近幾年來，有關地理資訊的網頁搜尋越來越受到重視。傳統的網頁搜尋引擎無法反應使用者查詢和網頁文件之間的地理關聯性。在一些情況下，我們希望網路搜尋引擎能夠考慮使用者查詢與網頁文件間的地理相關性，以提升搜尋的準確度。 我們的研究透過包圍矩形模型(Bounding Rectangle Model；BR Model)以搜尋與使用者查詢之地理相關程度較高的網頁文件。 使用者僅需輪入文字的查詢，即能得到相符結果的網頁文件。首先，我們建立一個地名辭典以找出使用者查詢與網頁文件內出現的地名及空間資料，接著我們利用空間資料建立空間索引項(spatial index term)集合，用來表示使用者查詢與網頁文件內的地理範圍，最後再透過使用者查詢與網頁文件的空間索引項集合計算兩者之間的地理相似程度，以找出與使用者查詢有較高地理關聯性的網頁文件。 此篇論文的貢獻在於我們提一套完整資訊檢索模型架構的方法，分析使用者查詢與網頁文件之間的地理關聯性，使用者藉由輸入文字查詢即能得到相符地理關聯性的網頁文件。 / Geographic web search becomes increasingly popular in recent years. Traditional web search engine, such as Google and Yahoo, can not accommodate geographic relevance between user queries and internet documents. Hence, they can not retrieve geographic related information from user queries. However, in many cases, the geographic relevance between user queries and internet documents could enhance the accuracy of this type of searches. In this thesis, we propose a mechanism that uses the Bounding Rectangle Model (BR Model) to retrieve geographic relevant internet documents in response to user queries. Users provide only the conventional input queries (keywords) and our search engine will return the geographic relevant results. Our method can be classified into the following three steps. In the first step, we create a gazetteer and use it to relate the user query’s geographic terms in internet documents. In the next step, we use the spatial data to build a set of spatial index terms that represents the geographic scope of user query and internet documents. And then we use these spatial index terms to calculate degree of geographic similarity between user query and internet documents to identify highly relevant geographic internet documents. We implemented a prototype search engine using our approach. The experiment results show that we can successfully retrieve geographic relevant data through this mechanism and provide more accurate search results.

面對全球資訊網(WWW)應用蓬勃發展，網際網路上充斥著各種類型的資訊資源。而如何有效地管理及檢索這些資料，就成為當前資訊管理的重要課題之一。在發掘資訊時，最常用的便是搜尋引擎，透過比對查詢字串與索引表格(index table)，找出相關的網頁文件，並回傳結果。但因為網頁描述資訊的不足，導致其回覆大量不相關的查詢結果，浪費使用者許多時間。 為了解決上述問題，就資訊搜尋的角度而言，本研究提出以文字開採技術實際分析網頁內容，並將其轉換成維度資訊來描述，再以多維度資料庫方式儲存的架構。做為改進現行資訊檢索的參考架構。 就資訊描述的角度，本研提出採用RDF(Resource Description Framework)來描述網頁Metadata的做法。透過此通用的資料格式來描述網路資源，做為跨領域使用、表達資訊的標準，便於Web應用程式間的溝通。期有效改善現行網際網路資源描述之缺失，大幅提昇搜尋之品質。

隨著GIS的發展，地圖定位成為空間查詢中極為普遍的行為。一般地圖定位大多透過地址來進行，但是在缺乏地址的情況之下，進行地圖上之定位變成極為困難之事。 本論文嘗試對手繪地圖在真實地圖上進行定位，我們提出了一套機制，使用者可以隨意地以手繪方式繪製街道圖與地標，透過我們提出的方法，即可自動地在真實的地圖上進行定位。 論文中，我們使用相鄰街廓中之地標配置與相鄰之交叉路口之地標配置等變數組成的表示法來描述地圖。我們將手繪地圖與真實地圖轉換成這些表示法，並透過字串編輯距離、圖同構等關係來比較手繪地圖與真實地圖之相似度，從而對手繪地圖進行定位。 實作中，我們挑選了幾處真實場景在台北市地圖中進行比對並觀察其結果。系統採用之地標包括政府機構(如派出所、消防隊、區公所等)、學校、醫院等資料。在實驗中，應用這套表示法可成功的定位出使用者所輸入之各場景所在位置。另外，透過控制相似度門檻值，我們可以調整辨識之精確度，不至於錯失可能之定位結果。 / As the widely spread of the GIS applications, map localization becomes one of the most important features in the spatial information retrieval. Normally, map localization is done through street addresses. Without this information, map localization becomes very difficult. In this research, we are trying to do map localization using hand drawing maps. We proposed a mechanism that can localize the user's drawing map in the reference map automatically. Our approaches use the landmark configurations of the adjacent street blocks as well as the landmark configurations of the adjacent street intersections as the descriptors in representing a map. The user's hand drawn maps and the reference maps are converted into these representations. The string editing distances and graph isomorphism are used in determining the similarities between the hand drawn map and the reference map. The map localization can be done by comparing these similarities. We used various real scenes in Taipei City to verify our systems. The landmarks we used including police offices, fire stations, county offices, schools and hospitals, etc. The experimental results shown that our system can localize the user's input successfully. Moreover, by controlling thresholds in similarity analysis, we can adjust the system's accuracy that reduces possibility of miss localizations.

