检索结果-内蒙古大学图书馆

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

作者： Nilesh N. Thorat Prashant Dhotre Nilesh Kulal Aarti P Pimpalkar Vijaya S. Patil Sachin M. Kolekar Computer Science & Engineering Department MIT School of Computing MIT Art Design and Technology University Pune Information Technology Department MIT School of Computing MIT Art Design and Technology University Pune

ISBN: (数字)9798350354348

ISBN: (纸本)9798350354355

Concerns with image security exist in every sector that uses digital photographs. Historically, public safety and forensics have depended on images from the crime scene, biometric photos, suspect photos, and other sources. With the development of digital imaging, there has been a significant increase in the use of digital images in this field. Although the use of digital image processing has led to the creation of several new forensic methods of inquiry, it has also simplified picture modification. Digital picture validity is an issue since several snipping and image alteration programs are freely available to the public. It serves as solid proof in many different types of crimes and is utilized as documentation for many purposes. Creating and modifying photos has become easier and more accessible with the development of image manipulation and editing tools. The two most common methods of photo counterfeiting are copy-and-move forgery and image splicing. An image can be spliced, or combined from two photos, to hide or show an error scenario. A section of a picture can be copied and pasted into another image. The many kinds of digital image frauds are examined in this study along with software that detects them. An analysis was done on the methods currently in use for spotting phony photos.

关键词： Reviews Digital images Forensics Splicing Training data Solids Forgery Software Fraud Security

来源：评论

学校读者我要写书评

暂无评论

An Ensemble Framework for Dropout Prediction in Online Learning

An Ensemble Framework for Dropout Prediction in Online Learn...

引用

2022 IEEE International Conference on Knowledge engineering and Communication Systems, ICKES 2022

作者： Srinivasan, Sruthi Dewan, M. Ali Akber School of Computer Science and Engineering Vellore Institute of Technology Chennai India School of Computing and Information Systems Athabasca University Faculty of Sceinece and Technology AB Canada

ISBN: (纸本)9781665456371

Online learning has gained traction over recent years, especially since online education has become more widespread. However, it comes with its own set of challenges of which high dropout is still a major one. Identifying at-risk learners at an early stage is pivotal to offering personalized attention that can potentially prevent them from dropping out from the online courses. This work proposes two methods to analyze students' progress in an online course and subsequently identify dropout prone students. The first method performs fusion of course activity features by concatenating previous weeks' features before training. The second method extracts course activity features from the start date of the courses to a current week instead of concatenating as the first method does. A set of machine learning models and an ensemble framework were trained and tested on these two types of feature sets. On evaluating the models, the benchmark dataset KDDCup15 has been used, where the first method yielded an F1-score 91% while the second method yielded a score 92%. It was observed that both feature fusion methods produce comparable results although we expected that the concatenation of the features over time would produce better results. We also found that using features over a longer duration of time can help in achieving better performance. Further, ensemble model consistently outperformed the base classifiers. © 2022 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

An Explainable Machine Learning-Based Phishing Website Detection using Gradient Boosting

An Explainable Machine Learning-Based Phishing Website Detec...

引用

2024 International Conference on Information technology Research and Innovation, ICITRI 2024

作者： Prayogo, Rizal Dwi Alfisyahrin, Alvin Rizqi Gambetta, Windy Karimah, Siti Amatullah Nambo, Hidetaka Kanazawa University Division of Electrical Engineering and Computer Science Graduate School of Natural Science and Technology Kanazawa Japan Telkom University School of Computing Bandung Indonesia Kanazawa University Faculty of Transdisciplinary Sciences Institute of Philosophy in Interdisciplinary Sciences Kanazawa Japan Institut Teknologi Bandung School of Electrical Engineering and Informatics Bandung Indonesia

ISBN: (纸本)9798350376210

As the need for achieving optimal performance in prediction models, several recent and complex models have been developed. However, many of these models operate as black boxes, providing little insight into their predictive results. In recent years, three gradient-boosting methods based on Decision Trees have been recommended, i.e., XGBoost, CatBoost, and LightGBM. These methods have proven to deliver competitive performance with fast training times. Nevertheless, in critical domains like security, there is a growing need for increased transparency among stakeholders. One pressing concern in the security field is the proliferation of phishing websites. To address this issue, we propose an explainable machine learning-based approach using gradient-boosting methods with hyperparameter optimization on three phishing website datasets. Our best methods surpass the state-of-the-art phishing website detection methods, achieving accuracy rates of 97.45%, 99.16%, and 97.85% for the UCI (2015), Mendeley (2018), and Mendeley (2020) datasets, respectively. Subsequently, we implement posthoc explainability using SHAP and LIME for the selected dataset. The experimental results indicate that three features, i.e., length_url, directory_length, and time_domain_activation, are consistently identified as the most influential features in the dataset. Moreover, our proposed approach demonstrates promising results for detecting phishing websites with both high accuracy and explainability. © 2024 IEEE.

