检索结果-内蒙古大学图书馆

AFuNet: an attention-based fusion network to classify texts in a resource-constrained language

Neural Computing and Applications 2025年第9期37卷 6725-6748页

作者： Hossain, Md. Rajib Hoque, Mohammed Moshiul Dewan, M. Ali Akber Hoque, Enamul Siddique, Nazmul Department of Computer Science & Engineering Chittagong University of Engineering & Technology Chittagong4349 Bangladesh School of Computing and Information Systems Faculty of Science and Technology Athabasca University AthabascaABT9S 3A3 Canada School of Information Technology York University TorontoONM3J 1P3 Canada School of Computing Engineering and Intelligent Systems Ulster University Coleraine United Kingdom

In the era of widespread Internet use and extensive social media interaction, the digital realm is accumulating vast amounts of unstructured text data. This unstructured data often contain undesirable information, necessitating time-consuming manual classification efforts. An intelligent text classification system capable of automatically categorizing digitized texts based on semantic meaning is crucial. However, this task is particularly challenging for low-resource languages like Bengali due to a shortage of annotated corpora, issues with out-of-vocabulary words, lack of domain-specific hyperparameter tuning, limited ability to extract generalized text features, and class imbalances within the corpus. AFuNet: an attention-based fusion network to classify texts in a resource-constrained language. AFuNet undergoes a comprehensive four-phase experimental process, including baseline model evaluation and hyperparameter tuning, late fusion and model selection, attention-based early fusion and model identification, and an ablation study with impact analysis. Fine-tuned based on five Bengali text classification corpora, AFuNet achieves impressive accuracies: 96.60 ± 0.2 (BTCC11), 85.37 ± 0.2 (OSBC), 97.35 ± 0.2 (BARD), 93.74 ± 0.2 (IndicNLP), and 96.51 ± 0.2 (ProthomAlo). In comparison with previous state-of-the-art models on these corpora, AFuNet demonstrates significant accuracy improvements ranging from 0.54% to 4.49%, showcasing its effectiveness in advancing text classification capabilities for the Bengali language. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Autism Spectrum Disorder Detection from EEG Through Hjorth Parameters and Classification Using Neural Network 1st

Autism Spectrum Disorder Detection from EEG Through Hjorth P...

引用

1st International Conference on Machine Intelligence and Emerging Technologies, MIET 2022

作者： Peya, Zahrul Jannat Zaman, Bipasha Akhand, M.A.H. Siddique, Nazmul Department of Computer Science and Engineering Khulna University of Engineering and Technology Khulna9203 Bangladesh School of Computing Engineering and Intelligent Systems Ulster University Northern Ireland Londonderry United Kingdom

ISBN: (纸本)9783031346217

Autism spectrum disorders (ASD) are a collection of neurodevelopmental disorders. Even though ASD has no cure, early detection and intervention can help developing language, behavior, and communication skills. Research shows that ASD can be diagnosed from brain signals, particularly electroencephalography (EEG) where the brain activity is recorded over time as an EEG signal from humans’ scalp and then used to study neuropsychiatric disorders. This study investigates the classification performance of the Neural Networks (NN) model with Hjorth features namely activity, mobility, and complexity extracted from EEG signals through selected channels using the XGBoost algorithm. The classification accuracy is 80% using all 19 channels of EEG data whereas the accuracy of the model using activity, mobility and complexity reached 100% with selected channels. Hjorth parameter-based NN model with channel selection seems to be promising that improves the computation complexity significantly. © 2023, ICST Institute for computer Sciences, Social Informatics and Telecommunications engineering.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Tolerant Tracking Control Protocol for PMSM Based on Policy Iteration Algorithm and Fault Compensation 16th

Tolerant Tracking Control Protocol for PMSM Based on Polic...

