,並加速恢復。機制包括增加ATP、減少乳酸累積及促進血液循環。


| 研究類型 | 關鍵發現 | 證據等級 | 參考 |

|----------|----------|----------|------|

| Meta分析(2015,巴西聖保羅大學,21項RCT) | 運動前紅光照射顯著改善疲勞時間(time-to-exhaustion)、重複次數,並加速恢復;效果大小中等(ES=0.6-1.0)。 | 中等 |  |

| 系統回顧(2016,Physiopedia) | 紅光增加肌肉質量、減少炎症及氧化壓力;預照3-5分鐘,效果持續3-6小時。 | 中等 |  |

| RCT(2015,近紅外光,n=20) | 劇烈阻力訓練後,紅光組力量損失減少50%,炎症標記(如CK酶)降低。 | 中等 |  |

| 回顧(2025,ACE Fitness) | 優於冷療(cryotherapy),但家用設備劑量不足研究級別。 | 低 |  |


**總結**:證據支持紅光作為運動恢復輔助,特別在預防肌肉疲勞方面,但最佳劑量(4-10 J/cm²)需個別化。


#### 2. 支持健康皮膚(Support healthy skin)

紅光促進膠原合成、纖維母細胞活性,改善皺紋、疤痕及彈性。常用於抗老化及傷口癒合。


| 研究類型 | 關鍵發現 | 證據等級 | 參考 |

|----------|----------|----------|------|

| RCT(2014,n=136) | 紅/近紅外光治療12週,細紋減少31%、皮膚粗糙度改善20%、膠原密度增加(超音波測量)。患者滿意度>90%。 | 高 |  |

| 系統回顧(2024,WebMD,11項研究) | 改善皺紋、痤瘡及疤痕;頭髮厚度增加(雄性禿患者)。 | 中等 |  |

| 回顧(2025,UCLA Health,3個月追蹤) | 面罩治療逆轉老化跡象(如紅腫、色素沉澱),效果持續1個月。 | 中等 |  |

| Meta分析(2023,Cleveland Clinic) | 減少紅腫及痤瘡,但長期安全需更多數據。 | 低 |  |


**總結**:強證據支持皮膚再juvenation,特別在臨床環境;家用LED效果較弱,建議結合醫師指導。


#### 3. 緩解炎症(Calm inflammation)

紅光抑制促炎細胞因子(如TNF-α、IL-6),促進抗炎介質(如IL-10),適用於關節炎及傷口炎症。


| 研究類型 | 關鍵發現 | 證據等級 | 參考 |

|----------|----------|----------|------|

| 系統回顧(2017,PMC,34項研究) | 紅光減少炎症介質,機制涉及線粒體及鈣離子通道;適用於關節炎及神經痛。 | 高 |  |

| Meta分析(2024,WebMD,11項RCT) | 疼痛及晨僵改善(ES=-0.5),特別風濕性關節炎;肌腱炎功能提升。 | 中等 |  |

| RCT(2025,UCLA,文獻回顧) | 慢性/急性疼痛炎症減少,優於安慰劑。 | 中等 |  |

| 回顧(2025,Stanford) | 組織炎症降低,但劑量依賴(>5000 lx最佳)。 | 低 |  |


**總結**:可靠證據顯示抗炎效果,作為非藥物輔助;癌症相關炎症(如化療後)也有初步支持。


#### 4. 改善睡眠節律(Help your body find a better sleep rhythm)

紅光對褪黑激素影響小(不像藍光抑制),可能透過增加血清褪黑激素及減少警覺性改善睡眠。證據較弱,多為小型研究。


| 研究類型 | 關鍵發現 | 證據等級 | 參考 |

|----------|----------|----------|------|

| RCT(2012,中國女籃球員,n=20,14天) | 每晚30分鐘紅光,匹茲堡睡眠指數(PSQI)改善、褪黑激素上升、總睡眠時間增加(P<0.05)。 | 中等 |  |

| RCT(2023,n=40,健康/失眠者) | 紅光增加主觀警覺但不影響睡眠;黑環境結合紅光改善入睡延遲及連續性。 | 中等 |  |

| 系統回顧(2023,meta分析,40項研究) | 光療法推進延遲睡眠時相(ES=-0.34),總睡眠時間增加;紅光避免藍光干擾。 | 低 |  |

| 回顧(2023,CNN) | 紅光不干擾晝夜節律,可能間接改善(避免藍光);但無強證據支持直接「重置」節律。 | 低 |  |


**總結**:初步證據顯示紅光可輔助睡眠質量(尤其是運動員),但不如亮光療法(bright light)對晝夜節律重置有效;晚上避免藍光更關鍵。


**整體注意事項**:紅光療法安全(無明顯副作用,如紅腫罕見),FDA批准多項家用設備,但效果依波長、劑量及持續時間而異。建議諮詢醫師,特別有光敏性疾病者。未來研究需聚焦長期效果及標準化協議。

Mac App - Photo Clean up


Product Requirements Document (PRD)

1) Summary

A macOS desktop app for rapid photo triage. Users browse a folder tree (parent/children), enter Cleanup Mode to preview photos one-by-one, and use swipe gestures:

  • Swipe Left → move photo to a staging folder named “ToDelete”.

