全國中小學科展

2025年

分子結構語言與熔沸點性質的人工智慧預測

背景:預測分子性質如溶解度、毒性及熔沸點對於基礎科學至關重要。然而,實驗測量這些性質耗時且昂貴,因此本研究使用多種機器學習模型藉由調整變相來準確預測熔、沸點。 方法:本研究使用超過一萬筆數據及兩種類型的機器學習方法:淺度與深度學習。淺度學習由 PyCaret實現,並以Mordred作為分子描述器;深度學習使用圖神經網路,包括(CMPNN和GCN),並調整隱藏層參數。 結果:CMPNN在目前嘗試的模型中表現最佳。發現影響沸點預測的關鍵特徵是piPC1,與鍵級相關;熔點則是AATS0d,與σ電子的 Moreau-Broto自相關有關。 結論:CMPNN模型在沸點與熔點預測中均表現最佳。沸點中深度學習模型優於淺度學習模型(p<0.05)。此外,使用SHAP成功找出piPC1和AATS0d對最關鍵。本研究不僅得出了高準確性的模型,還發現了影響分子性質的關鍵特徵,且可擴展至其他預測。

鈦錳啦!藍「解」「除」橘!──探討MnO2及TiO2對亞甲藍及甲基橙的去除效果

本研究利用合成不同形狀TiO2/MnO2/ZnO,藉由改變接觸面積進而提升染料去除率。在初實驗中將9 種金屬氧化物與甲基橙/亞甲藍/甲基紫反應,發現TiO2-甲基橙與MnO2-亞甲藍之組合有較好的去除能力。在改變反應溫度的實驗中,TiO2-甲基橙之去除率隨著溫度上升而降低,當中以25℃ 海膽形表現最佳,而在MnO2-亞甲藍的反應中,則以海膽形在25℃時表現最佳。最後改變染料溶液的pH 值,發現TiO2 海膽形在pH5.7 時表現較佳,MnO2 則是在低pH 時有較高的去除率,推測該結果與顆粒零電荷點及染料pKa 值相關。透過BET 與PL分析,TiO2 海膽形及MnO2 海膽形有較佳的比表面積與氧化能力,故整體去除效果最佳。此外本實驗亦利用LC-MS 驗證反應的確成功分解染料,且利用模式生物試驗證實處理後之溶液對生物毒性明顯降低。

YKT6與癌纖維母細胞的「泌」密關係

本研究以人類肺癌A549細胞株和纖維母細胞模擬體內腫瘤微環境,挖掘纖維母細胞如何促進癌細胞的生長。從病人的正常和癌組織提取癌相關纖維母細胞(cancer-associated fibroblasts, CAFs) 和 正常纖維母細胞(Normal Fibroblasts, NFs),經過基因序列一對對作分析,開發新的治療策略和潛在的靶點。利用核糖核酸定序(RNA-Seq)分析發現CAFs會比NFs分泌更多SNARE 蛋白 YKT6,而更深入地探究獲悉YKT6會透過活化YKT6+CAFs途徑促進肺癌A549細胞惡化,此惡化過程包括誘導及提升癌細胞的生殖(proliferation),轉移(migration)和入侵(invasion)能力。 此外,在 CAFs 中敲除 YKT6基因,減弱CAFs 的外泌體(exosome)釋放,從而調節了其對肺癌細胞A549的腫瘤促進作用。本研究發現靶向YKT6並抑制外泌體分泌,從而降低CAFs對肺腺癌細胞的腫瘤支援功能可以為肺癌治療提供一種新的策略。

降脂轉肌–將脂肪轉變成肌肉的可能性探討

先前研究發現一種多元不飽和脂肪酸 15-keto-PGE2 能減少肌肉慢性發炎以及增加肌肉生長因子胰島素的敏感性,具有增加肌肉的潛力。我們探討此脂肪酸在小鼠中將脂肪組織轉成肌肉組織的可能性。 我們先以 15-keto-PGE2 治療肥胖型肌少症小鼠後,再以全基因組mRNA定序,發現在小鼠皮下脂肪中,肌肉特異基因表現量高度上升。透過基因表現路徑分析軟體 GSEA證實此脂肪酸會高度引發皮下脂肪中,與肌肉分化、肌肉收縮與肌肉結構相關的生物路徑。另外, 15-keto-PGE2 也可以誘導脂肪前驅細胞3T3-L1中與肌肉生成相關的基因表現。 最後,我們發現以 15-keto-PGE2 治療的老年肥胖型肌少症小鼠,體重、血糖、脂肪比例下降,肌肉質量及力量上升,證實了它在體內同時減少脂肪並增加肌肉量的效果。

