检索结果-内蒙古大学图书馆

An Investigation Method Incorporates with Contextual Information and Transformer Residual BiLSTM to Improve the Accuracy of Detecting Sensitive Content in Various Contexts 8

An Investigation Method Incorporates with Contextual Informa...

引用

8th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), I-SMAC 2024

作者： Karne, Niharika Ramagundam, Chandra Shekar Patnala, Ranga Rao Ramagundam, Shashishekhar Tadiboina, Sai Nitisha C&rs Platform services Dt Amtrak United States University of South Alabama Department of Electrical Engineering Electrical engineering United States Cloud Platform Services PhiladelphiaPA United States Neuberger Berman United States Software Development & Engineering Content Discovery & Ai Comcast United States Troy University Montgomery Campus AL United States Department of Computer Science United States Geico - Chevy Chase Department of Information Technology Chevy ChaseMD20815 United States

ISBN: (纸本)9798350376425

In the modern era, the internet is an emerging technology with a rapidly growing user. Sensitive content uploaders consider this platform as a way to transmit disturbing visual content, such as animated cartoon videos to circulate unsuitable content among youngsters. Previous researches show that the interaction of online sensitive information has substantial offline effects on historically impoverished communities. As a result, it is strongly recommended that social media platforms have an automatic real-time sensitive content filtering method for detecting contextual information. In this proposed model, a novel deep-learning framework is developed for detecting sensitive content from contextual information. For this, the suggested architecture performs under three stages (i) text collection, (ii) preprocessing, and (iii) detection. Initially, the required texts from the contextual information are gathered from the standard available data resource. The collected text is subjected to text preprocessing, where the text is cleaned and prepared for further analysis. Finally, in the detection phase, the developed Transformer Residual Bidirectional Long Short-Term Memory (TR-BiLSTM) is employed to learn the effective representation from the preprocessed text and perform the sensitive content detection. Furthermore, performance comparisons are carried out between the proposed frameworks with other standard approaches. The developed architecture achieved better results in detecting the sensitive content from the text. © 2024 IEEE.

关键词： Pre-processing Techniques Sensitive Content Detection Social Media Platforms Transformer Residual Bidirectional Long Short-Term Memory

来源：评论

学校读者我要写书评

暂无评论

Deep domain adaptation by joint distribution neural matching

引用

Neural Computing and Applications 2025年第19期37卷 14541-14561页

作者： Hong, Zijie Chen, Sentao Wen, Lisheng Yang, Xiaowei School of Software Engineering South China University of Technology Panyu District Guangdong Guangzhou510006 China Department of Computer Science Shantou University Daxue Road Guangdong Shantou515063 China

Domain adaptation aims to learn a prediction model that performs well in a target domain with unlabeled data by harnessing the distributionally different labeled data from a source domain. In this paper, we design a simple yet powerful neural network approach named joint distribution neural matching (JOINT) to address the challenge of joint distribution difference/mismatch in domain adaptation. Our JOINT approach matches the source joint distribution and the target one in the activation space of a neural network by minimizing an estimate of the Jensen–Shannon (JS) divergence between the two joint distributions. The estimated JS divergence is derived in an explicit form, which frees our approach from solving a minimax adversarial problem when matching the distributions. Experiments on four representative large-scale visual recognition datasets show that our JOINT approach outperforms the state-of-the-art under both unsupervised and semi-supervised domain adaptation settings. Our code will be available at https://***/TitanRisen/JOINT-CODE. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Mental Workload Classification from fNIRS Signals by Leveraging Machine Learning

Mental Workload Classification from fNIRS Signals by Leverag...

引用

2023 IEEE Signal Processing in Medicine and Biology Symposium, SPMB 2023

作者： Hasan, M. Mahmud, M. Poudel, S. Donthula, K. Poudel, K. University of Memphis Department of Electrical and Computer Engineering TN United States Senior Software Engineer Optum Inc MurfreesboroTN United States Middle Tennessee State University Computational and Data Science MurfreesboroTN United States Middle Tennessee State University Computer Science MurfreesboroTN United States

ISBN: (纸本)9798350341256

Mental workload (MWL) identification is vital to know human cognitive functioning, performance, and well-being. In this work, we develop models for identifying low vs. high MWL using different genres of machine learning classifiers. We used non-invasive functional near-infrared spectroscopy (fNIRS) signals while participants classified the low vs. high levels of MWL tasks. Our analysis shows the low vs. high MWL can be identified best from the whole brain data. The k-nearest neighbors classifier showed the best performance with an accuracy of 98.8%, an area under the curve (AUC) of 98.8%, F1 score, precision, and recall of 98.0% from the whole brain data without overlapping signals. A separate hemisphere analysis using left hemisphere (LH) and right hemisphere (RH) activity showed that the LH activity has better classification ability than the RH activity. We also examined the classification with the top six features that could identify the low vs. high MWL with an accuracy of 97.4%, (AUC) 97.4%, F1 score, precision, and recall of 97.0%. These findings would be useful for developing more intuitive and user-friendly interfaces in the human-computer interface. © 2023 IEEE.

