检索结果-内蒙古大学图书馆

作者： Zhou, Chengcheng Xu, Haitao Tang, Runze Lin, Ruijie Guo, Chao Han, Zhu University of Science and Technology Beijing School of Computer and Communication Engineering Beijing China Beijing Institute of Electronic System Engineering Beijing China China Academy of Information and Communications Technology Beijing China Beijing Electronics Science and Technology Institute Department of Electronic and Communication Engineering Beijing China University of Houston HoustonTX77004 United States Kyung Hee University Department of Computer Science and Engineering Seoul446-701 Korea Republic of

In this article, the power control and interference pricing problems between the macro base station (MBS) and small cell base stations (SBSs) in Heterogeneous networks (HetNets) are investigated. To optimally allocate power resources and effectively manage the power resources to reduce interference in HetNets, an innovative Stackelberg differential game approach is proposed. In the proposed Stackelberg game, the SBSs control their transmit power to achieve cost minimization based on the interference price offered by the MBS. Given the optimal power control strategies of SBSs, the MBS can adjust the interference price to realize the objective optimization. Renewable energy sources are introduced into the proposed HetNets, and differential equations formulate the SBSs' dynamic energy. Meanwhile, the MBS's state is given by the dynamic spectrum resources. Then the differential game is imported to achieve optimal power control and interference pricing. The open-loop Nash equilibrium solutions are first analyzed for the MBS and SBSs. Then the feedback Nash equilibrium solutions are given. Under the feedback pattern, the proposed model's performances in the non-cooperative and cooperative situations are discussed. Numerical simulations are given to show the convergence and effectiveness of the proposed game approach. © 1967-2012 IEEE.

关键词： Power control

来源：评论

学校读者我要写书评

暂无评论

Handwritten Digit Classification based on Ensemble Majority Voting Classifier

Handwritten Digit Classification based on Ensemble Majority ...

引用

International Conference on systems and Control (ICSC)

作者： Mariam Alsharif Amina Abdo Kenz A Bozed Faculty of Information Technology University of Benghazi Benghazi Libya Departemnt of Artificial Intelligence Collage of Computer Technology-Benghazi Benghazi Libya Department of Computer System Design University of Benghazi Benghazi Libya

Handwritten digit recognition is a significant challenge in the field of machine learning, particularly for pattern recognition and computer vision applications. It has found applications in various areas, such as identifying digits on utility maps, postal mail zip codes, bank check amounts, and more. Offline handwritten digits possess distinct characteristics, including size, orientation, position, and thickness. Each person's handwriting is unique, making the classification process more difficult. Additionally, the high similarity between certain digits and the over fitting problem with high-dimensional data can increase computational time and cost. Consequently, numerous researchers have developed and implemented different machine learning algorithms to effectively address the issue of recognizing handwritten digits. This paper introduces a novel approach to improve the classification performance and accuracy of handwritten digit recognition. The proposed method utilizes an ensemble majority vote classifier, which combines three classifiers in each experiment by utilizing a range of different algorithms; Naïve Bayes (NB), Adaptive Boosting Algorithm (AdaBoost), K-Nearest Neighbors (K-NN), Multi-layer Perceptron Classifier (MLP), eXtreme Gradient Boosting algorithm (XGBoost), and Decision Tree Algorithm (DT) to form a single ensemble classifier. To validate the approach, we used the MINST free public handwritten dataset, to ascertain the classifier with the highest rate of accuracy in this study. The results obtained from the experiments demonstrated that the full performance of Ensemble model classifiers MLP, XGBOOST, and DT is superior to AdaBoost, K-NN, and NB. It achieved the highest accuracy level, reaching 98% in the experiment. The experimental results of this research showed that the recognition accuracy was improved compared to previous works.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CorcPUM: Efficient Processing Using Cross-Point Memory via Cooperative Row-Column Access Pipelining and Adaptive Timing Optimization in Subarrays 23

CorcPUM: Efficient Processing Using Cross-Point Memory via C...

引用

Proceedings of the 60th Annual ACM/IEEE Design Automation Conference

作者： Chengning Wang Dan Feng Wei Tong Jingning Liu Wuhan National Laboratory for Optoelectronics Key Laboratory of Information Storage System Engineering Research Center of Data Storage Systems and Technology Ministry of Education of China (School of Computer Science and Technology Huazhong University of Science and Technology) Wuhan China

ISBN: (纸本)9798350323481

Emerging cross-point memory can in-situ perform vector-matrix multiplication (VMM) for energy-efficient scientific computation. However, parasitic-capacitance-induced row charging and discharging latency is a major performance bottleneck of subarray VMM. We propose a memory-timing-compliant bulk VMM processing-using-memory design with row access and column access co-optimization from rethinking of read access commands and μ-op timing. We propose row-level-parallelism-adaptive timing termination mechanism to reduce tail latency of tRCD and tRP by exploiting row nonlinear charging and bulk-interleaved row-column-cooperative VMM access mechanism to reduce tRAS and overlap CL without increasing column ADC precision. Evaluations show that our design can achieve 5.03× performance speedup compared with an aggressive baseline.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DRCTL: A Disorder-Resistant Computation Translation Layer Enhancing the Lifetime and Performance of Memristive CIM Architecture

DRCTL: A Disorder-Resistant Computation Translation Layer En...

