检索结果-内蒙古大学图书馆

Predicting Student Behavior Using a Neutrosophic Deep Learning Model

Neutrosophic Sets and Systems 2025年 76卷 288-310页

作者： Shitaya, Ahmed Mohamed Wahed, Mohamed El Syed Abd El Khalek, Saied Helemy Ismail, Amr Shams, Mahmoud Y. Salama, A.A. Department of Mathematics and Computer Science Faculty of Science Port Said University Egypt Department of Computer Science Faculty of computer and information sciences Suez Canal University Egypt Department. of Communication and Computer Engineering Air Defense University Egypt Department of Cybersecurity College of Engineering and Information Technology Buraydah Private Colleges Buraydah51418 Saudi Arabia Faculty of Artificial Intelligence Kafrelsheikh University Kafrelsheikh33516 Egypt

We developed an information system using an object-oriented programming language and a distributed database (DDB) consisting of multiple interconnected databases across a computer network, managed by a distributed database management system (DDBMS) for easy access. An intelligent system was designed to assess the difficulty level of preliminary exams and select top-performing advanced students using a Neutrosophic Deep Learning Model. The dataset was randomly split into training (80%) and testing (20%) sets, and the model, trained with the Adam optimizer at a 0.001 learning rate over 50 epochs, incorporated early stopping based on validation loss. This system, implemented at a traditional Egyptian university, achieved a 95% accuracy in predicting student dropout. Student behavior, influenced by personal, environmental, and academic factors, is often evaluated subjectively, leading to inconsistent results. Traditional machine learning approaches struggle with the inherent uncertainty in behavioral data. To address this, we combined neutrosophic theory—a mathematical framework that accounts for truth, falsity, and indeterminacy—with deep learning, which excels at learning complex data relationships, to predict student outcomes such as dropout rates. Evaluating the model on student data, including attendance and grades, showed superior accuracy, achieving a determination coefficient of 0.95, demonstrating the approach's potential for identifying at-risk students and enabling targeted interventions. © 2025, University of New Mexico. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

A Novel Framework for Gauging Information Extracted from Smartphones Using Neutrosophic Logic

引用

Neutrosophic Sets and Systems 2025年 76卷 154-171页

作者： Abou Alzahab, R.M. Ismail, Amr Abd Elkhalik, S.H. Shams, M.Y. El-Bakry, H.M. Salama, A.A. Department of Mathematics and Computer Science Faculty of Science Port Said University Egypt Department of Cybersecurity College of Engineering and Information Technology Buraydah Private Colleges Buraydah51418 Saudi Arabia Department. of Communication and Computer Engineering Air Defense University Egypt Faculty of Artificial Intelligence Kafrelsheikh University Kafrelsheikh33516 Egypt Department of Information Systems. Faculty of Computer and Information Science Mansoura University Egypt

Smartphones contain a vast amount of information about their users, which can be used as evidence in criminal cases. However, the sheer volume of data can make it challenging for forensic investigators to identify and use the most relevant information. Neutrosophic logic is a generalization of fuzzy logic that allows for uncertainty and vagueness, making it a more potent tool for dealing with the ambiguity of real-world data. The proposed framework aims to identify and utilize the most relevant information for forensic investigators, making it easier to solve criminal cases using Neutrosophic logic. This novel approach provides a more powerful tool for dealing with the ambiguity of smartphone data, ultimately improving the accuracy and effectiveness of forensic investigations. Our research has utilized Neutrosophic logic to evaluate the degree of truth, falsity, or Indeterminacy of this information. Additionally, this study analyzes conversations between individuals using Excel’s fuzzy lookup add-in to determine the percentage of truth and false in each conversation. The results were compiled into a dataset and utilized a Neutrosophic Python code to evaluate the information. The results indicate the percentage of truth, false, and Indeterminacy in each conversation and which can be used to determine its admissibility as evidence and which not. © 2025, University of New Mexico. All rights reserved.

关键词： Smartphones

来源：评论

学校读者我要写书评

暂无评论

Long-Distance Fiber-Optic Polarization Sensors in Hazardous Areas

Long-Distance Fiber-Optic Polarization Sensors in Hazardous ...

