检索结果-内蒙古大学图书馆

International Conference on Applied Mathematics & computer Science (ICAMCS)

作者： Veska Gancheva Department of Programming and Computer Technologies Faculty of Computer Systems and Technologies Technical University of Sofia Sofia Bulgaria

A rising variety of platforms and software programs have leveraged repository-stored datasets and remote access in recent years. As a result, datasets are more vulnerable to malicious attacks. As a result, network security has grown in importance as a research topic. The usage of intrusion detection systems is a well-known strategy for safeguarding computer networks. This paper proposes an anomaly detection method that blends rule-based and machine-learning-based methods. In order to construct the appropriate rules, a genetic algorithm is utilized. Principal component analysis is used to extract the relevant features aimed to improve the performance. The suggested method is validated experimentally using the KDD Cup 1999 dataset, which meets the requirement of using appropriate data. The proposed method is applied to detect and analyze four types of attacks in a well-known benchmark dataset: Neptune, Ipsweep, Pod, and Teardrop, utilizing Support Vector Machine, Decision Tree, and Naive Bayes algorithms. After testing the characteristics specified in the training phase, the data is classified into attack categories and normal behavior during the machine learning phase.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Human VS AI-Generated Content: Where to Draw the Line?

Human VS AI-Generated Content: Where to Draw the Line?

引用

International Scientific Conference Electronics (ET)

作者： Daniela V. Minkovska Elena V. Antonova Department of Programming and Computer Technologies Faculty of Computer Systems and Technologies Technical University of Sofia 8 Kliment Ohridski blvd. Sofia Bulgaria

ISBN: (数字)9798350376449

ISBN: (纸本)9798350376456

The integration and detection of AI (Artificial Intelligence) in a variety of fields, primarily education, are examined in this paper. With an emphasis on virtual assistants and their uses, it explores the potential and constraints of such technology. A study was conducted with students at the Technical University of Sofia, to assess their ability to distinguish between texts written by humans and AI. The results showcase that learners need to develop their critical analysis skills evidenced by their mixed expertise.

关键词： Ethics Virtual assistants Education Artificial intelligence Standards

来源：评论

学校读者我要写书评

暂无评论

Network Intrusion Detection Based on Feature Selection and Hybrid Metaheuristic Optimization

引用

computers, Materials & Continua 2023年第2期74卷 2677-2693页

作者： Reem Alkanhel El-Sayed M.El-kenawy Abdelaziz A.Abdelhamid Abdelhameed Ibrahim Manal Abdullah Alohali Mostafa Abotaleb Doaa Sami Khafaga Department of Information Technology College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Communications and Electronics Delta Higher Institute of Engineering and TechnologyMansoura35111Egypt Department of Computer Science Faculty of Computer and Information SciencesAin Shams UniversityCairo11566Egypt Department of Computer Science College of Computing and Information TechnologyShaqra University11961Saudi Arabia Computer Engineering and Control Systems Department Faculty of EngineeringMansoura UniversityMansoura35516Egypt Information Systems Department College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of System Programming South Ural State UniversityChelyabinsk454080Russia Department of Computer Sciences College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia

Applications of internet-of-things(IoT)are increasingly being used in many facets of our daily life,which results in an enormous volume of *** computing and fog computing,two of the most common technologies used in IoT applications,have led to major security *** are on the rise as a result of the usage of these technologies since present security measures are *** artificial intelligence(AI)based security solutions,such as intrusion detection systems(IDS),have been proposed in recent *** technologies that require data preprocessing and machine learning algorithm-performance augmentation require the use of feature selection(FS)techniques to increase classification accuracy by minimizing the number of features *** the other hand,metaheuristic optimization algorithms have been widely used in feature selection in recent *** this paper,we proposed a hybrid optimization algorithm for feature selection in *** proposed algorithm is based on grey wolf(GW),and dipper throated optimization(DTO)algorithms and is referred to as *** proposed algorithm has a better balance between the exploration and exploitation steps of the optimization process and thus could achieve better *** the employed IoT-IDS dataset,the performance of the proposed GWDTO algorithm was assessed using a set of evaluation metrics and compared to other optimization approaches in 2678 CMC,2023,vol.74,no.2 the literature to validate its *** addition,a statistical analysis is performed to assess the stability and effectiveness of the proposed *** results confirmed the superiority of the proposed approach in boosting the classification accuracy of the intrusion in IoT-based networks.

