检索结果-内蒙古大学图书馆

Classification of Multivariate Time Series Signals Using Self-Supervised Representation Learning for Condition Monitoring

Classification of Multivariate Time Series Signals Using Sel...

引用

Joint e-Manufacturing and Design Collaboration Symposium (eMDC) & International Symposium on Semiconductor Manufacturing (ISSM)

作者： Koichi Sumiya Sumika Arima Doctoral Program in Policy and Planning Sciences University of Tsukuba Tsukuba Japan Institute of Systems and Information Engineering University of Tsukuba Tsukuba Japan

ISBN: (数字)9798331510589

ISBN: (纸本)9798331510596

In the analysis of real-world data, two significant challenges often arise: high-dimensional signals and their temporal interactions. To address these issues and identify transitions in process conditions through end-to-end learning, we propose a self-supervised representation learning framework that conceptualizes signals as images. This straightforward approach classifies imaged signals as time-specific conditions by maximizing mutual information within a domain-specific feature space. We applied this methodology to two labeled open datasets and one unlabeled real-world process dataset, yielding promising results.

关键词： Representation learning Furnaces Time series analysis Self-supervised learning Glass Medical services Semiconductor device manufacture Turning Wool Mutual information

来源：评论

学校读者我要写书评

暂无评论

Expert System Research for Prostate Cancer : A Literature Review

Expert System Research for Prostate Cancer : A Literature Re...

引用

2023 International Conference on Networking, Electrical engineering, Computer Science, and Technology, IConNECT 2023

作者： Rusliyawati, Rusliyawati Sutyarso, Sutyarso Wantoro, Agus University of Lampung Doctoral Program of Mathematics and Natural Science Faculty Bandar Lampung Indonesia Universitas Teknokrat Indonesia Faculty of Engineering and Computer Science Bandar Lampung Indonesia University of Lampung Faculty of Mathematics and Natural Sciences Bandar Lampung Indonesia

ISBN: (纸本)9798350331172

In the field of computer science, expert systems have attracted many computer scientists. In recent years, expert systems have been widely used in the medical field, particularly for diagnosing and treating various diseases, especially prostate cancer. Reality has shown that expert systems hold great promise for accurate diagnosis and treatment of prostate cancer. This research summarizes several studies related to the application of artificial intelligence in the field of prostate cancer through bibliometric analysis and explores potential future research. Articles and reviews on the application of expert systems in prostate cancer from 2015 to 2022 were selected from the PubMed, Embase, and Web of Science databases. Microsoft Excel 2019 and GraphPad Prism 8 were used for target variable analysis. A total of 37 articles were selected for this research. Research on artificial intelligence in prostate cancer has grown exponentially in recent years, particularly in Indonesia. Image data usage is more predominant (62%) than numerical data types in prostate cancer research. Artificial intelligence research in prostate cancer, especially in the field of treatment cases, and the use of Deep Neural Network (DNN), Human Neural Network (HNN), Fully Convolutional Network (FCN), QT Environment for C++, Artificial Neural Network (ANN) algorithms, are highly feasible for further research. © 2023 IEEE.

关键词： Fuzzy logic

来源：评论

学校读者我要写书评

暂无评论

Identification of benefits, challenges, and pathways in E-commerce industries: An integrated two-phase decision-making model

引用

Sustainable Operations and Computers 2023年第1期4卷 200-218页

作者： Gupta, Srikant Kushwaha, Pooja.S. Badhera, Usha Chatterjee, Prasenjit Gonzalez, Ernesto D.R. Santibanez Department of Operations and Decision Sciences Jaipuria Institute of Management Jaipur India Department of Business Analytics Jaipuria Institute of Management Indore India Department of Business Analytics Jaipuria Institute of Management Jaipur India Department of Mechanical Engineering MCKV Institute of Engineering West Bengal 711204 India Post-Doctoral Fellow Management Graduate Program Universidade Paulista Indianópolis Campus Brazil Department of Industrial Engineering and CES 4.0 Faculty of Engineering University of Talca Curico Chile

The e-commerce industry has seen significant growth over the past decade as it focuses on convenience and accessibility, leading to a surge in online shopping with more and more consumers opting for it. At the same time, the e-commerce industry faces various challenges. In order to fully harness the potential of this industry, it is important to identify its benefits and challenges and focus on pathways to mitigate the challenges and harness its growth. This study utilizes the Delphi approach and involves experts from the e-commerce domain to get their opinions to identify the top ten benefits, challenges, and pathways for the e-commerce industry. Analytic Hierarchy Process (AHP) and Criteria Importance Through Intercriteria Correlation (CRITIC) methods are subsequently, employed to prioritize the identified factors. Results of the study revealed that factors such as affordable advertising & marketing;availability and product variety;and Global reachability are the most important benefits, while technological upgradation;returns or refunds;and counterfeit products posed the greatest challenges for the industry. Government compliance check;better relationship with delivery partners;and strong data privacy and online security policies emerged as the best pathways. This study also provides valuable insights to businesses, policymakers, and researchers in the e-commerce industry on how to navigate the benefits, challenges, and pathways of this rapidly growing sector. © 2023

