Learning Euclidean Embeddings for Indexing and Classification

BoostMap is a recently proposed method for efficient approximate nearest neighbor retrieval in arbitrary non-Euclidean spaces with computationally expensive and possibly non-metric distance measures. Database and query objects are embedded into a Euclidean space, in which similarities can be rapidly measured using a weighted Manhattan distance. The key idea is formulating embedding construction as a machine learning task, where AdaBoost is used to combine simple, 1D embeddings into a multidimensional embedding that preserves a large amount of the proximity structure of the original space. This paper demonstrates that, using the machine learning formulation of BoostMap, we can optimize embeddings for indexing and classification, in ways that are not possible with existing alternatives for constructive embeddings, and without additional costs in retrieval time. First, we show how to construct embeddings that are query-sensitive, in the sense that they yield a different distance measure for different queries, so as to improve nearest neighbor retrieval accuracy for each query. Second, we show how to optimize embeddings for nearest neighbor classification tasks, by tuning them to approximate a parameter space distance measure, instead of the original feature-based distance measure.

Scalable Peer-to-Peer Indexing with Constant State

We present a distributed indexing scheme for peer to peer networks. Past work on distributed indexing traded off fast search times with non-constant degree topologies or network-unfriendly behavior such as flooding. In contrast, the scheme we present optimizes all three of these performance measures. That is, we provide logarithmic round searches while maintaining connections to a fixed number of peers and avoiding network flooding. In comparison to the well known scheme Chord, we provide competitive constant factors. Finally, we observe that arbitrary linear speedups are possible and discuss both a general brute force approach and specific economical optimizations.

Indexing Methods for Efficient Multiclass Recognition

Many real world image analysis problems, such as face recognition and hand pose estimation, involve recognizing a large number of classes of objects or shapes. Large margin methods, such as AdaBoost and Support Vector Machines (SVMs), often provide competitive accuracy rates, but at the cost of evaluating a large number of binary classifiers, thus making it difficult to apply such methods when thousands or millions of classes need to be recognized. This thesis proposes a filter-and-refine framework, whereby, given a test pattern, a small number of candidate classes can be identified efficiently at the filter step, and computationally expensive large margin classifiers are used to evaluate these candidates at the refine step. Two different filtering methods are proposed, ClassMap and OVA-VS (One-vs.-All classification using Vector Search). ClassMap is an embedding-based method, works for both boosted classifiers and SVMs, and tends to map the patterns and their associated classes close to each other in a vector space. OVA-VS maps OVA classifiers and test patterns to vectors based on the weights and outputs of weak classifiers of the boosting scheme. At runtime, finding the strongest-responding OVA classifier becomes a classical vector search problem, where well-known methods can be used to gain efficiency. In our experiments, the proposed methods achieve significant speed-ups, in some cases up to two orders of magnitude, compared to exhaustive evaluation of all OVA classifiers. This was achieved in hand pose recognition and face recognition systems where the number of classes ranges from 535 to 48,600.

Camera-Based Interfaces and Assistive Software for People with Sever Motion Impairments

Intelligent assistive technology can greatly improve the daily lives of people with severe paralysis, who have limited communication abilities. People with motion impairments often prefer camera-based communication interfaces, because these are customizable, comfortable, and do not require user-borne accessories that could draw attention to their disability. We present an overview of assistive software that we specifically designed for camera-based interfaces such as the Camera Mouse, which serves as a mouse-replacement input system. The applications include software for text-entry, web browsing, image editing, animation, and music therapy. Using this software, people with severe motion impairments can communicate with friends and family and have a medium to explore their creativity.

Indexing Distances in Large Graphs and Applications in Search Tasks

This thesis elaborates on the problem of preprocessing a large graph so that single-pair shortest-path queries can be answered quickly at runtime. Computing shortest paths is a well studied problem, but exact algorithms do not scale well to real-world huge graphs in applications that require very short response time. The focus is on approximate methods for distance estimation, in particular in landmarks-based distance indexing. This approach involves choosing some nodes as landmarks and computing (offline), for each node in the graph its embedding, i.e., the vector of its distances from all the landmarks. At runtime, when the distance between a pair of nodes is queried, it can be quickly estimated by combining the embeddings of the two nodes. Choosing optimal landmarks is shown to be hard and thus heuristic solutions are employed. Given a budget of memory for the index, which translates directly into a budget of landmarks, different landmark selection strategies can yield dramatically different results in terms of accuracy. A number of simple methods that scale well to large graphs are therefore developed and experimentally compared. The simplest methods choose central nodes of the graph, while the more elaborate ones select central nodes that are also far away from one another. The efficiency of the techniques presented in this thesis is tested experimentally using five different real world graphs with millions of edges; for a given accuracy, they require as much as 250 times less space than the current approach which considers selecting landmarks at random. Finally, they are applied in two important problems arising naturally in large-scale graphs, namely social search and community detection.

