检索结果-内蒙古大学图书馆

11th International Conference on Information Technology, computer and Electrical Engineering, ICITACEE 2024

作者： Al-Ikhsan, Hamdani Bachtiar, Fitra Abdurrachman Faculty of Computer Science Brawijaya University Informatics Department Malang Indonesia

ISBN: (纸本)9798350389289

Eye tracking is an important variable and offers benefits in Human-computer interaction (HCI) which is often complex and impractical in practice. Eye tracking implementation usually requires specialized devices, technology, or setup to work. On top of that, challenges like face obstructions like glasses or masks, differences in lighting, distance, and angles add another layer to the implementation difficulty. A novel random point detector algorithm called Pixel Gradient Value (PGV) is proposed which is an interest point detector-like algorithm to be used for eye-tracking purposes, which works by calculating the gradient value of a pixel in a given neighborhood by using an edge detection operator like Sobel edge detector and Canny edge detector as its basis. PGV is image-agnostic, it is capable of covering a wide amount of eye-tracking scenarios while running on a minimum setup. PGV is then used in a series of Fully Convolutional Network (FCN) machine learning system used for classification and point localization of the pupil center point. The proposed model is able to achieve higher results compared to the state-of-the-art result of em ax ≤ 0.025 value of 96.04, em ax ≤ 0.05 value of 98.71 and em ax ≤ 0.01 value of 99.19. © 2024 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Fine-Tuned Attribute Weighted Naïve Bayes with Modified Partial Instances Reduction for Gaming Disorder Classification

HighTech and Innovation Journal

引用

HighTech and Innovation Journal 2025年第1期6卷 67-80页

作者： Latubessy, Anastasya Wardoyo, Retantyo Musdholifah, Aina Kusrohmaniah, Sri Doctoral Program Department of Computer Science and Electronics Faculty of Mathematics and Natural Science Universitas Gadjah Mada Yogyakarta55281 Indonesia Department of Informatics Engineering Faculty of Engineering Universitas Muria Kudus Indonesia Department of Computer Science and Electronics Faculty of Mathematics and Natural Science Universitas Gadjah Mada Yogyakarta55281 Indonesia Department of Psychology Faculty of Psychology Universitas Gadjah Mada Yogyakarta55281 Indonesia

Fine Tuning Attribute Weighted Naïve Bayes (FTAWNB) is a reliable modified Naïve Bayes model. Even though it is able to provide high accuracy on ordinal data, this model is sensitive to outliers. To improve the performance of FTAWNB, this research modified the Partial Instances Reduction (PIR) technique to make the FTAWNB more adaptive to outliers. Nevertheless, in contrast to the original PIR technique, which substitutes missing values for data values deemed outliers, the PIR technique suggested in this study replaces data values deemed outliers using a Naïve Bayes weighting approach. The attribute values from the outlier data are replaced with the highest probability values for the attributes in the actual class. This PIR technique is referred to as modified PIR. The FTAWNB model with modified PIR has been evaluated using the Gaming Disorder dataset. Replacing the four attributes with the least amount of information resulted in accuracy gains of 99.74%, an increase of 1.53% over the FTAWNB model. The experimental result shows that adding the modified PIR technique to the FTAWNB model can handle the outlier in the data, proving it by increasing the performance in terms of accuracy, precision, and recall without pruning the dataset used. © 2025, Ital Publication. All rights reserved.

关键词： Attribute Weighted Classification Fine-Tune Gaming Disorder Instances Reduction Naïve Bayes

来源：评论

学校读者我要写书评

暂无评论

TimeSformer-MIL: A Hybrid Approach for Anomalous Activity Recognition in Real-World Surveillance Videos 6

TimeSformer-MIL: A Hybrid Approach for Anomalous Activity Re...

引用

6th IEEE Novel Intelligent and Leading Emerging sciences Conference, NILES 2024

作者： Khaled, Noorhan Saad, Sally Aref, Mostafa Ain Shams University Faculty of Computers and Information Sciences Computer Science Department Cairo Egypt

ISBN: (纸本)9798350378511

Anomaly detection in surveillance videos is vital for public safety. This paper introduces TimeSformer-MIL, a hybrid approach combining TimeSformer with Multiple Instance Learning (MIL) to identify anomalous activities. TimeSformer captures spatio-temporal features and highlights significant segments, while MIL uses video-level labels, treating videos as bags of segments. The model learns a deep anomaly ranking with sparsity and temporal smoothness constraints. Evaluated on a subset of the UCF-Crime dataset, TimeSformer-MIL shows significant improvements over three recent deep learning baselines, demonstrating its effectiveness in assessing surveillance footage. © 2024 IEEE.

