检索结果-内蒙古大学图书馆

CLIP-Flow:Decoding images encoded in CLIP space

Computational Visual Media 2024年第6期10卷 1157-1168页

作者： Hao Ma Ming Li Jingyuan Yang Or Patashnik Dani Lischinski Daniel Cohen-Or Hui Huang Visual Computing Research Center College of Computer Science and Software EngineeringShenzhen UniversityShenzhen 518060China Department of Computer Science Tel Aviv UniversityTel Aviv 6997801Israel School of Computer Science and Engineering the Hebrew University of JerusalemJerusalem 91904Israel

This study introduces CLIP-Flow,a novel network for generating images from a given image or *** effectively utilize the rich semantics contained in both modalities,we designed a semantics-guided methodology for image-and text-to-image *** particular,we adopted Contrastive Language-Image Pretraining(CLIP)as an encoder to extract semantics and StyleGAN as a decoder to generate images from such ***,to bridge the embedding space of CLIP and latent space of StyleGAN,real NVP is employed and modified with activation normalization and invertible *** the images and text in CLIP share the same representation space,text prompts can be fed directly into CLIP-Flow to achieve text-to-image *** conducted extensive experiments on several datasets to validate the effectiveness of the proposed image-to-image synthesis *** addition,we tested on the public dataset Multi-Modal CelebA-HQ,for text-to-image *** validated that our approach can generate high-quality text-matching images,and is comparable with state-of-the-art methods,both qualitatively and quantitatively.

关键词： image-to-image text-to-image contrastive language-image pretraining(CLIP) flow StyleGAN

来源：评论

学校读者我要写书评

暂无评论

An Improved Gannet Optimization Algorithm Based on Opposition-Based Schemes for Feature Selection Problems in High-Dimensional Datasets

引用

SN computer science 2024年第1期5卷 183页

作者： Avinash, N. Sinha, Sitesh Kumar Shivamurthaiah, M. Department of computer science and engineering Rabindranath tagore university Bhopal India Department of Computer Science and Engineering APS College of Engineering Bangalore India

In the ever-evolving landscape of optimization algorithms for healthcare datasets, this study introduces an innovative fusion of the gannet optimization algorithm (GOA) with advanced opposition-based learning (OBL) techniques, including quasi-OBL, generalized OBL, and partial OBL. The primary novelty of our approach lies in the hybridization of GOA with OBL schemes. While GOA itself draws inspiration from the hunting behavior of gannets, OBL techniques introduce a layer of opposition-based learning that mimics the dialectical nature of opposing forces. By integrating these two distinct paradigms, we create a symbiotic relationship between exploration and exploitation. This synergy empowers our optimization framework to dynamically adapt to the complex landscape of high-dimensional healthcare datasets, underlining its prowess in classification tasks, particularly when employed with support vector machine (SVM) and k-nearest neighbor (KNN) classifiers. Statistical validation further underscores the significance of our results. The p value analysis reveals that our GOBL–GOA approach stands as a statistically superior alternative, making substantial strides in feature selection and classification accuracy. Beyond statistics, our approach excels in practicality, effectively identifying and selecting relevant features to provide accurate insights from complex healthcare data, as demonstrated by precision, recall, and F1-score metrics. In conclusion, our study not only introduces a paradigm shift in feature selection and optimization but also advances the cause of precise disease detection and prognosis, holding immense potential to enhance healthcare outcomes globally. © 2024, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Feature selection Gannet optimization algorithm High-dimensional dataset Opposition-based learning

来源：评论

学校读者我要写书评

暂无评论

Hybrid DF and SIR Forwarding Strategy in Conventional and Distributed Alamouti Space-Time Coded Cooperative Networks

引用

computer Modeling in engineering & sciences 2025年第2期142卷 1933-1954页

作者： Slim Chaoui Omar Alruwaili Faeiz Alserhani Haifa Harrouch Department of Computer Engineering and Networks College of Computer and Information SciencesJouf UniversitySakaka72388Saudi Arabia Computer Science Department Applied CollegeUniversity of HailHail55424Saudi Arabia

