检索结果-内蒙古大学图书馆

6th International Conference on Mobile Computing and Sustainable Informatics, ICMCSI 2025

作者： Ramya, J. Poongodi, A. Department of Software Applications Agurchand Manmull Jain College Chennai India Department of Computer Sciences Vels Institute of Science Technology and Advanced Studies Chennai India

ISBN: (数字)9798331522667

ISBN: (纸本)9798331522667

Lung cancer is one of the main causes of death globally and adds to the burden of disease and mortality. Early detection of lung cancer may reduce the chance of developing lung cancer. Artificial intelligence (AI) in diagnostic imaging has garnered a lot of attention in recent years, particularly for the detection of lung cancer. On the other hand, manual CT scan analysis takes a lot of time and is inaccurate or prone to mistakes. Given these limitations, the accurate categorization of CT images as either malignant or non-cancerous is accelerated by the application of computer approaches, including machine learning and deep learning algorithms. In this work, we provide a new and improved CNN model architecture with FCN and Deeplab V3+ for segmentation and classification using hybrid efficient net B0 to investigate lung cancer. The suggested model achieves superior results in both segmentation and classification. © 2025 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Parallel implementation of a bioinformatics pipeline for the design of pathogen diagnostic assays

Parallel implementation of a bioinformatics pipeline for the...

引用

2009 DoD High Performance Computing Modernization Program - Users Group Conference, HPCMP-UGC 2009

作者： Satya, Ravi Vijaya Kumar, Kamal Zavaljevski, Nela Reifman, Jaques Biotechnology HPC Software Applications Institute Telemedicine and Advanced Technology Research Center Ft. Detrick MD United States

ISBN: (纸本)9780769539461

The genomes of hundreds of pathogens and their near neighbors are now available and many more are being sequenced. With the availability of this genome information, sequence-based pathogen identification has become an increasingly important tool for clinical diagnostics and environmental monitoring of biological threat agents. Chief among sequence-based identification tools are DNA microarrays, which have the ability to test for thousands of pathogens in a single diagnostic test. The design of microarray diagnostic assays involves the identification of short DNA sequences unique to a pathogen or groups of pathogens, where these unique sequences, or "fingerprints" (also referred to as probes) are used to identify the pathogens. To design pathogen fingerprints, we developed TOFI (Tool for Oligonucleotide Fingerprint Identification), a high performance computing software pipeline that designs microarray probes for multiple related pathogens in a single run. The TOFI pipeline is extremely efficient in designing microarray fingerprints for multiple pathogens. Parallel implementation of computationally expensive specificity analysis of the designed fingerprints drastically reduces the overall execution time of the software. Comprehensive performance analysis shows that TOFI achieves super-linear speedup for up to 74 processors. A Web-based user interface, developed using the User Interface Toolkit, provides easy access to the pipeline. Using 74 processors, TOFI took approximately nine hours to design 5,015 in-silico probes for eight Burkholderia genomes with a combined size of more than 50 million base pairs. Experimental validation of these probes with various Burkholderia genomes showed that nearly 80% of the designed fingerprints identify the intended targets. © 2010 IEEE.

关键词： Pathogens

来源：评论

学校读者我要写书评

暂无评论

Large-scale orthology predictions for inferring gene functions across multiple species

Large-scale orthology predictions for inferring gene functio...

引用

2010 DoD High Performance Computing Modernization Program Users Group Conference, HPCMP UGC 2010

作者： Yu, Chenggang Desai, Valmik Zavaljevski, Nela Reifman, Jaques Biotechnology HPC Software Applications Institute Telemedicine and Advanced Technology Research Center Ft. Detrick MD United States

