检索结果-内蒙古大学图书馆

5th International Conference on Computational Intelligence in Communications and Business Analytics, CICBA 2023

作者： Ray, Anubhab Singh, Kartikeya Harsh, Aditya Thorat, Shubham Kar, Nirmalya Department of Computer Science and Engineering NIT Agartala Agartala India

ISBN: (纸本)9783031488788

Security in digital world has become a paramount issue, even more so in the post pandemic world when the digital footprint of the world has increased. Multiple encryption techniques are used to ensure the same. Certain famous classical ciphers which were in prevalent use during ancient times are now not robust enough to keep up with security requirements of modern world. This paper analyses the different modifications proposed to one such cipher i.e., Playfair Cipher and how these modifications enhance it’s performance thus making it usable in modern world. © 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Advancing Crime Analysis and Prediction: A Comprehensive Exploration of Machine Learning Applications in Criminal Justice 2

Advancing Crime Analysis and Prediction: A Comprehensive Exp...

引用

2nd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2024

作者： Thoiba Singh, Nongmeikapam Mehra, Muskan Verma, Ishita Singh, Nihal Gandhi, Divyam Ahmad Alladin, Mahid Chandigarh University Department of Computer Science and Engineering Punjab India

ISBN: (纸本)9798350327533

The criminal justice system faces the challenge of effectively combating crime while respecting the rights of individuals. In recent years, machine learning has emerged as a powerful tool to assist law enforcement agencies, legal professionals, and criminal justice systems in addressing this challenge. This research study explores the application of machine learning techniques to various aspects of criminal analysis, including predictive policing, crime forecasting, suspect identification, and risk assessment. In this study, different data sources are used to train and evaluate the learning model, including criminal history data, image analysis, and social media content. The study uses a variety of algorithms, from statistical models to deep learning, to extract insights and patterns from data. This research focuses on the technological aspects of machine learning and decision-making in criminal investigations. The results of our analysis demonstrate the potential of machine learning to increase the effectiveness and efficiency of criminal justice. Predictive police models identify crime hot spots with a high degree of accuracy, allowing law enforcement to allocate resources. Crime prediction models provide insight into preventing future crimes. Crime prediction models provide insight into preventing future crimes. Suspect detection and risk assessment models assist in crime investigation and offender rehabilitation. This research study also emphasizes the importance of ethical considerations in deploying machine learning solutions within the criminal justice system. The study discusses the issues related to bias, fairness, and privacy, emphasizing the need for transparent and accountable algorithms. © 2024 IEEE.

关键词： criminal justice system machine learning predictive police privacy

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study on Resource Aware Allocation and Loadbalancing Techniques for Cloud Computing 14

A Comparative Study on Resource Aware Allocation and Loadbal...

引用

14th International Conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2023

作者： Kamatar, Malatesh Madhavi, P. Bindhu Department of Computer Science and Engineering PDIT Hosapete India Department of Computer Science and Engineering Oxford CE Bangalore India

Advances in cloud networking, cloud infrastructure, and data processing necessitate resource management flexibility. Fault tolerance systems, which include effective load balancing and migration of applications without disturbing any other services operating, should be the key criteria for ensuring the high availability of cloud data centres. Providers of Cloud service should intelligently supply resources to every customers to achieve the optimum resource assignment in changing hosting frameworks. Moreover, many problems in load balancing approaches such as security, fault tolerance, etc exist in today's cloud computing environments. Realizing its relevance and importance, issue of resource aware load balancing in the cloud has received a lot of attention, and numerous load balancing methods is introduced in the literature. Study intends to focus on the survey of many resource aware allocation and load balancing approaches with their advantages and disadvantages. Finally, conclusion with future work is derived a novel technique based on optimization strategy that should guaranteed a drastic improvement in resource utilization on Cloud than existing approaches. © Grenze Scientific Society, 2023.

