检索结果-内蒙古大学图书馆

7th International Conference on Electronics technology, ICET 2024

作者： Lu, Hui Zhang, Yi Wu, Zebin Wei, Zhihui Nanjing University of Science and Technology School of Computer Science and Engineering Nanjing China

ISBN: (纸本)9798350363951

During the last 3 years, researchers have endeavored to extend the efficacy of contrastive learning (CL) towards addressing the challenges inherent in cloud workload prediction, which has demonstrated considerable success in the domains of computer Vision (CV) and Natural Language Processing(NLP). However, due to the distinctive temporal characteristics of serialized workload information, relying solely on empirical guidance from other domains may prove insufficient for cloud workload prediction. Therefore, we systematically investigated three key components of CL, including: 1) designing backbone encoder for feature extraction, 2) designing methods for extracting negative samples for contrast, and 3) designing the CL loss. We found that inappropriate construction of negative samples may introduce excessive pseudo-negative samples, which neither preserve temporal characteristics nor provide sufficient discriminative features. Additionally, focusing solely on the discrimination between positive and negative samples in the CL loss may not be adequate for enabling the model to learn the temporal patterns of serialized workload information. To address these problems, we propose a novel self-supervised model named Cloudformer. Specifically, we first constructed a CL network based on the Transformer architecture using a pre-train-finetune framework. Following this, we proposed a method to filter pseudo-negative samples based on differential cosine similarity, aimed at assisting the model in more effectively distinguishing between positive and negative samples. Additionally, we introduced the BatchNCE loss, combining MSE loss with InfoNCE loss as a joint optimization objective for CL, effectively enhancing the predictive capability of the model. The experimental results indicate that Cloudformer is capable of learning high-quality patterns in serialized workload sequences and achieves more advanced performance in short sequence prediction tasks. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Focusing on your subject:Deep subject-aware image composition recommendation networks

引用

Computational Visual Media 2023年第1期9卷 87-107页

作者： Guo-Ye Yang Wen-Yang Zhou Yun Cai Song-Hai Zhang Fang-Lue Zhang BNRist Department of Computer Science and TechnologyTsinghua UniversityBeiing 100084China School of Engineering and Computer Science Victoria University of WellingtonWellington 6012New Zealand

Photo composition is one of the most important factors in the aesthetics of *** a popular application,composition recommendation for a photo focusing on a specific subject has been ignored by recent deep-learning-based composition recommendation *** this paper,we propose a subject-aware image composition recommendation method,SAC-Net,which takes an RGB image and a binary subject window mask as input,and returns good compositions as crops containing the *** model first determines candidate scores for all possible coarse cropping *** crops with high candidate scores are selected and further refined by regressing their corner points to generate the output recommended cropping *** final scores of the refined crops are predicted by a final score regression *** existing methods that need to preset several cropping windows,our network is able to automatically regress cropping windows with arbitrary aspect ratios and *** propose novel stability losses for maximizing smoothness when changing cropping windows along with view *** results show that our method outperforms state-of-the-art methods not only on the subject-aware image composition recommendation task,but also for general purpose composition *** also have designed a multistage labeling scheme so that a large amount of ranked pairs can be produced *** use this scheme to propose the first subject-aware composition dataset SACD,which contains 2777 images,and more than 5 million composition ranked *** SACD dataset is publicly available at https://***/SACD/.

关键词： subject-aware image composition image cropping deep learning recommendation

来源：评论

学校读者我要写书评

暂无评论

Reward Maximization for Disaster Zone Monitoring with Heterogeneous UAVs

引用

IEEE/ACM Transactions on Networking 2024年第1期32卷 890-903页

作者： Xu, Wenzheng Wang, Chengxi Xie, Hongbin Liang, Weifa Dai, Haipeng Xu, Zichuan Wang, Ziming Guo, Bing Das, Sajal K. Sichuan University College of Computer Science Chengdu610065 China City University of Hong Kong Department of Computer Science Hong Kong Hong Kong Nanjing University Department of Computer Science and Technology Nanjing210023 China Dalian University of Technology School of Software Dalian116024 China Sichuan University Key Laboratory of Birth Defects and Related Maternal and Child Diseases West China Second Hospital College of Computer Science Chengdu610066 China Missouri University of Science and Technology Department of Computer Science RollaMO65409 United States