ISBN: (纸本)9780769543925

An effective approach to infer the functions of genes is to use the concept of gene orthology. Because orthologous genes are likely to share similar functions, the functions of genes in an unstudied species can be inferred through the functions of their orthologs in a studied model species. To infer gene functions for a multitude of species, we developed a high-throughput orthology prediction method, termed PhyloTrace. PhyloTrace is both highly accurate and computationally efficient for large-scale applications, having the ability to infer orthologous genes across thousands of species. This is accomplished through three major steps: 1) all-against-all gene comparisons for every pair of genes, 2) pair-wise orthology predictions for every two genomes, and 3) the generation of orthologous clusters that contain orthologous genes across multiple genomes. We employed the previously developed Pipe man parallelization program to break down a set of millions of input sequences into small chunks and then processed them in parallel. We successfully predicted orthologs for over 900 bacterial genomes, achieving a false-positive prediction rate of 2.0, which was a significant improvement compared with the widely used bidirectional best-hit method, which yielded a false-positive rate of 5.5. © 2011 IEEE.

关键词： Genes

来源：评论

学校读者我要写书评

暂无评论

A tool for creating and parallelizing bioinformatics pipelines

A tool for creating and parallelizing bioinformatics pipelin...

引用

Department of Defense - HPCMP Users Group Conference 2007;High Performance Computing Modernization Program: A Bridge to Future Defense, DoD HPCMP UGC

作者： Yu, Chenggang Wilson, Paul A. Biotechnology HPC Software Applications Institute Telemedicine and Advanced Technology Research Center Ft. Detrick MD United States

ISBN: (纸本)0769530885

Bioinformatics pipelines enable life scientists to effectively analyze biological data through automated multi-step processes constructed by individual programs and databases. The huge amount of data and time consuming computations require effectively parallelized pipelines to provide results within a reasonable time. To reduce researchers' programming burden for pipeline creation and parallelization, we developed the Bioinformatics Pipeline Generation and Parallelization Toolkit (BioGent). A user needs only to create a pipeline definition file that describes the data processing sequence and input/output files. A program termed schedpipe in the BioGent toolkit takes the definition file and executes the designed procedure. Schedpipe automatically parallelizes the pipeline execution by performing independent data processing steps on multiple CPUs, and by decomposing big datasets into small chunks and processing them in parallel. Schedpipe controls program execution on multiple CPUs through a simple application programming interface (API) of the Parallel Job Manager (PJM) library. As a part of the BioGent toolkit, PJM was developed to effectively launch and monitor programs on multiple CPUs using a Message Passing Interface (MPI) protocol. The PJM API can also be used to parallelize other serial programs. A demonstration using PJM for parallelization shows 10% to 50% savings in time compared to an indigenous parallelization through a batch queuing system. © 2007 IEEE.

关键词： Pipelines

来源：评论

学校读者我要写书评

暂无评论

Optical neural network models applied to logic program execution

Optical neural network models applied to logic program execu...

引用

Neural Network Models for Optical Computing 1988

作者： Stormon, Charles D. New York State Center for Advanced Technology in Computer Applications and Software Engineering 120 Hinds Hall Syracuse University SyracuseNY13244-1190 United States

Logic programming is being used extensively by Artificial Intelligence researchers to solve problems including natural language processing and expert systems. These languages, of which Prolog is the most widely used, promise to revolutionize software engineering, but much greater performance is needed. Researchers have demonstrated the applicability of neural network models to the solution of certain NP-complete problems, but these methods are not obviously applicable to the execution of logic programs. This paper outlines the use of neural networks in four aspects of the logic program execution cycle, and discusses results of a simulation of three of these. Four neural network functional units are described, called the substitution agent, the clause filter, the structure processor, and the heuristics generator, respectively. Simulation results suggest that the system described may provide several orders of magnitude improvement in execution speed for large logic programs. However, practical implementation of the proposed architecture will require the application of optical computing techniques due to the large number of neurons required, and the need for massive, adaptive connectivity. © 1988 SPIE. All rights reserved.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

A geometry processor for image processing and pattern recognition

A geometry processor for image processing and pattern recogn...

