检索结果-内蒙古大学图书馆

7th International Conference on Software Engineering and Computer Systems and 4th International Conference on Computational science and Information Management, ICSECS-ICOCSIM 2021

作者： Miah, M. Saef Ullah Sulaiman, Junaida Azad, Saiful Zamli, Kamal Z. Jose, Rajan Universiti Malaysia Pahang Faculty of Computing College of Computing and Applied Sciences Pekan26600 Malaysia Universiti Malaysia Pahang Center for Data Science and Artificial Intelligence Data Science Center Faculty of Computing College of Computing and Applied Sciences Pekan26600 Malaysia Green University of Bangladesh Department of Cse Dhaka Bangladesh Universiti Malaysia Pahang Faculty of Industrial Sciences and Technology Gambang Malaysia

ISBN: (纸本)9781665414074

The idea of this study is to validate a list of keywords derived from a scientific article by a domain expert from years of knowledge with prominent document similarity algorithms. For this study, a list of handcrafted keywords generated by Electric Double Layer Capacitor (EDLC) experts are chosen, and relevant documents to EDLC are considered for the comparison. Then, different similarity calculation algorithms were employed in different settings on the documents such as using the whole texts of the documents, selecting the positive sentences of the documents, and generating similarity score with automatically extracted keywords from the documents. The experiment's outcome provides us with findings that the machine-generated keywords are mostly similar to the curated list by the domain experts. This study also suggests the preferable algorithms for similarity calculation and automated key-phrase extraction for the EDLC domain. © 2021 IEEE.

关键词： Supercapacitor

来源：评论

学校读者我要写书评

暂无评论

Facilities Utilization Framework for Universal Design in Tourism 13

Facilities Utilization Framework for Universal Design in Tou...

引用

13th IIAI International Congress on Advanced Applied Informatics Winter, IIAI-AAI-Winter 2022

作者： Tongtep, Nattapong Charoenporn, Thatsanee College of Computing Prince of Songkla University Phuket Thailand Musashino University AAII Faculty of Data Science Tokyo Japan

ISBN: (纸本)9798350309928

A suitable environment for people with disabilities has widely campaigned around the world. There are many attempts to mobilize the community to help people with disabilities can enjoy their lives equally. This paper, therefore, presents our initiative on adapting the universal design concept to develop a facilities utilization framework for tourist spots. The system provides information about places and various necessary details of the facilities and services in accordance with the unique needs of people with disabilities in the form of web applications. The paper presents the concept of development, related theories, and the result of applying the information system in practice. The preliminary usability evaluation results are at an outstanding level. Collecting more data on facilities and usage patterns are ongoing task with a focus on monitoring and suggesting the coverage and access rate of all groups of people in the public area. © 2022 IEEE.

关键词： Tourism

来源：评论

学校读者我要写书评

暂无评论

Modeling of toddler stunting in the province of east nusa tenggara using multivariate adaptive regression splines (mars) method 5

Modeling of toddler stunting in the province of east nusa te...

引用

5th International Conference on Mathematics: Pure, Applied and Computation, ICoMPAC 2019

作者： Azizah, D.M. Permatasari, E.O. Statistics Department Faculty of Mathematics Computing and Data Science InstitutTeknologiSepuluhNopember GebangKidul Road number 66 Surabaya60111 Indonesia

Stunting is a condition of failure to thrive in children under five (babies under five years old) as a result of chronic malnutrition so that the child is too short for his age. Malnutrition occurs since the baby is in the womb and in the early period after the baby is born. However, the condition of stunting only appears after the baby is 2 years old. Based on Basic Health Research in 2017 the province with the highest prevalence of short and very short toddlers in Indonesia is East Nusa Tenggara which is equal to 40.3 percent. This shows that the prevalence of stunting toddlers in NTT Province is still far from the overall prevalence of stunting toddlers in Indonesia. Cases of toddler stunting can be analyzed using the Multivariate Adaptive Regression Splines (MARS) method because the data used are high-dimensional data and do not show clear patterns of relationships between response variables and predictor variables. The data used is the percentage of stunting toddlers in NTT in 2017 with the district / city research unit. Based on the analysis, it was found that the district in NTT with the highest percentage of stunting children was South East Timor and the district with the lowest percentage was East Manggarai. The best MARS model is formed from 3 basis functions with 2 predictor variables included in the model, namely the percentage of pregnant women at risk of chronic lack of energy (X1) and the percentage of infants with low birth weight (X6). And after the classification results obtained the accuracy of the classification of 77.27% with an error of 22.72%. © Published under licence by IOP Publishing Ltd.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Next-Generation Human Activity Recognition Using Locality Constrained Linear Coding Combined With Machine Learning (NG-HAR-LCML)

