检索结果-内蒙古大学图书馆

1st International Conference on Intelligent computing, Smart Communication, and Network technologies, ICICSCNT 2023

作者： Preethy Jemima, P. Pretty Diana Cyril, C. Department of Computing Technologies SRM Institute of Science and Technology Chennai India

ISBN: (纸本)9783031759567

Most powerful technology of the trending world is Blockchain. Because of it’s shared, immutable ledger that facilitates the process of recording transactions and tracking assets in a business network. It does not gets limited here, it is widely used in Financial Management and Accounting, Record management in government, Healthcare, Banking, supply chain and so on. In simple terms, Blockchain is a collection of useful information (data). No central authority has the single control on it. Each transaction is documented as a "block" of data as it happens. Every block is interconnected with those that came before and after *** to its decentralized nature, after each and every transaction the block information gets appended in the longest chain and is made transparent to everyone enhancing the trust. But Blockchain is suffering from many cyber attacks. Many solutions are made to increase the level of security. Even in Jan 2019 majority attack has happened in Ethereum classic. The most rare occurrence of the event is the 51% attack (majority attack) which take the control of the hashing rate or hashing power of the network, potentially causing a network disruption. Leading to the cause of Mining Monopoly. Most of the time this happens when the attacker blocks all transactions from a miner in their own private network before broadcasting their own version to the network. The other possibilities of this majority attack can break the basis terms like Reverse transaction, Double spending attack. The attacker takes the control of not confirming some transaction, changing the block rewards, stealing the coins and even creating the coins. The majority assault, also known as the 51% attack, aims to split the blockchain in order to invalidate completed transactions and tamper with data integrity. Our approach is to provide security of blockchain transactions by following the POS (proof of stake) and tightening the network strength by tracing out the anomalous behaviour in the

关键词： Ethereum

来源：评论

学校读者我要写书评

暂无评论

Real-Time Anomaly Detection Without False Positives Using Genetic Algorithm 5

Real-Time Anomaly Detection Without False Positives Using Ge...

引用

5th International Conference on Intelligent Communication technologies and Virtual Mobile Networks, ICICV 2024

作者： Anand, Swati Prabodh, Bansod Malvika Vinoth, N.A.S. Srm Institute of Science and Technology Department of Computing Technologies Kattankulathur India

ISBN: (纸本)9798350385649

This research work addresses the growing significance of Anomaly Detection Systems (IDSs) in ensuring the security of digital systems and networks. The inherent challenge in distinguishing genuine anomalies from benign variations in network traffic demands considerable time and effort from analysts. To address this issue, the study proposes a novel approach that integrates Genetic Algorithm (GA) with machine learning and data mining technologies for real-time anomaly detection with a focus on minimizing false positives. The methodology involves using the genetic algorithm to evolve decision tree-based rules that encapsulate the characteristics of anomalies, enabling the system to autonomously discern between normal and aberrant behavior. By incorporating these rules into the genetic algorithm, the system gains the capability to proactively prevent identified anomalies, going beyond mere detection to actively mitigate potential threats. The research methodology includes creating a diverse dataset representative of network activities and anomalies, iteratively refining decision tree rules through the genetic algorithm, and evaluating the resulting model in real-time scenarios. The innovative amalgamation of genetic algorithms with decision tree-based classification offers a promising avenue for enhancing the efficiency and reliability of IDSs, with potential implications for the broader field of cybersecurity by providing a proactive defense mechanism against network anomalies and fortifying the resilience of digital infrastructures. © 2024 IEEE.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

A Systematic Review of Machine Learning Approaches for Trash Classification 7

A Systematic Review of Machine Learning Approaches for Trash...

引用

7th International Conference on Trends in Electronics and Informatics, ICOEI 2023

作者： Vidhya, S. School of Computing Srm Institute of Science and Technology Department of Computing Technologies Chennai India

ISBN: (纸本)9798350397284

In the fast-moving environment everyone handles different types of trash. A common man to large industries produces trash and it is accumulating everywhere. Recycling the trashes to reduce the source product requirement necessities huge manual work which reduces the recycle conversion efficiency. Since the manual worker needs to pick up the trash and categorize the trash into the respective category will take more time and also it is a tedious process. Instead of manual sorting for recycling, automatic trash classification systems are used These systems classify the trashes based on their texture, material, and natural characteristics. Various hardware and software modules are incorporated into the trash classification process. This study presents a systematic literature review of different trash classification systems and discusses the features of existing systems. Based on the analysis, a detailed summary is presented in the last part of the research work which will help the research community to develop efficient trash classification systems. © 2023 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Efficient Data Access and Streamlined Retrieval: Enhancing Performance in Cloud-Based Systems 2

Efficient Data Access and Streamlined Retrieval: Enhancing P...

