检索结果-内蒙古大学图书馆

Unveiling Interpretability: Analyzing Transfer Learning in Deep Learning Models for Traffic Sign Recognition

SN computer science 2024年第6期5卷 682页

作者： Waziry, Sadaf Rasheed, Jawad Ghabban, Fahad Mahmoud Alsubai, Shtwai Elkiran, Harun Alqahtani, Abdullah Department of Software Engineering Istanbul Aydin University Isanbul 34295 Turkey Department of Computer Engineering Istanbul Sabahattin Zaim University Istanbul 34303 Turkey Faculty of Computer Science and Engineering Taibah University Medina Saudi Arabia College of Computer Engineering and Sciences Prince Sattam bin Abdulaziz University Al Kharj 11942 Saudi Arabia

Since the advent of automobiles and driver assistance technologies, traffic sign recognition has been of the utmost importance for Industry 4.0. In the driving system, good data pre-processing is critical. For such objectives, sophisticated transformations or fundamentally computational image processing approaches are out of the question. Convolutional Neural Networks (CNN) have been used to perform more object identification challenges, thus, improving most computer vision applications, both existing and new, because of their excellent recognition rate and rapid execution. This study introduces a method for recognizing traffic signs by utilizing a CNN-based model and the transfer learning concept. The TensorFlow library is used for training the underlying neural network model. The offered approach makes use of the German Traffic Sign Recognition Benchmark (GTSRB) and images from the Traffic Sign Images from Turkey (TSIT) databases. These datasets are dependable and vibrant, and they have been used to train many algorithms. Furthermore, after training the model, the proposed scheme acquired a testing accuracy is 99.44%. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： CNN German traffic sign Image processing Transfer learning

来源：评论

学校读者我要写书评

暂无评论

A New Method of Search Engine Optimization Based on Semantic Kernel Idea

A New Method of Search Engine Optimization Based on Semantic...

引用

作者： Orekhov, Sergey Godlevsky, Michail Malyhon, Hennadiy Goncharenko, Tetiana Computer Science and Software Engineering Department National Technical University Kharkiv Polytechnical Institute Kharkiv61002 Ukraine

The results of more than 30 projects in the field of search engine optimization on the Internet show that the effectiveness of existing approaches is catastrophically reduced. Paid promotion methods no longer guarantee a banal increase in the traffic of a given web resource, and even more so the number of leads. The reason is that competition has moved to the Internet as much as possible. So, we need to look for new alternative methods. Therefore, the paper proposes to consider a new alternative way to promote goods on the Internet. This approach is a new information technology – virtual promotion. It is based on the creation of a virtual image of a product on the Internet. We called this virtual image the semantic kernel. Such a kernel is placed on the Internet in order to attract a potential buyer. It is placed in the Internet nodes according to a special online sales scheme, which is based on a map of the user's travels on the Internet. This scheme is called the virtual promotion map. The map must guarantee maximum traffic to a given web resource. However, it will not be possible to immediately build a map. Therefore, its creation is iterative. We are, as it were, setting ourselves up to find effective ways between the semantic core and the user who is ready to buy our product online. The article offers a description of the virtual promotion technology. The main idea of virtual promotion is that promotion is a logistical channel between a company and a client. We put a special message (semantic core) into the channel. He moves through the logistics channel and tries to attract as many new buyers of the goods as possible. This article presents the results of the work of special software that implements the synthesis, quality assessment and management of the semantic kernel of web content. The program generates and manages two channels: the first is intended for the distribution of the semantic kernel, the second is for assessing the quality of such distribution. T

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Automated Analysis of Halo2 Circuits 21

Automated Analysis of Halo2 Circuits

引用

21st International Workshop on Satisfiability Modulo Theories, SMT 2023

作者： Soureshjani, Fatemeh Heidari Hall-Andersen, Mathias Jahanara, MohammadMahdi Kam, Jeffrey Gorzny, Jan Ahmadvand, Mohsen Computer Engineering and Software Engineering Department Polytechnique Montréal MontrealQC Canada Quantstamp Inc. United States Department of Computer Science Aarhus University Denmark

