检索结果-内蒙古大学图书馆

2nd International Conference on Intelligent Cyber Physical Systems and Internet of Things (ICoICI)

作者： Sivalakshmi, P. Kavitha, U. Usha, r. Pattanaik, Ojasvi Maniraj, S. P. Srinivasan, C. RMK Coll Engn & Technol Dept Elect & Commun Engn Chennai Tamil Nadu India Veltech Rangarajan Dr Sagunthala R&D Inst Sci & T Sch Commerce Chennai Tamil Nadu India SA Engn Coll Dept Math Chennai Tamil Nadu India JNTU Dept Comp Sci & Engn Vignan Inst Management & Technol Women Hyderabad India SRM Inst Sci & Technol Fac Engn & Technol Dept Data Sci & Business Syst Chennai Tamil Nadu India Saveetha Univ Saveetha Sch Engn Saveetha Inst Med & Tech Sci Dept Comp Sci & Engn Chennai Tamil Nadu India

ISBN: (纸本)9798331540661;9798331540678

retail security and surveillance systems have transformed into data-driven smart solutions thanks to the fast development of technology. This paper presents a new method for improving retail shop security and surveillance by combining transfer learning (TL) algorithms with cloud-powered video analytics. It is now possible to remotely interpret, analyze, and store massive amounts of video data produced by security cameras using cloud computing capabilities. In addition, TL methods are used to customize pre-trained deep learning models for retail settings, allowing for precise event and anomaly identification. This method drastically reduces the computing load on local devices and makes surveillance systems more accurate and responsive. One of the main advantages of the proposed system is that it can monitor the store premises in real time. It can also automatically identify suspicious actions like stealing or damage and inform staff or security about possible risks. By using cloud infrastructure, the system can also adapt to changing security needs and expand dynamically to handle increasing data volumes. retailers may find useful information for refining shop layouts, product placements, and marketing tactics by integrating cloud-powered video analytics, which allows advanced functions like crowd analysis, heat mapping, and customer behavior analysis. A thorough plan for smart retail store security and surveillance, using cloud computing, video analytics, and TL algorithms to build a strong and effective system for protecting digital retail spaces.

关键词： real-time monitoring Anomaly detection Proactive alerting Crowd analysis Customer behavior retail optimization

来源：评论

学校读者我要写书评

暂无评论

Bayesian optimization design for dose-finding based on toxicity and efficacy outcomes in phase I/II clinical trials

引用

PHArMACEUTICAL STATISTICS 2021年第3期20卷 422-439页

作者： Takahashi, Ami Suzuki, Taiji Tokyo Inst Technol Sch Comp Dept Math & Comp Sci 2-12-1 Ookayama Meguro Tokyo 1528550 Japan Pfizer R&D Japan Clin Stat Biometr & Data Management Tokyo Japan Univ Tokyo Grad Sch Informat Sci & Technol Dept Math Informat Tokyo Japan RIKEN Ctr Adv Intelligence Project Tokyo Japan

In phase I trials, the main goal is to identify a maximum tolerated dose under an assumption of monotonicity in dose-response relationships. On the other hand, such monotonicity is no longer applied to biologic agents because a different mode of action from that of cytotoxic agents potentially draws unimodal or flat dose-efficacy curves. Therefore, biologic agents require an optimal dose that provides a sufficient efficacy rate under an acceptable toxicity rate instead of a maximum tolerated dose. Many trials incorporate both toxicity and efficacy data, and drugs with a variety of modes of actions are increasingly being developed;thus, optimal dose estimation designs have been receiving increased attention. Although numerous authors have introduced parametric model-based designs, it is not always appropriate to apply strong assumptions in dose-response relationships. We propose a new design based on a Bayesian optimization framework for identifying optimal doses for biologic agents in phase I/II trials. Our proposed design models dose-response relationships via nonparametric models utilizing a Gaussian process prior, and the uncertainty of estimates is considered in the dose selection process. We compared the operating characteristics of our proposed design against those of three other designs through simulation studies. These include an expansion of Bayesian optimal interval design, the parametric model-based EffTox design, and the isotonic design. In simulations, our proposed design performed well and provided results that were more stable than those from the other designs, in terms of the accuracy of optimal dose estimations and the percentage of correct recommendations.