引用

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

作者： Prabakaran, K. Sivakumar, B. SRM Institute of Science and Technology Department of Computing Technologies Kattankulathur India

ISBN: (纸本)9798350327533

Accessing data from cloud storage has become an essential part of information management since it simplifies data retrieval and manipulation. However, along with this ease comes possible latency problems and the requirement for quick data retrieval mechanisms. To improve user interactions with a data repository, this work presents a comprehensive system architecture. Specifically, performance evaluation utilizing the 'Global Organization Repository (GOR)' and the 'Retail Sales Benchmark dataset' is the main focus of this research. The Query Transformation Layer is crucial since it translates user-input SQL queries into HiveQL, facilitating effective communication with the Hive Data Repository Layer. The purpose of this layer is to simplify the intricacies of HiveQ Land also utilize a technique for parsing and translating queries. Assessment of the Hive framework highlights difficulties in retrieving data and user satisfaction. The existence of diverse datasets, such as GOR, highlights the necessity for precise query translation. The research improves system performance by addressing the problems and proposing contemporary techniques. The objectives are to improve the Query Transformation Layer to make it more user-friendly, reduce the difficulty in learning HiveQL, and optimize data retrieval for different types of datasets. © 2024 IEEE.

关键词： Cloud-Based Data Storage Hive Pig Query Translation Layer Spark User Interface (UI) Layer

来源：评论

学校读者我要写书评

暂无评论

Movie Recommendation System using DBSCAN Algorithm 9

Movie Recommendation System using DBSCAN Algorithm

引用

9th International Conference on Communication and Electronics Systems, ICCES 2024

作者： Siwach, Devvrat Rakhecha, Falguni Thanigaivelu, P.S. Srm Institute of Science and Technology Department of Computing Technologies Chennai India

ISBN: (纸本)9798350377972

This paper presents a movie recommendation system utilizing the DBSCAN(Density Based Spatial Clustering of Applications with Noise) algorithm. Traditional recommendation system mostly rely on collaborative filtering or content based filtering. The proposed system addresses these challenges by leveraging DBSCAN to identify dense regions in user-item interaction space, allowing for more robust recommendations. Our model demonstrates the effectiveness of the DBSCAN based approach, getting higher accuracy and user satisfaction compared to conventional methods. © 2024 IEEE.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

Stellar Data Analysis and Deep Space Data Analysis System 1

Stellar Data Analysis and Deep Space Data Analysis System

引用

1st IEEE International Conference on Electronics, computing, Communication and Control technology, ICECCC 2024

作者： Praneeth, Narra Kiran, K Chandra Vijaya, K. SRM Institute of Science and Technology Department Of Computing Technologies Chennai India

ISBN: (纸本)9798350371802

This paper focuses on developing an advanced Stellar Data Analysis and Deep Space Data Analysis System, leveraging the power of machine learning and deep learning algorithms. Utilizing cutting-edge techniques such as artificial neural networks, random forest regression, and other sophisticated models as VGG-19,ResNet-50, the system aims to enhance our understanding of celestial phenomena by analysing stellar data. It encompasses the application of these algorithms to decipher complex patterns and anomalies in deep space data, contributing to a more comprehensive comprehension of astronomical observations. The integration of advanced machine learning and deep learning technologies empowers the system to efficiently process vast datasets, providing valuable insights into stellar dynamics, celestial objects, improves celestial object classification by overcoming the vanishing gradient problem, and deep space events. This initiative represents a significant step toward optimizing data analysis methodologies for astronomical research and exploration. © 2024 IEEE.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

AI-Powered Traffic Management: Improving Congestion Detection and Signal Regulation

AI-Powered Traffic Management: Improving Congestion Detectio...

引用

2025 International Conference on Multi-Agent Systems for Collaborative Intelligence, ICMSCI 2025

作者： Malathi, D. Alaswad, Feisal Aljaddouh, Batoul Ranganayagi, Leela Sangeetha, R. Srm Institute of Science and Technology Department of Computing Technologies Kattankulathur Chennai India

ISBN: (纸本)9798331509828

This study presents an innovative approach to managing traffic congestion through an intelligent system that combines advanced congestion detection with adaptive signal control. The system leverages artificial intelligence to process various data sources, including real-time traffic flow, road conditions, and historical data, enabling it to detect congestion patterns with high accuracy. Machine learning algorithms are employed to analyze these patterns, allowing the system to automatically assess congestion levels and optimize signal timing dynamically based on factors such as traffic volume, queue length, and delay. The effectiveness of this approach has been validated through simulation studies, where the system demonstrated impressive performance metrics: an accuracy of 94.89%, a precision of 97.40%, a recall of 96.38%, and an F1 score of 96.76%. These results highlight the system's capability to effectively manage traffic conditions by accurately detecting congestion and minimizing false positives. By integrating these advanced techniques, the proposed solution significantly enhances traffic flow, reduces travel time, and improves the overall driving experience. © 2025 IEEE.