  • Swipe Right → keep photo, advance to next.
    Keyboard shortcuts mirror gestures. Users can later review or permanently delete staged photos.

2) Goals & Non-Goals

Goals

  • Fast, low-friction review of photos in any filesystem folder.

  • Reliable, reversible “stage for deletion” workflow.

  • Smooth navigation among parent and child folders.

Non-Goals

  • Editing photos (crop, color, etc.).

  • Managing Photos app library (this release is filesystem-only).

  • Cloud sync logic (beyond what Finder/OS already does).

3) Assumptions

  • Sandboxed app; user grants access via folder picker. Use security-scoped bookmarks to persist access.

  • Photos are regular files in the filesystem (JPEG, PNG, HEIC, GIF, TIFF, RAW variants).

  • “ToDelete” is a sibling of the current folder by default (configurable).

4) User Stories

  • US-01: As a user, I can select a root folder to review.

  • US-02: I can navigate up to parent or down into children quickly.

  • US-03: I can enter Cleanup Mode and preview photos full-screen or in a focused pane.

  • US-04: Swiping left sends the current photo to “ToDelete” and shows the next photo.

  • US-05: Swiping right skips the photo and shows the next photo.

  • US-06: I can use keyboard shortcuts instead of gestures.

  • US-07: I can undo the last action(s).

  • US-08: I can review the “ToDelete” folder and restore items.

  • US-09: I can permanently delete staged items (to macOS Trash) with a confirmation.

  • US-10: I can configure where “ToDelete” is created and how images are sorted.

5) UX & Interaction Model

Navigation

  • Left sidebar: folder tree (current folder highlighted).

  • Breadcrumb at top for quick jump to ancestors.

  • Toggle to switch among Parent / Current / Children (or a three-segment control).

Cleanup Mode

  • Enters a focused viewer.

  • HUD: file name, index (e.g., 14/238), resolution, creation date.

  • Controls: Exit Cleanup, Undo, “Open in Finder”, “Reveal in Finder”, “View in ToDelete”.

  • Gestures:

    • Trackpad swipe left → stage to delete, auto-advance.

    • Trackpad swipe right → keep, advance.

  • Shortcuts:

    • ← / D = Stage to delete.

    • → / K = Keep/Next.

    • U / ⌘Z = Undo.

    • Space = Toggle quick zoom.

    • Esc = Exit Cleanup Mode.

Staging

  • On first stage action, app creates ToDelete if missing.

  • Name collisions resolved by appending “ (1)”, “ (2)”, etc.

  • Across volumes: perform copy+delete (with progress), preserving metadata.

Settings

  • Sort order: Date created | Date modified | Name | Size (asc/desc).

  • Include subfolders in Cleanup Mode: On/Off.

  • “ToDelete” location: sibling folder (default) | fixed app-level staging folder | custom.

  • Preview quality: Auto (default) | High | Low.

  • Confirm permanent deletion: On (default) | Off.

  • Skip files larger than N MB without warning: On/Off.

6) Functional Requirements

  • FR-01 Folder Access: User chooses one or more root folders; app stores security-scoped bookmarks.

  • FR-02 Folder Navigation: Display parent and children; jumping between them must be O(1) visible action with lazy loading of large trees.

  • FR-03 Media Discovery: Filter visible items to supported image types (configurable).

  • FR-04 Sorting & Filtering: Apply user’s sort preferences consistently across navigation and Cleanup Mode.

  • FR-05 Preview Engine: Generate fast thumbnails and quick-look previews (respect EXIF orientation). Preload next/previous image.

  • FR-06 Cleanup Mode State: Linear traversal of the filtered set; resume where left off per folder.

  • FR-07 Stage Left (Delete): Move file to “ToDelete” (atomic when possible). Advance immediately. Log action to an in-memory and on-disk session history for undo.

  • FR-08 Skip Right (Keep): Advance without moving file.

  • FR-09 Undo/Redo: Undo last N actions in session; supports restoring a moved file to its original path (or warn if path unavailable).

  • FR-10 “ToDelete” Review: Dedicated view to browse, restore, or permanently delete items.

  • FR-11 Permanent Delete: Send to macOS Trash (not immediate unlink) with count summary and confirmation dialog.

  • FR-12 Cross-Volume Handling: If “ToDelete” is on a different volume, copy+delete with progress UI; on failure, rollback.

  • FR-13 Conflicts: If a same-name file exists in “ToDelete”, auto-rename deterministically.

  • FR-14 Persistence: Store settings and per-folder progress in user defaults / app support.

  • FR-15 Accessibility: Full keyboard operation, VoiceOver labels, large hit-targets.

  • FR-16 Localization-Ready: Strings externalized.

  • FR-17 Telemetry (optional toggle): Count of staged/kept per session (no file names/paths).

