For a well-established digital library (e.g., PubMed), searching in terms of a newly established ontology (e.g., Gene Ontology (GO)) is an extremely difficult task. Making such a digital library adaptive to any new ontology or to reorganize knowledge automatically is our main objective. The decomposition of the knowledge base into classes is a first step toward our main objective. In this paper, we will demonstrate an automated linking scheme for PubMed citations with GO terms using an improved version of extreme learning machine (ELM) type algorithms. ELM is an emergent technology, which has shown excellent performance in large data classification problems, with fast learning speeds.

Selecting important genes from microarray data is a considerably challenging problem as shown in Guyon's 2002 paper in this journal. We have developed an alternative feature ranking and selection methodology to tackle this problem. On the basis of several cancer data sets, AMFES (adaptive multiple features selection) outperforms Guyon's RFE (recursive feature elimination). In this paper, we will present a comprehensive and systematic comparison of three methods: AMFES, RFE, and the CORR (correlation coefficient) on five data sets (leukemia, colon, lymphoma, prostate, and potentially others). The leukemia, colon, and lymphoma data sets are adapted from Guyon's paper for convenience and the prostate cancer data set is from a public database, NCBI GEO (Gene Expression Omnibus). These three methods are compared in terms of test accuracy, number of selected features, computational time (total and training), statistical significance (t test, p values, and ROC (receiver operating characteristic)/AUC (area under curve)), and the discovery rate of informative features. AMFES obtains better results in computational time and number of selected features while maintaining higher or comparable test accuracy, statistical significance, and the discovery rate of informative features. In addition, AMFES can serve as a general methodology for other similar problems such as sampling and data mining.

We have used Quantum dots (QD) bioconjugated with Transferrin (Tf) as targeted luminescent probes to label pancreatic cancer cells, and have employed a confocal microscope to localize the distribution and track the dynamics of QD-Tf nanocomplexes. In this paper, we present our recent results on QD-Tf tracking and vesicle imaging, including quasi-real-time visualization of QD-Tf transport inside cells using a tracking algorithm. This work demonstrates that we have a potentially useful method for discovering the molecular delivery mechanism inside living cells by utilizing the QDs bioconjugates in combination with our tracking algorithm.

The emergence of new microscopy techniques in combination with the increasing resource of bioimaging data has given fresh impetus to utilizing image processing methods for studying biological processes. Cell tracking studies in particular, which are important for a wide range of biological processes such as embryonic development or the immune system, have recently become the focus of attention. These studies typically produce large volumes of data that are hard to investigate manually and therefore call for an automated approach. Due to the large variety of biological cells and the inhomogeneity of applications, however, there exists no widely accepted method or system for cell tracking until today. In this article, we present our publicly available DYNAMIK software environment that allows users to compute a suit of cell features and plot the trajectory of multiple cells over a sequence of frames. Using chemotaxis and Ras pathways as an example, we show how users can employ our software to compute statistics about cell motility and other cell information, and how to evaluate their test series based on the data computed. We see that DYNAMIK's segmentation and tracking compares favorably with the output produced by other software packages.

In this paper, we have developed an intelligent system for searching comparative genomic sequences which departs from the traditional sequence alignment methods of nucleic residues or alphabets. Instead, we use the Composition Vector method that exploits pattern structures in sequences and indexing techniques for building a genomic database of prokaryotic organisms and their phylogenetic relationships. For the structural analysis of prokaryotic patterns, we use this composition vector to express various fuzzy sequence pattern queries on genomic data that would be difficult to represent in traditional database technology. B.L. Hao and his group have used the Composition Vector method to construct a phylogenetic tree of prokaryotes to understand the evolutionary history of prokaryotic organisms. The Composition Vector method is based on counting the frequency of nucleotides of a fixed length K in the collection of gene sequences of each species. This method transforms variable length sequences to a fixed length vector. In addition to elaborating on the composition vector method, we also dwell on the sequence pattern queries, the implementation with its reasoning before we finally wrap up with a discussion which we are sure will kindle some more thoughts and views to progress this work.

BACKGROUND: The inference of homology from statistically significant sequence similarity is a central issue in sequence alignments. So far the statistical distribution function underlying the optimal global alignments has not been completely determined. RESULTS: In this study, random and real but unrelated sequences prepared in six different ways were selected as reference datasets to obtain their respective statistical distributions of global alignment scores. All alignments were carried out with the Needleman-Wunsch algorithm and optimal scores were fitted to the Gumbel, normal and gamma distributions respectively. The three-parameter gamma distribution performs the best as the theoretical distribution function of global alignment scores, as it agrees perfectly well with the distribution of alignment scores. The normal distribution also agrees well with the score distribution frequencies when the shape parameter of the gamma distribution is sufficiently large, for this is the scenario when the normal distribution can be viewed as an approximation of the gamma distribution. CONCLUSION: We have shown that the optimal global alignment scores of random protein sequences fit the three-parameter gamma distribution function. This would be useful for the inference of homology between sequences whose relationship is unknown, through the evaluation of gamma distribution significance between sequences.

