检索结果-内蒙古大学图书馆

7th International Conference on Electronics, Communication and Aerospace technology, ICECA 2023

作者： Arthi, A. Aggarwal, Kapil Karthikeyan, R. Kayalvili, S. Srimathi, S. Srivastava, Aviral Rajalakshmi Institute of Technology Department of Artificial Intelligence and Data Science Chennai India Department of Computer Science & Engineering Guntur Andhra Pradesh Vaddeswaram522302 India Dr NGP Institute of Technology Department of Artificial Intelligence and Data Science Coimbatore India Artificial Intelligence College Name & Address: Kongu Engineering College Perundurai India Saveetha School of Engineering SIMATS Department of Bio Technology Tamilnadu Chennai India Amity University Rajasthan Jaipur300202 India

ISBN: (纸本)9798350340600

Android mobile applications and devices can be extremely utilized and employed in industry and smart cities. Malware recognition is an efficient and powerful method for assurance security of Android schemes, mainly for industrial platforms and smart cities. In recent times, research utilizing machine learning (ML)-based approaches for Android malware recognition enhanced quickly. However, one of the performed methods to accomplish feature selection and analysis, so-called feature engineering is labour-intensive and depends on artificial knowledge. Therefore, this study presents a Hybrid Multimodal Machine Learning Driven Android Malware Recognition and Classification (HM3-AMRC) model. The proposed HM3-AMRC technique recognizes and categorizes the Android malware accurately and efficiently. In the presented HM3-AMRC technique, initial phase of data preprocessing is performed. Next, the classification process takes place using three ML techniques such as gradient boosting decision tree (GBDT), extreme learning machine (ELM), and multilayer perceptron (MLP). Moreover, Bayesian optimization (BO) technique is employed for optimal parameter selection of the ML approaches. The stimulation analysis of the HM3-AMRC method is tested on Android malware dataset. Extensive comparison analysis highlighted the betterment of the HM3-AMRC method over existing techniques. © 2023 IEEE.

关键词： Android malware

来源：评论

学校读者我要写书评

暂无评论

SourcePlag - Source Code Plagiarism Detection Based on Abstract Syntax Trees

SourcePlag - Source Code Plagiarism Detection Based on Abstr...

引用

Blockchain and Distributed Systems Security (ICBDS), IEEE International Conference on

作者： Nakul Sharma Siddharth Shinde Swarup Bhosale Suyog Patil Department of Artificial Intelligence and Data Science Faculty of Engineering Vishwakarma Institute of Information Technology Pune India Department of Artificial Intelligence and Data Science Student of Engineering Vishwakarma Institute of Information Technology Pune India

ISBN: (数字)9798350354348

ISBN: (纸本)9798350354355

Code plagiarism poses a significant challenge in programming communities, necessitating effective detection mechanisms. This paper introduces a novel system that employs Abstract Syntax Trees (ASTs) for code representation and comparison. The system utilizes ASTs to capture the structural essence of code, facilitating a comprehensive analysis of code similarity, it offers flexibility for application across multiple programming languages. In addition to leveraging the Levenshtein Distance Algorithm for Python code comparison, the system incorporates node counting for other languages such as Java and C/C++. By integrating AST-based representation and a combination of comparison techniques, the system offers a robust solution for identifying plagiarized code instances accurately across various programming environments. Through a detailed exploration of the system's methodology, this paper underscores its potential to address the pervasive issue of code plagiarism in programming communities.

关键词： Java Codes Plagiarism Source coding Syntactics Programming Security Reliability Python Testing

来源：评论

学校读者我要写书评

暂无评论

An effective compressed image authentication scheme based on N-variant AMBTC

引用

Multimedia Tools and Applications 2024年第2期83卷 3801-3829页

作者： Su, Guo-Dong Chang, Chin-Chen Lin, Chia-Chen School of Big Data and Artificial Intelligence Fujian Polytechnic Normal University Fuzhou350300 China Department of Information Engineering and Computer Science Feng Chia University 100 Wenhwa Road Seatwen Taichung40724 Taiwan Department of Computer Science and Information Engineering National Chin-Yi University of Technology Taichung41170 Taiwan

Image authentication is one technique that provides integrity protection for digital images, making them sensitive to any slight modification. Recently, the detectability of absolute moment block truncation coding (AMBTC) compressed images has been attracting more attention due to its integrity authentication concerns. Thus, this paper proposes an effective N-variant AMBTC based image authentication scheme for AMBTC compressed images. First, a novel AMBTC compression code is derived using a variant AMBTC technique that can provide a better quality of compressed images. Then, each AMBTC compression code is further eliminated into a version requiring fewer bits using the proposed N-variant AMBTC technique, and those vacated N-bits are used to conceal authentication codes, which is generated by hashing the AMBTC compression code and location information. Experimental results confirm that the proposed scheme has superior stability and accuracy in tampering detection while providing better visual quality of the watermarked image. © 2023, The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Integrating Enhanced Security Protocols with Moving Object Detection: A Yolo-Based Approach for Real-Time Surveillance 2

Integrating Enhanced Security Protocols with Moving Object D...