关键词： Travel time

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study on the Implementation of Advanced Neural Networks for Predictive Modelling of Carbon Emissions in India 2

A Comparative Study on the Implementation of Advanced Neural...

引用

2nd IEEE International Conference on Emerging Research in Computational science, ICERCS 2024

作者： Varma, Smridh Menta, Nikshith Alice, K. SRM Institute of Science and Technology Department of Computing Technologies Chennai India

ISBN: (纸本)9798331534950

One of today's most important issues is climate change, primarily due to carbon emissions. Accurate carbon emissions forecasting is crucial in developing countries like India to inform effective policy decisions and reduce environmental harm. This study addresses the gap by modeling and forecasting carbon emissions per capita based on a dataset of 172 data points from 1850 to 2022, with a special focus on emissions in India. The proposed methodology combines efficient pre-processing and data preparation with a thorough model selection process, which includes training models such as RNN, LSTM, Bidirectional LSTM, GRU and CNN-GRU. To enhance the performance of the models, hyperparameter tuning was performed. The models' performance was evaluated using measures including mean square error (MSE), mean absolute error (MAE), and R2. The study successfully advances the use of neural networks for carbon emission prediction, which can aid in the development of climate change policy. © 2024 IEEE.

关键词： Carbon sequestration

来源：评论

学校读者我要写书评

暂无评论

Adaptive grouped balanced binary tree based multi user secure data transmission on cloud

引用

International Journal of Information technology (Singapore) 2025年第2期17卷 941-949页

作者： Pavithra, P. Hariharan, B. Department of Computational Intelligence School of Computing SRM Institute of Science and Technology Kattankulathur India

Secure multi-keyword search for outsourced cloud data has gained popularity, especially for scenarios involving multiple data owners. This work proposes a method for secure multi-keyword searches across encrypted cloud data from various owners, utilizing an administrator or trustworthy third party for key management. The approach employs the TF-IDF model and Vector Space Model (VSM) to generate index and query vectors, and uses an advanced Attribute-Based Encryption (ABE) algorithm for data privacy. The Improved Dingo Optimization Algorithm (IDOA) optimally selects the key value. Encrypted emails are sent to a cloud server, and a Grouped Balanced Binary (GBB) tree structure is used for index construction. The Greedy Depth-First Search (GDFS) method efficiently searches the index, grouping relevant documents to exclude unnecessary ones. Performance is evaluated based on memory usage, execution time, encryption and decryption times, and search times, implemented in Java and tested on a cloud simulator. © Bharati Vidyapeeth's institute of Computer Applications and Management 2024.

关键词： Attribute-based encryption and vector space model Cloud computing Dingo optimization algorithm Multi keyword search scheme Multiple data owner

来源：评论

学校读者我要写书评

暂无评论

Malware Image Classification Using Deep Learning Approach 1

Malware Image Classification Using Deep Learning Approach

引用

1st International Conference on Innovations in Communications, Electrical and Computer Engineering, ICICEC 2024

作者： Yaddala, Sai Harshith Mounika, P. Jothikumar, C. Ashokkumar, Ashokkumar SRM Institute of Science and Technology Department of Computing Technologies Chennai India

ISBN: (纸本)9798350376517

The project aims to address the escalating challenge of malware, a critical threat in the cybersecurity domain. Traditional detection methods are struggling to keep pace with sophisticated, evolving malware attacks. Deep learning offers an innovative approach, leveraging its prowess in pattern recognition to detect and classify malware more effectively. This research involves applying various deep learning algorithms to a substantial dataset of known malware samples, aiming to achieve higher accuracy and faster detection rates compared to traditional methods. The anticipated outcomes include a robust, scalable model capable of adapting to new malware threats, significantly enhancing cybersecurity defenses. This abstract explores the transformative impact of deep learning on malware classification, a critical aspect of cybersecurity. We delve into prevalent deep learning approaches, including the utilization of CNNs for image-based classification and the synergy between deep learning and traditional feature engineering techniques. Additionally, we discuss the potential of hybrid models and the emerging field of dynamic malware analysis utilizing deep learning, highlighting its potential for real-time threat detection. Finally, we emphasize the continuous evolution of the field and the potential for further advancements through the integration of deep learning with other cybersecurity measures. © 2024 IEEE.

关键词： Adversarial machine learning

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：