  • FR-18 Error Handling: Friendly toasts for permission errors, missing files, iCloud download in progress, etc.

  • FR-19 Performance:

    • First preview < 300 ms p95 after assets indexed.

    • Next/prev transition < 120 ms p95.

    • Memory footprint < 500 MB when paging high-res photos (release decoded bitmaps).

7) Non-Functional Requirements

  • NFR-01 Platform: Current and last two major macOS versions. Universal build (Apple Silicon + Intel if required).

  • NFR-02 Privacy: All processing local; no network I/O by default.

  • NFR-03 Reliability: No data loss on interruption; operations are transactional where feasible.

  • NFR-04 Security: Respect sandbox; only user-granted folders accessible.

  • NFR-05 Observability: Lightweight logs (rotated), crash reports opt-in.

8) Data & Technical Notes

  • Use security-scoped bookmarks for persistent folder access.

  • Use file coordination for moves; preserve EXIF and extended attributes.

  • Use thumbnail APIs / CGImageSource for efficient previews; cache adjacent images.

  • Keep a session action log: {timestamp, originalPath, stagedPath, actionType} to power undo/redo and recovery after crash.

9) Out of Scope (v1)

  • Videos, Live Photos, and RAW sidecar pairing rules (treat as files for now).

  • Duplicate detection, fuzzy grouping, or AI.


Test Plan

A) Strategy

  • Unit Tests: file operations, name collision resolver, sort, state machine.

  • Integration Tests: security-scoped bookmark flow, cross-volume move, Trash deletion, EXIF orientation.

  • UI Tests (XCUITest): navigation, Cleanup Mode gestures/shortcuts, undo/redo.

  • Performance Tests: preview latency & memory under load.

  • Accessibility Tests: keyboard-only flows, VoiceOver labels.

  • Manual Exploratory: weird filenames, iCloud placeholders, external drives.

B) Test Environment

  • macOS latest and two prior majors; Apple Silicon primary.

  • File systems: APFS local; APFS external; network share (read/write).

  • Folder sets:

    • Small (≤100 photos), Medium (~5k), Large (≥50k, mixed formats).

    • Include HEIC, large JPEG (>25 MB), PNG, TIFF, common RAWs (CR2/NEF/ARW/DNG).

C) Acceptance Criteria (sample, traceable to FR-IDs)

  • AC-01 (FR-07): Swiping left moves file into “ToDelete” within 500 ms and advances to the next item.

  • AC-02 (FR-09): ⌘Z restores the last staged file to its original path even after folder change.

  • AC-03 (FR-11): “Delete staged” sends all items to macOS Trash and reduces “ToDelete” count to 0.

  • AC-04 (FR-05): Portrait photos show correctly oriented previews.

  • AC-05 (FR-02): Parent/children toggle switches views in ≤150 ms and preserves scroll and selection.

  • AC-06 (FR-12): Cross-volume stage shows progress and leaves no partials on failure.

  • AC-07 (FR-15): All primary actions are reachable by keyboard and announced by VoiceOver.

D) Core Test Cases

ID Precondition Steps Expected Result
TC-01 App fresh install Launch → Choose Folder Permission prompt shown; folder appears in sidebar; bookmark persisted.
TC-02 Folder with 500 JPEGs Enter Cleanup Mode → Swipe Right 5× Index increments; no files moved; HUD updates (6/500).
TC-03 Same as TC-02 Swipe Left 1× Current file appears in ToDelete; viewer advances; toast “Moved to ToDelete”.
TC-04 After TC-03 Press ⌘Z File restored to original path; index decrements; toast “Undo move”.
TC-05 “ToDelete” already has a file named IMG_0001.jpg Stage another IMG_0001.jpg New file saved as IMG_0001 (1).jpg (or next available).
TC-06 Large HEIC (30MB) Enter Cleanup → View file Preview < 300 ms p95 after first load; memory does not exceed cap.
TC-07 Mixed orientations Browse 10 photos All previews respect EXIF orientation (no sideways images).
TC-08 External APFS drive as “ToDelete” target Stage 50 files Progress UI shown; files appear on external; originals removed from source.
TC-09 iCloud Drive folder with placeholders Stage a placeholder App prompts/waits for download; on success, move proceeds; on failure, user gets actionable error.
TC-10 No write permission to target Stage file Clear error; action is rolled back; viewer remains consistent.
TC-11 Very long filename / unicode Stage & Undo Name preserved; no encoding issues; undo restores exact name.
TC-12 Settings: Sort by Date Created desc Enter Cleanup Order matches Finder’s equivalent sort; consistent across sessions.
TC-13 “Include subfolders” enabled Enter Cleanup on parent Traversal includes children; counter reflects combined count.
TC-14 ToDelete contains 100 items Click “Delete staged” System confirmation → items moved to Trash; counts zero; undo is not available for permanent delete.
TC-15 VoiceOver on Navigate & stage item All controls have labels; VoiceOver announces actions and counts.
TC-16 Keyboard-only Use ← / → / U keys Actions work without trackpad; focus ring visible.
TC-17 App crash simulated during move Relaunch app No orphan temp files; session log replays safely; user notified if any items could not be restored.
TC-18 Very large library (50k) Open folder tree, enter Cleanup UI remains responsive; lazy loading verified; no freezes >100 ms on main thread.
TC-19 Two windows Stage in Window A, navigate in Window B State is isolated per window; “ToDelete” reflects global filesystem state.
TC-20 Different volume for “ToDelete” Stage RAW + Sidecar Both files moved; pairing preserved if enabled; otherwise each handled independently.

