检索结果-内蒙古大学图书馆

Revisiting the privacy of censored credentials

Revisiting the privacy of censored credentials

2022 Informatik in den Naturwissenschaften, INFORMATIK 2022 - 2022 computer science in the Natural sciences, INFORMATIK 2022

作者： Garske, Viktor Noack, Andreas University of Applied Sciences Stralsund Department of Electrical Engineering and Computer Science Zur Schwedenschanze 15 Stralsund18435 Germany

ISBN: (纸本)9783885797203

On the internet, you find numerous images like screenshots where secret parts are hidden with irreversible redaction techniques like pixelation or blurring. In this paper, we propose a system that recovers information from redacted text in raster graphics using a composition of a Convolutional Neural Network (CNN), a Recurrent Neural Network (RNN) using Long short-term memory (LSTM) and a Connectionist Temporal Classification (CTC) layer to output the most probable character sequence. We furthermore show that our model operates in an automated pipeline, performs on blurred images without modification and is even able to compensate JPEG quality loss. Finally, our test results indicate that a generic neural network can be trained successfully to assist the recovery of pixelized or blurred information on screenshots or high-quality photos. © 2022 Gesellschaft fur Informatik (GI). All rights reserved.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

IoT Malware Detection Tool with CNN Classification for Small Devices 6

IoT Malware Detection Tool with CNN Classification for Small...

引用

6th International Conference on Contemporary Computing and Informatics, IC3I 2023

作者： Bhatnagar, Gunjan Kumar Rajoria, Yogendra Sakeel, Md. Vigenesh, M. Premananthan, G. Dongre, Deepika School of Engineering and Computer Dev Bhoomi Uttarakhand University Uttarakhand India School of Basic & Applied Sciences K. R. Mangalam University Department of Mathematics Gurugram India Invertis University Department of Computer Applications Bareilly India Karpagam Academy of Higher Education Department of Computer Science Engineering Coimbatore India Karpagam College of Engineering Department of Electronics and Communication Engineering Coimbatore India Vishwakarma Institute of Information Technology AI & Ds Pune India

ISBN: (纸本)9798350304480

Since the number of linked devices continues to grow quickly, the Web of Everything (IoT) is being employed change today in more industries. More issues in regards to safety, stability, and supportability are brought on by an increase in smart devices, particularly as it relates to 5G technology. We are concentrating on the safety component of IoT systems in just this article because it is a relatively new field. For varied purposes, such as cost savings or a desire to forego the use of generation system, many Internet device manufacturers need not take security into account when designing their products. The opponent may use those potentially dangerous technologies to carry out several destructive assaults. As a result, we created a device capable of recognizing malicious activity from a particular IoT networks node. They are capable to offer detection methods for IoT utilizing a primary key that may be put inside the system using a multilayer brain networks for identification and surveillance. The accomplishment dispels any misconceptions about methods for deep training while demonstrating how that systems can be simply adapted and deployed to every system. © 2023 IEEE.

关键词： Classification CNN IoT Machine Learning Malware Multicategories

来源：评论

学校读者我要写书评

暂无评论

Optimizing Software Defect Classification with Locally Linear Embedding Techniques

Optimizing Software Defect Classification with Locally Linea...

引用

Annual Symposium on Reliability and Maintainability (RAMS)

作者： Fatemeh Salboukh Hesam Saki Lance Fiondella Department of Applied Science and Engineering University of Massachusetts - Dartmouth North Dartmouth MA USA Department of Computer Engineering University of Tehran Tehran Iran

ISBN: (数字)9798350367744

ISBN: (纸本)9798350367751

Software defect classification is crucial for enhancing the quality and reliability of software. This research explores the integration of Locally Linear Embedding (LLE) into the preprocessing stages of classification models to improve accuracy. LLE is particularly effective as it transforms complex, nonlinear data into a simpler, linear format. This transformation is instrumental in reducing the complexity of the data, facilitating a more straightforward analysis and potentially improving the predictive accuracy of classifiers. For this study, we used the KC2 dataset from the PROMISE repository and applied several feature selection techniques, including Correlation-Based Feature Selection, Gain Ratio, Sequential Forward Selection, and K-nearest neighbors. After selecting the most informative features, LLE was employed to linearize this data, aiming to enhance the classifiers' performance by presenting them with data that is easier to interpret and analyze. The impact of LLE was evaluated by comparing the outcomes of five different classifiers, such as Random Forest, Gradient Boosting, Support Vector Machines, Non-Linear Support Vector Machines, and Naive Bayes, on both the original and the LLE-processed datasets. Our results demonstrated an average improvement of 4.5% in accuracy and 4% in F1-Score across the classifiers with the LLE-processed data, confirming the effectiveness of transforming nonlinear data into a linear space for enhancing software defect classification.

