检索结果-内蒙古大学图书馆

3rd IEEE International Conference on Electronic Communications, Internet of Things and Big Data, ICEIB 2023

作者： Zou, Xue-Ling Han, Kai-Xu Chien, Wei Gan, Xin-Yan Shi, Liu-Yue School of Electric and Information Engineering Beibu Gulf University Qinzhou China School of Information Management and Master's Program Lunghwa University of Science and Technology Taoyuan City Taiwan Guangxi University of Chinese Medicine Nanning China

ISBN: (纸本)9798350333862

Deep learning has excellent learning and feature classification abilities, extracting features in massive, multi-source, and high-dimensional measurement data. It also diagnoses and generalizes models without relying on manual intervention. Thus, it is widely used in equipment fault diagnosis. We introduce the common models of deep learning: deep confidence network, convolutional neural network, and automatic encoder. Using deep learning, the fault diagnosis of rolling bearings is executed, and the result provides the basis for future development. © 2023 IEEE.

关键词： Failure analysis

来源：评论

学校读者我要写书评

暂无评论

Improving Supplier Evaluation Model using Ensemble Method-Machine Learning for Food Industry

引用

Procedia Computer science 2023年 227卷 307-315页

作者： Muhammad Asrol Sofyan Wahyudi Suharjito Christian Harito Ditdit N Utama Muhammad Syafrudin Industrial Engineering Department BINUS Graduate Program – Master of Industrial Engineering Bina Nusantara University Jakarta 11480 Indonesia Computer Science Department BINUS Graduate Program – Master of Computer Science Bina Nusantara University Jakarta 11480 Indonesia Department of Artificial Intelligence Sejong University Seoul 05006 South Korea

Supplier evaluation has a crucial role in maintaining efficiency in the food industry supply chain. Machine learning approaches can be employed to formulate models aimed at analyzing and evaluating supplier performance. Previous research has successfully designed decision tree and neural network models for assessing suppliers in the food industry with accuracies of 84.2% and 92.8% separately. Recognizing the opportunity to improve the model's performance, this study aims to advancing the machine learning models accuracy for analyzing and evaluating suppliers in the food industry. Two main models are proposed to enhance model accuracy: ensemble methods and support vector machine. This research has successfully designed a supplier evaluation model and demonstrated that the ensemble method - gradient boosting model outperforms other ensemble methods and support vector machine which is achieved a accuracy of 93.6% on a cross-validation dataset. The development of a dashboard is required to implement the supplier evaluation model using machine learning, facilitating decision-makers in evaluating and controlling supplier performance.

关键词： Ensemble Method Food Machine Learning Supply chain Supplier evaluation

来源：评论

学校读者我要写书评

暂无评论

Measurement of key performance indicator Green Supply Chain Management (GSCM) in palm industry with green SCOR model

引用

Materials Today: Proceedings 2022年 63卷 S326-S332页

作者： Rosyidah, Masayu Khoirunnisa, Ninin Rofiatin, Umi Asnah, Asnah Andiyan, Andiyan Sari, Dyana Industrial Engineering Study Program Universitas Muhammadiyah South Sumatra Palembang 30263 Indonesia Agribusiness Study Program Faculty of Agriculture University of Tribhuwana Tunggadewi East Java Malang 65144 Indonesia Master of Agricultural Economics Postgraduate School of University of Tribhuwana Tunggadewi East Java Malang 65144 Indonesia Architecture Study Program Faculty of Science and Engineering Universitas Faletehan West Java Bandung 40266 Indonesia

SCOR (Supply Chain Operations Reference) model is a tool for diagnosing Supply Chain Management (SCM) that allows users to understand all processes in a business organization. This study aimed to analyze activities related to Green Supply Chain Management (GSCM), especially in the palm oil sector, and to determine the performance of Green Supply Chain Management (GSCM) at PT. Sutopo Lestari Jaya using the green score model. The results showed that the highest Green Objectives (GO) weight in environmentally friendly garden management was located on protected forest land used as plantation land by 38.82%, while waste minimization was found in Crude palm oil water content of 48%. Meanwhile, in minimizing and handling greenhouse gas emissions, the highest weight is found in the amount of fuel used in Fresh Fruit Bunch (FFB) shipments of 54.07%. For plantation management and palm oil management mills, the highest weight is in the percentage of water use per ton of FFB in PPKS 60.7%, while in waste management, the highest percentage lies in the standardized wastewater Biological Oxygen Demand (BOD) of 38.8%. In maximizing the use of new and renewable energy, the highest weight lies in renewable energy per tonne of FFB and the use of solid waste (empty shells and shells) as a substitute for fossil fuels of 45.5% each. © 2022