E) Performance Tests

  • PT-01 Preview Latency: Measure time to first frame and next/prev transitions across formats; must meet FR-19 thresholds.

  • PT-02 Memory: Scroll 1,000 photos; verify decoded image cache evicts correctly; memory plateau < 500 MB.

  • PT-03 Bulk Stage: Stage 2,000 photos cross-volume; mean throughput and no UI jank.

F) Accessibility Tests

  • Full keyboard path for: select folder, enter Cleanup, stage, undo, open ToDelete, delete staged.

  • VoiceOver reads: file name, index, action result.

  • Contrast & hit size meet macOS HIG.

G) Edge Cases

  • Files disappearing mid-session (external change): app skips with notice.

  • Read-only media (SD card switch): error & guidance.

  • Path length / unicode normalization differences across volumes.

  • iCloud items not downloaded; network offline.

  • Timezone/EXIF weirdness; files with creation date missing (fallback to modified date).

H) Regression Checklist (per release)

  • Bookmark restore on relaunch.

  • Gesture recognizers coexist with trackpad system gestures.

  • Trash API still reachable; deletion confirmation string localized.

I) Traceability (example)

  • FR-07TC-03, TC-04, TC-05, PT-03

  • FR-11TC-14

  • FR-15TC-15, TC-16

  • FR-19PT-01, PT-02



2025/09/18

電子為主、但很兇、帶點工業味

 如果你喜歡 Prodigy 那種「電子為主、但很兇、帶點工業味」的聲音,嚴格說它偏向 Big Beat/電子搖滾,不算傳統金屬。不過「金屬+電子」這條線上,常見有幾個分支可以一路聽過去:

1) 工業金屬(Industrial Metal)

特色:厚重的金屬吉他riff鼓機/采樣/合成器、機械感節奏。代表團常見:Rammstein、Fear Factory、KMFDM、Godflesh、Static-X、Nine Inch Nails(更靠工業搖滾)。這條分支是金屬與工業/電子結合的經典答案。(Wikipedia)
入門歌:Rammstein〈Du Hast〉、Fear Factory〈Replica〉、Static-X〈Push It〉、Nine Inch Nails〈Head Like a Hole〉

2) Electronicore(Metalcore+EDM)

特色:金屬核的吼腔與breakdown,混進trance/dubstep/電子旋律。推:Enter Shikari(英)、Crossfaith(日)、Electric Callboy(德,前 Eskimo Callboy)、The Browning、I See Stars、Fear, and Loathing in Las Vegas(日)。如果你要「電子感更濃+副歌洗腦」,這條很對味。(Wikipedia)
入門歌:Enter Shikari〈Sorry You’re Not a Winner〉、Crossfaith〈Monolith〉、Electric Callboy〈Hypa Hypa〉、The Browning〈Gravedigger〉

3) Digital Hardcore(電硬核)

特色:硬核龐克的怒火鼓打貝斯/Breakbeat/Techno,速度快、攻擊性強,常帶政治/社會題材。Atari Teenage Riot是開山角色;如果你喜歡 Prodigy 的狠勁、節奏再更狂,這支派很合。(Wikipedia)
入門歌:Atari Teenage Riot〈Start the Riot!〉、〈Speed〉

4) 另類/實驗的「電子×金屬」混種

  • The Algorithm:把djent/前衛金屬IDM/舞曲編曲拼起來,技術感爆棚。(Wikipedia)

  • Celldweller(Klayton)電子搖滾×工業金屬×Nu metal 的影片配樂常客。(Wikipedia)

  • Igorrrbreakcore+極端金屬+巴洛克的怪才混血。(Wikipedia)

  • Author & Punisher:一人工業/毀滅金屬,用自製機械控制器演出,質地超冷硬。(Wikipedia)

與 Prodigy 氣場相近(但不一定是金屬)

The Prodigy 本尊屬 Big Beat/電子搖滾/Electropunk,是 90s 電子樂代表;如果你想找「帶搖滾/金屬能量的電子」鄰居,可試 The Chemical Brothers、The Crystal Method,或Pendulum(鼓打貝斯×電子搖滾,後期有些金屬元素)。(Wikipedia)
入門歌:The Prodigy〈Firestarter〉、Pendulum〈Witchcraft〉/〈Watercolour〉


快速歌單(先感受各分支的味道)

