检索结果-内蒙古大学图书馆

statistical algorithms and a Lower Bound for Detecting Planted Cliques

JOURNAL OF THE ACM 2017年第2期64卷 8-8页

作者： Feldman, Vitaly Grigorescu, Elena Reyzin, Lev Vempala, Santosh S. Xiao, Ying IBM Corp Almaden Res Ctr San Jose CA 95120 USA Purdue Univ Dept Comp Sci W Lafayette IN 47907 USA Univ Illinois Dept Math Stat & Comp Sci Chicago IL 60607 USA Georgia Tech Atlanta GA USA Palantir Technol Palo Alto CA USA Georgia Inst Technol Sch Comp Sci Atlanta GA 30332 USA

We introduce a framework for proving lower bounds on computational problems over distributions against algorithms that can be implemented using access to a statistical query oracle. For such algorithms, access to the input distribution is limited to obtaining an estimate of the expectation of any given function on a sample drawn randomly from the input distribution rather than directly accessing samples. Most natural algorithms of interest in theory and in practice, for example, moments-based methods, local search, standard iterative methods for convex optimization, MCMC, and simulated annealing, can be implemented in this framework. Our framework is based on, and generalizes, the statistical query model in learning theory [Kearns 1998]. Our main application is a nearly optimal lower bound on the complexity of any statistical query algorithm for detecting planted bipartite clique distributions (or planted dense subgraph distributions) when the planted clique has size O(n(1/2)-delta) for any constant delta > 0. The assumed hardness of variants of these problems has been used to prove hardness of several other problems and as a guarantee for security in cryptographic applications. Our lower bounds provide concrete evidence of hardness, thus supporting these assumptions.

关键词： Learning theory statistical algorithms planted clique statistical dimension lower bounds

来源：评论

学校读者我要写书评

暂无评论

The Power of Prognosis: Cox Model Prediction of Disease-Free Survival in Colon Cancer

The Power of Prognosis: Cox Model Prediction of Disease-Fr...

引用

Workshop held at the 12th International Conference on Model and Data Engineering, MEDI 2023

作者： Belhouichet, Oussama Yahyaoui, Aymen Boulila, Wadii Zribi, Aref Attia, Rabah SERCOM Lab Polytechnic School of Tunisia University of Carthage Carthage Tunisia Military Academy of Fondouk Jedid Nabeul Tunisia Robotics and Internet-of-Things Laboratory Prince Sultan University Riyadh Saudi Arabia RIADI Laboratory National School of Computer Sciences University of Manouba Manouba Tunisia Department of Medical Oncology Military Hospital of Instruction of Tunis Tunis Tunisia

ISBN: (纸本)9783031557286

Colon cancer requires a lot of continuous monitoring either before the first discovery of the disease or even after the cure since, at any time, the patient can suffer a recurrence. Adequate treatments for colon cancer patients need to be determined using modern techniques. Indeed, artificial intelligence offers advanced techniques and methods to analyze the disease-free survival of patients with different types of treatment. The appropriate treatment choice, especially for chemotherapy, is very difficult and needs careful monitoring and analysis by doctors. In this work, an innovative method based on statistical algorithms, namely the Cox model, is proposed to help oncology doctors make the right treatment decision by allowing them to discover the different results and consequences of the different possible treatments following disease-free survival prediction. This work was tested and validated by medical staff at the military hospital of instruction in Tunisia. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Colon cancer CoxPH statistical algorithms Survival Analysis

来源：评论

学校读者我要写书评

暂无评论

Prediction of footwear demand using Prophet and SARIMA

引用

EXPERT SYSTEMS WITH APPLICATIONS 2024年第PartB期255卷

作者： Negre, Pablo Alonso, Ricardo S. Prieto, Javier Garcia, Oscar de-la-Fuente-Valentin, Luis Univ Salamanca BISITE Res Grp Salamanca 37006 Castile & Leon Spain AIR Inst Paseo Belen 9A Valladolid 47011 Castile & Leon Spain Int Univ La Rioja UNIR Av la Paz 137 La Rioja 26006 Spain