关键词： Ant colony optimization

来源：评论

学校读者我要写书评

暂无评论

A comparative analysis for deep-learning-based approaches for image forgery detection

International Journal of Systematic Innovation

引用

International Journal of Systematic Innovation 2024年第1期8卷 1-10页

作者： Ch, Ravikumar Radha, Marepalli Mahendar, Maragoni Manasa, Pinnapureddy Department of Artificial Intelligence &Data Science Chaitanya Bharathi Institute of Technology Hyderabad 500075 India Department of Computer Science and Engineering CVR College of Engineering Hyderabad 501510 India Department of Computer Science and Engineering Neil Gogte Institute of Technology Hyderabad 500039 India

The detection of counterfeit photographs is critical in the digital age because of the widespread development of digital media and its significant impact on social networks. The legitimacy of digital content is being threatened by the growing sophistication of picture counterfeiting. With the help of pre-trained VGG-16 models and deep learning techniques that integrate Error Level Analysis (ELA) and Convolutional Neural Networks (CNNs), this study presents a fresh solution to this problem. The study thoroughly assesses and contrasts these models with a dataset that has been carefully chosen to bring the presented findings into perspective. To ensure a reliable evaluation of each model's performance 5000 experiments were carried out in total. With an accuracy rate of 99.87% and an accurate identification rate of 99% of hidden forgeries, the results demonstrate the exceptional effectiveness of the ELA-CNN model. However, despite its robustness, the VGG-16 model only achieves a significantly lower accuracy rate of 97.93% and a validation rate of 75.87%. This study clarifies the relevance of deep learning in the identification of image forgeries and highlights the practical ramifications of various models. Moreover, the research recognizes its constraints, especially for highly advanced counterfeits, and proposes possible paths for enhancing the accuracy and scope of detection algorithms. In the ever-changing world of digital media, the thorough comparative analysis provided in this study offers insightful information that can direct the creation of accurate forgery detection tools, protecting digital content integrity and reducing the effects of image manipulation. © (2023), (Society of Sytematic Innovation). All Rights Reserved.

关键词： Counterfeit images deep learning ELA-CNN Image forgery detection VGG-16 model

来源：评论

学校读者我要写书评

暂无评论

Profit Demand Delegated Proof of Stake: Hypothetical Design Concept for Blockchain

Profit Demand Delegated Proof of Stake: Hypothetical Design ...

引用

2024 IEEE International Conference on Computing, Applications and Systems, COMPAS 2024

作者： Gupta, Udayan Das Haque, Md. Mokammel Reza, Ahmed Wasif Arefin, Mohammad Shamsul Chittagong University of Engineering and Technology Department of Computer Science and Engineering Chittagong Bangladesh Sciences University of Adelaide School of Computer and Mathematical Adelaide Australia East West University Department of Computer Science and Engineering Dhaka Bangladesh

ISBN: (纸本)9798331529765

Delegated Proof of Stake (DPoS) is indeed a fascinating consensus algorithm used on various blockchain platforms. It was designed to address some of the scalability and energy consumption issues associated with Proof of Work (PoW) while maintaining decentralization to a certain extent. But, DPoS has some disadvantages in the distribution of profit share for stake forwarding nodes to delegate nodes. The profit share is controlled by the delegate nodes rather than the staking nodes or token holder voting nodes. Here, in Profit Demand Delegated Proof of Stake (PD-DPoS), we introduced a new mechanism to facilitate the token holder voting nodes to demand a rate of profit/profit share. PD-DPoS will encourage the delegate nodes to invest in infrastructure for high connectivity and fast computing crypto systems. As the system builds targeting fast and reliable computing by extending the opportunity of demanding profit share for token holder voter nodes will experimentally perform and prove better than the DPoS. © 2024 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Analyzing Artificial Intelligence Based Intrusion Detection System in Detecting DDoS Attack 4th

Analyzing Artificial Intelligence Based Intrusion Detection ...