关键词： Palm oil

来源：评论

学校读者我要写书评

暂无评论

Assessment of Dar es Salaam's resilience to climate change disasters using the Climate Disaster Resilience Index (CDRI)

引用

Singapore Journal of Tropical Geography 2024年第3期45卷 475-497页

作者： Mkasimongwa, Simon William Fakour, Hoda Hassani, Hussein Juma Sultan, Basma Abdulla Lai, Hsin-Chih Master Degree Program in Safety and Health Science Chang Jung Christian University Tainan City Taiwan International Program for Sustainable Development International College of Practice and Education for the Environment Chang Jung Christian University Tainan Taiwan Graduate Institute of Environmental Engineering National Taiwan University Taipei Taiwan Department of Green Energy and Environmental Resources Chang Jung Christian University Tainan Taiwan

Climate change is becoming an increasingly significant issue in Africa, and the need for climate resilience assessment has intensified. Dar es Salam is one of Africa's emerging megacities. With a population of over seven million, which continues to grow, there is an urgent need to understand the city's ability to deal with natural disasters. The Climate Disaster Resilience Index (CDRI) was used in this study to assess the city's ability to withstand and cope with climatic hazards. The Index was quantified using sets of dimensions (social, physical, economic, natural, and institutional), with various parameters indicating the city's abilities, strengths, and vulnerabilities to potential climate-related disasters. Despite being moderately resilient to climate change disasters, the results of our study indicate that the city's economic and institutional features obtained the lowest scores and the least resilience level. The study's findings provide a perspective on aspects of the city management sectors in terms of resilience and which should be given greater consideration in order to strengthen the city's current and future resilience. © 2024 Department of Geography, National University of Singapore and John Wiley & Sons Australia, Ltd.

关键词： climate change flooding resilience weather trends

来源：评论

学校读者我要写书评

暂无评论

Overcoming the Blood-Brain Tumor Barrier with Docetaxel-Loaded Mesoporous Silica Nanoparticles for Treatment of Temozolomide-Resistant Glioblastoma

引用

ACS Applied Materials and Interfaces 2024年第17期16卷 21722-21735页

作者： Hsu, Tsung-I Chen, Yi-Ping Zhang, Rong-Lin Chen, Zih-An Wu, Cheng-Hsun Chang, Wen-Chang Mou, Chung-Yuan Chan, Hardy Wai-Hong Wu, Si-Han Ph.D. Program in Medical Neuroscience College of Medical Science and Technology Taipei Medical University and National Health Research Institutes Taipei110 Taiwan International Master Program in Medical Neuroscience College of Medical Science and Technology Taipei Medical University Taipei110 Taiwan Graduate Institute of Nanomedicine and Medical Engineering Taipei Medical University Taipei110 Taiwan International Ph.D. Program in Biomedical Engineering College of Biomedical Engineering Taipei Medical University Taipei110 Taiwan Nano Targeting & Therapy Biopharma Inc. Taipei110 Taiwan Graduate Institute of Medical Sciences College of Medicine Taipei Medical University Taipei110 Taiwan Department of Chemistry National Taiwan University Taipei106 Taiwan

While temozolomide (TMZ) has been a cornerstone in the treatment of newly diagnosed glioblastoma (GBM), a significant challenge has been the emergence of resistance to TMZ, which compromises its clinical benefits. Additionally, the nonspecificity of TMZ can lead to detrimental side effects. Although TMZ is capable of penetrating the blood-brain barrier (BBB), our research addresses the need for targeted therapy to circumvent resistance mechanisms and reduce off-target effects. This study introduces the use of PEGylated mesoporous silica nanoparticles (MSN) with octyl group modifications (C8-MSN) as a nanocarrier system for the delivery of docetaxel (DTX), providing a novel approach for treating TMZ-resistant GBM. Our findings reveal that C8-MSN is biocompatible in vitro, and DTX@C8-MSN shows no hemolytic activity at therapeutic concentrations, maintaining efficacy against GBM cells. Crucially, in vivo imaging demonstrates preferential accumulation of C8-MSN within the tumor region, suggesting enhanced permeability across the blood-brain tumor barrier (BBTB). When administered to orthotopic glioma mouse models, DTX@C8-MSN notably prolongs survival by over 50%, significantly reduces tumor volume, and decreases side effects compared to free DTX, indicating a targeted and effective approach to treatment. The apoptotic pathways activated by DTX@C8-MSN, evidenced by the increased levels of cleaved caspase-3 and PARP, point to a potent therapeutic mechanism. Collectively, the results advocate DTX@C8-MSN as a promising candidate for targeted therapy in TMZ-resistant GBM, optimizing drug delivery and bioavailability to overcome current therapeutic limitations. © 2024 The Authors. Published by American Chemical Society.