In an increasingly globalized market, where world container traffic since 2000 has almost quadrupled, the prediction of demand is an element of great importance for the optimal business development of a company. This work focuses on demand forecasting in the fashion sector. It is a very volatile market, with some characteristics such as: seasonality, culture and fashion trends, that makes it difficult to estimate the interseasonal footwear demand. In recent years, many algorithms for the prediction of demand have been studied;they can be divided into three natures: statistical algorithms, artificial intelligence algorithms and hybrid algorithms, each of them with its own characteristics. AI-generated predictions provide business professionals with the ability to organize the purchase of materials, manage production processes and stock quantity. Therefore, the purpose of this work is to forecast the long-term sales of a highly seasonal footwear model based on its historical data, using the Prophet and SARIMA (Seasonal Autoregressive Integrated Moving Average) algorithms. This represents a novelty as sales predictions for footwear in the state of the art are not typically made over the long term or highly seasonal, and there is no model that clearly outperforms others. Additionally, a set of Key Performance Indicators has been established to evaluate the prediction outcomes, as the same indicators such as MAE, MAPE and RMSE are commonly used in the state of the art. Furthermore, a relational database structure has been proposed for the organized storage of future predictions. Finally, the results between Prophet and SARIMA have been compared to ascertain whether Prophet (a non-linear statistical algorithm) outperforms SARIMA (a linear statistical algorithm). In the model prediction Prophet obtains an accuracy of 98.8% and a 158.8 MAE, while SARIMA reaches an accuracy of 93% and a 83.9 MAE;all in all really positive results taking into account long-term prediction and

关键词： Footwear market statistical algorithms Time series prediction SARIMA Prophet Forecasting KPIs

来源：评论

学校读者我要写书评

暂无评论

Segmentation of natural images based on super pixel and graph merging

引用

IET COMPUTER VISION 2021年第1期15卷 1-11页

作者： Mukherjee, Aritra Sarkar, Soumik Saha, Sanjoy K. Jadavpur Univ Dept Comp Sci & Engn Kolkata India Jadavpur Univ Dept Informat Technol Kolkata India

The task of natural image segmentation is one of the most researched topics of computer vision. There are mainly two principal approaches for the task, the statistical approach and the supervised approach. The proposed methodology segments natural images combining a set of statistical algorithms. First, the image is preprocessed to enhance the edges. Weighted average of the denoised image and its derivatives is the preprocessed output. Thereafter, an energy based super pixelation is applied to over segment the image. Finally, a connectivity graph is built where nodes correspond to super pixels and edges connect the adjacent super pixels. The adjacent super pixels are merged based on the confidence value defined in terms of their textural and colour similarity. Proposed methodology has been applied on the images of BSDS500 dataset. Performance of the proposed work has been compared with that of other works based on detected edge maps. Few works generate ultrametric contour maps (UCM). To compare the performance with those works, UCM is also generated by the proposed methodology. To do so images at multiple scales are considered. It is observed that the output of segmentation is better in case of the proposed methodology. Proposed methodology is much faster than others. Thus, makes it suitable for real time application in robot vision.

关键词： robot vision researched topics image denoising super pixel computer vision natural image segmentation methodology segments natural images principal approaches statistical algorithms supervised approach connectivity graph edge detection super pixelation preprocessed output denoised image image segmentation detected edge maps graph theory adjacent super pixels statistical approach

来源：评论

学校读者我要写书评

暂无评论

Theoretical Analysis of Straightness Errors in Coordinate Measuring Machines (CMM) with Three Linear Axes

引用

INTERNATIONAL JOURNAL OF PRECISION ENGINEERING AND MANUFACTURING 2021年第1期22卷 63-72页

作者： Patricio, Franco Jodar, Jose Univ Politecn Cartagena Dept Mat & Mfg Engn Escuela Tecn Super Ingn Ind C Doctor Fleming S-N Cartagena 30202 Spain Univ Politecn Cartagena Dept Appl Phys Escuela Tecn Super Ingn Ind C Doctor Fleming S-N Cartagena 30202 Spain

Diverse studies were developed in last years about the precision of coordinate measuring machines (CMMs) in order to enhance the calibration method for these testing devices or their application for dimensional verification of manufactured parts, but new research works are needed to identify the effect of the different types of geometric errors that exists in CMMs and deduce the measuring conditions that allow the optimization of CMM performance. The aim of this work consist of analyzing the influence of some of these machine errors such as the straightness errors and position errors associated to the CMM axis displacement, with the purpose of deducing the specific contribution of these errors inside the global uncertainty of these testing devices. This study was focused on coordinate measuring machines with a configuration type FXYZ, and it was carried out using a simplified model that is restricted to the effect of the straightness errors and position errors, without considering the contribution of the rest of CMM geometric errors. The unexpected variations that can be originated in the machine errors between the successive calibration points were described by the numerical model, and their influence on the CMM measuring accuracy were also discussed.