关键词： Support vector machines Accuracy Transforms Software quality Boosting Feature extraction Software Software reliability Bayes methods Random forests

来源：评论

学校读者我要写书评

暂无评论

Evaluating the socioeconomic and environmental sustainability of barrages using analytical hierarchy process with a rating approach

Discover Sustainability

引用

Discover Sustainability 2025年第1期6卷 1-13页

作者： Ijaz, Usama Shahid, Saman Ali, Shahid Osman, Onur Alsubai, Shtwai Rasheed, Jawad Department of Civil and Environmental Engineering Clarkson University Potsdam USA Department of Sciences & Humanities National University of Computer & Emerging Sciences (NUCES) FAST Lahore Campus Lahore Pakistan Department of Civil Engineering National University of Computer & Emerging Sciences (NUCES) FAST Lahore Campus Lahore Pakistan Department of Electrical and Electronics Engineering Istanbul Topkapi University Istanbul Turkey Department of Computer Science College of Computer Engineering and Sciences in Al-Kharj Prince Sattam Bin Abdulaziz University Al-Kharj Saudi Arabia Department of Computer Engineering Istanbul Sabahattin Zaim University Istanbul Turkey Department of Software Engineering Istanbul Nisantasi University Istanbul Turkey Applied Science Research Center Applied Science Private University Amman Jordan

Assessing the environmental sustainability and economic viability of barrage infrastructure is a critical challenge in water resource management. To address this, the analytical hierarchy process (AHP) approach was applied to develop a novel model for three barrages in Punjab, Pakistan: Jinnah, Khanki, and Rasul. The model incorporates three impacts, nine parameters, and twenty-seven sub-parameters within a structured decision tree to rank the three alternatives (Barrages). Quantitative weights were assigned using pairwise comparisons to impacts, parameters, and sub-parameters. As a result, socio-economic impacts received the highest priority (64.10%), followed by environmental (28%) and other impacts (7.41%). Jinnah Barrage ranked first among alternatives with a sustainability score of 0.426, due to superior performance in irrigation potential, renewable energy generation, water quality, low carbon emissions, and recreational value. The proposed model provides a structured framework for the future design of barrages to enhance their environmental resilience and optimize socio-economic benefits.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Improved Fuzzy Logic Based Alcohol Detection System to Preserve Road Safety using Smart Sensors Association 3

An Improved Fuzzy Logic Based Alcohol Detection System to Pr...

引用

3rd IEEE International Conference on Mobile Networks and Wireless Communications, ICMNWC 2023

作者： Kavitha, V.R. Muthu, Annamalai Geetha, B. Pandi, V. Samuthira Dinesh, M. Princy, B. Anni R.M.K. Engineering College Department of Computer Science and Business Systems Tamil Nadu Chennai India University of Technology & Applied Science Department of Engineering Nizwa Oman Prince Shri Venkateshwara PadmavathyEngineering College Department of Science & Humanities Tamil Nadu Chennai India Centre for Advanced Wireless Integrated Technology Chennai Institute of Technology Tamil Nadu Chennai India Saveetha School of Engineering SIMATS Department of VLSI Microelectronics Tamil Nadu Chennai India Panimalar Engineering College Department of Computer and Communication Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350317022

The increased risk of being involved in a traffic collision is directly proportional to the rate at which the number of vehicles on the road is growing. The majority of people in the world believe that driving under the influence of alcohol is a significant factor in the number of people killed in car accidents. The fundamental purpose of this investigation is to develop a device that is able to determine the degree of drunkenness that is present in the driver of a motor vehicle. The purpose of the proposed system is to discourage users from getting behind the wheel while under the influence of alcohol or drugs in order to reduce the number of accidents that are caused by intoxicated drivers. As part of this investigation, we propose the Fuzzy Assisted Alcohol Detection Mechanism (FAADM), which is a logical fuzzy-based alcohol detection mechanism. It uses a Direct Current (DC) motor as the vehicle's engine and a push button as its ignition system. This mechanism detects the presence of alcohol using a fuzzy-logic approach. The efficiency of this system is always being evaluated to ensure that it performs as designed. If this system were put into place, there would be a reduction in the number of accidents on the roads of smart cities that were caused by drivers who were under the influence of alcohol. It is strongly suggested that this system be fitted and installed inside the vehicle. In the event of an unexpected emergency, the engine should be turned off and the alarm should be activated. If there has been no drinking or accidents, the security system can be disarmed and the vehicle's engine should be started. If alcohol is found, the car will be turned off and an alarm will ring. As the number of incidents caused by intoxicated drivers continues to rise, the implementation of a system that combines alcohol detection and vehicle immobilization has been proposed as a potential solution. Engineers have developed a gadget that can detect the amount of alcohol in a d

关键词： Alcohol Detection Mechanism Alcohol Identification Drunk and Drive FAADM Fuzzy Logic Microcontroller Road Safety Sensors

来源：评论

学校读者我要写书评

暂无评论

Fresnel Diffraction of High-Dimensional Biphoton Wavefunctions: Computational Method and Characterization

Fresnel Diffraction of High-Dimensional Biphoton Wavefunctio...

