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

Deepfake Audio Detection for Urdu Language Using Deep Neural Networks

引用

IEEE Access 2025年 13卷 97765-97778页

作者： Ahmad, Omair Khan, Muhammad Sohail Jan, Salman Khan, Inayat University of Engineering and Technology Department of Computer Software Engineering Mardan Pakistan Arab Open University Faculty of Computer Studies A’Ali732 Bahrain University of Engineering and Technology Department of Computer Science Mardan Pakistan

Audio Deepfakes, which are highly realistic fake audio recordings driven by AI tools that clone human voices, With Advancements in Text-Based Speech Generation (TTS) and Vocal Conversion (VC) technologies have enabled it easier to create realistic synthetic and imitative speech, making audio Deepfakes a common and potentially dangerous form of deception. Well-known people, like politicians and celebrities, are often targeted. They get tricked into saying controversial things in fake recordings, causing trouble on social media. Even kids’ voices are cloned to scam parents into ransom payments, etc. Therefore, developing effective algorithms to distinguish Deepfake audio from real audio is critical to preventing such frauds. Various Machine learning (ML) and Deep learning (DL) techniques have been created to identify audio Deepfakes. However, most of these solutions are trained on datasets in English, Portuguese, French, and Spanish, expressing concerns regarding their correctness for other languages. The main goal of the research presented in this paper is to evaluate the effectiveness of deep learning neural networks in detecting audio Deepfakes in the Urdu language. Since there’s no suitable dataset of Urdu audio available for this purpose, we created our own dataset (URFV) utilizing both genuine and fake audio recordings. The Urdu Original/real audio recordings were gathered from random youtube podcasts and generated as Deepfake audios using the RVC model. Our dataset has three versions with clips of 5, 10, and 15 seconds. We have built various deep learning neural networks like (RNN+LSTM, CNN+attention, TCN, CNN+RNN) to detect Deepfake audio made through imitation or synthetic techniques. The proposed approach extracts Mel-Frequency-Cepstral-Coefficients (MFCC) features from the audios in the dataset. When tested and evaluated, Our models’ accuracy across datasets was noteworthy. 97.78% (5s), 98.89% (10s), and 98.33% (15s) were remarkable results for the RNN+LSTM

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Utilization of Two Cross Two Switch for Bitonic Sorting Circuit

引用

Micro and Nanosystems 2025年第1期17卷 45-57页

作者： Bhattacharjee, Subhasree Sarkar, Soumyadip Das, Kunal Sadhu, Arindam Sarkar, Bikramjit Department of Computer Application Narula Institute of Technology Kolkata India Department of Computer Science Acharya Prafulla Chandra College Kolkata India Department of Electronics & Communication Engineering Greater Kolkata College of Engineering and Management West Bengal India Department of Computer Science & Engineering JIS College of Engineering West Bengal India

Background: The synthesis of reversible logic has gained prominence as a crucial research area, particularly in the context of post-CMOS computing devices, notably quantum computing. Objective: To implement the bitonic sorting circuit, 2x2 switch, is used. The overarching objective of implementing a reversible sorting circuit is to mitigate power consumption while promising secure communication. The successful implementation of the bitonic sorting circuit utilizing the proposed 2x2 switch is validated through simulations conducted in IBM Qiskit. Methods: This study begins by employing the control swap gate to implement a 2x2 switch, aimed at enabling concurrent computing operations within multiprocessor systems to enhance throughput. Subsequently, following the successful implementation of the 2x2 switch, the study proceeds to design a bitonic sorting circuit. Results: Bitonic sort using a 2x2 switch on the IBM Quantum Experience (IBMQ) platform via the QISKit SDK in Python 3.6. Specifically, Qiskit v0.29.0 is utilized, with OpenQASM. OpenQASM serves as the quantum assembly and instruction language. Conclusion: This work presents a methodology for constructing a 2x2 switch, utilizing a reversible control swap gate as its core component. Additionally, it demonstrates the intricate development and implementation of a bitonic sorting circuit, capitalizing on this innovative switch architecture. © 2025 Bentham science Publishers.

关键词： Quantum computers

来源：评论

学校读者我要写书评

暂无评论

Automatic Image Acquisition and Matching in Control System of Near-Field Beam Shaping 8

Automatic Image Acquisition and Matching in Control System o...