In this paper,we propose a hybrid decode-and-forward and soft information relaying(HDFSIR)strategy to mitigate error propagation in coded cooperative *** the HDFSIR approach,the relay operates in decode-and-forward(DF)mode when it successfully decodes the received message;otherwise,it switches to soft information relaying(SIR)*** benefits of the DF and SIR forwarding strategies are combined to achieve better performance than deploying the DF or SIR strategy ***-form expressions for the outage probability and symbol error rate(SER)are derived for coded cooperative communication with HDFSIR and energy-harvesting ***,we introduce a novel normalized log-likelihood-ratio based soft estimation symbol(NL-SES)mapping technique,which enhances soft symbol accuracy for higher-order modulation,and propose a model characterizing the relationship between the estimated complex soft symbol and the actual high-order modulated ***-more,the hybrid DF-SIR strategy is extended to a distributed Alamouti space-time-coded cooperative *** evaluate the~performance of the proposed HDFSIR strategy,we implement extensive Monte Carlo simulations under varying channel *** demonstrate significant improvements with the hybrid technique outperforming individual DF and SIR strategies in both conventional and distributed Alamouti space-time coded cooperative ***,at a SER of 10^(-3),the proposed NL-SES mapping demonstrated a 3.5 dB performance gain over the conventional averaging one,highlighting its superior accuracy in estimating soft symbols for quadrature phase-shift keying modulation.

关键词： Cooperative communication soft information relaying soft symbols modeling cooperative diversity gain distributed Alamouti space-time code

来源：评论

学校读者我要写书评

暂无评论

mLBOA-DML: modified butterfly optimized deep metric learning for enhancing accuracy in intrusion detection system

引用

Journal of Reliable Intelligent Environments 2023年第3期9卷 333-347页

作者： Prabhakaran, Varun Kulandasamy, Ashokkumar Department of Computer Science and Engineering St.Joseph’s College of Engineering Chennai India Department of Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai India

Intrusion detection is a prominent factor in the cybersecurity domain that prevents the network from malicious attacks. Cloud security is not satisfactory for securing the user’s information because it is based on standard protocols. Hence, cloud users cannot fully trust the security offered by cloud service providers. The state-of-the-art techniques create clusters for classes and manually label the unknown classes to detect novel attacks. This notion binds the network traffic associated with each attack together and drifts the similarity between the same attacks. These techniques are often prone to errors and degrade performance. To overcome this drawback, various researchers have developed different intrusion detection system which relies on specific attack patterns to distinguish between normal and abnormal behavior. This paper presents a modified Lagrange interpolated Butterfly optimization algorithm-based deep metric learning (mLBOA-DML) architecture for intrusion detection to detect both host-based and network attacks. DML architecture parameters are optimized utilizing mLBOA algorithm via its global optimization capability for increasing the accuracy of attack prediction. DML algorithm does both feature extraction and classification processes. When evaluated using the UNSW-NB15 and NSL-KDD datasets, the proposed model offers improved accuracy near 99% for both datasets. © 2023, The Author(s), under exclusive licence to Springer Nature Switzerland AG.

关键词： Intrusion detection

来源：评论

学校读者我要写书评

暂无评论

Enhancing User Experience in AI-Powered Human-computer Communication with Vocal Emotions Identification Using a Novel Deep Learning Method

引用

computers, Materials & Continua 2025年第2期82卷 2909-2929页

作者： Ahmed Alhussen Arshiya Sajid Ansari Mohammad Sajid Mohammadi Department of Computer Engineering College of Computer and Information SciencesMajmaah UniversityAl-Majmaah11952Saudi Arabia Department of Information Technology College of Computer and Information SciencesMajmaah UniversityAl-Majmaah11952Saudi Arabia Department of Computer Science College of Engineering and Information TechnologyOnaizah CollegesQassim51911Saudi Arabia

Voice, motion, and mimicry are naturalistic control modalities that have replaced text or display-driven control in human-computer communication (HCC). Specifically, the vocals contain a lot of knowledge, revealing details about the speaker’s goals and desires, as well as their internal condition. Certain vocal characteristics reveal the speaker’s mood, intention, and motivation, while word study assists the speaker’s demand to be understood. Voice emotion recognition has become an essential component of modern HCC networks. Integrating findings from the various disciplines involved in identifying vocal emotions is also challenging. Many sound analysis techniques were developed in the past. Learning about the development of artificial intelligence (AI), and especially Deep Learning (DL) technology, research incorporating real data is becoming increasingly common these days. Thus, this research presents a novel selfish herd optimization-tuned long/short-term memory (SHO-LSTM) strategy to identify vocal emotions in human communication. The RAVDESS public dataset is used to train the suggested SHO-LSTM technique. Mel-frequency cepstral coefficient (MFCC) and wiener filter (WF) techniques are used, respectively, to remove noise and extract features from the data. LSTM and SHO are applied to the extracted data to optimize the LSTM network’s parameters for effective emotion recognition. Python Software was used to execute our proposed framework. In the finding assessment phase, Numerous metrics are used to evaluate the proposed model’s detection capability, Such as F1-score (95%), precision (95%), recall (96%), and accuracy (97%). The suggested approach is tested on a Python platform, and the SHO-LSTM’s outcomes are contrasted with those of other previously conducted research. Based on comparative assessments, our suggested approach outperforms the current approaches in vocal emotion recognition.

