全國中小學科展

電腦科學與資訊工程

A Person Re-identification based Misidentification-proof Person Following Service Robot

Two years ago, I attended a robot contest, in which one of the missions required the robot to follow the pedestrian to complete the task. At that time, I used their demo program to complete the task. Not long after, I found two main issues: 1. The program follows the closest point read by the depth camera, which if I walk close to a wall next to, the robot may likely ‘follow’ the wall. 2. Not to mention if another pedestrian crosses between the robot and the target. Regarding these two issues, I decided to improve it. We’ve designed a procedure of using YOLO Object Detection and Person re-identification to re-identify the target for continuous following.

以深度學習與遷移學習防範社群媒體片面新聞訊息之研究

現代民眾獲取新聞的途徑逐漸轉移到網路媒體,然而在網路資訊快速傳播以及媒體為追求報導曝光度以增加金錢利益的情形下,片面、誘導等形式的新聞標題與短句訊息在新聞媒體傳播中日益嚴重;本次研究透過Fake News Challenge提供的Stance Detection dataset,運用深度學習與遷移學習方法訓練可預測兩文本之間相關程度的自然語言處理模型,在過程中改善調參及訓練方式,並將其實際運用在預測美國新聞媒體於Facebook網路社群平台發文推播新聞的同時所附的短句與新聞報導文本內容之間的相關關係程度,分析社群平台中新聞可能造成的誤導式文句是否實際造成片面報導,而影響了受眾對於媒體的使用程度與信任程度。使此模型有助即時預警社群平台上的報導資訊型態品質,輔助使用者獲取新聞時所應具備的媒體識讀能力,進而改善片面報導於網路的流竄,同時提升未來媒體生態。

Method of prosthetic vision

This work is devoted to solving the problem of orientation in the space of visually impaired people. Working on the project, a new way of transmitting visual information through an acoustic channel was invented. In addition, was developed the device, which uses distance sensors to analyze the situation around a user. Thanks to the invented algorithm of transformation of the information about the position of the obstacle into the sound of a certain tone and intensity, this device allows the user to transmit subject-spatial information in real time. Currently, the device should use a facette locator made of 36 ultrasonic locators grouped in 12 sectors by the azimuth and 3 spatial cones by the angle. Data obtained in such a way is converted into its own note according to the following pattern : the angle of the place corresponds to octave, the azimuth corresponds to the note and the distance corresponds to the volume. The choice of the notes is not unambiguous. However, we used them for the reason that over the centuries, notes have had a felicitous way of layout on the frequency range and on the logarithmic scale. Therefore, the appearance of a new note in the total signal will not be muffled by a combination of other notes. Consequently, a blind person, moving around the room with the help of the tone and volume of the sound signals, will be able to assess the presence and location of all dangerous obstacles. After theoretical substantiation of the hypothesis and analysis of the available information, we started the production of prototypes of the devices that would implement the idea of transmitting information via the acoustic channel.

Development of an Android Application for Triage Prediction in Hospital Emergency Departments

Triage is the process by which nurses manage hospital emergency departments by assigning patients varying degrees of urgency. While triage algorithms such as the Emergency Severity Index (ESI) have been standardized worldwide, many of them are highly inconsistent, which could endanger the lives of thousands of patients. One way to improve on nurses’ accuracy is to use machine learning models (ML), which can learn from past data to make predictions. We tested six ML models: random forest, XGBoost, logistic regression, support vector machines, k-nearest neighbors, and multilayer perceptron. These models were tasked with predicting whether a patient would be admitted to the intensive care unit (ICU), another unit in the hospital, or be discharged. After training on data from more than 30,000 patients and testing using 10-fold cross-validation, we found that all six models outperformed ESI. Of the six, the random forest model achieved the highest average accuracy in predicting both ICU admission (81% vs. 69% using ESI; p<0.001) and hospitalization (75% vs. 57%; p<0.001). These models were then added to an Android application, which would accept patient data, predict their triage, and then add them to a priority-ordered waiting list. This approach may offer significant advantages over conventional triage: mainly, it has a higher accuracy than nurses and returns predictions instantaneously. It could also stand-in for triage nurses entirely in disasters, where medical personnel must deal with a large influx of patients in a short amount of time.

Cross-lingual Information Retrieval

In this project, we evaluate the effectiveness of Random Shuffling in the Cross Lingual Information Retrieval (CLIR) process. We extended the monolingual Word2Vec model to a multilingual one via the random shuffling process. We then evaluate the cross-lingual word embeddings (CLE) in terms of retrieving parallel sentences, whereby the query sentence is in a source language and the parallel sentence is in some targeted language. Our experiments on three language pairs showed that models trained on a randomly shuffled dataset outperforms randomly initialized word embeddings substantially despite its simplicity. We also explored Smart Shuffling, a more sophisticated CLIR technique which makes use of word alignment and bilingual dictionaries to guide the shuffling process, making preliminary comparisons between the two. Due to the complexity of the implementation and unavailability of open source codes, we defer experimental comparisons to future work.

