检索结果-内蒙古大学图书馆

作者： She, Dongdong Columbia University

学位级别：Ph.D., Doctor of Philosophy

Security vulnerabilities have a large real-world impact, from ransomware attacks costing billions of dollars every year to sensitive data breaches in government, military and industry. Fuzzing is a popular technique to discover these vulnerabilities in an automated fashion. Industries have poured tons of resources into building large-scale fuzzing factories (e.g., Google’s ClusterFuzz and Microsoft’s OneFuzz) to test their products and make their product more secure. Despite the wide application of fuzzing in industry, there remain many issues constraining its performance. One fundamental limitation is the rule-based design in fuzzing. Rule-based fuzzers heavily rely on a set of static rules or heuristics. These fixed rules are summarized from human experience, hence failing to generalize on a diverse set of programs. In this dissertation, we present an adaptive and effective fuzzing framework in data-driven approach. A data-driven fuzzer makes decisions based on the analysis and reasoning of data rather than the static rules. Hence it is more adaptive, effective, and flexible than a typical rule-based fuzzer. More interestingly, the data-driven approach can bridge the connection from fuzzing to various data-centric domains (e.g., machine learning, optimizations and social network), enabling sophisticated designs in the fuzzing framework. A general fuzzing framework consists of two major components: seed scheduling and seed mutation. The seed scheduling module selects a seed from a seed corpus that includes multiple testcases. Then seed mutation module applies perturbation on the selected seed to generate a new testcase. First, we present Neuzz, the first machine learning (ML) based general-purpose fuzzer that adopts ML to seed mutation and greatly improves fuzzing performance. Then we present MTFuzz, a follow-up work of Neuzz by including diverse data into ML to generate effective seed mutations. In the end, we present K-Scheduler, a fuzzer-agnostic seed scheduling

关键词： Fuzzing Machine learning Software testing Security vulnerabilities data-driven approach

来源：评论

学校读者我要写书评

暂无评论

A systematic data-driven approach for targeted marketing in enterprise information system

引用

ENTERPRISE INFORMATION SYSTEMS 2024年第8期18卷

作者： Upadhyay, Utsav Kumar, Alok Sharma, Gajanand Sharma, Satyajeet Arya, Varsha Panigrahi, Prabin Kumar Gupta, Brij B. Sir Padampat Singhania Univ Dept Comp Sci & Engn Udaipur India JECRC Univ Dept Comp Sci & Engn Jaipur India Asia Univ Dept Business Adm Taichung Taiwan Lebanese Amer Univ Dept Elect & Comp Engn Beirut Lebanon Indian Inst Management Indore Dept Informat Syst Indore India Asia Univ Dept Comp Sci & Informat Engn Taichung 413 Taiwan Symbiosis Int Univ Symbiosis Ctr Informat Technol SCIT Pune India Univ Petr & Energy Studies UPES Ctr Interdisciplinary Res Dehra Dun India

In the rapidly evolving landscape of digital marketing, leveraging data analytics within Enterprise Information Systems (EIS) has become crucial for businesses aiming to understand and engage their customers more effectively. This study presents a comprehensive analysis of data-driven marketing strategies, emphasising the critical role of diverse data sources in developing targeted, EIS-specific campaigns. Central to our investigation is a comparative analysis of various machine learning algorithms, including Random Forest, CART, Support Vector Machine, Linear Discriminant Analysis, Logistic Regression, K-Nearest Neighbours, and Na & iuml;ve Bayes. Our selection and evaluation of these models are grounded in their ability to address the complex dynamics of customer behaviour and marketing data, demonstrating the superior efficacy of Random Forest and CART in this context.

关键词： Enterprise information systems targeted marketing data-driven approach machine learning techniques advanced data analytics in marketing marketing strategy optimization

来源：评论

学校读者我要写书评

暂无评论

A data-driven approach using the remotely sensed soil moisture product to identify water-demand in agricultural regions

引用

SCIENCE OF THE TOTAL ENVIRONMENT 2022年 837卷 155893页

作者： Singh, Gurjeet Das, Narendra N. CALTECH Radar Sci & Engn Sect NASA Jet Prop Lab Pasadena CA USA Michigan State Univ Biosyst & Agr Engn E Lansing MI 48824 USA Michigan State Univ Civil & Environm Engn E Lansing MI USA

