检索结果-内蒙古大学图书馆

IAENG International Journal of computer science 2022年第1期49卷 260-269页

作者： Li, M.Y. Zhao, J. Master’s Student of School of Computer Science and Software Engineering University of Science and Technology Liaoning Anshan114051 China School of Computer Science and Software Engineering University of Science and Technology Liaoning Anshan114051 China

Accurately detecting the keypoints of small persons in an image using bottom-up multi-person pose estimation algorithms is exceptionally difficult owing to scale variation challenges. HigherHRNet initially solved the challenge of multi-player scale change pose estimation. However, because it uses repeated cross-scale fusion, owing to inherent defects in channel reduction, semantic information is lost. Furthermore, the aliasing effects produced by the miscellaneous feature maps formed after cross-scale fusion have a significant impact on the detection accuracy of small persons. In this paper, we propose a novel bottom-up human pose estimation algorithm based on HigherHRNet, called Channel-Enhanced HigherHRNet (CE-HigherHRNet). CE-HigherHRNet comprises three main components: a multiscale sub_pixel skip fusion module, a lightweight attention mechanism (with channel attention enhanced and spatial attention modules), and a high-resolution feature pyramid with an added Dupsampling module. The lightweight attention mechanism optimizes the feature map after each fusion. Deconvolution is replaced with Dupsampling, which strengthens the network’s scale awareness and makes it more sensitive to robust scale changes. The average precision (AP) of CE-HigherHRNet on the COCO test-dev dataset was 71.9% (an improvement of 1.4% compared with HigherHRNet). Furthermore, the average detection accuracy of small persons was 68.1% AP (an improvement of 1.5% AP). These results verify that the proposed CE-HigherHRNet is more robust in processing scale changes and has a stronger ability to handle crowded environments. Thus, it is more accurate in positioning small persons in images and human bodies in crowded environments. © 2022. All Rights Reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Autism spectrum disorder prediction system using machine learning and deep learning

引用

International Journal of Applied Systemic Studies 2024年第2期11卷 159-173页

作者： Sharma, Anshu Tanwar, Poonam School of Computer Science and Engineering Manav Rachna International Institute of Research and Studies Haryana Faridabad121002 India

Autism spectrum disease (ASD) is a neuro developmental illness that is both complicated and degenerative. A majority of known approaches use autism detection observation schedule (ADOS), pattern recognition, etc. to detect ASD with a small dataset, resulting in high accuracy but low generality. In this research, an ASD detection hybrid model is presented which is works on two different types of datasets. Firstly, behavioural datasets which works on logistic regression technique and secondly, facial dataset which works on based on convolutional neural network (CNN) Classifier in order to predict whether a person is suffering from autism or not. The suggested hybrid model which works on behavioural and facial dataset of a person beats state-of-the-art approaches in terms of accuracy, according to simulation findings. The proposed hybrid model had an average accuracy of 88% for the logistic regression model while it achieved an accuracy of 82.76% for the CNN model. © 2024 Inderscience Enterprises Ltd.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Region-adaptive Concept Aggregation for Few-shot Visual Recognition

引用

Machine Intelligence Research 2023年第4期20卷 554-568页

作者： Mengya Han Yibing Zhan Baosheng Yu Yong Luo Han Hu Bo Du Yonggang Wen Dacheng Tao School of Computer Science National Engineering Research Center for Multimedia SoftwareWuhan UniversityWuhan430072China Hubei Luojia Laboratory Wuhan430072China School of Computer Science The University of SydneySydney2006Australia JD Explore Academy Beijing101116China School of Information and Electronics Beijing Institute of TechnologyBeijing100081China School of Computer Science and Engineering Nanyang Technological UniversitySingapore639798Singapore

