检索结果-内蒙古大学图书馆

Smart bird identification system based on a hybrid approach: Petri nets, convolutional neural and deep residual networks

引用

Multimedia Tools and Applications 2024年第12期83卷 34795-34823页

作者： Chang, Jen-Chun Chen, Si-Ann Shen, Victor R. L. Department of Computer Science and Information Engineering National Taipei University 151 University Rd. Sanxia District New Taipei City237 Taiwan Department of Information Management Chaoyang University of Technology Taichung City Taiwan

Currently, most people mind the environmental ecology and animal protection. To maintain the ecology of wild animals, the relevant associations have been established. Taiwan is well known for a rich variety of bird species. Certain people love the bird watching activity most around the world. One of the precious wild animals is Taiwan endemic birds. To assist the public in identifying the 30 endemic birds of Taiwan, this study aims to combine Petri nets, You Only Look Once (YOLOv5) and Residual Network (ResNet-50) to develop a smart bird identification system. The identification process consists of three stages. At the first stage, Petri nets are used to model and analyze the system design process. At the second stage, YOLOv5 was used to precisely find the position of a bird in the image and to mark down the bounding box with object detection. At the third stage, ResNet-50 was used to train the classification model of the processed images, to compare the similarity of each image with others, to summarize the Top-5 similar category of each image, and to determine its maximum similarity as a final decision. Finally, the experimental results show that this hybrid approach can achieve an acceptable accuracy, 97.95%. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2023.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Usefulness of Honeypots Towards Data Security: A systematic Literature Review

Usefulness of Honeypots Towards Data Security: A Systematic ...

引用

2023 International Workshop on Artificial Intelligence and Image Processing, IWAIIP 2023

作者： Silaen, Kalpin Erlangga Meyliana, Meyliana Warnars, Harco Leslie Hendric Spits Prabowo, Harjanto Hidayanto, Achmad Nizar Anggreainy, Maria Susan Bina Nusantara University Binus Graduate Program - Computer Science Computer Science Department Jakarta Indonesia Bina Nusantara University School of Information Systems Information Systems Department Jakarta Indonesia Universitas Indonesia Faculty of Computer Science Department of Information System Depok Indonesia

ISBN: (纸本)9798350382914

The increasing data volume given by the exponential growth of digital devices, cloud platforms, and the Internet of Things (IOT) had become an attractive target for attackers. This makes the search for innovative defense mechanisms intensified leading to a renewed focus on the utilization of honeypots to improve data security. This systematic Literature Review (SLR) examines the usage and contributions of honeypots in data security field across diverse sectors and environments. Analyzing 38 selected articles from 2018 to 2023, the study highlights the growing adoption of honeypots as tools for detecting and preventing data breaches, exfiltration, and other security incidents. Our finding found that honeypots, with their deceptive capabilities, have proven could be deployed in sectors like healthcare, cloud computing, and industrial control systems and effective in detection and prevention data breaches, exfiltration, and other data breaches, making them as a crucial tool in the data security protection. The future of honeypots lies in their integration with machine learning and AI, to predict and counteract sophisticated. Moreover, evolving honeypots into tools for deterrence and corrective action opens new avenues for cybersecurity strategies. Their ability to act as deterrents by increasing perceived risks for attackers, coupled with their role in aiding recovery from data breaches through detailed forensic analysis, positions honeypots as a cornerstone in the development of resilient data security frameworks. This study paves the way for a more adaptive, proactive, and comprehensive approach to data security, highlighting the indispensable role of honeypots in the ever-evolving landscape of cybersecurity. © 2023 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Security in the Age of Deepfakes: Detecting Manipulated Media with Neural Networks 1

引用

8th International Conference on information system Design and Intelligent Applications, ISDIA 2024

作者： Phatale, Utkarsh Limkar, Suresh Department of Computer Engineering AISSMS Institute of Information Technology Maharashtra Pune India Department of Computer Science and Engineering Central University of Jammu Jammu and Kashmir India