关键词： Anomaly Detection Multiple instance learning TimeSformer UCF-Crime Dataset Video Surveillance Weakly Supervised Learning

来源：评论

学校读者我要写书评

暂无评论

Gaussian Filter Optimization for Segmentation Retinal Fundus Images in Proliferative Diabetic Retinopathy Screening

Gaussian Filter Optimization for Segmentation Retinal Fundus...

引用

2024 Beyond Technology Summit on informatics International Conference, BTS-I2C 2024

作者： Santika, Gayatri Dwi Afia, Lailatul Nur Adiwijaya, Nelly Oktavia University of Jember Faculty of Computer Science Department of Informatics Jember Indonesia

ISBN: (纸本)9798331508579

Diabetic Retinopathy alludes to a boundary that takes put in diabetes mellitus harming the blood vessel arranged display within the retina. This may imperil the subject's vision if they have diabetes. It can take a little time to perform a DR determination utilizing color fundus pictures since experienced clinicians are required to identify the tumors within the symbolism utilized to distinguish the sickness. This research using 3669 data were collage using open data. CNN are also highly successful at classifying pictures when connected within the display circumstance, especially compared to the high quality and usefulness strategies utilized. To guarantee high results, it needs a cutting-edge CNN show that might decide the characteristics of the fundus pictures. The implementation of the Gaussian filter result image on the identification performance gets the highest accuracy from the 3×3 structural element is 77%. Its shown that algorithm is feasible. The investigation's discoveries that the approach performed way better than elective approaches and can identify the specifics of an image as a health industry option for early detection of disease. © 2024 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Wind Power Prediction Based on Machine Learning and Deep Learning Models

引用

computers, Materials & Continua 2023年第1期74卷 715-732页

作者： Zahraa Tarek Mahmoud Y.Shams Ahmed M.Elshewey El-Sayed M.El-kenawy Abdelhameed Ibrahim Abdelaziz A.Abdelhamid Mohamed A.El-dosuky Faculty of Computers and Information Computer Science DepartmentMansoura UniversityMansoura35561Egypt Faculty of Artificial Intelligence Kafrelsheikh UniversityKafrelsheikh33511Egypt Faculty of Computers and Information Computer Science DepartmentSuez UniversitySuezEgypt Department of Communications and Electronics Delta Higher Institute of Engineering and TechnologyMansoura35111Egypt Faculty of Artificial Intelligence Delta University for Science and TechnologyMansoura35712Egypt Computer Engineering and Control Systems Department Faculty of EngineeringMansoura UniversityMansoura35516Egypt Department of Computer Science Faculty of Computer and Information SciencesAin Shams UniversityCairo11566Egypt Department of Computer Science College of Computing and Information TechnologyShaqra University11961Saudi Arabia Department of Computer Science Arab East CollegesRiyadh13544Saudi Arabia

Wind power is one of the sustainable ways to generate renewable *** recent years,some countries have set renewables to meet future energy needs,with the primary goal of reducing emissions and promoting sustainable growth,primarily the use of wind and solar *** achieve the prediction of wind power generation,several deep and machine learning models are constructed in this article as base *** regression models are Deep neural network(DNN),k-nearest neighbor(KNN)regressor,long short-term memory(LSTM),averaging model,random forest(RF)regressor,bagging regressor,and gradient boosting(GB)*** addition,data cleaning and data preprocessing were performed to the *** dataset used in this study includes 4 features and 50530 *** accurately predict the wind power values,we propose in this paper a new optimization technique based on stochastic fractal search and particle swarm optimization(SFSPSO)to optimize the parameters of LSTM *** evaluation criteria were utilized to estimate the efficiency of the regression models,namely,mean absolute error(MAE),Nash Sutcliffe Efficiency(NSE),mean square error(MSE),coefficient of determination(R2),root mean squared error(RMSE).The experimental results illustrated that the proposed optimization of LSTM using SFS-PSO model achieved the best results with R2 equals 99.99%in predicting the wind power values.