引用

2nd International Conference on Cyber Resilience, ICCR 2024

作者： Al-E'mari, Salam Sanjalawe, Yousef Alqudah, Hamzah University Of Petra Faculty Of Information Technology Information Security Department Amman Jordan American University Of Madaba Faculty Of Information Technology Cybersecurity Department Amman Jordan American University Of Madaba Faculty Of Information Technology Department Of Data Science And Artificial Intelligence Amman Jordan

ISBN: (纸本)9798350394962

This paper presents a novel approach to enhancing real-time surveillance systems using an augmented YOLO (You Only Look Once) v8 architecture. The primary focus is on integrating advanced security features into the YOLO framework to improve the detection and analysis of moving objects in various surveillance scenarios. The key enhancements include the implementation of an Anomaly Detection Layer, the integration of Behavior Analysis Algorithms, and the enhancement of Real-Time data Processing capabilities. These modifications are designed to increase the accuracy of threat detection while maintaining the high processing speeds essential for real-time applications. The Anomaly Detection Layer utilizes unsupervised learning algorithms to identify deviations from normal patterns, enabling the system to flag potential security threats that might otherwise go unnoticed. The Behavior Analysis Algorithms are incorporated to analyze movement patterns and identify suspicious behaviors, adding a layer of contextual understanding to object detection. To ensure the practicality of these enhancements, the model is optimized to handle live video feeds with minimal latency, maintaining an average processing speed of 45 frames per second. The experimental setup involved testing the enhanced YOLO v8 model in various simulated and real-world environments, comparing its performance with standard YOLO v8 and other existing surveillance models. The results demonstrated a significant improvement in detection accuracy, particularly in identifying anomalous behaviors and potential threats. The enhanced model outperformed the baseline models in various complex scenarios, including crowded public spaces and high-activity zones. This research contributes to the field of surveillance technology by offering a more sophisticated and efficient tool for public safety and security applications. It highlights the potential of integrating advanced AI features into existing object detection frameworks

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Building a Robust Machine Translation System for Punjabi to English Using Deep Learning Approaches 4

Building a Robust Machine Translation System for Punjabi to ...

引用

4th International Conference on Technological Advancements in Computational sciences, ICTACS 2024

作者： Nisha Chhabra, Megha Abidi, Ali Imam Setia, Sonia Maurya, Ajay Anjli, Km. Noida Institute of Engineering and Technology Department of Data Science U.P. Greater Noida India School of Engineering and Technology Sharda University Department of Computer Science & Engineering U.P. Greater Noida India Poornima Institute of Engineering and Technology Department of Artificial Intelligence and Data Science Rajasthan Jaipur India Delhi New Delhi India

ISBN: (纸本)9798350387490

In the dynamic realm of artificial intelligence, the evolution of Machine Translation Systems (MTS) for Indian languages faces unique challenges due to linguistic diversity. The diversity of morphology and the inherited dialects make it difficult to translate. The translation can be improved with pre-processing and optimization of MTS. Our MTS proposes the steps to improve the translation of Punjabi to English by employing two models, one with a Gated Recurrent Unit (GRU) layer and another with a Long Short-Term Memory (LSTM) layer. Another step involves Hyperparameter tuning to reduce complexity and increase model's efficiency. The experimentation shows accuracy rate on Samanantar dataset. The research aims to provide solutions to gaps identified in MTS for Punjabi, contributing to the advancement of machine translation technology in Punjabi's linguistic landscape. © 2024 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

A Novel AI-based Hybrid Ensemble Segmentation CAD System for Lumber Spine Stenosis pathological Regions Using MRI Axial Images 8

A Novel AI-based Hybrid Ensemble Segmentation CAD System for...

