台灣正面臨整個大環境的不景氣，各產業均須擬定策略來因應環境的挑戰。在政府重視電子科技產業的情況下，傳統產業並沒有受到重視，但還是有一些廠商，能自力自強走出一片天。因此，本研究的議題是：面對世界經濟變化，傳統產業要如何才能持續生存和重新整合再出發？本研究以個案研究的方式探討企業如何運用群聚策略以提昇競爭力，希望研究結果有助於傳統產業未來的轉型。 傳統產業的業者甚多，本研究以一家玻璃製造公司進行研究，達到以下研究目的： 1.綜合分析現有玻璃產業現況及產業結構與環境變化，以利研究標的之掌握。 2.探討個案公司對於群聚策略之導入：所遇到的問題及如何解決;同時分析群聚資 源的整合方向。 3.了解傳統產業以群聚方式轉型過程中的作法，以提供其他產業之參考。 本研究整理個案公司的群聚策略與思考邏輯，發現因玻璃加工的生產技術透明度高，產業的進入障礙低，廠商無法成為價格的決定者，若採用群聚方式就能創造新的經營方向。因此，傳統產業群聚之焦點廠商如能將現有的資源加以整合，並可運用下列方式來提升競爭力： 1.聯合展示，如展覽館或博物館 2.品牌的建立和推廣 3.文化創意與藝術的結合，如玻璃廟和玻璃神轎 4.生態保育和文創的組合，如保育的推廣、白海豚、和玻璃文創 5.善用優勢分工以整合群聚成員的資源。 / In Taiwan, the whole environment is downturn because of industry changing. How do make individual industry to take strategic decision to face the challenges and struggle to survive in this timing. Traditional industries were not appealed and paid attention by government in Taiwan under government focus on High-Tech electronic industry. But some companies made good even outstanding by themselves. How do these traditional industries survive and face the whole world changing? How do they reintegrate the resource to start again? It is worth to study this topic. We use case-studying way to research. My paper theme is “In A’company case, using Clustering-Policy to enhance its competitiveness ”. We use depth interviews way to understand how these company choose solution to restruct under fierce international competition. We choose the company to research that it is glass-making manufacture afer evaluating many traditional companies. And we want to achieve the following purpose: 1. Analyze environment and structure of glass industry in many ways in order to handle my research topic. 2. To study how the case company use the Cluster-Policy strategy. Which problems did they face? How did they solve ? And we analyze the direction of cluster resource. 3. We want to understand the way they took in company changing for survival for suggesting to other industry. The following list are my research results: How to integrate the resource is the key point to raise their competitiveness in traditional industry. Under limited resource, we can use the following ways to jump up. 1. Joint show - exhibition or museum 2. Brand building and brand made-TTG 3. Cultural creativeness and artistic - glass temple and glass temple palanquin (folk binding) 4. Ecological conservation and cultural and creative combinations - plus brand to promote conservation 5. Clustering Integration Division - make good use of the advantages of division of labor Through by stating the relevant operating methods, analyzing problems and ideas, we can understand the Clustering-Policy solution and thinking logic of this company taking. According to my research, we can see that the glass industry entry barriers are not difficult, by production technology and high transparency, the manufacturers are unable to be price makers, but they can use Clustering-Policy to create a new business direction.

