检索结果-内蒙古大学图书馆

27th International Conference on Knowledge Based and Intelligent Information and engineering Sytems, KES 2023

作者： Ali, Maria Liaquat, Muhammad Daniyal Atta, Muhammad Nouman Khan, Abdullah Lashari, Saima Anwar Ramli, Dzati Athiar Institute of Computer Science and Information Technology The University of Agriculture Peshawar Pakistan College of Computing and Informatics Saudi Electronic University Riyadh Saudi Arabia School of Electrical and Electronic Engineering University Sains Malaysia USM Engineering Campus Nibong Tebal Pulau Pinang14300 Malaysia

The ANN is a commonly used network for pattern recognition, and has been trained for various tasks such as prediction, classification, and engineering. However, this model faces challenges such as local minima and slow convergence, which have been addressed through different strategies such as combining the artificial neural network (ANN) with optimised models like the cuckoo search (CS) algorithm. However, for large datasets, the hybrid ANN-based CS algorithm can lead to overfitting. To overcome this issue, the authors propose a new algorithm called Principal Component Analysis with Cuckoo Search Neural Network (PCACSNN). The performance of this algorithm is compared to other commonly used algorithms such as ANN, backpropagation neural network (BPNN), and cuckoo search backpropagation (CSBP), using the Mean Square Error (MSE) and accuracy on classification problems. The simulations were performed on the Student Performance dataset taken from the UCIMLR. The results show that the proposed model performs better than the other models, achieving high accuracy and low MSE for both mathematics and Portuguese student datasets. For the mathematics students, the suggested model attained an accuracy of (99.32%) with MSE of 2.77E-07 for 70% training data and an accuracy of 98.52% with MSE of 2.50E-04 for 30% training data. Similarly, for the Portuguese student dataset, the proposed model obtained (99.38%) accuracy with MSE of 1.09E-08 for 70% training data and 98.72% accuracy with MSE of 1.01E-04 for 30% training data. © 2023 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (https://***/licenses/by-nc-nd/4.0)

关键词： Accuracy Artificial Neural Network (ANN) Back Propagation Cuckoo Search (CS) Algorithm Local Minima Mathematics Mean Square Error (MSE) Portuguese Slow Convergence

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Approach for Enhancing Motor Imagery EEG Classification in BCI’s 12th

A Comprehensive Approach for Enhancing Motor Imagery EEG Cl...

引用

12th International Conference on Health Information Science, HIS 2023

作者： Sadiq, Muhammad Tariq Siuly, Siuly Li, Yan Wen, Paul Advanced Engineering Center School of Architecture Technology and Engineering University of Brighton BrightonBN2 4AT United Kingdom Institute for Sustainable Industries and Liveable Cities Victoria University MelbourneVIC3011 Australia School of Mathematics Physics and Computing University of Southern Queensland Toowoomba Campus Toowoomba4350 Australia School of Engineering University of Southern Queensland Toowoomba Campus Toowoomba4350 Australia

ISBN: (纸本)9789819971077

Electroencephalography (EEG) based on motor imagery has become a potential modality for brain-computer interface (BCI) systems, allowing users to control external devices by imagining doing particular motor activities. The existence of noise and the complexity of the brain signals, however, make it difficult to classify motor imagery EEG signals. This work suggests a systematic method for classifying motor imagery in the EEG. A technique known as Multiscale Principal Component Analysis (MSPCA) is used for efficient noise removal to improve the signal quality. A unique signal decomposition technique is proposed for modes extraction, allowing the separation of various oscillatory components related to motor imagery tasks. This breakdown makes it easier to isolate important temporal and spectral properties that distinguish various classes of motor imagery. These characteristics capture the dynamism and discriminative patterns present in motor imagery tasks. The motor imagery EEG signals are then classified using various machine learning and deep learning-based models based on the retrieved features. The findings of the classification show how well the suggested strategy works in generating precise and trustworthy classification success for various motor imaging tasks. The proposed method has enormous potential for BCI applications, allowing people with motor limitations to operate extrasensory equipment via brain signals. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2023.

