检索结果-内蒙古大学图书馆

Large-signal behavior modeling of GaN HEMTs using SSA augmented ELM algorithm

JOURNAL OF COMPUTATIONAL ELECTRONICS 2023年第5期22卷 1415-1422页

作者： Wang, Shaowei Zhang, Jincan Yang, Shi Jin, Hao Xu, Binrui Wang, Jinchan Zhang, Liwen Henan Univ Sci & Technol Elect Engn Coll Luoyang 471023 Peoples R China Novaco Microelect Technol Ltd Nantong 226000 Peoples R China Luoyang Elect Equipment Test Ctr China Luoyang 471003 Peoples R China

The machine-learning algorithm is a technology that can learn from data. It can solve some problems that are difficult for humans to design and use deterministic programs. Among the available machine-learning algorithms for solving these problems, the Extreme learning machine (ELM) algorithm is well known because it only needs to set the number of the network hidden layer nodes and could generate a unique optimal solution. And, due to the randomness of its connection weights and thresholds, the simulated effect is random. Therefore, the selection of weights and thresholds needs to be optimized. In this paper, an enhanced ELM model is proposed to model the large-signal characteristics of GaN High Electron Mobility Transistors (HEMTs). The Sparrow Search algorithm (SSA) is used to optimize the initial weights and thresholds of the ELM algorithm, which significantly improves the prediction ability. Moreover, the SSA algorithm has the characteristics of strong optimization ability and fast convergence speed, which greatly improves the feasibility of model training. Through comparing the training effects of the SSA-ELM model and the ELM model, it can be seen that the proposed SSA-ELM model improves the ability of the ELM model to simulate the large-signal characteristics of GaN HEMTs.

关键词： machine-learning algorithm ELM model SSA-ELM model GaN HEMT

来源：评论

学校读者我要写书评

暂无评论

Cyborg Intelligence: Recent Progress and Future Directions

引用

IEEE INTELLIGENT SYSTEMS 2016年第6期31卷 44-50页

作者： Wu, Zhaohui Zhou, Yongdi Shi, Zhongzhi Zhang, Changshui Li, Guanglin Zheng, Xiaoxiang Zheng, Nenggan Pan, Gang Zhejiang Univ Coll Comp Sci & Technol Hangzhou Zhejiang Peoples R China East China Normal Univ Key Lab Brain Funct Genom Shanghai Peoples R China Chinese Acad Sci Inst Comp Technol Key Lab Intelligent Informat Proc Beijing Peoples R China Tsinghua Univ Dept Automat Beijing Peoples R China Chinese Acad Sci Shenzhen Inst Adv Studies Shenzhen Peoples R China Zhejiang Univ Qiushi Acad Adv Studies Hangzhou Zhejiang Peoples R China Zhejiang Univ Dept Biomed Engn Hangzhou Zhejiang Peoples R China

The combination of biological and artificial intelligence is a promising methodology to construct a novel intelligent modality, proposed as cyborg intelligence. The hierarchical conceptual framework is based on the interaction and combination of comparable components of biological cognitive units and computing intelligent units. The authors extend the previous conceptual framework and focus on sensorimotor circuits to explore the representation and integration of sensation. They then present a cognitive computing model for brain-computer integration and design efficient machine-learning algorithms for neural signal decoding. They also propose biological reconstruction methods for sensorimotor circuits to not only restore but enhance functionalities with AI. They develop a series of demonstrating systems to validate the conceptual framework of cyborg intelligence and possibly herald bright prospects and high values in diversified aspects of theoretical research, engineering techniques, and clinical applications. Finally, the authors summarize the latest research trends and challenges, which they believe will further boost new scientific frontiers in cyborg intelligence.