关键词： Axis displacement errors Coordinate measure machines (CMMs) Position errors statistical algorithms Straightness errors Theoretical modelling

来源：评论

学校读者我要写书评

暂无评论

Analysis of the Factors Influencing the Participation of University Students in Rural Education for Poverty Alleviation

引用

Journal of Contemporary Educational Research 2023年第12期7卷 92-99页

作者： Yin Chen Xinyu Liu Peng Shao Huanhuan Yuan School of Humanities and Public Management Jiangxi Agricultural UniversityNanchang 330045Jiangxi ProvinceChina School of Computer and Information Engineering Jiangxi Agricultural UniversityNanchang 330045Jiangxi ProvinceChina Asset and Laboratory Management Service Jiangxi Agricultural UniversityNanchang 330045Jiangxi ProvinceChina

The principle of“poverty alleviation first helps the poor”is fundamental to poverty alleviation through education in rural *** serves as an important foundation for improving the soft power of rural culture and promoting the development of rural cultural ***,college students,being one of the main participants in educational poverty alleviation,have not been equipped with a well-established institutionalized participation mechanism and a sufficient awareness of *** enhance college students’awareness and participation in rural education and poverty alleviation and to improve the institutionalization,this research focuses on college students as a group,delves into the current situation and willingness of college students to participate in rural education and poverty alleviation,and analyzes the influencing factors affecting college students’participation in rural education and poverty alleviation by means of a questionnaire and a computerized statistical ***,based on mathematical and statistical analysis,the research puts forward corresponding optimization countermeasures and suggestions from the perspectives of the government,colleges and universities,and villages,so as to provide decision-making guidelines for solving the problems of rural education development and talent constraints.

关键词： Rural education Rural construction Influencing factors statistical algorithms University students

来源：评论

学校读者我要写书评

暂无评论

statistical algorithms and a Lower Bound for Detecting Planted Cliques 13

Statistical Algorithms and a Lower Bound for Detecting Plant...

引用

45th Annual ACM Symposium on the Theory of Computing (STOC)

作者： Feldman, Vitaly Grigorescu, Elena Reyzin, Lev Vempala, Santosh S. Xiao, Ying IBM Corp Almaden Res Ctr San Jose CA 95120 USA Purdue Univ Dept Comp Sci W Lafayette IN 47907 USA Univ Illinois Dept Math Chicago IL 60607 USA Georgia Inst Technol Sch Comp Sci Atlanta GA 30332 USA

ISBN: (纸本)9781450320290

We introduce a framework for proving lower bounds on computational problems over distributions, based on a class of algorithms called statistical algorithms. For such algorithms, access to the input distribution is limited to obtaining an estimate of the expectation of any given function on a sample drawn randomly from the input distribution, rather than directly accessing samples. Most natural algorithms of interest in theory and in practice, e.g., moments-based methods, local search, standard iterative methods for convex optimization, MCMC and simulated annealing, are statistical algorithms or have statistical counterparts. Our framework is inspired by and generalize the statistical query model in learning theory [34]. Our main application is a nearly optimal lower bound on the complexity of any statistical algorithm for detecting planted bipartite clique distributions (or planted dense subgraph distributions) when the planted clique has size 0(n1/2-6) for any constant (5 > 0. Variants of these problems have been assumed to be hard to prove hardness for other problems and for cryptographic applications. Our lower bounds provide concrete evidence of hardness, thus supporting these assumptions.

关键词： statistical algorithms Lower bounds Planted clique statistical query

来源：评论

学校读者我要写书评

暂无评论

iODA: An integrated tool for analysis of cancer pathway consistency from heterogeneous multi-omics data

引用

JOURNAL OF BIOMEDICAL INFORMATICS 2020年 112卷 103605-103605页

作者： Yu, Chunjiang Qi, Xin Lin, Yuxin Li, Yin Shen, Bairong Suzhou Ind Pk Inst Serv Outsourcing Sch Biotechnol Suzhou Peoples R China Suzhou Univ Sci & Technol Sch Chem Biol & Mat Engn Suzhou Peoples R China Soochow Univ Ctr Syst Biol Suzhou Peoples R China Sichuan Univ West China Hosp Frontiers Sci Ctr Dis Related Mol Network Inst Syst Genet Chengdu 610041 Peoples R China