Comme une méthode d’apprentissage automatique non supervisé, la classification automatique est largement appliquée dans des tâches diverses. Différentes méthodes de la classification ont leurs caractéristiques uniques. La classification hiérarchique, par exemple, est capable de produire une structure binaire en forme d’arbre, appelée dendrogramme, qui illustre explicitement les interconnexions entre les instances de données. Le co-clustering, d’autre part, génère des co-clusters, contenant chacun un sous-ensemble d’instances de données et un sous-ensemble d’attributs de données. L’application de la classification sur les données textuelles permet d’organiser les documents et de révéler les connexions parmi eux. Cette caractéristique est utile dans de nombreux cas, par exemple, dans les tâches de recherche d’informations basées sur la classification. À mesure que la taille des données disponibles augmente, la demande de puissance du calcul augmente. En réponse à cette demande, de nombreuses plates-formes du calcul distribué sont développées. Ces plates-formes utilisent les puissances du calcul collectives des machines, pour couper les données en morceaux, assigner des tâches du calcul et effectuer des calculs simultanément.Dans cette thèse, nous travaillons sur des données textuelles. Compte tenu d’un corpus de documents, nous adoptons l’hypothèse de «bag-of-words» et applique le modèle vectoriel. Tout d’abord, nous abordons les tâches de la classification en proposant deux méthodes, Sim_AHC et SHCoClust. Ils représentent respectivement un cadre des méthodes de la classification hiérarchique et une méthode du co-clustering hiérarchique, basé sur la proximité. Nous examinons leurs caractéristiques et performances du calcul, grâce de déductions mathématiques, de vérifications expérimentales et d’évaluations. Ensuite, nous appliquons ces méthodes pour tester l’hypothèse du cluster, qui est l’hypothèse fondamentale dans la recherche d’informations basée sur la classification. Dans de tels tests, nous utilisons la recherche du cluster optimale pour évaluer l’efficacité de recherche pour tout les méthodes hiérarchiques unifiées par Sim_AHC et par SHCoClust . Nous aussi examinons l’efficacité du calcul et comparons les résultats. Afin d’effectuer les méthodes proposées sur des ensembles de données plus vastes, nous sélectionnons la plate-forme d’Apache Spark et fournissons implémentations distribuées de Sim_AHC et de SHCoClust. Pour le Sim_AHC distribué, nous présentons la procédure du calcul, illustrons les difficultés rencontrées et fournissons des solutions possibles. Et pour SHCoClust, nous fournissons une implémentation distribuée de son noyau, l’intégration spectrale. Dans cette implémentation, nous utilisons plusieurs ensembles de données qui varient en taille pour examiner l’échelle du calcul sur un groupe de noeuds. / As a major type of unsupervised machine learning method, clustering has been widely applied in various tasks. Different clustering methods have different characteristics. Hierarchical clustering, for example, is capable to output a binary tree-like structure, which explicitly illustrates the interconnections among data instances. Co-clustering, on the other hand, generates co-clusters, each containing a subset of data instances and a subset of data attributes. Applying clustering on textual data enables to organize input documents and reveal connections among documents. This characteristic is helpful in many cases, for example, in cluster-based Information Retrieval tasks. As the size of available data increases, demand of computing power increases. In response to this demand, many distributed computing platforms are developed. These platforms use the collective computing powers of commodity machines to parallelize data, assign computing tasks and perform computation concurrently.In this thesis, we first address text clustering tasks by proposing two clustering methods, Sim_AHC and SHCoClust. They respectively represent a similarity-based hierarchical clustering and a similarity-based hierarchical co-clustering. We examine their properties and performances through mathematical deduction, experimental verification and evaluation. Then we apply these methods in testing the cluster hypothesis, which is the fundamental assumption in cluster-based Information Retrieval. In such tests, we apply the optimal cluster search to evaluation the retrieval effectiveness of different clustering methods. We examine the computing efficiency and compare the results of the proposed tests. In order to perform clustering on larger datasets, we select Apache Spark platform and provide distributed implementation of Sim_AHC and of SHCoClust. For distributed Sim_AHC, we present the designed computing procedure, illustrate confronted difficulties and provide possible solutions. And for SHCoClust, we provide a distributed implementation of its core, spectral embedding. In this implementation, we use several datasets that vary in size to examine scalability.

