检索结果-内蒙古大学图书馆

ieee International conference on Robotics and Automation (ICRA)

作者： Mohsen Raoufi Pawel Romanczuk Heiko Hamann Science of Intelligence Research Cluster of Excellence Berlin Germany Department of Biology Institute for Theoretical Biology Humboldt Universität zu Berlin Berlin Germany Department of Electrical Engineering and Computer Science Technical University of Berlin Berlin Germany Bernstein Center for Computational Neuro-science Berlin Germany Department of Computer and Information Science University of Konstanz Konstanz Germany

Collective decision-making is an essential capability of large-scale multi-robot systems to establish autonomy on the swarm level. A large portion of literature on collective decision-making in swarm robotics focuses on discrete decisions selecting from a limited number of options. Here we assign a decentralized robot system with the task of exploring an unbounded environment, finding consensus on the mean of a measurable environmental feature, and aggregating at areas where that value is measured (e.g., a contour line). A unique quality of this task is a causal loop between the robots' dynamic network topology and their decision-making. For example, the network's mean node degree influences time to convergence while the currently agreed-on mean value influences the swarm's aggregation location, hence, also the network structure as well as the precision error. We propose a control algorithm and study it in real-world robot swarm experiments in different environments. We show that our approach is effective and achieves higher precision than a control experiment. We anticipate applications, for example, in containing pollution with surface vehicles.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A machine learning based approach for identifying traumatic brain injury patients for whom a head CT scan can be avoided

A machine learning based approach for identifying traumatic ...

引用

Annual International conference of the ieee Engineering in Medicine and biology Society (EMBC)

作者： Somayeh Molaei Frederick K. Korley S.M. Reza Soroushmehr Hayley Falk Haris Sair Kevin Ward Kayvan Najarían Michigan Center for Integrative Research in Critical Care (MCIRCC) University of Michigan Ann Arbor MI USA School of Medicine Johns Hopkins University Baltimore MD USA Department of Computational Medicine and Bioinformatics University of Michigan MI USA

ISBN: (纸本)9781457702198

Head CT scan is more often used to evaluate patients with suspected traumatic brain injury (TBI). However, the use of head CT scans in evaluating TBI is costly with low value endeavor. In this paper, we propose a new algorithm and a set of features to help clinicians determine which patients evaluated for TBI need a head CT scan using cost sensitive random forest (CSRF) classifier. We show that random forest (RF) and CSRF are useful methods for identifying patients likely to have a positive head CT scan. The proposed algorithm has superior diagnostic accuracy in comparison to the Canadian head CT algorithm, which is currently the most accurate and widely used algorithm for determining which TBI patients need a head CT scan. In the highest sensitivity (i.e. 100%), our method outperforms the Canadian rule in terms of specificity, accuracy and area under ROC curve using cost sensitive classifier. Clinical implementation of this algorithm can help decrease financial costs associated with Emergency Department evaluations for traumatic brain injury, while decreasing patient exposure to avoidable ionizing radiation.

关键词： Computed tomography Head Magnetic heads Brain injuries Radio frequency Sensitivity

来源：评论

学校读者我要写书评

暂无评论

Thematic role assignment through a biologically plausible symbolic-connectionist hybrid system

Thematic role assignment through a biologically plausible sy...

引用

International Joint conference on Neural Networks (IJCNN)

作者： J.L.G. Rosa A.B. da Silva Ambientais e de Tecnologias Centro de Ciencias Exatas Campinas Brazil Centro de Ciências Exatas PUC-Campinas Campinas SP Brazil

There are several connectionist systems concerning natural language computational processing applications in artificial intelligence literature. Some try to predict the next word in a sentence context. Others attempt to discover grammatical symbolic rules from the neural network architecture, and others deal with semantic relationships between words. Unfortunately, very few of them employ psycholinguistic theories. Recently, some systems have made use of biologically plausible approaches to connectionist natural language processing, which are computationally as efficient as conventional methods. The system described here, in a way, presents all the properties and characteristics enumerated previously: it is a symbolic-connectionist hybrid system, designed to "predict" thematic (semantic) roles assigned to words in a sentence context with a biologically inspired training algorithm and architecture, and adopting a psycholinguistic view of thematic theory. Its lexicon, which includes lexically ambiguous nouns and "thematically ambiguous" verbs, can be increased, provided that semantic "features" of words are entered. The system has proven to be even more computationally efficient than conventional connectionist systems.