Few-shot learning (FSL) aims to learn novel concepts from very limited examples. However, most FSL methods suffer from the issue of lacking robustness in concept learning. Specifically, existing FSL methods usually ignore the diversity of region contents that may contain concept-irrelevant information such as the background, which would introduce bias/noise and degrade the performance of conceptual representation learning. To address the above-mentioned issue, we propose a novel metric-based FSL method termed region-adaptive concept aggregation network or RCA-Net. Specifically, we devise a region-adaptive concept aggregator (RCA) to model the relationships of different regions and capture the conceptual information in different regions, which are then integrated in a weighted average manner to obtain the conceptual representation. Consequently, robust concept learning can be achieved by focusing more on the concept-relevant information and less on the conceptual-irrelevant information. We perform extensive experiments on three popular visual recognition benchmarks to demonstrate the superiority of RCA-Net for robust few-shot learning. In particular, on the Caltech-UCSD Birds-200-2011 (CUB200) dataset, the proposed RCA-Net significantly improves 1-shot accuracy from 74.76% to 78.03% and 5-shot accuracy from 86.84% to 89.83% compared with the most competitive counterpart.

关键词： Few-shot learning metric-based meta learning concept learning region-adaptive concept-aggregation

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Harmony Search Algorithm based on Firefly Algorithm and Boltzmann Machine

IAENG International Journal of Computer Science

引用

IAENG International Journal of computer science 2022年第1期49卷 241-251页

作者： Yang, J. Zhang, Xiaoxia Fu, S. Hu, Y.Y. Master Student of School of Computer Science and Software Engineering University of Science and Technology LiaoNing Anshan114051 China Professor of School of computer Science and Software Engineering University of Science and Technology LiaoNing Anshan11041 China

Harmony Search Algorithm (HS) is a new meta-heuristic algorithm based on music creation process. The algorithm has been widely used in many fields because of its simple and flexible structure and fewer controlled parameters. However, HS is easy to be affected by the initial harmony memory and falls into local optimization. In addition, there are also problems, such as low searching accuracy and slow convergence speed of the optimal solution. Therefore, this paper proposes a hybrid harmony search algorithm based on firefly algorithm and boltzmann machine (HSFA-BM). First, in order to avoid the possibility of harmony search algorithm falling into local optimum, boltzmann machine (BM) mechanism is used to update the harmony memory in this paper. Second, in order to enhance the ability of the algorithm to exploit optimal solutions, this paper uses the movement mode of fireflies to generate new solutions. The improved algorithm enhances the ability of global optimization and search precision, and speeds up the convergence speed. In this paper, six classical test functions are used to test the effectiveness of the algorithm, and a very obvious optimization result is obtained. © 2022. All Rights Reserved.

关键词： Flexible structures

来源：评论

学校读者我要写书评

暂无评论

A Multimodal Multiobjective Evolutionary Algorithm for Filter Feature Selection in Multilabel Classification

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第9期5卷 4428-4442页

作者： Hancer, Emrah Xue, Bing Zhang, Mengjie Victoria University of Wellington Center for Data Science and Artificial Intelligence School of Engineering and Computer Science Wellington6140 New Zealand Mehmet Akif Ersoy University Department of Software Engineering Burdur15039 Turkey

Multilabel learning is an emergent topic that addresses the challenge of associating multiple labels with a single instance simultaneously. Multilabel datasets often exhibit high dimensionality with noisy, irrelevant, and redundant features. In recent years, multilabel feature selection (MLFS) has gained prominence as a crucial and emerging machine learning task due to its ability to handle such data effectively. However, existing approaches for MLFS often prioritize top-ranked features based on intrinsic data criteria, disregarding relationships within the feature subset. Additionally, compared with conventional feature selection, multiobjective evolutionary algorithms (MOEAs) have not been widely explored in the context of MLFS. This study aims to address these gaps by proposing a multimodal multiobjective evolutionary algorithm (MMOEA) called MMDE_SICD which incorporates a preelimination scheme, an improved initialization scheme, an exploration scheme inspired by genetic operations and a statistically inspired crowding distance scheme. The results show that the proposed MMDE_SICD algorithm can outperform a variety of MOEAs and MMOEAs as well as conventional MLFS algorithms. Notably, this study is the first of its kind to consider MLFS as a multimodal multiobjective problem. © 2020 IEEE.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

A Construction of Object Detection Model for Acute Myeloid Leukemia

引用

Intelligent Automation & Soft Computing 2023年第4期36卷 543-560页

作者： K.Venkatesh S.Pasupathy S.P.Raja Department of Computer Science and Engineering Annamalai UniversityChidambaram608002India School of Computer Science and Engineering Vellore Institute of TechnologyVellore632014India