Με την πραγματικότητα των υπέρογκων και ολοένα αυξανόμενων πηγών κειμένου στο διαδίκτυο, καθίστανται αναγκαία η ύπαρξη μηχανισμών οι οποίοι βοηθούν τους χρήστες ώστε να λάβουν γρήγορες απαντήσεις στα ερωτήματά τους. Η δημιουργία περιεχομένου, προσωποποιημένου στις ανάγκες των χρηστών, κρίνεται απαραίτητη σύμφωνα με τις επιταγές της συνδυαστικής έκρηξης της πληροφορίας που είναι ορατή σε κάθε ``γωνία'' του διαδικτύου. Ζητούνται άμεσες και αποτελεσματικές λύσεις ώστε να ``τιθασευτεί'' αυτό το χάος πληροφορίας που υπάρχει στον παγκόσμιο ιστό, λύσεις που είναι εφικτές μόνο μέσα από ανάλυση των προβλημάτων και εφαρμογή σύγχρονων μαθηματικών και υπολογιστικών μεθόδων για την αντιμετώπισή τους. Η παρούσα διδακτορική διατριβή αποσκοπεί στο σχεδιασμό, στην ανάπτυξη και τελικά στην αξιολόγηση μηχανισμών και καινοτόμων αλγορίθμων από τις περιοχές της ανάκτησης πληροφορίας, της επεξεργασίας φυσικής γλώσσας καθώς και της μηχανικής εκμάθησης, οι οποίοι θα παρέχουν ένα υψηλό επίπεδο φιλτραρίσματος της πληροφορίας του διαδικτύου στον τελικό χρήστη. Πιο συγκεκριμένα, στα διάφορα στάδια επεξεργασίας της πληροφορίας αναπτύσσονται τεχνικές και μηχανισμοί που συλλέγουν, δεικτοδοτούν, φιλτράρουν και επιστρέφουν κατάλληλα στους χρήστες κειμενικό περιεχόμενο που πηγάζει από τον παγκόσμιο ιστό. Τεχνικές και μηχανισμοί που σκοπό έχουν την παροχή υπηρεσιών πληροφόρησης πέρα από τα καθιερωμένα πρότυπα της υφιστάμενης κατάστασης του διαδικτύου. Πυρήνας της διδακτορικής διατριβής είναι η ανάπτυξη ενός μηχανισμού συσταδοποίησης (clustering) τόσο κειμένων, όσο και των χρηστών του διαδικτύου. Στο πλαίσιο αυτό μελετήθηκαν κλασικοί αλγόριθμοι συσταδοποίησης οι οποίοι και αξιολογήθηκαν για την περίπτωση των άρθρων νέων προκειμένου να εκτιμηθεί αν και πόσο αποτελεσματικός είναι ο εκάστοτε αλγόριθμος. Σε δεύτερη φάση υλοποιήθηκε αλγόριθμος συσταδοποίησης άρθρων νέων που αξιοποιεί μια εξωτερική βάση γνώσης, το WordNet, και είναι προσαρμοσμένος στις απαιτήσεις των άρθρων νέων που πηγάζουν από το διαδίκτυο. Ένας ακόμη βασικός στόχος της παρούσας εργασίας είναι η μοντελοποίηση των κινήσεων που ακολουθούν κοινοί χρήστες καθώς και η αυτοματοποιημένη αξιολόγηση των συμπεριφορών, με ορατό θετικό αποτέλεσμα την πρόβλεψη των προτιμήσεων που θα εκφράσουν στο μέλλον οι χρήστες. Η μοντελοποίηση των χρηστών έχει άμεση εφαρμογή στις δυνατότητες προσωποποίησης της πληροφορίας με την πρόβλεψη των προτιμήσεων των χρηστών. Ως εκ' τούτου, υλοποιήθηκε αλγόριθμος προσωποποίησης ο οποίος λαμβάνει υπ' όψιν του πληθώρα παραμέτρων που αποκαλύπτουν έμμεσα τις προτιμήσεις των χρηστών. / With the reality of the ever increasing information sources from the internet, both in sizes and indexed content, it becomes necessary to have methodologies that will assist the users in order to get the information they need, exactly the moment they need it. The delivery of content, personalized to the user needs is deemed as a necessity nowadays due to the combinatoric explosion of information visible to every corner of the world wide web. Solutions effective and swift are desperately needed in order to deal with this information overload. These solutions are achievable only via the analysis of the refereed problems, as well as the application of modern mathematics and computational methodologies. This Ph.d. dissertation aims to the design, development and finally to the evaluation of mechanisms, as well as, novel algorithms from the areas of information retrieval, natural language processing and machine learning. These mechanisms shall provide a high level of filtering capabilities regarding information originating from internet sources and targeted to end users. More precisely, through the various stages of information processing, various techniques are proposed and developed. Techniques that will gather, index, filter and return textual content well suited to the user tastes. These techniques and mechanisms aim to go above and beyond the usual information delivery norms of today, dealing via novel means with several issues that are discussed. The kernel of this Ph.d. dissertation is the development of a clustering mechanism that will operate both on news articles, as well as, users of the web. Within this context several classical clustering algorithms were studied and evaluated for the case of news articles, allowing as to estimate the level of efficiency of each one within this domain of interest. This left as with a clear choice as to which algorithm should be extended for our work. As a second phase, we formulated a clustering algorithm that operates on news articles and user profiles making use of the external knowledge base of WordNet. This algorithm is adapted to the requirements of diversity and quick churn of news articles originating from the web. Another central goal of this Ph.d. dissertation is the modeling of the browsing behavior of system users within the context of our recommendation system, as well as, the automatic evaluation of these behaviors with the obvious desired outcome or predicting the future preferences of users. The user modeling process has direct application upon the personalization capabilities that we can over on information as far as user preferences predictions are concerned. As a result, a personalization algorithm we formulated which takes into consideration a plethora or parameters that indirectly reveal the user preferences.