Zero-knowledge proof systems are becoming increasingly prevalent and being widely used to secure decentralized financial systems and protect the privacy of users. Given the sensitivity of these applications, zero-knowledge proof systems are a natural target for formal verification methods. We describe methods for checking one such proof system: Halo2. We use abstract interpretation and an SMT solver to check various properties of Halo2 circuits. Using abstract interpretation, we can detect unused gates, unconstrained cells, and unused columns. Using an SMT solver, we can detect under-constrained circuits (in the sense that for the same public input they have two efficiently computable satisfying assignments). This is the first work we are aware of that applies lightweight formal methods to PLONKish arithmetization and Halo2 circuits. © 2023 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).

关键词： Timing circuits

来源：评论

学校读者我要写书评

暂无评论

PSCS4CPP: A Generative PSCS Implementation for C++ 1

引用

Model-Driven engineering and software Development - 9th International Conference, MODELSWARD 2021, and 10th International Conference, MODELSWARD 2022, Revised Selected Papers

作者： Hammer, Maximilian Maschotta, Ralph Wichmann, Alexander Jungebloud, Tino Bedini, Francesco Zimmermann, Armin Systems and Software Engineering Group Computer Science and Automation Department Technische Universität Ilmenau Ilmenau Germany

ISBN: (数字)9783031388217

ISBN: (纸本)9783031388200

Since the early 2000s, Model-driven engineering has aimed to accomplish executable UML models. With fUML and PSCS, the Object Management Group (OMG) published standardized specifications of precise semantics for certain parts of UML in the form of metamodels, which form an execution environment. A certain characteristic of these environments is that static information about a model is analyzed and evaluated during runtime. With composite structures being a concept for describing structural properties of a model, the majority of execution semantics specified by PSCS concern analysis and processing of such static information about the model’s fine-grained structure. Thus, the PSCS specification appears suitable for a generative realization approach. Using Model-To-Text-Transformation to generate source code, which serves as an input for the actual execution environment, the runtime level of model executions can be relieved by outsourcing analysis and processing of static information to the level of code generation. By inserting this preprocessing step, the performance of the actual model execution at runtime can be improved. This paper introduces an implementation of the PSCS specification for C++ based on code generation using Model-to-Text-Transformation. This also includes a generative approach to realize an extension mechanism of the fUML and PSCS execution environments by introducing user-defined semantic execution strategies. The proposed PSCS implementation was developed as a part of the MDE4CPP project. Moreover, this paper presents a set of test models validating the correct functionality of the implementation as well as a performance benchmark. Finally, analysis results of an application example for the presented realization are evaluated and discussed. © 2023, Springer Nature Switzerland AG.

关键词： Specifications

来源：评论

学校读者我要写书评

暂无评论

Prediction of Covid-19 using Machine Learning and Deep Learning approaches: A data driven study 1

Prediction of Covid-19 using Machine Learning and Deep Learn...

引用

1st International Conference on Circuits, Power, and Intelligent Systems, CCPIS 2023

作者： Akhter, Thanzina Barua, Labannya Sultana, Mahmuda Masum, Abdul Kadar Muhammad International Islamic University Chittagong Department of Computer Science and Engineering Chittagong Bangladesh Daffodil International University Department of Software Engineering Dhaka Bangladesh

