我們設計了一款透過壓電片與摩擦片收集資料的智慧鞋，壓電片嵌入在鞋底，摩擦片安裝在前腳掌，兩者並聯。當人行走時，感測器會被擠壓變形，藉由DAQ（數據採集）收集感測器的電壓輸出，可顯示出正常步行、快走、慢跑和漫步等活動的訊息，利用時變電壓形式的輸出數據，與能夠識別時域信號的CNN深度學習（卷積神經網絡）進行不同類型步態辨識。 實驗結果顯示此方法可以辨檢測這四種步態，其辨識率高達95%。訓練好的CNN可同時辨識個人身份與步態。結果顯示，識別快走時辨識率極高，識別正常步行和漫步時辨識率為90%，識別慢跑時辨識率僅達49%。因此，我們未來預計將提高同時辨識不同受試者與不同步態之辨識率，並透過壓電能量擷取器為藍牙模組供電。

網路上已經有很多人在做遠端的魚缸環境監控，但監控好環境條件，魚也不一定過得好，本實驗則是導入魚活動的參數，直接分析魚的活動力，以最直接的方式去觀測小丑魚的舒適程度。 本實驗研究目的為利用Arduino監測系統，監測裝置，並應用Blynk程式繪製環境數值趨勢變化圖。 本實驗的監控變因分為四個：水溫、pH值、水濁度，利用Blynk程式建立起一個能長時間即時監控及紀錄的系統，並建立起警示系統作為提醒裝置。 本實驗更進一步的結合Pixy Cam的監控系統，改變溫度及光照週期，並結合Raspberry pi的數據處理功能，自動處理龐大的數據，探討此兩變因對小丑魚活動力的影響。 此實驗是個發想，自動追蹤紀錄並處理大數據，此方法在未來可用來延伸研究養殖小丑魚的各種行為模式。

Electricity has become an essential part of modern life, powering homes, businesses, and industries. However, the misuse of electricity or malfunctioning electrical systems can lead to hazardous situations such as electrical fires, shocks, and significant energy wastage. This project focuses on creating a Comprehensive Electrical Security System to protect users and properties from the risks associated with electricity. The system is designed to prevent electrical malfunctions, ensure safety in various scenarios, and monitor energy consumption effectively. It integrates a variety of sensors and safety mechanisms to detect dangers and take preemptive action

在2021年4月2日台鐵太魯閣號在清水隧道行駛到轉彎口與滑落邊坡的工程車碰撞，造成火車出軌，衝入隧道中擦撞到隧道壁，造成49人死亡和247人輕重傷!當我們看到這則新聞時，心裡充滿驚訝與心疼!為了改善這問題，我們開始討論和查資料，發現台鐵在107年12月有一個「邊坡全生命監測系統」計畫，運用AI影像辨識技術，台鐵的規格是95%以上準確率，但因為辨識準確度不夠高，所以延宕到現在仍未完成。 我們設計AI鐵道辨識異物入侵系統，藉由攝影機將鐵道周遭影像傳至台鐵行控中心，運用AI深度學習技術辨識入侵鐵道的異物，從而準確判斷，讓火車駕駛員能提前預警，達到保障人車安全的目的。本研究並建立一套科學系統的方法來訓練視覺辨識模型，從而提高準確率，目前最高的準確率是97%!

MAGALH˜AES, Eduardo De Mˆonaco. PiezoPioggia: Energy Harvesting with Raindrops. 2024. 24 p. Research report – Scientific Apprentice Program, Col´egio Dante Alighieri, S˜ao Paulo, 2024. This project wishes to study and analyze the possibility of generating clean and accessible energy with the plain impact of droplets in the ground. Therefore, it was necessary to use piezoelectric devices in order to convert the kinetic energy of each droplet into electric energy throughout piezoelectric energy harvesting processes, (PEH). Piezoelectricity is a method of clean and sustainable energy generation, developed and explored by several scientists worldwide. Thus, while studying the proprieties of those devices, the project evaluates the present situation of electricity harvesting in Brazil, the benefits of piezoelectric technology and the possibilities it presents to economy and society. Throughout the development the project builds itself upon mathematical equations and experimental results, analyzing the deformation and generated tensions of piezos. Brand new data on the behavior of rain, as well as about the potential it presents for PEH are highlighted throughout the research, reinforcing the value of such process as a sustainable energy generation method alongside with its investment potential, both from governmental and private institutions. The project also deeply characterizes the piezoelectric device studied, diving deeply in its characteristics and evaluating the deformation of the device and treating the data sets with statistical analysis methods, in order to improve the precision of the data presented. All in all, the opportunities of piezoelectric energy harvesting in the rain, nella pioggia, shall be discussed profoundly throughout the project.

