检索结果-内蒙古大学图书馆

2nd International Conference on Advances in Computation, Communication and Information technology, ICAICCIT 2024

作者： Anisha Sabharwal, Munish Tripathi, Rohit Department of Computer Science and Engineering Galgotias Univerisity Greater Noida India MRIIRS Faridabad India Department of Computer Science and Engineering IILM University Greater Noida India Department of Electronics Engineering JC Bose University of Science & Technology India

ISBN: (纸本)9798331541217

Millions of people worldwide suffer from urinary tract infections (UTIs), which are a common and recurring health problem. In order to limit possible health problems and stop the spread of disease, early identification and prompt management are essential. In order to overcome this issue, the Internet of Things and machine learning techniques are combined in the novel approach presented in this study. The suggested method continually monitors real-time vital signs and urine biomarkers using IoT-enabled wearable and smart sensors. Principle Component Analysis feature selection approaches are used to optimize the pertinent data inputs in order to improve the accuracy of UTI prediction. A centralized ML-driven processing unit is used to perform complex ML algorithms, such as the Ensemble Bagging Decision Tree Classifier classification model, to analyses and decipher the patterns of the gathered data. The technology reliably recognizes and anticipates UTIs, sending early warning signals to patients and medical professionals. In order to improve patient care and public health outcomes, our ML-IoT fusion in UTI detection offers a non-intrusive and proactive technique. The suggested EBDTC technique outperforms the existing approaches with an accuracy rate of 96.25%. The results of the study demonstrate how disruptive technology has the ability to successfully treat common health issues, expanding the area of healthcare diagnostics. © 2024 IEEE.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Biomedical Lay Summarization: Research Progress and Challenges 3

Biomedical Lay Summarization: Research Progress and Challeng...

引用

3rd International Conference on Intelligent Systems, Advanced Computing, and Communication, ISACC 2025

作者： Bhowmik, Souramita Jamatia, Anupam Rudrapal, Dwijen Chakma, Kunal National Institute of Technology Agartala Computer Science & Engineering Department Agartala India

ISBN: (纸本)9798331523893

Biomedical lay summarization focuses on transforming complex scientific concepts into clear, concise, and accessible language, avoiding specialized technical terminology. This approach enables audiences without specialized knowledge to understand intricate biomedical topics. As research in biomedical lay summarization progresses, it aims to deliver accurate and user-friendly health information. Lay summaries not only condense content but also simplify language, enhancing both accessibility and readability. This review provides an extensive analysis of the field, highlighting key methods, models, evaluation systems, and challenges. The study surveys recent advancements in summarization quality and underscores the potential of biomedical lay summarization to improve patient engagement, public health communication, and informed decision-making. This thorough review encourages further innovation and emphasizes the need for multimodal approaches in biomedical summarization. © 2025 IEEE.

关键词： Biomedical Biomedical Lay summarization Lay-friendly Language Machine learning Natural Language Processing Summarization

来源：评论

学校读者我要写书评

暂无评论

Efficient Fetal Health Monitoring and Classification with Machine Learning 7

Efficient Fetal Health Monitoring and Classification with Ma...

引用

7th International Conference on Intelligent Computing and Control Systems, ICICCS 2023

作者： Singh, Kabir Shyry, Prayla Franklin, Ramya G Sathyabama Institute of Science and Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350397253

The goal of the research on fetal health categorization using machine learning is to create a model that can precisely predict the condition of a fetus during pregnancy. This is crucial because prompt action following early identification of fetal health issues might enhance the pregnancy's outcome. This research study suggests classifying fetal health status using machine learning approaches based on ultrasound images and other clinical parameters. To train and test our model, we will gather a sizable dataset of ultrasound images and clinical characteristics from pregnant women. To categorize the state of fetal health, the proposed model will employ machine learning algorithms and image processing techniques. Our approach should categorize fetal health status with a high degree of accuracy, and it will help obstetricians and gynecologists provide better treatment for pregnant patients. © 2023 IEEE.