关键词： Man-machine systems Biological information theory Computers Artificial intelligence Brain modeling Computational modeling Actuators INSPEC: Controlled Indexing learning (artificial intelligence) biocybernetics brain-computer interfaces cognitive systems INSPEC: Non-Controlled Indexing biological reconstruction method cyborg intelligence biological intelligence artificial intelligence intelligent modality hierarchical conceptual framework biological cognitive units computing intelligent units sensorimotor circuits sensation representation sensation integration cognitive computing model brain-computer integration machine-learning algorithm neural signal decoding Author Keywords intelligent systems cyborg intelligence computational framework multimodal sensory representation cognitive model machine learning biological functionality reconstruction brain machine integration

来源：评论

学校读者我要写书评

暂无评论

Sweet-Heart - An integrated suite of enabling computational tools for automated MS2/MS3 sequencing and identification of glycopeptides

引用

JOURNAL OF PROTEOMICS 2013年 84卷 1-16页

作者： Wu, Sz-Wei Liang, Suh-Yuen Pu, Tsung-Hsien Chang, Fang-Yu Khoo, Kay-Hooi Natl Taiwan Univ Inst Biochem Sci Taipei Taiwan Acad Sinica NRPGM Core Facil Prote & Glyc Taipei 115 Taiwan Acad Sinica Inst Biol Chem Taipei 115 Taiwan

High efficiency identification of intact glycopeptides from a shotgun glycoproteomic LC-MS2 dataset remains problematic. The prevalent mode of identifying the de-N-glycosylated peptides is littered with false positives and addresses only the issue of site occupancy. Here, we present Sweet-Heart, a computational tool set developed to tackle the heart of the problems in MS' sequencing of glycopeptide. It accepts low resolution and low accuracy ion trap MS2 data, filters for glycopeptides, couples knowledge-based de novo interpretation of glycosylation-dependent fragmentation pattern with protein database search, and uses machine-learning algorithm to score the computed glyco and peptide combinations. Higher ranking candidates are then compiled into a list of MS2/MS3 entries to drive subsequent rounds of targeted MS3 sequencing of putative peptide backbone, allowing its validation by database search in a fully automated fashion. With additional fishing out of all related glycoforms and final data integration, the platform proves to be sufficiently sensitive and selective, conducive to novel glycosylation discovery, and robust enough to discriminate, among others, N-glycolyl neuraminic acid/fucose from N-acetyl neuraminic acid/hexose. A critical appraisal of its computing performance shows that Sweet-Heart allows high sensitivity comprehensive mapping of site-specific glycosylation for isolated glycoproteins and facilitates analysis of glycoproteomic data. Biological significance The biological relevance of protein site-specific glycosylation cannot be meaningfully addressed without first defining its pattern by direct analysis of glycopeptides. Sweet-Heart is a novel suite of computational tools allowing for automated analysis of mass spectrometry-based glycopeptide sequencing data. It is developed to accept ion trap MS2/MS3 data and uses a machine learning algorithm to score and rank the candidate peptide core and glycosyl substituent combinations. By eliminating the

关键词： Site-specific glycosylation Glycoproteomics Automated glycopeptide identification MS3 machine-learning algorithm EGFR

来源：评论

学校读者我要写书评

暂无评论

Model-based prediction of the potential geographical distribution of the invasive coconut mite, Aceria guerreronis Keifer (Acari: Eriophyidae) based on MaxEnt

引用

AGRICULTURAL AND FOREST ENTOMOLOGY 2022年第3期24卷 390-404页

作者： Aidoo, Owusu Fordjour da Silva, Ricardo Siqueira Santana Junior, Paulo Antonio Corcino Souza, Philipe Guilherme Kyerematen, Rosina Owusu-Bremang, Felix Yankey, Ndede Borgemeister, Christian Univ Environm & Sustainable Dev UESD Sch Nat & Environm Sci Dept Biol Phys & Math Sci Somanya Ghana Univ Educ UEW Inst Teacher Educ & Continuing Profess Dev ITECPD Winneba Ghana Univ Fed Vales do Jequitinhonha & Mucuri UFVJM Dept Agron Diamantina Brazil Univ Fed Vicosa Dept Entomol Vicosa MG Brazil Univ Ghana Dept Anim Biol & Conservat Sci DABCS Legon Ghana Council Sci & Ind Res CSIR Oil Palm Res Inst Coconut Res Programme Sekondi Ghana Univ Bonn Ctr Dev Res ZEF Bonn Germany