引用

16th International Conference on Social Robotics, ICSR + InnoBiz 2024

作者： Yan, Shuya Li, Xiaocong Qian, Huaming Ma, Jun Al Mamun, Abdullah College of Intelligent Systems Science and Engineering Harbin Engineering University Harbin150001 China Department of Electrical and Computer Engineering National University of Singapore Singapore117583 Singapore Guangzhou China Information Science and Technology Eastern Institute of Technology Ningbo China

ISBN: (纸本)9789819611508

In robotics applications, ensuring reliable performance in the presence of actuator faults is essential for maintaining system safety and reliability. This paper presents a tolerant tracking control method for permanent magnet synchronous motors (PMSMs) based on adaptive dynamic programming and fault compensation. The method simultaneously considers tracking accuracy and energy consumption through a policy iteration algorithm. In the optimality analysis of the algorithm, more relaxed conditions are provided to demonstrate that the performance function can converge to a near-optimal value within a finite number of iterations. In practical implementation, an actor-critic network is used to approximate the performance function and control protocol, alongside a fault detection mechanism based on an expanded time horizon, which achieves fault detection from arbitrary initial values. The effectiveness of the proposed algorithm is verified using a high-fidelity PMSM model in Simulink. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Permanent magnets

来源：评论

学校读者我要写书评

暂无评论

Assessing adversarial replay and deep learning-driven attacks on specific emitter identification-based security approaches

引用

Discover Internet of Things 2024年第1期4卷 25页

作者： Tyler, Joshua H. Fadul, Mohamed K. M. Hilling, Matthew R. Reising, Donald R. Loveless, T. Daniel Electrical Engineering Department The University of Tennessee at Chattanooga 735 Vine Street ChattanoogaTN37403 United States Department of Intelligent Systems Engineering Indiana University 700 N. Woodlawn Avenue BloomingtonIN47408 United States Department of Computer Science Tennessee Technological University 1 Williams L. Jones Drive CookevilleTN38505 United States

Specific Emitter Identification (SEI) has been put forward as an Internet of Things (IoT) Physical Layer Security (PLS) approach for its abilities to detect, characterize, and identify wireless emitters by exploiting distinct, inherent, and unintentional features in their transmitted signals. Since its introduction, a significant amount of work has been conducted;however, most assume the emitters are passive and their identifying signal features are immutable and challenging to mimic. This suggests the emitters are reluctant and incapable of developing and implementing effective SEI countermeasures;however, Deep Learning (DL) has been shown capable of learning emitter-specific features directly from their raw in-phase and quadrature signal samples, while Software-Defined Radios (SDRs) are capable of manipulating these signal samples. Based on these capabilities, it is fair to question the ease at which an emitter can effectively mimic the SEI features of another or manipulate its own to hinder or defeat SEI. This work considers SEI mimicry using three signal features mimicking countermeasures;"off-the-self" DL;two SDRs of different sizes, weights, power, and cost (SWaP-C);handcrafted and DL-based SEI processes, and assessment of an SEI mimicry countermeasure in a "coffee shop" deployment. Our results show "off-the-shelf" DL algorithms, and SDR enables SEI mimicry;however, adversary success is hindered by: (i) the use of decoy emitter preambles, (ii) the use of a denoising autoencoder and (iii) SDR SWaP-C constraints. © The Author(s) 2024.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Robust Counting in Overcrowded Scenes Using Batch-Free Normalized Deep ConvNet

引用

computer systems Science & engineering 2023年第9期46卷 2741-2754页

作者： Sana Zahir Rafi Ullah Khan Mohib Ullah Muhammad Ishaq Naqqash Dilshad Amin Ullah Mi Young Lee Institute of Computer Sciences and Information Technology(ICS/IT) The University of AgriculturePeshawar25130Khyber PakhtunkhwaPakistan Department of Convergence Engineering for Intelligent Drone Sejong UniversitySeoul05006Korea Collaborative Robotics and Intelligent Systems(CoRIS)Institute Oregon State UniversityORUSA Department of Software Sejong UniversitySeoul05006Korea

