This dissertation addresses data manipulation in collaborative research systems, including what data should be stored, the operations to be performed on that data, and a programming interface to effect this manipulation. Collaborative research systems are discussed, and requirements for next-generation systems are specified, incorporating a range of emerging technologies including multimedia storage and presentation, expert systems, and object-oriented database management systems. A detailed description of a generic query processor constructed specifically for one collaborative research system is given, and its applicability to next-generation systems and emerging technologies is examined. Chapter 1 discusses the Arizona Analyst Information System (AAIS), a successful collaborative research system being used at the University of Arizona and elsewhere. Chapter 2 describes the generic query processing approach used in the AAIS, as an efficient, nonprocedural, high-level programmer interface to databases. Chapter 3 specifies requirements for next-generation collaborative research systems that encompass the entire research cycle for groups of individuals working on related topics over time. These requirements are being used to build a next-generation collaborative research system at the University of Arizona called CARAT, for Computer Assisted Research and Analysis Tool. Chapter 4 addresses the underlying data management systems in terms of the requirements specified in Chapter 3. Chapter 5 revisits the generic query processing approach used in the AAIS, in light of the requirements of Chapter 3, and the range of data management solutions described in Chapter 4. Chapter 5 demonstrates the generic query processing approach as a viable one, for both the requirements of Chapter 3 and the DBMSs of Chapter 4. The significance of this research takes several forms. First, Chapters 1 and 3 provide detailed views of a current collaborative research system, and of a set of requirements for next-generation systems based on years of experience both using and building the AAIS. Second, the generic query processor described in Chapters 2 and 5 is shown to be an effective, portable programming language to database interface, ranging across the set of requirements for collaborative research systems as well as a number of underlying data management solutions.

Wu Yuen-Ting. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2005. / Includes bibliographical references (leaves 88-90). / Abstracts in English and Chinese. / Chapter 1. --- Introduction --- p.1 / Chapter 1.1 --- Background --- p.1 / Chapter 1.2 --- Research Objective --- p.4 / Chapter 1.3 --- Contribution --- p.5 / Chapter 1.4 --- Structure of this thesis --- p.6 / Chapter 2. --- Literature Review --- p.7 / Chapter 2.1 --- Genetic Algorithms --- p.7 / Chapter 2.1.1 --- Pre-processing step --- p.8 / Chapter 2.1.2 --- Generation of initial population --- p.10 / Chapter 2.1.3 --- Crossover --- p.11 / Chapter 2.1.4 --- Mutation --- p.12 / Chapter 2.1.5 --- Selection --- p.12 / Chapter 2.1.6 --- Results of GA on Container Loading Algorithm --- p.13 / Chapter 2.2 --- Layering Approach --- p.13 / Chapter 2.3 --- Mixed Integer Programming --- p.14 / Chapter 2.4 --- Tabu Search Algorithm --- p.15 / Chapter 2.5 --- Other approaches --- p.16 / Chapter 2.5.1 --- Block arrangement --- p.17 / Chapter 2.5.2 --- Multi-Directional Building Growing algorithm --- p.17 / Chapter 2.6 --- Comparisons of different container loading algorithms --- p.18 / Chapter 3. --- Principle of LFF Algorithm --- p.8 / Chapter 3.1 --- Definition of Flexibility --- p.8 / Chapter 3.2 --- The Less Flexibility First Principle (LFFP) --- p.23 / Chapter 3.3 --- The 2D LFF Algorithm --- p.25 / Chapter 3.3.1 --- Generation of Corner-Occupying Packing Move (COPM) --- p.26 / Chapter 3.3.2 --- Pseudo-packing and the Greedy Approach --- p.27 / Chapter 3.3.3 --- Real-packing --- p.30 / Chapter 3.4 --- Achievement of 2D LFF --- p.31 / Chapter 4. --- Error Bound Analysis on 2D LFF --- p.21 / Chapter 4.1 --- Definition of Error Bound --- p.21 / Chapter 4.2 --- Cause and Analysis on Unsatisfactory Results by LFF --- p.33 / Chapter 4.3 --- Formal Proof on Error Bound --- p.39 / Chapter 5. --- LFF for Container Loading Problem --- p.33 / Chapter 5.1 --- Problem Formulation and Term Definitions --- p.48 / Chapter 5.2 --- Possible Problems to be solved --- p.53 / Chapter 5.3 --- Implementation in Container Loading --- p.54 / Chapter 5.3.1 --- The Basic Algorithm --- p.56 / Chapter 5.4 --- A Sample Packing Scenario --- p.62 / Chapter 5.4.1 --- Generation of COPM list --- p.63 / Chapter 5.4.2 --- Pseudo-packing and the greedy approach --- p.66 / Chapter 5.4.3 --- Update of corner list --- p.69 / Chapter 5.4.4 --- Real-Packing --- p.70 / Chapter 5.5 --- Ratio Approach: A Modification to LFF --- p.70 / Chapter 5.6 --- LFF with Tightness Measure: CPU time Cut-down --- p.75 / Chapter 5.7 --- Experimental Results --- p.77 / Chapter 5.7.1 --- Comparison between LFF and LFFR --- p.77 / Chapter 5.7.2 --- "Comparison between LFFR, LFFT and other algorithms" --- p.78 / Chapter 5.7.3 --- Computational Time for different algorithms --- p.81 / Chapter 5.7.4 --- Conclusion of the experimental results --- p.83 / Chapter 6. --- Conclusion --- p.85 / Bibiography --- p.88

