检索结果-南通市图书馆

Pharmaceutical digital transformation in China:digital quality assurance takes the driver’s seat

在线全文

学校读者我要写书评

暂无评论

生物设计与制造(英文) 2023年第5期6卷 609-615页

作者： Yuanyuan Ge Meng Cao Hui Cao Bin Han Jingchen Zhang Zhengyu Yi Yaowei Wu Beifen Zhu Keping Ruan Yiyi Pu Yi Zeng Tongjing Tao Zhenzhong Lyu Hongmei Yuan Guiliang Chen School of business administration Shenyang Pharmaceutical UniversityShenyang 110016China Shanghai Center for Drug Evaluation and inspection Shanghai 201203China Shanghai Pharmaceutical Profession Association Shanghai 200003China Sanofi(China)investment Co. Ltd.Shanghai 200040China Shanghai Dendreon Biopharmaceuticals Shanghai 201203China Shanghai Cellular Biomedicine Group Shanghai 201203China Fosun Kite Biotechnology Shanghai 201203China Merck Pharmaceuticals Nantong 226000China

The development of automation,the internet of Things(ioT),artificial intelligence(Ai),big data,and other digi-tal technologies has made it imperative for pharmaceutical companies to undergo digital transformation to improve their research and development capabilities,increase the quality of their products,lower operating costs,and gain a competitive *** of the most crucial steps in the life-cycle riskman-agement chain for drugs is digital quality assurance(DQA).Based on a literature review,questionnaire survey,and expert consensus,a panel of experts was convened in Shanghai to generate a set of conceptual,pharmaceutical manufacturing-specific DQA *** goal of the consensus is to advance common practices that use digital tools to quickly collect,record,evaluate,and review particular forms of data to enhance the automation of quality assurance and make drug quality activities more efficient.

关键词： ioT transformation companies

Convolutional Neural Network Based intelligent Handwritten Document Recognition

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2022年第3期70卷 4563-4581页

作者： Sagheer Abbas Yousef Alhwaiti Areej Fatima Muhammad A.Khan Muhammad Adnan Khan Taher M.Ghazal Asma Kanwal Munir Ahmad Nouh Sabri Elmitwally School of Computer Science National College of Business administration and EconomicsLahore54000Pakistan College of Computer and information Sciences Jouf UniversitySakaka72341Saudi Arabia Department of Computer Science Lahore Garrison UniversityLahore54000Pakistan Riphah School of Computing&innovation Faculty of ComputingRiphah International UniversityLahore CampusLahore54000Pakistan Pattern Recognition and Machine Learning Lab Department of SoftwareGachon UniversitySeongnam13557Korea Center for Cyber Security Faculty of Information Science and TechnologyUniversiti Kebangsaan Malaysia(UKM)Bangi 43600SelangorMalaysia School of information Technology Skyline University CollegeUniversity City Sharjah1797SharjahUAE Department of Computer Science GC UniversityLahorePakistan Department of Computer Science Faculty of Computers and Artificial IntelligenceCairo University12613Egypt

This paper presents a handwritten document recognition system based on the convolutional neural network *** today’s world,handwritten document recognition is rapidly attaining the attention of researchers due to its promising behavior as assisting technology for visually impaired *** technology is also helpful for the automatic data entry *** the proposed systemprepared a dataset of English language handwritten character *** proposed system has been trained for the large set of sample data and tested on the sample images of user-defined handwritten *** this research,multiple experiments get very worthy recognition *** proposed systemwill first performimage pre-processing stages to prepare data for training using a convolutional neural *** this processing,the input document is segmented using line,word and character *** proposed system get the accuracy during the character segmentation up to 86%.Then these segmented characters are sent to a convolutional neural network for their *** recognition and segmentation technique proposed in this paper is providing the most acceptable accurate results on a given *** proposed work approaches to the accuracy of the result during convolutional neural network training up to 93%,and for validation that accuracy slightly decreases with 90.42%.

关键词： Convolutional neural network segmentation skew cursive characters recognition

Customer Point Collaboration-Based Multi-trip Vehicle Scheduling Algorithm to Pickup and Delivery Service to Airport

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Customer Point Collaboration-Based Multi-trip Vehicle Schedu...

Ai-Based Hybrid Models for Predicting Loan Risk in the Banking Sector

第26届中国控制与决策会议

作者： XU Zhengzheng TANG Jiafu School of business administration Northeastern University State Key Laboratory of integrated Automation for Process industries Northeastern University

ISBN: (纸本)9781479937097

This paper studies the multi-trip vehicle scheduling problem with time window in the pickup and delivery service to airport. The collaboration and multi-trip approaches are used to improve the vehicle scheduling scheme’ performance and effectiveness. Firstly, the multi-trip optimal cost model with collaborations is presented to describe the vehicle scheduling problem in such a service. Then a heuristic method is proposed to find the optimal solution to this model. After sorting customer points via arriving time requirement and the constraints, the basic and collaborative routes can be built to finish the optimal vehicle scheduling meeting the given constraints. Simulation results show that the proposed approach is effective and feasible.

