检索结果-内蒙古大学图书馆

NeuroProbe: A Performance Profiling Feed Forward Neural Network Simulator for Hardware Interaction Analysis

SN computer science 2025年第5期6卷 1-22页

作者： Ayyappan, Binu Kumar, G. Santhosh Department of Computer Science Cochin University of Science and Technology Kochi India Department of Artificial Intelligence and Data Science Rajagiri School of Engineering & Technology Kochi India

NeuroProbe is a simple neural network simulator designed by authors specifically for educational purposes focusing on simulating inference phase on a computationally capable embedded hardware, aiming to provide a deeper understanding of hardware interactions and performance improvement. This simulator incorporates performance profiling capabilities, allowing students and educators to analyze and optimize the performance of a simulated trained neural network. By simulating the intricate hardware interactions, NeuroProbe enables users to gain insights into how various components impact the overall performance of neural networks. Using this simulator, learners can experiment with different configurations and architectures, identify potential bottlenecks, and explore optimization strategies to enhance neural network performance before deploying the model on an Edge Computing environment. It also enriches computer science education by enabling learners to gain deeper insights into hardware interactions and performance improvement. By identifying performance bottlenecks, learners can refine their understanding of neural networks and develop skills in optimizing their models for enhanced performance. In conclusion, NeuroProbe empowers users to bridge the gap between theoretical knowledge and practical implementation of neural network on an embedded device, fostering a more comprehensive understanding of neural networks and their hardware requirements. Currently, it is focused solely on single-threaded CPU-based computation enabling SSE, AVX. At present, NeuroProbe does not support SIMD extensions such as AVX-FMA, AVX-512, multi-threaded computation, and accelerators such as NPU, TPU, and GPU. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Hardware–software interactions Neural network simulator NeuroProbe Performance bottlenecks Performance profiling Simulations

来源：评论

学校读者我要写书评

暂无评论

Bi-clustering of Binary data via Neurodynamics-driven Binary Matrix Factorization 13

Bi-clustering of Binary Data via Neurodynamics-driven Binary...

引用

13th International Conference on Intelligent Control and Information Processing, ICICIP 2025

作者： Li, Hongzong Wang, Jun Department of Computer Science City University of HongKong Kowloon Hong Kong Department of Computer Science Department of Data Science City University of HongKong Kowloon Hong Kong

ISBN: (纸本)9798331516147

Bi-clustering, also known as co-clustering, is a powerful data analysis technique that simultaneously clusters rows and columns of a data matrix, revealing hidden patterns. In this paper, we propose a neurodynamics-driven binary matrix factorization approach for bi-clustering binary data. The proposed method utilizes multiple discrete Hopfield networks operating concurrently to explore local optimal solutions. Furthermore, a particle swarm optimization rule is iteratively applied to reinitialize the neuronal states for directing the search toward better solutions. Comparative evaluations across six benchmark datasets reveal that the proposed method outperforms five existing methods in terms of five internal and external indices. © 2025 IEEE.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

Ordinal classification for knee osteoarthritis x-rays using vision transformers

引用

Multimedia Tools and Applications 2025年 1-28页

作者： Tariq, Tayyaba Suhail, Zobia Nawaz, Zubair Department of Computer Science University of the Punjab Allama Iqbal Campus Punjab Lahore54000 Pakistan Department of Data Science University of the Punjab Allama Iqbal Campus Punjab Lahore54000 Pakistan

Knee Osteoarthritis is a progressive and chronic knee joint disease that shows symptoms of pain, stiffness, and swelling and is diagnosed by knee radiographs. These radiographs are evaluated by radiologists using Kellgren and Lawrence’s (KL) grading scheme. According to this scheme, the knee radiograph is graded from KL grade 0 (i.e., Normal) to KL grade 4 (i.e., Severe) to assess the KOA severity. For an automated system, the first step is to localize knee joints from knee radiographs and then classify them according to the KL grading system. In this work, we have proposed vision-based transformers to localize knee joints. We also proposed a single-stage model to localize the knee and classify KOA using a single model. We also explored and compared the performance of various transformers using a multiclass image classification strategy. Since KL grades maintain intrinsic ordinal information of KL grades, we employed an ordinal classification-based strategy to improve automated knee osteoarthritis classification performance. A total of 10 models are trained and validated on multiple datasets, and visualizations are generated for the best model for better comprehension. Our model obtained state-of-the-art results for knee detection and ordinal X-ray classification for KOA. Analysis of Variance (ANOVA) tests also indicate that the ordinal classification approach significantly improves the performance of models over traditional image classification approaches. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Arthroplasty