关键词： Electronic commerce

来源：评论

学校读者我要写书评

暂无评论

Picrasidine I Regulates Apoptosis in Melanoma Cell Lines by Activating ERK and JNK Pathways and Suppressing AKT Signaling

引用

Environmental Toxicology 2024年第12期39卷 5309-5320页

作者： Shieu, Mu-Kuei Lin, Chia-Chieh Ho, Hsin-Yu Lo, Yu-Sheng Chuang, Yi-Ching Hsieh, Ming-Ju Department of Dermatology Changhua Christian Hospital Changhua Taiwan Oral Cancer Research Center Changhua Christian Hospital Changhua Taiwan Graduate Institute of Clinical Medicine College of Medicine National Chung Hsing University Taichung Taiwan Doctoral Program in Tissue Engineering and Regenerative Medicine College of Medicine National Chung Hsing University Taichung Taiwan Graduate Institute of Biomedical Sciences China Medical University Taichung Taiwan

World Health Organization data indicate a continuous increase in melanoma incidence, with metastatic melanoma characterized by poor prognosis and drug resistance. The exploration of therapeutics derived from natural products remains an active area of in vitro research. The aim of this study was to determine the antitumor effects of picrasidine I, a natural compound extracted from Picrasma quassioides, against two melanoma cell lines. We selected two metastatic melanoma cell lines, HMY-1 and A2058, for molecular studies, including Western blotting, 4′,6-diamidino-2-phenylindole staining, and flow cytometry. Picrasidine I demonstrated cytotoxic effects against the HMY-1 and A2058 melanoma cell lines. It induced cell cycle arrest in the sub-G1 phase and downregulated cell cycle–related proteins (e.g., cyclin A2, D1, cyclin-dependent kinases 4, and 6). In the intrinsic apoptosis pathway, picrasidine I activated proapoptotic proteins (e.g., Bax, Bak, t-Bid, BimL/S) and suppressed the expression of antiapoptotic proteins (e.g., Bcl-2, Bcl-xL), with an observed increase in the quantity of depolarized cells. In addition, the apoptotic effects of picrasidine I were linked to the activation of the c-Jun N-terminal kinase and extracellular signal-regulated kinase pathways and the inhibition of the protein kinase B signaling pathway. A human apoptosis array indicated claspin inhibition upon picrasidine I treatment, suggesting the potential involvement of picrasidine I in apoptosis and cell cycle regulation. Our findings suggest that picrasidine I has potential as a candidate for treating advanced melanoma, and thus these findings warrant further investigation. The modulation of claspin expression by picrasidine I could be investigated further as a potential biomarker to predict its efficacy in related to advanced stages of melanoma. © 2024 The Author(s). Environmental Toxicology published by Wiley Periodicals LLC.

关键词： Dermatology

来源：评论

学校读者我要写书评

暂无评论

Development of A Deep Learning Hybrid Model for Classification of Plastic Waste Objects in the Coastal Environment

Development of A Deep Learning Hybrid Model for Classificati...

引用

Advancement in Data Science, E-learning and Information Systems (ICADEIS), International Conference on

作者： Imran Djafar Indrabayu Syafruddin Syarif Doctoral Program of Electrical Engineering Department Hasanuddin University Dipa Makassar University Makassar Indonesia Department of Informatics Hasanuddin University Makassar Indonesia Department of Electrical Engineering Hasanuddin University Makassar Indonesia

ISBN: (数字)9798331513320

ISBN: (纸本)9798331513337

Plastic, glass, metal, and wood waste has become a global scourge and nightmare to the marine environment and the development of the coastal areas. This paper aims at developing a hybrid model of deep learning technique using Convolutional Neural Networks (CNN) and Vision transformers (ViT) in the performance of detecting underwater waste materials. The model is designed with the use of transfer learning and high-resolution imaging sourced from underwater drones to help overcome the challenges of underwater work such as poor visibility and insufficient ambient light. The local features are extracted using CNNs and the global spatial relationships of the images are attended to by the ViTs. The results achieved a waste detection accuracy rate of about 90%, which is effective even in difficult environmental conditions. The concept is for a waste management system where drones or underwater robotics systems can assist automated waste management, waste treatment processes, and aid marine renovation activities.