The analysis of overcrowded areas is essential for flow monitoring,assembly control,and *** counting’s primary goal is to calculate the population in a given region,which requires real-time analysis of congested scenes for prompt reactionary *** crowd is always unexpected,and the benchmarked available datasets have a lot of variation,which limits the trained models’performance on unseen test *** this paper,we proposed an end-to-end deep neural network that takes an input image and generates a density map of a crowd *** proposed model consists of encoder and decoder networks comprising batch-free normalization layers known as evolving normalization(EvoNorm).This allows our network to be generalized for unseen data because EvoNorm is not using statistics from the training *** decoder network uses dilated 2D convolutional layers to provide large receptive fields and fewer parameters,which enables real-time processing and solves the density drift problem due to its large receptive *** benchmark datasets are used in this study to assess the proposed model,resulting in the conclusion that it outperforms conventional models.

关键词： Artificial intelligence deep learning crowd counting scene understanding

来源：评论

学校读者我要写书评

暂无评论

Automatic speaker identification system based on MLP network and deep learning in the presence of severe interference

引用

Multimedia Tools and Applications 2025年 1-42页

作者： Shafik, Amira Sedik, Ahmed El-Shafai, Walid Khalaf, Ashraf A. M. El-Rabaie, El-Sayed M. El-Samie, Fathi E. Abd Department of Electronics and Electrical Communications Engineering Faculty of Electronic Engineering Menoufia University Menouf32952 Egypt Department of Electrical Engineering Faculty of Engineering Minia University Minia61519 Egypt Smart Systems Engineering Laboratory College of Engineering Prince Sultan University Riyadh11586 Saudi Arabia Department of the Robotics and Intelligent Machines Faculty of Artificial Intelligence Kafr Elsheikh University Kafr El‑Shaikh Egypt Computer Science Department Prince Sultan University Riyadh11586 Saudi Arabia Department of Information Technology College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University P.O. Box 84428 Riyadh11671 Saudi Arabia

Automatic Speaker Identification (ASI) is so crucial for security. Current ASI systems perform well in quiet and clean surroundings. However, in noisy situations, the robustness of an ASI system against additive noise and interference is a crucial factor. An investigation of the impact of interference on ASI system performance is presented in this paper, which introduces algorithms for achieving high ASI system performance. The objective is to resist the interference of various forms. This paper presents two models for the ASI task in the presence of interference. The first one depends on Normalized Pitch Frequency (NPF) and Mel-Frequency Cepstral Coefficients (MFCCs) as extracted features and Multi-Layer Perceptron (MLP) as a classifier. In this model, we investigate the utilization of a Discrete Transform (DT), such as Discrete Wavelet Transform (DWT), Discrete Cosine Transform (DCT) and Discrete Sine Transform (DST), to increase the robustness of extracted features against different types of degradation through exploiting the sub-band decomposition characteristics of DWT and the energy compaction property of DCT and DST. This is achieved by extracting features directly from contaminated speech signals in addition to features extracted from discrete transformed signals to create hybrid feature vectors. The enhancement techniques, such as Spectral Subtraction (SS), Winer Filter, and adaptive Wiener filter, are used in a preprocessing stage to eliminate the effect of the interference on the ASI system. In the second model, we investigate the utilization of Deep Learning (DL) based on a Convolutional Neural Network (CNN) with speech signal spectrograms and their Radon transforms to increase the robustness of the ASI system against interference effects. One of this paper goals is to introduce a comparison between the two models and build a more robust ASI system against severe interference. The experimental results indicate that the two proposed models lead to satisfa

关键词： Additive noise

来源：评论

学校读者我要写书评

暂无评论

Survey on Cryptoprocessors Advances and Technological Trends 3rd

Survey on Cryptoprocessors Advances and Technological Tren...