一種新的複音音樂片段相似性度量

平常聽音樂時經常有種似曾相識的感覺。為了描述這種感覺,我們展開了複音音樂片段相似性度量的研究。因為曾經使用過最長公共子序列實作卻效果不如預期,我們將音樂片段正規化後,視為座標平面上的時間、音高點對的集合,使用點對應與二分圖匹配的方法,定義兩個複音音樂片段的相似度為最大權重匹配的平均邊權。我們計算了資料集(JKUPDD)中相同、相異的音樂片段的相似性,調整算法中的參數,找出最適合的參數組合,並且透過音符之間的權重,畫出自相似度矩陣,發現樂曲中的重複片段。

Automated Debugging System – Implementing Program Spectrum Analysis and Information Retrieval on Fault Localization

在程式專案開發中,偵測錯誤常為最耗時的環節,進而影響整個專案的開發時長。而現今雖有些許輔助開發者提升偵錯效能的工具,但這些工具也只能藉由提供編譯執行中的資訊讓開發者省去偵錯時的繁瑣步驟,仍須開發者自行評估每段程式碼的正確性。此研究透過程式段落分析與資訊檢索實現自動錯誤定位,在每個程式段落標記其成為臭蟲(bug)的可能性。在程式段落分析中,執行使用者之原始碼,並透過歸納最終結果為正確及錯誤之執行路徑差異分析出每個程式段落的可疑性。接著運用資訊檢索技術於資料庫中找尋相似之原始碼,並參考其偵錯結果優化現有之可疑性,形成最終之可疑性排名。此研究不只結合了上述兩種技術,更優化可疑程度之計算方法以及資訊檢索中的相似度比對機制,達到更完善的錯誤定位。(此指「臭蟲」非語法錯誤(Syntax Errors),而為邏輯錯誤(Logic Errors)。)

Solving Mathematical and Chemical Equations using Python

Max Gold's project, titled “Solving Mathematical and Chemical Equations using Python”, is a website comprising of 4 main programmes: one to find the smallest possible combination of two chemical compounds or elements; a self-made parsing function to convert a chemical equation into a matrix, then using Gaussian-Jordan elimination to find coefficients for an equation; a programme to parse a mathematical expression and use that parsed expression in algebraic division of an algebraic dividend of nth degree polynomial by a divisor of 1st degree polynomial; finally, a programme to solve binomial equations for the power s∈Q. This website was originally made so that Max Gold could improve his programming skills for GCSE computer science but expanded to incorporate his passion for chemistry and maths and thus allow others to use these programmes to help them with their problems as well. A problem with many conventional calculator websites is their lack of specificity – they tend to be able to compute some functions but not all. These programmes are tailored to GCSE and A level maths and chemistry, meaning this website provides an outlet to compute specific topics of problems.

腦波辨識特徵提取於即時身分認證的研究

本研究的腦波辨識基於特徵提取,可應用於身分認證,具有不能被仿冒的優點。我們用低成本高便利性的腦波儀,自行撰寫程式讀取原始腦波,建立一致性的實驗程序。首先用腦波專心度的高低來控制智能車,再用腦波來測謊,有隱藏說謊行為時會觸發高電位腦波,在兩項前期研究後發現可用腦波特徵進行身分認證。三位受測者於不同日期提取10份腦波,每份腦波紀錄5120筆數據。接著我們反覆嘗試組合數十種統計函數進行特徵提取,找到兩項最佳特徵,達成將大量凌亂腦波資料降低維度又具有辨識力。我們腦波辨識分類方法使用近鄰演算法,測試程序用盲測交叉驗證法,辨識正確率百分百。最後我們用Arduino板來展示腦波辨識應用於腦波身分認證,資料庫中只要儲存每位受測者的腦波特徵值,就能在數秒內正確辨識說出受測者身分,顯示每個人腦波是不同的,而且能用特徵將其分辨出來。

圖論演算法學習用之繪圖程式

本研究針對學習圖論演算法的需求,設計一套使用者友善的繪圖軟體Graphene。Graphene繪圖程式除了提供高可讀性的繪製結果,作為輔助繪圖的工具外,也可直接輸入競賽題目的文字格式測試資料產生繪圖結果,並結合現有繪圖演算法,改善、優化樹與類樹圖的繪製結果。此外,也加入時間軸、自訂外觀、參數調整、匯出圖片等功能,幫助學習者理解圖論演算法,亦可幫助教師製作教材,有助於圖論演算法教學。 Graphene採用的繪圖演算法以force-directed graph drawing演算法為基礎,實作節點的分布。然而初始的節點分布會影響繪圖結果,因此我們利用biconnected component、block-cut tree等圖論結構對圖的繪製進行優化。首先找出圖的biconnected component及關節點,重新定義block-cut tree裡的block,接著利用radial tree的布局方式配置每個block,再套用force-directed graph drawing演算法,得到最後的布局結果。如此可以減少不同block之間的交錯,得到較佳的結果。