关键词： Human-computer communication(HCC) vocal emotions live vocal artificial intelligence(AI) deep learning(DL) selfish herd optimization-tuned long/short K term memory(SHO-LSTM)

来源：评论

学校读者我要写书评

暂无评论

Weighted PageRank Algorithm Search Engine Ranking Model for Web Pages

引用

Intelligent Automation & Soft Computing 2023年第4期36卷 183-192页

作者： S.Samsudeen Shaffi I.Muthulakshmi Department of Computer Science and Engineering PET Engineering CollegeVallioorTamil Nadu627117India Department of Computer Science and Engineering V.V.College of EngineeringTisaiyanvilaiTamil Nadu627657India

As data grows in size,search engines face new challenges in extracting more relevant content for users’*** a result,a number of retrieval and ranking algorithms have been employed to ensure that the results are relevant to the user’s ***,most existing indexes and ranking algo-rithms crawl documents and web pages based on a limited set of criteria designed to meet user expectations,making it impossible to deliver exceptionally accurate *** a result,this study investigates and analyses how search engines work,as well as the elements that contribute to higher *** paper addresses the issue of bias by proposing a new ranking algorithm based on the PageRank(PR)algorithm,which is one of the most widely used page ranking algorithms We pro-pose weighted PageRank(WPR)algorithms to test the relationship between these various *** Weighted Page Rank(WPR)model was used in three dis-tinct trials to compare the rankings of documents and pages based on one or more user preferences ***ﬁndings of utilizing the Weighted Page Rank model showed that using multiple criteria to rankﬁnal pages is better than using only one,and that some criteria had a greater impact on ranking results than others.

关键词： Weighted pagerank algorithms search engines web pages web crawlers World Wide Web

来源：评论

学校读者我要写书评

暂无评论

A Verifiably Secure and Lightweight Device-to-Device (D2D) Authentication Protocol for the Resource-Constrained IoT Networks

引用

IEEE Access 2025年 13卷 92982-92996页

作者： Alzahrani, Naif University of Jeddah College of Computer Science and Engineering Department of Cybersecurity Saudi Arabia

Due to the growth of Internet of Things (IoT) devices on networks with limited resources, developing a safe and effective authentication method for Device-to-Device (D2D) communication has become necessary. Conventional authentication methods frequently have high communication and processing overhead, which makes them inappropriate for resource-constrained IoT networks. An innovative, lightweight, and verifiably secure D2D authentication protocol designed for resource-constrained IoT networks is proposed in this research. The protocol minimizes energy and computational costs while ensuring strong security by utilizing mutual authentication and effective cryptographic primitives. According to security analysis, the proposed protocol resists widespread attacks, such as DoS, replay, man-in-the-middle, and impersonation attacks. Additionally, the accuracy and security features of the protocol are confirmed by formal verification using commonly used techniques such as the ROR model and ProVerif validation. It is a feasible option for IoT deployments as performance examinations show considerable improvements over current systems regarding energy consumption, communication, computation, storage, and bandwidth utilization. © 2013 IEEE.

关键词： Authentication Protocol

来源：评论

学校读者我要写书评

暂无评论

A semi-supervised deep neuro-fuzzy iterative learning system for automatic segmentation of hippocampus brain MRI

引用

Mathematical Biosciences and engineering 2024年第12期21卷 7830-7853页

作者： Nisha, M. Kannan, T. Sivasankari, K. Department of Computer Science and Engineering Akshaya College of Engineering and Technology Tamil Nadu Coimbatore India Department of Mechanical Engineering Amrita College of Engineering and Technology Tamil Nadu Nagercoil India Department of Electronics and Engineering Akshaya College of Engineering and Technology Tamil Nadu Coimbatore India