关键词： Prediction of wind power data preprocessing performance evaluation

来源：评论

学校读者我要写书评

暂无评论

SEDARU-net: a squeeze-excitation dilated based residual U-Net with attention mechanism for automatic melanoma lesion segmentation

引用

Multimedia Tools and Applications 2024年 1-28页

作者： Lafraxo, Samira El Ansari, Mohamed Koutti, Lahcen Kerkaou, Zakaria Souaidi, Meryem LabSIV Department of Computer Science Faculty of Sciences Ibnou Zohr University Agadir80000 Morocco Department of Computer Sciences Faculty of Sciences Informatics and Applications Laboratory Moulay Ismail University Meknès Morocco

One of the most dangerous types of skin cancer, malignant melanoma, must be detected early on in order to receive successful therapy. If melanoma is not diagnosed in a timely manner, it might possibly result in death. According to clinical research, because of their varied hue, texture, and imperceptible borders, these early melanoma indications are very challenging for dermatologists to recognize. Therefore, it’s crucial to suggest an automated method that can accurately identify and distinguish between benign and malignant melanoma. Numerous automated methods have been developed by scientists to segment abnormalities from dermoscopic images. On the other hand, conventional models could find it difficult to reliably capture the multi-scale properties, which could result in inconsistent segmentation performance for a variety of object shapes and sizes. Furthermore, models with complicated forms and bounds, such as U-Net and DeepLabV3+, have difficulty properly segmenting tiny, thin, or complex lesions. Thus, we introduce A Squeeze-Excitation Dilated Residual U-Net with Attention Mechanism (SEDARU-Net) in this paper, a novel and automated semantic segmentation network for efficient skin lesion segmentation. To keep spatial information across layers and capture both local and global context, the model is built on U-net combined with dilated convolution. To solve optimization problems, residual blocks are used instead of the basic U-net units. This enhances feature learning, encourages better feature reuse, and allows for the creation of deeper and more robust networks. In order to encourage feature recalibration, global context awareness, and spatial adaptation, each residual block is supplemented with squeeze and excitation units. In addition, The attention gate is also included in the skip connection part of the network to enhance the beneficial channel dimension characteristics and suppress the unreliable background features. According to the results of the experim

关键词： Dermatology

来源：评论

学校读者我要写书评

暂无评论

Intelligent Decision Support System for Crime Investigation

Intelligent Decision Support System for Crime Investigation

引用

2024 International Conference on computer and Applications, ICCA 2024

作者： Abdelshafy, Alaa Ezzat Elsawy, Ahmed Aboelyazed Amen, Shaimaa Talaat Benha University Faculty of Computers and Artificial Intelligence Department of Information Systems Benha Egypt Benha University Faculty of Computers and Artificial Intelligence Department of Computer Science Benha Egypt

ISBN: (纸本)9798350367560

Crime presents one of society's most formidable challenges, with its escalating rates significantly impacting individuals, families, and communities in detrimental ways. Therefore, efforts aimed at reducing the spread of crimes seek to reduce the spread of crimes by analyzing this large amount of data related to crime and accurately predicting it in real time. Thus, the competent authorities can take the necessary measures to prevent the occurrence of crime. Hence, advanced systems and contemporary methodologies for crime analysis are imperative to safeguard society. This paper presents an intelligent decision-support system in investigating crimes, using intensive crime data analysis to predict the quantity and types of crimes that occur at specific times and locations. Herein, Comparative analyzes are performed between machine learning and deep learning models, including Random Forest, K-NN, Naïve Bayes, ANN, Linear Regression, ARIMA, and LSTM, across datasets from the Urban Institute, Chicago, and Boston. The results indicate that linear regression outperformed the other methods in terms of regression, achieving higher R-squared values, particularly 0.946 and 0.476 for Chicago and the Urban Institute, respectively. On the other hand, LSTM exhibited in Boston by 0.525. For classification, Random Forest showed superior performance, with accuracies of 99.6%, 72.5%, and 78.6% for the Chicago, Boston, and Urban Institute datasets, respectively. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Mixed Reality Application in Robot Navigation and Control 16