关键词： Waste management Deep learning Transfer learning Sea measurements Metals Glass Feature extraction Transformers Convolutional neural networks Drones

来源：评论

学校读者我要写书评

暂无评论

Hydrogel derived from water hyacinth and pectin from banana peel as a membrane layer

Hydrogel derived from water hyacinth and pectin from banana ...

引用

3rd International Conference on Chemical engineering and Applied Sciences, ICChEAS 2022

作者： Elma, Muthia Kadek Devi Ananda Saraswati, Ni Fransiska Afrida Simatupang, Paskah Febriyanti, Retno Rahma, Aulia Ria Mustalifah, Fitri Chemical Engineering Department Engineering Faculty Lambung Mangkurat University Jl A. Yani Km 36 South Kalimantan Banajrbaru70714 Indonesia Magister Program of Chemical Engineering Faculty of Engineering Lambung Mangkurat University Jl. A. Yani KM 36 Banjarbaru70714 Indonesia Doctoral Program of Environemntal Science Postgraduate Program Lambung Mangkurat University Jl Brigjen H. Hasan Basri Kayutangi South Kalimantan Banjarmasin70123 Indonesia Lambung Mangkurat University Jl. A. Yani KM 36 Banjarbaru70714 Indonesia

Hydrogels is a unique material that affordable to apply as a membranes layer. In tropical country, such as Indonesia there is easily found water hyacinth (a weed plant) which is potentially used for hydrogels materials fabrication due to high cellulose content. Carboxymethyl cellulose (CMC) from water hyacinth cellulose and banana peels pectin are used to produce hydrogel for ultrafiltration membrane. The aims of this study are to characterize the functionalization of CMC-pectin membrane with different ratio using Fourier transform infrared spectroscopy (FTIR) and to determines the morphology of its membranes structure. The CMC was synthesized from water hyacinth stems through carboxymethylation. The functionalization group of multiple CMC-pectin membrane ratio is domination with carboxyl group (COO-), carbonyl stretching and carbon group. Meanwhile, CMC-pectin 70:30 wt% ratio displays not smooth structure. There is a water hyacinth stems extracted cellulose fibre on the surface of hydrogel CMC:pectin membrane. In other hand, the addition of pectin in all ratio variation exhibit increasing contact angle number from 63.98° to 68.16° (0-30 wt% pectin). The existence of pectin from banana peels on hydrogel membranes contributes to increase hydrophobicity of hydrogel-membrane, in spite of the contact angle value is below than 90°. © 2023 Elsevier Ltd. All rights reserved.

关键词： Membranes

来源：评论

学校读者我要写书评

暂无评论

The Concept of Sustainability in the Formation of Unplanned Settlement Spaces in Depok Lama, West Java 1

引用

AUA Academic Conference in conjunction with 5th International Conference on Strategic and Global Studies, AUA and ICSGS 2021

作者： Rakhmanita Purwanto, Edi Rukayah, R. Siti Rahman, Arief Doctoral Program in Architecture and Urban Sciences Diponegoro University Semarang Indonesia Department of Architecture Faculty of Engineering Diponegoro University Semarang Indonesia Department of Architecture Faculty of Civil Engineering and Planning Gunadarma University Depok City Indonesia

ISBN: (数字)9783030999797

ISBN: (纸本)9783030999780

As a village that later developed into an area that resembled a colonial city at that time, Depok Lama had a concept of residential space that was different from the colonial settlements that existed during the Dutch colonial period. In other colonial settlements, the concept of settlement was the result of a design from the Dutch government, in the Depok Lama settlement the concept of residential space was formed from the activities of citizens directed by a will. This method is used to find a detailed picture based on facts about the beginning of the formation of Depok lama settlement through collecting Depok Lama maps, Chastelein's will, and observing city artifacts. The results of this study note that the concept of space that was applied at the beginning of the formation of the Depok Lama settlement was an unplanned concept of sustainability, prioritizing easy access to various main facilities in the Depok Lama settlement, forming a comfortable environment for the residents of Depok Lama in building their lives and improving they socio-economic quality. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Sustainable development

来源：评论

学校读者我要写书评

暂无评论

Digital Representation of the Terrain Associated with an Archaeological Site: Case Study of the ‘Baker’s House’ in Torreparedones 30th

Digital Representation of the Terrain Associated with an Arc...