引用

2024 Conference on Lasers and Electro-Optics, CLEO 2024

作者： Brown, Charlotte Dunham, Jake Zhao, Haoqi Hu, Chenfei Feng, Liang Gao, Zihe Department of Physics Auburn University AuburnAL36849 United States Department of Electrical and Computer Engineering Auburn University AuburnAL36849 United States Department of Electrical and Systems Engineering University of Pennsylvania PhiladelphiaPA19104 United States Applied Materials Inc. Santa Clara95054 United States Department of Materials Science and Engineering University of Pennsylvania PhiladelphiaPA19104 United States

ISBN: (纸本)9781957171395

Nonclassical biphoton wavefunctions reside in a higher-dimensional Hilbert space than classical or single-photon wavefunctions. Using the separability that holds for both spatial and multi-photon dimensions, we generalize FFT-based computational Fourier optics techniques to biphoton wavefunctions. © Optica Publishing Group 2024 © 2024 The Author(s)

关键词： Hilbert spaces

来源：评论

学校读者我要写书评

暂无评论

The Smart Coverage Path Planner for Autonomous Drones Using TSP and Tree Selection 1

引用

9th International Conference on Mining Intelligence and Knowledge Exploration, MIKE 2023

作者： Sundarrajan, M. Jothi, Akshya Prabakar, D. Kadry, Seifedine SRM Institute of Science and Technology Chennai India Department of Applied Data Science Noroff University College Kristiansand Norway Ajman University Ajman346 United Arab Emirates Department of Electrical and Computer Engineering Lebanese American University Byblos Lebanon

ISBN: (数字)9783031440847

ISBN: (纸本)9783031440830

The problem of efficiently covering an area with a limited number of sensors or cameras is an important research topic in various fields such as surveillance, monitoring, and inspection. This problem can be posed as a Traveling Salesman Problem (TSP), where the optimal path needs to be found to visit all the coverage points and return to the starting point. However, the computational complexity of solving TSP increases exponentially with the number of coverage points, making it impractical for large-scale applications. This paper proposes a novel approach to solving the coverage problem as a TSP by incorporating tree selection algorithms to improve efficiency and accuracy. The proposed approach represents the study area as a graph, with each node representing a coverage point and the edges representing the distance between them. To reduce computational complexity, we use various tree selection algorithms to select the best possible starting point for the TSP algorithm. To evaluate the effectiveness of the proposed approach, we conduct simulations using different scenarios with varying numbers of coverage points. The simulation results demonstrate that the proposed approach significantly improves the quality of coverage while reducing computational complexity compared to traditional TSP algorithms. Moreover, the proposed approach can be applied in a wide range of real-world applications, such as surveillance, monitoring, or inspection, where efficient and accurate coverage of an area is essential. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

A new trigonometric kernel function for support vector machine

引用

Iran Journal of computer science 2023年第2期6卷 137-145页

作者： Fathi Hafshejani, Sajad Moaberfard, Zahra Department of Applied Mathematics Shiraz University of Technology Modarres Boulevard Fars Shiraz 71557-13876 Iran Department of Math and Computer Science University of Lethbridge 4401 University Dr W Lethbridge T1K 3M4 AB Canada

In the last few years, various types of machine learning algorithms, such as support vector machine (SVM), support vector regression (SVR), and non-negative matrix factorization (NMF) have been introduced. The kernel approach is an effective method for increasing the classification accuracy of machine learning algorithms. This paper introduces a family of one-parameter kernel functions for improving the accuracy of SVM classification. The proposed kernel function consists of a trigonometric term and differs from all existing kernel functions. We show this function is a positive definite kernel function. Finally, we evaluate the SVM method based on the new trigonometric kernel, the Gaussian kernel, the polynomial kernel, and a convex combination of the new kernel function and the Gaussian kernel function on various types of datasets. Empirical results show that the SVM based on the new trigonometric kernel function and the mixed kernel function achieve the best classification accuracy. Moreover, some numerical results of performing the SVR based on the new trigonometric kernel function and the mixed kernel function are presented. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2022.

关键词： Kernel method Support vector machine Trigonometric kernel function

来源：评论

学校读者我要写书评

暂无评论

Wavelength Computation from RGB 23rd

Wavelength Computation from RGB

引用

23rd International Conference on Computational science and Its Applications , ICCSA 2023

作者： Skala, Vaclav Bellot, Tristan Claude Louis Berault, Xavier Department of Computer Science and Engineering Faculty of Applied Sciences University of West Bohemia Pilsen301 00 Czech Republic University of Technology of Troyes Troyes CEDEX10004 France

ISBN: (纸本)9783031368073

Conversion RGB to wavelength is not a simple problem. This contribution describes a simple method for wavelength extraction for colors given by the RGB triplet. The method is simple and accurate, based on known RGB values of the rainbow. It also respects different saturation of a color. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Fresnel Diffraction of High-Dimensional Biphoton Wavefunctions: Computational Method and Characterization

Fresnel Diffraction of High-Dimensional Biphoton Wavefunctio...

引用

CLEO: science and Innovations in CLEO 2024, CLEO: S and I 2024 - Part of Conference on Lasers and Electro-Optics

关键词： Hilbert spaces

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：