关键词： Infrared devices

来源：评论

学校读者我要写书评

暂无评论

Hybrid Signal Integrity Modeling and Analysis of Heterogeneous Integrated System With Neuromorphic Darwin Chip

IEEE Transactions on Signal and Power Integrity

引用

IEEE Transactions on Signal and Power Integrity 2024年 3卷 37-46页

作者： Chen, Quankun Ma, Hanzhi Li, Da Tao, Tuomin Tan, Shurun Liu, En-Xiao Schutt-Aine, Jose Li, Er-Ping Zhejiang University Key Laboratory of Advanced Micro/Nano Electronic Devices and Smart Systems and Applications College of Information Science and Electronic Engineering Hangzhou310027 China Zhejiang University University of Illinois at Urbana-Champaign Institute Haining314400 China A∗star Institute of High Performance Computing Singapore138632 Singapore University of Illinois at Urbana-Champaign Department of Electrical and Computer Engineering UrbanaIL61820 United States

This article introduces a comprehensive approach for designing and analyzing signal integrity in heterogeneous integrated systems that incorporate neuromorphic Darwin chips. The proposed integrated system architecture includes a neuromorphic Darwin chip, digital signal processing unit, microcontroller unit, field programmable gate arrays, and coding and decoding modules to encode and reconstruct analog spiking signals. The study evaluates the encoding module and the heterogeneous integration structure and conducts signal integrity analysis. To achieve optimal signal integrity performance, the article proposes a novel binocular eye diagram analysis technique. This innovative approach guides the encoding algorithm modification and improves the overall system performance. This research is the first to combine joint field-circuit simulation, heterogeneous integration modeling, and signal integrity analysis of the Darwin neuromorphic chip, and it is expected to serve as a valuable reference for future studies on similar systems. © 2022 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Some Experience Required: Comparing Professional Requirements engineering Experience to Students' Perspectives

Some Experience Required: Comparing Professional Requirement...

引用

Conference on software engineering Education & Training (CSEE&T)

作者： Ben Jelen Stephen Tsung-Han Sher Helena Donaldson Gloria Liou Amanda Stouder Steve Chenoweth Mark Hays Department of Computer Science and Software Engineering Rose-Hulman Institute of Technology Terre Haute IN USA Department of Psychological Sciences Purdue University West Lafayette IN USA

ISBN: (数字)9798331537098

ISBN: (纸本)9798331537104

Requirements engineering (RE) is a challenging topic to teach, especially when not all students see the value in learning it. Students have limited experience with RE before graduation, even after taking a required RE class and doing internships. In contrast, alumni from our program often highlight RE as one of the more important classes they take. To address this gap, we investigated current industry practices and compare that with students' perspectives. We conducted surveys with computer science and software engineering alumni ( $\mathrm{N}=116$ ) and upperclassmen ( $\mathrm{N}=38$ ), asking both groups for their thoughts on RE and examples of where it has shown up in their (budding) careers. We also interviewed survey respondents ( $\mathrm{N}=12$ ) to add more detailed examples of RE. We found that while both alumni and students find the class important, many students have negative impressions of RE and do not have opportunities to gain experience outside of our RE course or capstone. Alumni shared what the current state of RE looks like in practice, such as how some only receive requirements secondhand. Also, their examples highlight how intertwined software engineering areas can be, such as the frequent overlap with software design. We discuss these findings and offer recommendations for teaching requirements engineering to undergraduates, such as giving students RE experiences in the classroom since they do have many other opportunities before graduating.