关键词： Bayesian optimization biological agent dose‐ finding nonparametric method optimal dose

来源：评论

学校读者我要写书评

暂无评论

Aspect category and sentiment polarity detection using a permutation language-based transformer model

引用

Procedia Computer Science 2025年 258卷 4179-4189页

作者： Ashok Kumar Jayaraman Tina Ester Trueman Gayathri Ananthakrishnan Abirami Murugappan Erik Cambria Manikandan G Satanik Mitra HCLTech Engineering and R&D Services Chennai Tamil Nadu India Department of Computer Science University of the People California USA School of Computer Science Engineering and Information Systems Vellore Institute of Technology Vellore India Department of Information Science and Technology Anna University Chennai India College of Computing and Data Science Nanyang Technological University Nanyang Singapore School of Computer Science and Engineering Vellore Institute of Technology Vellore India Department of Management BITS Pilani India

Aspect-based sentiment analysis (ABSA) performs fine-grained analysis on text to determine a specific aspect category and a sentiment polarity. recently, machine learning models have played a key role in ABSA tasks. In particular, transformer-based pre-trained models have achieved promising results in natural language processing tasks. Therefore, we propose a permutation based XLNet fine-tuning model for aspect category detection and sentiment polarity detection. Our model learns bidirectional contexts via positional encoding and factorization order. We evaluate the proposed permutation language model on three ABSA datasets, namely, SentiHood, SemEval 2015, and SemEval 2016. Specifically, we studied the ABSA tasks in a constrained system with a multi-class environment. Our result indicates that the proposed permutation language model achieves a better result.

关键词： Aspect-based sentiment analysis permutation language model deep learning transformers multiclass classification

来源：评论

学校读者我要写书评

暂无评论

A Pearson correlation-based adaptive variable grouping method for large-scale multi-objective optimization

引用

INFOrMATION SCIENCES 2023年 639卷

作者： Zhang, Maoqing Li, Wuzhao Zhang, Liang Jin, Hao Mu, Yashuang Wang, Lei Henan Univ Technol Sch Artificial Intelligence & Big Data Zhengzhou 450001 Henan Peoples R China Minist Educ Engn Res Ctr Integrat & Applicat Digital Learning Beijing 100039 Peoples R China Polytech Wenzhou 325000 Zhejiang Peoples R China Jiangsu Prov Support Software Engn R&D Ctr Modern Suzhou 215104 Peoples R China Tongji Univ Sch Elect & Informat Engn Shanghai 201804 Peoples R China Shanghai Univ Finance & Econ Sch Stat & Management Shanghai 200433 Peoples R China

dividing variables into groups is an intuitive idea for tackling large-scale multi-objective problems. However, regular grouping methods often suffer from the computationally expensive budget, resulting in the inflexibility of the division of variables. To remedy this issue, this paper proposes a Pearson correlation-based adaptive variable grouping method, which not only consumes no additional computational budget, but also is able to adaptively divide variables with the evolvement of solutions. According to our observation, variables with similar effects on objectives exhibit similar evolutionary trends. Therefore, the Pearson correlation coefficient is used to measure the similarities of the evolutionary trends of variables. Based on the Pearson correlation-based adaptive variable grouping method, this paper further designs a weighted optimization framework based on Pearson correlation-based adaptive variable grouping. Experiments and analyses are conducted on three popular test suites with up to 5000 decision variables. Extensive comparisons demonstrate that the proposed Pearson correlation-based adaptive variable grouping method is superior to existing grouping methods and the weighted optimization framework based on Pearson correlation-based adaptive variable grouping outperforms state-of-the-art optimizers.