Effective agricultural water management requires accurate and timely identification of crop water stress at the farm scale for irrigation advisories or to allocate the optimal amount of water for irrigation. Various drought indices are being utilized to map the water-stressed locations/farms in agricultural regions. Most of these existing drought indices provide some degree of characterization of water stress but do not adequately provide spatially resolved high resolution (farm-scale) information for decision-making about irrigation advisories or water allocation. These existing drought indices need modeling and climatology information, hence making them data-intensive and complex to compute. Therefore, a reliable, simple, and computationally easy method without modeling to characterize the water stress at high-resolution is essential for the operational mapping of water-stressed farms in agricultural regions. The proposed new approach facilitates improved and quick decision-making without compromising much of the skills imparted by the established drought indices. This study aims to formulate a water-demand index (WDI) based on a parameter independent data-driven approach using readily available remote sensing observations and weather data. We hypothesize that the WDI for an agricultural domain can be characterized by soil moisture, vegetative growth (NDVI), and heat unit (growing degree day, GDD). To this end, we used remote sensing-based soil moisture and NDVI and modeled ambient temperature datasets to generate weekly WDI maps at 1 km. The proposed methodology is verified over a few intensively irrigated agricultural-dominated areas with different climatic conditions. Our results suggest that the proposed approach characterizes water-stressed fields through WDI maps with good spatial representativeness. Overall, this study provides a framework to generate weekly WDI maps quickly with readily available measurements. These water-demand maps will help water resour

关键词： Agricultural water management data-driven approach High-resolution SMAP-Sentinel Soil moisture Water-demand Water-stressed

来源：评论

学校读者我要写书评

暂无评论

Extending the total neutron emission rate of steady-state deuterium large helical plasma guided by a data-driven approach

引用

FUSION ENGINEERING AND DESIGN 2021年 167卷

作者： Ogawa, Kunihiro Isobe, Mitsutaka Yokoyama, Masayuki Natl Inst Nat Sci Natl Inst Fus Sci Toki Gifu 5095292 Japan Grad Univ Adv Studies SOKENDAI Toki Gifu 5095292 Japan

A trial for extending the total neutron emission rate (Sn) was performed in the Large Helical Device (LHD) deuterium plasma experiment using a gas puff in order to show the way to realize a steady-state fusion reactor. In the 22nd experimental campaign of the LHD, a high Sn discharge was performed by the experimental scenario guided by a data-driven approach. A regression analysis of Sn was conducted beforehand using the externally controllable parameters based on the database of the previous three campaigns. Then, the high Sn record was successfully updated to be 3.7 x 1015 n/s in a steady-state discharge during the 22nd campaign in line with the regression expression. This study demonstrates that such a data-driven approach is effective for the gradual extension of Sn beyond the employed database.

关键词： LHD Deuterium experiment Total neutron emission rate data-driven approach Steady-state plasmas

来源：评论

学校读者我要写书评

暂无评论

Investigating the bulk density of construction waste: A big data-driven approach

引用

RESOURCES CONSERVATION AND RECYCLING 2021年 169卷

作者： Lu, Weisheng Yuan, Liang Xue, Fan Univ Hong Kong Fac Architecture Dept Real Estate & Construct Hong Kong Peoples R China

Construction waste contains inert (e.g., construction debris, rubble, earth, bitumen, and concrete) and non-inert materials (e.g., bamboo, plastics, wood, paper, and vegetation), while it is often a combination of the two when it is generated at source. The bulk density of construction waste is the yardstick information for many subsequent waste management efforts. One feasible way to derive the bulk density information is to segregate the mixture of inert and non-inert substances and examine their compositions, but clearly, this is an onerous task. This paper reports a data-driven approach to obtain the bulk densities of inert and non-inert construction waste by analyzing a big dataset of 4.9 million loads of construction waste in Hong Kong in the years 2017 to 2019. It is discovered that the means of bulk density are 336 kg/m(3) for non-inert waste, 528 kg/m(3) for mixed waste, and 991 kg/m(3) for inert waste, and their coefficients of variation are 69%, 43%, and 29%, respectively. The research not only proved our heuristic rules concerning the bulk densities of the three generic types of construction waste, but also articulated, for the first time, their converged means and ranges. The findings can be used in adjusting the admission criteria as adopted in the governmental waste management facilities. Future research is recommended to further narrow down the bulk density ranges to provide more accurate references for construction waste management.