引用

4th International Conference on Smart IoT Systems: Innovations and Computing, SSIC 2023

作者： Kurra, Sai Suchith Rayana, Likhitha Yoosuf, Mohamed Sirajudeen School of Computer Science and Engineering VIT-AP University Andhra Pradesh Amaravati India Department of Mathematics and Computer Science Modern College of Business and Science Muscat Oman

ISBN: (纸本)9789819751990

With the increasing complexity of the cyber-attacks, traditional intrusion systems have become inadequate in effectively detecting and preventing network attacks. Modern machine learning techniques have the capability of preventing sophisticated and aggressive cyber-attacks and have emerged as a promising approach to enhance the accuracy and efficiency of the intrusion detection. This research paper provides a comprehensive analysis and evaluation of the integration of machine learning and deep learning algorithms into intrusion detection system with respect to the Distributed Denial of Service (DDoS) attack. The study begins by presenting an overview of intrusion detection systems, highlighting their importance and significance in safeguarding network infrastructure. Subsequently, it explores supervised machine learning algorithms and deep learning models, such as Random Forest tree, Support Vector Machines (SVM), ResNet and TabNet. The paper presents the pros and cons of existing IDS models with respect to real-time processing, scalability, false positive and false negative results, and IDS vulnerabilities. The above-mentioned algorithms have been trained and evaluated with CICIDS-2017 dataset. The performance metrics used to evaluate the IDS models are accuracy, precision, F1 score, training time of each model, and adaptability to evolving attack patterns. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

NeuroProbe: A Performance Profiling Feed Forward Neural Network Simulator for Hardware Interaction Analysis

引用

SN computer science 2025年第5期6卷 1-22页

作者： Ayyappan, Binu Kumar, G. Santhosh Department of Computer Science Cochin University of Science and Technology Kochi India Department of Artificial Intelligence and Data Science Rajagiri School of Engineering & Technology Kochi India

NeuroProbe is a simple neural network simulator designed by authors specifically for educational purposes focusing on simulating inference phase on a computationally capable embedded hardware, aiming to provide a deeper understanding of hardware interactions and performance improvement. This simulator incorporates performance profiling capabilities, allowing students and educators to analyze and optimize the performance of a simulated trained neural network. By simulating the intricate hardware interactions, NeuroProbe enables users to gain insights into how various components impact the overall performance of neural networks. Using this simulator, learners can experiment with different configurations and architectures, identify potential bottlenecks, and explore optimization strategies to enhance neural network performance before deploying the model on an Edge Computing environment. It also enriches computer science education by enabling learners to gain deeper insights into hardware interactions and performance improvement. By identifying performance bottlenecks, learners can refine their understanding of neural networks and develop skills in optimizing their models for enhanced performance. In conclusion, NeuroProbe empowers users to bridge the gap between theoretical knowledge and practical implementation of neural network on an embedded device, fostering a more comprehensive understanding of neural networks and their hardware requirements. Currently, it is focused solely on single-threaded CPU-based computation enabling SSE, AVX. At present, NeuroProbe does not support SIMD extensions such as AVX-FMA, AVX-512, multi-threaded computation, and accelerators such as NPU, TPU, and GPU. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Hardware–software interactions Neural network simulator NeuroProbe Performance bottlenecks Performance profiling Simulations

来源：评论

学校读者我要写书评

暂无评论

MCM-Llama: A Fine-Tuned Large Language Model for Real-Time Threat Detection through Security Event Correlation 4

MCM-Llama: A Fine-Tuned Large Language Model for Real-Time T...

引用

4th IEEE International Conference on Electrical, computer, and Energy Technologies, ICECET 2024

作者： Diakhame, Mouhamadou Lamine Diallo, Cherif Mejri, Mohamed Gaston Berger University Department of Computer Science Saint Louis Senegal Laval University Department of Computer Science & Software Engineering Quebec Canada