ISBN: (纸本)9798350315769

COVID-19 is generated by the SARS-CoV2 virus, which has caused an outbreak around the world. Since 2020, it has been labeled a pandemic. Due to the daily growth in the number of cases, this takes time for demonstrating the laboratory data, and as a result, treatment and resource limits have emerged. Because of such limitations the necessity for making decisions using clinical data with prognostic algorithms has emerged. Forecasting algorithms could positively relieve the pressure on healthcare systems by correctly identifying the disease. We employ the following machine learning models in this research: RF, SVM, hybrid RF-SVM and deep learning: ANN, CNN, LSTM, CNN-LSTM models and Laboratory data is being used to develop clinical forecasting models that will help medical professionals to figure out the patients that are most likely to develop COVID-19. Our models' prediction ability is measured using recall, F1-score, precision, accuracy and AUC scores. The models were verified using train test method and cross validation strategy. The assessment shows that most of our prediction models can reliably identify patients with COVID-19 disease, amidst the hybrid CNN-LSTM model outperforming the others with an accuracy of 89.5 percent,0.93 F1-score, 0.91 in precision,0.97 in recall, and AUC of 0.70, whereas among the machine learning models the hybrid ensemble outperforms other ML models with an accuracy of 92%. Predictive models obtained from laboratory findings have been found to be successful in predicting COVID-19 infection, which can help medical experts administer resources more effectively. © 2023 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

ML-based Anomalies Detection in Wireless Network Link Layer of the Internet of Things (IoT) 5

ML-based Anomalies Detection in Wireless Network Link Layer ...

引用

5th International Congress on Human-computer Interaction, Optimization and Robotic Applications, HORA 2023

作者： Goswami, Pankaj Kumar Goswami, Garima Mahdi, Hussain Falih Vaish, Arti Dewangan, Bhupesh Kumar Choudhury, Tanupriya Teerthanker Mahaveer University Moradabad India University of Diyala Department of Computer and Software Engineering Baquba Iraq OP Jindal University Department of Computer Science and Engineering Punjipathra Raigarh India Graphic Era Hill University Department of Computer Science and Engineering Dehradun India

ISBN: (纸本)9798350337525

Internet of things is the most emergent technology, expanding interconnected device networks day by day to enhance the ease of device control and monitoring. IoTs are not covering the commercial utility but also providing emergency benefits to health care centres too. The extensive number of device connections over a network challenges a huge cost of operation management. The most recent research activity deals with anomaly detection in IoT networks over wide IoT networks. The automatic malfunctioning over the network is the most tedious task for researchers. The real-world IoT system analysis motivates this work to identify the anomalies in wireless networks. The link layer is selected to analyse, identifies and detect the wireless network anomalies. A comprehensive review on the performance threshold of machine learning-based algorithms is presented for automatic detection. © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

A Comparative Analysis and Prediction of Diabetes Using Machine Learning Approaches 5th

A Comparative Analysis and Prediction of Diabetes Using Mach...

引用

5th Doctoral Symposium on Computational Intelligence, DoSCI 2024

作者： Ansari, Gufran Ahmad Bhat, Salliah Shafi Bhoite, Sachin Department of Computer Science and Engineering and Software Engineering University of Hail Hail Saudi Arabia Computer Applications B.S. Abdur Rahman Crescent Institute of Science and Technology Chennai600048 India Pune411 038 India

ISBN: (纸本)9789819763177

Diabetes is a leading cause of death. People with type 1 diabetes (T1D) can face a number of consequences from their illness. Hyperglycemia is a symptom of T1D disease. Hyperglycemia can be symptoms that can be used for predicting diabetes in patients using the machine learning approach (MLA). Learning algorithms play a role in disease detection and prediction of decision-making. The leading cause of diabetes is really a high blood sugar level or a lack of insulin. As a consequence, it is critical to develop a reliable method to predict diabetes. Once it becomes a serious health concern, it will damage different organs such as the lungs, brain, nerves, blood vessels and heart as a result. Several approaches for detecting diabetes have been used in recent decades. Early diabetic diagnosis is currently very important to help the patients’ health, and this can be done by utilizing a variety of procedures. Tenfold cross-validation technique was used to train dataset for classification. In this paper, authors use different classifications of algorithms such as random forest, decision tree, logistic regression and multilayer perceptron for finding T1D patients. The accuracy of MLP is 98.077% which is the highest among other algorithms. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Sorting Algorithms: A Review 11

Comparative Analysis of Sorting Algorithms: A Review

引用

11th International Conference on Soft Computing and Machine Intelligence, ISCMI 2024