引用

30th International conference on The Digital Transformation in the Graphic engineering, INGEGRAF 2021

作者： Triviño-Tarradas, Paula Molina, Diego Francisco García Fernández, Rafael Hidalgo Criado, Irene Cáceres Department of Graphic and Geomatics Engineering University of Cordoba Córdoba Spain Department of Graphic Engineering Design and Engineering Projects of the University of Jaen Jaen Spain Doctoral Program in Agricultural Food Forestry and Rural Development Engineering University of Córdoba Córdoba Spain

ISBN: (纸本)9783030924256

Nowadays, it is essential to provide 3D digital reconstructions with the highest possible reliability and veracity. Archaeological sites within the framework of the building to be rebuilt are important. The data provided by Geographic Information Systems (GIS) can be extracted from different sources, and are a crucial tool to carry out the topographical survey in the context of Virtual Archaeology. Therefore, engineering and archaeology work hand in hand to form multidisciplinary teams with the aim of addressing the design of heritage cultural elements. The aim of this study was to represent the terrain associated with the "the Baker’s House", at the archaeological site of Torreparedones (Cordoba, Spain). The interest in this representation increased after the virtual reconstruction of the domus, which was performed to geographically place the house in its exact location. Two methodologies were used through different software and data to obtain the topographical survey. The first methodology was the one applied in QGIS 2.3.15 with data from the CNIG, and the second methodology was the one applied in Blender 2.90.0 using the Google Satellite database. Both methodologies were compared, analysing the time invested in the two processes, as well as the orography of the terrain, which was captured with a 360 panoramic picture taken on the site. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Blender Domus GIS Orography QGIS Recreation Virtual archaeology

来源：评论

学校读者我要写书评

暂无评论

Exploring Regression and Classification in Big Data with Deep Learning

Exploring Regression and Classification in Big Data with Dee...

引用

2023 International Conference on Power Energy, Environment and Intelligent Control, PEEIC 2023

作者： Pandey, Ravindra Rongali, Aruna Sri Gopinath, S. Anute, Nilesh Nama, Forda Pund, Sachin Hult International Business School United States University of the Cumberlands Doctoral Information Technology Information Technology Emphasis Information Technology United States Karpagam Institute of Technology Department of Electronics and Communication Engineering Coimbatore India ASM's Institute of Business Management and Research Pune India University of Lampung Doctoral Program of Environtmental Science Department of Informatics Bandar Lampung Indonesia Shri Ramdeobaba College of Engineering and Management Department of Industrial Engineering Maharashtra Nagpur India

ISBN: (纸本)9798350357769

Deep gaining knowledge is a synthetic intelligence approach used to recognize complex facts. It uses many facts to recognize the complicated relationships between various factors. With deep learning, models can be built which might be capable of understanding the complicated patterns within big datasets. In this paper, we can explore using deep mastering in regression and type tasks on large datasets. In particular, we can use deep learning strategies to build a regression model that predicts a target value primarily based on the functions in a massive dataset and a classification version that can classify an object into one of the many classes of an extensive dataset. We can then discuss the overall performance of the fashions in comparison to standard models and talk about capability areas for development. Moreover, we will analyze the scalability of deep mastering strategies used on large datasets and discuss exceptional practices for building deep mastering fashions on massive datasets. Finally, we will summarize our findings and offer our conclusions approximately the use of deep studying in regression and type obligations on large datasets. © 2023 IEEE.

关键词： approximately gaining knowledge mastering performance regression

来源：评论

学校读者我要写书评

暂无评论

Q-Learning Energy Management System (Q-EMS) in Wireless Sensor Network

Q-Learning Energy Management System (Q-EMS) in Wireless Sens...

引用

2024 International Conference on Smart Computing, IoT and Machine Learning, SIML 2024

作者： Ardiansyah, Deden Mustafid Mantoro, Teddy Universitas Diponegoro Doctoral Program of Information Systems School of Postgraduate Central Java Semarang Indonesia Universitas Pakuan Vocational School Computer Engineering Department West Java Bogor Indonesia Sampoerna University Media-Tech-Lab Computer Science Department DKI Jakarta Indonesia

ISBN: (纸本)9798350364101

The energy control of a Wireless Sensor Network (WSN) often leads to an unbalanced state between the battery storage system, energy extraction through photovoltaic systems energy, and energy utilization in the WSN. These disparities result in suboptimal wireless sensor network performance. The reliance on batteries is a major factor contributing to this problem. The Q-Learning Energy Management System (Q-EMS) is designed to address these challenges and improve energy management strategies. The Q-EMS algorithm used a learning process resulting in optimal actions for sensor nodes in different situations. The rewards or punishments nodes receive determine their decisions, which are determined by the Q-EMS algorithm. The Q-learning model approach is aimed at reducing energy consumption and supply in WSNs. Energy supply is categorized into battery-based, transfer-based, and harvesting, while energy consumption can be classified into task-cycle, mobility-based, and data-driven. The development of the Q Learning algorithm model has three scenarios: determining energy needs for WSN, effective energy harvesting strategy, and effective energy transfer. As a result, effective energy demand, harvesting and transfer using the Q-learning algorithm are balanced. However, it needs to be studied in more depth using real data in the field. In future research, I will use real data and optimize the use of the Q-Learning algorithm. © 2024 IEEE.

关键词： Energy management systems

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：