检索结果-内蒙古大学图书馆

international Symposium on Advanced Computing and Communication (ISACC)

作者： Parth Wani Sachin Chavan Siddhesh Paithankar Diptee Ghusse Sunita Barve School of Computer Engineering MIT Academy of Engineering Pune India

ISBN: (数字)9798331523893

ISBN: (纸本)9798331523909

DeepFake technology, driven by advanced generative models, threatens online authenticity and privacy. This paper presents a comparative analysis of three convolutional neural network (CNN) architectures—VGGFace16, DenseNet-121, and a custom CNN model—for DeepFake image detection. The study utilizes the 140k Faces Dataset, comprising 70,000 real and 70,000 synthetic images, and the Real and Fake Face Detection Dataset from Yonsei University, ensuring a diverse and well-balanced training set while accounting for computational constraints. Feature extraction from the final convolutional layers, dimensionality reduction via Principal component Analysis (PCA), and classification with a Support Vector Machine (SVM) using a polynomial kernel form the core methodology. DenseNet-121 achieved the highest accuracy (97%) on grayscaled images, while the augmented custom CNN balanced accuracy (86%) and interpretability, attaining a Receiver Operating Characteristic Area Under the Curve (ROC-AUC) score of 0.953. PCA visualizations confirmed the models’ ability to distinguish real from fake images. The findings underscore dataset selection’s role in model performance and the necessity of resource-efficient training. Future work will expand dataset diversity, explore cross-dataset validation, and leverage advanced computational resources to enhance generalization, contributing to more robust DeepFake detection systems.

关键词： Support vector machines Training Deepfakes Accuracy Computational modeling Computer architecture Feature extraction Polynomials Convolutional neural networks Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Object Recognition and Audio Tactile System for Visually Impaired

Object Recognition and Audio Tactile System for Visually Imp...

引用

Intelligent Data Communication Technologies and Internet of Things (IDCIoT), international conference on

作者： S. Maheswari S. Mangai J. R Aksharasree S Gobika M Janani S Janani Department of Biomedical Engineering Velalar College of Engineering and Technology Erode Tamil Nadu India

ISBN: (数字)9798331527549

ISBN: (纸本)9798331527556

This design focuses on designing and developing an assistive technology system tailored to the needs of visually impaired individuals, enhancing their daily lives and fostering independence. The system integrates a high-resolution camera module and an ESP32 microcontroller to capture and process images of the user's surroundings using advanced computer vision algorithms programmed in Python. The object recognition component identifies objects and generates audio descriptions, delivered through a speaker module, while a vibration band provides tactile feedback for obstacle detection. Unique vibration patterns corresponding to specific objects or obstacles ensure intuitive navigation and increased confidence for users. The system's technical features, including customizable vibration patterns, clear audio feedback, and a portable design, address key challenges faced by visually impaired individuals, offering a comprehensive, cost-effective, and user-friendly solution to improve mobility and awareness. The system's technical specifications include Python programming, ESP32microcontroller, high-resolution camera module, clear and loud speaker module, and customizable vibration band. The integration of object recognition, audio-tactile feedback, and vibration band creates a assistive technology system that addresses the unique challenges faced by visually impaired individualities.

关键词： Vibrations Navigation Microcontrollers Tactile sensors Assistive technologies programming Cameras Real-time systems Object recognition Python

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Approach for Language Variety Prediction Using BERT and T5 Embeddings

A Hybrid Approach for Language Variety Prediction Using BERT...