Mixed Reality Application in Robot Navigation and Control

引用

16th International Conference on Applied and Theoretical Electricity, ICATE 2024

作者： Cismaru, Stefan-Irinel Petcu, Florina-Luminita Resceanu, Ionut-Cristian Roibu, Horatiu Trasculescu, Andrei-Costin Pana, Cristina-Floriana Bizdoaca, Nicu-George University of Craiova Faculty of Automation Computers and Electronics Mechatronics and Robotics Department Craiova Romania University of Craiova Faculty of Automation Computers and Electronics Computer Science Department Craiova Romania

ISBN: (纸本)9798350388107

Among the emerging technologies, Mixed Reality (MR) has provided the means to interact with holograms. A very distant future is now near and accessible, which allows for the replacement of classic controllers for robots and is driven by MR. Holograms involve dynamic 3D elements that are integrated into the environment, enhancing control means for the user. These elements may be visually attended to and interacted with via eye concentration or hand gestures, and they have the capability to execute a variety of activities. This emerging technology enables interactions that are otherwise unattainable in alternative settings or contexts, such as the presence of an avatar inside the program. Furthermore, it has the potential to be expanded to govern other mechatronic devices, including robots. The purpose of this work is to offer an improved and interactive method of controlling a mechatronic platform by using holograms, such that the adaptability of this technology may be shown in the context of operating real systems. Important for the authors of this paper is the broadening of the spectrum in which the application lies, thus contributing to the process followed for the development and applicability of the solution in key areas such as industry, training, and medicine. © 2024 IEEE.

关键词： Holograms

来源：评论

学校读者我要写书评

暂无评论

Comparative Study for Identifying and Categorizing DDoS Attacks 21

Comparative Study for Identifying and Categorizing DDoS Atta...

引用

21st International Learning and Technology Conference, L and T 2024

作者： Saad, Asaad B. Hossny, Eman Omara, Fatma A. Cairo University Faculty of Computers and Artificial Intelligence Software Engineering Department Cairo Egypt Cairo University Faculty of Computers and Artificial Intelligence Computer Science Department Cairo Egypt

ISBN: (纸本)9798350393569

Distributed Denial of Service, known as DDoS attacks, significantly compromise network security and availability. Certain DDoS detection methods utilize machine learning techniques, whereas others are based on statistical techniques. Therefore, this study provides a classification of the currently available DDoS detection techniques based on these two methodologies, strengths, and limitations. In addition, a comparative study of some DDoS detection techniques proposed in recent years is presented. We obtained similar results in related studies using different datasets. Thus, the compared DDoS techniques were dataset-independent. Finally, this study highlights areas for further research and improvement. © 2024 IEEE.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

TL-IDS: A Transfer Learning Technique for Botnet Detection in IoT 6

TL-IDS: A Transfer Learning Technique for Botnet Detection i...

引用

6th International Conference on Computing and informatics, ICCI 2024

作者： Abdelhamid, Salma Hegazy, Islam Aref, Mostafa Roushdy, Mohamed Computer Science Department Faculty of Computers and Information Technology Future University in Egypt Cairo Egypt Computer Science Department Faculty of Computer and Information Sciences Ain Shams University Cairo Egypt

ISBN: (纸本)9798350373875

With the exponential rise of Internet of Things (IoT) devices in our modern-day lifestyle, the potential danger of botnet intrusions has become inevitable. These botnet attacks cause extensive damage to both individual users and large organizations. In the realm of IoT botnet intrusion detection, learning-based Intrusion Detection Systems (IDS) were proposed as a powerful strategy for identifying malicious behaviors and consolidating the security of IoT systems. Moreover, Transfer Learning (TL) techniques have emerged to overcome the problems of scarce data and the long training time of traditional learning approaches. This paper proposes an IDS for IoT networks based on the TL EfficientNet model. We train the system and validate it using the Bot-IoT network intrusion dataset. Our approach incorporates balancing the dataset, redundancy removal, dimensionality reduction, and transformation of the dataset into RGB images to be fed as input to the detection model. The findings of our experimental work prove that the proposed model is robust and effective, and it surpasses existing models with an accuracy of 99.53%, recall of 99.53%, and F1-score of 99.52%. © 2024 IEEE.

关键词： Intrusion detection

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：