引用

National Conference on Communications (NCC)

作者： Martin Kyselak Zdenek Vylezich Jiri Vavra David Grenar Karel Slavicek Department of Electrical Engineering Faculty of Military Technology University of Defence Brno Czech Republic Dept. of Telecommunications Faculty of Electrical Eng. and Communication University of Technology Brno Czech Republic IT Infrastructure Division Institute of Computer Science Masaryk University Brno Czech Republic

ISBN: (数字)9798331536015

ISBN: (纸本)9798331536022

Due to their non-electrical characteristics, fiber-optic sensors are finding broad applications in high-risk environments. The safety of these sensors is ensured by the absence of potential differences and low detectability. This article aims to introduce polarization fiber-optic sensors and their connections, which allow for the effective placement of sensors at great distances from control rooms and sources of electrical signals. Furthermore, the research presented here focuses on maintaining high sensitivity of the sensors while also being economically efficient compared to other fiber-optic technologies. The key output of the article is the design of an arrangement of optical fiber components that ensures optimal use of sensors in challenging conditions, with an emphasis on the detection of variable non-electrical quantities. The results of the work confirm that the proposed sensors offer high reliability even in extreme conditions, making them ideal for use in special applications, including long-distance detection and utilization in military or chemical environments.

关键词： Optical fiber polarization Military communication Wiring Optical fiber sensors Chemical sensors Ultraviolet sources Optical fiber networks Sensor phenomena and characterization Optical fiber testing Chemicals

来源：评论

学校读者我要写书评

暂无评论

An intelligent ensemble EfficientNet prediction system for interpretations of cardiac magnetic resonance images in heart failure severity diagnosis

引用

Intelligence-Based Medicine 2025年 11卷 100218-100218页

作者： Muthulakshmi, Muthunayagam Venkatesan, Kotteswaran Prasanalakshmi, Balaji Syarifah Bahiyah, Rahayu Divya, Vijayakumar Department of Electronics and Communication Engineering Amrita School of Engineering Amrita Vishwa Vidyapeetham Chennai 601103 India Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Chennai 601103 India Department of Computer Science King Khalid University Abha Saudi Arabia Faculty of Defense Science and Technology National Defence University Malaysia Kuala Lumpur Malaysia

Ensemble models as part of federated learning leverage the ability of individual models to learn unique patterns from the training dataset to make more efficient predictions than single predicting systems. This study aggregates the output of four best-performing EfficientNet models to arrive at the final heart failure severity prediction through federated learning. The seven variants of EfficientNet models (B0-B7) learn the features from the cardiac magnetic resonance images that are most relevant to heart failure severity. Further, the performance of every model variant has been analysed with three different optimizers i.e. Adam, SGD, and RMSprop. It has been observed that the developed ensemble prediction system provides an improved overall testing accuracy of 0.95. It is also worthy to note that the ensemble prediction has yielded significant improvement in the prediction of individual classes which is evident from sensitivity measure of 0.95, 0.88, 1.00, 0.93, and 0.98 for hyperdynamic, mild, moderate, normal and severe classes respectively. It is obvious from these results that the proposed ensemble EfficientNet prediction system would assist the radiologist in better interpretation of cardiac magnetic resonance images. This in turn would benefit the cardiologist in understanding the HF progress and planning effective therapeutic intervention. © 2025 The Authors

关键词： Cardiac magnetic resonance images Deep features Efficientnet Ensemble prediction Federated learning Heart failure severity

来源：评论

学校读者我要写书评

暂无评论

Hybrid Machine Learning Approach for Enhanced Vulnerability Detection in Cloud Environments Using NIST and MITRE Frameworks

Hybrid Machine Learning Approach for Enhanced Vulnerability ...

引用

Advanced Research in Computing (ICARC), International Conference on

作者： N W Chanaka Lasantha M W P Maduranga Ruvan Abeysekara Valmik Tilwari Nilotpal Chakraborty Debashree Sharma Faculty of Graduate Studies IIC University of Technology Phnom Penh Cambodia Department of Electrical and Electronic Engineering University of Sri Jayewardenepura Nugegoda Sri Lanka Faculty of Computing BCAS Campus Colombo Sri Lanka Department. of Electronics & Communication Engineering Indian Institute of Information Technology Guwahati India Department of Computer Science Engineering Indian Institute of Information Technology Guwahati India Department of Electronics & Communication Engineering Indian Institute of Information Technology Guwahati India

ISBN: (数字)9798331530983

ISBN: (纸本)9798331530990

Cloud security is challenged by constant adaptive cyber threats and traditional detection methods lack real time adaptability. In this paper, we propose a new hybrid ML approach stitching data from National Institute of Standards and technology (NIST) and MITRE Adversarial Tactics, Techniques and Common Knowledge (ATT&CK) databases together. In contrast to existing methods, this framework combines, in unique and unprecedented fashion, ensemble ML models and Realtime data processing for increased detection accuracy and reduced false positives. This approach addresses specific challenges in the cloud environments and by leveraging standardised frameworks, it offers actionable audiences for efficient and effective vulnerability management process. The framework is validated by the experimental results which prove its robustness to evolution of the cybersecurity demands.