关键词： Large scale multi-objective optimization Grouping method decision variable Computational budget Pearson correlation coefficient

来源：评论

学校读者我要写书评

暂无评论

Constructing a Blockchain-Based Loyalty Program Model for Secure and Transparent Customer rewards in retail Marketing

Constructing a Blockchain-Based Loyalty Program Model for Se...

引用

International Conference on Communication Systems and Network Technologies (CSNT)

作者： Ch. Anudeep Kathari Santosh M Sandeep Kumar Jahnavi M Sabareesh r B Kiran Bala GITAM school of business GITAM University Visakhapatnam A.P. Department of MBA CMR Institute of Technology Bengaluru India RV Institute of Management Bengaluru India Skill Development & Employability Programs Fortuna Business Solutions(R&D) Coimbatore Tamil Nadu Department of Artificial Intelligence and Data Science K. Ramakrishnan college of Engineering Trichy TN

ISBN: (数字)9798350305463

ISBN: (纸本)9798350305470

As the retail industry continues to evolve in the digital era, businesses are exploring innovative solutions to enhance customer engagement and loyalty. This research proposes a novel approach to loyalty programs by leveraging blockchain technology to create a secure and transparent model for customer rewards. Traditional loyalty programs often face challenges related to security, transparency, and trust, leading to issues such as fraud and customer skepticism. The proposed model outlines the design and implementation of a blockchainbased loyalty program, ensuring a secure and immutable ledger for tracking customer transactions and rewards. Smart contracts, self-executing contracts with predefined rules, are utilized to automate and enforce the terms of the loyalty program, reducing the potential for disputes and enhancing transparency. The decentralized nature of the blockchain ensures that customer data is securely stored and accessible only to authorized parties, addressing privacy concerns prevalent in centralized loyalty systems. This research employs a mix of theoretical analysis and practical implementation to validate the feasibility and effectiveness of the blockchain-based loyalty program model. The proposed Ethereum Blockchain model stands out with a significantly higher throughput of 5300 transactions per day, accompanied by an exceptional transaction transparency score of 99.5 .

关键词： Industries data privacy Communication systems Smart contracts Throughput Blockchains Fraud

来源：评论

学校读者我要写书评

暂无评论

radiographic and clinical effects of 10 mg and 25 mg twice-weekly etanercept over 52 weeks in Japanese patients with active rheumatoid arthritis

引用

MOdErN rHEUMATOLOGY 2021年第2期31卷 319-325页

作者： Takeuchi, Tsutomu Miyasaka, Nobuyuki Pedersen, ron d. Sugiyama, Noriko Hirose, Tomohiro Keio Univ Sch Med Dept Internal Med Div Rheumatol Tokyo Japan Tokyo Med & Dent Univ Grad Sch Dept Med & Rheumatol Tokyo Japan Pfizer Collegeville PA USA Pfizer R&D Japan Clin Stat Biometr & Data Management Tokyo Japan Pfizer Japan Inc Immunol & Inflammat Med Affairs Innovat Med Business Tokyo Japan

Objectives To compare the radiographic and clinical effects of 25 versus 10 mg twice-weekly (BIW) etanercept over 52 weeks in Japanese patients with active rheumatoid arthritis (rA). Methods This was apost-hocanalysis of a Phase 3 study where Japanese patients with active rA were randomized to receive BIW etanercept 25 mg (n = 182), etanercept 10 mg (n = 192), or methotrexate (n = 176) for 52 weeks (NCT00445770). This analysis included assessments of week-24 and week-52 disease activity, week-52 radiographic progression, and the relationship between baseline characteristics and week 52 clinical outcomes with clinically relevant radiographic progression (CrrP) at week 52. results At week 52, there were no significant differences between 25 and 10 mg etanercept in terms of achieving low disease activity or remission. CrrP was observed in 36% and 32% of patients in the 10 and 25 mg groups, respectively. Predictor analysis suggested that worse background disease status, treatment with methotrexate rather than etanercept, and poorer clinical outcomes at week 52 were associated with CrrP. Conclusions The 25 mg BIW etanercept dosage does not appear to be significantly more efficacious than 10 mg in Japanese patients with rA. Further studies evaluating the optimal etanercept dosing regimen in this patient population may be merited. NCT: NCT00445770