ISBN: (数字)9789819748921

ISBN: (纸本)9789819748914

The proliferation of deep fake technology presents a substantial peril to both individuals and society, underscoring the urgent requirement for the development of effective deep fake detection techniques. This study introduces a novel methodology that combines convolutional neural networks (CNNs) and deep convolutional generative adversarial networks (DCGANs) in order to improve the detection of deep fake videos. In this study, we present the findings of our research, which involved a comparative analysis of the CNN, recurrent neural network (RNN), and CNN-DCGAN models. The performance evaluation was conducted based on several metrics, including accuracy, sensitivity, specificity, Matthews correlation coefficient (MCC), and Cohen’s Kappa. The accuracy of the DCGAN model reached 99.2%, establishing a benchmark for comparative analysis. Although the CNN and RNN models demonstrate satisfactory performance, the hybrid approach of CNN-DCGAN surpasses them in various metrics, thereby showcasing its potential for effective identification of deep fakes. This study emphasizes the efficacy of integrating convolutional neural networks (CNNs) for extracting features and deep convolutional generative adversarial networks (DCGANs) for generating synthetic data. This advancement holds promise for the development of more sophisticated and dependable deep fake detection systems, particularly in a time where the risk of manipulated media is escalating. © The Author(s).

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Predicting Gold Prices with Rolling Average Representation and Machine Learning 1

Predicting Gold Prices with Rolling Average Representation a...

引用

1st International Conference on Innovative Engineering sciences and Technological Research, ICIESTR 2024

作者： Kannan, Rajkumar Andres, Frederic Muthu, Kalaiarasi Sonai Anutariya, Chutiporn Department of Computer Science Tiruchirappalli India National Institute of Informtics Digital Content and Media Science Tokyo Japan Multimedia University Faculty of Information Science and Technology Malaysia Asian Institute of Technology School of Engineering and Technology Pathum Thani Thailand

ISBN: (纸本)9798350348637

Price prediction and forecasting have been important topics that have been long studied in the financial world. Commodity price prediction is one such highly popular application in stock markets across the world. Among all commodities such as gold, silver, platinum and others, gold has continued to be the prime and forefront commodity which decides the price movements of other commodities. Moving average approach and its variants are the important technical indicators which help financial institutions, investors and traders to understand the movement of gold prices throughout the year. Some of the popular technical indicators are simple moving averages, cumulative moving averages and exponential moving averages. This paper proposes a unique gold price prediction methodology by building popular ensemble machine learning models utilizing all three types of moving average values as feature representation and next day price as the target for prediction. The predicted values based on the three moving average features are presented to users, investors and traders, so that investors and traders will know the gold price for the next day. Extensive experiments are conducted on the Indian gold price daily data from December 2011 to March 2024 by comparing six prominent machine learning models and ARIMA model. We also present a detailed study of different feature importance. Experimental results on the gold price daily data have confirmed that polynomial regression models have given superior performance in terms of regression accuracy and error metrics namely MSE, RMSE and MAE © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Eco-Detect: A Sustainable Solution to Advanced Waste Sorting using AI and IoT 4

Eco-Detect: A Sustainable Solution to Advanced Waste Sorting...

引用

4th International Conference on Ubiquitous Computing and Intelligent information systems, ICUIS 2024

作者： Nandini Prasad, K.S. Manjula, G. Aishwarya, K.J. Chetankumar Prakash, K. N. Bhanu Chandan, V Sai Dayananda Sagar Academy of Technology and Management Department of Information Science and Engineering India Dayananda Sagar Academy of Technology and Management Department of Computer Science and Design India Dayananda Sagar Academy of Technology and Management Department of Information Science and Engineering Bangalore India

ISBN: (纸本)9798331529635

The traditional waste management system, prevalent in many regions, relies heavily on manual sorting processes carried out by human workers. These processes are often labor- intensive and time-consuming, leading to inefficiencies in waste management operations. Manual sorting methods struggle to cope with the increasing volume and complexity of waste generated, resulting in challenges in accurately categorizing and classifying different types of waste materials. This limitation not only hampers the effectiveness of waste sorting but also impedes efforts to maximize recycling rates and minimize environmental impact. In response to the limitations of traditional waste management approaches, the proposed Eco Detect Advanced Waste Sorting system presents a transformative solution. Leveraging the advancements in artificial intelligence and computer vision, this system introduces the utilization of the YOLOv7 algorithm for real-time interference. YOLOv7, renowned for its exceptional accuracy and speed in object detection, is integrated into the waste sorting process to enable rapid and precise identification and classification of diverse waste materials. By employing deep learning methodologies, the system is capable of recognizing a wide array of waste categories, including plastics, paper, glass, metals, and organic materials, with remarkable efficiency. The integration of the YOLOv7 algorithm into the proposed waste sorting system represents a significant advancement in waste management technology. By enabling swift and accurate identification of various waste types, the system facilitates the optimization of recycling practices, promotes the establishment of a circular economy, and contributes to the overall sustainability agenda. Its adaptability and scalability make it well-suited for widespread implementation, addressing the pressing need for sustainable waste management for clean energy solutions on a global scale. Ultimately, the paper envisions a future where te

关键词： Waste utilization

来源：评论

学校读者我要写书评

暂无评论

TensorFlow vs Theano: Issues and Challenges for Natural Language Processing 3

TensorFlow vs Theano: Issues and Challenges for Natural Lang...