关键词： Phishing

来源：评论

学校读者我要写书评

暂无评论

Converter design For Self-Power Sensor Of Medical Equipments 8

Converter Design For Self-Power Sensor Of Medical Equipments

引用

8th International Conference on Electrical, Electronics and Information engineering, ICEEIE 2023

作者： Aripriharta Aprilia, Tiwi Ananda Purwatiningsih, Ayu Yazid, Muhammad Omar, Saodah Binti Hong, Gwo Jiun Department of Electrical Engineering Malang Indonesia Universitas Negeri Malang Department of Electrical Engineering Malang Indonesia Institut Teknologi Sepuluh Nopember Faculty of Intelligent Electrical and Information Technology Surabaya Indonesia Faculty of Engineering Pulau Pinang Malaysia Southren Taiwan University Department of Computer Science and Information Engineering Tainan City Taiwan

ISBN: (纸本)9798350340501

The system for collecting wasted energy and converted into electrical energy is called an energy harvesting system. This paper focuses on the application of a boost converter to harvest leg muscle energy using a permanent magnet generator. A permanent magnet generator is a medium to convert the energy wasted from the leg muscles due to leg movements into electrical energy. The voltage result reaches 1.7Vac with a total 100 steps in 3 minutes. The output voltage generated by the permanent magnet generator is low-voltage with AC current. Therefore, there are stages of designing a rectifier and boost converter circuit in the self-power generation system. The output voltage generated from the rectifier and boost converter circuit is 5 Vdc. The 5Vdc output voltage will be supplied to the supercapacitor for storage. The supercapacitor charging takes ± 1 hour 25 minutes to full. The distance required to fully charging the supercapacitor reaches 5,500 steps on an average of 4.18 Km. Electrical energy stored in supercapacitors can be used by electronic devices such as sensors, IoT, and others. © 2023 IEEE.

关键词： Permanent magnets

来源：评论

学校读者我要写书评

暂无评论

Application of Adaptive Modulation Strategies for Enhancing Peak Bit Rates in High-Speed Fiber Optic Communication Networks 3

Application of Adaptive Modulation Strategies for Enhancing ...

引用

3rd International Conference on Smart Generation Computing, Communication and Networking, SMART GENCON 2023

作者： Futane, Pravin R. Yadav, Rakesh Kumar Khurana, Saniya Shankar, Amar Kar, Abhijeet Ashok, V. Vishwakarma Institute of Information Technology Department of Information Technology Pune India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India Chitkara University Institute of Engineering and Technology Chitkara University Centre of Interdisciplinary Research in Business and Technology Punjab India Food Technology Faculty of Engineering and Technology Karnataka Bangalore India Vivekananda Global University Department of Computer Science & Engineering Jaipur India Prince Shri Venkateshwara Padmavathy Engineering College Department of Mechanical Engineering Chennai127 India

ISBN: (纸本)9798350319125

Optical communication networks suffer from excessive peak bit quotes today's the physical and environmental constraints present day fiber optic cables. Adaptive modulation techniques offer a potential approach to the trouble with the aid of making an allowance for increased facts throughput with the aid of tailoring the information rate latest the signal to the channel's country. Those techniques have the ability to modify modulation formats and facts fees in real-time to optimize the height bit fee and universal throughput modern the network. This paper examines the software trendy adaptive modulation strategies for enhancing top bit prices in excessive-velocity fiber optic verbal exchange networks and evaluations the to be had strategies for fixing this hassle. The evaluation additionally critiques the present day adaptive modulation algorithms and their overall performance in terms modern-day top bit fee and throughput modern-day the verbal exchange networks. Finally, this paper affords an overview modern day several future research challenges important for further improvements in this discipline. © 2023 IEEE.

关键词： Exchange Modern Modulation Performance Throughput

来源：评论

学校读者我要写书评

暂无评论

Cybersecurity Threats in the Era of AI: Detection of Phishing Domains Through Classification Rules 2

Cybersecurity Threats in the Era of AI: Detection of Phishin...