关键词： collaborative vehicle pickup and delivery service isolated points collaboration point basic vehicle

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Big Data Mining and Analytics 2023年第4期6卷 478-490页

作者： Vikas Kumar Shaiku Shahida Saheb Preeti Atif Ghayas Sunil Kumari Jai Kishan Chandel Saroj Kumar Pandey Santosh Kumar Humanities and Management Department Dr.B.R.Ambedkar National Institute of Technology JalandharJalandhar 144027India. Mittal School of business Lovely Professional UniversityPhagwara 144402India. Department of Commerce&business administration Kanya Maha Vidyalaya(KMV)Jalandhar 144004India School of Management Gitam(to be deemed university)Bangalore 561203India Government College for Women Indra Gandhi UniversityAteli 123021India. institute of Management Studies Kurukshetra UniversityKurukshetra 136119India Department of Computer Engineering and Applications GLA UniversityMathura 281406India Department of Management Jaipuriya Institute of ManagementJaipur 302033India

Every real-world scenario is now digitally replicated in order to reduce paperwork and human labor *** Learning(ML)models are also being used to make predictions in these *** forecasting requires knowledge of these machine learning models and their distinguishing *** datasets we use as input for each of these different types of ML models,yielding different *** choice of an ML model for a dataset is critical.A loan risk model is used to show how ML models for a dataset can be linked *** purpose of this study is to look into how we could use machine learning to quantify or forecast mortgage credit *** phrase refers to the process of evaluating massive amounts of data in order to derive useful information for making decisions in a variety of *** credit risk is considered,a method based on an examination of what caused and how mortgage credit risk affected credit defaults during the still-current economic crisis of 2021 will be *** approaches to credit risk calculation will be examined,ranging from the most basic to the most *** addition,we will conduct a case study on a sample of mortgage loans and compare the results of three different analytical approaches,logistic regression,decision tree,and gradient boost to see which one produced the most commercially useful insights.

关键词： Artificial intelligence(Ai) Machine Learning(ML) loan prediction Support Vector Machine(SVM) Random Forest(RF) accuracy

A new construction method of the scientific and technological innovation team and its multi-agent simulation 25th

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

A new construction method of the scientific and technologica...

QpefBD:A Benchmark Dataset Applied to Machine Learning for Minute-Scale Quantitative Precipitation Estimation and Forecasting

第25届中国控制与决策会议

作者： Sun Wei Yu Yang Zhu Huabo Wang Weidi Scholl of business administration Northeast University Dept of Systems Engineering of Northeast University

ISBN: (纸本)9781467355339

For overcoming the shortcomings of the existing method of the construction of scientific and technological innovation team, this paper proposes a new method. in the new method, the selected candidate has the higher similarity not only with the knowledge that team needs, but also with the selected persons previously. Therefore, this method may increase the knowledge communication greatly. By the simulation based on the Repast platform to compare the old method and our proposed method of the construction of scientific and technological innovation team, we validate the novel approach of scientific and technology innovative has the advantage..

关键词： scientific and technological innovation team construction multi-agent simulation

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Journal of Meteorological Research 2022年第1期36卷 93-106页

作者： Anyuan XiONG Na LiU Yujia LiU Shulin ZHi Linlin WU Yongjian XiN Yan SHi Yunjian ZHAN National Meteorological information Center China Meteorological AdministrationBeijing 100081 Jiangxi Meteorological Observatory Nanchang 330096 Anhui Weather Modification Office Hefei 230061

Nowcasts of strong convective precipitation and radar-based quantitative precipitation estimations have always been hot yet challenging issues in meteorological ***-driven machine learning,especially deep learning,provides a new technical approach for the quantitative estimation and forecasting of precipitation.A high-quality,large-sample,and labeled training dataset is critical for the successful application of machine-learning technology to a specific *** present study develops a benchmark dataset that can be applied to machine learning for minutescale quantitative precipitation estimation and forecasting(QpefBD),containing 231,978 samples of 3185 heavy precipitation events that occurred in 6 provinces of central and eastern China from April to October *** individual sample consists of 8 products of weather radars at 6-min intervals within the time window of the corresponding event and products of 27 physical quantities at hourly intervals that describe the atmospheric dynamic and thermodynamic *** data labels,i.e.,ground precipitation intensity and areal coverage of heavy precipitation at 6-min intervals,are also *** present study describes the basic components of the dataset and data processing and provides metrics for the evaluation of model performance on precipitation estimation and *** on these evaluation metrics,some simple and commonly used methods are applied to evaluate precipitation estimates and *** results can serve as the benchmark reference for the performance evaluation of machine learning models using this *** paper also gives some suggestions and scenarios of the QpefBD *** believe that the application of this benchmark dataset will promote interdisciplinary collaboration between meteorological sciences and artificial intelligence sciences,providing a new way for the identification and forecast of heavy precipitation.