引用

Healthcare Technology Letters 2025年第1期12卷

作者： Maryam Shabbir Fahad Ahmad Saad Awadh Alanazi Muhammad Hassan Khan Jianqiang Li Tariq Mahmood Shahid Naseem Muhammad Anwar Department of Computer Sciences Bahria University Lahore Punjab Pakistan Department of Computer Science Faculty of Computing & Information Technology University of the Punjab Lahore Pakistan School of Computing Faculty of Technology University of Portsmouth Portsmouth UK Portsmouth Artificial Intelligence and Data Science Centre (PAIDS) University of Portsmouth Portsmouth UK Department of Computer Science College of Computer and Information Sciences Jouf University Sakaka Aljouf Saudi Arabia The School of Software Engineering Beijing University of Technology Beijing China Artificial Intelligence and Data Analytics (AIDA) Lab CCIS Prince Sultan University Riyadh Saudi Arabia Department of Information Sciences University of Education Vehari Pakistan Faculty of Information Sciences Division Science &Technology University of Education Lahore Pakistan

Accurate Human Activity Recognition (HAR) is a critical challenge with wide-ranging applications in healthcare, assistive technologies, and human-computer interaction. Traditional feature extraction methods often struggle to capture the complex spatial and temporal dynamics of human movements, leading to suboptimal classification performance. To address this limitation, this study introduces a novel encoding approach using Locality-Constrained Linear Coding (LLC) to enhance the discriminative power of hand-crafted features extracted from low-cost wearable sensors—an accelerometer and a gyroscope. The proposed LLC-based encoding scheme enables robust feature representation, improving the accuracy of HAR models. The encoded features are classified using a diverse set of Machine Learning (ML) and Deep Learning (DL) algorithms, including Support Vector Machine (SVM), Logistic Regression (LR), Naive Bayes (NB), K-Nearest Neighbours (KNN), AdaBoost, Gradient Boosting Machine (GBM), and Deep Belief Network (DBN). Extensive quantitative evaluations demonstrate that LLC significantly outperforms conventional feature encoding techniques, leading to improved classification accuracy. Among the tested models, DBN achieves a state-of-the-art accuracy of 99%, highlighting its superiority for HAR tasks. The contributions of this research are threefold: (1) it establishes the necessity of an advanced encoding scheme (LLC) for feature enhancement in HAR, (2) it provides a rigorous comparative analysis of multiple ML and DL classifiers, and (3) it introduces a scalable and cost-effective HAR framework suitable for real-world applications. Performance is comprehensively assessed using robust evaluation metrics such as Area Under the Curve (AUC), Classification Accuracy (CA), F1 Score, Precision, Recall, and Matthews Correlation Coefficient (MCC). The findings of this study offer new insights into feature encoding for HAR, setting a foundation for future advancements in sensor-based act

关键词： feature encoding human activity recognition locality constrained linear coding support vector machine wearable sensors

来源：评论

学校读者我要写书评

暂无评论

Explaining Decision-Tree Predictions by Addressing Potential Conflicts between Predictions and Plausible Expectations 14

Explaining Decision-Tree Predictions by Addressing Potential...

引用

14th International Conference on Natural Language Generation, INLG 2021

作者： Maruf, Sameen Zukerman, Ingrid Reiter, Ehud Haffari, Gholamreza Dept. of Data Science and AI Faculty of IT Monash University VIC Australia Dept. of Computing Science University of Aberdeen United Kingdom

ISBN: (纸本)9781954085510

We offer an approach to explain Decision Tree (DT) predictions by addressing potential conflicts between aspects of these predictions and plausible expectations licensed by background information. We define four types of conflicts, operationalize their identification, and specify explanatory schemas that address them. Our human evaluation focused on the effect of explanations on users' understanding of a DT's reasoning and their willingness to act on its predictions. The results show that (1) explanations that address potential conflicts are considered at least as good as baseline explanations that just follow a DT path;and (2) the conflict-based explanations are deemed especially valuable when users' expectations disagree with the DT's predictions. © 2021 Association for Computational Linguistics

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Computer vision and Generative AI for yield prediction in Digital Agriculture 2

Computer vision and Generative AI for yield prediction in Di...