ISBN: (纸本)9798350395914

The correlation of security alerts is crucial for effective threat detection and mitigation in modern cybersecurity landscapes. With the exponential growth in the volume of generated alerts, there arises an imperative to continually develop new, efficient methods for alert correlation. The use of Large Language Models (LLMs) presents new avenues for enhancing real-time threat detection in the field of cybersecurity. In this paper, we introduce MCM-Llama, a fine-tuned language model aimed at improving security event correlation for real-time threat detection. Building upon our prior research, we augment the current framework by integrating MCM-Llama and introducing a novel architecture to practically implement our proposition. In doing so, we replace the correlation module previously based on Named Entity Recognition (NER) and semantic similarity with a fine-tuned Large Language Model (LLM). This transition allows us to capitalize on the advanced capabilities of LLM in comprehending and correlating security events dynamically. Through this enhancement, we aim to significantly improve the accuracy and efficiency of our threat detection system while leveraging the full potential of LLM technology in cybersecurity. Our experimental results validate the efficacy of the proposed approach by significantly improving the correlation rate, thereby reinforcing the pivotal role of Large Language Models (LLMs) in advancing security event correlation and threat detection methodologies. © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Multi-Task Scheduling Method for Information Security of Heterogeneous Big Data Networks Based on Artificial Intelligence Technology 2

Multi-Task Scheduling Method for Information Security of Het...

引用

2nd IEEE International Conference on Sensors, Electronics and computer engineering, ICSECE 2024

作者： Chen, Yiping Zheng, Yingzi Guangzhou Institute of Science and Technology Department of Computer Science and Engineering Guangzhou510540 China

ISBN: (纸本)9798350373646

Multi-task scheduling of heterogeneous big data network information is proposed to improve the optimal configuration and application ability of network big data resources. A multi-task scheduling method of heterogeneous big data network information security based on artificial intelligence technology is proposed. A distributed storage and transmission structure model of heterogeneous big data is established under the task scheduling framework of cloud computing, and the heterogeneous mapping relationship is described according to the task submitted by users and the network information distribution between virtual machines. This paper establishes a scheduling channel between virtual machines and hosts, reasonably places and migrates heterogeneous big data network information to suitable hosts through artificial intelligence technology, and realizes reasonable allocation of computing resources and multi-task scheduling by using weighted polling scheduling method, so as to realize load-balanced scheduling of heterogeneous network information. The simulation results show that this method has good load balance in information task scheduling of heterogeneous big data networks, and the scheduling method has excellent global search and parallel search capabilities, which can adapt to large-scale information optimization of heterogeneous big data networks. © 2024 IEEE.

关键词： Scheduling algorithms

来源：评论

学校读者我要写书评

暂无评论

Prediction of Heart Disease using Data Mining and Machine Learning

Prediction of Heart Disease using Data Mining and Machine Le...

引用

2024 International Visualization, Informatics and Technology Conference, IVIT 2024

作者： Waseemullah Manzoor, Saba Baig, Mirza Adnan Ned University of Engineering and Technology Department of Computer Science and Information Technology Karachi Pakistan Iqra University Department of Computer Science Karachi Pakistan

ISBN: (纸本)9798350354447

In this new generation, cardiac disease is expanding abruptly. The main reason for spreading this disease is the way of life of human beings, such as poor nutrition, absence of activities, medication, smoking, and so on. Today's heart disease is normally happening in individuals, and 85% of people die due to heart disease. There is an enormous amount of data created every single day in the discipline of medication, which is put away in a clinical data bank. This dataset consists of rough data that consists of conflicting and excess information. There is no question about the well-being care framework;they are extremely wealthy in keeping information and yet exceptionally poor in bringing information. Data mining techniques may help in separating significant information by using data mining procedures such as classification, regression method, clustering, and so forth. Later, when the information gathered in the dataset increases and becomes more complicated, data mining algorithms are utilized. The target of this paper is to investigate the different data mining procedures, specifically Random Forest, logistic regression, and SVM, by using an approved dataset for the prediction of heart disease, which includes various characteristics such as age, sexual orientation, chest pain, blood pressure, hyperglycemia, and so on. © 2024 IEEE.

关键词： ANN Classification Dataset Logistic Regression Random Forest SVM

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：