引用

3rd International Conference on Innovations in Computing Research, ICR 2024

作者： Kakoulli, Elena Zacharioudakis, Eleftherios Intelligent Systems Laboratory Department of Computer Science Neapolis University Pafos Paphos Cyprus Electrical Engineering and Computer Engineering and Informatics Cyprus University of Technology Limassol Cyprus National Technical University of Ukraine Igor Sikorsky Kyiv Polytechnic Institute Kyiv Ukraine

ISBN: (纸本)9783031655210

Cryptoprocessors play a pivotal role in enhancing the security of modern computing systems by accelerating cryptographic operations and fortifying data protection. This survey delves into the world of cryptoprocessors, encompassing their historical development, architectural features, and various types based on their applications. The paper explores the crucial security considerations surrounding cryptoprocessors, covering both physical and logical aspects, as well as potential threats and countermeasures. Furthermore, the survey navigates through the latest technological trends and advancements in cryptoprocessor design. This includes discussions on post-quantum cryptography, secure enclaves, and mitigating side-channel attacks, all of which are shaping the future of cryptoprocessors. Real-world use cases and applications in domains such as secure communications, the Internet of Things (IoT), and data centers are presented, showcasing the practical significance of cryptoprocessors. However, the paper also highlights the persistent challenges faced by cryptoprocessor designers and provides insights into future research directions aimed at addressing emerging security and performance issues. As the digital landscape continues to evolve, the role of cryptoprocessors becomes increasingly vital in safeguarding sensitive information and fortifying the foundations of cybersecurity. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Facial Expression Recognition Model Depending on Optimized Support Vector Machine

引用

computers, Materials & Continua 2023年第7期76卷 499-515页

作者： Amel Ali Alhussan Fatma M.Talaat El-Sayed M.El-kenawy Abdelaziz A.Abdelhamid Abdelhameed Ibrahim Doaa Sami Khafaga Mona Alnaggar Department of Computer Sciences College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Machine Learning&Information Retrieval Department Faculty of Artificial IntelligenceKafrelsheikh UniversityKafrelsheikh33516Egypt Department of Communications and Electronics Delta Higher Institute of Engineering and TechnologyMansoura35111Egypt Department of Computer Science College of Computing and Information TechnologyShaqra University11961Saudi Arabia Department of Computer Science Faculty of Computer and Information SciencesAin Shams UniversityCairo11566Egypt Computer Engineering and Control Systems Department Faculty of EngineeringMansoura UniversityMansoura35516Egypt Robotics and Intelligent Machines Department Faculty of Artificial IntelligenceKafrelsheikh UniversityKafrelsheikh33516Egypt

In computer vision,emotion recognition using facial expression images is considered an important research *** learning advances in recent years have aided in attaining improved results in this *** to recent studies,multiple facial expressions may be included in facial photographs representing a particular type of *** is feasible and useful to convert face photos into collections of visual words and carry out global expression *** main contribution of this paper is to propose a facial expression recognitionmodel(FERM)depending on an optimized Support Vector Machine(SVM).To test the performance of the proposed model(FERM),AffectNet is *** uses 1250 emotion-related keywords in six different languages to search three major search engines and get over 1,000,000 facial photos *** FERM is composed of three main phases:(i)the Data preparation phase,(ii)Applying grid search for optimization,and(iii)the categorization *** discriminant analysis(LDA)is used to categorize the data into eight labels(neutral,happy,sad,surprised,fear,disgust,angry,and contempt).Due to using LDA,the performance of categorization via SVM has been obviously *** search is used to find the optimal values for hyperparameters of SVM(C and gamma).The proposed optimized SVM algorithm has achieved an accuracy of 99%and a 98%F1 score.