引用

8th International Symposium on computer science and Intelligent Control, ISCSIC 2024

作者： Li, Suicheng Shen, Wenwen He, Zizhou Zhou, Chen Li, Li Luo, Jun Institute of Computer Application Caep Department of Computer Engineering and Science Mianyang China

ISBN: (纸本)9798350380286

In the high power laser system of inertial Confinement fusion (ICF), in order to improve the safe operation flux of the system, near-field beam shaping is necessary to output the laser beam with uniform and smooth intensity distribution. Therefore, how to use optical control systems to automatically and efficiently accomplish near-field beamforming is an important issue. The optical control system based on liquid crystal spatial light modulator can control the beam shape and intensity distribution in real time. The control system of near-field beam shaping algorithm mainly includes the modules of light path control, image loading on liquid crystal spatial light modulator, Charge Coupled Device (CCD) nearfield light spot perception and image processing. There is a lot of data exchange between those modules. In the laser system, the manual operation mainly involves two parts: one is the interaction and data exchange between different modules. In the past work, the image data is collected by the operator on different devices, and then the compensation image is calculated on the computing device, and finally loaded into the display device. The whole process is complex, tedious and repetitive. The other is the image matching of input image on spatial light modulator and near-field light spot. This work requires staff to manually match feature points on computing equipment, and the accuracy of matching is difficult to guarantee, which is very time-consuming and labor-intensive. This paper will address the above problems and propose a distributed network architecture to connect different devices in near-field beam shaping and carry out image acquisition from them. In addition, a new image matching algorithm is proposed to extract and match the feature points of input image on spatial light modulator and near-field light spot. It enables the compensation algorithm to be completed automatically to avoid manual operation. © 2024 IEEE.

关键词： Light modulators

来源：评论

学校读者我要写书评

暂无评论

An Experimental Study on Dynamic Lifelong Learning with GPT for Mitigating Catastrophic Forgetting in Aspect-Based Sentiment Analysis

引用

IEEE Access 2025年 13卷 90316-90332页

作者： Huang, Huang Mustafa, Mumtaz Begum Asemi, Adeleh University of Malaya Faculty of Computer Science and Information Technology Department of Software Engineering Kuala Lumpur50603 Malaysia Branch Faculty of Engineering Department of Computer Engineering Isfahan81551-39998 Iran

GPT is widely recognized as one of the most versatile and powerful large language models, excelling across diverse domains. However, its significant computational demands often render it economically unfeasible for individuals and small businesses, underscoring the need for efficient, domain-specific alternatives. In Aspect-Based Sentiment Analysis (ABSA), existing models are typically optimized for single domains, facing challenges in performing effectively across multiple domains. A key issue, known as "catastrophic forgetting,"arises when models trained on one domain lose previously learned knowledge upon exposure to new domain data. This leads to two significant problems: limited cross-domain generalization and difficulty in retaining prior knowledge while learning domain-specific information. To address these challenges, we introduce the Dynamic Lifelong Learning Aspect-Based Sentiment Analysis GPT (DllaGPT), a model designed to handle multiple domains while mitigating catastrophic forgetting. Leveraging datasets from four ABSA domains - Laptops, Restaurants, Tweets, and Finance - this study fine-tunes a pretrained GPT model from HuggingFace sequentially across domains. DllaGPT employs a mechanism to retain real data from earlier domains during new domain training, effectively preserving prior knowledge. Experimental results highlight that DllaGPT achieves an average accuracy of 0.85 and a Backward Transfer (BWT) score of -0.09 across the four domains, showcasing its high accuracy and robust lifelong learning capabilities. © 2013 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

A Collaborative Framework for Intrusion Detection in Cloud Computing Based on HLA-CNN-BiLSTM-SVM Model

A Collaborative Framework for Intrusion Detection in Cloud C...