关键词： Etanercept rheumatoid arthritis Japan clinical trial methotrexate

来源：评论

学校读者我要写书评

暂无评论

Safety and pharmacokinetics (PK) of vepdegestrant in Japanese patients with estrogen receptor (Er) plus /human epidermal growth factor receptor 2 (HEr2)- advanced breast cancer: results from a Japanese phase I study

引用

ANNALS OF ONCOLOGY 2023年 34卷 S1488-S1489页

作者： Iwata, H. Naito, Y. Hattori, M. Yoshimura, A. Yonemori, K. Aizawa, M. Mori, Y. Yoshimitsu, J. Umeyama, Y. Mukohara, T. Aichi Canc Ctr Hosp Dept Breast Oncol Nagoya Aichi Japan Natl Canc Ctr Hosp East Dept Med Oncol Kashiwa Chiba Japan Natl Canc Ctr Dept Med Oncol Tokyo Japan Pfizer R&D Japan Dept Biometr & Data Management Tokyo Japan Pfizer R&D Japan Dept Clin Res Tokyo Japan Natl Canc Ctr Hosp East Dept Med Oncol Kashiwa Chiba Japan

58P

关键词：

来源：评论

学校读者我要写书评

暂无评论

Probabilistic forecasting with temporal convolutional neural network

引用

NEUrOCOMPUTING 2020年 399卷 491-501页

作者： Chen, Yitian Kang, Yanfei Chen, Yixiong Wang, Zizhuo Bigo Inc Bigo Beijing R&D Ctr Beijing 100191 Peoples R China Beihang Univ Sch Econ & Management Beijing 100191 Peoples R China IBM China CIC KIC Technol Ctr Shanghai 200433 Peoples R China Chinese Univ Hong Kong Inst Data & Decis Analyt Shenzhen 518172 Peoples R China

We present a probabilistic forecasting framework based on convolutional neural network (CNN) for multiple related time series forecasting. The framework can be applied to estimate probability density under both parametric and non-parametric settings. More specifically, stacked residual blocks based on dilated causal convolutional nets are constructed to capture the temporal dependencies of the series. Combined with representation learning, our approach is able to learn complex patterns such as seasonality, holiday effects within and across series, and to leverage those patterns for more accurate forecasts, especially when historical data is sparse or unavailable. Extensive empirical studies are performed on several real-world datasets, including datasets from ***, China's largest online retailer. The results show that our framework compares favorably to the state-of-the-art in both point and probabilistic forecasting. (c) 2020 Elsevier B.V. All rights reserved.

关键词： Probabilistic forecasting Convolutional neural network dilated causal convolution demand forecasting High-dimensional time series

来源：评论

学校读者我要写书评

暂无评论

Framework for sensitization assessment of extractables and leachables in pharmaceuticals

引用

CrITICAL rEVIEWS IN TOXICOLOGY 2022年第2期52卷 125-138页

作者： Parris, Patricia Whelan, Geraldine Burild, Anders Whritenour, Jessica Bruen, Uma Bercu, Joel Callis, Courtney Graham, Jessica Johann, Esther Griffin, Troy Kohan, Martin Martin, Elizabeth A. Masuda-Herrera, Melisa Stanard, Brad Tien, Eric Cruz, Maureen Nagao, Lee Pfizer Worldwide Res Dev & Med Ramsgate Rd Sandwich CT13 9NJ Kent England GlaxoSmithKline Ware Herts England Novo Nordisk AS Safety Sci Imaging & Data Management Malov Denmark Pfizer Worldwide Res Dev & Med Groton CT USA Organon USA Inc Jersey City NJ USA Gilead Sci Inc 353 Lakeside Dr Foster City CA 94404 USA Eli Lilly & Co Lilly Res Labs Indianapolis IN 46285 USA Genentech Inc San Francisco CA 94080 USA Merck KGaA Darmstadt Germany Teva Branded Pharmaceut Prod R&D W Chester PA USA AstraZeneca Clin Pharmacol & Safety Sci R&D Cambridge England Ultragenyx Pharmaceut Inc Novato CA USA Biogen Inc 14 Cambridge Ctr Cambridge MA 02142 USA Faegre Drinker Biddle & Reath LLP Washington DC USA