关键词： Construction waste management Inert waste Non-inert waste Bulk density Big data data-driven approach

来源：评论

学校读者我要写书评

暂无评论

Key Parameters for Economic Valuation of V2G Applied to Ancillary Service: data-driven approach

引用

ENERGIES 2022年第23期15卷

作者： Kim, Junhyung Kim, Jinho Jeong, Hwanmin Gwangju Inst Sci & Technol Sch Integrated Technol Gwangju 61005 South Korea

Global automakers are speeding up both the suspension of production of internal combustion engine vehicles and the transition to electric vehicles (EVs) in order to respond to global goals to become carbon-free and energy-efficient. Recently, vehicle-to-grid (V2G) technology has reached the commercialization stage in Korea. Many studies have mostly discussed profits that an EV owner can make by participating in a regulation program. However, all the stakeholders who are involved with V2G service have not been sufficiently considered. Thus, we propose a novel framework for the economic valuation of V2G in ancillary service. Furthermore, to estimate the available capacity of V2G and find an optimal strategy in order for the V2G service to run, a data-driven approach is proposed in this research. Comprehensive simulation results show the optimal situation requiring the minimum financial support for the EV owner when the V2G-service operator aggregates AC chargers. In addition, promotions from government and public utilities can accelerate the V2G service into the ancillary service. As a final remark, given the flexibility of the proposed framework, it could be adapted to validate its performance in other countries, as part of future works.

关键词： vehicle-to-grid (V2G) ancillary service stakeholder economic analysis data-driven approach

来源：评论

学校读者我要写书评

暂无评论

A data-driven approach to Trace the Development of Lean Construction in Building Projects: Topic Shift and Main Paths

引用

BUILDINGS 2022年第5期12卷

作者： Wu, Hengqin Lin, Xue Li, Xiao Zhang, Boyu Li, Clyde Zhengdao Duan, Huabo Shenzhen Univ Coll Civil & Transportat Engn Shenzhen 518060 Peoples R China Hong Kong Polytech Univ Dept Bldg & Real Estate Hong Kong 999077 Peoples R China Nanjing Univ Sch Govt Nanjing 210093 Peoples R China China Acad Bldg Res Dept Sci Technol & Stand Beijing 100029 Peoples R China Shenzhen Univ Underground Polis Acad Coll Civil & Transportat Engn Shenzhen 518060 Peoples R China

Due to the varied ideas of lean philosophy adopted in the construction industry, it is challenging to trace the development of lean philosophy in terms of how the field evolved by adopting the lean ideas and how the topic shifted. However, it is challenging to extract useful information from the massive body of literature and to trace the development of Lean Construction in Building Projects. Previous studies have conducted longitudinal analyses of scientific areas depending on the authors' interpretation and explanation, which is time-consuming and labor-intensive. To address this concern, this study proposes a data-driven approach integrating N-gram extraction, citation analysis, and a global key-route algorithm to trace the development. Based on the collected literature of Lean Construction in Building Projects, N-grams were extracted as topics from the raw texts of titles, abstracts, and keywords, and the shifts in topics were measured. Then, the references were extracted from the literature to create a citation network to represent the knowledge flows, and the global key-route algorithm was used to identify the most valuable flows reflecting the main paths of the development. The results illustrate how Lean Construction in Building Projects evolved and how the topics shifted, providing an exciting opportunity to reveal this development by using a data-driven approach rather than personal judgments. The findings can help us to understand that the field of Lean Construction in Building Projects was driven and motivated not only by the "lean theory", but also by problems in the practice of building projects. Moreover, lean theory leads to flourishing research on informatization, and BIM will be an important tool to better achieve lean thinking in construction.

关键词： lean philosophy Building Projects N-gram main paths data-driven approach

来源：评论

学校读者我要写书评

暂无评论

New Gap-Filling Strategies for Long-Period Flux data Gaps Using a data-driven approach

引用

ATMOSPHERE 2019年第10期10卷

作者： Kang, Minseok Ichii, Kazuhito Kim, Joon Indrawati, Yohana M. Park, Juhan Moon, Minkyu Lim, Jong-Hwan Chun, Jung-Hwa Natl Ctr Agro Meteorol Seoul 08826 South Korea Chiba Univ Ctr Environm Remote Sensing Chiba 2638522 Japan Seoul Natl Univ Dept Landscape Architecture & Rural Syst Engn Seoul 08826 South Korea Seoul Natl Univ Interdisciplinary Program Agr & Forest Meteorol Seoul 08826 South Korea Seoul Natl Univ Res Inst Agr & Life Seoul 08826 South Korea Seoul Natl Univ Asia Ctr Future Earth Program Seoul 08826 South Korea Seoul Natl Univ Inst Green Bio Sci & Technol Pyeongchang Campus Pyeongchang 25354 South Korea Boston Univ Dept Earth & Environm Boston MA 02215 USA Natl Inst Forest Sci Forest Ecol & Climate Change Div Seoul 02455 South Korea Natl Inst Forest Sci Res Planning & Coordinat Div Seoul 02455 South Korea