关键词： Genetic programming

来源：评论

学校读者我要写书评

暂无评论

Bangla Protest News Categorization Using Deep Learning 26

Bangla Protest News Categorization Using Deep Learning

引用

26th International Conference on computer and Information technology, ICCIT 2023

作者： Mosleh, Mahir Sayem, Md. Abu Shahidur Rahman, M. Islam, Md Saiful Shahjalal University of Science and Technology Department of Computer Science and Engineering Sylhet Bangladesh

ISBN: (纸本)9798350359015

Protests are a vital form of public expression, often reflecting collective dissent towards specific policies or injustices. In recent years, the significance of protests as a medium for public opinion has escalated, necessitating effective categorization for informed decision-making by policymakers, law enforcement, researchers, and journalists. This paper presents the first study on categorizing Bangla protest-related news articles, addressing the absence of a publicly available annotated dataset in this domain. We collected and annotated a dataset of 8,039 protest-related news articles from prominent Bangla newspapers, such as Prothom Alo, Samakal, Daily Star Bangla, and Ittefaq. We employed a multifaceted approach, leveraging attention mechanisms with deep learning and transformer-based models to categorize protest news into eight predefined protest categories. The fine-tuned multilingual BERT model showcased superior efficacy, achieving an accuracy of 91.58% and an F1 score of 91.43%. This study fills a critical gap in protest categorization research and provides a comprehensive dataset and methodological approach for future exploration. The findings have significant implications for understanding the dynamics of social movements and public protests, offering valuable insights for academics and practitioners alike. This research paves the way for further studies in categorizing protest-related news, particularly in underrepresented languages like Bangla. © 2023 IEEE.

关键词： Bangla Bangla News BERT LSTM NLP Protest Classification Protest News

来源：评论

学校读者我要写书评

暂无评论

A Dataset Development for Fake News Detection in Low-Resource Romanized Manipuri 3

A Dataset Development for Fake News Detection in Low-Resourc...

引用

3rd International Conference on Intelligent Systems, Advanced Computing, and Communication, ISACC 2025

作者： Devi, Takhellambam Babylon Jamatia, Anupam Rudrapal, Dwijen Chakma, Kunal National Institute of Technology Agartala Computer Science & Engineering Department Agartala India

ISBN: (纸本)9798331523893

In today's digital landscape, the rapid spread of fake news presents significant challenges, particularly in multilingual nations like India. Manipuri, the primary language of Manipur in Northeast India, has seen a surge in online usage and digital adaptation, making it easier for Manipuri-speaking communities to engage with each other. However, despite this growth, there is a lack of resources for identifying fake news in Manipuri, especially in its Romanized form. This study focuses on developing a dataset to detect fake news in Romanized Manipuri, especially in the sports domain. Since there were no existing datasets for this language, the dataset was compiled by collecting articles from credible Manipuri news sources, transliterating them with contributors, and labelling each as either 'fake' or 'real' to aid in effective detection. Every step, from collecting data to labelling it, was done carefully by hand to ensure accuracy. Statistical tests were also performed to find important language patterns that help distinguish between real and fake news. Our findings show the unique language features of Romanized Manipuri and provide a solid foundation for future work in developing machine-learning models for detecting misinformation. By developing this dataset, we aim to improve the availability of reliable information for Manipuri-speaking communities. © 2025 IEEE.

关键词： Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Unmasking Deepfake Faces from Videos Using An Explainable Cost-Sensitive Deep Learning Approach 26

Unmasking Deepfake Faces from Videos Using An Explainable Co...

引用

26th International Conference on computer and Information technology, ICCIT 2023

作者： Mahmud, Faysal Abdullah, Yusha Islam, Minhajul Aziz, Tahsin Ahsanullah University of Science and Technology Department of Computer Science and Engineering Dhaka Bangladesh