The hippocampus is a small, yet intricate seahorse-shaped tiny structure located deep within the brain’s medial temporal lobe. It is a crucial component of the limbic system, which is responsible for regulating emotions, memory, and spatial navigation. This research focuses on automatic hippocampus segmentation from Magnetic Resonance (MR) images of a human head with high accuracy and fewer false positive and false negative rates. This segmentation technique is significantly faster than the manual segmentation methods used in clinics. Unlike the existing approaches such as UNet and Convolutional Neural Networks (CNN), the proposed algorithm generates an image that is similar to a real image by learning the distribution much more quickly by the semi-supervised iterative learning algorithm of the Deep Neuro-Fuzzy (DNF) technique. To assess its effectiveness, the proposed segmentation technique was evaluated on a large dataset of 18,900 images from Kaggle, and the results were compared with those of existing methods. Based on the analysis of results reported in the experimental section, the proposed scheme in the Semi-Supervised Deep Neuro-Fuzzy Iterative Learning System (SS-DNFIL) achieved a 0.97 Dice coefficient, a 0.93 Jaccard coefficient, a 0.95 sensitivity (true positive rate), a 0.97 specificity (true negative rate), a false positive value of 0.09 and a 0.08 false negative value when compared to existing approaches. Thus, the proposed segmentation techniques outperform the existing techniques and produce the desired result so that an accurate diagnosis is made at the earliest stage to save human lives and to increase their life span. © 2024 the Author(s),

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Insider Attack Prevention:LAPUP—Lightweight Authentication Protocol Using PUF

引用

Journal of Communications and Information Networks 2024年第2期9卷 192-206页

作者： Siranjeevi Rajamanickam Satyanarayana Vollala N.Ramasubramanian Department of Computer Engineering Government Polytechnic CollegeTiruchirappalli 620022India Department of Computer Science and Engineering Dr.Shyama Prasad Mukherjee International Institute of Information Technology-Naya RaipurChhattisgarh 493661India Department of Computer Science and Engineering National Institute of TechnologyTiruchirappalli 620015India

The incredible progress in technologies has drastically increased the usage of Web *** share their credentials like userid and password or use their smart cards to get authenticated by the application *** cards are handy to use,but they are susceptible to stolen smart card attacks and few other notable security *** prefer to use Web applications that guarantee for security against several security attacks,especially insider attacks,which is *** of several existing schemes prove the security pitfalls of the protocols from preventing security attacks,specifically insider *** paper introduces LAPUP:a novel lightweight authentication protocol using physically unclonable function(PUF)to prevent security attacks,principally insider *** PUFs are used to generate the security keys,challenge-response pair(CRP)and hardware signature for designing the *** transmitted messages are shared as hash values and encrypted by the keys generated by *** messages are devoid of all possible attacks executed by any attacker,including insider *** is also free from stolen verifier attacks,as the databases are secured by using the hardware signature generated by *** analysis of the protocol exhibits the strength of LAPUP in preventing insider attacks and its resistance against several other security *** evaluation results of the communication and computation costs of LAPUP clearly shows that it achieves better performance than existing protocols,despite providing enhanced security.

关键词： physically unclonable function(PUF) insiderattacks authenticationkeymanagementserver(AKMS) security

来源：评论

学校读者我要写书评

暂无评论

Federated Approach for Privacy-Preserving Traffic Prediction Using Graph Convolutional Network

引用

Journal of Shanghai Jiaotong university(science) 2024年第3期29卷 509-517页

作者： LONARE Savita BHRAMARAMBA Ravi Pimpri Chinchwad College of Engineering Pune 411044India Department of Computer Science and Engineering GITAMViskhapatnam 530045India

Existing traffic flow prediction frameworks have already achieved enormous success due to large traffic datasets and capability of deep learning ***,data privacy and security are always a challenge in every field where data need to be uploaded to the *** learning(FL)is an emerging trend for distributed training of *** primary goal of FL is to train an efficient communication model without compromising data *** traffic data have a robust spatio-temporal correlation,but various approaches proposed earlier have not considered spatial correlation of the traffic *** paper presents FL-based traffic flow prediction with spatio-temporal *** work uses a differential privacy(DP)scheme for privacy preservation of participant's *** the best of our knowledge,this is the first time that FL is used for vehicular traffic prediction while considering the spatio-temporal correlation of traffic data with DP *** proposed framework trains the data locally at the client-side with *** then uses the model aggregation mechanism federated graph convolutional network(FedGCN)at the server-side to find the average of locally trained *** results of the proposed work show that the FedGCN model accurately predicts the *** scheme at client-side helps clients to set a budget for privacy loss.

关键词： federated learning(FL) traffic flow prediction data privacy graph convolutional network(GCN) differential privacy(DP)

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：