引用

2024 Asian Conference on Intelligent Technologies, ACOIT 2024

作者： Mogal, Amit K. Sonaje, Vaibhav P. Department of Computer Science & Application School of Computer Science and Engineering Sandip University Nashik India

ISBN: (纸本)9798350374933

In addition to describing a way to make better use of preexisting computer infrastructures, the phrase "cloud computing" describes a technology that facilitates the sale of access to shared computer resources and services. The flip side is that these dispersed and convoluted infrastructures are attractive targets for attackers. Because cyberattacks can reduce the quality of service offered to clients, the system constitute a substantial risk. This proposed method consists of three steps like preprocessing, feature selection, and model training. Data preprocessing, which includes both feature discretization and feature normalization, is a critical step in any knowledge discovery process. In this proposed to evaluate the impact of feature selection on improving classifier algorithm accuracy by comparing two feature selection methods: one that takes linear correlation into account, and another that takes mutual information into account. When training the model, an HLA-CNN-BiLSTM-SVM was utilized. With a 92.35 percent average accuracy, the suggested method surpasses CNN-SVM and BiLSTM. © 2024 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Illumination-Free Clustering Using Improved Slime Mould Algorithm for Acute Lymphoblastic Leukemia Image Segmentation

引用

Journal of Bionic engineering 2023年第6期20卷 2916-2934页

作者： Krishna Gopal Dhal Swarnajit Ray Sudip Barik Arunita Das Department of Computer Science and Application Midnapore College(Autonomous)Paschim MedinipurMidnaporeWest BengalIndia Department of Computer Science and Engineering Maulana Abul Kalam Azad University of TechnologyKolkataWest BengalIndia Department of Computer Science and Engineering Kalyani Government Engineering CollegeKalyaniWest BengalIndia

Partitional clustering techniques such as K-Means(KM),Fuzzy C-Means(FCM),and Rough K-Means(RKM)are very simple and effective techniques for image ***,because their initial cluster centers are randomly determined,it is often seen that certain clusters converge to local *** addition to that,pathology image segmentation is also problematic due to uneven lighting,stain,and camera settings during the microscopic image capturing ***,this study proposes an Improved Slime Mould Algorithm(ISMA)based on opposition based learning and differential evolution’s mutation strategy to perform illumination-free White Blood Cell(WBC)*** ISMA helps to overcome the local optima trapping problem of the partitional clustering techniques to some *** paper also performs a depth analysis by considering only color components of many well-known color spaces for clustering to find the effect of illumination over color pathology image *** and visual results encourage the utilization of illumination-free or color component-based clustering approaches for image ***-KM and“ab”color channels of CIELab color space provide best results with above-99%accuracy for only nucleus ***,for entire WBC segmentation,ISMA-KM and the“CbCr”color component of YCbCr color space provide the best results with an accuracy of above 99%.Furthermore,ISMA-KM and ISMA-RKM have the lowest and highest execution times,*** the other hand,ISMA provides competitive outcomes over CEC2019 benchmark test functions compared to recent well-established and efficient Nature-Inspired Optimization Algorithms(NIOAs).

关键词： Pathology image Image segmentation Clustering Color space White blood cell Optimization Swarm intelligence Fuzzy clustering Rough clustering

来源：评论

学校读者我要写书评

暂无评论

A mathematical multi-objective optimization model and metaheuristic algorithm for effective advertising in the social internet of things

引用

Neural Computing and applications 2025年第6期37卷 4797-4821页

作者： Molaei, Reza Rahsepar Fard, Kheirollah Bouyer, Asgarali Department of Computer Engineering and Information Technology University of Qom Qom Iran Department of Software Engineering Azarbaijan Shahid Madani University Tabriz Iran Department of Software Engineering Faculty of Engineering and Natural Science Istinye University Istanbul Turkey

The integration of social networks with the Internet of Things (IoT) has been explored in recent research, giving rise to the Social Internet of Things (SIoT). One promising application of SIoT is viral marketing, which plays a critical role in modern advertising. However, current solutions proposed for viral marketing are often impractical in real-world scenarios, and there has been limited investigation into viral marketing within the context of SIoT. To address this issue, we present a multi-objective integer linear programming model named ILP-ASoT that facilitates advertising through SIoT. Our approach introduces two realistic parameters: the node sociality rate and the node appropriateness rate as an advertising destination. By balancing the cost of selecting a seed set with the number of users who receive the advertisement, our model offers an appropriate trade-off. Since this is proven as an NP-hard problem, A PSO-based metaheuristic algorithm is proposed to provide near-optimal solutions for advertising in SIoT, called PSO-ASoT. Through simulations, we show that our PSO-ASoT algorithm outperforms state-of-the-art algorithms in several metrics, such as influence spread, advertising cost, and duplicated advertising rate. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Heuristic algorithms