無線通信和移動技術已經從根本上改變了人和人之間相互通信的方式，隨著像智能手機這樣功能強大的移動設備不斷普及，現在我們有更多的機會去監測用戶的運動狀態、社交情況和地理位置等信息。近期，越來越多的基於智能手機的傳感研究相繼出現，這些研究利用智能手機中的多種傳感、定位以及近距離無線設備來識別手機用戶當前的活動狀態和周圍環境。一些可識別用戶活動狀態和監控身體健康狀況的移動應用程式已經被開發并投入使用。儘管如此，當前大部份關於智能手機的研究忽視了這樣一個問題，智能手機是用戶與外界通信的一個指令中心。移動用戶可以使用智能手機用很多種方式聯繫他們的朋友，例如打電話、發送短消息、電子郵件、或者通過即時通信程序或者社交網絡，這些多渠道的通信方式和人與人之間面對面的交流一樣重要，因此智能手機是識別用戶和其他聯繫人的社會關係的關鍵。在本論文中，我們提出用智能手機中 獨有的多渠道用戶通信數據來對用戶的的社會關係進行分類。作為我們研究的開始，我們生成人工的通信數據並且用社交矩陣來為人與人之間的通信建立模型，這也幫助我們測試了很多可以應用在此類問題的數據挖掘算法。接下來，我們通過招募真實用戶來採集他們的各種社交通信數據，這些數據包括手機通話記錄、電子郵件、社交網絡（Facebook和Renren）和面對面的交流。通過在社交矩陣上應用不同的分類算法，我們發現SVM的分類性能要超過KNN和決策樹算法，SVM對於社會關係的分類準確率可以達到82.4%。我們也對來自不同渠道的通信數據進行了比較，最終發現來自社交網絡和面對面交流的數據在社交關係分類中起更大的作用。另外，我們通過使用降低維度算法可以把社交矩陣從65維度映射到9維度，關係分類的準確率卻沒有明顯降低，在降低維度的過程中我們也可以提取出用戶主要的通信特徵，從而更好地解釋社會關係分類的原理。最後，我們也應用了CUR矩陣分解算法從社交矩陣65列中選出13列建立新的社交矩陣，關係分類的準確率從82.4%降低到77.7%，但是我們卻可以通過 CUR來選擇合適的傳感器抽樣採集頻率，這樣可以在利用手機採集數據過程中節省更多手機電量。 / Wireless Communications and Mobile Computing have fundamentally changed the way people interact and communicate with each other. The proliferation of powerful and programmable mobile devices, smartphones in particular, has offered an unprecedented opportunity to continuously monitor the physical, social and geographical activities of their users. Recently, much research has been done on smartphone-based sensing which leverages the rich set of sensing, positioning and short-range radio capabilities of the smartphones to identify the context of user activities and ambient environment conditions. Mobile applications for personal behavior tracking and physical wellness monitoring have also been developed. Despite that, most of the existing work in mobile sensing has neglected the role of smartphone as the command-center of the user’s communications with the outside world. As mobile users contact their friends via phone, SMS, emails, instant messaging, and other online social-networking applications, these multi-modal communication activities are as equally important as physical activities in proling one’s life. They also hold the key to understand the user’s social relationship with other people of interest. In this thesis, we propose to use the unique multi-model interaction data from smartphone to classify social relationships. To jump start our study, we generate articial interaction data and build social interaction matrix to modeMl the interaction between people. This also helps us in testing a wide range of data mining analysis techniques for this type of problem. We then carry out a social interaction data collection campaign with a group of real users to obtain real-life multi-modal communication data, e.g., phone call, Email, online social network(Facebook and Renren), and physical location/proximity. After applying different classification algorithms on social interaction matrix, we find that SVM outperforms KNN and decision tree algorithms, with a classification accuracy of 82.4% (the accuracies of KNN and decision tree are 79.9% and 77.6%, respectively). We also compare the data from different interaction channels and finally find that on-line social network and location/proximity data contribute more to the overall classification accuracy. Additionally, with dimensionality reduction algorithms, the social interaction matrix can be embedded from 65 to 9 dimensional space while preserving the high classification accuracy and we also get principle interaction features as by-product. At last, we use CUR decomposi¬tion to select 13 out of the 65 features in the social interaction matrix. The classification accuracy drops from 82.4% to 77.7% after CUR decomposition. But it can help to determine the right sensor sampling frequency so as to enhance energy efficiency for social data collection. / Detailed summary in vernacular field only. / Sun, Deyi. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2012. / Includes bibliographical references (leaves 90-96). / Abstracts also in Chinese. / Chapter 1 --- Introduction --- p.1 / Chapter 2 --- Research Background --- p.7 / Chapter 2.1 --- Related work of social relationship analysis --- p.7 / Chapter 2.1.1 --- Community detection in social network --- p.8 / Chapter 2.1.2 --- Social influence analysis --- p.10 / Chapter 2.1.3 --- Modeling social interaction data --- p.10 / Chapter 2.1.4 --- Social relationship prediction --- p.12 / Chapter 2.2 --- Classification methodologies --- p.14 / Chapter 2.2.1 --- Algorithms for social relationship classification --- p.14 / Chapter 2.2.2 --- Algorithms for dimensionality reduction --- p.16 / Chapter 3 --- Problem Formulation of Relationship Classicification --- p.19 / Chapter 3.1 --- Multi-modal data in smartphones --- p.20 / Chapter 3.2 --- Formulation of relationship classification problem --- p.21 / Chapter 3.3 --- Refinement of feature definition and energy efficiency --- p.27 / Chapter 3.4 --- Chapter summary --- p.28 / Chapter 4 --- Social Interaction Data Acquisition --- p.30 / Chapter 4.1 --- Social interaction data collection campaign overview --- p.31 / Chapter 4.2 --- Format of raw interaction data --- p.33 / Chapter 4.3 --- Building social interaction matrix with real-life interaction data --- p.37 / Chapter 4.4 --- Chapter summary --- p.43 / Chapter 5 --- Statistical Analysis of Social Interaction Data --- p.45 / Chapter 5.1 --- Coverage of social interaction data --- p.46 / Chapter 5.2 --- Social relationships statistics --- p.48 / Chapter 5.3 --- Social relationship interaction patterns --- p.52 / Chapter 5.4 --- Chapter summary --- p.59 / Chapter 6 --- Automatic Social Relationship Classification Based on Smartphone Interaction Data --- p.61 / Chapter 6.1 --- Comparison of different classification algorithms --- p.62 / Chapter 6.2 --- Advantages of multi-modal interaction data --- p.65 / Chapter 6.3 --- Comparison of interaction data in different communication channels --- p.67 / Chapter 6.4 --- Dimensionality reduction on social interaction data --- p.72 / Chapter 6.5 --- Discussions in deploying social relationship classification application --- p.80 / Chapter 6.5.1 --- Considerations of user privacy --- p.81 / Chapter 6.5.2 --- Saving smartphone resources --- p.82 / Chapter 6.6 --- Chapter summary --- p.83 / Chapter 7 --- Conclusion and Future Work --- p.86 / Bibliography --- p.90