In this paper, we study the deployment of K heterogeneous UAVs to monitor Points of Interest (PoIs) in a disaster zone, where a PoI may represent a school building or an office building, in which people are trapped. A UAV can take images/videos of PoIs and send its collected information back to a nearby rescue station for decision-making. Unlike most existing studies that focused on only homogeneous UAVs, we here study the scheduling of K heterogeneous UAVs, where different UAVs have different energy capacities and functionalities that lead to different monitoring qualities (monitoring rewards) of each PoI. For example, one type of UAVs can take only visual images while the other type of UAVs can take both visual and thermal infrared images. In this paper, we investigate a problem of scheduling K heterogeneous UAVs to monitor PoIs so that the sum of monitoring rewards received by all UAVs is maximized, subject to energy capacity on each UAV. We propose the very first 13 -approximation algorithm for this scheduling problem. We also evaluate the performance of the proposed algorithm, using real parameters of commercial UAVs. Experimental results show that the performance of the proposed algorithm is promising, which is improved by 25%, compared with existing algorithms. © 1993-2012 IEEE.

关键词： Approximation algorithms

来源：评论

学校读者我要写书评

暂无评论

REGAC: Multi-Class Offensive Content Identification Using Graphical Approach

IAENG International Journal of Computer Science

引用

IAENG International Journal of computer science 2025年第4期52卷 931-952页

作者： Chinivar, Sneha Roopa, M.S. Arunalatha, J.S. Venugopal, K.R. Department of Computer Science and Engineering Bangalore University K R Circle Karnataka Bengaluru India Department of Computer Science and Engineering Nitte Meenakshi Institute of Technology Karnataka Bengaluru India Department of Computer Science and Engineering Bangalore University K R Circle Karnataka Bengaluru India Karnataka Bengaluru India

Online offensive behaviour continues to rise with the increasing popularity and use of social media. Various techniques have been used to address this issue. However, most existing studies consider offensive content identification as a binary or ternary problem, disregarding the potential for multi-class classification of derogatory content. In this work, we propose RoBERTa Embedding-based Graphical Approach Classifier (REGAC), which aims to designate the identified offensive content into varied classes,like age, gender, ethnicity, religion, and others to understand what exact qualities the bully usually targets in their victim so that pertinent measures can be taken to battle them. Additionally, the models’ efficiency is evaluated using an unbalanced dataset to identify types of offensive content. The word embeddings are generated for a balanced dataset using RoBERTa embedding model to bring out the best-fitting vectors. These vectors are then input into traditional Machine Learning algorithms (SVM, KNN, Logistic Regression, Random Forest, and XGBoost) and graph-based algorithms (Graph Convolution Network (GCN), GraphSAGE, and Graph Attention Network (GAT)) for fine-grained categorization of offensive textual content. The experimental results demonstrate the efficiency of combating social media’s offensive content of the proposed work with higher Precision, Recall, F1-Score, and Accuracy compared with most state-of-art approaches. © (2025.0), (International Association of Engineers). All Rights Reserved.

关键词： Graph embeddings

来源：评论

学校读者我要写书评

暂无评论

Design of a ML-based trust prediction model using intelligent TrustBoxes in challenged networks

引用

International Journal of Systems, Control and Communications 2024年第3期15卷 209-234页

作者： Barai, Smritikona Kundu, Anindita Bhaumik, Parama Department of Computer Science and Engineering Heritage Institute of Technology Kolkata India Department of Software Systems School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu India Department of Information Technology Jadavpur University Kolkata India

Challenged networks (CNs) contain resource-constrained nodes deployed in regions where human intervention is difficult. Opportunistic networks (OppNets) are CNs with no predefined source-to-destination paths. Due to their inherent properties, CNs and OppNets are highly susceptible to black-hole (BH) attacks, resulting in degraded packet-delivery ratio. In this work, an ML-based trust prediction model (MLTPM) is proposed to identify potential BH nodes in OppNets. MLTPM uses a novel function to calculate the total-trust-value (TTV) of each node. Intelligent TrustBoxes are introduced in the network to identify possible BH nodes, using TTV, along with five more node-behaviour features. TrustBoxes reduce the computational overhead of the resource-constrained nodes. Three simulated scenarios are compared - no detection, non-ML-based detection, and MLTPM, each using epidemic, prophet, and spray-and-wait routing protocols. MLTPM performs best with spray-and-wait, exhibiting about 25.21% and 80% mean improvement in delivery-ratio and dropped-message numbers respectively, compared to non-ML-based detection. An overall 12.62% improvement in delivery-ratio and 26.7% improvement in dropped messages is observed using MLTPM, compared to the above-mentioned scenarios. © 2024 Inderscience Enterprises Ltd.