Abstract Summary: cMap, a www comparative genetic map graphical utility, has a search capability and provides comparison of two genetic maps within or between species with dynamic links to data resources and text lists of the shared loci, running in a relational database environment. Currently, maps from three species (maize ‘Zea mays L.’, rice‘ Oryza sativa L.’, and sorghum ‘Sorghum bicolor L.’), representing over 13 800 distinct loci, are available for comparison at http://www.agron.missouri.edu/cMapDB/cMap.html Availability: cMap source code is available without cost on request for non-commercial use. Contact: [email protected] * To whom correspondence should be addressed. † Current address: Computer & Information Science & Engineering, University of Florida, Gainesville, FL 32611, USA

No abstract available.

Active learning is an effective learning approach. In this article we present an intelligent agent-assisted environment for active learning to better support the student-centered, self-paced, and highly interactive learning approach. The environment uses the student’s learning-related profile such as learning style and background knowledge in selecting, organizing, and presenting learning material, and it adopts a new approach to course content organization and delivery based on smart instructional components that can be integrated into a wide range of courses. The environment is being implemented using the prevalent Internet, Web, digital library, and multiagent technologies.

This paper is concerned with a localized protein-folding problem. In computational biology, the prediction of a three-dimensional protein from its amino acid sequence is a major outstanding problem. In this paper, we will first present this problem as a computational geometry problem. Then we will describe a pattern recognition method for the localized prediction problem. Since protein-folding plays a central role in understanding the structure and function of life—building molecular computers, designing drugs and biotech products—we will provide an intelligent system approach to these practical domains. © 2001 John Wiley & Sons, Inc.

Active learning is an effective learning approach. In this article we present an intelligent agent-assisted environment for active learning to better support the student-centered, selfpaced, and highly interactive learning approach. The environment uses the students learningrelated profile such as learning style and background knowledge in selecting, organizing, and presenting learning material, and it adopts a new approach to course content organization and delivery based on smart instructional components that can be integrated into a wide range of courses. The environment is being implemented using the prevalent Internet, Web, digital library, and multiagent technologies.

In the biosphere, biological phenomena manifest as gene functions and metabolic pathways. A challenging problem is the representation, learning and reasoning about these biochemical reactions, relationships between genotypes and phenotypes, and their interplay. Building knowledge bases of gene functions and metabolic pathways often requires integrating various different kinds of knowledge into a single hierarchical framework. On one hand, the knowledge of metabolic pathways consists of kinetic simulation, graphical representation and databases. On the other hand, the complexity of gene functions includes QTL (quantitative trait locus) mappings and higher-level data mining analysis. This paper describes a hierarchical model of cognitive maps for representing signaling and metabolism knowledge as well as genotype-to-phenotype mappings. Cognitive maps are bi-directional graphs that can learn and reason quantitatively and qualitatively. This knowledge representation scheme, coupled with numerical and statistical packages, becomes a useful tool for understanding genomics and metabolism.

In recent years, agent technology has been used increasingly in information management and distributed computing. A CSE curriculum that cultivates the knowledge of agent technology will increase the likelihood that the next generation of IT professionals have the background needed to design and develop software systems that are scalable, reliable, adaptable, and secure. In this paper, we present the rationale and our practice in incorporating agent technology into the CSE curriculum. We develop agent-based teaching materials and software modules and apply them to existing CSE courses including artificial intelligence, parallel and distributed processing, networking, and software engineering. Promising results have been obtained in teaching two graduate level courses using agent components.

In this paper, we present a multi-agent system for supporting student-centered, self-paced, and highly interactive learning in undergraduate computer science education. The system is based on a hybrid problem-based and case-based learning model, for both creative problem solving and mechanical experience simulation. It aims at enhancing the effectiveness of the undergraduate learning experience in computer science. Implemented using the prevalent Internet, Web, and digital library technologies, the system adopts an open architecture design and targets at large-scale, distributed operations. In the initial implementation of the system, a number of prototypes using different Java-based software environments have been developed. They offer tradeoffs in system performance and design complexity.

No abstract available.