关键词： Tumors

来源：评论

学校读者我要写书评

暂无评论

Verification of the Inactivation Effect of Near-UV LEDs using a Pulsed Lighting System on Staphylococcus aureus

Verification of the Inactivation Effect of Near-UV LEDs usin...

引用

2024 IEEE Sustainable Smart Lighting World Conference and Expo, LS24 2024

作者： Nomura, Hiroki Kihara, Seiji Zukeran, Akinori Sawai, Jun Misu, Takayuki Kanagawa Institute of Technology Graduate School of Engineering Master's Degree Program in Electrical and Electronic Engineering Atsugi Kanagawa243-0292 Japan Kanagawa Institute of Technology Faculty of Engineering Department of Electrical and Electronic Engineering Atsugi Kanagawa243-0292 Japan Kanagawa Institute of Technology Faculty of Health and Medical Sciences Department of Nutrition and Life Science Atsugi Kanagawa243-0292 Japan

ISBN: (纸本)9798331540197

The purpose of this study is to investigate the disinfection effect of Near-UV LED light, which is pulsed using PWM control, on Staphylococcus aureus. To evaluate the disinfection effect of Near-UV LED light, three types of Near-UV LEDs with wavelengths of 395 nm, 385 nm, and 365 nm were installed within a sealed space inside an incubator and energized with a forward current of 1000 mA and a forward voltage of 3.6 V, and the disinfection rate under each type of light was assessed. Additionally, the disinfection effect was evaluated when the same three types of Near-UV LEDs were pulsed with a 50% duty cycle. As a result, 100% disinfection was achieved with 365 nm Near-UV LED direct-current irradiation for 120 seconds, and a 93% disinfection rate was obtained with pulsed irradiation for 150 seconds. © 2024 IEEE.

关键词： Light emitting diodes

来源：评论

学校读者我要写书评

暂无评论

RUL Estimation for Power Electronic Devices Using RNNs

RUL Estimation for Power Electronic Devices Using RNNs

引用

Prognostics and System Health Management Conference (PHM)

作者： Congrui Cai Zhonghai Lu Embedded Systems Master Program School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Department of Electrical Engineering School of Electrical Engineering and Computer Science KTH Royal Institute of Technology

ISBN: (数字)9798350360585

ISBN: (纸本)9798350360592

Recurrent Neural Networks (RNNs) are commonly used in data-driven approaches to estimate the Remaining Useful Lifetime (RUL) of power electronic devices. RNNs are preferred because their intrinsic feedback mechanisms are better suited to model time-series data. However, the impact of RNN complexity on estimation accuracy is rarely discussed in the literature. This issue is important because choosing a lower-complexity model that delivers the same or similar performance as a higher-complexity model can increase implementation efficiency. In the paper, we use three RNN models, namely, the vanilla version, LSTM (Long Short Term Memory) and GRU (Gated Recurrent Unit) to conduct RUL estimation for power electronic devices. We use two accelerated aging datasets, one dataset targeting the package failure of MOSFETs, and the other dataset targeting package failure of power diodes. Our study shows that a lower-complexity RNN does not necessarily deliver a lower performance. Similarly, a higher-complexity model does not assure a higher performance. As such, our work highlights the importance of selecting a proper neural network for RUL estimation not biased towards complex models. This is especially useful and important for implementing such RUL estimation techniques in embedded resource-constrained and speed-limited computins platforms.

关键词： Performance evaluation Semiconductor device modeling Recurrent neural networks Computational modeling Estimation Power electronics Data models

来源：评论

学校读者我要写书评

暂无评论

CAMRI Loss: Improving the Recall of a Specific Class without Sacrificing Accuracy

CAMRI Loss: Improving the Recall of a Specific Class without...

引用

作者： Nishiyama, Daiki Fukuchi, Kazuto Akimoto, Youhei Sakuma, Jun Master's Program in Computer Science Degree Programs in Systems and Information Engineering Graduate School of Science and Technology University of Tsukuba Tsukuba-shi305-8577 Japan RIKEN Center for Advanced Intelligence Project Tokyo103-0027 Japan Department of Computer Science Faculty of Engineering Information and Systems University of Tsukuba Tsukuba-shi305-8577 Japan