关键词： machine learning benchmark dataset quantitative precipitation estimation precipitation forecast

New directions for artificial intelligence:human,machine,biological,and quantum intelligence

在线全文

学校读者我要写书评

暂无评论

Frontiers of information Technology & Electronic Engineering 2022年第6期23卷 984-990页

作者： Li WEiGANG Lirian Michi ENAMOTO Denise Leyi Li Geraldo Pereira ROCHA FiLHO Department of Computer Science Uniuersily of BrasiliaBasilia-DF 70910-900Bazil Faculty of Economics AdministrationAccounting and ActuariesUnversity of Sao PauloSao Paulo 05508-010Bazil

1 introduction This comment reviews the“once learning”mechanism(OLM)that was proposed by Weigang(1998),the subsequent success of“one-shot learning”in object categories(Li FF et al.,2003),and“youonly lookonce”(YO... 详细信息

关键词： directions intelligence subsequent

模拟中国四级行政尺度下耕地位移对粮食生产潜力的影响

在线全文

学校读者我要写书评

暂无评论

Journal of Geographical Sciences 2023年第1期33卷 18-36页

作者：杨柏寒盛思雨柯新利代先华卢新海 College of Public administration Central China Normal UniversityWuhan 430079China College of Public administration Huazhong Agricultural UniversityWuhan 430070China College of Public administration Huazhong University of Science and TechnologyWuhan 430074China

Cropland displacement, as an important characteristic of cropland change, places more emphasis on changes in spatial location than on quantity. The effects of cropland displacement on global and regional food production are of general concern in the context of urban expansion. Few studies have explored scale-effects, however, where cropland is displaced not only within, but also outside, the administrative boundary of a certain region. This study used a spatially explicit model(LANDSCAPE) to simulate the potential cropland displacement caused by urban land expansion from 2020 to 2040 at four scales of the Chinese administration system(national, provincial, municipal, and county levels). The corresponding changes in potential cereal production were then assessed by combining cereal productivity data. The results show that 4700 km^(2) of cropland will be occupied by urban expansion by 2040, and the same amount of cropland will be supplemented by forest, grassland, wetland, and unused land. The potential loss of cropland will result in the loss of 3.838×10^(6) tons of cereal production, and the additional cropland will bring 3.546×10^(6) tons, 3.831×10^(6) tons, 3.836×10^(6) tons, and 3.528×10^(6) tons of potential cereal production in SN(national scale), SP(provincial scale), SM(municipal scale), and SC(county scale), respectively. Both SN and SC are observed to make a huge difference in cereal productivity between the lost and the supplemented cropland. We suggest that China should focus on the spatial allocation of cropland during large-scale displacement, especially at the national level.

关键词： cropland displacement potential cereal production LANDSCAPE model scale-effects food security

3D Kronecker Convolutional Feature Pyramid for Brain Tumor Semantic Segmentation in MR imaging

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2023年第9期76卷 2861-2877页

作者： Kainat Nazir Tahir Mustafa Madni Uzair iqbal Janjua Umer Javed Muhammad Attique Khan Usman Tariq Jae-Hyuk Cha Medical imaging and Diagnostics Lab NCAIDepartment of Computer ScienceCOMSATS University IslamabadIslamabad44000Pakistan Department of Electrical and Computer Engineering COMSATS University IslamabadWah CampusWahPakistan Department of Computer Science HITEC UniversityTaxilaPakistan Department of Management information Systems College of Business AdministrationPrince Sattam Bin Abdulaziz UniversityAl-Kharj16273Saudi Arabia Department of Computer Science Hanyang UniversitySeoul04763Korea

Brain tumor significantly impacts the quality of life and changes everything for a patient and their loved *** a brain tumor usually begins with magnetic resonance imaging(MRi).The manual brain tumor diagnosis from the MRO images always requires an expert ***,this process is time-consuming and ***,a computerized technique is required for brain tumor detection in MRi *** the MRi,a novel mechanism of the three-dimensional(3D)Kronecker convolution feature pyramid(KCFP)is used to segment brain tumors,resolving the pixel loss and weak processing of multi-scale lesions.A single dilation rate was replaced with the 3D Kronecker convolution,while local feature learning was performed using the 3D Feature Selection(3DFSC).A 3D KCFP was added at the end of 3DFSC to resolve weak processing of multi-scale lesions,yielding efficient segmentation of brain tumors of different sizes.A 3D connected component analysis with a global threshold was used as a post-processing *** standard Multimodal Brain Tumor Segmentation 2020 dataset was used for model *** 3D KCFP model performed exceptionally well compared to other benchmark schemes with a dice similarity coefficient of 0.90,0.80,and 0.84 for the whole tumor,enhancing tumor,and tumor core,***,the proposed model was efficient in brain tumor segmentation,which may facilitate medical practitioners for an appropriate diagnosis for future treatment planning.

关键词： Brain tumor segmentation connect component analysis deep learning kronecker convolution magnetic resonance imaging