引用

2nd International engineering Conference on Electrical, Energy, and Artificial Intelligence, EICEEAI 2023

作者： Aljaidi, Mohammad Alsarhan, Ayoub Al-Fraihat, Dimah Al-Arjan, Ahmed Igried, Bashar El-Salhi, Subhieh M. Khalid, Muhammad Al-Na'amneh, Qais Zarqa University Faculty of Information Technology Department of Computer Science Zarqa13110 Jordan The Hashemite University Department of Information Technology Jordan Isra University Faculty of Information Technology Department of Software Engineering Amman11622 Jordan The Hashemite University Faculty of Prince AL-Hussein Bin Abdullah Ii of Information Technology Department of Information Technology Jordan The Hashemite University Department of Computer Science and Applications Zarqa Jordan The Hashemite University P. O Box 330127 Zarqa13133 Jordan University of Hull Department of Computer Sciences and Technology Kingston upon Hull United Kingdom Applied Science Private University Dep. of Cyber Security Amman Jordan

ISBN: (纸本)9798350373363

Phishing is a cyber threat where attackers create deceptive websites or emails to exploit individuals for fraudulent purposes such as providing sensitive information like usernames, passwords, or financial details. Hence, detecting phishing emails is of paramount importance to protect sensitive information, preventing financial losses, protecting against identity theft, and maintaining trust. This study employs machine learning techniques to classify and categorize websites that are used for phishing attacks. To achieve this, we proposed a classification model for the detection of phishing domains based on classification rules. These rules were formulated based on analyzing and distributing them into three classifiers: domain name features, search engine opinion (SEO) information of the domain, and security scans by security vendors. A total of eleven classification rules were formulated which were distributed as follows: six rules for the first classifier, four rules for the second classifier, and one rule for the third classifier. Each classifier feeds its results to the main classifier, which then evaluates the received results based on its rules. Domain names from 222 confirmed phishing URLs were used to test the suggested model. The model demonstrated exceptional performance, achieving an impressive accuracy rate of 99.1% during testing. © 2023 IEEE.

关键词： Websites

来源：评论

学校读者我要写书评

暂无评论

The Power of PDF-to-Audio Summaries in Modern Learning

The Power of PDF-to-Audio Summaries in Modern Learning

引用

Sentiment Analysis and Deep Learning (ICSADL), International Conference on

作者： Dhanshri Kawde Sameer Mendhe Department of Computer Science and Engineering Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research Sawangi Wardha Maharashtra India

ISBN: (数字)9798331523923

ISBN: (纸本)9798331523930

PDF -to-audio based summarization technology is designed to enhance information accessibility and efficiency by transforming long written reports into short, audible summaries. AI, NLP, and TTS technologies that have developed recently have made it possible to extract main points without losing context. Yet, current systems have various shortcomings such as inability to process intricate PDF layouts like tables, charts, and annotations, contextual summarization inaccuracies, robotic or unhuman speech synthesis, and limited customization. Furthermore, the absence of multilingual support and easy integration into various platforms hinders wider adoption. These issues are addressed in this paper with a better approach that employs sophisticated NLP methods, context-sensitive summarization algorithms, and adaptive TTS systems. Our goal is to create a strong, user-oriented solution that provides greater summarization accuracy, personalized speech output, and improved accessibility for a variety of users, such as professionals, students, and the disabled.

关键词： Productivity Sentiment analysis Privacy Layout Transforms Portable document format Real-time systems Text to speech Multilingual Robots

来源：评论

学校读者我要写书评

暂无评论

A Large Scale Dataset for Fire Detection and Segmentation in Indoor Spaces

A Large Scale Dataset for Fire Detection and Segmentation in...