关键词： Surveys Industries computer science software design engineering profession Education Requirements engineering Mirrors Interviews software engineering

来源：评论

学校读者我要写书评

暂无评论

Improving Multiple Sclerosis Disease Prediction Using Hybrid Deep Learning Model

引用

computers, Materials & Continua 2024年第10期81卷 643-661页

作者： Stephen Ojo Moez Krichen Meznah A.Alamro Alaeddine Mihoub Gabriel Avelino Sampedro Jaroslava Kniezova Department of Electrical and Computer Engineering College of EngineeringAnderson UniversityAndersonSC 29621USA Faculty of Computing and Information Al-Baha UniversityAl-Baha65528Saudi Arabia ReDCAD Laboratory University of SfaxSfax3038Tunisia Department of Information Technology College of Computer&Information SciencePrincess Nourah Bint Abdul Rahman UniversityRiyadh11564Saudi Arabia Department of Management Information Systems College of Business and EconomicsQassim UniversityP.O.Box 6640Buraidah51452Saudi Arabia School of Management and Information Technology De La Salle-College of Saint BenildeManila1004Philippines Department of Information Management and Business Systems Faculty of ManagementComenius University BratislavaBratislava 2582005Slovakia

Myelin damage and a wide range of symptoms are caused by the immune system targeting the central nervous system in Multiple Sclerosis(MS),a chronic autoimmune neurological *** disrupts signals between the brain and body,causing symptoms including tiredness,muscle weakness,and difficulty with memory and *** methods for detecting MS are less precise and time-consuming,which is a major gap in addressing this *** gap has motivated the investigation of new methods to improve MS detection consistency and *** paper proposed a novel approach named FAD consisting of Deep Neural Network(DNN)fused with an Artificial Neural Network(ANN)to detect MS with more efficiency and accuracy,utilizing regularization and combat *** use gene expression data for MS research in the GEO GSE17048 *** dataset is preprocessed by performing encoding,standardization using min-max-scaler,and feature selection using Recursive Feature Elimination with Cross-Validation(RFECV)to optimize and refine the ***,for experimenting with the dataset,another deep-learning hybrid model is integrated with different ML models,including Random Forest(RF),Gradient Boosting(GB),XGBoost(XGB),K-Nearest Neighbors(KNN)and Decision Tree(DT).Results reveal that FAD performed exceptionally well on the dataset,which was evident with an accuracy of 96.55%and an F1-score of 96.71%.The use of the proposed FAD approach helps in achieving remarkable results with better accuracy than previous studies.

关键词： Multi Sclerosis(MS) machine learning deep learning artificial neural network healthcare

来源：评论

学校读者我要写书评

暂无评论

Real-Time Detection of UAV Small Target's Infrared Imaging via OSTD-YOLOv8

Real-Time Detection of UAV Small Target's Infrared Imaging v...

引用

2024 IEEE URUCON, URUCON 2024

作者： Dahri, Fida Hussain Laghari, Asif Ali Dahri, Nisar Ahmed Abro, Ghulam E Mustafa Estrela, Vania V. De Oliveira, G.G. Iano, Y. Chuma, Euclides L. Southeast University School of Computer Science and Engineering Nanjing China Shenyang Normal University Software College Shenyang China University Teknologi Malaysia Faculty of Educational Sciences and Technology Johor Bahru Malaysia King Fahd University of Petroleum and Minerals Interdisciplinary Research Centre for Aviation and Space Exploration Dhahran Saudi Arabia Department of Telecommunications Niteroi Brazil School of Electrical and Computer Engineering Campinas Brazil School of Technology Limeira Brazil

ISBN: (纸本)9798350355383

Unmanned aerial vehicles (UAVs) have boosted modern living. Tiny, frail high-density targets, low resolution, complicated backgrounds, noise, and poor real-time exposure performance have augmented due to UAV firms. Realtime recognition in high-altitude (HA) infrared thermal images is intricate. Our fresh OSTD-YOLOv8 is a multi-class target recognition tactic to tackle these issues and spot and classify objects on the HIT-UAV dataset. YOLOv8 is an effective advanced object detection model. Our OSTD-YOLOv8 model detects small objects in HA thermal images with 90% precision, 91.5% recall, 90.5% F1-score, 89.1% AP, and 98% mAP. Our unique approach delivers effective object recognition in difficult thermal imaging conditions. Consequently, this distinctive UAV-focused HA, thermal, target detection scheme can be used. © 2024 IEEE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Automatic Detection of Peripheral Facial Landmarks Using 3D Facial Data

Automatic Detection of Peripheral Facial Landmarks Using 3D ...