引用

Architectures and Algorithms for Digital Image Processing III 1985

作者： Suk, Minsoo Pyo, Sam S. Department of Electrical and Computer Engineering Syracuse University SyracuseNY13244-1240 United States Center for Advanced Technology in Computer Applications and Software Engineering Syracuse University United States

A one-dimensional systolic geometry processor (SGP) which is useful in image processing and pattern recognition is described. The geometry processor can be used to enhance processing speed and throughput of the host computer by working as an attached processor. SGP algorithms for solving several primitive geometric problems such as convex hull, inclusion and intersection are shown. © 1986 SPIE. All rights reserved.

关键词： Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

A web-accessible protein structure prediction pipeline

A web-accessible protein structure prediction pipeline

引用

2009 DoD High Performance Computing Modernization Program - Users Group Conference, HPCMP-UGC 2009

作者： Lee, Michael S. Bondugula, Rajkumar Desai, Valmik Zavaljevski, Nela Yeh, In-Chul Wallqvist, Anders Reifman, Jaques Biotechnology HPC Software Applications Institute Telemedicine and Advanced Technology Research Center US Army Medical Research and Materiel Command Ft. Detrick MD United States US Army Research Laboratory Computational and Information Sciences Directorate Aberdeen Proving Ground MD United States Biotechnology HPC Software Applications Institute Telemedicine and Advanced Technology Research Center Ft. Detrick MD United States

ISBN: (纸本)9780769539461

Proteins are the molecular basis of nearly all structural, catalytic, sensory, and regulatory functions in living organisms. The biological function of a protein is inextricably linked to its three-dimensional (3D) atomic structure. Traditional structure determination methods, such as X-ray and nuclear magnetic resonance techniques, are time-consuming, expensive, and infeasible for the millions of proteins that have been sequenced so far from various organisms. Alternatively, computational structure prediction methods provide a faster and more cost-effective, albeit approximate, alternative to experimental structure determination. We present a high-throughput protein structure prediction pipeline (dubbed "PSPP"), which given input protein sequences infers their 3D atomic structures. The pipeline was designed to be used with high performance computing clusters and to scale with the number of processors. The pipeline encompasses a core Perl module, a parallel job manager, and a Web browser graphical user interface accessible at our Website (***). The software is currently installed at the Department of Defense (DoD) Maui High Performance Computing Center, and it is available for download along with its associated databases from our site. Currently, DoD scientists are using the pipeline in basic science and drug and vaccine development projects. © 2010 IEEE.

关键词： Pipelines

来源：评论

学校读者我要写书评

暂无评论

Application of a knowledge based expert system to space shuttle main propulsion propellant loading 33rd

Application of a knowledge based expert system to space shut...

引用

33rd Joint Propulsion Conference and Exhibit, 1997

作者： Fineberg, Larry H. Beil, Robert Engle, James Lane, J. Randy Orbiter Main Propulsion Engineering Boeing North American Inc. Kennedy Space Center FL United States Main Propulsion Systems Engineering National Aeronautics and Space Administration Kennedy Space Center FL United States Advanced Software and Technology Applications Boeing North American Inc Kennedy Space Center FL United States Software Systems Engineering Advanced Software and Technology Applications Boeing North American Inc Kennedy Space Center FL United States

The need to apply a knowledge based artificial intelligence system is driven by the complexity of the space shuttle propellant loading process and by the need to evaluate the hardware's performance;both tasks are man-power intensive and difficult to program using standard techniques. The Propulsion Advisory Tool (PAT) identifies both actual and potential system failures and provides pertinent data required for anomaly resolution. The knowledge base is coded using a natural language interface and is developed based on existing requirements documents and knowledge captured from experts working in the propulsion arena. The development and implementation of the PAT knowledge base applies a hybrid methodology utilizing commercial off-the-shelf tools and custom computer code. Each "real" hardware component is modeled by a virtual object that is defined within the knowledge base architecture. These objects have characteristics that correspond directly to the real component. The conclusions required to establish component/system status are based upon several levels of knowledge. Specific electrical circuits have been modeled within the G2 knowledge base to show "live" wires along with active objects that represent the various talkbacks within the circuit. Thus, the systems engineer can directly relate the data provided by the computer with the paperbased circuit drawings. The PAT kn owledge based expert system continues to be an essential part of Boeing North American's Integrated Health Management philosophy. © 1997, American Institute of Aeronautics and Astronautics, Inc.