引用

3rd IEEE World Conference on Applied Intelligence and Computing, AIC 2024

作者： Dhasmana, Gulshan Praveen Gujjar, J. Guru Prasad, M.S. Devadas, Raghavendra M Hiremani, Vani Divya Shree, N. Department of Computer Science and Engg. Dehradun India Faculty of Management Studies Bengaluru India Manipal Institue of Technology Department of Information Technology Bengaluru India University Symbiosis Institute of Technology Pune India Reva University School of Computing & Information Technology Bengaluru India

ISBN: (纸本)9798350384598

ensorFlow and Theano were popular deep learning frameworks for building and training neural networks, including image classification and NLP models. TensorFlow's evolution from a static graph-based approach to incorporating Eager Execution is examined, shedding light on its impact on ease of use and dynamic operations. Deep learning frameworks play a pivotal role in shaping the landscape of machine learning research and applications. Natural Language Processing (NLP) has witnessed remarkable advancements in recent years, owing much of its progress to deep learning frameworks. This paper presents an in-depth comparative analysis of two influential deep learning frameworks, TensorFlow and Theano, with a specific focus on their issues and challenges in the domain of NLP. Through a comprehensive exploration, this study aims to provide NLP practitioners and researchers with insights to navigate the complexities of framework selection for their linguistic tasks. By distilling the nuances of TensorFlow and Theano in the context of NLP challenges, this research equips NLP practitioners with a well-rounded understanding of the trade-offs and considerations in framework selection. Findings contribute to the informed decision-making process for choosing the appropriate framework based on the specific requirements of NLP tasks. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

IoT-Aided Charity-Redistribution of Excess Food 2

IoT-Aided Charity-Redistribution of Excess Food

引用

2nd International Conference on Emerging Trends in information technology and Engineering, ic-ETITE 2024

作者： Yogananth, V.S. Balasubramani, M. Vellore Institute of Technology Department of Computer Applications Tamil Nadu Vellore India School of Computer Science Engineering and Information Systems Vellore Institute of Technology Tamil Nadu Vellore India

ISBN: (纸本)9798350328202

The utilization of the Internet of Things (IOT) has shown significant potential in various aspects of daily life, yet its application in addressing social issues remains underdeveloped. India, with a substantial number of orphanages, faces challenges in efficiently distributing crucial information, hindering donors from obtaining accurate data on food reserves. This project proposes an IOT-based system to tackle this issue, using Node MCU IOT devices connected to sensors that relay data through a network, accessible and monitorable via web applications. The proposed system architecture aims to bridge the gap between those who waste food and those in poverty who desperately need it. We intend to facilitate food donations by implementing smart containers equipped with IOT technology. These containers can detect excess food waste and share this information via a GSM module with trusted charitable organizations. This application is designed to serve three main stakeholders: service providers, donors, and food recipients in need. By creating smart containers, we ensure that donated food reaches the right individuals. We prioritize collaborating with trusted charities to oversee the distribution process. Only authorized charity members can access and distribute the food stored in these containers, ensuring that it reaches those who need it most. © 2024 IEEE.

关键词： Containers

来源：评论

学校读者我要写书评

暂无评论

Binary and Multi-Class Classification on the IoT-23 Dataset

Binary and Multi-Class Classification on the IoT-23 Dataset

引用

2023 Advances in science and Engineering technology International Conferences, ASET 2023

作者： Ahli, Alia Raza, Ayesha Akpinar, Kevser Ovaz Akpinar, Mustafa Rochester Institute of Technology Computing Security Department Dubai United Arab Emirates Higher Colleges of Technology Faculty of Computer Information System Sharjah United Arab Emirates