In real world applications of multiclass classification models, misclassification in an important class (e.g., stop sign) can be significantly more harmful than in other classes (e.g., no parking). Thus, it is crucial to improve the recall of an important class while maintaining overall accuracy. For this problem, we found that improving the separation of important classes relative to other classes in the feature space is effective. Existing methods that give a class-sensitive penalty for cross-entropy loss do not improve the separation. Moreover, the methods designed to improve separations between all classes are unsuitable for our purpose because they do not consider the important classes. To achieve the separation, we propose a loss function that explicitly gives loss for the feature space, called class-sensitive additive angular margin (CAMRI) loss. CAMRI loss is expected to reduce the variance of an important class due to the addition of a penalty to the angle between the important class features and the corresponding weight vectors in the feature space. In addition, concentrating the penalty on only the important class hardly sacrifices separating the other classes. Experiments on CIFAR-10, GTSRB, and AwA2 showed that CAMRI loss could improve the recall of a specific class without sacrificing accuracy. In particular, compared with GTSRB's second-worst class recall when trained with cross-entropy loss, CAMRI loss improved recall by 9%. © 2023 The Institute of Electronics, Information and Communication Engineers.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Single-cell transcriptomics uncovers EGFR signaling-mediated gastric progenitor cell differentiation in stomach homeostasis (vol 14, 3750, 2023)

引用

NATURE COMMUNICATIONS 2023年第1期14卷 1-16页

作者： Takada, Hitomi Sasagawa, Yohei Yoshimura, Mika Tanaka, Kaori Iwayama, Yoshimi Hayashi, Tetsutaro Isomura-Matoba, Ayako Nikaido, Itoshi Kurisaki, Akira Laboratory of Stem Cell Technologies Graduate School of Science and Technology Nara Institute of Science and Technology Takayama-cho Ikoma Nara Japan Laboratory for Bioinformatics Research RIKEN Center for Biosystems Dynamics Research Wako Saitama Japan Department of Functional Genome Informatics Biological Data Science Medical Research Institute Tokyo Medical and Dental University Bunkyo Tokyo Japan Master’s/Doctoral Program in Life Science Innovation (Bioinformatics) Degree Programs in Systems and Information Engineering Graduate School of Science and Technology University of Tsukuba Tsukuba Ibaraki Japan

Defects in gastric progenitor cell differentiation are associated with various gastric disorders, including atrophic gastritis, intestinal metaplasia, and gastric cancer. However, the mechanisms underlying the multilineage differentiation of gastric progenitor cells during healthy homeostasis remain poorly understood. Here, using a single-cell RNA sequencing method, Quartz-Seq2, we analyzed the gene expression dynamics of progenitor cell differentiation toward pit cell, neck cell, and parietal cell lineages in healthy adult mouse corpus tissues. Enrichment analysis of pseudotime-dependent genes and a gastric organoid assay revealed that EGFR-ERK signaling promotes pit cell differentiation, whereas NF-κB signaling maintains gastric progenitor cells in an undifferentiated state. In addition, pharmacological inhibition of EGFR in vivo resulted in a decreased number of pit cells. Although activation of EGFR signaling in gastric progenitor cells has been suggested as one of the major inducers of gastric cancers, our findings unexpectedly identified that EGFR signaling exerts a differentiation-promoting function, not a mitogenic function, in normal gastric homeostasis.

关键词： Adult stem cells Stem-cell differentiation Stem-cell niche

来源：评论

学校读者我要写书评

暂无评论

Extraction of c- F os Protein Regions from Mouse Brain Slice Images using Multi-channelization, 1 x 1 Convolution and U -Net 13

Extraction of c- F os Protein Regions from Mouse Brain Slice...

引用

Joint 13th International Conference on Soft Computing and Intelligent Systems and 25th International Symposium on Advanced Intelligent Systems, SCIS and ISIS 2024

作者： Wang, Ziyue Okamura, Hibiki Luo, Shijie Hayashi, Yu Takizawa, Hotaka Master's Program in Computer Science University of Tsukuba Tsukuba Japan International Institute for Integrative Sleep Medicine University of Tsukuba Ph.D. Program in Humanics Tsukuba Japan International Institute for Integrative Sleep Medicine University of Tsukuba Tsukuba Japan Institute of Systems and Information Engineering Academic Computing and Communications Center University of Tsukuba Tsukuba Japan

ISBN: (纸本)9798350373332

This study proposed a novel extraction method of c-Fos protein regions in DAB(3,3'-diaminobenzidine)-stained mouse brain slice images using the U-Net model combined with the multi-channelization and 1×1 convolution techniques. Our U-Net m odel, called 1× 1 conv U-Net, was applied to three DAB- strainedmouse slice images whose resolutions were 1000x1000 pixels. The experimental results demonstrated that the 1×1 conv U-Net outperformed the conventional U-Net. © 2024 IEEE.

关键词： Mammals

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：