关键词： Computer architecture Natural languages Artificial neural networks Natural language processing biology computing Psychology Algorithm design and analysis Biological system modeling Computer applications Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Automated Abnormality Detection in Patient Retinal Function: A Deep Learning-Powered Electroretinogram Analysis System

Automated Abnormality Detection in Patient Retinal Function:...

引用

Annual International conference of the ieee Engineering in Medicine and biology Society (EMBC)

作者： Binh Duong Giap Keely Likosky Karthik Srinivasan Naheed W. Khan Nambi Nallasamy Department of Ophthalmology & Visual Sciences University of Michigan Ann Arbor MI USA Medical School University of Michigan Ann Arbor MI USA Department of Vitreo Retinal Aravind Eye Hospital Chennai Tamil Nadu India Department of Computational Medicine & Bioinformatics Ann Arbor MI USA

ISBN: (数字)9798350371499

ISBN: (纸本)9798350371505

The electroretinogram (ERG) is an ophthalmic electrophysiology test designed to objectively measure the electrical response of the photoreceptor cells in the human retina. The analysis of the ERG is highly useful in evaluating various retinal diseases arising from both inherited and acquired disorders. However, analyzing ERG test results can be a time-intensive process for electrophysiologists, requiring meticulous examination of recorded ERG waveforms for accurate diagnosis and assessment. In this paper, we present a novel deep learning-based ERG analysis system to automatically detect abnormalities in the retinal function of patients. To train and validate the proposed system, a dataset of 5,640 ERG tracings recorded from 470 patients, along with diagnoses from experienced electrophysiologists, was built. Our results indicate that the proposed system demonstrates effectiveness in detecting anomalies in retinal function on full-field ERGs with an F1-score of 77.59%, and an inference time of 1.2 milliseconds. This system can be used as an effective tool to assist electrophysiologists and ophthalmologists by providing rapid and reliable automated assessments.

关键词： Electric potential Accuracy Electric variables measurement Electrophysiology Retina Photoreceptors Recording Reliability Engineering in medicine and biology Diseases

来源：评论

学校读者我要写书评

暂无评论

Information Theory Based Genome-Scale Gene Networks Construction Using MapReduce

Information Theory Based Genome-Scale Gene Networks Construc...

引用

International conference on High Performance Computing

作者： Sriram P. Chockalingam Maneesha Aluru Srinivas Aluru Dept. of Computer Science and Engineering Indian Institute of Technology Mumbai India School of Biology Georgia Institute of Technology Atlanta USA School of Computational Science and Engineering Georgia Institute of Technology Atlanta USA

ISBN: (纸本)9781467384872

Reverse-engineering genome-scale gene networks from gene expression data is a principal challenge in systems biology. Mutual information (MI) based methods are favored because of their ability to recover non-linear relationships, low algorithmic complexity, and their successful use in various biological applications such as gene function prediction. In this paper, we present the first ever construction of MI based genome-scale gene networks using MapReduce. We develop the solution for all the stages of a MI-based network construction algorithm using only the map and reduce operations on distributed datasets. Our solution is implemented using Spark, a software that provides a compute and memory abstraction for distributed datasets. We deploy our solution using on-demand virtual instances on Amazon EC2 cloud computing platform, thus demonstrating the use of a rent-by-the-hour ad-hoc cluster for this grand challenge problem in systems biology. Our implementation can scale with the number of virtual instances, and can be used to construct networks of sizes in the range of 2000 to 5000 genes within an hour in a cost effective manner. We demonstrate the capability to construct genome-scale networks by reverse engineering a network of over 17,000 genes for the widely studied model plant Arabidopsis Thaliana.

关键词： Correlation Genomics bioinformatics Bayes methods Gene expression Complexity theory Random variables

来源：评论

学校读者我要写书评

暂无评论

Comprehensive analysis of gene expression profiles to radiation exposure reveals molecular signatures of low-dose radiation response

Comprehensive analysis of gene expression profiles to radiat...