by Tam Chi-Fai. / Thesis (M.Phil.)--Chinese University of Hong Kong, 1999. / Includes bibliographical references (leaves 87-88). / abstract --- p.I / table of content --- p.II / list of figures --- p.V / acknowledgments --- p.VII / Chapter chapter 1 --- introduction --- p.1 / Chapter 1.1 --- Two Stage Operations Planning --- p.1 / Chapter 1.2 --- Iterative Activities in the Two Stage Planning Approach --- p.3 / Chapter 1.3 --- Expert Decision Support System for Two Stage Planning --- p.4 / Chapter 1.4 --- Scope of the Study --- p.5 / Chapter 1.5 --- Organization of the Thesis --- p.6 / Chapter chapter 2 --- literature review --- p.7 / Chapter 2.1 --- Network Design for Air Express Service --- p.7 / Chapter 2.2 --- Integrative Use of Optimization and Simulation Model --- p.8 / Chapter 2.3 --- Expert System & Decision Support System --- p.11 / Chapter 2.3.1 --- Expert System --- p.11 / Chapter 2.3.2 --- Decision Support System --- p.13 / Chapter 2.3.3 --- ES / DSS Integration --- p.14 / Chapter chapter 3 --- research methodology --- p.19 / Chapter 3.1 --- Review on DSS / ES Integration --- p.19 / Chapter 3.2 --- System Design --- p.20 / Chapter 3.3 --- Prototyping --- p.22 / Chapter 3.4 --- Analysis and Evaluation --- p.23 / Chapter chapter 4 --- system architecture and knowledge modeling --- p.24 / Chapter 4.1 --- Architecture Overview --- p.24 / Chapter 4.1.1 --- System Architecture and Interactions --- p.26 / Chapter 4.1.2 --- Decision Support System --- p.27 / Chapter 4.1.3 --- Expert System --- p.32 / Chapter 4.2 --- System Operations --- p.35 / Chapter 4.2.1 --- Operations Flow --- p.35 / Chapter chapter 5 --- case study and prototyping --- p.38 / Chapter 5.1 --- Case Background --- p.38 / Chapter 5.1.1 --- The Service Network --- p.38 / Chapter 5.1.2 --- Objectives of the Project --- p.40 / Chapter 5.1.3 --- Network Design Methodology --- p.41 / Chapter 5.2 --- Iterative Network Planning --- p.49 / Chapter 5.2.1 --- Multi-period Network Planning Feedback --- p.50 / Chapter 5.2.2 --- Feedback in Validation and Evaluation --- p.51 / Chapter 5.3 --- The System Prototype --- p.57 / Chapter 5.3.1 --- Data Management and Model Manipulation --- p.57 / Chapter 5.3.2 --- Intelligent Guidance for the Iterations --- p.65 / Chapter chapter 6 --- evaluation and analysis --- p.75 / Chapter 6.1 --- Test Scenario for Network Planning --- p.75 / Chapter 6.1.1 --- Consultation Process --- p.75 / Chapter 6.1.2 --- Consultation Results --- p.78 / Chapter 6.2 --- Effectiveness of EDSS in Network Planning --- p.81 / Chapter 6.3 --- Generalized Advancement and Limitation --- p.82 / Chapter chapter 7 --- conclusion --- p.85 / bibliography --- p.87 / appendices --- p.89

