New Screening Method for Early Pediatric Cancer Detection Through Automated Handwriting Analysis
Pediatric cancer has an incidence rate of more than 175,000 per year with a mortality rate of approximately 96,000 per year. One major cause of this problem is late diagnosis. A novel promising way of pediatric cancer screening is handwriting analysis. This method surpasses other methods by detecting pediatric cancer in a very early stage. However, studies are still limited to manual analysis which needs an expert and a long period of time. The aim of this project is to design a computer program to extract handwriting features and build a classification model to classify the user as patient or as control. Dataset was collected from schools and hospitals where all participants could read and write in English. After data cleansing, number of samples was 440 samples. MATLAB (Matrix Laboratory) program was used for extracting geometric features in handwriting. Program was validated using a subset of 50 samples of the dataset. WEKA Package was used to test and build the classifier. Experiments were done using classifiers: Logistic, Multilayer Perceptron, J48, LibSVM, AdaBoostM1 and Naïve Bayes. Best subset of attributes was evaluated and used for each classifier and all calculations were done as the average of cross validation operations of several folds assignments. Best performance was achieved by Logistic classifier with average accuracy of 80.15%, standard deviation of 0.43% and Matthews's correlation coefficient of 0.59. Finally, this project presents a new fast, free, ready, easy and psychologically comfortable method for pediatric cancer detection while keeping suitable accuracy for mass screening.
Artificial Photosynthesis -Formic Acid Generated from Carbon Dioxide by Using Photocatalyst-
Reduction of carbon dioxide is desired as an environmental problem of global warming. The study of generation of formic acid from carbon dioxide was performed under irradiation of ultra violet to photocatalyst. Ta2O5 could reduce carbon dioxide, but the band gap of Ta2O5 was 4.0 voltage. In this research, it was found that tantalum oxide / tantalum plate responds to visible radiation. Therefore, the reason of visible light response was examined. It was studied to make efficient tantalum oxide / tantalum plate.
都是氣泡惹的禍
當輕敲啤酒杯時,會發覺酒杯發出之聲調隨氣泡漸漸消失而有所改變。為了解氣泡是如何影響頻率,我測試了幾種含氣泡之飲料,以探討當氣泡漸漸消失時,杯子發聲頻率之變化。實驗發現杯子內飲料之氣泡漸漸消失時,裝啤酒與可樂杯子的發聲頻率逐漸增高,然而裝沙士杯子的頻率卻逐漸降低。為解開此相互矛盾的現象,我設計了將液面上之泡沫及液面下之氣泡分開檢驗的實驗。實驗結果發現,液體中氣泡的存在會使杯子發聲頻率變高。而當液體表面受到擾動時,會降低杯子的發聲頻率。若液面上存在泡沫時,杯子的發聲頻率也會變低。這表示裝盛含氣泡飲料杯子音律之變化,須同時考量液內含泡量與液體表面之效應。此結果可以成功的解釋為何啤酒、可樂與沙士於氣泡漸漸消失時,杯子頻率會變高或變低的現象。Tapping the side of a glass of beer as the bubbles escape, one can find that the pitch will change. In order to know how the bubbles would influence the frequency, I survey the pitches of a wine glass with various drinks that would generate bubbles. As bubbles getting away from the glass, my experimental data shows that the frequencies of the tone did get higher when the glass contains beer and coke. However, I surprisingly find a different result when the same glass contains sarsaparilla. Hence I design a series of experiments to understand the possible mechanism. The data suggests that when the drinks contain bubbles in it, the frequencies of the tones will be higher. When the liquid surfaces were disturbed, the frequencies of the tones will become lower. If there were foams above the liquid surfaces, the frequencies of the tones will also be lower. This finding proposes that people needs to consider both the bubble bulk status and surface effects. The consequences of the competitions between these two effects can successfully explain how the tones are changed in the cases of beer or sarsaparilla or coke.