The evolution of bone marrow morphology is necessary in Acute Mye-loid Leukemia(AML)*** takes an enormous number of times to ana-lyze with the standardization and inter-observer ***,we proposed a novel AML detection model using a Deep Convolutional Neural Network(D-CNN).The proposed Faster R-CNN(Faster Region-Based CNN)models are trained with Morphological *** proposed Faster R-CNN model is trained using the augmented *** overcoming the Imbalanced Data problem,data augmentation techniques are *** Faster R-CNN performance was com-pared with existing transfer learning *** results show that the Faster R-CNN performance was signiﬁcant than other *** number of images in each class is *** example,the Neutrophil(segmented)class consists of 8,486 images,and Lymphocyte(atypical)class consists of eleven *** dataset is used to train the CNN for single-cell morphology classiﬁ*** proposed work implies the high-class performance server called Nvidia Tesla V100 GPU(Graphics processing unit).

关键词： Acute myeloid leukemia(AML) convolutional neural network(CNN) and nvidia tesla v100 gpu

来源：评论

学校读者我要写书评

暂无评论

An IoMT-based Federated Learning Survey in Smart Transportation

引用

Recent Advances in computer science and Communications 2024年第4期17卷 20-39页

作者： Karnam, Geetha Vani Maddikunta, Praveen Kumar Reddy School of Computer Science Engineering and Information Systems Vellore Institute of Technology Tamil Nadu Vellore632014 India

Internet of Medical Things (IoMT) is a technology that encompasses medical devices, wearable sensors, and applications connected to the Internet. In road accidents, it plays a crucial role in enhancing emergency response and reducing the impact of accidents on victims. Smart Transportation uses this technology to improve the efficiency and safety of transportation systems. The current Artificial Intelligence applications lack transparency and interpretability which is of utmost importance in critical transportation scenarios, such as autonomous vehicles, air traffic control systems, and traffic management systems. Explainable Artificial Intelligence (XAI) provides a clear, transparent explanation and actions. Traditional Machine Learning techniques have enabled Intelligent Transportation systems by performing centralized vehicular data training at the server where data sharing is needed, thus introducing privacy issues. To reduce transmission overhead and achieve privacy, a collaborative and distributed machine learning approach called Federated Learning (FL) is used. Here only model updates are transmitted instead of the entire dataset. This paper provides a comprehensive survey on the prediction of traffic using Machine Learning, Deep Learning, and FL. Among these, FL can predict traffic accurately without compromising privacy. We first present the overview of XAI and FL in the introduction. Then, we discuss the basic concepts of FL and its related work, the FL-IoMT framework, and motivations for using FL in transportation. Subsequently, we discuss the applications of using FL in transportation and open-source projects. Finally, we highlight several research challenges and their possible directions in FL. © 2024 Bentham science Publishers.

关键词： Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

A Novel Fuzzy Marine White Shark Optimization Based Efficient Routing and Enhancing Network Lifetime in MANET

引用

WIRELESS PERSONAL COMMUNICATIONS 2023年第4期132卷 2363-2385页

作者： Devi, K. Lalitha Bhat, C. Rohith Devi, K. Lalitha KSR College of Engineering Tiruchengode Namakkal India Department of Computer Science and Engineering Saveetha School of Engineering SIMATS Chennai Tamil Nadu 602105 India Department of Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai India

A mobile ad hoc network (MANET) is an independent wireless temporary network established by employing a set of mobile nodes (i.e. laptops, smartphones, iPods, etc.) appropriate for the environment in which the network infrastructures are not fixed. The most common problems faced by MANET are energy efficiency, high energy consumption, low network lifetime as well as high traffic overhead which create an impact on overall network topology. Hence, it is necessary to provide an energy-effective CH election to take steps against such issues. Therefore, this paper proposes a novel model to enhance the network lifetime and energy efficiency by performing a routing strategy in MANET. In this paper, an optimal CH is selected by proposing a novel Fuzzy Marine White Shark optimization (FMWSO) algorithm which is obtained by integrating fuzzy operation with two optimization algorithms namely the marine predator algorithm and white shark optimizer. The proposed approach comprises three diverse stages namely Generation of data, Cluster Generation and CH selection. A novel FMWSO algorithm is proposed in such a way to determine the CH selection in MANET thereby enhancing the network topology, network lifetime and minimizing the overhead rate, and energy consumption. Finally, the performance of the proposed FMWSO approach is compared with various other existing techniques to determine the effectiveness of the system. The proposed FMWSO approach consumes minimum energy of 0.62 mJ which is lower than other approaches.