关键词： Facial expression recognition machine learning linear dis-criminant analysis(LDA) support vector machine(SVM) grid search

来源：评论

学校读者我要写书评

暂无评论

From Simulation to Reality with Random Noise

From Simulation to Reality with Random Noise

引用

AIAA Science and Technology Forum and Exposition, AIAA SciTech Forum 2025

作者： Luo, Steven Lipkis, Rory López-Francos, Ignacio Vlastos, Pavlo Agogino, Adrian Department of Electrical Engineering and Computer Sciences University of California BerkeleyCA94720 United States Intelligent Systems Division NASA Ames Research Center Moffett FieldCA94035 United States

ISBN: (数字)9781624107238

ISBN: (纸本)9781624107238

The challenging environment of autonomous vehicle (AV) navigation necessitates certain functions be performed by deep neural networks. Optimizing these models involves collecting vast quantities of domain-specific training data and ensuring that the dataset is representative of expected conditions. High-fidelity simulation plays a vital role in making this process feasible, allowing a wide range of scenarios to be explored at relatively low cost. However, learning from simulation introduces subtle biases into models, which can degrade real-world performance in unpredictable ways. This effect can be mitigated with learning schemes specialized to bridge distributional shifts (transfer learning). Given the complex nature of these methods, the underlying models, and their environments, meaningfully evaluating performance is not straightforward. Many unrelated factors can effect an improvement in generalization accuracy, but a full ablation analysis is often difficult to perform. To tease out signal from noise, it is necessary to understand how transfer learning performance is affected by noise itself. The goals of this paper are (i) to establish a domain randomization baseline for a simple classification transfer learning task and (ii) to validate the RRAV testbed as a platform for further research in sim-to-real learning. We generate imagery from a simulation of NASA Ames Research Center and train a small convolutional neural network to classify camera position of an ego vehicle relative to a center line. Further models are trained with different types of noise progressively added to the data. In our experiments, we find that naive domain randomization raises sim-to-real accuracy from 64% to 79%, while training directly on real data yields an 89% accuracy ceiling. These results suggest that the isolated mechanism of domain randomization can significantly improve generalization. © 2025, American Institute of Aeronautics and Astronautics Inc, AIAA. All rights reserved.

关键词： NASA

来源：评论

学校读者我要写书评

暂无评论

Multi-modal classification of breast cancer lesions in Digital Mammography and contrast enhanced spectral mammography images

引用

computers in Biology and Medicine 2024年 183卷 109266-109266页

作者： Bouzarjomehri, Narjes Barzegar, Mohammad Rostami, Habib Keshavarz, Ahmad Asghari, Ahmad Navid Azad, Saeed Talatian Department of Computer Engineering Faculty of Intelligent Systems Engineering and Data Science Persian Gulf University Bushehr*** Iran Department of Electrical Engineering Faculty of Intelligent Systems Engineering and Data Science Persian Gulf University Bushehr*** Iran

Breast cancer ranks as the second most prevalent cancer in women, recognized as one of the most dangerous types of cancer, and is on the rise globally. Regular screenings are essential for early-stage treatment. Digital mammography (DM) is the most recognized and widely used technique for breast cancer screening. Contrast-Enhanced Spectral Mammography (CESM or CM) is used in conjunction with DM to detect and identify hidden abnormalities, particularly in dense breast tissue where DM alone might not be as effective. In this work, we explore the effectiveness of each modality (CM, DM, or both) in detecting breast cancer lesions using deep learning methods. We introduce an architecture for detecting and classifying breast cancer lesions in DM and CM images in Craniocaudal (CC) and Mediolateral Oblique (MLO) views. The proposed architecture (JointNet) consists of a convolution module for extracting local features, a transformer module for extracting long-range features, and a feature fusion layer to fuse the local features, global features, and global features weighted based on the local ones. This significantly enhances the accuracy of classifying DM and CM images into normal or abnormal categories and lesion classification into benign or malignant. Using our architecture as a backbone, three lesion classification pipelines are introduced that utilize attention mechanisms focused on lesion shape, texture, and overall breast texture, examining the critical features for effective lesion classification. The results demonstrate that our proposed methods outperform their components in classifying images as normal or abnormal and mitigate the limitations of independently using the transformer module or the convolution module. An ensemble model is also introduced to explore the effect of each modality and each view to increase our baseline architecture's accuracy. The results demonstrate superior performance compared with other similar works. The best performance on DM images

关键词： Image enhancement

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：