Low-Cost Nickel-based Catalyst for Electrocatalytic Splitting Of Ammonia Towards Clean Hydrogen Production

Increasing energy needs alongside the urgent issues of chemical pollution has prompted the need for developing novel green energy sources. Nitrogen-based fertilizers are of fundamental importance for the ecosystem as their usage has increased eight times in the last fifty years [1]. On the other hand , increased use of nitrogenous fertilizers is followed by higher ammonia emissions, which are dangerous pollutants responsible for deterioration in biodiversity by means of eutrophication, acidification of soil and water, and climate change [2]. Ammonia has the2apacityy to bond with other pollutants including sulfur oxides and nitrogen oxides to create particles that cause smog, which is associated with lung disease. Ammonia also increases frost sensitivities and causes necrosis of many plant species [3.] Therefore, there is a need to properly manage the ammonia-rich nitrogen waste to decrease the environmental threat factors. Of the possible approaches suggested for ammonia waste treatment, the ammonia electro-oxidation reaction (eAOR) has various promising features for application in the energy sector. It is economically appealing because Ammonia can serve as an excellent hydrogen carrier due to its storage capabilities and existing transport infrastructure alongside having no net carbon emissions. Apart from this, it requires 95% less of the theoretical energy [4] to perform the process. But the reaction is kinetically slow [5], which has been a research obstacle during the development of (eAOR), due to factors ofmslow reaction rate and large catalytic overpotential that this process consumes an unnecessary amount of power [6]. Nickel-based catalysts are a promising solution to these problems, they are cheaper , more stable and easier to produce than electrocatalysts for water electrolysis which makes it highly energy efficient for widespread use on the industrial scale. N films deposited on the anodic side also allow the creation of N-containing products such as (NH42SO3) and nitrates, which can be converted into fertilizers or renewed into the nitrogen cycle to make the process more environmentally friendly while enhancing the (eAOR) process [7,8]. Compared to Pt and Ir which are the most used noble metals, they are less poisoned on the potentials less than 0.65V and are more stable [9,10]. However , noble metals are scarce, and their cost is high for industrial applications as well as the energy they waste during (eAOR) [11].

複合葡萄糖氧化酶的金奈米團簇應用於葡萄糖檢測

本研究使用牛血清白蛋白(BSA)、穀胱甘肽(GSH)、金離子合成金奈米螢光團簇,並修飾上葡萄糖氧化酶(GOx)。此金奈米團簇上的葡萄糖氧化酶與葡萄糖反應,製造出過氧化氫,改變金奈米螢光團簇表面特性使螢光強度減弱,偵測葡萄糖濃度。 本研究探討不同條件金奈米團簇和不同濃度的葡萄糖反應,知道此材料可檢測到最低濃度的葡萄糖,且金奈米團簇在血液中對葡萄糖具有專一性,可穩定進行血糖檢測。另外,與不同濃度的人體血清樣本反應,發現血清濃度越高的螢光訊號下降明顯,因此可知修飾上葡萄糖氧化酶的穀胱甘肽輔助之牛血清白蛋白金奈米團簇(BSA/GSH-Au NCs)可用於人體血糖檢測。本研究開發出靈敏、快速、穩定的葡萄糖檢測材料,並期待未來能運用於實際的人體血糖檢測上。

運用深度學習色彩校正模型之黃疸偵測 Jaundice Detection Using Deep Learning-Based Color Correction Models