来源：评论

学校读者我要写书评

暂无评论

Using CNN and Transformer Model for Unimodal Speech Emotion Recognition on MELD and IEMOCAP

Using CNN and Transformer Model for Unimodal Speech Emotion ...

引用

2025 International Conference on Advancement in data science, E-learning and Information System, ICADEIS 2025

作者： Aurelio, Clarence Chowanda, Andry Bina Nusantara University Binus Graduate Program - Master of Computer Science Computer Science Department Jakarta Indonesia School of Computer Science Bina Nusantara University Computer Science Department Jakarta Indonesia

ISBN: (纸本)9798331513320

Emotion Recognition is one field that is taking the world by storm in this current age. Multimodal emotion recognition has shown promising results however, previous studies shows that recognition using speech is a field has not performed that greatly. Previous research used popular methods such as CNN, RNN, and other machine learning methods has been used to achieved good results with the help of other modality, where if speech were to be used alone the results won't be as good. A factor that contributes to the result of the speech modality not performing as well is the fact of the dataset and the way it was processed. Therefore, this research looks into what makes speech one of the lowest performing modalities by preprocessing the dataset using a different method than previous researches as well as using a CNN model paired with a Transformer model. Results achieved from this research showed an improvement when using IEMOCAP by 8.09% and MELD by 1.06%. A comparison results of using the pre-processed data with previous studies model was also done to compare the results. In conclusion, this research has explored a different preprocessing method and deep learning model that has achieved results better than previous works with the same dataset. © 2025 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

StealthFace:Transfer Learning-Based Ensemble Model for Disguised Face Recognition using Skin-Segmented Images

IAENG International Journal of Computer Science

引用

IAENG International Journal of computer science 2025年第4期52卷 1244-1260页

作者： Padmashree, G. Kotegar, Karunakar A Department of Data Science and Computer Applications Manipal Institute of Technology Manipal Academy of Higher Education Karnataka Manipal576104 India

Disguised face identification is challenging since people cover their identities by wearing masks, hats, sunglasses, or other disguises. These disguises dramatically modify face features, making identifying individuals a difficult task. In this study, we introduce StealthFace, an ensemble model that utilizes transfer learning and skin-segmented images to improve the recognition of disguised faces. To improve the accuracy and resilience of disguised face recognition, StealthFace leverages the power of deep learning algorithms, transfer learning, and ensemble methods. The framework employs pre-trained convolutional neural network models, such as ResNet50 and DenseNet121 for feature extraction and to learn discriminative features that are important in identifying individuals despite the disguises. The ensemble approach combines models’ predictions, utilizing their collective expertise and capturing multiple perspectives on disguised faces. Our ensemble model outperforms other state-of-the-art methods with an overall accuracy of 99.24% and contributes to enhancing security measures and advancing the development of face recognition systems. © (2025), (International Association of Engineers). All Rights Reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Effi-CNN: real-time vision-based system for interpretation of sign language using CNN and transfer learning

引用

Multimedia Tools and Applications 2025年第6期84卷 3137-3159页

作者： Pranav Katarya, Rahul Big Data Analytics and Web Intelligence Laboratory Computer Science & Engineering Department Delhi Technological University New Delhi India