No description available.

With the help of new technology it has become much easier to apply for a job. Reaching out to a larger audience also results in a lot of more applications to consider when hiring for a new position. This has resulted in that many big companies uses statistical learning methods as a tool in the first step of the recruiting process. Smaller companies that do not have access to the same amount of historical and big data sets do not have the same opportunities to digitalise their recruitment process. Using topological data analysis, this thesis explore how clustering methods can be used on smaller data sets in the early stages of the recruitment process. It also studies how the level of abstraction in data representation affects the results. The methods seem to perform well on higher level job announcements but struggles on basic level positions. It also shows that the representation of candidates and jobs has a huge impact on the results. / Ny teknologi har förenklat processen för att söka arbete. Detta har resulterat i att företag får tusentals ansökningar som de måste ta hänsyn till. För att förenkla och påskynda rekryteringsprocessen har många stora företag börjat använda sig av maskininlärningsmetoder. Mindre företag, till exempel start-ups, har inte samma möjligheter för att digitalisera deras rekrytering. De har oftast inte tillgång till stora mängder historisk ansökningsdata. Den här uppsatsen undersöker därför med hjälp av topologisk dataanalys hur klustermetoder kan användas i rekrytering på mindre datauppsättningar. Den analyserar också hur abstraktionsnivån på datan påverkar resultaten. Metoderna visar sig fungera bra för jobbpositioner av högre nivå men har problem med jobb på en lägre nivå. Det visar sig också att valet av representation av kandidater och jobb har en stor inverkan på resultaten.

Doctor of Philosophy / Department of Mathematics / Andrew G. Bennett / The main objective of the study is to identify the general characteristics of groups within a typical Studio College Algebra class and then adapt aspects of the course to best suit their needs. In a College Algebra class of 1,200 students, like those at most state funded universities, the greatest obstacle to providing personalized, effective education is the anonymity of the students. Data mining provides a method for describing students by making sense of the large amounts of information they generate. Instructors may then take advantage of this expedient analysis to adjust instruction to meet their students’ needs. Using exam problem grades, attendance points, and homework scores from the first four weeks of a Studio College Algebra class, the researchers were able to identify five distinct clusters of students. Interviews of prototypical students from each group revealed their motivations, level of conceptual understanding, and attitudes about mathematics. The student groups where then given the following descriptive names: Overachievers, Underachievers, Employees, Rote Memorizers, and Sisyphean Strivers. In order to improve placement of incoming students, new student services and student advisors across campus have been given profiles of the student clusters and placement suggestions. Preliminary evidence shows that advisors have been able to effectively identify members of these groups during their consultations and suggest the most appropriate math course for those students. In addition to placement suggestions, several targeted interventions are currently being developed to benefit underperforming groups of students. Each student group reacts differently to various elements of the course and assistance strategies. By identifying students who are likely to struggle within the first month of classes, and the recovery strategy that would be most effective, instructors can intercede in time to improve performance.

