全國中小學科展

2022年

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。

Development of an autonomous Search and Rescue Drone

The number of natural disasters has risen significantly in recent years, and with climate change there is no end in sight. Consequently, the demands on rescue forces around the world are increasing. For this reason, I asked myself what I can do to improve the work of rescue teams. Advances in artificial intelligence and drone technology enable new possibilities for problem solving. Based on the technological advances mentioned above, an autonomous Search and Rescue drone was developed as part of this project. The system assists rescue workers in searching for survivors of natural disasters or missing people. This paper also suggests a method for prioritizing survivors based on their vitality. The system was implemented using a commercial Parrot ANAFI drone and Python. The software was tested on a simulated drone. To simplify the development, the whole system was divided into the following subsystems: Navigation System, Search System and Mission Abort System. These subsystems were tested independently. The testing of solutions and new concepts were performed using smaller test programs on the simulated drone and finally on the physical drone. The Search and Rescue system was successfully developed. The person detection system can detect humans and distinguish them from the environment. Furthermore, based on the movements of a person, the system can distinguish whether the person is a rescuer or a victim. In addition, an area to be flown over can be defined. If something goes wrong during the mission, the mission can be aborted by the Mission Abort System. In the simulation, the predefined area can successfully be flown over. Unfortunately, controlling the physical drone does not work. It stops in the air after takeoff due to the firmware of the drone. It does not change the flight state of the drone, which results in all subsequent commands from the system being ignored. This paper shows that artificial intelligence and drone technologies can be combined to deliver better rescue services. The same system can be applied to other applications.

BIOINFORMATIC PREDICTION OF CORONAVIRUS (SARS-COV-2) MUTATIONS THAT INCREASE CONTAGIOUSNESS

Inhibitory effects of the secondary metabolite of actinomycete were examined on cell cycle of the yeasts of S. pombe and S. cerevisiae. The secondary metabolite was obtained from cultivation of the actinomycete isolated from the soil of Owakudani in Hakone, Japan. The fifth fraction of the secondary metabolite by ODS column separation (HK-T5), which was soluble to pure methanol, was used in the present experiments. The HK-T5 brought about the delay of forming colonies of S. pombe for about 11 days compared to that cultivated without the HK-T5. The delay of the colony formation was longer for the S. pombe cultivated with more amount of the HK-T5. The cultivation with HK-T5 also brought about the extension of the lifespan of the S. pombe for more than 10 weeks in a liquidus medium. The cell life recovered the ordinary manner by removal of the HK-T5, meaning that the activities of the HK-T5 is reversible. These facts confirm the suppression of cell cycle, and the delay of cell growth by the HK-T5. These phenomena were similarly observed for S. cerevisiae. Comparison of the action of HK-T5 with hydroxyurea, which is an anticancer drug inhibiting the cell cycle at S phase, clarified that the inhibitory action of HK-T5 worked at the phase earlier than S phase. The combined effects of HK-T5 on the cell cycle were evaluated with triamcinolone acetonide (TA), or aspirin, the former of which is a drug synchronizing cancer cells in S phase, and the latter keeping human cells in G1/G0 phases. The combined use of HK-T5 with TA synchronized the cells at the phase slightly proceeding from G1 to S phase without toxicity. On the other hand, the combined use with aspirin made the inhibitory effect of HK-T5 inactive. Hence, the HK-T5 is attractive as a drug for the extension of cell lifespan, and anticancer therapy.

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)。)

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.

The Population Structure of the Orange River mudfish (Labeo capensis) in Allemanskraal Dam and Its potential as a Fishery Species

The aim of this research was to investigate whether the ecology and biology of the Orange River mudfish Labeo capensis were suitable for the species to be used in fisheries. Three fleets of the gill nets were set, parallel to the shore. One fleet was lifted, and the fish were collected by hand. The two remaining fleets were lifted the next day. The seine net was pulled for 10 metres within the littoral zone. The net was then pulled towards the shore of the dam and the procedure was repeated four times. The four fyke nets were set parallel to the shore and were left for two nettings nights and then lifted. All fish caught were collected by hand and placed into buckets. The majority (82.93%) of the fish caught were within the 0-100 mm size class. The 101-200mm and 201-300mm size classes contain similar numbers of fish, while no fish were caught in the 301-400mm size class. The hypothesis was accepted. Allemanskraal Dam, as of the study period, has a very small juvenile fish population of L. capensis, as only 7 out of 41 fish individuals caught were within the 101- 300mm fork length size class. These results show that the population of L. capensis is not established as of yet, as the research did was right after their breeding season. Historical research has shown that sexually mature individuals of the L. capensis species tend to be a minimum of 300mm SL, 4-6 years after hatching. The population was largely young-of-the-year and may develop into an established population in 3-4 years (after sexual maturity). The L. capensis population in Allemanskraal Dam has the potential to be a fishery species if suitable conditions are maintained. Establishing this species’ potential will therefore allow economically viable fisheries to utilise them sustainably and to their full economic potential.