ISBN: (纸本)9781665454742

In the recent years, Internet of Things (IoT) technology has become widespread and is commonly used by organizations for many different purposes. With the increase in the demand for this technology, new security challenges arise. It becomes difficult for cybersecurity experts to administer security measures and prevent the IoT network from malicious attacks. This paper proposes the use of machine learning algorithms - Random Forest (RF), Multi- layer Perceptron (MLP) and Gradient Boosting (GB) to detect malicious traffic flows and anomalies in the IoT network. For this purpose, Aposemat IoT-23 dataset is used, and the models are built, trained and tested on it. Two types of classification are considered - binary and multi-label. Random Forest and Gradient Boosting classifier were able to achieve high accuracies of 98.6% and 97.7% respectively. © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Forecasting the Impact of Deep Learning on Data science Practices: A Comprehensive Analysis 15

Forecasting the Impact of Deep Learning on Data Science Prac...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Acharjya, Kalyan Devaraj Verma, C. Umamaheswari, B. Shelke, Priya M. Kumar, Mukesh Maharishi University of Information Technology Maharishi School of Engineering and Technology Uttar Pradesh India Faculty of Engineering and Technology Department of Computer Science and Engineering Karnataka Ramnagar District562112 India Prince Shri Venkateshwara Padmavathy Engineering College Department of Computer Science and Engineering Chennai127 India Vishwakarma Institute of Technology Department of Information Technology Pune India Vivekananda Global University Department of Mechanical Engineering Jaipur India

ISBN: (纸本)9798350370249

It comprehensively discusses the effect of deep mastering on data technology practices. Deep studying has advanced to become a powerful tool for information mining, pattern recognition, and feature engineering. It is miles information scientists are increasingly using the accuracy and efficiency of information science initiatives. Furthermore, the era has stepped forward hastily to one of these excessive levels. Many leading facts scientists throughout numerous domains have begun to contain deep mastering into their facts technological know-how workflows. In this paper, we examine and forecast the modern-day and destiny impact of deep gaining knowledge of data technology practices. We start by analyzing the distinct advantages of deep learning, including progressed accuracy, reduced guide attempt, more suitable automation, and advanced scalability. We then become aware of extraordinary applications in which deep learning is being applied and evaluate its impact on the respective information science pipelines. Sooner or later, we provide a comprehensive forecast of the capability applications of deep getting to know within the records technology subject inside the near and far destiny. Notably, we recall the capacity of deep studying to force essential modifications in how information mining, analytical choice-making, and large records packages. Through our analysis, we will forecast the ability of deep studying to revolutionize statistics technological know-how practices in extraordinary ways. © 2024 IEEE.

关键词： Automation Practices Processing technology Unprecedented

来源：评论

学校读者我要写书评

暂无评论

Adaptive Attribute-Based Honey Encryption: A Novel Solution for Cloud Data Security

引用

computers, Materials & Continua 2025年第2期82卷 2637-2664页

作者： Reshma Siyal Muhammad Asim Long Jun Mohammed Elaffendi Sundas Iftikhar Rana Alnashwan Samia Allaoua Chelloug School of Computer Science and Engineering Central South UniversityChangsha410083China EIAS LAB College of Computer and Information Sciencesand Center of Excellence in Quantum and Intelligent ComputingPrince Sultan UniversityRiyadh11586Saudi Arabia Gianforte School of Computing Montana State UniversityBozemanMT 59717USA Department of Information Technology College of Computer and Information SciencesPrincess Nourah Bint Abdulrahman UniversityRiyadh11671Saudi Arabia

A basic procedure for transforming readable data into encoded forms is encryption, which ensures security when the right decryption keys are used. Hadoop is susceptible to possible cyber-attacks because it lacks built-in security measures, even though it can effectively handle and store enormous datasets using the Hadoop Distributed File system (HDFS). The increasing number of data breaches emphasizes how urgently creative encryption techniques are needed in cloud-based big data settings. This paper presents Adaptive Attribute-Based Honey Encryption (AABHE), a state-of-the-art technique that combines honey encryption with Ciphertext-Policy Attribute-Based Encryption (CP-ABE) to provide improved data security. Even if intercepted, AABHE makes sure that sensitive data cannot be accessed by unauthorized parties. With a focus on protecting huge files in HDFS, the suggested approach achieves 98% security robustness and 95% encryption efficiency, outperforming other encryption methods including Ciphertext-Policy Attribute-Based Encryption (CP-ABE), Key-Policy Attribute-Based Encryption (KB-ABE), and Advanced Encryption Standard combined with Attribute-Based Encryption (AES+ABE). By fixing Hadoop’s security flaws, AABHE fortifies its protections against data breaches and enhances Hadoop’s dependability as a platform for processing and storing massive amounts of data.

关键词： Cybersecurity data security cloud storage hadoop encryption and decryption privacy protection attribute-based honey encryption

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：