The coconut mite Aceria guerreronis Keifer (Acari: Eriophyidae), is a destructive mite pest of coconut, causing significant economic losses. However, an effective pest management strategy requires a clear understanding of the geographical areas at risk of the target pest. Therefore, we predicted the potential global distribution A. guerreronis using a machine learning algorithm based on maximum entropy. The potential future distribution for A. guerreronis covered the 2040 and 2060 periods under two climate change emission scenarios (SSP1-2.6 and SSP5-5.85) in the context of the sixth assessment report (AR6) of the Intergovernmental Panel on Climate Change. The MaxEnt model predicts the habitat suitability for A. guerreronis outside its present distribution, with suitable habitats in Oceania, Asia, Africa, and the Americas. The habitat suitability for the pest will decrease from 2040 to 2060. The areas with the highest risk of A. guerreronis are those with an annual average temperature of around 25 degrees C, mean annual precipitation of about 1459 mm, mean precipitation seasonality close to 64%, an average variation of daytime temperature of about 8.6 degrees C, and mean seasonality of temperature of about 149.7 degrees C. Our findings provide information for quarantine measures and policymaking, especially where A. guerreronis is presently still absent.

关键词： Aceria guerreronis climate change coconut mite machine-learning algorithm MaxEnt

来源：评论

学校读者我要写书评

暂无评论

Integrated machine learning developed a prognosis-related gene signature to predict prognosis in oesophageal squamous cell carcinoma

引用

JOURNAL OF CELLULAR AND MOLECULAR MEDICINE 2024年第21期28卷 e70171页

作者： Tang, Peng Li, Baihui Zhou, Zijing Wang, Haitong Ma, Mingquan Gong, Lei Qiao, Yufeng Ren, Peng Zhang, Hongdian Tianjin Med Univ Natl Clin Res Ctr Canc Tianjins Clin Res Ctr Canc Tianjin Key Lab Digest CancDept Esophageal CancC Tianjin Peoples R China Tianjin Med Univ Natl Clin Res Ctr Canc Tianjins Clin Res Ctr Canc Dept Radiat OncolKey Lab Canc Prevent & TherapyC Tianjin Peoples R China

The mortality rate of oesophageal squamous cell carcinoma (ESCC) remains high, and conventional TNM systems cannot accurately predict its prognosis, thus necessitating a predictive model. In this study, a 17-gene prognosis-related gene signature (PRS) predictive model was constructed using the random survival forest algorithm as the optimal algorithm among 99 machine-learning algorithm combinations based on data from 260 patients obtained from TCGA and GEO. The PRS model consistently outperformed other clinicopathological features and previously published signatures with superior prognostic accuracy, as evidenced by the receiver operating characteristic curve, C-index and decision curve analysis in both training and validation cohorts. In the Cox regression analysis, PRS score was an independent adverse prognostic factor. The 17 genes of PRS were predominantly expressed in malignant cells by single-cell RNA-seq analysis via the TISCH2 database. They were involved in immunological and metabolic pathways according to GSEA and GSVA. The high-risk group exhibited increased immune cell infiltration based on seven immunological algorithms, accompanied by a complex immune function status and elevated immune factor expression. Overall, the PRS model can serve as an excellent tool for overall survival prediction in ESCC and may facilitate individualized treatment strategies and predction of immunotherapy for patients with ESCC.

关键词： machine-learning algorithm oesophageal squamous cell carcinoma predictive model random survival forest tumour-infiltrating immune cells

来源：评论

学校读者我要写书评

暂无评论

Genomic approach towards personalized anticancer drug therapy

引用

PHARMACOGENOMICS 2012年第2期13卷 191-199页

作者： Midorikawa, Yutaka Tsuji, Shingo Takayama, Tadatoshi Aburatani, Hiroyuki Univ Tokyo Adv Sci & Technol Res Ctr Genome Sci Div Meguro Ku Tokyo 1538904 Japan Nihon Univ Sch Med Dept Digest Surg Itabashi Ku Tokyo 1738610 Japan

Stratification of patients for multidrug response is a promising strategy for cancer treatment. Genome-based prediction models have great potential for this purpose because the extent of drug sensitivity may be attributed to the heterogeneity of the underlying genetic characteristics of cancer. However, microarray data is difficult to analyze and is not reproducible. Several machine-learning algorithms have therefore been developed in a repeatable manner. Random forests algorithm, which uses an ensemble approach based on classification and regression trees, appears to be superior for predicting multidrug sensitivity. This is because ensemble methods are more effective when there are much more predictors than samples. Here, we review recent advances in the development of classification algorithms using microarray technology for prediction of anticancer sensitivity, discuss the availability of ensemble methods for prediction models, and present data regarding the identification of potential responders to FOLFOX therapy using random forests algorithm.