近年有許多研究開發粉末顆粒的防沾黏材料，在手術中可以輕易地噴灑在傷口附近達到防沾黏的目的。本研究首先篩選天然植物澱粉，探討並比較不同澱粉作為防沾黏材料的合適性，其次，在顆粒改質的乳化法中採用不同離子來製成防沾黏澱粉，並比較材料特性，包含粉末顆粒大小形貌、吸水效率、黏度。我們比較市場上多種食用性澱粉，乙醯化磷酸二澱粉具有最高約的吸水效率598%。在此研究中我們以乳化法將界面活性劑接枝在澱粉顆粒的表面來增加材料的親水性，並在乳化法中添加不同的離子化合物，結果顯示氯化鈉（NaCl）改質的乙醯化磷酸二澱粉，其吸水效率可進一步提升到1328.3 %，使用氯化鉀（KCl）改質的澱粉為1131.6%，而使用氯化鈣（CaCl2）則是1096.9%。實驗結果與討論顯示越高的吸水率有越好的抗沾黏效果。

此研究選擇以袋鼠為仿生對象，希望應用袋鼠高速移動的特點，製作仿生動物，並觀測其跳耀動作，提升動作的流暢度。 首先對澳洲袋鼠在跳躍時的動作，進行動態分析，取得跳躍時其最佳腿部彎曲動作。經歷二次的外觀與整體結構更改，以及數十次的細微尺寸與外觀修飾的調整，完成了此次使用的仿生袋鼠。 此仿生袋鼠使用18公分長的小腿為基準，設計跳躍動作影響便因。首先更改個部位的馬達扭力進行跳躍距離和高度的紀錄，測驗出距離最遠，高度最高的數據，並依同樣的變因條件，進行腿部長度的變更，同樣求得最佳數據再進行下一實驗，以此求得在各變因下最佳的條件。 本研究包含生物觀察、機械繪圖、動作分析，而希望此實驗數據在未來能應用於跳躍型的外骨骼。

傳統藍染，染個深藍色的布，需要反覆侵染二、三十次才行，而每一次洗滌，都是藍水會對環境污染!我們自製鑑色儀器的設計，以白光照射吸光儀，讓光敏電阻感光後，測量一般電阻電壓大小，以不同濃度製作檢量線比較染液濃度；染布鑑色儀則是以GY-33顏色感測器校正後，快速測出色布上同樣區塊面積的RGB值，再利用線上顏色代碼轉換工具，轉換成HSB 值來分析染布顏色。而染布動力的部份我們想把一直都是用塑膠積木製作的二~六槳水車更新成金屬，然後再次比較出不同水位負載物的氧化及還原轉速，希望能找出最佳水車運轉速率及水位高度比，為了因應長度較大的藍巾，水車轉動還加入程式控制順逆轉軸的動力輪替。最後，我們比較增加風速或溫度可否加速藍染氧化之定色，讓精準快速的藍染文化成為可能。

Visual impairment ranks among the top three disabilities globally, with affected individuals projected to increase from 39 million in 2015 to 115 million by 2050. Despite this growing prevalence, over 95% of visually impaired individuals face difficulties in learning Braille (AFB, 2022). In Thailand, the issue is compounded by limited resources, with only 48 schools for the blind serving 6.5% of visually impaired children, alongside a shortage of trained teachers and prohibitively expensive Braille displays. To address these challenges, the EIBraille Box was developed as a cost-effective and accessible tool enabling visually impaired individuals to practice Braille independently. The device utilizes electromagnetic field generation based on Lenz's Law and electromagnetic induction, employing copper coils and varying currents to drive a Braille dot display mechanism controlled by a microcontroller. Results show the device achieves an average display rate of 30–120 milliseconds per cell and a Braille dot-changing frequency of 3–20 cycles per second. The production cost is reduced from 11,660 USD to 87 USD—over 130 times more affordable—while maintaining performance comparable to traditional mechanisms. Additionally, the device integrates with a web application aligned with the Ministry of Education's curriculum to enhance learning. The EIBraille Box is planned for deployment across 48 schools affiliated with the Northern School for the Blind. Plans include extending access to individuals unable to attend schools via alternative distribution channels. This project stores high capacity to achieve global reach by partnering with the World Blind Union, extending its services to rural areas and ensuring access for underprivileged communities. This effort seeks to promote literacy among the blind on a worldwide scale. This innovation strives to enhance equity for the visually impaired by enabling blind individuals to participate in inclusive educational environments alongside their peers. It aims to eradicate the challenges of illiteracy and ensure equitable access to quality education.

腦部腫瘤是沉默殺手， 藏匿在腦中數十年。 一旦發作，通常都會造成巨大的影響。雖有數種高階儀器，可以檢測。但檢測過程繁複、 等待時間以及價格， 對於民眾都是不小的負擔。 腦部腫瘤的診斷方式為： 神經內、 外醫生會用筆燈對患者做初步的瞳孔光反應檢查。 藉由患者瞳孔縮小的速率，判斷是否要安排進階的檢查。但此行為仰賴醫生的經驗，沒有統一的方法及數據可供判斷。 本研究設計一款成本約$1,300 元， 重量僅 159 g，圓柱直徑與柱高皆約為 7cm 的隨身裝置。 藉由 MCU 控制攝影機， 頂部 1.44 吋 TFT 螢幕可即時顯示患者眼部狀態，檢查結果計算後， 也會立即顯示在螢幕上。除提供醫護人員即時數據化的解讀患者狀態。更協助醫護人員在做瞳孔光刺激檢查時，有科學化的標準。