The latest advances in the next generation sequencing technology have greatly facilitated the extensive research of genomics and transcriptomics, thereby promoting the decoding of carcinogenesis with unprecedented resolution. Considering the contribution of analyzing high-throughput multi-omics data to the exploration of cancer molecular mechanisms, an integrated tool for heterogeneous multi-omics data analysis (iODA) is proposed for the systems-level interpretation of multi-omics data, i.e., transcriptomic profiles (mRNA or miRNA expression data) and protein-DNA interactions (ChIP-Seq data). Considering the data heterogeneity, iODA can compare six statistical algorithms in differential analysis for the selected sample data and assist users in choosing the globally optimal one for dysfunctional mRNA or miRNA identification. Since molecular signatures are more consistent at the pathway level than at the gene level, the tool is able to enrich the identified dysfunctional molecules onto the KEGG pathways and extracted the consistent items as key components for further pathogenesis investigation. Compared with other tools, iODA is multi-functional for the systematic analysis of different level of omics data, and its analytical power was demonstrated through case studies of single and cross-level prostate cancer omics data. iODA is open source under GNU GPL and can be downloaded from http://***/iODA.

关键词： Next generation sequencing Omics data statistical algorithms Integrative analysis Pathway

来源：评论

学校读者我要写书评

暂无评论

statistical Inference on Desirability Function Optimal Points To Evaluate Multi-Objective Response Surfaces

Statistical Inference on Desirability Function Optimal Point...

引用

作者： Calhoun, P. A AIR FORCE INSTITUTE OF TECHNOLOGY WRIGHT-PATTERSON AFB OH GRADUATE SCHOOL OF ENGINEERING AND MANAGEMENT AIR FORCE INSTITUTE OF TECHNOLOGY WRIGHT-PATTERSON AFB OH

A shortfall of the Derringer and Suich (1980) desirability function is lack of inferential methods to quantify uncertainty. Most articles for addressing uncertainty usually involve robust methods, providing a point estimate that is less affected by variation. Few articles address confidence intervals or bands but not specifically for the Derringer and Suich method. This research provides two valuable contributions to the field of response surface methodology. The first contribution is evaluating the effect of correlation and plane angles on Derringer and Suich optimal solutions. The second contribution proposes and compares 8 inferential methodsboth univariate and multivariatefor creating confidence intervals on each desirability function solution for first order and second order models. The effect of the Derringer and Suich method parameters, objective plane angles, and differing correlation between response surfaces are examined through simulation. The 8 proposed methods include a simple best/worst case method, 2 generalized methods, 4 simulated surface methods, and a nonparametric bootstrap method. One of the generalized methods, 2 of the simulated surface methods, and the nonparametric method account for covariance between the response surfaces. Bivariate examples showcase these methods in the first order and second order models. A multivariate real-world case with 3 objectives is also examined. While all 7 novel methods and the best/worst method seem to perform decently on the second order models.

关键词： Information science Data science Experimental design statistical analysis Knowledge management statistical algorithms Air force statistical inference Statistics United states Engineering Random variables United states government Covariance Data mining Governments Information processing

来源：评论

学校读者我要写书评

暂无评论

Improving the Fairness of Coast Guard Recruitment and Selection with the ASVAB and AFCT: A Dynamic Measurement Modeling Paradigm

Improving the Fairness of Coast Guard Recruitment and Sele...

引用

作者： Dumas, D McNeish, D Dong, Y Duelberg, D OPM/USA Learning Center Center for Leadership development Washington DC OFFICE OF THE UNDER SECRETARY OF DEFENSE (PERSONNEL AND READINESS) WASHINGTON DC

A large-scale re-analysis of scores from the Armed Service Vocational Aptitude Battery/Armed Forces Classification Test (ASVAB/AFCT), the primary tools for military recruit accession and training qualification for occupational classification, was conducted using training data from the United States Coast Guard (USCG). The analysis evaluated whether these instruments could be used differently to increase the aperture for different candidate pools, including Underrepresented Minorities (URMs), for qualification into the Coast Guard, as well as qualification for a specific rate qualification. The idea to measure a recruit s learning capacity, by calculating the growth trajectories from in-between test scores, provides the military with more relevant information regarding trainability, which is a new and necessary focus for todays military due to advanced technical training requirements. The research found 10% of Coast Guard recruits re-take the ASVAB/AFCT in order to elevate composite scores, probably with the hopes of qualifying for their occupation of choice.

关键词： Propensity score matching Minority groups Information science Data science Data mining Psychology Students Surveys Coast guard Demography Educational psychology Knowledge management Probability statistical algorithms Statistics Applied psychology Behavioral research

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：