# Winter Break Research ###### tags: `log` --- We've searched for stuff. We found this paper: [Accurate Image Localization Based on Google Maps Street View (2010)](https://link.springer.com/chapter/10.1007/978-3-642-15561-1_19) Well this is basically what we wanted to do at first... Looking into its citations, apparently people have been doing this for a decade already. ---- > We need to determine our topic. Or at least a direction. ---- Well we've got no idea. So we reached out to ChatGPT, and here are the "random" topics provided: 1. "Developing deep learning algorithms for accurate object detection and recognition in autonomous vehicles." 2. "Investigating the use of computer vision for enhancing medical imaging and diagnosis." 3. "Exploring the potential of computer vision for detecting and preventing fraudulent activities in financial transactionImage analysis: Computer vision algorithms can be used to analyze images of financial transactions, such as checks and credit card transactions, to detect signs of tampering or counterfeiting. 4. "Designing algorithms for efficient and effective image and video compression using deep learning." 5. "Evaluating the performance of computer vision algorithms for recognizing and tracking human activity in surveillance systems." ---- : I think the third one is kinda interesting 1. Image analysis: Computer vision algorithms can be used to analyze images of financial transactions, such as checks and credit card transactions, to detect signs of tampering or counterfeiting. 2. Face recognition: Computer vision algorithms can be used to perform biometric authentication of individuals, such as through facial recognition, to detect fraudulent activity such as identity theft. 3. Video analysis: Computer vision algorithms can be used to analyze video footage of financial transactions, such as ATM transactions, to detect signs of fraud such as skimming or card cloning. 4. Object detection: Computer vision algorithms can be used to detect unusual or suspicious objects in financial transactions, such as counterfeit money or fake ID cards. ---- **Problems:** * DATA SOURCE? * Wait, how do we know if this person is gonna do robbery or not from their face lol --- 人工智慧應用於社群媒體資料分析常見有： * 憂鬱症、現代人心理健康狀況預測分析／社群中毒小孩救治 * [What drives students' online self-disclosure behaviour on social media? A hybrid SEM and artificial intelligence approach](https://www.inderscienceonline.com/doi/abs/10.1504/IJMC.2020.105847) * [Social media users and cybersecurity awareness: predicting self-disclosure using a hybrid artificial intelligence approach](https://www.emerald.com/insight/content/doi/10.1108/K-05-2021-0377/full/html) * [Artificial intelligence applications in social media for depression screening: A systematic review protocol for content validity processes](https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0259499) ---- * 有關討論機器人或人工智能 * [Arming the public with artificial intelligence to counter social bots](https://onlinelibrary.wiley.com/doi/abs/10.1002/hbe2.115) * [Artificial Intelligence Ethics: Governance through Social Media](https://ieeexplore.ieee.org/abstract/document/9032907) ---- * 災難及時與後續不同階段影響狀況管理與分析 * [AIDR: artificial intelligence for disaster response](https://dl.acm.org/doi/abs/10.1145/2567948.2577034) * [Emergent Use of Artificial Intelligence and Social Media for Disaster Management](https://link.springer.com/chapter/10.1007/978-981-16-5348-3_15) ---- * [Humanitarian health computing using artificial intelligence and social media: A narrative literature review](https://www.sciencedirect.com/science/article/abs/pii/S1386505618300212)包含自然災害、疾病爆發和衝突，協助人道主義健康援助，聽起來很高大上 * [A near-real-time global landslide incident reporting tool demonstrator using social media and artificial intelligence](https://www.sciencedirect.com/science/article/pii/S2212420922003089)偷看你家山坡 ---- * 假新聞== * [ARTIFICIAL INTELLIGENCE, SOCIAL MEDIA, AND FAKE NEWS:IS THIS THE END OF DEMOCRACY?](https://westminsterresearch.westminster.ac.uk/download/cf99c72689c33eacd4e7cc8ad5680d1c0e939e2a2b9d3ffff86b6693c213a815/4794770/2B799F5AB7A14F628F90BFC458B38029.pdf#page=165) ---- * 量化客戶需求行銷 * [Supporting customer-oriented marketing with artificial intelligence: automatically quantifying customer needs from social media ](https://link.springer.com/article/10.1007/s12525-019-00351-0) ---- * 電影分析 * [Machine learning in films: an approach towards automation in film censoring](https://link.springer.com/article/10.1007/s42488-019-00016-9) * [A hybrid CNN-LSTM model for improving accuracy of movie reviews sentiment analysis](https://www.researchgate.net/profile/Basit-Raza/publication/333706654_A_Hybrid_CNN-LSTM_Model_for_Improving_Accuracy_of_Movie_Reviews_Sentiment_Analysis/links/5d00b1eb299bf13a384ea950/A-Hybrid-CNN-LSTM-Model-for-Improving-Accuracy-of-Movie-Reviews-Sentiment-Analysis.pdf) ---- 痾 一些想法 * AI工具／大眾使用／社群傳播／影響 * 創意 * 討論串評分 * 高端討論：專有名詞、具邏輯性、多元論點 * 低端討論：激烈負面詞彙 * Analyze whether the picture or text is generated by AI?? (So we're using ai to test ai hmmmm)似乎太難 但超需要 找不太到論文 (But even human aren't capable of this...) 路邊有什麼 * 建築 * 交通 * 行人安全規劃 * 人流／車流 * 犯罪 * 攤販 * [Detecting the city-scale spatial pattern of the urban informal sector by using the street view images: A street vendor massive investigation case](https://www.sciencedirect.com/science/article/abs/pii/S0264275122003985) * 造成問題 * 影響都市樣貌 * 交通堵塞 * 擾亂安全／汙染環境 * 街邊非正式從業者空間調查 * 非正規經濟常見職業 * 聚集因素 * 提供治理政策改進／實施提供建議 * [Uncovering inconspicuous places using social media check-ins and street view images](https://www.sciencedirect.com/science/article/pii/S0198971519306003)