  • 工業金屬:Rammstein〈Du Hast〉/Fear Factory〈Replica〉/Static-X〈Push It〉

  • Electronicore:Enter Shikari〈Sorry You’re Not a Winner〉/Crossfaith〈Monolith〉/Electric Callboy〈We Got The Moves〉

  • Digital Hardcore:Atari Teenage Riot〈Start the Riot!〉

  • 實驗混種:The Algorithm〈Trojans〉/Celldweller〈Switchback〉/Igorrr〈Very Noise〉/Author & Punisher〈Drone Carrying Dread〉

  • Prodigy 同溫層:The Prodigy〈Breathe〉/Pendulum〈Watercolour〉

路線推薦(由易入門→更兇)

工業搖滾/工業金屬
3TEETH、HEALTH、Ministry、KMFDM、Fear Factory(特別是 Remanufacture 時期)、Rammstein、Godflesh、Pitchshifter、Stabbing Westward、Filter

Rocktronica/大拍延伸(有吉他、有推力)
The Qemists、The Glitch Mob、Overseer、Junkie XL、Propellerheads、Hybrid(較電影感)

D&B × 金屬/搖滾能量
Noisia、Black Sun Empire、The Upbeats、Spor(Feed Me)、Chase & Status(早期帶狠勁)、Pendulum(你已懂)、The Qemists(再強推一次)

Digital Hardcore/電硬核(最像怒吼版電子)
Atari Teenage Riot、The Mad Capsule Markets、Mindless Self Indulgence(更偏電龐)

Darksynth/合成波金屬感
Carpenter Brut、Perturbator、GOST、Dance With the Dead(旋律掛但有riff)

實驗×金屬/前衛混種
The Algorithm(djent×IDM)、Igorrr(breakcore×極端金屬)、Author & Punisher(機械冷硬)、Amon Tobin(重節奏聲響設計)

先聽這 20 首(火力展示)

  • 3TEETH – Atrophy

  • HEALTH – STONEFIST

  • Ministry – N.W.O.

  • KMFDM – Megalomaniac

  • Fear Factory – Linchpin(或整張 Remanufacture 的混音)

  • Rammstein – Sonne

  • Godflesh – Crush My Soul

  • Pitchshifter – Genius

  • Stabbing Westward – Shame

  • The Qemists – Stompbox

  • Noisia – Machine Gun

  • Black Sun Empire – Arrakis

  • Overseer – Supermoves

  • Atari Teenage Riot – Speed

  • The Mad Capsule Markets – Pulse

  • Author & Punisher – Nihil Strength

  • Carpenter Brut – Turbo Killer

  • The Algorithm – Trojans

依你的喜好再加幾個「同溫層」延伸

  • 喜歡 Celldweller → Blue Stahli、Scandroid(同一派系的狠勁+旋律)

  • 喜歡 Nine Inch Nails → How to Destroy Angels、Stabbing Westward、Filter、Statiс-X

  • 喜歡 Chemical Brothers/Crystal Method → The Prodigy(硬電子)、Junkie XL、Propellerheads、Overseer

  • 喜歡 Pendulum/Photek → Noisia、Black Sun Empire、Spor、The Upbeats(更重、更暗的 D&B)

  • 喜歡 Squarepusher/Aphex Twin/Björk → Amon Tobin、Clark、Igorrr(更瘋的切拍)、Arca(Björk 合作者,偏實驗)

俄羅斯/烏克蘭/白俄羅斯

  • Illidiance(俄)— cyber/industrial metal,節奏機械、旋律科幻感。Wikipedia

  • Слот/Slot(俄)— nu-metal × 電子搖滾,俄搖圈的長青混種。Wikipedia

  • IC3PEAK(俄)— 暗黑電子/witch-house 雙人組,冷感合成器+強烈視覺。先聽〈Смерти Больше Нет〉。Wikipedia

  • Shortparis(俄)— 工業感濃的實驗舞曲/後龐克,現場超狠。Wikipedia

  • The Hardkiss(烏)— 電子搖滾/流行金屬嗓線,hook 很洗腦。Wikipedia

  • Molchat Doma(白俄)— 冷潮/暗潮合成器,低音線中毒。Wikipedia

  • Teddy Killerz(俄/烏)— neurofunk d’n’b 三人組,能量感接近 Pendulum 的硬派一面。Wikipedia

  • Gydra(俄)— 俄系 neurofunk 代表,聲音設計超殺。eatbrain.net

中東(含土耳其、以色列、伊朗、敘利亞…)

  • Infected Mushroom(以色列)— psytrance/electronica 旗手,常把搖滾與吉他融進猛爆合成器。Wikipedia

  • Orphaned Land(以色列)— 「東方金屬」先驅,把中東音階與前衛金屬融合。Wikipedia

  • maNga(土耳其)— nu-metal × electronic rock,拿過 MTV 獎、唱過歐歌。從〈We Could Be The Same〉入坑。Wikipedia+1