关键词： Adaptation models Accuracy Cloud computing security Scalability NIST Transformers Data models Threat assessment Robustness Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Comparative analysis of resource-efficient YOLO models for rapid and accurate recognition of intestinal parasitic eggs in stool microscopy

引用

Intelligence-Based Medicine 2025年 11卷 100212-100212页

作者： Venkatesan, Kotteswaran Muthulakshmi, Muthunayagam Prasanalakshmi, Balaji Karthickeien, Elangovan Pabbisetty, Harshini Syarifah Bahiyah, Rahayu Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Chennai 601103 India Department of Electronics and Communication Engineering Amrita School of Engineering Amrita Vishwa Vidyapeetham Chennai 601103 India Department of Computer Science King Khalid University Abha 61421 Saudi Arabia Faculty of Defense Science and Technology National Defence University Malaysia Kuala Lumpur 57000 Malaysia Cyber Security and Digital Industrial Revolution Centre National Defence University Malaysia Kuala Lumpur 57000 Malaysia

Faster and reliable recognition of the specific species of intestinal parasite eggs in stool microscopic images is required for targeted and quick intervention of soil transmitted helminths (STH) disease. The main objective of the proposed work is to identify the effective light weight basic yolo models among the recent compact yolo variants such as yolov5n, yolov5s, yolov7, yolov7-tiny, yolov8n, yolov8s, yolov10n and yolov10s, that could assist in rapid and accurate recognition of 11 parasite species egg. The real time performance of the compact yolo models have been analyzed in embedded platforms: Raspberry Pi 4, Intel upSquared with the Neural Compute Stick 2 and Jetson Nano. Finally, Gradient-weighted class activation mapping (Grad-CAM) has been used as an explainable AI (XAI) visualization method to elucidate the egg detection performance of the proposed models. Yolov7-tiny achieved the overall highest mean Average Precision (mAP) score of 98.7 %. On contrary, yolov10n yielded highest recall and F1 score of 100 % and 98.6 %. On other hand, yolov8n took least inference time with processing speed of 55 frames per second with Jetson Nano. Notably, the proposed framework demonstrates superior performance in detection of egg classes - Enterobius vermicularis, Hookworm egg, Opisthorchis viverrine, Trichuris trichiura, and Taenia spp. which is a significant outcome of the current research. Further, Grad-CAM depicts the discriminative power of unique features in parasite eggs. Thus, this study demonstrates the effectiveness, compactness and inference latency analysis of basic compact yolo variants in learning the specific patterns, texture and shape of parasitic egg species, thereby potentially enhancing the diagnostic accuracy of STH. © 2025 The Authors

关键词： Intel up squared board Intelligent parasitic egg detection Jetson nano Raspberry pi 4 Soil transmitted helminths YOLOv7-tiny

来源：评论

学校读者我要写书评

暂无评论

Factors Influencing Users’ Satisfaction Towards Image Use in Social Media: A PLS-SEM Analysis

International Journal of Interactive Mobile Technologies

引用

International Journal of Interactive Mobile Technologies 2022年第15期16卷 172-186页

作者： Ilias, Irma Syarlina Che Ramli, Suzaimah Wook, Muslihah Hasbullah, Nor Asiakin Department of Computer Science Faculty of Defense Science and Technology National Defence University of Malaysia Selangor Malaysia Computer Engineering Technology Section Malaysian Institute of Information Technology Universiti Kuala Lumpur Kuala Lumpur Malaysia

Images for social media are an essential component of any blog or social media post. As we now live in the age of the ‘camera in everyone’s pocket’, a new dynamic era of image creation and content has emerged. However, people use media due to specific motives or gratifications that lead to their satisfaction of social media use. This research study utilized uses and gratification theory (UGT), a sociology theory related to the motives of people using the media. The UGT factors include enjoyment, entertainment, social influence, social interaction, and information sharing. There were 441 data that were collected and analysed. IBM SPSS Statistics 20 and Smart PLS 3.3.3 were used for the data analysis. Result showed that information sharing was the most influencing factors on users’ satisfaction to use image in social media. Therefore, the factors identified in these studies could be used as a guideline and references in future study related to social media awareness and implications. © 2022. International Journal of Interactive Mobile Technologies. All Rights Reserved.