关键词： Brain computer interface

来源：评论

学校读者我要写书评

暂无评论

Modality-Specific Interactive Attack for Vision-Language Pre-Training Models

引用

IEEE Transactions on Information Forensics and Security 2025年 20卷 5663-5677页

作者： Zhang, Haiqi Tang, Hao Sun, Yanpeng He, Shengfeng Li, Zechao Nanjing University of Science and Technology School of Computer Science and Engineering Nanjing210094 China The Hong Kong Polytechnic University Centre for Smart Health Hong Kong Singapore Management University School of Computing and Information Systems Singapore

Recent advances have heightened the interest in the adversarial transferability of Vision-Language Pre-training (VLP) models. However, most existing strategies constrained by two persistent limitations: suboptimal utilization of crossmodal interactive information, and inherent discrepancies across hierarchical textual representation. To address these challenges, we propose the Modality-Specific Interactive Attack (MSIAttack), a novel approach that integrates semantic-level image perturbations with embedding-level text perturbations, all while maintaining minimal inter-modal constraints. In our image attack methodology, we introduce Multi-modal Integrated Gradients (MIG) to guide perturbations toward the core semantics of images, enriched by their associated deeply text information. This technique enhances transferability by capturing consistent features across various models, thereby effectively misleading similar-model perception areas. Additionally, we employ a momentum iteration strategy in conjunction with MIG, which amalgamates current and historical gradients to expedite the perturbation updates. For text attacks, we streamline the perturbation process by operating exclusively at the embedding level. This reduces semantic gaps across hierarchical structures and significantly enhances the generalizability of adversarial text. Moreover, we delve deeper into how semantic perturbations with varying degrees of similarity affect the overall attack effectiveness. Our experimental results on image-text retrieval tasks using the multi-modal datasets Flickr30K and MSCOCO underscore the efficacy of MSI-Attack. Our method achieves superior performance, setting a new state-of-the-art benchmark, all without the need for additional mechanisms. 2005-2012 IEEE.

关键词： Photointerpretation

来源：评论

学校读者我要写书评

暂无评论

Frequency-aware Adaptive Filtering Network for Few-Shot Medical Image Segmentation

Frequency-aware Adaptive Filtering Network for Few-Shot Medi...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Ziming Cheng Shidong Wang Tong Xin Haofeng Zhang School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China School of Engineering Newcastle University Newcastle upon Tyne UK School of Computing Newcastle University Newcastle upon Tyne UK

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Manual annotation of massive data in the biomedical field necessitates huge costs, expertise, and privacy considerations. However, Few-Shot Medical Image Segmentation (FSMIS) offers the possibility of learning a segmentation model with excellent performance from limited medical data. In this paper, we propose a Frequency-aware Adaptive Filtering Network (FAF-Net) for FSMIS, which is the first to calibrate the correlations between support prototype and query features from a frequency perspective, addressing the problems of FSMIS. The FAF-Net mines the commonalities between the support prototype and query features to reduce the intra-class differences through an Intra-class Commonality Miner (ICM), and introduces an Adaptive Fourier Filter (AFF) to adaptively filter the spectrum of the attention map, thus balancing the foreground and background classes. Additionally, an Adaptive Threshold Learner (ATL) is incorporated to learn an adaptive threshold for each spatial location of the predicted mask from the support features, overcoming the limitations of single thresholding. Extensive experiments on four generic medical datasets showcase that our model significantly outperforms SoTA methods (exceeding SoTA by 2.13% on average).

关键词： Image segmentation Adaptation models Adaptive systems Filtering Prototypes Adaptive filters Medical services Manuals Interference Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

Robust Stabilization of a Knee Exoskeleton Robot using an LMI-based Composite Controller 10

Robust Stabilization of a Knee Exoskeleton Robot using an LM...

引用

10th Indian Control Conference, ICC 2024

作者： Jenhani, Sahar Gritli, Hassène Narayan, Jyotindra National Engineering School of Tunis University of Tunis El Manar Le Belvédère Tunis1002 Tunisia The Higher Institute of Information and Communication Technologies University of Carthage Borj Cedria Tunis1164 Tunisia The RISC Lab The Department of Mechanical Engineering Thapar Institute of Engineering and Technology Punjab Patiala147004 India The Department of Computing Imperial College London United Kingdom

ISBN: (纸本)9798331517212

Rehabilitation exoskeleton robots are vital for restoring lower limb functionality in individuals with locomotor disorders. Extensive research has focused on optimizing the control of these robotic systems and make them more stable. However, there is still a considerable gap in developing robust controllers. This work introduces a robust control approach tailored for a one-degree-of-freedom (1-DoF) knee rehabilitation exoskeleton robot. Emphasizing position control, our method addresses challenges such as parameter uncertainties, solid and viscous frictions, external disturbances, and motion constraints. To effectively manage these issues, we propose a composite controller that integrates a linear state-feedback controller and a nonlinear control law. By employing a quadratic Lyapunov function, we derive the expression of the nonlinear controller and establish the LMI conditions required for calculating the matrix gain of the composite controller using two different design methods. To confirm the developed LMI conditions and demonstrate the proposed control method’s ability to ensure robust position control of the knee exoskeleton robotic system, simulation results are finally provided. © 2024 IEEE.