Master of Science / Department of Computing and Information Sciences / David A. Gustafson William Hsu / In this study, we identify a new method of tracking motion over a sequence of images using feature point clusters. We identify and implement a system that takes as input a sequence of images and generates clusters of SIFT features using the K-Means clustering algorithm. Every time the system processes an image it compares each new cluster to the clusters of previous images, which it stores in a local cache. When at least 25% of the SIFT features that compose a cluster match a cluster in the local cache, the system uses the centroid of both clusters in order to determine the direction of travel. To establish a direction of travel, we calculate the slope of the line connecting the centroid of two clusters relative to their Cartesian coordinates in the secondary image. In an experiment using a P3-AT mobile robotic agent equipped with a digital camera, the system receives and processes a sequence of eight images. Experimental results show that the system is able to identify and track the motion of objects using SIFT feature clusters more efficiently when applying spatial outlier detection prior to generating clusters.

ITC/USA 2010 Conference Proceedings / The Forty-Sixth Annual International Telemetering Conference and Technical Exhibition / October 25-28, 2010 / Town and Country Resort & Convention Center, San Diego, California / This paper presents a method for managing a Mixed Network with multiple ground stations and Test Articles (TA) preferences. The main difference between a Ground Station (cellular) network and the over the horizon (ad-hoc) network is that the ad-hoc method has no fixed infrastructure. This paper presents the computation and performance of a clustering technique for mobile nodes within the simulated mixed network environment with multiple ground stations and users preferences for those ground stations. This includes organization for multiple ground stations and for TA's gravitating toward a ground station of their choice on the basis of service and performance.

ITC/USA 2010 Conference Proceedings / The Forty-Sixth Annual International Telemetering Conference and Technical Exhibition / October 25-28, 2010 / Town and Country Resort & Convention Center, San Diego, California / This paper presents a model for Quality of Service (QoS) management in a mix of fixed Ground Station (GS) and ad-hoc telemetry networks, and introduces an enhanced clustering scheme that jointly optimizes the performance of the network using multiple distance measures based on the location of the wireless nodes and the traffic level. It also demonstrates that a "power" performance measure is an effective tool for modeling and managing QoS in Mixed Networks. Simulation results show that significant QoS performance improvements can be obtained and maintained even under severe traffic conditions.

De nombreuses applications dans le domaine de la recherche d'information voient leur performance influencée par le modèle de représentation de documents. En effet, théoriquement, meilleure est la modélisation, meilleure sera la performance de l'application qui exploite la modélisation. Or la modélisation"parfaite" d'un document est celle qui utilise l'intégralité des théories linguistiques. Cependant, en pratique, celles-ci sont difficiles à traduire sous forme de traitements informatiques. Néanmoins, il existe des modèles qui s'appuient partiellement sur ces théories comme les modèles vectoriels classiques, les modèles par séquences de mots ou encore les chaînes lexicales. Ces précédents modèles exploitent, soit l'information syntaxique, soit l'information sémantique. D'autres modèles plus raffinés exploitent à la fois l'information syntaxique et sémantique mais sont appliqués dans un contexte spécifique. Dans cette étude, nous proposons une nouvelle modélisation de documents dans un contexte général qui considère simultanément l'information syntaxique et sémantique. Notre modèle est une combinaison de deux composantes, l'une syntaxique représentée par les arbres de dépendances syntaxiques obtenus à l'aide d'un analyseur de dépendances syntaxiques, l'autre sémantique représentée par le sens des mots dans leur contexte obtenu grâce à une méthode de désambiguïsation du sens. Dans ce modèle, chaque document est représenté par un ensemble de concepts fréquents formé de sous-arbres ayant les mêmes dépendances syntaxiques et étant sémantiquement proches. L'extraction de tels concepts est réalisée à l'aide d'un algorithme de forage d'arbres FREQT. Notre modèle sera évalué sur une application de clustering de documents des collections Reuters, 20 newsgroups et Ohsumed. La mesure du cosinus valable pour un modèle vectoriel a été utilisée pour définir la mesure de similarité entre les documents. Contrairement au modèle vectoriel, l'espace vectoriel considéré n'est pas engendré par l'ensemble des mots fréquents mais par l'ensemble des concepts fréquents. Les résultats expérimentaux obtenus montrent que l'intégration de l'information sémantique dans le modèle basé sur les arbres de dépendances syntaxiques contribue à améliorer la qualité des clusters.