引用

2nd IEEE International Conference on Networking and Communications, ICNWC 2024

作者： Majumder, Sayan Khandelwal, Yash Sornalakshmi, K. SRM Institute of Science and Technology School of Computing Faculty of Engineering and Technology Department of Data Science and Business Systems Kattankulathur Chennai603203 India

ISBN: (纸本)9798350365269

For the cause of evolution of agriculture to its next generation, the introduction of A.I. and data-driven approach is going to be an important part of the agricultural industry that as per our vision would offer numerous economic, environmental and social benefits. Controlled Environment Agriculture (CEA) is providing more benefits since the weather and other environmental conditions is controlled and predictable. In CEA, the benefits include enhanced productivity in yield, reduced environmental footprints and better resource management. Our solution uses the adoption of Generative AI to visually forecast the potential yield of a crop using stable diffusion and conditional prompts additionally implementing several Generative Adversarial Networks (GAN) architectures for data generation, augmentation and super-resolution. Our proposed system also adopts generative AI for real time monitoring of plants. studying their respective conditions and their autonomous cultivation and harvesting patterns. The dataset used contained over 8479 examples for different fruits alongside annotations. This data was used to train the detection models as well categorically feed the GANs for data generation. data generated by DCGAN has a structural similarity of 0.5-0.7 whereas data generated by pix2pix network returns us a structural similarity of 0.7-0.9. © 2024 IEEE.

关键词： Cultivation

来源：评论

学校读者我要写书评

暂无评论

U1 snRNP regulates alternative promoter activity by inhibiting premature polyadenylation

引用

Molecular Cell 2025年第10期85卷 1968-1981.e7页

作者： Kim, GyeungYun Carroll, Christine L. Wakefield, Zachary Peters Tuncay, Mustafa Fiszbein, Ana Biology Department Boston University Boston 02215 United States Graduate Program in Molecular Biology Cell Biology & Biochemistry Boston University Boston 02215 United States Graduate Program in Cell and Molecular Biology Boston University Boston 02215 United States Bioinformatics Program Faculty of Computing and Data Science Boston University Boston 02215 United States Center for Computing & Data Sciences Boston University Boston 02215 United States

Emerging evidence indicates that splicing factors mediate the close link between transcription and splicing. However, the mechanisms underlying this coupling remain unclear. U1 small nuclear ribonucleoprotein particle (U1 snRNP) not only initiates splicing but also plays a crucial role in preventing premature cleavage and polyadenylation, facilitating long-distance transcriptional elongation. Here, we show that U1 snRNP regulates alternative promoter activity in human cells by inhibiting premature polyadenylation. In genes carrying premature polyadenylation sites between two promoters, U1 snRNP inhibition with antisense oligonucleotides leads to a significant decrease in downstream promoter activity. Conversely, restoring U1 snRNP activity or inhibiting premature polyadenylation rescues downstream promoter activity. Mechanistically, U1 snRNP inhibition correlates with reduced chromatin accessibility, decreased RNA polymerase II serine 5 phosphorylation, and increased promoter-proximal pause at downstream promoters. Our findings support a model in which U1 snRNP favors productive elongation from upstream promoters, triggering downstream promoter activation by destabilizing nucleosomes and promoting promoter escape. © 2025 The Author(s)

关键词： alternative promoters dowsntream promoters promoter-proximal pause splicing factors splicing transcription transcription cooperativity transcription initiation transcription interfierence transcription start sites U1 snRNP

来源：评论

学校读者我要写书评

暂无评论

Advanced Arabic Alphabet Sign Language Recognition Using Transfer Learning and Transformer Models

Advanced Arabic Alphabet Sign Language Recognition Using Tra...