关键词： Feature selection grey wolf optimization dipper throated optimization intrusion detection internet-of-things(IoT)

来源：评论

学校读者我要写书评

暂无评论

Speech recognition with Transformers - Creating and testing datasets for Bulgarian language 30

Speech recognition with Transformers - Creating and testing ...

引用

30th International Scientific Conference Electronics, ET 2021

作者： Mateva, Maya Angelova, Maria Faculty of Computer Systems and Technologies Technical University of Sofia Department of Programming and Computer Technologies Sofia1000 Bulgaria

ISBN: (纸本)9781665445184

Speech is a natural way of communicating between human beings and as such, it triggers an interest of transforming it to a way of interaction with a computer as well. Once it is converted into a sequence of words, it can easily be applied for executing commands, thus enabling people to perform tasks easily or in some cases - tasks that are even impossible for them to be performed. The automatic speech recognition becomes a task solved with various success based on the accuracy, online/offline availability, speed. However, with the constant improvement of the neural networks, it is getting easier to solve and the most prominent solution seems to be the Transformer architecture of neural networks. In this paper, we describe the design of an encoder-decoder TensorFlow architecture and the process of training the model with a specially created Bulgarian dataset. © 2021 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

A Machine Learning Approach for Predicting Student Enrollment in the University 30

A Machine Learning Approach for Predicting Student Enrollmen...

引用

30th International Scientific Conference Electronics, ET 2021

作者： Ujkani, Berat Minkovska, Daniela Stoyanova, Lyudmila Faculty of Computer Systems and Technologies Technical University of Sofia Department of Programming and Computer Technologies Sofia1000 Bulgaria

ISBN: (纸本)9781665445184

The Matura exam is the final national examination that high school students in many countries must pass to be eligible for admission to a university. This paper discusses the key factors that have the most impact in producing a reliable machine learning model for predicting students' enrollment in the university. These factors include the final grades from each high school year, matura exam results and the university entry exam points. It should be noted that demographic factors were not taken into consideration in this study. Four machine learning (ML) techniques with a total of sixteen algorithms were implemented using the Weka software: Bayes (Bayes Net, Naive Bayes, etc.), Logistic Regression (Logistic and SimpleLogistic), K-Nearest Neighbors (IBK, KStar, and LWL) and Decision Tree (J48, Random Forest, RepTree, etc.). According to the results, The RepTree algorithm performed the best with a True Positive (TP) rate of 0.902 and a False Positive (FP) rate of 0.148. The algorithm with the lowest performance was NaiveMulti with a TP rate of only 0.790. However, the range between the worst and the best-performing algorithms was 14.18%. © 2021 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Understanding Student Success Prediction Using SHapley Additive exPlanations

Understanding Student Success Prediction Using SHapley Addit...

引用

computer Science (COMSCI), International Scientific Conference on

作者： Berat Ujkani Daniela Minkovska Ognyan Nakov Department of Programming and Computer Technologies Faculty of Computer Systems and Technologies Technical University of Sofia 8 Kliment Ohridski blvd. Sofia Bulgaria

Predicting student success is an important task in educational institutions, as it allows for targeted interventions and support systems to enhance educational outcomes. This paper explores the use of SHAP (SHapley Additive exPlanations) model-agnostic method in understanding and interpreting student success prediction. The predictive model was built using Multi-Layer Perceptron neural network algorithm on a large public dataset. By shedding light on the underlying factors driving student success, this research contributes to the advancement of data-driven decision-making in education.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Neuromorphic Assisted Sensor Grids

Neuromorphic Assisted Sensor Grids

引用

International Scientific Conference Electronics (ET)