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

Web Vulnerability Assessment: Outsource dilemmas

Web Vulnerability Assessment: Outsource dilemmas

引用

2011 International Conference on Electrical Engineering and Informatics, ICEEI 2011

作者： Ahmad, Arniyati Ahmad, Siti Rohaidah Awang, Nor Fatimah Ali, Zulkarnain Md. Computer Science Department Faculty of Science and Defence Technology National Defence University of Malaysia 57000 Kuala Lumpur Malaysia Computer Science Department Faculty of Information Science and Technology National University of Malaysia 43600 Bangi Selangor Malaysia

ISBN: (纸本)9781457707520

Vulnerability Assessment (VAS) is a process to search for any potential loopholes contain in a system that lead to compromise it. It is important to do VAS on the system to make sure that it will be safely release and not offer any illegitimate access that can affect availability, confidentiality and integrity of the system[1][12]. VAS can be done by out sourcing it to a third party or do it yourself (DIY) depending on the budget and time allocated. It can sometimes depend on the confidentiality of the project that might pretend you from open it for a third party assessment. By choosing DIY, another thing to consider is implementing the VAS as in standard and common practices to make sure that the system can pass the security requirements needed. Even though there are so many standards, testing guidelines and common practices for VAS that is available on the net, the process of selecting the best and suitable VAS approach will need you to sacrifice a lot of your time and effort. This paper tries to share some experiences in setting up some criteria for outsourcing the task. It also shares the way to simplify standard practise from Open Web Application Security Project (OWASP) and turning it into simple practice yet thorough assessment process. The assessment was done in a clone environment to protect the real system from any disruptions and conflict. © 2011 IEEE.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

The design of fingerprint biometric authentication on smart card for pulapot main entrance system

The design of fingerprint biometric authentication on smart ...

引用

2010 International Symposium on Information technology, ITSim'10

作者： Isa, Mohd Rizal Mohd Yahaya, Yuhanim Hani Halip, Mohd Hazali Mohamed Khairuddin, Mohammad Adib Maskat, Kamaruzaman Department of Computer Science Faculty of Science and Defence Technology Universiti Pertahanan Nasional Malaysia Kuala Lumpur Malaysia

ISBN: (纸本)9781424467181

Biometrics personal authentication utilizing fingerprints have been thoroughly studied and applied. Exploiting the unique features of a fingerprint and the pleasant way of capturing the required information permits it to be used in numerous applications. Smart card is also being widely adopted in many applications and refers as an essential platform to hold biometrics information. This paper presents a fingerprint verification that can be embedded in a smart card. The smart card plays a data storage for storing the cardholder's fingerprint data. The card holder is required to scan his/her fingerprint on a sensor. The scanned fingerprint image is then sent to the card for matching. © 2010 IEEE.

关键词： Smart cards

来源：评论

学校读者我要写书评

暂无评论

Integrating Machine Learning Algorithms with EEG Signals to Identify Emotions Among University Students 7th

Integrating Machine Learning Algorithms with EEG Signals to ...

引用

7th Computational Methods in Systems and Software, CoMeSySo 2023

作者： Mohamad Amran, Mohd Fahmi Mohan, Venothanee Sundra Mohd Yusop, Nurhafizah Moziyana Yahaya, Yuhanim Hani Abd Rauf, Muhammad Fairuz Mat Razali, Noor Afiza Ali, Fazilatulaili Syed Ali, Sharifah Aishah Department of Computer Science Faculty of Defence Science and Technology Universiti Pertahanan Nasional Malaysia Kuala Lumpur Malaysia

ISBN: (纸本)9783031535482

Emotion level of the students during their academic sessions has a significant effect on their performance and overall academic grades. The most pre-eminent way of evaluating emotion levels is by analysing the EEG signals obtained from the brain. This paper showcases the experimental study on obtaining the Electroencephalogram (EEG) signals from the students during their academic sessions and classifying it to the types of emotions using machine learning algorithms. This paper explores the method of how the data collection session is conducted and recorded. The data collected is then compiled and divided for the machine learning algorithms. Furthermore, this paper proposed a method of acquiring the emotion labels without prior inducing by using a standard normal distribution method. Finally, this paper also proposed a deep learning neural network model and machine learning models that can be used to determine the emotion level from the EEG signals. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Electroencephalography

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：