In Silico Modeling of Lovastatin Analogues as Inhibitors of HIV-1 Nef Protein

Currently, no method can completely eliminate the human immunodeficiency virus (HIV) in an infected person. HIV employs an accessory protein called Nef that forms a complex with cellular AP-1, preventing detection of HIV-infected cells. Lovastatin has been recently identified to inhibit the formation of said Nef-AP-1 complex, but its effective concentration is remarked to be far higher than other Nef inhibitors. This study aims to develop a modified lovastatin molecule exhibiting higher binding affinity to the HIV-1 Nef protein than lovastatin in silico. Modified lovastatin molecules based on the interaction map of lovastatin with Nef were modeled, and flexible ligand-flexible receptor docking to the Nef binding site was performed using AutoDock Vina. Residues within the Nef binding site identified by Liu et al. (2019) to be crucial (Glu-63, Val-66, Phe-68, Asp-108, Leu-112, Tyr-115) were set as flexible. Fragment-based drug design was utilized to append molecular fragments to lovastatin in order to maximize its interactions with said crucial residues. From the fragment-based approach, molecule F4 ((1S,3S)‐8‐{2‐[(2R,4R)‐4‐chloro‐6‐oxooxan‐2‐yl]ethyl}‐3‐(hydroxymethyl)‐7‐methyl‐1,2,3,4‐tetrahydronaphthalen‐1‐yl 4‐aminobenzoate) exhibited a binding affinity of -9.0 kcal/mole, and its estimated IC50 ranges between 0.25-0.51 μM which is at least 7.5 times lower than the reported IC50 of lovastatin from literature. This study presents insights on the key modifications to improve lovastatin as an HIV-1 Nef inhibitor and pertinent information about the Nef binding site for future drug development studies.

推廣圓冪定理及圓錐曲線內接四邊形判定定理之探討

在歐氏幾何和射影幾何中,相異五點可決定一圓錐曲線。若給定任意四邊形,是由四邊形的四個頂點及異於此四頂點的第五點來決定圓錐曲線,則稱此四邊形為圓錐曲線内接四邊形。 圓冪定理是一個圓內接四邊形的幾何定理,包含相交弦定理、割線定理、切割線定理等三個定理,我們將圓冪定理推廣至圓錐曲線內接四邊形。首先由圓錐截痕推廣圓內兩交弦定理,是考慮兩垂直交弦,進而推導出圓冪定理推廣一式及區分圓錐曲線種類。接著利用圓錐曲線的方向直徑、邊或對角線斜率及平行邊的切線長推導出圓冪定理推廣二式、三式及四式,推廣式是採統一與歸納方式呈現。 其次,由解析幾何推導另一種圓冪定理推廣式(推廣五式),加上圓錐曲線直徑性質,論證出二種圓錐曲線及其内接四邊形的作圖及其判定條件。最後也證明圓錐曲線內接四邊形判定定理及有趣的錐線中心軌跡圖形。

Development of an autonomous Search and Rescue Drone

The number of natural disasters has risen significantly in recent years, and with climate change there is no end in sight. Consequently, the demands on rescue forces around the world are increasing. For this reason, I asked myself what I can do to improve the work of rescue teams. Advances in artificial intelligence and drone technology enable new possibilities for problem solving. Based on the technological advances mentioned above, an autonomous Search and Rescue drone was developed as part of this project. The system assists rescue workers in searching for survivors of natural disasters or missing people. This paper also suggests a method for prioritizing survivors based on their vitality. The system was implemented using a commercial Parrot ANAFI drone and Python. The software was tested on a simulated drone. To simplify the development, the whole system was divided into the following subsystems: Navigation System, Search System and Mission Abort System. These subsystems were tested independently. The testing of solutions and new concepts were performed using smaller test programs on the simulated drone and finally on the physical drone. The Search and Rescue system was successfully developed. The person detection system can detect humans and distinguish them from the environment. Furthermore, based on the movements of a person, the system can distinguish whether the person is a rescuer or a victim. In addition, an area to be flown over can be defined. If something goes wrong during the mission, the mission can be aborted by the Mission Abort System. In the simulation, the predefined area can successfully be flown over. Unfortunately, controlling the physical drone does not work. It stops in the air after takeoff due to the firmware of the drone. It does not change the flight state of the drone, which results in all subsequent commands from the system being ignored. This paper shows that artificial intelligence and drone technologies can be combined to deliver better rescue services. The same system can be applied to other applications.

The Reproduction success of the Cyprinidae and a Claridae fish species and its impact on small- scale fisheries

To investigate the reproduction success and natural recruitment of several Cyprinidae fish and Claridae fish species in the Allemanskraal Dam. The purpose of the project included investigating whether each individual fish species studied has a successful 2020/2021 spawning season in comparison with each other. Sections of the seine net were measured along with a distance of 10 along the shoreline. The ends of the seine nets were attached to one foot and the top of the net was held by hand. Both volunteers moved in unison while covering the 10m. The volunteer in the “deep end” moved towards the shoreline creating a semi-circle while the other volunteer remained stationary. The two ends of the net were then pulled onto the shore and the fish were collected. The results found that the Labeo Umbratus and Cyprinus carpio had the most successful spawning seasons with the highest recorded numbers. These high numbers of the Labeo Umbratus can be due to the fact that the species lays a large number of eggs. The high numbers of the Cyprinus carpio is due to the lower numbers of the other fish species as previous studies have shown that the species negatively impacts the environment which could in turn negatively impact the other fish species. The Claridae gariepinus and Labeobarbus aeneusas were the lowest. The low numbers of the Labeobarbus aneusas may be due to their slow growth and late maturity rate. The Labeo capensis had an average number relative to the other species and this is due to the fact that during the sampling period the dam was at 100% capacity as this is essential for the survival of the juvenile fish. The hypothesis was accepted as the Labeo Umbratus, Cyprinus carpio and Labeo capensis all have a successful spawning season. However, due to the size of the Cyprinus carpio, they would be most suited for a small scale fishery.