关键词： HTTP

来源：评论

学校读者我要写书评

暂无评论

A location-based fog computing optimization of energy management in smart buildings:DEVS modeling and design of connected objects

引用

Frontiers of computer science 2023年第2期17卷 179-195页

作者： Abdelfettah MAATOUG Ghalem BELALEM Saïd MAHMOUDI Computer Science Department Faculty of Exact and Applied SciencesUniversity of Oran 1 Ahmed Ben BellaOran 31000Algeria Science and Technology Department Faculty of Science and TechnologyUniversity of TIARETTiaret 14000Algeria Computer Science Department Faculty of EngineeringUniversity of MonsMons 7000Belgium

Nowadays,smart buildings rely on Internet of things(loT)technology derived from the cloud and fog computing paradigms to coordinate and collaborate between connected *** is characterized by low latency with a wider spread and geographically distributed nodes to support mobility,real-time interaction,and location-based *** provide optimum quality of user life in moderm buildings,we rely on a holistic Framework,designed in a way that decreases latency and improves energy saving and services efficiency with different *** EVent system Specification(DEVS)is a formalism used to describe simulation models in a modular *** this work,the sub-models of connected objects in the building are accurately and independently designed,and after installing them together,we easily get an integrated model which is subject to the fog computing *** results show that this new approach significantly,improves energy efficiency of buildings and reduces ***,with DEVS,we can easily add or remove sub-models to or from the overall model,allowing us to continually improve our designs.

关键词： smart building energy consumption IoT fog computing Framework DEVS simulation models

来源：评论

学校读者我要写书评

暂无评论

Energy Efficient Unequal Fault Tolerance Clustering Approach

引用

computer Systems science & engineering 2023年第5期45卷 1971-1983页

作者： Sowjanya Ramisetty Divya Anand Kavita Sahil Verma NZ Jhanjhi Mehedi Masud Mohammed Baz Department of Computer Science and Engineering KG Reddy College of Engineering and TechnologyHyderabadIndia School of Computer Science and Engineering Lovely Professional UniversityPhagwaraIndia Department of Computer Science and Engineering Chandigarh UniversityMohaliIndia Department of Computer Science and Engineering Tailor’s UniversityMalaysia Department of Computer Science College of Computers and Information TechnologyTaif UniversityTaif21944Saudi Arabia Department of Computer Engineering College of Computer and Information TechnologyTaif UniversityTaif21994Saudi Arabia

For achieving Energy-Efficiency in wireless sensor networks(WSNs),different schemes have been proposed which focuses only on reducing the energy consumption.A shortest path determines for the Base Station(BS),but fault tolerance and energy balancing gives equal importance for improving the network *** saving energy in WSNs,clustering is considered as one of the effective methods for Wireless Sensor *** of the excessive overload,more energy consumed by cluster heads(CHs)in a cluster based WSN to receive and aggregate the information from member sensor nodes and it leads to *** increasing the WSNs’lifetime,the CHs selection has played a key role in energy consumption for sensor *** Energy Efficient Unequal Fault Tolerant Clustering Approach(EEUFTC)is proposed for reducing the energy utilization through the intelligent methods like Particle Swarm Optimization(PSO).In this approach,an optimal Master Cluster Head(MCH)-Master data Aggregator(MDA),selection method is proposed which uses the fitness values and they evaluate based on the PSO for two optimal nodes in each cluster to act as Master Data Aggregator(MDA),and Master Cluster *** data from the cluster members collected by the chosen MCH exclusively and the MDA is used for collected data reception from MCH transmits to the ***,the MCH overhead *** the heavy communication of data,overhead controls using the scheduling of Energy-Efficient Time Division Multiple Access(EE-TDMA).To describe the proposed method superiority based on various performance metrics,simulation and results are compared to the existing methods.

关键词： Energy-efficiency unequal fault tolerant clustering approach particle swarm optimization master data aggregator energy efficient time division multiple access optimal nodes

来源：评论

学校读者我要写书评

暂无评论

Research on facial expression recognition based on multimodal data fusion and neural network

引用

International Journal of Wireless and Mobile Computing 2024年第1期27卷 47-55页

作者： Han, Yi Wang, Xubin Lu, Zhengyu School of Mechanical Science and Engineering Huazhong University of Science and Technology Hubei Wuhan China Anyang Institute of Technology Department of Computer Science and Information Engineering Henan Province Anyang China School of Computer Science and Information Engineering Shanghai Institute of Technology FengXian District Shanghai China