引用

2022 International Conference on Electrical, computer, Communications and Mechatronics engineering, ICECCME 2022

作者： Maric, Petar Arlovic, Matej Balen, Josip Vdovjak, Kresimir Damjanovic, Davor Faculty of Electrical Engineering Computer Science and Information Technology Osijek J. J. Strossmayer University of Osijek Osijek Croatia

ISBN: (数字)9781665470957

ISBN: (纸本)9781665470957

Fire represents a dangerous event, especially in inhabited areas where it can cause extensive economical damage, as well as take human lives, and therefore early fire detection is of utmost importance and requires careful attention. Utilizing images from security cameras and computer vision algorithms, it is possible to detect and raise the alarm in the event of a fire. The existence of similar-colored lights to the flame's color is the greatest obstacle to indoor fire detection when it comes to computer vision. The lights may trigger false positive detections, resulting in false alarms and potential fire suppression by automated systems. By developing a new fire dataset for the training of deep neural networks, we attempted to circumvent the stated issue. Our dataset includes images of different colored lights, images with reflections of light that resemble the color of fire, and images of fire in a variety of environments, including warehouses, factories, shopping malls, residential buildings, offices, etc. Although there are numerous scientific papers and datasets for fire detection, there are not many datasets containing images of indoor fires. In this paper, we show a process of collecting and annotating images representing indoor fire in a manner suitable for deep neural network training. Furthermore, we present the developed Fire Sense image annotation tool and the process of image annotation. The dataset currently consists of more than 11000 annotated images of various types of fires in different environments. © 2022 IEEE.

关键词： Fires

来源：评论

学校读者我要写书评

暂无评论

An optimized facial recognition model for identifying criminal activities using deep learning strategy

引用

International Journal of Information technology (Singapore) 2023年第7期15卷 3907-3921页

作者： Gokulakrishnan, S. Chakrabarti, Prasun Hung, Bui Thanh Shankar, S. Siva Artificial Intelligence Laboratory Faculty of Information Technology Ton Duc Thang University Ho Chi Minh City Viet Nam Deputy Provost ITM SLS Baroda University Gujarat Vadodara India Department of Computer Science and Engineering KG Reddy College of Engineering and Technology (Autonomous) Telangana Hyderabad India

The most important research field in the current period is facial recognition and detection. Furthermore, facial expression recognition applications are essential in various research areas such as criminal investigation, security, data base management systems (DBMS), innovative card application, and video surveillance systems. A criminal investigation is an important area of study. Thus, in today’s world, crime activities are fast expanding in response to psychological trauma. As a result, applying deep learning (DL) algorithms for face expression identification and crime activity monitoring is a growing area of investigation. In terms of pre-processing, feature extraction, and recognizing diverse facial emotions, DL produces better results. As a result, the current study seeks to offer a revolutionary intelligent Strawberry-based convolution neural network (SbCNN). When applied to the Kaggle face expression database, the created SbCNN technique performed best. Face verification and criminal face detection can be accomplished using this approach and the optimization fitness function. Even though the established design improves the robustness of feature extraction and classification, it is a time-consuming process. © 2023, The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of computer Applications and Management.

关键词： Data base management system Deep learning Facial recognition and detection Kaggle Optimization Psychological harm Video surveillance systems

来源：评论

学校读者我要写书评

暂无评论

Speech Detection and Comparison using Different Feature Extraction Method for Correct Verification 3

Speech Detection and Comparison using Different Feature Extr...

引用

3rd International Conference on Communication, Control, and Intelligent Systems, CCIS 2024

作者： Upadhyay, Shrikant Kumar, Binod Singh, Rajan Alam, Md. Irfan Kumari, Barkha Hinz, Binita Roshima Mlr Insitute of Technology Department of Electronics and Communication Engineeing Hyderabad India Jharkhand Rai University Facultyt of Cse & It Ranchi India Mlr Institute of Technology Department of Electronics and Communication Engineering Hyderabad India Jharkhand Rai University Faculty of Cse & It Ranchi India Pune India Rtc Institute of Technology Department of Computer Science and Engineering-Cyber Security Ranchi India

ISBN: (纸本)9798331528201

Mental status through physical appearance identification is not possible as it does not give complete status of any human. Using voice and considering quality extraction of talked it is quite easy to predict the mental behavior and internal variation that will help the doctor related with medical treatment that support them to give proper treatment to person. Hindi is the natural language of India and large community of population talk and speaks this language to exchange and communicate. Various inputs like specific feature, images and vital report of serious person and it is one of the important facts sources for deep training or gaining systems. In this research paper we try to identify the speech signal under different scenario like gun noise, car noise etc. following different feature extraction approaches and compare it for its proper verification. This verification may help to enhance the quality of speech in different adverse scenario and make the speech detection easy. Here, the comparison has been done with various feature extraction method and the results reflects that MFCC has good efficiency of 95% and with a low error rate of 2% compared to other approach. For analysis Hindi voice sample were used for the experimental analysis for 50 samples. © 2024 IEEE.

关键词： Speech enhancement

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：