关键词： anticancer therapy ensemble method expression array machine-learning algorithm personalized therapy predictor genes

来源：评论

学校读者我要写书评

暂无评论

Bioinformatical approaches to characterize intrinsically disordered/unstructured proteins

引用

BRIEFINGS IN BIOINFORMATICS 2010年第2期11卷 225-243页

作者： Dosztanyi, Zsuzsanna Meszaros, Balint Simon, Istvan Hungarian Acad Sci Biol Res Ctr Inst Enzymol Prot Res Grp H-1518 Budapest Hungary

Intrinsically disordered/unstructured proteins exist without a stable three-dimensional (3D) structure as highly flexible conformational ensembles. The available genome sequences revealed that these proteins are surprisingly common and their frequency reaches high proportions in eukaryotes. Due to their vital role in various biological processes including signaling and regulation and their involvement in various diseases, disordered proteins and protein segments are the focus of many biochemical, molecular biological, pathological and pharmaceutical studies. These proteins are difficult to study experimentally because of the lack of unique structure in the isolated form. Their amino acid sequence, however, is available, and can be used for their identification and characterization by bioinformatic tools, analogously to globular proteins. In this review, we first present a small survey of current methods to identify disordered proteins or protein segments, focusing on those that are publicly available as web servers. In more detail we also discuss approaches that predict disordered regions and specific regions involved in protein binding by modeling the physical background of protein disorder. In our review we argue that the heterogeneity of disordered segments needs to be taken into account for a better understanding of protein disorder.

关键词： protein disorder coupled folding and binding machine-learning algorithm prediction method binary classification

来源：评论

学校读者我要写书评

暂无评论

Genome-enabled prediction using probabilistic neural network classifiers

引用

BMC GENOMICS 2016年第1期17卷 1-16页

作者： Manuel Gonzalez-Camacho, Juan Crossa, Jose Perez-Rodriguez, Paulino Ornella, Leonardo Gianola, Daniel Colegio Postgrad Campus Montecillo Mexico City 056230 DF Mexico Int Maize & Wheat Improvement Ctr CIMMYT Biometr & Stat Unit Apdo Postal 6-641 Mexico City *** DF Mexico NIDERA SEMILLAS SA Ruta 8 Km 376 RA-2600 Venado Tuerto Argentina Univ Wisconsin Dept Anim Sci Madison WI 53706 USA

Background: Multi-layer perceptron (MLP) and radial basis function neural networks (RBFNN) have been shown to be effective in genome-enabled prediction. Here, we evaluated and compared the classification performance of an MLP classifier versus that of a probabilistic neural network (PNN), to predict the probability of membership of one individual in a phenotypic class of interest, using genomic and phenotypic data as input variables. We used 16 maize and 17 wheat genomic and phenotypic datasets with different trait-environment combinations (sample sizes ranged from 290 to 300 individuals) with 1.4 k and 55 k SNP chips. Classifiers were tested using continuous traits that were categorized into three classes (upper, middle and lower) based on the empirical distribution of each trait, constructed on the basis of two percentiles (15-85 % and 30-70 %). We focused on the 15 and 30 % percentiles for the upper and lower classes for selecting the best individuals, as commonly done in genomic selection. Wheat datasets were also used with two classes. The criteria for assessing the predictive accuracy of the two classifiers were the area under the receiver operating characteristic curve (AUC) and the area under the precision-recall curve (AUCpr). Parameters of both classifiers were estimated by optimizing the AUC for a specific class of interest. Results: The AUC and AUCpr criteria provided enough evidence to conclude that PNN was more accurate than MLP for assigning maize and wheat lines to the correct upper, middle or lower class for the complex traits analyzed. Results for the wheat datasets with continuous traits split into two and three classes showed that the performance of PNN with three classes was higher than with two classes when classifying individuals into the upper and lower (15 or 30 %) categories. Conclusions: The PNN classifier outperformed the MLP classifier in all 33 (maize and wheat) datasets when using AUC and AUCpr for selecting individuals of a specific c

关键词： Average precision Bayesian classifier Genomic selection machine-learning algorithm Multi-layer perceptron Non-parametric model

来源：评论

学校读者我要写书评

暂无评论

Identification of Gene Signatures Used to Recognize Biological Characteristics of Gastric Cancer Upon Gene Expression Data