来源：评论

学校读者我要写书评

暂无评论

Advanced Optimized Anomaly Detection System for IoT Cyberattacks Using Artificial Intelligence

引用

computers, Materials & Continua 2024年第2期78卷 1525-1545页

作者： Ali Hamid Farea Omar H.Alhazmi Kerem Kucuk Department of Computer Science Taibah UniversityMedina42315Saudi Arabia Department of Software Engineering Kocaeli UniversityKocaeli41001Turkey

While emerging technologies such as the Internet of Things(IoT)have many benefits,they also pose considerable security challenges that require innovative solutions,including those based on artificial intelligence(AI),given that these techniques are increasingly being used by malicious actors to compromise IoT *** an ample body of research focusing on conventional AI methods exists,there is a paucity of studies related to advanced statistical and optimization approaches aimed at enhancing security *** contribute to this nascent research stream,a novel AI-driven security system denoted as“AI2AI”is presented in this ***2AI employs AI techniques to enhance the performance and optimize security mechanisms within the IoT *** also introduce the Genetic Algorithm Anomaly Detection and Prevention Deep Neural Networks(GAADPSDNN)sys-tem that can be implemented to effectively identify,detect,and prevent cyberattacks targeting IoT ***,this system demonstrates adaptability to both federated and centralized learning environments,accommodating a wide array of IoT *** evaluation of the GAADPSDNN system using the recently complied WUSTL-IIoT and Edge-IIoT datasets underscores its *** an impressive overall accuracy of 98.18%on the Edge-IIoT dataset,the GAADPSDNN outperforms the standard deep neural network(DNN)classifier with 94.11%***,with the proposed enhancements,the accuracy of the unoptimized random forest classifier(80.89%)is improved to 93.51%,while the overall accuracy(98.18%)surpasses the results(93.91%,94.67%,94.94%,and 94.96%)achieved when alternative systems based on diverse optimization techniques and the same dataset are *** proposed optimization techniques increase the effectiveness of the anomaly detection system by efficiently achieving high accuracy and reducing the computational load on IoT devices through the adaptive selection of active features.

关键词： Internet of Things security anomaly detection and prevention system artificial intelligence optimization techniques

来源：评论

学校读者我要写书评

暂无评论

A machine learning approach for skin lesion classification on iOS: implementing and optimizing a convolutional transfer learning model with Create ML

引用

International Journal of computers and applications 2024年第8期46卷 666-685页

作者： Benedek Szabo, Aron Katona, Jozsef Department of Software Development and Application Institute of Computer Engineering University of Dunaujvaros Dunaujvaros Hungary Department of Instrumentation and Automation Institute of Electronics and Communication Systems Kandó Kálmán Faculty of Electrical Engineering Obuda University Budapest Hungary Department of Informatics GAMF Faculty of Engineering and Computer Science Kecskemét Hungary

The integration of machine learning (ML) into mobile applications presents unique challenges, particularly in resource-constrained environments such as iOS devices. Skin lesion classification is a critical task in dermatology, where accurate and efficient diagnostic tools can significantly aid in early detection of malignant lesions. This study aims to implement a machine learning-based iOS mobile application and develop a binary classification model for skin lesion images to determine whether a lesion is malignant. The research utilized Create ML to develop a convolutional neural network optimized for iOS, employing a transfer learning approach. A logistic regression model was cascaded with the convolutional neural network N to enhance classification accuracy. The model's performance was assessed through various validation metrics, ensuring its robustness and efficiency within the constraints of mobile hardware. A curated dataset from the International Skin Imaging Collaboration archive was used for training and testing. The model achieved an accuracy of 92%, a precision of 90%, a recall of 93%, and an F1-score of 91% in classifying skin lesions. These metrics validate the model's efficacy in identifying malignant lesions. Data curation involved collecting, labeling, and preparing a dataset from publicly available sources, ensuring the inclusion of diagnostically relevant features. The final model was integrated into an iOS application using Core ML and Vision frameworks. The developed application demonstrates reliable performance in classifying skin lesions with high accuracy on iOS devices. The inclusion of comprehensive performance metrics justifies the efficacy of the proposed approach. Future work will explore enhancements in model architecture and object detection capabilities to further improve diagnostic precision and application usability. © 2024 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Image recognition

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：