引用

ieee International conference on bioinformatics and Biomedicine (BIBM)

作者： Xihaier Luo Sean McCorkle Gilchan Park Vanessa López-Marrero Shinjae Yoo Edward R. Dougherty Xiaoning Qian Francis J. Alexander Byung-Jun Yoon Computational Science Initiative Brookhaven National Laboratory Upton NY Department of Electrical and Computer Engineering Texas A&M University College Station TX

ISBN: (数字)9781665468190

ISBN: (纸本)9781665468206

There are various sources of ionizing radiation exposure, where medical exposure for radiation therapy or diagnosis is the most common human-made source. Understanding how gene expression is modulated after ionizing radiation exposure and investigating the presence of any dose-dependent gene expression patterns have broad implications for health risks from radiotherapy, medical radiation diagnostic procedures, as well as other environmental exposure. In this paper, we perform a comprehensive pathway-based analysis of gene expression profiles in response to low-dose radiation exposure, in order to examine the potential mechanism of gene regulation underlying such responses. To accomplish this goal, we employ a statistical framework to determine whether a specific group of genes belonging to a known pathway display coordinated expression patterns that are modulated in a manner consistent with the radiation level. Findings in our study suggest that there exist complex yet consistent signatures that reflect the molecular response to radiation exposure, which differ between low-dose and high-dose radiation.

关键词： Radiation effects Ionizing radiation Genomics Probabilistic logic biology Regulation Radiation therapy

来源：评论

学校读者我要写书评

暂无评论

Diagnosis Neuro-Oncology Diseases via Artificial intelligence and Multi-Sequence MRI Methods

Diagnosis Neuro-Oncology Diseases via Artificial Intelligenc...

引用

Cognitive Sciences, Genomics and bioinformatics (CSGB)

作者： Andrey Letyagin Evgeniya Amelina Bair Tuchinov Vladimir Groza Mikhail Amelin Sergey Golushko Evgeniy Pavlovskiy Branch of IC&G SB RAS Research Institute of Clinical and Experimental Lymphology Novosibirsk Russia SDAML lab. Novosibirsk State University Novosibirsk Russia Radiodiagnosis dept. FSBI “Federal Neurosurgical Center” Novosibirsk Russia Novosibirsk State University Novosibirsk Russia

The study of brain tumor structure and its type-dependent variations is one of the most important research areas in which medical imaging techniques are used. The structural and statistical analysis of these lesions raises various related problems and projects, such as the detection of the neuro oncology diseases, the shape and the segmentation of specific sub-regions (i.e. necrotic part, (non-)enhanced part, edema), the classification of the tumor occurrence and the subsequent treatment up-prognosis. Almost all of these problems are usually solved numerically, particularly with the tendency to use methods related to artificial intelligence (AI), often including deep learning (DL) networks. One of the most complicated, least researched and challenging tasks in this field is the classification of tumor types. This difficulty can be explained by several reasons, the most important of which is the severe limitation of existing open-source datasets that contain clinically confirmed tumor type designations based on radiological examination protocols. Magnetic resonance imaging (MRI) is the most common method for screening, primary detection and non-invasive diagnosis of brain diseases, as well as a source of recommendations for further treatment and observation. In this paper, we extend the previous research works on the robust multi-sequences segmentation and classification methods which allows to consider all available information from MRI scans by the composition of TI, TIC, T2 and T2-FLAIR sequences. It is based on the clinical radiology hypothesis and presents an efficient approach to combining and matching 3D methods to search for areas of comprised the GD-enhancing tumor in order to significantly improve the model's performance of the particular applied numerical problem of brain tumor classification and metastasis segmentation. All investigations performed and results presented are based on the private Siberian brain tumor dataset, including labeled volumetric MR

关键词：

来源：评论

学校读者我要写书评

暂无评论

Roe: A computational-Efficient Anti-hallucination Fine-Tuning Technology for Large Language Model Inspired by Human Learning Process 16th

Roe: A Computational-Efficient Anti-hallucination Fine-Tunin...