現今醫療中,黃疸的早期偵測對肝臟疾病的預防與治療至關重要,但多數人難以在症狀輕微時察覺。我們希望藉由智慧手機影像結合機器學習進行黃疸檢測,提升民眾自我監測的能力。Su 等人(2021)曾使用深度學習和機器學習進行黃疸預測,但其方法依賴專業色卡進行色彩校正,成本高且限制應用範圍。本研究提出以白平衡演算法中的白色補丁法與灰界演算法,搭配深度學習模型 DCCNM1和2 取代色卡,提升黃疸檢測的普及性與便利性。經黃疸偵測效果評估顯示,DCCNM2 在無色卡模型中表現最佳,雖然各指標略低於色卡校正,但其展現出優異的穩定性和準確性,證明其作為無色卡黃疸篩檢方案的可行性。本方法將能提供便捷的居家黃疸檢測途徑,尤其對偏鄉地區居民而言,不僅提升早期發現的機會,還能有效減輕醫護人員的負擔,推動大眾健康管理。

AI-Based Customer Sentiments Dashboard

In this fast-paced digital economy, customers' judgment is based on their experience with a company’s products and services. Customer reviews become a vital source of information for companies because this information can be used to enhance their products, understand customer wants and needs, improve brand reputation, and provide a competitor’s advantage. A company can understand customer needs and wants by going through reviews. Customers are encouraged to leave not only their opinion but also their ideas for the development of the product or service. By understanding these reviews, a company can actively respond and engage with a reviewer or problem. Failure of companies who don't answer customer queries may negatively impact customer loyalty. Customers will feel neglected by these companies and will choose competing companies to handle their needs. Additionally, customers may speak negatively about a company that does not respond to reviews. The AI-based customer sentiment dashboard can help gain a company's competitive advantage by identifying weaknesses in themselves and others. Companies will be enabled to understand where they succeed and where improvement is needed compared to their competitors, leveraging businesses to address strengths and weaknesses before competitors do. Through AI-based customer sentiment dashboards, a company can analyze its competitor’s reviews and use that information as leverage to make improvements to its products and services. Customers are increasingly leaving reviews on popular apps like Google Play, Stamped.io, Yapto, and Judge.me, Loox, Qualaroo, and Yelp. The reviews are rich in customer sentiments offering valuable insights into user satisfaction and pointing out the areas for improvement that are crucial to every company no matter how big or small. Despite their value, manually processing these reviews is a challenging task due to the large volume of unstructured data. Manual processing is also vulnerable to bias and human error, leading to inaccurate information. Traditional methods such as surveys have been proven to be ineffective if the main focus is targeted feedback and have low responses compared to reviews. The advances in artificial intelligence like Natural Language Processing (NLP) help us interpret and analyze human language and generate outputs like predicting what type of sentiments are in reviews. This project proposes developing an AI-based sentiment analysis model to evaluate customer feedback on two widely used taxi applications. Natural Language Processing libraries, such as the Valence Aware Dictionary and Sentiment Reasoner (. The model aims to categorize customer reviews into positive, negative, and neutral sentiments.

Production of Nano-Composite Artificial Bone Tissue Using Bioceramic Synthesis from Bio-Waste

Certain specially structured ceramics, which can be used as biomaterials to replace bone, have recently started being utilized in the medical field. The aim of this study is to produce high-bioactivity silica from corn cob waste, a widely available organic material in nature, and combine it with calcium oxide (CaO) obtained by grinding organic mussel shell waste with high bioactivity. This combination is intended to synthesize dicalcium silicate (2CaO.SiO₂) to develop an alternative tissue scaffold with high bioactivity, capable of replacing bone, for existing titanium alloys. The goal is to incorporate this scaffold into PEEK (polyether ether ketone), a novel tissue scaffold material, at varying percentages to create a next-generation innovative bone substitute material. An additional objective is to demonstrate through biocompatibility tests that the produced ceramic-polymer biocomposite exhibits antibacterial activity against Staphylococcus aureus.

關於Repunit數列 之餘數性質探討

在這篇作品中,主要研究Repunit數列=在模n之下的餘數數列循環性質。我們探討了Repunit餘數數列在什麼條件下 為純循環週期數列、混循環週期數列和完全純循環週期數列,同時給出了循環週期的公式及上界。接著我們發現一階非齊次線性遞迴數列在模n之下的循環週期與c進制Repunit數列在模 n/gcd(n,c)之下的循環週期相同,並且進一步探討餘數數列在什麼條件下為純循環數列、混循環循環數列和完全純循環數列。