引用

Intelligent Data Communication Technologies and Internet of Things (IDCIoT), international conference on

作者： Karunakar Kavuri T. Raghunadha Reddy Archana Gelli B H D D Priyanka Department of CSE Swarnandhra College of Engineering and Technology Narasapuram AP India Department of CSE Matrusri Engineering College Hyderabad Telangana India Department of IT S R K R Engineering College Bhimavaram AP India

ISBN: (数字)9798331527549

ISBN: (纸本)9798331527556

A crucial component of author profiling is language variety prediction, which looks for stylistic and regional differences in language usage in written texts. Applications for this activity are substantial in fields including localization, forensics, and customized marketing. Conventional methods depend on manually created features or embeddings from separate models, which might not fully represent the nuanced linguistic differences. In order to improve language variety prediction performance, we presented a hybrid model in this work that integrates statistical features and embeddings from two sophisticated transformer models, such as T5 (Text-to-Text Transfer Transformer) and BERT (Bidirectional Encoder Representations from Transformers). Different statistical features identified in this work are Lexical features, Syntactic features, Orthographic and Phonological features, Stylistic features, Semantic features, Pragmatic and discourse-level features and Temporal features. The embeddings from both models are projected into a shared dimensions space, averaged, appended, and utilized as input to a downstream classifier in order to accomplish effective integration. This method makes use of T5's generative capabilities and BERT's contextual richness to better capture syntactic and semantic patterns in text. The English language diversity dataset from the PAN 2017 competition is used to test the suggested framework. According to experimental evaluations, the hybrid embedding technique achieves better accuracy and Fl-score for language variety prediction, outperforming individual transformer models by a wide margin. When compared to other models for language variety prediction, the XGBoost classifier with Statistical Features, BERT, and T5 embeddings performed better in terms of Fl-Score (93.4 % ) and Accuracy (93.5 % ). These results demonstrate the importance of including complimentary transformer embeddings to improve author profiling tasks' state-of-the-art performanc

关键词： Location awareness Accuracy Semantics Bidirectional control Predictive models Syntactics Transformers Encoding Internet of Things Pragmatics

来源：评论

学校读者我要写书评

暂无评论

Developing extendible component-oriented finite element software

引用

ADVANCES IN engineering SOFTWARE 2004年第10-11期35卷 703-714页

作者： Dolenc, M Univ Ljubljana Fac Civil & Geodet Engn SI-1000 Ljubljana Slovenia

The component-oriented software development can greatly improve the implementation efficiency and ease the extensibility and maintenance of large engineering software. In this paper, a prototype component-oriented software system for structural analysis using the finite element method is presented. The prototype program is completely based on the component object model that enables the development of modular, object-oriented, customizable and upgradable, distributed programming systems using a number of different programming languages. (C) 2004 Civil-Comp Ltd and Elsevier Ltd. All rights reserved.

关键词： component-oriented software development finite element method component object model extensible markup language object-oriented programming C++ engineering software

来源：评论

学校读者我要写书评

暂无评论

Meta-programming with typed object-language representations

引用

3rd international conference on generative programming and component engineering

作者： Pasalic, E Linger, N Oregon Hlth & Sci Univ OGI Sch Sci & Engn Portland OR 97201 USA

ISBN: (纸本)3540235809

We present two case studies demonstrating the use of type-equality constraints in a meta-language to enforce semantic invariants of object-language programs such as scoping and typing rules. We apply this technique to several interesting problems, including (1) the construction of tagless interpreters;(2) statically checking de Bruijn indices involving pattern-based binding constructs;and (3) evolving embedded DSL implementations to include domain-specific types and optimizations that respect those types.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Sustaining the engineering education and training by real-time systems

Sustaining the engineering education and training by real-ti...

引用

3rd international conference on Education and Information Systems

作者： Letia, Tiberiu S. Tech Univ Cluj Napoca Dept Automat RO-400020 Cluj Napoca Romania

ISBN: (纸本)9789806560345

The paper presents the real-time aspects of education and training applications. Some uses of the real-time system in training are described. The design and building of real-time learning systems are based on object approach, model oriented approach, real-time generating programming and system modeling approach. For these aims some real-time languages, operating systems and tools are available. Some of the real-time training applications are distributed on computers linked through Internet. In this case, real-time communication systems are necessary to fulfill the real-time requirements.