Genome-wide association studies (GWAS) have identified thousands of genetic variants associated with hundreds of human traits. Yet the common variant model tested by traditional GWAS only provides an incomplete explanation for the known genetic heritability of many traits. Many divergent methods have been proposed to address the shortcomings of GWAS, including most notably the extension of association methods into rarer variants through whole exome and whole genome sequencing. GWAS methods feature numerous simplifications designed for feasibility and ease of use, as opposed to statistical rigor. Furthermore, no systematic quantification of the performance of GWAS across all traits exists. Beyond improving the utility of data that already exist, a more thorough understanding of the performance of GWAS on common variants may elucidate flaws not in the method but rather in its implementation, which may pose a continued or growing threat to the utility of rare variant association studies now underway. This thesis focuses on systematic evaluation and incremental improvement of GWAS modeling. We collect a rich dataset containing standardized association results from all GWAS conducted on quantitative human traits, finding that while the majority of published significant results in the field do not disclose sufficient information to determine whether the results are actually valid, those that do replicate precisely in concordance with their statistical power when conducted in samples of similar ancestry and reporting accurate per-locus sample sizes. We then look to the inability of effectively all existing association methods to handle missingness in genetic data, and show that adapting missingness theory from statistics can both increase power and provide a flexible framework for extending most existing tools with minimal effort. We finally undertake novel variant association in a schizophrenia cohort from a bottleneck population. We find that the study itself is confounded by nonrandom population sampling and identity-by-descent, manifesting as batch effects correlated with outcome that remain in novel variants after all sample-wide quality control. On the whole, these results emphasize both the past and present utility and reliability of the GWAS model, as well as the extent to which lessons from the GWAS era must inform genetic studies moving forward.