引用

IEEE/ACM International Symposium on Microarchitecture (MICRO)

作者： Heng Zhou Bing Wu Huan Cheng Jinpeng Liu Taoming Lei Dan Feng Wei Tong Wuhan National Laboratory for Optoelectronics Key Laboratory of Information Storage System Engineering Research Center of Data Storage Systems and Technology School of Computer Science and Technology Huazhong University of Science and Technology Ministry of Education of China

ISBN: (数字)9798350350579

ISBN: (纸本)9798350350586

The memristive Computing-in-Memory (CIM) sys-tem can efficiently accelerate matrix-vector multiplication (MVM) operations through in-situ computing. The data layout has a significant impact on the communication performance of CIM systems. Existing software-level communication opti-mizations aim to reduce communication distance by carefully designing static data layouts, while wear-leveling (WL) and error mitigation methods use dynamic scheduling to enhance system reliability, resulting in randomized data layouts and increased communication overhead. Besides, existing CIM compilers di-rectly map data to physical crossbars and generate instructions, which causes inconvenience for dynamic scheduling. To address these challenges of balancing communication performance and reliability while coordinating existing CIM compilers and dy-namic scheduling, we propose a disorder-resistant computation translation layer (DRCTL), which improves system lifetime and communication performance through co-optimization of data layout and dynamic scheduling. It consists of three parts: (1) We propose an address conversion method for dynamic scheduling, which updates the addresses in the instruction stream after dynamic scheduling, thereby avoiding recompilation. (2) Dynamic scheduling strategy for reliability improvement. We propose a hierarchical wear-leveling (HWL) strategy, which reduces communication by increasing scheduling granularity. (3) Communication optimization for dynamic scheduling. We propose data layout-aware selective remapping (LASR), which helps dynamic scheduling methods improve communication lo-cality and reduce latency by exploiting data dependencies. The experiments demonstrate that HWL extends lifetime by 100.3-205.9 x compared to not using WL. Even with a slight lifetime decrease compared to the state-of-the-art WL (TIWL), it still supports continuous neural network training for 7 years. After applying LASR to HWL, the number of execution cycles, energy consumption

关键词： Training Energy consumption Processor scheduling Layout Dynamic scheduling In-memory computing Common information Model (computing) system-on-chip Reliability Optimization

来源：评论

学校读者我要写书评

暂无评论

A Practical Cloud API Complementary Recommendation Service for Mashup Creation

A Practical Cloud API Complementary Recommendation Service f...

引用

International Conference on computer Supported Cooperative Work in Design

作者： Xiaowei Liu Wenhui Chen Mengmeng Sun Yali Si Zhen Chen School of Information Science and Engineering Yanshan University Qinhuangdao China School of Computer Science and Engineering Changshu Institute of Technology Changshu China Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Yanshan University Qinhuangdao China

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

With the popularity of the service-oriented development paradigm in the cloud era, numerous cloud APIs have been developed. The continuous proliferation of cloud APIs has submerged developers in a sea of options, bringing the need for cloud API recommendation techniques. Most existing cloud API recommendation methods focus on theoretical studies and neglect practical applications. As a result, these methods face several challenges, such as covering recommendation scenarios, generating real-time responses, and handling concurrent requests. In this paper, we propose and implement a practical cloud API complementary recommendation service for mashup creation. To address the above challenges, we first propose a cloud API complementary recommendation framework named FICR, which exploits feature interactions to mine implicit complementarity and models complementarity from the mashup side and the target cloud API side for scenario coverage. Then, we conduct performance optimization via precoding and batch size tuning to optimize FICR for real-time responses. Finally, we design a minimum-connection load balancing algorithm with resource early warning and build a distributed system for concurrent requests. Experiments conducted on real-world datasets show that FICR outperforms state-of-the-art baseline models in complementary recommendation scenarios, and demonstrate that the implemented service meets the real-time and concurrency requirements. The service will serve as a practical tool to help developers during mashup creation.