Facial expression recognition is a challenging task when neural network is applied to pattern recognition. Most of the current recognition research is based on single source facial data, which generally has the disadvantages of low accuracy and low robustness. In this paper, a neural network algorithm of facial expression recognition based on multimodal data fusion is proposed. The algorithm is based on the multimodal data, and it takes the facial image, the histogram of oriented gradient of the image and the facial landmarks as the input, and establishes Convolutional Neural Network (CNN) designed to extract features from facial image, neural network designed to extract features from facial Landmarks and Neural Network (LNN) designed to extract features from Histogram of gradient (HNN), three sub-neural networks to extract data features, using multimodal data feature fusion mechanism to improve the accuracy of facial expression recognition. Experimental results show that, the algorithm has a great improvement in accuracy, robustness and detection speed. Copyright © 2024 Inderscience Enterprises Ltd.

关键词： Data fusion

来源：评论

学校读者我要写书评

暂无评论

Jointly Estimation of Microstructure Maps Across Acquisition Protocols

Jointly Estimation of Microstructure Maps Across Acquisition...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Wang, Tenglong Yu, Jiahao Pan, Yiang He, Jianzhong He, Yifei Wu, Ye Nanjing University of Science and Technology School of Computer Science and Engineering Nanjing China Zhejiang University of Technology College of Information Engineering Hangzhou China

ISBN: (纸本)9798350386226

Diffusion MRI (dMRI) allows for examining microarchitecture profiles and tissue changes using specific microstructure modeling but depends on advanced acquisition protocol and well-established biological model assumptions. It is also limited in clinical applications due to lengthy acquisition time and dense q-space sampling requirements. In this study, we present a method that aims to estimate multiple functional microstructural parameters robustly, thereby enhancing clinical applications with different acquisition protocols. Instead of learning the mapping between dMRI and microstructure maps directly, our approach learns a set of explainable over-completed tissue-compartment kernels between parameterized spherical mean signal and widely-used microstructure maps and apply into the joint characterization of multiple biological models. We validate the effectiveness of our method using an in vivo dataset across different health conditions collected by a clinical scanner. This work sets the foundation for future techniques that integrate clinical data acquisition protocols and enhance sensitivity to microstructure measures. The code is provided at https://***/1nlandempire/JEMAP. © 2024 IEEE.

关键词： Tissue

来源：评论

学校读者我要写书评

暂无评论

Cyber-attack detection based on a deep chaotic invasive weed kernel optimized machine learning classifier in cloud computing

引用

Soft Computing 2025年第4期29卷 2015-2030页

作者： Indrasena Reddy, M. Siva Kumar, A.P. Subba Reddy, K. Department of Computer Science and Engineering BVRIT Hyderabad College of Engineering for Women Hyderabad500090 India Department of Computer Science and Engineering Jawaharlal Nehru Technological University Ananthapuramu Andhra Pradesh Ananthapuramu India Department of Computer Science and Engineering Rajeev Gandhi Memorial College of Engineering and Technology Andhra Pradesh Nandyala India

Nowadays, Cloud Computing has attracted a lot of interest from both individual users and organization. However, cloud computing applications face certain security issues, such as data integrity, user privacy, and service availability. The only better solution to such issues is to identify and prevent cyber threats before they can cause seriously harm the cloud computing system. Several methods have been suggested so far to detect the attack in cloud computing (CC), but no one method attains satisfactory results. To overwhelm these drawbacks, a Cyber Security Attack Detection using Deep Kernel Machine Learning optimized with Chaotic Invasive Weed Optimization algorithm is proposed in this paper for Cloud Computing. Here, the data is amassed from CSE-CIC-IDS2018 and Bot-IoT datasets. Subsequently, a pre-processing step involving redundancy reduction and missing value replacement for uncertainty removal is achieved through the Developed Random Forest with Local Least Squares (DRFLLS) method. By utilizing Entropy-Kurtosis based feature selection approach, the pre-processing data is given to the feature selection to identify the optimal features. The selected features are supplied to the Deep Kernel Machine Learning classifier (DK-ML), which is optimized using the Chaotic Invasive Weed Optimization algorithm (Chaotic-IWOA) for classification. This classification process classifies the data as normal or anomalous categories with anomalies encompassing, like DoS, DDoS, Theft attacks, and normal attacks. The proposed technique is activated in MATLAB. The proposed technique achieves 24.88%, 17.98%, 45.65%, 35.95% better accuracy for CSE-CIC-IDS2018 dataset, and 23.93%, 13.94%, 32.94%, and 29.04% better accuracy for Bot-IoT dataset. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Cyber attacks

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：