In computer vision and image processing, the high degree of parallelism and pipelining of algorithms is often obstructed by the raster-scan I/O constraint and the information growing property of multiresolution structures. The approach of formulating algorithms in the pyramid structure as a binary tree structure, and mapping the binary tree structure into a linear pipelined array of 2logN levels for N*N images using a first-in, first-out technique (FIFO) to emulate the tree connections is proposed. It turns out that several geometric feature extraction algorithms such as moment generation can be represented in this scheme so that the inherent information growing of the algorithms enables the exploitation of bit-level concurrency in the architectural design. Consequently, the design of pipelined processor at each level is significantly simplified using bit-serial arithmetic, and this VLSI architecture is capable of generating moments concurrently in real-time.>

Recursive rules are important to deductive databases. A recursive rule may be compiled into expansions. In this article, the variable-predicate graph (V-P graph) based on the α-graph by loannidis is developed to represent linear recursive function-free rules and their expansions. A naming convention is used for variables and predicates in the V-P graph so that all equivalent recursive rules may map into a unique V-P graph. We propose a graphic construction method (g.c.m.) which derives V-P graphs of expansions directly from the V-P graph of the original rule. This graphic representation reveals some expansion properties not easy to obtain otherwise. We also propose a rule rewriting method in the context of deductive database so that constants, repeated distinguished variables, and/or repeated recursive variables may be removed from recursive rules.

A partial taxonomy for cognitive maps is provided. The notions of NPN (negative-positive-neural) logic, NPN relations, coupled-type neurons, and coupled-type neural networks are introduced and used as a framework for cognitive map modeling. D-POOL a cognitive-map-based architecture for the coordination of distributed cooperative agents, is presented. D-POOL consists of a collection of distributed nodes. Each node is a cognitive-map-based metalevel system coupled with a local expert/database system (or agent). To solve a problem, a local node first pools cognitive maps from relevant agents in an NPN relation that retains both negative and positive assertions. New cognitive maps are then derived and focuses of attentions are generated. With the focuses, a solution is proposed by the local node and passed to the remote systems. The remote systems respond to the proposal, and D-POOL strives for a cooperative or compromised solution through coherent communication and perspective sharing. The utility of D-POOL is demonstrated using two examples in distributed group decision support.>

P. Kanerva's (1988) sparse distributed memory model is applied to character recognition. The results of recognizing corrupted characters, using a sparse distributed memory with fewer than 10000 locations, is described: 100 corrupted test patterns were generated to recognize 18 template patterns. The performance of the model is evaluated. Insights about the behavior of sparse distributed memories as well as the model's applicability to character recognition are provided. It was found that a sparse distributed memory of small size can recognize patterns with considerable noise.>

A high-performance partitionable parallel/pipeline architecture (P/sup 3/A) that is capable of real-time image processing is discussed. The architecture consists of P disjoint pipes of L processors each, connected together through a novel wraparound memory. Many different problem classes, including shuffle-exchange, butterfly, and tree algorithms, can be easily mapped into P/sup 3/A. The power of the architecture lies in its ability to exploit both the spatial and temporal aspects of concurrency balancing parallelism and pipelining.>

The authors present Pool2, a generic system for cognitive map development and decision analysis that is based on negative-positive-neutral (NPN) logics and NPN relations. NPN logics and relations are extensions of two-valued crisp logic, crisp (binary) relations, and fuzzy relations, NPN logics and relations assume logic values in the NPN interval (-1, 1) instead of values in (0, 1). A theorem is presented that provides conditions for the existence and uniqueness of heuristic transitive closures of an NPN relation. It is shown that NPN logic and NPN relations can be used directly to model a target world with a combination of NPN relationships of attributes and/or concepts for the purposes of cognitive map understanding, and decision analysis. Two algorithms are presented for heuristic transitive closure computation and for heuristic path searching, respectively. Basic ideas are illustrated by example. A comparison is made between this approach and others.>

Some extended versions of the 8-point algorithm of H.C. Longuet-Higgins (1981, 1984) are presented. First, the algorithm is extended to (not necessarily rigid) affine transformations. Differentiable transformations are also discussed. Second, the solution of all the affine transformations for the 8-point algorithm, given any point correspondences, is shown to have dimension 9-r, where r is the rank of given point configuration. It is argued that degenerate cases considered by Longuet-Higgins are covered by present extended version.>

Most artificial intelligence applications require reasoning with uncertainty and incompleteness. Such information is not captured in terms of simple true and false values nor in terms of probabilistic estimates when relevant statistical data are lacking. In this paper, we extend Nilsson's probabilistic logic, a semantic generalization of logic, in which the truth value of a sentence is a probability value between Ø and 1 to evidential logic in the framework of Dempster-Shafer theory.