This dissertation adopts an interdisciplinary approach to the field of law and artificial intelligence. It argues that the conceptual structuring of legal knowledge within an appropriate theoretical framework is of primary importance when building knowledge-based systems. While technical considerations also play a role, they must take second place to an in-depth understanding of the law. Two alternative methods of structuring legal knowledge in very different domains are used to explore the thesis. A deep-structure approach is used on nervous shock, a rather obscure area of the law of negligence. A script-based method is applied to impaired driving, a well-known part of the criminal law. A knowledge-based system is implemented in each area. The two systems, Nervous Shock Advisor (NSA) and Impaired Driving Advisor (IDA), and the methodologies they embody, are described and contrasted. In light of the work undertaken, consideration is given to the feasibility of lawyers without much technical knowledge using general-purpose tools to build knowledge-based systems for themselves.

Bin packing is a problem with many applications in various industries. This thesis addresses a specific instance of the this problem, known as the Container Packing problem. Special attention is paid to the Pallet Loading problem which is a restricted sub-problem of the general Container Packing problem. Since the Bin Packing problem is NP-complete, it is customary to apply a heuristic measure in order to approximate solutions in a reasonable amount of computation time rather than to attempt to produce optimal results by applying some exact algorithm. Several heuristics are examined for the problems under consideration, and the results produced by each are shown and compared where relevant. / Thesis (M.Sc.)-University of Natal, Durban, 1991.

This dissertation adopts an interdisciplinary approach to the field of law and artificial intelligence. It argues that the conceptual structuring of legal knowledge within an appropriate theoretical framework is of primary importance when building knowledge-based systems. While technical considerations also play a role, they must take second place to an in-depth understanding of the law. Two alternative methods of structuring legal knowledge in very different domains are used to explore the thesis. A deep-structure approach is used on nervous shock, a rather obscure area of the law of negligence. A script-based method is applied to impaired driving, a well-known part of the criminal law. A knowledge-based system is implemented in each area. The two systems, Nervous Shock Advisor (NSA) and Impaired Driving Advisor (IDA), and the methodologies they embody, are described and contrasted. In light of the work undertaken, consideration is given to the feasibility of lawyers without much technical knowledge using general-purpose tools to build knowledge-based systems for themselves. / Graduate and Postdoctoral Studies / Graduate

Publicly available datasets in health science are often large and observational, in contrast to experimental datasets where a small number of data are collected in controlled experiments. Variables' causal relationships in the observational dataset are yet to be determined. However, there is a significant interest in health science to discover and analyze causal relationships from health data since identified causal relationships will greatly facilitate medical professionals to prevent diseases or to mitigate the negative effects of the disease. Recent advances in Computer Science, particularly in Bayesian networks, has initiated a renewed interest for causality research. Causal relationships can be possibly discovered through learning the network structures from data. However, the number of candidate graphs grows in a more than exponential rate with the increase of variables. Exact learning for obtaining the optimal structure is thus computationally infeasible in practice. As a result, heuristic approaches are imperative to alleviate the difficulty of computations. This research provides effective and efficient learning tools for local causal discoveries and novel methods of learning causal structures with a combination of background knowledge. Specifically in the direction of constraint based structural learning, polynomial-time algorithms for constructing causal structures are designed with first-order conditional independence. Algorithms of efficiently discovering non-causal factors are developed and proved. In addition, when the background knowledge is partially known, methods of graph decomposition are provided so as to reduce the number of conditioned variables. Experiments on both synthetic data and real epidemiological data indicate the provided methods are applicable to large-scale datasets and scalable for causal analysis in health data. Followed by the research methods and experiments, this dissertation gives thoughtful discussions on the reliability of causal discoveries computational health science research, complexity, and implications in health science research.

Bibliography : leaves 196-200. / Thesis (Ph. D.)--Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science, 1977. / Microfiche copy available in the Institute Archives and Barker Engineering Library. / by Loren Kerry Platzman. / Ph.D.