引用

8th International artificial intelligence and data Processing Symposium, IDAP 2024

作者： Salem, Saied Mukhlis, Raza Katar, Oguzhan Ertugrul, Bilal Yildirim, Ozal Al-Antari, Mugahed A. Sejong University College of Ai Convergence Department of Artificial Intelligence and Data Science Seoul05006 Korea Republic of Firat University Faculty of Technology Department of Software Engineering Elazig Turkey Firat University Faculty of Medicine Department of Neurosurgery Elaziǧ Turkey

ISBN: (纸本)9798331531492

Lumbar Spinal Stenosis (LSS) is a condition where the spinal canal in the lower back becomes narrower, resulting in pressure on the spinal cord and nearby nerves. To predict LSS, neurologists focus on four key regions in MRI axial scans: the Intervertebral Disc (IVD), Thecal Sac (TS), Posterior Element (PE), and the Area between the Anterior and Posterior (AAP) vertebrae. To delineate these regions, we present a novel hybrid ensemble deep learning CAD system for multi-class segmentation, encompassing data collection, preprocessing, automated hyperparameter optimization and selection, segmentation ensemble learning, and both qualitative and quantitative performance evaluation. The core of the proposed pipeline features two ensemble phases: (1) ensemble learning through feature space fusion of three distinct AI models (SwinUNETR, Attention Unet, and UNet++), and (2) ensemble learning via a stacking method of the feature maps outputs from the same AI models used in phase 1. The Mendeley benchmark dataset is employed to train and assess both CAD systems, while a private dataset from Firat University Hospital in Turkey is used for verification and validation. The best achieved results via FFA's mean dice score is 93.1% and mean IoU is 87.76%. showing the usefulness of using ensemble methods to capture different features from the trained models. © 2024 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Life Expectancy Prediction Based on Particle Swarm Optimization Support Vector Machine Regression 3

Life Expectancy Prediction Based on Particle Swarm Optimizat...

引用

3rd IEEE International Conference on Electrical engineering, Big data and Algorithms, EEBDA 2024

作者： Guo, Zhaodong Que, Yuanxi Li, Xiang College of Artificial Intelligence and Data Science Hebei University of Technology Tianjin China College of Computer Science & Software Engineering Shenzhen University Shenzhen China College of Computer Science Nankai University Tianjin China

ISBN: (纸本)9798350380989

This study delves into the application of Particle Swarm Optimization (PSO) algorithms in the parameter optimization of Support Vector Regression (SVR) models to enhance the accuracy of predicted average life expectancy. An adaptive PSO algorithm augmented with random perturbations is introduced. Through a fitness-function-guided dynamic adjustment mechanism, this method circumvents the premature convergence issue typical of conventional PSO, locating the optimal penalty parameter C and kernel parameter for the SVR model. These parameters are then incorporated into the SVR model for training and regression prediction, achieving optimal data fitting and generalization effects. Comparative analysis reveals that the PSO-enhanced SVR model outperforms the traditional SVR across various performance metrics. Notably, there is a marked improvement in the coefficient of determination, a significant re-duction in root mean square error, and mean absolute percentage error, affirming the advancements of the improved PSO-SVR model in prediction accuracy and reliability. © 2024 IEEE.

关键词： Composite Model PSO PSO-SVR SVM

来源：评论

学校读者我要写书评

暂无评论

SPEAR: Design and Implementation of an Advanced Virtual Assistant 4

SPEAR: Design and Implementation of an Advanced Virtual Assi...

引用

4th International Conference on Sustainable Expert Systems, ICSES 2024

作者： Jain, Garima Shukla, Amita Bairwa, Nitesh Kumar Chaudhary, Anamika Patel, Ashish Jain, Ankush Noida Institute of Engineering and Technology Department of Computer Science and Buisness Systems Greater Noida India Noida Institute of Engineering and Technology Department of Artificial Intelligence Greater Noida India Noida Institute of Engineering and Technology Department of Data Science Greater Noida India Dronacharya Group of Institutions Department of Artificial Intelligence and Machine Learning Greater Noida India Netaji Subhash University of Technology Department of Computer Science and Enginnering Delhi India

