Sergio A. Alvarez

Quadratic-Based Computation of Four-Impulse Optimal Rendezvous near Circular Orbit

Thewell-knownproblemofminimizingthetotalcharacteristicvelocityofaspacecraftinanimpulsiverendezvous with a satellite in circular orbit is considered by using the Clohessy ‐Wiltshire equations. It is well known that, for boundary conditions in the plane of the orbit, four impulses at most are required. The mathematical framework is presented for four-impulse optimal rendezvous near a circular orbit resulting in relatively simple formulas that determine if four impulses are required and, if so, how the four optimal velocity increments can be calculated.

Mining Statistically Significant Associations for Exploratory Analysis of Human Sleep Data

We introduce a specialized association rule mining technique that can extract patterns from complex sleep data comprising polysomnographic recordings, clinical summaries, and sleep questionnaire responses. The rules mined can describe associations among temporally annotated events and questionnaire or summary data; e.g., the likelihood that an occurrence of a rapid eye movement (REM) sleep stage during the second 100 sleep epochs of the night is associated with moderate caffeine intake. We use chi2 analysis to ensure statistical significance of the mined rules at the level P<0.05. Our results, obtained by mining sleep-related data from 242 human subjects, reveal clinically interesting associations among the polysomnographic and summary variables. Our experience suggests that association mining may also be useful for selection of variables prior to using logistic regression

Machine learning of clinical performance in a pancreatic cancer database

OBJECTIVE We consider predictive models for clinical performance of pancreatic cancer patients based on machine learning techniques. The predictive performance of machine learning is compared with that of the linear and logistic regression techniques that dominate the medical oncology literature. METHODS AND MATERIALS We construct predictive models over a clinical database that we have developed for the University of Massachusetts Memorial Hospital in Worcester, Massachusetts, USA. The database contains retrospective records of 91 patient treatments for pancreatic tumors. Classification and regression targets include patient survival time, Eastern Cooperative Oncology Group (ECOG) quality of life scores, surgical outcomes, and tumor characteristics. The predictive performance of several techniques is described, and specific models are presented. RESULTS We show that machine learning techniques attain a predictive performance that is as good as, or better than, that of linear and logistic regression, for target attributes that include tumor N and T stage, survival time, and ECOG quality of life scores. Bayesian techniques are found to provide the best performance overall. For tumor size as the target attribute, however, logistic regression (respectively linear regression in the case of a numerical as opposed to discrete target) performs best. Preprocessing in the form of attribute selection and supervised attribute discretization improves predictive performance for most of the predictive techniques and target attributes considered. CONCLUSION Machine learning provides techniques for improved prediction of clinical performance. These techniques therefore merit consideration as valuable alternatives to traditional multivariate regression techniques in clinical medical studies.

Knowledge Discovery in Clinical Performance of Cancer Patients

Our goal in this research is to construct predictive models for clinical performance of pancreatic cancer patients. Current predictive model design in medical oncology literature is dominated by linear and logistic regression techniques. We seek to show that novel machine learning methods can perform as well or better than these traditional techniques.We construct these predictive models via a clinical database we have developed for the University of Massachusetts Memorial Hospitalin Worcester, Massachusetts, USA. The database contains retrospective records of 91 patient treatments for pancreatic tumors.Classification and regression prediction targets include patient survival time, ECOG quality of life scores, surgical outcomes,and tumor characteristics. The predictive accuracy of various data mining models is described, and specific models are presented.

Neural expert networks for faster combined collaborative and content-based recommendation

We consider techniques based on artificial neural networks for combining collaborative (social) and content information in a recommender system in order to enhance recommendation performance. We find that the recommendation quality achieved by a feedforward multilayer perceptron network operating on combined collaborative and content-based information (preprocessed using the singular value decomposition) is statistically significantly better than that of a network that is provided with the collaborative data alone, assuming that dimensionality reduction is performed on the collaborative and content-based data components separately. We propose a mixture of attribute experts neural network architecture that exploits the natural division between content and social information in order to reduce the number of network connections, resulting in more efficient training and recommendation than a standard fully connected network. We characterize the set of functions that can be expressed by mixture of attribute experts networks. The top 3 precision achieved by a recommender system based on our mixture of attribute experts architecture is superior to that of a purely collaborative system at a strong statistical significance level (P > 0.01). A random restarting technique reduces the average running time without affecting recommendation precision. CR Categories and Subject Descriptors. H.3.3 [Information Storage and Retrieval]: Information Search and Retrieval - Information Filtering; H.2.8 [Database Management]: Database Applications - Data Mining; 1.2.6 [Artificial Intelligence]: Learning - Connectionism and neural nets; 1.5.1 [Pattern Recognition]: Models - Neural nets; 1.5.5 [Pattern Recognition I: Implementation - Special architectures.

Four-Impulse Rendezvous Near Circular Orbit

Using the Clohessy-Wiltshire equations, the well-known problem of minimizing the total characteristic velocity of a spacecraft in an impulsive rendezvous with a satellite in circular orbit is considered. It is well-known that, for boundary conditions in the plane of the orbit, at most four impulses are required. This paper presents the mathematical framework for fourimpulse rendezvous near a circular orbit resulting in simple formulas for the computation of the four optimal velocity increments.

Discovery of sleep composition types using expectation-maximization

Human sleep exhibits characteristic patterns during the course of a full night, exemplified by alternation of deep sleep (stage N3/4) and light sleep (stages N1 and N2 occasionally interrupted by REM sleep). However, individual variations in this pattern occur. This paper uncovers a coarse classification of such sleep patterns into types described by varying balances among all-night summary variables such as sleep efficiency and the fraction of sleep period time spent in each of the sleep stages N1, N2, N3/4, and REM. Unsupervised expectation-maximization (EM) clustering is used over data obtained from 244 all-night polysomnographic sleep studies, revealing several naturally occurring sleep type clusters. It is found that sleep efficiency plays a major role in differentiating among sleep types, with time in deep sleep further refining the sleep type classification. Associations are found between sleep type on the one hand, and variables that describe health history and habits on the other. These findings suggest that the discovered sleep types describe medically meaningful groups of sleep behaviors that may be useful in future sleep research.

Computational methods for single-point and multipoint analysis of genetic variants associated with a simulated complex disorder in a general population.

Several techniques for association analysis have been applied to simulated genetic data for a general population. We describe and compare the performance of three single‐point methods and two multipoint approaches rooted in machine learning and data mining.

Prediction of Pancreatic Cancer Survival through Automated Selection of Predictive Models

Cancer survival forecasting may be attempted using models constructed through predictive techniques of various kinds, including statistical multivariate regression and machine learning. However, no single such technique provides the best predictive performance in all cases. We present an automated meta-learning approach that learns to predict the best performing technique for each individual patient. The individually selected technique is then used to forecast survival for the given patient. We evaluate the proposed approach over a database of retrospective records of pancreatic cancer surgical resections.

Predicting Outcome of Ischemic Stroke Patients using Bootstrap Aggregating with M5 Model Trees.

The objective of our study is to predict the clinical outcome of ischemic stroke patients after 90 days of stroke using the modified Rankin Scale (mRS) score. After experimentation with various regression techniques, we discovered that using M5 model trees to predict the score and then using bootstrap aggregating as a meta-learning technique produces the best prediction results. The same regression when followed by classification also performs better than regular multi-class classification. In this paper, we present the methodology used, and compare the results with other standard predictive techniques. We also analyze the results to provide insights on the factors that affect stroke outcomes.