关键词： MANET Cluster head Fuzzy Marine White Shark Cluster generation Network lifetime Energy consumption

来源：评论

学校读者我要写书评

暂无评论

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年第5期6卷 1360-1372页

作者： Wang, Shuyue Liu, Zhunga Zhang, Zuowei Bennamoun, Mohammed Northwestern Polytechnical University School of Automation Shaanxi Xi’an710072 China The University of Western Australia Department of Computer Science and Software Engineering PerthWA6009 Australia

Multimodal domain adaptation (MMDA) aims to transfer knowledge across different domains that contain multimodal data. Current methods typically assume that both the source and target domains have paired multimodal data with the same modalities, allowing for direct knowledge transfer between corresponding types of data. However, in certain applications, the source domain benefits from advanced sensors and equipment, capturing more modalities than those available in the target domain. As a result, the information from the source modalities may not strongly align with that of the target modalities. This weak correlation hinders the effective utilization of all source data for the target domain. To address this challenge, we propose a weakly correlated multimodal domain adaptation (WCMMDA) method for pattern classification. WCMMDA is designed to acquire the modality-independent and category-related knowledge from the source domain, enabling the full utilization of available source modalities for effective knowledge transfer. Specifically, modality-invariant features are first extracted from the multimodal data to bridge the heterogeneity gap within each domain. Subsequently, domain-invariant features are further learned from these modality-invariant features to align the feature distributions across the source and target domains. A source-specific classifier is employed here, which predicts pseudo-labels for the target data and enables the feature extractor to explore category-related information in source features. Finally, a target-specific classifier is trained using the pseudolabeled target data, where highly reliable pseudolabels are selected based on confidence to improve classification performance. Extensive experiments are performed on the real-world multimodal datasets to demonstrate the superiority of WCMMDA. © 2020 IEEE.

关键词： Labeled data

来源：评论

学校读者我要写书评

暂无评论

Research On Fatigue Driving Detection Based On Deep Learning

引用

engineering Letters 2025年第2期33卷 348-356页

作者： Zhou, Huinan Dai, Hong University of Science and Technology Liaoning Liaoning AnshanCO 114051 China School of Computer Science and Software Engineering University of Science and Technology Liaoning Liaoning AnshanCO 114051 China

Fatigue driving is one of the main causes of traffic accidents. Effective fatigue driving detection technology can reduce traffic accidents caused by fatigue driving. Traditional fatigue driving detection methods usually use a two-stage detection method, which has the problems of low efficiency and poor accuracy. To solve these problems, this paper designs a single-stage fatigue driving detection model based on separable convolution Road Safety Net (RSNet), which extracts the features in the driver's image or video and classifies these features to determine whether the driver is in an abnormal driving state. RSNet borrows the structure of Swin Transformer and adopts a hierarchical design, which makes the model better able to extract features and classify. Each level is composed of a GDS Layer and multiple RS Blocks. To solve the problem of low efficiency of traditional methods, we use separable convolution in RS Block to replace the traditional convolutional neural network, which reduces the complexity of the model and effectively improves the computational efficiency of the model. Experimental results show that the Top-1 and Top-5 Accuracy of RSNet on the HMDB51 dataset reaches 85 % and 97.35 %, respectively, and the delay is 5.97 ms. Compared with ResNet, EfficientNet, and Swin Transformer, RSNet has higher accuracy and efficiency. In addition, this paper takes the YOLACT algorithm as an example, selects different backbone networks for object detection, and compares the indicators of mean Average Precision (mAP) and Frames Per Second (FPS). Experiments show that RSNet performs better when used as the backbone network for object detection, with mAP reaching 32.4 % and FPS of 39.6 ms. It indicates that RSNet performs well in action recognition tasks. © 2025, International Association of Engineers. All rights reserved.

关键词： 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：