ISBN: (纸本)9798331540364

This research presents the development and evaluation of SPEAR, an advanced voice-activated personal desktop assistant designed to address challenges in existing virtual assistant technology, such as limited language support, low recognition accuracy, and inadequate task automation. Despite recent advancements in Natural Language Processing (NLP) and machine learning, implementation in current systems remains subpar. SPEAR achieves an 88% overall command execution success rate, with a speech recognition accuracy of 92% and an average response time of 1.8 seconds, demonstrating efficiency in real-time interactions. Developed using Python and machine learning libraries, SPEAR supports 15 voice commands across multiple platforms, excelling in note creation (95% success), web searching (94%), and information retrieval (92%). Its natural language understanding score of 0.86 and context retention rate of 75% highlight its conversational capabilities. While the assistant performs well in messaging functionality (85% success) and currently supports three languages, expanding its multilingual capabilities is essential for broader user engagement. Metrics indicate a satisfaction score of 8.2/10 and an average of 12 daily interactions per user, showcasing its practical utility. Additionally, the system's text-to-speech quality (8.5/10) and error recovery rate (82 %) affirm its robustness. These findings contribute valuable insights for future research, focusing on enhancing multilingual support, broadening task categories, and improving context retention, ultimately positioning SPEAR to rival established industry leaders by offering a comprehensive suite of services. © 2024 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

LLM4Decompile: Decompiling Binary Code with Large Language Models

LLM4Decompile: Decompiling Binary Code with Large Language M...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Tan, Hanzhuo Luo, Qi Li, Jing Zhang, Yuqun Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China Department of Computing The Hong Kong Polytechnic University Hong Kong Research Centre for Data Science & Artificial Intelligence Hong Kong

ISBN: (纸本)9798891761643

Decompilation aims to convert binary code to high-level source code, but traditional tools like Ghidra often produce results that are difficult to read and execute. Motivated by the advancements in Large Language Models (LLMs), we propose LLM4Decompile, the first and largest open-source LLM series (1.3B to 33B) trained to decompile binary code. We optimize the LLM training process and introduce the LLM4Decompile-End models to decompile binary directly. The resulting models significantly outperform GPT-4o and Ghidra on the HumanEval and ExeBench benchmarks over 100% in terms of re-executability rate. Additionally, we improve the standard refinement approach to fine-tune the LLM4DecompileRef models, enabling them to effectively refine the decompiled code from Ghidra and achieve a further 16.2% improvement over the LLM4Decompile-End. LLM4Decompile demonstrates the potential of LLMs to revolutionize binary code decompilation, delivering remarkable improvements in readability and executability while complementing conventional tools for optimal results. © 2024 Association for Computational Linguistics.

关键词： Binary codes

来源：评论

学校读者我要写书评

暂无评论

Prediction of Alzheimer’s Disease Using Adaptive Fine-Tuned Deep Resnet-50 with Attention Mechanism

引用

SN Computer science 2024年第4期5卷 392页

作者： Venkatesh, R. Anantharajan, Shenbagarajan Gunasekaran, Shenbagalakshmi Yogaraja, C.A. Gethzi Ahila Poornima, I. Computer Science and Engineering Ramco Institute of Technology Rajapalayam Tamil Nadu Virudhunagar 626117 India Artificial Intelligence and Data Science Mepco Schlenk Engineering College Sivakasi Tamilnadu Virudhunagar 626005 India Computer Science and Engineering Mepco Schlenk Engineering College Sivakasi Tamilnadu Virudhunagar 626005 India

Alzheimer’s disease (AD) sufferers can benefit from early detection and diagnosis so that protective treatments can be taken before permanent brain impairment develops. Magnetic resonance imaging (MRI)-detected lesion sites in AD patients exhibit significant heterogeneity and these characteristics are spread throughout the imaging space, according to cross-sectional imaging studies of Alzheimer's disease. Because conventional Deep Learning (DL) methods can’t generate enough long-distance correlations in the characteristic space, adaptive fine-tuned deep resnet-50 with attention mechanism (AFDR-AM) is introduced in this research for the early identification of AD. The input MRI data is de-noised using a wavelet thresholding approach, and the contrast is enhanced using Improved Color Histogram Equalization (ICHE). Image recognition and classification characteristics are extracted at the feature extraction phase using a Gabor Filter Bank (GFB). To narrow down a big list of traits, the artificial Bee Colony Optimization (ABCO) technique can be used to pick the most useful ones and get rid of the rest. Measures of accuracy, precision, recall, f1-score, specificity, and MSE are used to evaluate the effectiveness of the suggested strategy. Comprehensive experiments reveal that our approach achieved the best performance compared to other approaches. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd 2024.

关键词： AFDR-AM Alzheimer’s disease (AD) artificial Bee colony optimization (ABCO) Deep learning (DL) Gabor filter bank (GFB) Improved color histogram equalization (ICHE) Magnetic resonance imaging (MRI)

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：