Learning Embeddings for Indexing, Retrieval, and Classification, with Applications to Object and Shape Recognition in Image Databases

Nearest neighbor retrieval is the task of identifying, given a database of objects and a query object, the objects in the database that are the most similar to the query. Retrieving nearest neighbors is a necessary component of many practical applications, in fields as diverse as computer vision, pattern recognition, multimedia databases, bioinformatics, and computer networks. At the same time, finding nearest neighbors accurately and efficiently can be challenging, especially when the database contains a large number of objects, and when the underlying distance measure is computationally expensive. This thesis proposes new methods for improving the efficiency and accuracy of nearest neighbor retrieval and classification in spaces with computationally expensive distance measures. The proposed methods are domain-independent, and can be applied in arbitrary spaces, including non-Euclidean and non-metric spaces. In this thesis particular emphasis is given to computer vision applications related to object and shape recognition, where expensive non-Euclidean distance measures are often needed to achieve high accuracy. The first contribution of this thesis is the BoostMap algorithm for embedding arbitrary spaces into a vector space with a computationally efficient distance measure. Using this approach, an approximate set of nearest neighbors can be retrieved efficiently - often orders of magnitude faster than retrieval using the exact distance measure in the original space. The BoostMap algorithm has two key distinguishing features with respect to existing embedding methods. First, embedding construction explicitly maximizes the amount of nearest neighbor information preserved by the embedding. Second, embedding construction is treated as a machine learning problem, in contrast to existing methods that are based on geometric considerations. The second contribution is a method for constructing query-sensitive distance measures for the purposes of nearest neighbor retrieval and classification. In high-dimensional spaces, query-sensitive distance measures allow for automatic selection of the dimensions that are the most informative for each specific query object. It is shown theoretically and experimentally that query-sensitivity increases the modeling power of embeddings, allowing embeddings to capture a larger amount of the nearest neighbor structure of the original space. The third contribution is a method for speeding up nearest neighbor classification by combining multiple embedding-based nearest neighbor classifiers in a cascade. In a cascade, computationally efficient classifiers are used to quickly classify easy cases, and classifiers that are more computationally expensive and also more accurate are only applied to objects that are harder to classify. An interesting property of the proposed cascade method is that, under certain conditions, classification time actually decreases as the size of the database increases, a behavior that is in stark contrast to the behavior of typical nearest neighbor classification systems. The proposed methods are evaluated experimentally in several different applications: hand shape recognition, off-line character recognition, online character recognition, and efficient retrieval of time series. In all datasets, the proposed methods lead to significant improvements in accuracy and efficiency compared to existing state-of-the-art methods. In some datasets, the general-purpose methods introduced in this thesis even outperform domain-specific methods that have been custom-designed for such datasets.

Integrating Sensor-Network Research and Development into a Software Engineering Curriculum

The emergence of a sensor-networked world produces a clear and urgent need for well-planned, safe and secure software engineering. It is the role of universities to prepare graduates with the knowledge and experience to enter the work-force with a clear understanding of software design and its application to the future safety of computing. The snBench (Sensor Network WorkBench) project aims to provide support to the programming and deployment of Sensor Network Applications, enabling shared sensor embedded spaces to be easily tasked with various sensory applications by different users for simultaneous execution. In this report we discus our experience using the snBench research project as the foundation for semester-long project in a graduate level software engineering class at Boston University (CS511).

Legal regulation of the software "patentable subject matter" requirement in the US and in Europe: The need for certainty, predictability and uniformity

This thesis critically investigates the divergent international approaches to the legal regulation of the patentability of computer software inventions, with a view to identifying the reforms necessary for a certain, predictable and uniform inter-jurisdictional system of protection. Through a critical analysis of the traditional and contemporary US and European regulatory frameworks of protection for computer software inventions, this thesis demonstrates the confusion and legal uncertainty resulting from ill-defined patent laws and inconsistent patent practices as to the scope of the “patentable subject matter” requirement, further compounded by substantial flaws in the structural configuration of the decision-making procedures within which the patent systems operate. This damaging combination prevents the operation of an accessible and effective Intellectual Property (IP) legal framework of protection for computer software inventions, capable of securing adequate economic returns for inventors whilst preserving the necessary scope for innovation and competition in the field, to the ultimate benefit of society. In exploring the substantive and structural deficiencies in the European and US regulatory frameworks, this thesis develops to ultimately highlight that the best approach to the reform of the legal regulation of software patentability is two-tiered. It demonstrates that any reform to achieve international legal harmony first requires the legislature to individually clarify (Europe) or restate (US) the long-standing inadequate rules governing the scope of software “patentable subject matter”, together with the reorganisation of the unworkable structural configuration of the decision-making procedures. Informed by the critical analysis of the evolution of the “patentable subject matter” requirement for computer software in the US, this thesis particularly considers the potential of the reforms of the European patent system currently underway, to bring about certainty, predictability and uniformity in the legal treatment of computer software inventions.