The deaf and mute population has difficulty conveying their thoughts and ideas to others. Sign language is their most expressive mode of communication, but the general public is callow of sign language;therefore, the mute and deaf have difficulty communicating with others. A system that can correctly translate sign language motions to speech and vice versa in real time is required to overcome this communication barrier. Effi-CNN, a vision-based Sign Language Recognition (SLR) system employing transfer learning with EfficientNetB2, is proposed in this paper. We have also developed a system covering sign gestures to text in real time. Our approach was evaluated on eight publicly available datasets, including the Massey University gesture dataset, the ArSL2018 dataset, the MNIST-ASL dataset, and others. When comparing our results to state-of-the-art algorithms, the experimental findings showed that our proposed work is more successful than existing models. Our proposed model delivered an accuracy of 99.90 on MNIST dataset. The results show that our Effi-CNN surpasses most currently existing solutions and can categorize many gestures with a low error rate. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-Based Routing Protocol in Flying Ad Hoc Networks: A Review

引用

computers, Materials & Continua 2025年第2期82卷 1615-1643页

作者： Priyanka Manjit Kaur Deepak Prashar Leo Mrsic Arfat Ahmad Khan Department of Computer Science and Engineering(CSE) Lovely Professional UniversityPhagwara144411India Department for Program Engineering Algebra UniversityGradiscanska 24Zagreb10000Croatia Department of Computer Science College of ComputingKhon Kaen UniversityKhon Kaen40002Thailand

“Flying Ad Hoc Networks(FANETs)”,which use“Unmanned Aerial Vehicles(UAVs)”,are developing as a critical mechanism for numerous applications,such as military operations and civilian *** dynamic nature of FANETs,with high mobility,quick node migration,and frequent topology changes,presents substantial hurdles for routing protocol *** the preceding few years,researchers have found that machine learning gives productive solutions in routing while preserving the nature of FANET,which is topology change and high *** paper reviews current research on routing protocols and Machine Learning(ML)approaches applied to FANETs,emphasizing developments between 2021 and *** research uses the PRISMA approach to sift through the literature,filtering results from the SCOPUS database to find 82 relevant *** research study uses machine learning-based routing algorithms to beat the issues of high mobility,dynamic topologies,and intermittent connection in *** compared with conventional routing,it gives an energy-efficient and fast decision-making solution in a real-time environment,with greater fault tolerance *** protocols aim to increase routing efficiency,flexibility,and network stability using ML’s predictive and adaptive *** comprehensive review seeks to integrate existing information,offer novel integration approaches,and recommend future research topics for improving routing efficiency and flexibility in ***,the study highlights emerging trends in ML integration,discusses challenges faced during the review,and discusses overcoming these hurdles in future research.

关键词： FANET protocol machine learning

来源：评论

学校读者我要写书评

暂无评论

Leveraging BERT, DistilBERT, and TinyBERT for Rumor Detection

引用

IEEE Access 2025年 13卷 72918-72929页

作者： Qazi, Aijazahamed Goudar, R.H. Patil, Rudragoud Hukkeri, Geetabai S. Kulkarni, Dhanashree Angadi Institute of Technology and Management Department of Artificial Intelligence and Data Science Belagavi591108 India Visvesvaraya Technological University Department of Computer Science and Engineering Belagavi590018 India KLS Gogte Institute of Technology Department of Computer Science and Engineering Belagavi590008 India Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Department of Computer Science and Engineering Karnataka Manipal576104 India Angadi Institute of Technology and Management Department of Computer Science and Engineering Belagavi591108 India

The rapid spread of false information on social media has become a major challenge in today’s digital world. This has created a need for an effective rumor detection system that can identify and control the spread of false information in real-time. The proposed work introduces a rumor detection system by integrating transformer-based models such as BERT, DistilBERT, and TinyBERT with traditional Machine Learning (ML) techniques. The classifiers include Decision Tree (DT), Support Vector Machine (SVM), Random Forest (RF) and Naïve Bayes (NB) help in categorizing content as either rumor or non-rumor based on the patterns. The proposed work evaluated BERT, DistilBERT, TinyBERT combined with ML models (SVM, DT, RF, NB) across PHEME dataset using 70:30, 60:40, and 80:20 splits. Overall, BERT + DT and TinyBERT + SVM provided significant results, with BERT + RF and DistilBERT + NB demonstrating better classification capabilities across various events and split ratios on the dataset. © 2013 IEEE.