  • She Past Away(土耳其)— 暗潮/後龐克,80s 合成器質地,很適合喜歡 Björk 黑暗面的人。Wikipedia

  • Tiny Fingers(以色列)— 器樂後搖 × live electronics,dubstep/數學搖滾元素混搭。Pelagic Records

  • Sote(伊朗)— 實驗電子,常把波斯樂器/音階與前沿音色結合。Ableton

  • Omar Souleyman(敘利亞)— dabke-techno 王者,民謠旋律+舞池級合成器。Wikipedia

  • Confess(伊朗→挪威)— groove/nu-metal,編制含 DJ/sampler,能量炸裂。Wikipedia

東歐(波蘭/斯洛維尼亞/克羅埃西亞/捷克…)

  • Laibach(斯洛維尼亞)— 工業/前衛傳奇,硬朗節拍與政治美學;聽《Opus Dei》或〈Tanz mit Laibach〉。Wikipedia+1

  • Thy Disease(波蘭)— 工業金屬,鍵盤與程序化節拍押著密集吉他。Wikipedia

  • Manntra(克羅埃西亞)— 工業 × 民謠金屬,旋律民族風很洗腦。Wikipedia

  • Vanessa(捷克)— 自 1989 年起的 electro-industrial/EBM 老團,聲音灰暗帶侵略性。Discogs

一條「入門試聽」路線(歌單順著播就好)

Infected Mushroom〈Becoming Insane〉 → IC3PEAK〈Смерти Больше Нет〉 → Laibach〈Tanz mit Laibach〉 → She Past Away〈Kasvetli Kutlama〉 → maNga〈We Could Be The Same〉 → Orphaned Land〈Sapari〉 → Molchat Doma〈Судно (Sudno)〉 → Teddy Killerz〈Teddynator〉 → Gydra(任選單曲)→ Thy Disease〈Slave State〉 → Omar Souleyman〈Wenu Wenu〉


電子團 × 客座MC(最貼近 Big Beat / breaks 氣場)

  • The Chemical Brothers — 〈Galvanize〉(feat. Q-Tip), 〈Go〉(feat. Q-Tip)

  • The Crystal Method — 〈Name of the Game〉(feat. Ryu from Styles of Beyond)

  • The Prodigy — 〈Diesel Power〉(feat. Kool Keith)

  • Leftfield — 〈Afrika Shox〉(feat. Afrika Bambaataa)

  • UNKLE — 〈Guns Blazing〉(feat. Kool G Rap)(他們超愛找 MC:Mobb Deep、Roots Manuva 等)

樂團/計畫型團體(大量 feat. MC 是常態)

  • Gorillaz — 〈Clint Eastwood〉(feat. Del), 〈November Has Come〉(feat. MF DOOM), 〈Dirty Harry〉(feat. Bootie Brown)

  • Handsome Boy Modeling School(Prince Paul+Dan the Automator)— 〈Rock n’ Roll (Could Never Hip Hop Like This) Pt.2〉(豪華 MC 大亂鬥)

  • The Avalanches — 〈Because I’m Me〉(feat. Camp Lo), 〈The Noisy Eater〉(feat. Biz Markie)

  • Chinese Man — 〈Get Up〉(feat. ASM, Taiwan MC), 〈Miss Chang〉(feat. Taiwan MC, Taïwan MC)

Trip-hop/UK Bass/重節奏製作人(酷愛請 MC)

  • DJ Shadow — 〈Rocket Fuel〉(feat. De La Soul), 〈Systematic〉(feat. Nas)

  • Coldcut — 〈True Skool〉(feat. Roots Manuva)

  • DJ Krush — 〈Meiso〉(feat. Black Thought & Malik B), 〈Only the Strong Survive〉(feat. C.L. Smooth)

  • The Bug — 〈Skeng〉(feat. Killa P & Flowdan)(更偏 grime/dancehall 的狠勁)

DnB/Breaks × MC(有你喜歡的能量牆)

  • The Qemists — 〈Dem Na Like Me〉(feat. Wiley)

  • Pendulum(加碼現場版) — 找 MC Verse 同台,錄音室版可聽 〈Tarantula〉(feat. $pyda, Tenor Fly)

實驗/前衛向(偏你 Aphex Twin/Squarepusher 的那面)

  • Two Fingers(Amon Tobin 計畫)— 〈That Girl〉(feat. Sway)

  • Prefuse 73(常與地下 MC 合作;前衛切拍)— 可從合輯/合作曲找 Busdriver/Aesop Rock 相關軌


想直接開聽?給你一條 12 首「先感受」清單

Galvanize → Name of the Game → Diesel Power → Afrika Shox → Guns Blazing → Clint Eastwood → November Has Come → Because I’m Me → True Skool → Meiso → Skeng → Dem Na Like Me