作者： Ala'anzy, Mohammed Alaa Mazhit, Zhanar Ala'anzy, Alaa Fadhil Algarni, Abdulmohsen Akhmedov, Ramis Bauyrzhan, Abdiyev SDU University Department of Computer Science Almaty Kazakhstan Al-Hikma University College Department of Business Administration Baghdad Iraq King Khalid University Department of Computer Science Abha61421 Saudi Arabia Eurasian National University Department of Computer and Software Engineering Astana Kazakhstan

ISBN: (纸本)9798331518127

In the realm of computer science, sorting algorithms play a pivotal role in optimising data organisation and retrieval processes across various applications. This paper presents a comprehensive examination and comparative analysis of the most commonly used sorting algorithms, focusing on their time, space complexity, and efficiency. By scrutinising both traditional methods like bubble sort, selection sort, and insertion sort, and advanced techniques such as merge sort, quick sort, heap sort, and radix sort, this study sheds light on the performance metrics of each algorithm. Through meticulous implementation and evaluation across datasets of varying magnitudes, ranging from 100 to 100,000 integers, the research provides valuable insights into the strengths and weaknesses of these sorting techniques. The outcomes of this study offer practical guidance for professionals in data engineering and software development, aiding in the informed selection of sorting algorithms tailored to specific application needs. Utilising a rigorous experimental setup with the pseudocode, the study meticulously measures the time complexity of each algorithm, recording CPU time in seconds. The analysis reveals significant performance differentials among the algorithms, showcasing the efficiency of quick sort, shell sort, and heap sort on small datasets, while highlighting the scalability of merge sort, radix sort, and quick sort as dataset sizes increase. This research contributes to the advancement of algorithmic knowledge and provides a valuable resource for practitioners seeking to optimise sorting processes in their computational tasks. © 2024 IEEE.

关键词： software design

来源：评论

学校读者我要写书评

暂无评论

Finite-difference time-domain methods

NATURE REVIEWS METHODS PRIMERS

引用

NATURE REVIEWS METHODS PRIMERS 2023年第1期3卷 1-19页

作者： [Anonymous] Department of Electrical and Computer Engineering The Ohio State University Columbus OH USA Department of Electrical and Computer Engineering University of Toronto Toronto Ontario Canada Department of Electrical and Computer Engineering University of Utah Salt Lake City UT USA Department of Electrical Engineering Pohang University of Science and Technology Pohang Korea Department of Electrical and Electronic Engineering The University of Manchester Manchester UK Biomedical Engineering Department Northwestern University Evanston IL USA Department of Electrical and Software Engineering University of Calgary Calgary Canada Department of Electrical and Computer Engineering Purdue University West Lafayette IN USA

This PrimeView highlights how algorithm and hardware develops could expand the application range of finite-difference time-domain methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The Human Behind the Data: Reflections from an Ongoing Co-Design and Deployment of a Data-Navigation Interface for Front-Line Emergency Housing Shelter Staff

The Human Behind the Data: Reflections from an Ongoing Co-De...

引用

Extended Abstracts of the 2023 CHI Conference on Human Factors in Computing Systems, CHI EA 2023

作者： Masrani, Teale W. He, Helen Ai Messier, Geoffrey Department of Computer Science University of Calgary Calgary Canada Electrical and Software Engineering University of Calgary Calgary Canada

ISBN: (纸本)9781450394222

On any night in Canada, at least 35,000 individuals experience homelessness. These individuals use emergency shelters to transition out of homelessness and into permanent housing. We designed and deployed a technology to support front-line staff at the largest emergency housing shelter in Calgary, Canada. Over a period of five months in 2022, we worked closely with front-line staff to co-design an interface for supporting a holistic understanding of client context and facilitating decision-making. The tool is currently in-use and our collaboration is ongoing. In this paper, we reflect on preliminary findings regarding the second iteration of the tool. We find that supporting shelter staff in understanding the human behind the data was a critical component of design. This work contributes to literature on how data tools may be integrated into homeless shelters in a way that aligns with shelters' values. © 2023 Owner/Author.

关键词： Housing

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：