引用

International Conference on Image and Vision Computing New Zealand, IVCNZ

作者： Mehraan Chowdhury Mohammed Bennamoun Farid Boussaid Syed Mohammed Shamsul Islam Department of Computer Science and Software Engineering University of Western Australia Perth Australia Department of Electrical Electronic and Computer Engineering University of Western Australia Perth Australia Discipline of Computing and Security Edith Cowan University Perth Australia

ISBN: (数字)9798331518776

ISBN: (纸本)9798331518783

Facial landmarking research has traditionally fo-cused on midface landmarks, largely overlooking peripheral facial features that are crucial in specialized medical applications. This study addresses this gap by developing a novel model to detect 12 peripheral landmarks, which are valuable in clinical scenarios such as obstructive sleep apnea detection and facial palsy assessment. Using the FRGC v2 dataset of 3D facial scans, we manually annotated a subset of 900 scans with peripheral landmarks following a rigorous pre-processing protocol. Building upon a high-performance deep learning model initially designed for midface landmark detection, we restructured its architecture to predict peripheral landmarks by modifying its output layers and training it from scratch using 2D projections of 3D scans. We conducted a comprehensive set of experiments, systematically testing different input configurations by varying both the number of images per scan (16, 32, and 64) and the image types (mesh-only, RGB, and depth maps). The model demonstrated its potential by achieving a mean error of 10.72 mm, highlighting the promise of deep learning techniques in addressing the complex challenge of peripheral landmark detection. These findings underscore the model's capability to support niche medical applications and open pathways for future advancements that could refine its accuracy, ultimately contributing to improved diagnostic tools in healthcare.

关键词： Training Deep learning Solid modeling Biomedical equipment Three-dimensional displays Protocols Medical services Transforms Sleep apnea Testing

来源：评论

学校读者我要写书评

暂无评论

Enhanced Synthetic Images Classification with Vision Transformers and Effective Data Augmentation Techniques

Enhanced Synthetic Images Classification with Vision Transfo...

引用

IEEE International Conference on Multi Topic

作者： Khadija Haider Muhammad Sohail Abbas Asif Muhammad Muhid Qaiser Department of Artificial Intelligence and Data Science National University of Computer and Emerging Sciences Islamabad Pakistan Department of Software Engineering National University of Computer and Emerging Sciences Islamabad Pakistan

ISBN: (数字)9798331507213

ISBN: (纸本)9798331507220

Synthetic images have made significant advancements, resulting in highly realistic and high-quality visuals generated at an unprecedented speed. However, the proliferation of synthetic images raises growing concerns regarding their potential misuse, ethical implications, and associated risks in various sectors. This study focuses on leveraging data augmentation techniques to enhance the accuracy and reliability of synthetic image detection. In our study, we fine-tuned a Vision Transformer (ViT) on the CIFAKE dataset, comprising real and synthetic images, augmented using various techniques such as transformations, photometric adjustments, geometric changes, and noise addition. The best results were obtained with ViT fine-tuned by distortions and noise augmentation, achieving an accuracy rate of 98.66%, demonstrating that sophisticated augmentation techniques improve performance. Data augmentation plays a crucial role in handling the increasing realism and sophistication of synthetic images, contributing to more effective content moderation, digital forensics efforts, and the mitigation of potential risks associated with synthetic media.

关键词： Performance evaluation computer vision Visualization Accuracy Computational modeling Transformers Distortion Data augmentation Reliability Image classification

来源：评论

学校读者我要写书评

暂无评论

MR Image Quality Assessment via Enhanced Mamba: A Hybrid Spatial-Frequency Approach

MR Image Quality Assessment via Enhanced Mamba: A Hybrid Spa...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Yiwei Lou Dexuan Xu Rongchao Zhang Jiayu Zhang Yongzhi Cao Hanpin Wang Yu Huang Ministry of Education Key Laboratory of High Confidence Software Technologies (Peking University) School of Computer Science Peking University Beijing China School of Software & Microelectronics Peking University Beijing China National Engineering Research Center for Software Engineering Peking University Beijing China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Magnetic resonance (MR) image quality assessment plays a crucial role in disease diagnosis and data analysis. Existing methods typically treat the data as images and process them with convolutional networks, thereby ignoring the sequential characteristics of MR data. In this paper, we propose a hybrid spatial-frequency network (HSFNet) for MR image quality assessment, which extracts MR image quality features in both spatial and frequency domains. Specifically, within each data domain, information from local images and global sequences is iteratively integrated by applying a Mamba-based cascading processing module for multiple times. Extensive experiments on both T1-weighting and T2-weighting MR datasets demonstrate the proposed method’s effectiveness and generalization ability in comparison with state-of-the-art MR image quality assessment methods.

关键词： Image quality Accuracy Data analysis Frequency-domain analysis Noise Magnetic resonance Focusing Feature extraction Medical diagnosis Convolutional neural networks

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：