引用

16th International conference on Brain Informatics, BI 2023

作者： Liu, Xueqing Sajda, Paul Columbia University New YorkNY10027 United States

ISBN: (纸本)9783031430749

Large language models (LLMs) have shown significant potential in natural language processing (NLP) tasks, but they are plagued by issues of hallucination, where generated text contains false or fabricated information. This paper introduces a novel method, called "Roe," to combat hallucination in LLMs by incorporating a fine-tuning technique that promotes honesty in the model’s responses. Inspired by psychological studies on promoting honesty in children, the method rewards both correct answers and the behavior of admitting uncertainty by answering "I don’t know" when the model is unsure. The objective function is designed to encourage the model to switch between these two types of responses based on its confidence level. Experiments demonstrate that the Roe method achieves significantly better performance in addressing hallucination compared to the base Llama model and the original Alpaca model. The method also achieves comparable results to the state-of-the-art GPT4All model while using a smaller training dataset. The results of the HALTT4LLM benchmark further confirm the effectiveness of the Roe method in combating hallucination, particularly in handling fake questions. Sample outputs of the Roe model compared to the Alpaca model highlight the model’s adherence to factual information and its avoidance of direct references to fictional items in fabricated questions. Overall, the Roe method presents a promising approach for mitigating hallucination in large language models, enhancing their reliability and trustworthiness in generating text. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Topological-based classification using artificial gene networks

Topological-based classification using artificial gene netwo...

引用

ieee International conference on Cognitive Informatics

作者： Chun-Chi Liu W.-S.E. Chen Pei-Chun Chang J.J.W. Chen Department of Computer Science National Chung Hsing University Taichung Taiwan Institutes of Bioinformatics Taichung Healthcare and Management University Taichung Taiwan Institutes of Biomedical Sciences and Molecular Biology National Chung Hsing University Taichung Taiwan NTU Center for Genomic Medicine National Taiwan University College of Medicine Taipei Taiwan

The topological properties of artificial gene networks that rely on the assessment of similarities between the expressions profile of gene pairs would be consistent with specific cellular states. Furthermore, some topological properties of the network would have significant variance regarding different cellular states. In this study, we proposed a novel and highly efficient computational framework for a topological-based classification using microarray gene expression data. Owing to the high prediction accuracy with this approach, we believe that there is a noticeable advantage of using topological-based classification. We used the microarray gene expression data sets containing 14 classes of cancer to construct 14 basic artificial gene networks accordingly. For each test sample, we add the sample into the data set of each class and reconstruct all of the networks. Cancer type was classified according to the correlation of topological quantity between the basic artificial gene networks and the reconstructed networks. Total classification accuracy can achieve 78.26% in the test data set (95.83% in the standard data set). After screening the quality of the standard data set, we can achieve a prediction accuracy of 86.48% in the test data set. Thus, we can achieve higher prediction accuracy in comparison to previous studies.

关键词： Cancer bioinformatics Gene expression Support vector machines Support vector machine classification Classification tree analysis Genomics Cellular networks Accuracy Testing

来源：评论

学校读者我要写书评

暂无评论

Compressive genomics for protein databases

引用

bioinformatics 2013年第13期29卷 283-290页

作者： Daniels, Noah M. Gallant, Andrew Peng, Jian Cowen, Lenore J. Baym, Michael Berger, Bonnie Tufts Univ Dept Comp Sci Medford MA 02451 USA MIT Dept Math Cambridge MA 02139 USA MIT Comp Sci & Artificial Intelligence Lab Cambridge MA 02139 USA Harvard Univ Sch Med Dept Syst Biol Boston MA 02115 USA

Motivation: The exponential growth of protein sequence databases has increasingly made the fundamental question of searching for homologs a computational bottleneck. The amount of unique data, however, is not growing nearly as fast;we can exploit this fact to greatly accelerate homology search. Acceleration of programs in the popular PSI/DELTA-BLAST family of tools will not only speed-up homology search directly but also the huge collection of other current programs that primarily interact with large protein databases via precisely these tools. Results: We introduce a suite of homology search tools, powered by compressively accelerated protein BLAST (CaBLASTP), which are significantly faster than and comparably accurate with all known state-of-the-art tools, including HHblits, DELTA-BLAST and PSI-BLAST. Further, our tools are implemented in a manner that allows direct substitution into existing analysis pipelines. The key idea is that we introduce a local similarity-based compression scheme that allows us to operate directly on the compressed data. Importantly, CaBLASTP's runtime scales almost linearly in the amount of unique data, as opposed to current BLASTP variants, which scale linearly in the size of the full protein database being searched. Our compressive algorithms will speed-up many tasks, such as protein structure prediction and orthology mapping, which rely heavily on homology search.

关键词：

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：