关键词： Tweets

来源：评论

学校读者我要写书评

暂无评论

Steel Surface Defect Detection Using Learnable Memory Vision Transformer

引用

computers, Materials & Continua 2025年第1期82卷 499-520页

作者： Syed Tasnimul Karim Ayon Farhan Md.Siraj Jia Uddin Department of Computer Science and Engineering BRAC UniversityDhaka1212Bangladesh Department of AI and Big Data Endicott CollegeWoosong UniversityDaejeon34606Republic of Korea

This study investigates the application of Learnable Memory Vision Transformers(LMViT)for detecting metal surface flaws,comparing their performance with traditional CNNs,specifically ResNet18 and ResNet50,as well as other transformer-based models including Token to Token ViT,ViT withoutmemory,and Parallel *** awidely-used steel surface defect dataset,the research applies data augmentation and t-distributed stochastic neighbor embedding(t-SNE)to enhance feature extraction and *** techniques mitigated overfitting,stabilized training,and improved generalization *** LMViT model achieved a test accuracy of 97.22%,significantly outperforming ResNet18(88.89%)and ResNet50(88.90%),aswell as the Token to TokenViT(88.46%),ViT without memory(87.18),and Parallel ViT(91.03%).Furthermore,LMViT exhibited superior training and validation performance,attaining a validation accuracy of 98.2%compared to 91.0%for ResNet 18,96.0%for ResNet50,and 89.12%,87.51%,and 91.21%for Token to Token ViT,ViT without memory,and Parallel ViT,*** findings highlight the LMViT’s ability to capture long-range dependencies in images,an areawhere CNNs struggle due to their reliance on local receptive fields and hierarchical feature *** additional transformer-based models also demonstrate improved performance in capturing complex features over CNNs,with LMViT excelling particularly at detecting subtle and complex defects,which is critical for maintaining product quality and operational efficiency in industrial *** instance,the LMViT model successfully identified fine scratches and minor surface irregularities that CNNs often *** study not only demonstrates LMViT’s potential for real-world defect detection but also underscores the promise of other transformer-based architectures like Token to Token ViT,ViT without memory,and Parallel ViT in industrial scenarios where complex spatial relationships are *** research m

关键词： Learnable Memory Vision Transformer(LMViT) Convolutional Neural Networks(CNN) metal surface defect detection deep learning,computer vision image classification learnable memory gradient clipping label smoothing t-SNE visualization

来源：评论

学校读者我要写书评

暂无评论

Immersive video interaction system: a survey

引用

Visual Intelligence 2025年第1期3卷 1-14页

作者： Fang, Xiaohan Chen, Peilin Wang, Meng Wang, Shiqi Department of Computer Science City University of Hong Kong Hong Kong School of Data Science Lingnan University Hong Kong

As communication technologies undergo rapid evolution, human interaction technologies have become increasingly efficient and accessible. Videoconferencing, for example, facilitates real-time, face-to-face communication worldwide, providing unprecedented convenience. Nevertheless, traditional two-dimensional (2D) videoconferencing systems frequently fall short of delivering a fully immersive experience, as they lack the ability to convey physical presence, depth perception, and natural interaction—key elements that are of particular significance in replicating the subtleties inherent in in-person communication. This disconnection leaves users yearning for the rich, multi-sensory experiences that real-life interactions can offer. In response, significant research efforts have been dedicated to the development of immersive video interaction systems (IVISs). This paper introduces the concept of IVISs and reviews a spectrum of systems advanced by researchers and industry innovators, each of whom contributes unique insights into the evolution of this field. A comparative analysis of the characteristics of current IVISs is provided, offering insights across multiple dimensions. This survey concludes with a discussion of potential future research directions and the challenges that remain in enhancing the IVIS technology. Through a comprehensive analysis, this work aims to foster further exploration and innovation in immersive communication technologies. © The Author(s) 2025.

关键词： 3D vision Immersive video interaction systems Survey Video communication

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：