In the Korea Flux Monitoring Network, Haenam Farmland has the longest record of carbon/water/energy flux measurements produced using the eddy covariance (EC) technique. Unfortunately, there are long gaps (i.e., gaps longer than 30 days), particularly in 2007 and 2014, which hinder attempts to analyze these decade-long time-series data. The open source and standardized gap-filling methods are impractical for such long gaps. The data-driven approach using machine learning and remote-sensing or reanalysis data (i.e., interpolating/extrapolating EC measurements via available networks temporally/spatially) for estimating terrestrial CO2/H2O fluxes at the regional/global scale is applicable after appropriate modifications. In this study, we evaluated the applicability of the data-driven approach for filling long gaps in flux data (i.e., gross primary production, ecosystem respiration, net ecosystem exchange, and evapotranspiration). We found that using a longer training dataset in the machine learning generally produced better model performance, although there was a greater possibility of missing interannual variations caused by ecosystem state changes (e.g., changes in crop variety). Based on the results, we proposed gap-filling strategies for long-period flux data gaps and used them to quantify the annual sums with uncertainties in 2007 and 2014. The results from this study have broad implications for long-period gap-filling at other sites, and for the estimation of regional/global CO2/H2O fluxes using a data-driven approach.

关键词： eddy covariance long-term database gap-filling long gap data-driven approach uncertainty

来源：评论

学校读者我要写书评

暂无评论

A data-driven approach for Decision-Making support of factory simulation solutions

引用

Procedia CIRP 2020年 93卷 971-976页

作者： Fei Yu Christian P. Nielsen University of Southern Denmark Alsion 2 Sønderborg 6400 Denmark

Factory simulation, one of the Industry 4.0 technologies, has increased in popularity. However, there is a limited number of strategies on how to implement this technology. This paper describes a data-driven approach that supports the Decision-Making process of factory simulation solutions. A performed literature review focused on manufacturing simulation frameworks, criteria for simulation solution selection, software evaluation methodologies, and simulation solutions, creates the foundation for the key contribution. An industrial case is used to test the initial findings. In addition, to suggest solutions as the output, the approach triggers the process of learning and thinking, which shows more value to practitioners.

关键词： Decision-making factory simulation data-driven approach

来源：评论

学校读者我要写书评

暂无评论

Predicting vessel service time: A data-driven approach

引用

ADVANCED ENGINEERING INFORMATICS 2024年 62卷

作者： Yan, Ran Chu, Zhong Wu, Lingxiao Wang, Shuaian Nanyang Technol Univ Sch Civil & Environm Engn 50 Nanyang Ave Singapore Singapore Hong Kong Polytech Univ Fac Business Dept Logist & Maritime Studies Hong Kong Peoples R China Hong Kong Polytech Univ Fac Engn Dept Aeronaut & Aviat Engn Hong Kong Peoples R China

Vessel Service Time (VST) refers to the period from when a ship arrives at a berth until it departs. VST is a critical metric for port operational efficiency and service quality. Uncertainty in VST can undermine the operational efficiency in port management and lead to financial setbacks. To mitigate this uncertainty and lay the foundation for subsequent berth allocation, vessels typically provide an estimated departure time (EDT). However, substantial discrepancies often exist between the reported EDT and the actual departure time (ADT). These discrepancies mainly stem from unforeseen port handling inefficiencies and supply chain disruptions. This variability results in significant differences between the actual VST and its anticipated duration, thereby complicating port operations. To tackle this issue, our research represents the first study to predict VST from a data-driven perspective. We introduce an advanced tree-based stacking regression model for VST prediction, utilizing vessel port call records from 2020 to 2023. Our machine learning stacking approach achieves more accurate VST predictions than EDT reported by vessels, significantly reducing the mean absolute error (MAE) by 29.7% (from 4.54 to 3.19 h) and the root mean square error (RMSE) by 31.9% (from 6.58 to 4.48 h). The model also demonstrates reliable predictive power with an R-squared (R2) R 2 ) value of 0.8. These results underscore the significant scientific value of data-driven approaches in maritime studies. Our findings highlight the potential of the proposed tree-based models to surpass traditional models and originally reported data in predictive accuracy for VST. This advancement not only represents a notable improvement in predictive capabilities for VST but also lays the groundwork for further research into enhancing vessel scheduling efficiency through machine learning.

关键词： Maritime transport Port management and optimization Vessel service time prediction Machine learning in port operations data-driven approach

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：