ISBN: (纸本)9798350359015

Deepfake technology is widely used, which has led to serious worries about the authenticity of digital media, making the need for trustworthy deepfake face recognition techniques more urgent than ever. This study employs a resource-effective and transparent cost-sensitive deep learning method to effectively detect deepfake faces in videos. To create a reliable deepfake detection system, four pre-trained Convolutional Neural Network (CNN) models: XceptionNet, InceptionResNetV2, EfficientNetV2S, and EfficientNetV2M were used. FaceForensics++ and CelebDf-V2 as benchmark datasets were used to assess the performance of our method. To efficiently process video data, key frame extraction was used as a feature extraction technique. Our main contribution is to show the model's adaptability and effectiveness in correctly identifying deepfake faces in videos. Furthermore, a cost-sensitive neural network method was applied to solve the dataset imbalance issue that arises frequently in deepfake detection. The XceptionNet model on the CelebDf-V2 dataset gave the proposed methodology a 98% accuracy, which was the highest possible whereas, the InceptionResNetV2 model, achieves an accuracy of 94% on the FaceForensics++ dataset. Source Code: https://***/Faysal-MD/Unmasking-Deepfake-Faces-from-Videos-An-Explainable-Cost-Sensitive-Deep-Learning-Approach-IEEE2023 © 2023 IEEE.

关键词： CelebDf CNN Cost-sensitive Deepfake video Explainable AI (XAI) Face Detection FaceForensics++ Keyframe

来源：评论

学校读者我要写书评

暂无评论

Transition metal anchored on C_(9)N_(4) as a single-atom catalyst for CO_(2) hydrogenation: A first-principles study

引用

Chinese Physics B 2022年第10期31卷 520-528页

作者： Jia-Liang Chen Hui-Jia Hu Shi-Hao Wei Department of Microelectronic Science and Engineering School of Physical Science and TechnologyNingbo UniversityNingbo 315211China Department of Electronic and Information Engineering School of Electrical Engineering and Computer ScienceNingbo UniversityNingbo 315211China

To alleviate the greenhouse effect and maintain the sustainable development, it is of great significance to find an efficient and low-cost catalyst to reduce carbon dioxide(CO_(2)) and generate formic acid(FA). In this work, based on the first-principles calculation, the catalytic performance of a single transition metal(TM)(TM = Cr, Mn, Fe, Co, Ni, Cu, Zn,Ru, Rh, Pd, Ag, Cd, Ir, Pt, Au, or Hg) atom anchored on C_(9)N_(4) monolayer(TM@C_(9)N_(4)) for the hydrogenation of CO_(2) to FA is calculated. The results show that single TM atom doping in C_(9)N_(4) can form a stable TM@C_(9)N_(4) structure, and Cu@C_(9)N_(4) and Co@C_(9)N_(4) show better catalytic performance in the process of CO_(2) hydrogenation to FA(the corresponding maximum energy barriers are 0.41 eV and 0.43 e V, respectively). The partial density of states(PDOS), projected crystal orbital Hamilton population(p COHP), difference charge density analysis and Bader charge analysis demonstrate that the TM atom plays an important role in the reaction. The strong interaction between the 3d orbitals of the TM atom and the non-bonding orbitals(1πg) of CO_(2) allows the reaction to proceed under mild conditions. In general, our results show that Cu@C_(9)N_(4) and Co@C_(9)N_(4) are a promising single-atom catalyst and can be used as the non-precious metals electrocatalyst for CO_(2) hydrogenation to formic acid.

关键词： first-principles calculation CO_(2)hydrogenation catalysts electronic structure reaction mechanisms reaction paths

来源：评论

学校读者我要写书评

暂无评论

Dempster-shafer deep capsule attention model (DDCAM)

引用

Multimedia Tools and Applications 2025年 1-29页

作者： Mehravaran, Zahra Ghanizadeh, Ahmad Navid Hamidzadeh, Javad Harati, Ahad Mashhad Iran Department of Computer Science Saarland University Saarbrücken Germany Faculty of Computer Engineering and Information Technology Sadjad University Mashhad Iran

