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

Machine learning-assisted image analysis techniques for glaucoma detection

引用

EURASIP Journal on Image and Video Processing 2025年第1期2025卷 1-28页

作者： Yadav, Vaibhav Dey, Barnali Baruah, Udayan Das, Saumya Prakash, Om Department of Information Technology Sikkim Manipal Institute of Technology Sikkim Manpal University Majitar India Birangana Sati Sadhani Rajyik Vishwavidyalaya (A State University Under Government of Assam) Golaghat India Department of Computer Science and Engineering—Artificial Intelligence Brainware University Kolkata India Department. of Electronics and Communication Engineering Sri Venkateswara College of Engineering & Technology (Autonomous) Chittoor India

Glaucoma is an eye disease that damages the optic nerve which is necessary for clear vision. This injury is frequently caused by extremely high pressure inside the eye. Any damage to the optic nerve, which is responsible for transmitting visual information from the eye to the brain, can result in vision loss and, in the worst-case scenario, blindness. In most cases of glaucoma, structural changes occur first, followed by functional deficits. Ophthalmologists use three well-established tests to diagnose glaucoma: Intraocular pressure (IOP) measurements, visual field tests, and (stereoscopic) assessments of the optic nerve. These methods, when combined, provide information on both structural and functional defects. However, carrying out these tests is not simple. For the correct diagnosis of glaucoma, ophthalmologists must have many years of experience. As a result, even in the modern world, glaucoma is underdiagnosed or, paradoxically, overtreated. To address these issues, a combination of Artificial Intelligence, Image Processing, and computer vision-based models are being developed for easy and rapid glaucoma diagnosis. Many research experiments used traditional machine learning and deep learning techniques to detect glaucoma. These techniques mainly focused on standard retinal image datasets to train the model and demonstrated good detection accuracy. This article provides a comprehensive description of the numerous forms of glaucoma, their pathophysiology, distinct diagnosis procedures, available datasets, and machine learning, deep learning, and hybrid methods of glaucoma detection. This review evaluates a variety of published studies on glaucoma detection approaches ranging from conventional machine learning to complex neural networks and summarizes the benefits and drawbacks of each procedure in a table style. The discussed methodologies are further evaluated in terms of performance parameters, such as accuracy, sensitivity, specificity, and area under the cur

关键词：

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

Machine learning applied to functionalized graphene sensors for noninvasive detection of renal diseases

Machine learning applied to functionalized graphene sensors ...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Sarkar, Lisa Bhattacharyya, Arindam Sett, Avik Karmakar, Gairik Bhattacharyya, Tarun Kanti Iit Kharagpur Department. of Electronics and Electrical Communication Engineering Kharagpur India Uc Davis Department of Computer and Electrical Engineering United States Tu Delft Department. of Microelectronics Delft Netherlands

ISBN: (纸本)9798350386226

Breath biomarker detection has been a significant non-invasive approach for disease diagnosis. This method has significant potential for early diagnosis and accurate analysis of diseases. Emission from breath contains several volatile organic compounds. Among them, ammonia is a very commonly found VOC and mainly responsible for chronic kidney diseases. There exist several strategies to detect ammonia, however they demonstrate severe limitations such as cross-sensitivity and poor selectivity. This work demonstrates the synergistic effect of sensor functionalization and application of machine learning for selective detection of ammonia in the environment. The sensor exhibits high degree of selectivity towards ammonia owing to enormous hydroxyl groups contributed through curcumin. At 500 ppm ammonia, the sensor demonstrates 274% response and very high selectivity among seven volatile organic compounds. The machine learning models were trained with the help of sensor transients. Random Forest and CNN models were applied to predict the presence of ammonia in a mixture. Random Forest achieved 96.25% accuracy compared to 89% accuracy of CNN. Hence, Random Forest algorithms applied to curcumin functionalized reduced graphene oxide sensors can detect ammonia vapors with very high efficiency among a mixture of gases. © 2024 IEEE.

关键词： Ammonia

来源：评论

学校读者我要写书评

暂无评论

A novel robust technique to compensate I/Q imperfections in quadrature modulator using LMS algorithm

A novel robust technique to compensate I/Q imperfections in ...

引用

2021 IEEE International Conference on Electrical, computer, communications and Mechatronics engineering, ICECCME 2021

作者： Talebpour, Faraz Sali, Aduwati Alirezaee, Reza Varahram, Pooria Alirezaee, Shahpour University of Windsor Department of Electrical and Computer Engineering Windsor Canada Universiti Putra Malaysia Department. of Computer and Communication Systems Engineering Serdang Malaysia National University of Maynooth Department of Electronic Engineering Dublin Ireland

ISBN: (纸本)9781665412629

In the modern era, the increasing demand for high data rate transmission enquires for wireless communication devices with large spectral bandwidth. Large spectral bandwidth increases the level of fault in the transmitter block. Quadrature modulator is one of the sensitive blocks in the transmitter. Having large spectral bandwidth makes the transmitter's quadrature modulators more prone to high level of physical and electrical faults. Physical faults in quadrature modulators, known as I/Q imperfections, will cause incorrect demodulation on the receiving end resulting in high bit error rate. In this paper, we propose a new 2-feedbacks compensation scheme based on Least Mean Square algorithm, its related channel modeling, a novel 1-bit online least mean square algorithm and finally a theoretical modulation/compensation method based on 1-bit modulation. To evaluate our proposed scheme and algorithm, we calculated normalized mean square error, image rejection ratio and convergence speed of our proposed algorithm for 128 iterations, gain and phase imbalances. While the normalized mean square error of adaptive algorithms used in other studies was -68dB, normalized mean square error for our proposed 2-feedbacks method is only -79.8dB. Moreover, image rejection ratio, signal errors and speed of the convergence shows improvements in our method as well. © 2021 IEEE.