关键词： real-time systems simulation object based approach model oriented approach generative programming and real-time communication

来源：评论

学校读者我要写书评

暂无评论

A generative framework for managed services

引用

3rd international conference on generative programming and component engineering

作者： Peyton, L Rajwani, A Univ Ottawa Sch Informat Technol & Engn Ottawa ON K1N 6N5 Canada

ISBN: (纸本)3540235809

We identify a special category of applications that manage delivery of services by reporting and configuring services based on data collected in the delivery of services. Managed delivery has typically been an aspect of software systems entangled in domain specific application logic. generative approaches, and in particular domain specific languages, have attempted to release application logic from such aspects. We demonstrate that such aspects can be considered applications in their own right. For managed delivery of services, key elements of a generative approach are the domain specialist, reports, metrics, data model, configuration parameters, rules, and template-based generation.

关键词： generative programming templates rules data model metrics managed services

来源：评论

学校读者我要写书评

暂无评论

Generic advice: On the combination of AOP with generative programming in AspectC plus

引用

3rd international conference on generative programming and component engineering

作者： Lohmann, D Blaschke, G Spinczyk, O Univ Erlangen Nurnberg D-8520 Erlangen Germany

ISBN: (纸本)3540235809

Besides object-orientation, generic types or templates and aspect-oriented programming (AOP) gain increasing popularity as they provide additional dimensions of decomposition. Most modem programming languages like Ada, Eiffel, and C++ already have built-in support for templates. For Java and C# similar extensions will be available in the near future. Even though promising, the combination of aspects with generic and generative programming is still a widely unexplored field. This paper presents our extensions to the AspectC++ language, an aspect-oriented C++ derivate. By these extensions aspects can now affect generic code and exploit the potentials of generic code and template metaprogramming in their implementations. This allows aspects to inject template metaprograms transparently into the component code. A case study demonstrates that this feature enables the development of highly expressive and efficient generic aspect implementations in AspectC++. A discussion whether these concepts are applicable in the context of other aspect-oriented language extensions like AspectJ rounds up our contribution.

关键词： Codes (symbols)

来源：评论

学校读者我要写书评

暂无评论

Metaphor: A multi-stage, object-oriented programming language

引用

3rd international conference on generative programming and component engineering

作者： Neverov, G Roe, P Queensland Univ Technol Ctr Informat Technol Innovat Brisbane Qld Australia

ISBN: (纸本)3540235809

This paper presents a language (called Metaphor) for expressing staged programs in a strongly-typed, imperative, object-oriented environment. The language is based on a subset of C* or Java;it is multi-stage and provides static type checking of later stage code. Object-oriented frameworks usually offer a type introspection or reflection capability to discover information about types at run-time. Metaphor allows this reflection system to be incorporated into the language's staging constructs, thus allowing the generation of code based on the structure of types - a common application for code generation in these environments. The paper presents the language, gives a formal description of its type system and discusses a prototype implementation of the language as a compiler targeting the NET Common Language Runtime.

关键词： Codes (symbols)

来源：评论

学校读者我要写书评

暂无评论

A pointcut language for control-flow

引用

3rd international conference on generative programming and component engineering

作者： Douence, R Teboul, L Ecole Mines EMN INRIA Obasco Grp F-44307 Nantes 3 France

ISBN: (纸本)3540235809

In AOP, a pointcut matches base-program execution points where an advice must be executed. Most pointcut are method signatures. In AspectJ, pointcuts based on control-flow (e.g. the method foo when it is called during the method bar) can be defined with a cflow operator which also provides context passing (e.g., when foo is called, print the argument of the pending call to bar). In this article, we propose a pointcut language that extends the pointcut language of AspectJ for control-flow. We exemplify how it enables definition of useful pointcuts based on control-flow with context passing. We provide both an intuitive semantics based on post-mortem execution traces and an implementation based on program instrumentation. We also provide analyses for pointcut conflict and instrumentation optimization.

关键词： Semantics

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：