Planning a portfolio of controls for software development

A growing number of software development projects successfully exhibit a mix of agile and traditional software development methodologies. Many of these mixed methodologies are organization specific and tailored to a specific project. Our objective in this research-in-progress paper is to develop an artifact that can guide the development of such a mixed methodology. Using control theory, we design a process model that provides theoretical guidance to build a portfolio of controls that can support the development of a mixed methodology for software development. Controls, embedded in methods, provide a generalizable and adaptable framework for project managers to develop their mixed methodology specific to the demands of the project. A research methodology is proposed to test the model. Finally, future directions and contributions are discussed.

The Multiscale Systems Immunology project: software for cell-based immunological simulation.

BACKGROUND: Computer simulations are of increasing importance in modeling biological phenomena. Their purpose is to predict behavior and guide future experiments. The aim of this project is to model the early immune response to vaccination by an agent based immune response simulation that incorporates realistic biophysics and intracellular dynamics, and which is sufficiently flexible to accurately model the multi-scale nature and complexity of the immune system, while maintaining the high performance critical to scientific computing. RESULTS: The Multiscale Systems Immunology (MSI) simulation framework is an object-oriented, modular simulation framework written in C++ and Python. The software implements a modular design that allows for flexible configuration of components and initialization of parameters, thus allowing simulations to be run that model processes occurring over different temporal and spatial scales. CONCLUSION: MSI addresses the need for a flexible and high-performing agent based model of the immune system.

Implementation of customer relationship management and inventory control software: a multiple case study of small retailers

Gemstone Team Small Business Solutions

Validation of ICDPIC software injury severity scores using a large regional trauma registry.

BACKGROUND: Administrative or quality improvement registries may or may not contain the elements needed for investigations by trauma researchers. International Classification of Diseases Program for Injury Categorisation (ICDPIC), a statistical program available through Stata, is a powerful tool that can extract injury severity scores from ICD-9-CM codes. We conducted a validation study for use of the ICDPIC in trauma research. METHODS: We conducted a retrospective cohort validation study of 40,418 patients with injury using a large regional trauma registry. ICDPIC-generated AIS scores for each body region were compared with trauma registry AIS scores (gold standard) in adult and paediatric populations. A separate analysis was conducted among patients with traumatic brain injury (TBI) comparing the ICDPIC tool with ICD-9-CM embedded severity codes. Performance in characterising overall injury severity, by the ISS, was also assessed. RESULTS: The ICDPIC tool generated substantial correlations in thoracic and abdominal trauma (weighted κ 0.87-0.92), and in head and neck trauma (weighted κ 0.76-0.83). The ICDPIC tool captured TBI severity better than ICD-9-CM code embedded severity and offered the advantage of generating a severity value for every patient (rather than having missing data). Its ability to produce an accurate severity score was consistent within each body region as well as overall. CONCLUSIONS: The ICDPIC tool performs well in classifying injury severity and is superior to ICD-9-CM embedded severity for TBI. Use of ICDPIC demonstrates substantial efficiency and may be a preferred tool in determining injury severity for large trauma datasets, provided researchers understand its limitations and take caution when examining smaller trauma datasets.

Automatic verification of linear controller software

© 2015 IEEE.We consider the problem of verification of software implementations of linear time-invariant controllers. Commonly, different implementations use different representations of the controller's state, for example due to optimizations in a third-party code generator. To accommodate this variation, we exploit input-output controller specification captured by the controller's transfer function and show how to automatically verify correctness of C code controller implementations using a Frama-C/Why3/Z3 toolchain. Scalability of the approach is evaluated using randomly generated controller specifications of realistic size.

CPAG: software for leveraging pleiotropy in GWAS to reveal similarity between human traits links plasma fatty acids and intestinal inflammation.

Meta-analyses of genome-wide association studies (GWAS) have demonstrated that the same genetic variants can be associated with multiple diseases and other complex traits. We present software called CPAG (Cross-Phenotype Analysis of GWAS) to look for similarities between 700 traits, build trees with informative clusters, and highlight underlying pathways. Clusters are consistent with pre-defined groups and literature-based validation but also reveal novel connections. We report similarity between plasma palmitoleic acid and Crohn's disease and find that specific fatty acids exacerbate enterocolitis in zebrafish. CPAG will become increasingly powerful as more genetic variants are uncovered, leading to a deeper understanding of complex traits. CPAG is freely available at www.sourceforge.net/projects/CPAG/.

Transformaciones en el plano utilizando software de geometría dinámica

Se presenta una experiencia sobre el estudio de las isometrías en el plano en la educación secundaria, utilizando software de geometría dinámica. Se construye y estudia las propiedades de los distintos movimientos (traslaciones, giros y simetrías). La actividad se desarrolla en la clase de informática con apoyo de programas como geogebra y applets de cabriweb. Se tratan elementos invariantes, composición de movimientos y motivos que teselan el plano.