俄羅斯/烏克蘭/白俄

  • Illidiance(俄)— cyber/industrial metal,機械感+旋律掛。Wikipedia

  • IC3PEAK(俄)— 暗黑電子/witch-house 雙人組(近年也混嘻哈切拍)。Wikipedia+1

  • Shortparis(俄)— 工業質地的實驗舞曲/後龐克。Wikipedia

  • The HARDKISS(烏)— 電子搖滾×大副歌,舞台能量滿。Wikipedia

  • Molchat Doma(白俄)— 後龐克/dark-wave 合成器,冷感低頻線條很抓耳。Wikipedia+1

  • Teddy Killerz(俄/烏)— 硬派 D’n’B/neurofunk(三人組)。Wikipedia

  • Gydra(俄)— 俄圈代表性 neurofunk 雙人組。eatbrain.net

  • Sunchase(烏)— 老牌烏克蘭 D’n’B/電子製作人。Resident Advisor+1

中東(含土耳其/以色列/伊朗/敘利亞…)

  • Infected Mushroom(以)— psytrance × 電子搖滾,聲響層次狂。Wikipedia+1

  • Orphaned Land(以)— 「東方金屬」先驅,把中東音階與前衛金屬融合。Wikipedia+1

  • maNga(土)— nu-metal/electronic rock,歐歌舞台也拿過亞軍。Wikipedia+1

  • She Past Away(土)— 暗潮/後龐克,電子拍超冷冽。Wikipedia

  • Tiny Fingers(以)— live electronics × 後搖/dubstep 手感演奏。Pelagic Records

  • Sote(伊朗)— 德黑蘭的實驗電子旗手,聲音設計取向。sotesound.com+1

  • Omar Souleyman(敘)— 把傳統 dabke 舞曲做成合成器/節拍的舞池殺器。Wikipedia+1

  • Niyaz / Azam Ali(伊朗系)— 蘇非詩歌×電子的迷幻融合。Wikipedia+1

  • A-WA(以)— 葉門猶太民謠×hip-hop/電子節拍的三姊妹。Wikipedia+1

  • Noga Erez(以)— 電子×說唱的利落製作(你喜歡的 MC feature 氣質這裡很多)。Wikipedia

東歐(斯洛維尼亞/波蘭/克羅埃西亞/捷克…)

  • Laibach(斯)— 工業/前衛傳奇,冷峻機械節拍+概念美學。Wikipedia+1

  • Thy Disease(波)— 工業金屬,鍵盤與程序化節拍很重。Wikipedia+1

  • Manntra(克)— 工業×民謠金屬,旋律很洗腦。Wikipedia

  • Vanessa(捷)— 老牌 electro-industrial / EBM。Discogs+1

  • Dubioza Kolektiv(波黑)— rap-rock × 巴爾幹節奏,現場超嗨(適合你想要的「找 MC 合作」氛圍)。Wikipedia+1

  • Forbidden Society(捷)— 硬派 D’n’B/廠牌主理,聲音設計兇狠。forbiddensocietyrecordings.com+1


怎麼入坑(依你口味從「電子先行→更金屬」)

  1. Infected MushroomShe Past AwayMolchat Doma(電子/冷潮面)Wikipedia+2Wikipedia+2

  2. Dubioza KolektivNoga Erez(MC/說唱能量面)Wikipedia+1

  3. IC3PEAKShortparisLaibach(黑暗工業/實驗面)Wikipedia+2Wikipedia+2

  4. Teddy Killerz/Gydra/Sunchase(D’n’B 硬派→經典流)Wikipedia+2eatbrain.net+2


俄羅斯

  • DJ Vadim(俄羅斯出生、英國發展)— 老派抽樣+downtempo/trip-hop 氛圍、專輯常大量找 MC 客串(如 Abstract Rude、Skinnyman、Big Red 等)。入門:The Soundcatcher(2007)裡的 MC 曲目如「Ballistic Affairs」「Soundcatchers」。 DJ Vadim+2rapreviews.com+2

  • IC3PEAK(雙人電子/實驗嘻哈)— 常與說唱歌手合作(如 Husky、ZillaKami、Ghostemane;2022 Kiss of Death 還與 Oliver Sykes、Grimes 合作),黑暗工業與陷阱質地很貼近你喜歡的狠勁。入門:專輯 До свидания(2020)與 Kiss of Death(2022)。 Wikipedia+1

  • Kunteynir / Lapti(莫斯科地下傳奇)— 由製作人 Lapti 打底、MC 輪流上麥的地下流派,粗糙卻極具氣味;可追一下 Pitchfork 對莫斯科場景的長文。 Pitchfork

中東(含黎凡特/以色列/巴勒斯坦)

  • Balkan Beat Box(以色列)— 地中海×電子×嘻哈節奏,長年與各路來賓合作;2025 還發了和美國饒舌歌手 Trinidad James 合作的〈African Coast〉。入門:經典「Hermetico」與新單曲〈African Coast〉。 Wikipedia+2Wikipedia+2

  • 47SOUL(巴勒斯坦/約旦)— 「Shamstep」開創者,把 dabke 舞步節奏與 hip-hop、人聲吶喊混搭,現場常與 MC/來賓互動。推:Shamstep(2015)。 Wikipedia+1