作者： Ianislav Trendafilov Veska Gancheva Neuromorphica Ltd. Sofia Bulgaria Department of Programming and Computer Technologies Faculty of Computer Systems and Technologies Technical University of Sofia Sofia Bulgaria

A particular problem in using artificial intelligence techniques in the sensor grid is the high power consumption. Remote sensors are usually limited by the amount of power available, thus our general goal is to minimize it while preserving accurate experimentation results. Using emerging technologies like spiking neural networks and neuromorphic hardware, we can create sensor grids that perform data processing with preserving low power consumption. In this paper, we demonstrate a remote node with integrated visual sensor that works on less than 10mW of energy, while performing continuous scene monitoring, object detection and classification. The system has intelligent power management and the ability to send data wirelessly.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Neuromorphic Neurons and Networks for Artificial Intelligence Built Using Temporal Space Calculations

Neuromorphic Neurons and Networks for Artificial Intelligenc...

引用

International Scientific Conference Electronics (ET)

We deigned a spiking neural network that computes network weights in the temporal dimension. Such a network can be used for artificial intelligence and deep learning. We demonstrate circuits implementing blocks for building such a network and then a training model. This enables creation of efficient Hessenstein-Reichardt detectors observed in motion detection networks in the nature. The proposed network allows reconfiguration across network layers algorithmically.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Personalize Web Searching Strategies Classification and Comparison

arXiv

引用

arXiv 2022年

作者： Evtimova, Mariya Savova Momtchev, Ivan Momtchilov Faculty of Computer Systems and Control Programming Computer Technologies Department Technical University of Sofia Sofia1000 Bulgaria

Personalization is becoming very important direction in semantic web search for the users that needs to find appropriate information. In this paper, a classification of web personalization is proposed and semantic web search tools are investigated. Building user interest profile is essential for personalizing. Nowadays, semantic web tools use ontologies for personalization because of their advantages. It is important to mention that most of the semantic web search tools use agent technologies for implementation. © 2022, CC BY.

关键词： Search engines

来源：评论

学校读者我要写书评

暂无评论

Data Poisoning: Issues, Challenges, and Needs 7

Data Poisoning: Issues, Challenges, and Needs

引用

7th IET Smart Cities Symposium, SCS 2023

作者： Aljanabi, Mohammad Omran, Alaa Hamza Mijwil, Maad M. Abotaleb, Mostafa El-Kenawy, El-Sayed M. Mohammed, Sahar Yousif Ibrahim, Abdelhameed Department of computer College of Education Aliarqai university Baghdad Iraq University of information technology and communications Baghdad Iraq Computer Techniques Engineering Department Baghdad College of Economic Sciences University Baghdad Iraq Department of System Programming South Ural State University Chelyabinsk Russia Department of Communications and Electronics Delta Higher Institute of Engineering and Technology Egypt Computer Science Department Computer Science &Information Technology College Anbar University Anbar Iraq Computer Engineering and Control Systems Department Faculty of Engineering Mansoura University Mansoura Egypt

ISBN: (纸本)9781839539831

Data poisoning attacks, where adversaries manipulate training data to degrade model performance, are an emerging threat as machine learning becomes widely deployed in sensitive applications. This paper provides a comprehensive overview of data poisoning including attack techniques, adversary incentives, impacts on security and reliability, detection methods, defenses, and key research gaps. We examine label flipping, instance injection, backdoors, and other attack categories that enable malicious outcomes ranging from IP theft to accidents in autonomous systems. Promising detection approaches include statistical tests, robust learning, and forensics. However, significant challenges remain in translating academic defenses like adversarial training and sanitization into practical tools ready for operational use. With safety and trustworthiness at stake, more research on benchmarking evaluations, adaptive attacks, fundamental tradeoffs, and real-world deployment of defenses is urgently needed. Understanding vulnerabilities and developing resilient machine learning pipelines will only grow in importance as data integrity is fundamental to developing safe artificial intelligence. © The Institution of Engineering & Technology 2023.

关键词： 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：