引用

BIOMARKER INSIGHTS 2014年 9卷 67-76页

作者： Yan, Zhi Luke, Brian T. Tsang, Shirley X. Xing, Rui Pan, Yuanming Liu, Yixuan Wang, Jinlian Geng, Tao Li, Jiangeng Lu, Youyong Peking Univ Canc Hosp Key Lab Carcinogenesis & Translat Res Minist Educ Lab Mol Oncol Beijing Peoples R China Peking Univ Inst Key Lab Carcinogenesis & Translat Res Minist Educ Lab Mol Oncol Beijing Peoples R China Adv Biomed Comp Ctr Frederick Natl Lab Canc Res Frederick MD 21702 USA BioMatrix Rockville MD 20850 USA Georgetown Univ Lombardi Comprehens Canc Ctr Washington DC USA Beijing Univ Technol Coll Elect Informat & Control Engn Beijing Peoples R China

High-throughput gene expression microarrays can be examined by machine-learning algorithms to identify gene signatures that recognize the biological characteristics of specific human diseases, including cancer, with high sensitivity and specificity. A previous study compared 20 astric cancer (GC) samples against 20 normal tissue (NT) samples and identified 1,519 differentially expressed genes (DEGs). In this study, Classification Information Index (CII), Information Gain Index (IGI), and RELIEF algorithms are used to mine the previously reported gene expression profiling data. In all, 29 of these genes are identified by all three algorithms and are treated as GC candidate biomarkers. Three biomarkers, COL1A2, ATP4B, and HADHSC, are selected and further examined using quantitative real-time polymerase chain reaction (qRT-PCR) and immunohistochemistry (IHC) staining in two independent sets of GC and normal adjacent tissue (NAT) samples. Our study shows that COL1A2 and HADHSC are the two best biomarkers from the microarray data, distinguishing all GC from the NT, whereas ATP4B is diagnostically significant in lab tests because of its wider range of fold-changes in expression. Herein, a data-mining model applicable for small sample sizes is presented and discussed. Our result suggested that this mining model may be useful in small sample-size studies to identify putative biomarkers and potential biological features of GC.

关键词： gastric cancer gene signature microarray machine-learning algorithm

来源：评论

学校读者我要写书评

暂无评论

A Bottom-up Approach to Sustained Curtailment and Comfort for Controlled Demand Response 2

A Bottom-up Approach to Sustained Curtailment and Comfort fo...

引用

EEE Conference on Technologies for Sustainability (SusTech)

作者： Frincu, Marc Gima, Zachary Univ Southern Calif Dept Elect Engn Los Angeles CA 90089 USA Univ Southern Calif Dept Mech Engn Los Angeles CA 90089 USA

ISBN: (纸本)9781479952380

Curtailment prediction and efficient demand response (DR) strategy selection challenge the effectiveness of developing smart grid applications. Here we present solutions to both challenges, taking a bottom-up approach to demonstrate that curtailment at the equipment-level determined based on the equipment mechanical properties and models can be used to efficiently estimate curtailment and to optimize human comfort during a DR event across a subset of energy consumers. We focus on a controlled microgrid environment present on the University of Southern California campus and address two HVAC oriented DR strategies: variable frequency drive and global temperature reset. Strong correlation between equipment and building level consumption was found to exist in less than half the cases, showing that building level consumption can be successfully used as well for those scenarios. Several fast heuristics aiming to optimize human comfort during equipment level DR proved to be successful and showed that the best method depends on the DR strategy. Finally, relying on the equipment specifications and consumption models for our analyses circumvents the common challenges associated with statistical and machine-learning algorithm approaches that rely on large amounts of historical data.

关键词： demand side management distributed power generation smart power grids DR strategy selection HVAC oriented DR strategies University of Southern California bottom-up approach building level consumption controlled demand response controlled microgrid environment curtailment prediction energy consumers equipment mechanical properties global temperature reset human comfort machine-learning algorithm smart grid applications statistical algorithm sustained comfort sustained curtailment variable frequency drive Buildings Cooling Correlation Educational institutions Load modeling Microgrids Springs COMFORT Smart grids machine learning algorithms bottom-up approach variable frequency drives distributed power generation Load modeling Educational institutions Buildings springs Device Spring Demand-Responsive MICRO-GRID Cooling DR

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：