关键词： Transmitters

来源：评论

学校读者我要写书评

暂无评论

A fuzzy condition sensitive hierarchical algorithm for template matching in emotionally expressive facial images

A fuzzy condition sensitive hierarchical algorithm for templ...

引用

2011 International Conference on Image Processing, computer Vision, and Pattern Recognition, IPCV 2011

作者： Mandal, Rajshree Halder, Anisha Konar, Amit Nagar, Atulya K. Department of Electronics and Tele-Communication Engineering Jadavpur University Calcutta-32 India Department. of Computer Science Liverpool Hope University Liverpool United Kingdom

ISBN: (纸本)9781601321916

The paper aims at developing a hierarchical algorithm for matching a given template of m × n on an image of M × N pixels partitioned into equal sized blocks of m × n pixels. The algorithm employs a fuzzy metric to measure the dispersion of individual feature of a block with respect to that of the template. A fuzzy threshold, preset by the user, is employed to restrict less likely blocks from participation in the matching. A decision tree is used to test the feasibility of a block for matching with the template. The tree at each link examines the condition for fuzzy thresholding for one feature of the image. If the block satisfies the condition, it is passed on to the next level in the tree for testing its feasibility of matching with respect to the next feature. If it fails, the block is discarded from the search space, and the next block from the partitioned image is passed on for examination. The process goes on until all the blocks pass through the decision tree. If a suitable block satisfies all the test conditions in the decision tree, the block is declared as the solution for the matching problem. The ordering of features to be examined by the tree is performed here by an entropy measure as used in classical decision tree. The algorithm has successfully been implemented for template matching of human eyes in facial images carrying different emotions, and the classification accuracy is as high as 94%.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Modelling and Simulation of Cloud Service Cost Analysis using Resource Scheduling 1

Modelling and Simulation of Cloud Service Cost Analysis usin...

引用

1st International Conference on Data Science, Machine Learning and Artificial Intelligence, DSMLAI 2021

作者： Rajput, Ravindra Kumar Singh Hussain, Rashid Goyal, Dinesh Centre of Cloud Infrastructure and Security Suresh Gyan Vihar University Rajasthan Jaipur India Department. of Electronics and Communication Engineering Suresh Gyan Vihar University Rajasthan Jaipur India Department of Computer Science and Engineering Poornima Institute of Engineering and Technology Rajasthan Jaipur India

ISBN: (纸本)9781450387637

Organizations are avoiding investments in infrastructure because of 3 reasons, age of technology, maintenance and scalability. This has created a huge market for Cloud service providers like AWS, Azure, Google etc. Cloud computing services are usually sorted into three groups SaaS, PaaS and IaaS. Each service belongs to a specified group and is offered at specific prices. The Cloud service providers (CSP's) offer services in small modules, and users feel their investment is low;on the other hand, these CSP's provision resources in a manner to maximize their revenues in the context of cloud resource management. © 2021 ACM.

关键词： Investments

来源：评论

学校读者我要写书评

暂无评论

Machine learning applied to functionalized graphene sensors for noninvasive detection of renal diseases

Machine learning applied to functionalized graphene sensors ...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Lisa Sarkar Arindam Bhattacharyya Avik Sett Gairik Karmakar Tarun Kanti Bhattacharyya Department. of Electronics and Electrical Communication Engineering IIT Kharagpur Kharagpur India Department of Computer and Electrical Engineering UC Davis Department. of Microelectronics TU Delft Delft Netherlands

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

关键词： Volatile organic compounds Ammonia Gases Accuracy Graphene Chronic kidney disease Sensors Transient analysis Random forests Diseases

来源：评论

学校读者我要写书评

暂无评论

Tightly-Coupled Integrated LR-WPAN/WiMAX Network: Architecture and Performance Modelling

引用

IERI Procedia 2013年 4卷 59-67页

作者： Ayyoub Akbari-Moghanjoughi Aduwati Sali José Roberto Amazonas Burhanuddin Mohd Ali Shamala Subramaniam Sabira Khatun Department. of Computer & Communications Systems Engineerin Faculty of Engineering Universiti Putra Malaysia Department of Telecommunications and Control Engineering of Escola Politécnica of the University of São Paulo Brazil Department of Communication Technology & Networks Faculty of Computer Science and IT Universiti Putra Malaysia School of Computer and Communication Engineering Universiti Malaysia Perlis Malaysia

In this paper a general architecture of tightly-coupled integrated LR-WPAN/WiMAX network has been introduced by proposing and utilising a novel access router named Wireless Integrated Access Router (WIAR). The suggested access router effectively combines both WiMAX and LR-WPAN technologies in a same device. The main motivation to propose this integration is to deploy Internet of Things (IoT) applications and services in wide area networks. Using WiMAX as backhaul service, the Internet connection can be provided for dispersed mobile LR-WPAN users over a wide area. Moreover, it enables to access all collected data in the local LR-WPAN coverage area – which is named as Senspot in this paper – by third-party clients through the Internet. Furthermore, an analytic model has been developed for the integrated network to evaluate the system's performance. Theoretical results on blocking probability of new and handover calls from WiMAX subscribers, as well as new connections from LR-WPAN Senspots in a cell of WiMAX have been investigated in terms of call/connection rates and number of allocated channels.

关键词： Backhaul Support Heterogeneous Wireless Network IoT Networks Integration WiMAX LR-WPAN.

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：