关键词： Exoskeleton (Robotics)

来源：评论

学校读者我要写书评

暂无评论

An Ensembled Convolutional Recurrent Neural Network approach for Automated Classroom Sound Classification

An Ensembled Convolutional Recurrent Neural Network approach...

引用

Artificial Intelligence (CAI), IEEE Conference on

作者： Rashed Iqbal Christian Ritz Jack Yang Sarah Howard Abigail Copiaco School of Electrical Computer and Telecommunications Engineering University of Wollongong NSW Australia School of Computing and Information Technology University of Wollongong NSW Australia School of Education University of Wollongong NSW Australia College of Engineering and Information Technology University of Dubai Dubai UAE

ISBN: (数字)9798350354096

ISBN: (纸本)9798350354102

The paper explores automated classification techniques for classroom sounds to capture diverse learning and teaching activities' sequences. Manual labeling of all recordings, especially for long durations like multiple lessons, poses practical challenges. This study investigates an automated approach employing scalogram acoustic features as input into the ensembled Convolutional Neural Network (CNN) and Bidirectional Gated Recurrent Unit (BiGRU) hybridized with Extreme Gradient Boost (XGBoost) classifier for automatic classification of classroom sounds. The research involves analyzing real classroom recordings to identify distinct sound segments encompassing teacher's voice, student voices, babble noise, classroom noise, and silence. A sound event classifier utilizing scalogram features in an XGBoost framework is proposed. Comparative evaluations with various other machine learning and neural network methodologies demonstrate that the proposed hybrid model achieves the most accurate classification performance of 95.38%.

关键词： Training Accuracy Recurrent neural networks Noise Feature extraction Real-time systems Recording

来源：评论

学校读者我要写书评

暂无评论

Computer Aided Diagnosis Multi-model System using Late Fuison and Ensemble Learning

Computer Aided Diagnosis Multi-model System using Late Fuiso...

引用

Pervasive Computational Technologies (ICPCT), International Conference on

作者： M.Kani Priya Gunabhiram Aruru Nikhil Vanam M. Suganiya M. Salomi Department Of Computational Intelligence School of Computing Faculty of Engineering and Technology SRM Institute of Science and Technology Chennai Tamil Nadu Department of Computing Technologies SRM Institute of Science and Technology Chennai Tamil Nadu Department of Computational Intelligence SRM Institute of Science and Technology Chennai Tamil Nadu

ISBN: (数字)9798331508685

ISBN: (纸本)9798331519476

Lung Cancer and brain tumors are the well-known causes of cancer deaths universal. Therefore, appropriate and accurate diagnosis is an important issue that affects better and more reliable treatment and the patient's chance of survival. Present diagnostic strategies are mostly based on a single piece of information. This often leads to missing necessary information, which can lead to Misidentification of condition or delay in timely treatment. This study presents a novel Computer-Aided-Diagnosis system designed to enhance the detection of lung cancer and brain tumors by integrating multimodal data, including medical images (CT and MRI scans) and clinical information. The proposed approach employs late fusion and ensemble learning techniques, utilizing CNN for processing CT images, VGG19 for analyzing MRI scans, and Random Forest classifiers for evaluating clinical data. By separately training these models, the system capitalizes on the distinct characteristics of each data modality, overcoming the limitations of traditional CAD systems that typically rely on a single data source. This comprehensive analysis not only improves diagnostic accuracy but also provides reliable predictions, ultimately facilitating better clinical decision-making for lung cancer and brain tumor detection.

关键词： Solid modeling Computed tomography Magnetic resonance imaging Decision making Lung cancer Brain tumors Brain modeling Data models Ensemble learning Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

A Review on Environmental Sustainability Using Machine Learning Applications

A Review on Environmental Sustainability Using Machine Learn...