以往的音樂資訊檢索方法多使用歌詞、曲風、演奏的樂器或一段音頻訊號來當作查詢的媒介，然而，在某些情況下，使用者沒有辦法清楚描述他們想要尋找的歌曲，如：情境式的音樂檢索。本論文提出了一種基於圖像的情境式音樂資訊檢索方法，可以透過輸入圖片來找尋相應的音樂。此方法中我們使用了卷積神經網絡（Convolutional Neural Network）技術來處理圖片，將其轉為低維度的表示法。為了將異質性的多媒體訊息映射到同一個向量空間，資訊網路表示法學習（Network Embedding）技術也被使用，如此一來，可以使用距離計算找回和輸入圖片有關的多媒體訊息。我們相信這樣的方法可以改善異質性資訊間的隔閡（Heterogeneous Gap），也就是指不同種類的多媒體檔案之間無法互相轉換或詮釋。在實驗與評估方面，首先利用從歌詞與歌名得到的關鍵字來搜尋大量圖片當作訓練資料集，接著實作提出的檢索方法，並針對實驗結果做評估。除了對此方法的有效性做測試外，使用者的回饋也顯示此檢索方法和其他方法相比是有效的。同時我們也實作了一個網路原型，使用者可以上傳圖片並得到檢索後的歌曲，實際的使用案例也將在本論文中被展示與介紹。 / Listening to music is indispensable to everyone. Music information retrieval systems help users find their favorite music. A common scenario of music information retrieval systems is to search songs based on user's query. Most existing methods use descriptions (e.g., genre, instrument and lyric) or audio signal of music as the query; then the songs related to the query will be retrieved. The limitation of this scenario is that users might be difficult to describe what they really want to search for. In this paper, we propose a novel method, called ``image2song,'' which allows users to input an image to retrieve the related songs. The proposed method consists of three modules: convolutional neural network (CNN) module, network embedding module, and similarity calculation module. For the processing of the images, in our work the CNN is adopted to learn the representations for images. To map each entity (e.g., image, song, and keyword) into a same embedding space, the heterogeneous representation is learned by network embedding algorithm from the information graph. This method is flexible because it is easy to join other types of multimedia data into the information graph. In similarity calculation module, the Euclidean distance and cosine distance is used as our criterion to compare the similarity. Then we can retrieve the most relevant songs according to the similarity calculation. The experimental results show that the proposed method has a good performance. Furthermore, we also build an online image-based music information retrieval prototype system, which can showcase some examples of our experiments.

偵測新興議題對於研究者而言是一個相當重要的問題，研究者如何在有限的時間和資源下探討同一領域內的新興議題將比解決已經成熟的議題帶來較大的貢獻和影響力。本研究將致力於協助研究者偵測新興且具有未來潛力的研究議題，並且從學術論文中探究對於研究者在做研究中有幫助的學術智慧。在搜尋可能具有研究潛力的議題時，我們假設具有研究潛力的議題將會由同一領域中較具有影響力的作者和刊物發表出，因此本研究使用貝式估計的方法去推估同一領域中相關的研究者和學術刊物對於該領域的影響力，進而藉由這些資訊可以找出未來具有潛力的新興候選議題。此外就我們所知的議題偵測文獻中對於認定一個議題是否已經趨於成熟或者是否新穎且具有研究的潛力仍然缺乏有效及普遍使用的衡量工具，因此本研究試圖去發展有效的衡量工具以評估議題就本身的發展生命週期是否仍然具有繼續投入的學術價值。 本研究從許多重要的資料庫中挑選了和資料探勘和資訊檢索相關的論文並且驗證這些在會議論文中所涵蓋的議題將會領導後續幾年期刊論文相似的議題。此外本研究也使用了一些已經存在的演算法並且結合這些演算法發展一個檢測的流程幫助研究者去偵測學術論文中的領導趨勢並發掘學術智慧。本研究使用貝式估計的方法試圖從已經發表的資訊和被引用的資訊來建構估計作者和刊物的影響力的事前機率與概似函數，並且計算出同一領域重要的作者和刊物的影響力，當這些作者和刊物的論文發表時將會相對的具有被觀察的價值，進而檢定這些新興候選議題是否會成為新興議題。而找出的重要研究議題雖然已經縮小探索的範圍，但是仍然有可能是發展成熟的議題使得具有影響力的作者和刊物都必須討論，因此需要評估議題未來潛力的指標或工具。然而目前文獻中對於評估議題成熟的方法僅著重在議題的出現頻率而忽視了議題的新穎度也是重要的指標，另一方面也有只為了找出新議題並沒有顧及這個議題是否具有未來的潛力。更重要的是單一的使用出現頻率的曲線只能在議題已經成熟之後才能確定這是一個重要的議題，使得這種方法成為落後的指標。 本研究試圖提出解決這些困境的指標進而發展成衡量新興議題潛力的方法。這些指標包含了新穎度指標、發表量指標和偵測點指標，藉由這些指標和曲線可以在新興議題的偵測中提供更多前導性的資訊幫助研究者去建構各自領域中新興議題的偵測標準。偵測點所代表的意義並非這個議題開始新興的正確日期，它代表了這個議題在自己發展的生命週期上最具有研究的潛力和價值的時間點，因此偵測點會根據後來的蓬勃發展而在時間上產生遞延的結果，這表示我們的指標可以偵測出議題生命力的延續。相對於傳統的次數分配曲線可以看出議題的崛起和衰退，本研究的發表量指標更能以生命週期的概念去看出議題在各個時間點的發展潛力。本研究希望從這些過程中所發現的學術智慧可以幫助研究者建構各自領域的議題偵測標準，節省大量人力與時間於探究新興議題。本研究所提出的新方法不僅可以解決影響因子這個指標的缺點，此外還可以使用作者和刊物的影響力去針對一個尚未累積任何索引次數的論文進行潛力偵測，解決Google 學術搜尋目前總是在論文已經被很多檢索之後才能確定論文重要性的缺點，學者總是希望能夠領先發現重要的議題或論文。然而，我們以議題為導向的檢索方法相信可以更確實的滿足研究者在搜尋議題或論文上的需求。 / This research presents endeavors that seek to identify the emerging topics for researchers and pinpoint research intelligence via academic papers. It is intended to reveal the connection between topics investigated by conference papers and journal papers which can help the research decrease the plenty of time and effort to detect all the academic papers. In order to detect the emerging research topics the study uses the Bayesian estimation approach to estimate the impact of the authors and publications may have on a topic and to discover candidate emerging topics by the combination of the impact authors and publications. Finally the research also develops the measurement tools which could assess the research potential of these topics to find the emerging topics. This research selected huge of papers in data mining and information retrieval from well-known databases and showed that the topics covered by conference papers in a year often leads to similar topics covered by journal papers in the subsequent year and vice versa. This study also uses some existing algorithms and combination of these algorithms to propose a new detective procedure for the researchers to detect the new trend and get the academic intelligence from conferences and journals. The research uses the Bayesian estimation approach and citation analysis methods to construct the prior distribution and likelihood function of the authors and publications in a topic. Because the topics published by these authors and publications will get more attention and valuable than others. Researchers can assess the potential of these candidate emerging topics. Although the topics we recommend decrease the range of the searching space, these topics may so popular that even all of the impact authors and publications discuss it. The measurement tools or indices are need. But the current methods only focus on the frequency of subjects, and ignore the novelty of subjects which is critical and beyond the frequency study or only focus one of them and without considering the potential of the topics. Some of them only use the curve of published frequency will make the index as a backward one. This research tackles the inadequacy to propose a set of new indices of novelty for emerging topic detection. They are the novelty index (NI) and the published volume index (PVI). These indices are then utilized to determine the detection point (DP) of emerging topics. The detection point (DP) is not the real time which the topic starts to be emerging, but it represents the topic have the highest potential no matter in novelty or hotness for research in its life cycle. Different from the absolute frequent method which can really find the exact emerging period of the topic, the PVI uses the accumulative relative frequency and tries to detect the research potential timing of its life cycle. Following the detection points, the intersection decides the worthiness of a new topic. Readers following the algorithms presented this thesis will be able to decide the novelty and life span of an emerging topic in their field. The novel methods we proposed can improve the limitations of impact factor proposed by ISI. Besides, it uses the impact power of the authors and the publication in a topic to measure the impact power of a paper before it really has been an impact paper can solve the limitations of Google scholar’s approach. We suggest that the topic oriented thinking of our methods can really help the researchers to solve their problems of searching the valuable topics.