关键词： Concurrent computing Federated learning Mashups Precoding Load management Real-time systems Tuning

来源：评论

学校读者我要写书评

暂无评论

Digital forensics for the socio-cyber world (DF-SCW): A novel framework for deepfake multimedia investigation on social media platforms

引用

Egyptian Informatics Journal 2024年 27卷

作者： Ayub Khan, Abdullah Chen, Yen-Lin Hajjej, Fahima Ahmed Shaikh, Aftab Yang, Jing Soon Ku, Chin Yee Por, Lip Department of Computer Science and Information Technology Benazir Bhutto Shaheed University Lyari Sindh Karachi75660 Pakistan Department of Computer Science Sindh Madressatul Islam University Sindh Karachi74000 Pakistan Department of Computer Science and Information Engineering National Taipei University of Technology Taipei106344 Taiwan Department of Software Engineering College of Computer and Inf. Sci. Princess Nourah bint Abdulrahman University P.O. Box 84428 Riyadh11671 Saudi Arabia Department of Computer System and Technology Faculty of Computer Science and Information Technology Universiti Malaya Kuala Lumpur50603 Malaysia Department of Computer Science Universiti Tunku Abdul Rahman Kampar31900 Malaysia

Owing to the major development of social media platforms, the usage of technological adaptation increases by means of editing software tools. Posting media in social communication environments has become one of our common daily routines. Before posting, various editing generators are used to manipulate pixel values, such as for enhancing brightness and contrast. Undoubtedly, this software helps bring posting media from ordinary to outstanding. But such a type of editing crosses the line in terms of creating fakes—anything that comes from anywhere and does not retain its originality anyway. It poses a series of issues in the process of multimedia forensics investigation and chain of custody. In order to restrict the attempts at deep faking and make the investigation hierarchy more effective, efficient, and reliable in the socio-cyber space (SCS), this paper presents a novel framework called DF-SCW. A digital forensics-enabled socio-cyber world with artificial intelligence (AI), especially deep neural networks (DNNs), for detecting and analyzing deep fake media investigations on social media platforms. It compares pixels with their neighboring values in the same media (such as images and videos) to identify information about the original one. There is a media flag designed to filter out malicious and dangerous attempts, like a powerful leader declaring war. Putting flags on such fakes helps digital investigators resist sharing the posts. In addition, the other prospect of this research is to make the digital forensics ecosystem more appropriate to take qualitative judgments in real-time while media is uploaded on social media platforms. The simulation of the proposed DF-SCW is tested on three different platforms, such as Instagram, Facebook, and Twitter. Through the experiment, the DF-SCW outperformed in terms of detection, identification, and analysis of deepfake media by an increased rate of 3.77%. © 2024

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

Multi-Scale and Improved Skip Connections Network for Skin Lesion Segmentation

Multi-Scale and Improved Skip Connections Network for Skin L...

引用

6th International Conference on Intelligent Computing and Signal Processing (ICSP)

作者： Botao Zhang Jun Chen College of Computer Science and Technology Wuhan University of Science and Technology Wuhan China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan University of Science and Technology Wuhan China

ISBN: (数字)9798350376548

ISBN: (纸本)9798350376555

To solve the problem that the current skin lesion segmentation networks have a poor segmentation accuracy when lesion areas are of different shapes and sizes and low contrast at the edge areas, based on U-Net, we present a skin lesion segmentation network based on multi-scale and improved skip connections. Firstly, a multi-scale feature enhancement module is designed to replace the U-Net's $\boldsymbol{3\times 3}$ convolution blocks, which can improve the feature extraction ability of the network about lesion areas of different shapes and sizes. Secondly, a lesion attention module is introduced into the skip connection to improve the semantic expression of low-level features and the location attention of high-level features, which can improve the fine-grained information transmission efficiency at the skip connection. Finally, a new hybrid loss function is designed to calculate the label and the edge loss of lesion areas, which improves the ability of the network to segment lesion areas and edges. Experiments are conducted on the ISIC2017 and ISIC2018 datasets, and the results prove that our method have a higher segmentation accuracy in skin lesion segmentation.

关键词： Accuracy Shape Convolution Semantics information processing Feature extraction Skin Lesions

来源：评论

学校读者我要写书评

暂无评论

HCU-Net: An Efficient Fully Convolutional Neural Network for Thyroid Nodules Ultrasound Image Segmentation

HCU-Net: An Efficient Fully Convolutional Neural Network for...