引用

2024 International Conference on Computer and Applications, ICCA 2024

作者： Balat, Mazen Awaad, Rewaa Adel, Hend Zaky, Ahmed B. Aly, Salah A. Egypt-Japanese University of Science & Technology Cs & It Dept. Alexandria Egypt Fayoum University Faculty of Science Fayoum Egypt Badya University Faculty of Computing & Data Science Giza Egypt

ISBN: (纸本)9798350367560

This paper presents an Arabic Alphabet Sign Language recognition approach, using deep learning methods in conjunction with transfer learning and transformer-based models. We study the performance of the different variants on two publicly available datasets, namely ArSL2018 and AASL. This task will make full use of state-of-the-art CNN architectures like ResNet50, MobileNetV2, and EfficientNetB7, and the latest transformer models such as Google ViT and Microsoft Swin Transformer. These pre-trained models have been fine-tuned on the above datasets in an attempt to capture some unique features of Arabic sign language motions. Experimental results present evidence that the suggested methodology can receive a high recognition accuracy, by up to 99.6% and 99.43% on ArSL2018 and AASL, respectively. That is far beyond the previously reported state-of-the-art approaches. This performance opens up even more avenues for communication that may be more accessible to Arabic-speaking deaf and hard-of-hearing, and thus encourages an inclusive society. © 2024 IEEE.

关键词： Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Improving brain tumor classification: An approach integrating pre-trained CNN models and machine learning algorithms

引用

Heliyon 2025年第10期11卷

作者： Shoaib, Mohamed R. Zhao, Jun Emara, Heba M. Mubarak, Ahmed S. Omer, Osama A. Abd El-Samie, Fathi E. Esmaiel, Hamada College of Computing and Data Science (CCDS) Nanyang Technological University (NTU) Singapore 639798 Singapore Department of Electronics and Electrical Communications Engineering Ministry of Higher Education Pyramids Higher Institute (PHI) for Engineering and Technology 6th of October City 3220412 Egypt Department of Electronics and Electrical Communications Engineering Faculty of Electronic Engineering Menoufia University Menouf 32952 Egypt Department of Information Technology College of Computer and Information Sciences Princess Nourah bint Abdulrahman University Riyadh 84428 Saudi Arabia Electrical Engineering Department Aswan Faculty of Engineering Aswan University Aswan 81542 Egypt Department of Electronics and Communication Engineering College of Engineering A'Sharqiyah University Ibra 400 Oman Faculty of Engineering Aswan University Aswan 81542 Egypt

Accurate detection of brain tumors is crucial for enhancing patient outcomes, yet the interpretation of Magnetic Resonance Imaging (MRI) scans poses significant challenges. This study introduces a novel approach to brain tumor classification by exploring three pre-trained convolutional neural network (CNN) models: DenseNet201, EfficientNetB5, and InceptionResNetV2, combined with softmax activation for feature extraction. These features are then subjected to Principal Component Analysis (PCA) for dimensionality reduction. Subsequently, three machine learning models—Support Vector Machine (SVM), Multi-layer Perceptron (MLP), and Gaussian Naive Bayes (GNB)—are employed for classification. The results reveal that DenseNet201, when combined with SVM and MLP, outperforms the other models in terms of accuracy, recall, and precision. Specifically, DenseNet201 achieves 100% accuracy, recall, and precision on dataset-I and 98% accuracy, recall, and precision on dataset-II when paired with SVM and MLP. This study provides valuable insights into the interplay between CNN models, feature extraction techniques, and machine learning algorithms for brain tumor classification, highlighting the efficacy of DenseNet201 combined with SVM and MLP. © 2024 The Author(s)

关键词： Brain tumor classification Convolutional neural networks Feature extraction Image classification Machine learning Pre-processing Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Integrating local energetics into Maxwell-Calladine constraint counting to design mechanical metamaterials

引用

Physical Review E 2024年第2期110卷 025002-025002页

作者： Jason W. Rocks Pankaj Mehta Department of Physics Biological Design Center Faculty of Computing and Data Science

The Maxwell-Calladine index theorem plays a central role in our current understanding of the mechanical rigidity of discrete materials. By considering the geometric constraints each material component imposes on a set of underlying degrees of freedom, the theorem relates the emergence of rigidity to constraint counting arguments. However, the Maxwell-Calladine paradigm is significantly limited—its exclusive reliance on the geometric relationships between constraints and degrees of freedom completely neglects the actual energetic costs of deforming individual components. To address this limitation, we derive a generalization of the Maxwell-Calladine index theorem based on susceptibilities that naturally incorporate local energetic properties such as stiffness and prestress. Using this extended framework, we investigate how local energetics modify the classical constraint counting picture to capture the relationship between deformations and external forces. We then combine this formalism with group representation theory to design mechanical metamaterials where differences in symmetry between local energy costs and structural geometry are exploited to control responses to external forces.

关键词： Mechanical deformation Mechanical metamaterials Discrete symmetries Group theory

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：