关键词： Systems engineering

来源：评论

学校读者我要写书评

暂无评论

Structure-based pKa prediction provides a thermodynamic basis for the role of histidines in pH-induced conformational transitions in dengue virus

引用

Biochemistry and Biophysics Reports 2015年 4卷 375-385页

作者： Chaudhury, Sidhartha Ripoll, Daniel R. Wallqvist, Anders Department of Defense Biotechnology High Performance Computing Software Applications Institute Telemedicine and Advanced Technology Research Center U.S. Army Medical Research and Materiel Command Ft. Detrick 21702 MD United States

pH-induced conformational changes in dengue virus (DENV) are critical to its ability to infect host cells. The envelope protein heterodimers that make up the viral envelope shift from a dimer to a trimer conformation at low-pH during membrane fusion. Previous studies have suggested that the ionization of histidine residues at low-pH is central to this pH-induced conformational change. We sought out to use molecular modeling with structure-based pKa prediction to provide a quantitative basis for the role of histidines in pH-induced conformational changes and identify which histidine residues were primarily responsible for this transition. We combined existing crystallographic and cryo-electron microscopy data to construct templates of the dimer and trimer conformations for the mature and immature virus. We then generated homology models for the four DENV serotypes and carried out structure-based pKa prediction using Rosetta. Our results showed that the pKa values of a subset of conserved histidines in DENV successfully capture the thermodynamics necessary to drive pH-induced conformational changes during fusion. Here, we identified the structural determinants underlying these pKa values and compare our findings with previous experimental results. © 2015.

关键词： Flavivirus Histidine PKa shift Viral fusion

来源：评论

学校读者我要写书评

暂无评论

Exploring polypharmacology using a ROCS-based target fishing approach

Exploring polypharmacology using a ROCS-based target fishing...

引用

作者： Abdulhameed, Mohamed Diwan M. Chaudhury, Sidhartha Singh, Narender Sun, Hongmao Wallqvist, Anders Tawa, Gregory J. Biotechnology High Performance Computing Software Applications Institute Telemedicine and Advanced Technology Research Center U.S. Army Medical Research and Materiel Command Fort Detrick MD 21702 United States

Polypharmacology has emerged as a new theme in drug discovery. In this paper, we studied polypharmacology using a ligand-based target fishing (LBTF) protocol. To implement the protocol, we first generated a chemogenomic database that links individual protein targets with a specified set of drugs or target representatives. Target profiles were then generated for a given query molecule by computing maximal shape/chemistry overlap between the query molecule and the drug sets assigned to each protein target. The overlap was computed using the program ROCS (Rapid Overlay of Chemical Structures). We validated this approach using the Directory of Useful Decoys (DUD). DUD contains 2950 active compounds, each with 36 property-matched decoys, against 40 protein targets. We chose a set of known drugs to represent each DUD target, and we carried out ligand-based virtual screens using data sets of DUD actives seeded into DUD decoys for each target. We computed Receiver Operator Characteristic (ROC) curves and associated area under the curve (AUC) values. For the majority of targets studied, the AUC values were significantly better than for the case of a random selection of compounds. In a second test, the method successfully identified off-targets for drugs such as rimantadine, propranolol, and domperidone that were consistent with those identified by recent experiments. The results from our ROCS-based target fishing approach are promising and have potential application in drug repurposing for single and multiple targets, identifying targets for orphan compounds, and adverse effect prediction. © 2011 American Chemical Society.

关键词： Ligands

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：