引用

IoT Based Control Networks and Intelligent Systems (ICICNIS), International Conference on

作者： E. Nirmala Manish Yadav Palanichamy Naveen M. Maragatharajan M. Suresh Pranjal Bhargava School of Computing Science and Engineering VIT Bhopal University Kothri Kalan Madhya Pradesh India School of Computing Science engineering and Artificial Intelligence VIT Bhopal University Kothri Kalan Madhya Pradesh India Department of Electrical and Electronics Engineering KPR Institute of Engineering and Technology Coimbatore Tamil Nadu India

ISBN: (数字)9798331518097

ISBN: (纸本)9798331518103

Environmental sustainability reduces the destruction of natural resources in the hands of mother earth for next generation. Due to the development of cities and its social and economic factors leads the major role of any such destruction. It affects huge volume of biological system in terms of environmental pollution, change in climate and respective population growth. Henceforth, the general population is severely affected with their quality of life in the present scenario. This research study discusses about various resources that are affected severely due to the environmental factors have stated with the proven evident. Along with this various prediction technology using machine learning procedures are discussed in detail to prevent any such destruction by improving the present style of work. The prediction of any such destruction exploiting resources like land, water, mineral and planetaries creates its impact in the form of climatic changes, as a result of this we are facing drought, earthquakes and landslide. Apart from preventing techniques over plantation of greeneries, it is necessary to implement techniques towards efficient use of resources Monitoring is essential features. All these things are now essentially managed with the help of computer aided technology. Further the effective usage of environmental factors results into safe future for the next generation. This can be achieved by using AI with SUV to increase the prediction accuracy. Further this article is directed towards future direction to prevent and use the natural resources is discussed for the benefit of population around the world.

关键词： Natural resources Pollution Reviews Green products Urban areas Plantations Machine learning Terrain factors Next generation networking Water resources

来源：评论

学校读者我要写书评

暂无评论

Improving Breast Cancer Diagnosis: Insights From Machine Learning Models

Improving Breast Cancer Diagnosis: Insights From Machine Lea...

引用

Communication, Computer Sciences and engineering (IC3SE), International Conference on

作者： Naween Kumar Yajnaseni Dash Sasmita Padhy Sachikanta Dash Preetam Suman School of Computer Science Engineering and Technology Bennett University Uttar Pradesh India School of Computing Science and Engineering VIT Bhopal University Bhopal MP Computer Science and Engineering GIET University Gunupur Odisha

ISBN: (数字)9798350366846

ISBN: (纸本)9798350366853

Data mining is a technique used in the healthcare industry to analyze vast amounts of information for early illness diagnosis and prognosis. When it comes to its early prediction stages of breast cancer, many different classification algorithms play an essential role. This study proposed a pragmatic method to evaluate the effectiveness of four different classification algorithms, namely Decision Tree, Naïve Bayes, K-nearest neighbor and Support Vector Machines, in accordance to forecast breast cancer. These algorithms were examined for their ability to diagnose and predict the early stages of illness. The classifier is strengthened by using exploratory data analysis and the boosting method in this study. Additionally, the problem of imbalanced classes is resolved during the classification phase. In this particular instance, cross-validation techniques were utilized to investigate the behavior of each classifier concerning the accuracy, true positive rate, and false positive rate. This study attempted for improvement of the accuracy level in the prediction of breast cancer employing through the aforementioned machine-learning methods.

关键词： Support vector machines Accuracy Nearest neighbor methods Prediction algorithms Breast cancer Classification algorithms Naive Bayes methods

来源：评论

学校读者我要写书评

暂无评论

MEIM:A Multi-Source Software Knowledge Entity Extraction Integration Model

引用

Computers, Materials & Continua 2021年第1期66卷 1027-1042页

作者： Wuqian Lv Zhifang Liao Shengzong Liu Yan Zhang School of Computer Science and Engineering Central South UniversityChangsha410075China School of Information Technology and Management Hunan University of Finance and EconomicsChangsha410205China School of Computing Engineering and Built EnvironmentGlasgow Caledonian UniversityGlasgowG40BAUK

Entity recognition and extraction are the foundations of knowledge graph *** data in the field of software engineering come from different platforms and communities,and have different *** paper divides multi-source software knowledge entities into unstructured data,semi-structured data and code *** these different types of data,Bi-directional Long Short-Term Memory(Bi-LSTM)with Conditional Random Field(CRF),template matching,and abstract syntax tree are used and integrated into a multi-source software knowledge entity extraction integration model(MEIM)to extract software *** model can be updated continuously based on user’s feedbacks to improve the *** deal with the shortage of entity annotation datasets,keyword extraction methods based on Term Frequency–Inverse Document Frequency(TF-IDF),TextRank,and K-Means are applied to annotate *** proposed MEIM model is applied to the Spring Boot framework,which demonstrates good *** extracted entities are used to construct a knowledge graph,which is applied to association retrieval and association visualization.

关键词： Entity extraction software knowledge graph software data

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：