during the toxicological assessment of extractables and leachables in drug products, localized hazards such as irritation or sensitization may be identified. Typically, because of the low concentration at which leachables occur in pharmaceuticals, irritation is of minimal concern;therefore, this manuscript focuses on sensitization potential. The primary objective of performing a leachable sensitization assessment is protection against Type IV induction of sensitization, rather than prevention of an elicitation response, as it is not possible to account for the immunological state of every individual. Sensitizers have a wide range of potencies and those which induce sensitization upon exposure at a low concentration (i.e. strong, or extreme sensitizers) pose the highest risk to patients and should be the focus of the risk assessment. The Extractables and Leachables Safety Information Exchange (ELSIE) consortium has reviewed the status of dermal, respiratory, and systemic risk assessment in cosmetic and pharmaceutical industries, and proposes a framework to evaluate the safety of known or potential dermal sensitizers in pharmaceuticals. due to the lack of specific regulatory guidance on this topic, the science-driven risk-based approach proposed by ELSIE encourages consistency in the toxicological assessment of extractables and leachables to maintain high product quality and ensure patient safety.

关键词： Extractables leachables sensitization risk assessment

来源：评论

学校读者我要写书评

暂无评论

A survey of Bayesian statistical methods in biomarker discovery and early clinical development

引用

Communications in Statistics Case Studies data Analysis and Applications 2024年第1期10卷 67-93页

作者： Paul, Erina Afzal, Avid M. Brown, roland Cao, Shanshan Liu, Yushi Matejovicova, Tatiana Porwal, Anupreet Sun, Zhe Baumgartner, richard Mallick, Himel Biostatistics and Research Decision Sciences Merck & Co. Inc Rahway NJ United States Data Sciences & Quantitative Biology Discovery Sciences R&D AstraZeneca Cambridge United Kingdom Nonclinical and Biomarker Biostatistics Biogen Inc Cambridge MA United States Global Statistical Science Lilly Research Laboratories Eli Lilly and Company Indianapolis IN United States Department of Statistics University of Washington Seattle WA United States Division of Biostatistics Department of Population Health Sciences Weill Cornell Medicine Cornell University New York NY United States Department of Statistics and Data Science Cornell University Ithaca NY United States

The increasing importance of uncertainty quantification in the regulatory evaluation of pharmaceutical products has triggered an explosion of Bayesian methods in recent years. In biomarker discovery and early clinical development, Bayesian methods have established a foothold in developing new drugs, in part due to the increasing availability of greater computational power, often complementing both traditional pharmaceutical statistics and classical statistical methods. In this paper, we present a selective survey of the recent efforts that have been made toward the development and application of effective statistical and computational models in early development statistics. The survey introduces four such case studies and methods that can be used for end-to-end biomarker discovery that includes pre-clinical and early clinical development, from unsupervised clustering to supervised machine learning to modern statistical inference, including but not limited to Bayesian clustering, Bayesian additive regression trees, Bayesian neural networks, and empirical Bayes procedures with the overarching goal of promoting their use and applications among pharmaceutical statisticians. Finally, we present some open issues in Bayesian early clinical methods to help guide the future advancement and wide adoption of Bayesian applications in early clinical pharmaceutical statistics. © 2023 Taylor & Francis Group, LLC.

关键词： Bayesian additive regression trees Bayesian clustering Bayesian discovery Bayesian neural networks early development statistics empirical Bayes

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：