A capsule neural network faces significant challenges in achieving high accuracy on complex datasets due to its high computational complexity and limited ability to represent features. To overcome these limitations, this paper proposes a novel framework, Dempster-Shafer Deep Capsule Attention Model (DDCAM), that combines 3D convolution with attention mechanisms to improve feature representation. This model utilizes the Dempster-Shafer Theory to manage uncertainty and optimize feature selection, resulting in more reliable and accurate learning. In this architecture, dense capsule blocks are used to improve gradient flow and mitigate the effects of vanishing gradients. The DDCAM consistently outperforms state-of-the-art capsule networks on a wide range of datasets, especially complex datasets such as MNIST, CIFAR10, SVHN, and Fashion MNIST. DDCAM improves accuracy by 1.29% on CIFAR10 and 0.76% on SVHN compared to existing models, while achieving precision improvements of 1.22% and 1.08% on CIFAR10 and SVHN, respectively. Additionally, experiments conducted on the AffNIST dataset demonstrate the robustness of DDCAM in handling affine transformations, where it achieved significantly higher accuracy compared to existing models. These results illustrate the model’s enhanced ability to capture complex data relationships and improve both accuracy and precision, advancing capsule neural network performance. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Affine transforms

来源：评论

学校读者我要写书评

暂无评论

High-Frequency Performance with Microwave and Millimeter-Wave Methods 1

High-Frequency Performance with Microwave and Millimeter-Wav...

引用

1st IEEE International Conference on Emerging Research in Computational science, ICERCS 2023

作者： Poornima, D. Jany Shabu, S.L. Refonaa, J. Karunya, K. Bobby, M.P. Sathyabama Institute of Science & Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350359756

Modern wireless communication, radar systems, and the realization of new technologies like 5G and beyond all rely heavily on high-frequency performance. The use of microwave and millimeter-wave techniques (MMWT) could provide revolutionary new uses for vast amounts of data at extremely low latency. High-frequency performance optimization is still a challenging and essential problem. Interference Mitigation, Antenna Design, Signal Processing, and Regulatory Compliance are all considered to be sizeable obstacles towards accomplishing High-Frequency Performance. The motive of the research is to advocate the use of Regulatory Compliance Frequency Band Analysis (RCFBA) for the purpose of figuring out target frequencies in accordance with utility necessities and acting spectrum scanning and evaluation with the intention to assess regulatory constraints and available channels. Maximizing signal energy even as keeping off interference via cautiously choosing and positioning antennas. Enabling higher data throughput, decrease latency, and a wider variety of applications for high-frequency systems by way of easing their adoption and deployment in fields like telecommunications, radar systems, satellite communique, and 5G networks. High-frequency performance can be modelled and evaluated with the help of present day modeling tools, that may then be used to optimize gadget parameters, propagation, and antenna designs. It equips users with the way for thorough simulation evaluation, optimization, and fulfillment in excessive-frequency packages, taking into account the deployment of excessive-frequency structures that healthy the desires of contemporary packages and regulatory standards. © 2023 IEEE.

关键词： Regulatory compliance

来源：评论

学校读者我要写书评

暂无评论

Advancing Abstractive Bangla Text Summarization: A Deep Learning Approach Using Seq2seq Encoder- Decoder Model and T5 Transformer 5

Advancing Abstractive Bangla Text Summarization: A Deep Lear...

引用

5th International Conference on Sustainable Technologies for Industry 5.0, STI 2023

作者： Tasnimul Hasan, S.M. Rahman, Md Ashfaqur Hasan, Md Mahamudul Hasan, Mohammad Rakibul Hoque, Md Moinul Ahsanullah University of Science and Technology Department of Computer Science and Engineering Dhaka Bangladesh

ISBN: (纸本)9798350394290

Text summarization plays a vital role in distilling essential information from large volumes of text. While significant progress has been made in English text summarization using deep learning techniques, the research on Bangla text summarization remains limited, with most existing methods relying on non-deep learning approaches. This study addresses the scarcity of abstractive Bangla text summarization methods by conducting a comprehensive analysis using two deep learning models: Sequence-to-sequence (se q2se q) encoder-decoder model and T5 transformer. Through evaluation using BERT and ROUGE scores on the AUST NLP Research dataset and standard BNLPC datasets, this study reveals the Seq2seq model's superior performance in generating coherent abstractive summaries. According to the investigation's findings, the average F1-score is 0.8551, with average precision and recall of 0.8527 and 0.8578, respectively, determined through BERT score evaluations. © 2023 IEEE.

关键词： Deep learning

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：