引用

IEEE International Conference on systems, Man and Cybernetics

作者： Mengxi Ren Jun Liu School of Computer Science and Technology Wuhan University of Science and Technology Wuhan China Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System Wuhan University of Science and Technology Wuhan China

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

Thyroid nodules, which can manifest as solitary or multiple growths, are among the most prevalent diseases with a high incidence rate. When examining thyroid nodules, ultrasound is typically the first step. Ultrasound image segmentation of thyroid nodules can assist physicians in diagnosis. However, the following three factors limit the development of thyroid nodule segmentation: (1) most of the existing studies optimize the segmentation of single nodules, and the incidence of multiple nodules is higher, so the segmentation of multiple nodules is also very important; (2) the ultrasound image of thyroid nodules is difficult to segment because of its low resolution and fuzzy boundary; (3) Due to the small data set of thyroid nodule ultrasound, in such a small dataset, attention mechanisms may be prone to overfitting, resulting in poorer generalization performance. Therefore, the attention-based model may not be suitable for the segmentation of thyroid nodules. Hence, we propose Hybrid Convolutional U-Net (HCU-Net), a simple and strong fully convolutional neural network for the segmentation of single or multiple thyroid nodules. HCU-Net incorporates a large receptive field to ensure accurate and stable segmentation. Specifically, we design Hybrid Branch Block to enhance the network's feature extraction capability for single or multiple nodules in ultrasound images by integrating multi-scale features. Furthermore, we add Enhanced ConvNeXt Blocks to the U-Net's final layer, enabling the extraction of global contextual information for segmentation performance. The Experimental results show that our proposed method can effectively improve these issues on two publicly available datasets. In addition, compared to attention-based models, our network is simpler and more suitable for small datasets like ultrasound images.

关键词： Image segmentation Ultrasonic imaging Image resolution Medical services Feature extraction Convolutional neural networks Medical diagnostic imaging Thyroid Overfitting Diseases

来源：评论

学校读者我要写书评

暂无评论

RPUDet: Learning Relational Prior and Uncertainty for Robust Aerial Object Detection 25

RPUDet: Learning Relational Prior and Uncertainty for Robust...

引用

Proceedings of the 2025 International Conference on Multimedia Retrieval

作者： Kun Qian Wei Liu Minshi Chen Xiao Wang Xin Yuan School of Computer Science and Technology Wuhan University of Science and Technology Wuhan Hubei China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan University of Science and Technology Wuhan Hubei China

ISBN: (纸本)9798400718779

Aerial object detection remains a challenging task in the computer vision community. While general object detectors perform well on natural images, they struggle with aerial images due to missed detections from small, low-resolution objects and misdetections caused by classification uncertainty between semantically similar objects. To address these issues, we propose a Relational Prior and Uncertainty detector (RPUDet). RPUDet consists of two core modules: 1) Relation Aware Reasoning Module (RARM), which leverages a relational prior graph to help detect correlated objects and reduce missed detections of low-resolution objects; and 2) Uncertainty Guided Awareness Module (UGAM), which computes a uncertainty map to identify low-confidence regions, dynamically adjusts feature weights, and refines areas with high semantic ambiguity to mitigate misdetections. Additionally, to advance aerial object detection in industrial applications, we introduce the Low-Voltage Distribution Insulator Dataset (LVDID), focusing on static scenes, in contrast to existing dynamic datasets. This enables us to evaluate RPUDet's performance across diverse real-world scenarios. We evaluate RPUDet on VisDrone2019, VEDAI, and LVDID, demonstrating superior performance compared to existing methods. The code and dataset will be available at https://***/Godk02/RPUDet.

关键词： aerial object detection

来源：评论

学校读者我要写书评

暂无评论

On the Generalization and Causal Explanation in Self-Supervised Learning

arXiv

引用

arXiv 2024年

作者： Qiang, Wenwen Song, Zeen Gu, Ziyin Li, Jiangmeng Zheng, Changwen Sun, Fuchun Xiong, Hui The National Key Laboratory of Space Integrated Information System Institute of Software Chinese Academy of Sciences University of Chinese Academy of Sciences Beijing China The National Key Laboratory of Space Integrated Information System Department of Computer Science and Technology Tsinghua University Beijing China The Hong Kong University of Science and Technology China

Self-supervised learning (SSL) methods learn from unlabeled data and achieve high generalization performance on downstream tasks. However, they may also suffer from overfitting to their training data and lose the ability to adapt to new tasks. To investigate this phenomenon, we conduct experiments on various SSL methods and datasets and make two observations: (1) Overfitting occurs abruptly in later layers and epochs, while generalizing features are learned in early layers for all epochs;(2) Coding rate reduction can be used as an indicator to measure the degree of overfitting in SSL models. Based on these observations, we propose Undoing Memorization Mechanism (UMM), a plug-and-play method that mitigates overfitting of the pre-trained feature extractor by aligning the feature distributions of the early and the last layers to maximize the coding rate reduction of the last layer output. The learning process of UMM is a bi-level optimization process. We provide a causal analysis of UMM to explain how UMM can help the pre-trained feature extractor overcome overfitting and recover generalization. We also demonstrate that UMM significantly improves the generalization performance of SSL methods on various downstream tasks. The source code is to be released at https://***/ZeenSong/UMM. © 2024, CC BY.

关键词： Self-supervised learning

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：