  • Ramallah Underground/Muqata’a、Asifeh(巴勒斯坦)— 以製作人身份組織 feat 文化的鼻祖級 collective,結合 trip-hop/downtempo 與阿拉伯音素;延伸可聽 Muqata’a 的個人作品與他帶出的新生代(如 Julmud)。 Wikipedia+2Pitchfork+2

  • Hadag Nahash(以色列)— 樂團式 hip-hop,長年與本地歌手/MC 合作,社會議題重。入門:精選歌單或與客座歌手的合作曲。 Jewish Telegraphic Agency+1

東歐(中東歐/巴爾幹)

  • DJ Wich(捷克)— 超典型「製作人+MC 大拼盤」模式;專輯 The Golden Touch(2008)一次網羅 Talib Kweli、Raekwon、M.O.P.、Kurupt、Royce 5’9″、Slum Village、Lil Wayne 等。入門就聽整張。 Wikipedia+1

  • Subcarpați(羅馬尼亞)— 傳統民謠 × 電子 × hip-hop 的大團企劃,常見不同 MC/歌手加入 cypher。入門:從現場影片或精選歌單切入。 Europavox+1

  • Night Marks Electric Trio(波蘭)— 電子靈魂×嘻哈的三人製作組,EP 就找 Raashan Ahmad、AB 等客席。入門:〈Glorious Tune (feat. Raashan Ahmad)〉、〈Walk Inside Your Dream (feat. AB)〉。 U Know Me Records+2Discogs+2

  • Gramatik(斯洛維尼亞)— 以器樂 hip-hop/glitch-hop 聞名的製作人,常與不同樂手與製作人合體(GRiZ 等);若你想要「重拍+取樣」的器樂場景,這是東歐代表。入門:The Age of ReasonEpigramWikipedia+1

  • Dubioza Kolektiv(波黑)— 巴爾幹 × hip-hop × 電子 × 搖滾的大雜燴團,合作清單長,近年也持續跨界單曲與聯名。入門:〈No Escape (from Balkan)〉、與 Manu Chao 等合作曲。 Wikipedia+1


西亞/中東(West Asia)

  • 47SOUL(巴勒斯坦/約旦)— “Shamstep” 先鋒:dabke 節奏+hip-hop+電子,常見 cypher 式多人客座。

  • DAM(巴勒斯坦)— 團體本身以 MC 為核心,也常與地區製作人跨作;節拍多電子/低音取向。

  • BLTNM / Muqata’a 陣線(巴勒斯坦)— 以製作人為底的 collective,經常「製作人+MC」拼盤釋出。

  • Balkan Beat Box(以色列)— 地中海打擊+低音電子,單曲裡常找說唱/MC 站台。

南亞/南亞裔

  • Nucleya(印度)— desi bass 旗手,習慣找本地 MC 客座(例如與街頭說唱場景合作);舞池能量直上。

  • DJ Vadim(俄羅斯出生/英國發展)— 老派抽樣×downtempo×hip-hop,專輯常是「製作人串各路 MC」的拼盤。

  • Swet Shop Boys(Riz Ahmed + Heems)— 南亞取樣與全球低音的混血,常與不同製作人互拼(雖然本身是雙 MC,氣質很接近你要的跨域感)。

東南亞

  • SpaceSpeakers Group(越南)— 以 Touliver 為中心的製作人團隊,長年串連 Binz、Rhymastic、SOOBIN 等 MC/歌手,標準「製作人×客座」運作。

  • Rap Against Dictatorship(泰國)— 政治力度強的說唱 collective,作品常見不同 MC/製作人參與;和 Pyra 的議題取向相通。

  • Suboi ×(越南製作人群)— 越南女王級 MC,長期與本地 beatmaker/團隊合作(如 SpaceSpeakers 成員);可當你探索越南「製作人+MC」圈的入口。

  • PYRA(泰國)— 你已經在聽了;她常與不同製作人共作,聲音在 alt-pop、電子與說唱之間切換,很適合做串場樞紐。

東亞/亞洲血統的國際製作人

  • Balming Tiger(韓國)— 另類嘻哈 collective,製作人+多位 MC 的鬆散編制,合作非常頻繁。

  • m-flo(loves 系列)(日本)— 典型「團體+海量 feat.」的長期企劃,名單從歌手到 MC 都有。

  • DJ Krush(日本)— 日本傳奇級製作人,專輯常找美英地下 MC 合作(Black Thought、C.L. Smooth 等),陰鬱的重拍很貼 NIN/ADF 的黑色感。

  • TOKiMONSTA(韓裔美籍)— 電子/左場 hip-hop 製作人,與各路 MC/歌手跨作,旋律跟低音比例拿捏漂亮。


先聽這幾首(把門味道抓住)

  • 47SOUL – Intro to Shamstep

  • DAM – Born Here

  • Balkan Beat Box – Hermetico

  • Nucleya – Jungle Raja (feat. DIVINE)

  • DJ Krush – Meiso (feat. Black Thought & Malik B)

  • Balming Tiger – SEXY NUKIM (feat. RM)