检索结果-内蒙古大学图书馆

2023 IEEE International Conference on Integrated Circuits and communication Systems, ICICACS 2023

作者： Mohan Gowda, V. Sanjeev Kumar, A.N. Kumar, Dhanesh Hemalatha, K.L. Chaithra, N.K. Gitam School of Technology Gitam University Department of Computer Science & Engineering India K L University Vadeeshwaram Department of Computer Science & Engineering Vijayawada India Sri Krishna Institute of Technology Department of Information Science and Engineering Bangalore India Nitte Meenakshi Institute of Technology Department of Electronics and Communication Engineering Bengaluru India

ISBN: (纸本)9798350398465

A concept map is a graphical tool used to organize and represent knowledge or information visually. It consists of a collection of concepts or ideas that are linked together by relationships or connections to form a structured and hierarchical representation of a subject or topic. A concept map can be used to show the relationships between ideas, identify patterns, and clarify complex information. It is commonly used in education, research, and problem-solving to help individuals better understand and visualize information. The graph's entropy serves as a useful indicator of how accurately it represents the document. This study explains how to construct a concept map from the document's sentences by using a tree-based convolution neural network to extract key concepts. The use of latent relations based on a shared word embedding representation of concepts enables the removal of duplication and the efficient organization of concepts. This leads to a more precise, concise, and unambiguous concept map. The paper also describes the modifications made to the concept map and the additional data incorporated into it. By utilizing the latent semantic structure and hierarchical linkage of ideas and by adding significant information to the concepts themselves, the information content of the concept map is improved. © 2023 IEEE.

关键词： Entropy

来源：评论

学校读者我要写书评

暂无评论

Optimizing the Capacity of Extreme Learning Machines for Biomedical Informatics Applications 1

Optimizing the Capacity of Extreme Learning Machines for Bio...

引用

1st IEEE International Conference on Emerging Research in Computational Science, ICERCS 2023

作者： Logeshwaran, J. Bhardwaj, Rajat Salagrama, Shailaja Das, Abhijit Sri Eshwar College of Engineering Department of Electronics and Communication Engineering Tamil Nadu Coimbatore India University of the Cumberland's Department of Information Technology Kentucky Williamsburg United States Amity University Aset Department of Computer Science and Engineering Karnataka Bengaluru India Rv University School of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350359756

the paper discusses a way of growing the capability of severe deep learning machines (ELM) for biomedical informatics programs. This technique involves varying the dimensions of the training set, the variety of neurons in the hidden layer, the kind of activation function used, the range of different sorts of neurons used and the regularization techniques *** that it will maximize the ability of ELM fashions for biomedical informatics applications, the authors advocate using a stepwise seek technique to determine the fine combination of parameters. This technique entails first defining a baseline or initial configuration of ELM parameters and then iteratively enhancing that configuration via deep learning from the empirical effects of each optimization step. distinctive regularization strategies are carried out at every optimization step which could involve pruning hidden neurons as a way to reduce the complexity of the model. The authors verified their technique on publicly to be had datasets consisting of the Michigan Imputation of missing Values (MIMV) dataset and on a dataset of clinical records from the branch of Anesthesiology, branch of health and Human services. © 2023 IEEE.

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

A Broadband High Gain Base Station Antenna 7

A Broadband High Gain Base Station Antenna

引用

7th IEEE International Conference on Electronic information and communication Technology, ICEICT 2024

作者： Ding, Xiao Feng, Botao Rao, Liwei Gu, Wenzhe Deng, Li Zeng, Qingsheng Macau University of Science and Technology Faculty of Humanities and Arts Macau999078 China Shenzhen University College of Electronics and Information Engineering Shenzhen518060 China Huizhou University School of Computer Science and Engineering Huizhou China Beijing University of Posts and Telecommunications College of Information and Communication Engineering Beijing China Nanjing University of Aeronautics and Astronautics College of Astronautics Nanjing210016 China

ISBN: (纸本)9798350384437

This paper suggests a base-station antenna unit designed for 2G/3G/LTE frequencies, featuring ±45° polarization, high gain, and low cross-polarization. The antenna is excited by two circular arc probes and uses two orthogonal rectangular ring dipoles to achieve a wider bandwidth. In order to achieve higher gain and better cross-polarization level, four parasitic elements are added around the dual dipole. The simulation results show that |S11|27 dB), higher gain (9.6±1.4 dBi), front-to-back ratio(>18 dB) and a beamwidth of 57.5±7.5° in the desired bandwidth range. The antenna can be used in the broadband base station of the communication system. © 2024 IEEE.

关键词： Bandwidth

来源：评论

学校读者我要写书评

暂无评论

A Polarization Reconfigurable Magneto-Electric Dipole Antenna for 2.2-2.7 GHz Band 7

A Polarization Reconfigurable Magneto-Electric Dipole Antenn...

引用

7th IEEE International Conference on Electronic information and communication Technology, ICEICT 2024

作者： Zhou, Xuhang Feng, Botao Ding, Xiao Deng, Li Gu, Wenzhe Zeng, Qingsheng Shenzhen University College of Electronics and Information Engineering Shenzhen518060 China Macau University of Science and Technology Faculty of Humanities and Arts Macau999078 China Beijing University of Posts and Telecommunications College of Information and Communication Engineering Beijing China Huizhou University School of Computer Science and Engineering Huizhou516007 China Nanjing University of Aeronautics and Astronautics College of Astronautics Nanjing210016 China

ISBN: (纸本)9798350384437

In this article, a polarization-reconfigurable antenna based on magneto-electric (ME) dipoles is proposed. This antenna has three polarized states: linear polarization (LP), right-hand circular polarization (RHCP), and left-hand circular polarization (LHCP), which are mainly achieved through the cross strips with a bridge structure on top of the ME dipole. By changing the on/off states of diodes D1 and D2, the connections of the cross strips can be altered, thereby changing the surface current on the horizontal patches to achieve polarization reconfiguration. The proposed antenna is fed through a microstrip line and an H-shaped slot. The selected operating frequency band is 2.2-2.7 GHz. In all states, the bandwidth and 3-dB axial ratio bandwidth cover the operating band, and the gain is greater than 7 dBi within the operating band. This indicates that the antenna achieves polarization reconfiguration while maintaining good overall performance. Moreover, the reconfiguration method using diodes is easy to manufacture, making its application in wireless communication systems feasible. © 2024 IEEE.

关键词： Bandwidth

来源：评论

学校读者我要写书评

暂无评论

A Reconfigurable Reflectarray Antenna at X-band 7

A Reconfigurable Reflectarray Antenna at X-band

引用

7th IEEE International Conference on Electronic information and communication Technology, ICEICT 2024

作者： Du, Lin Feng, Botao Ding, Xiao Deng, Li Gu, Wenzhe Zeng, Qingsheng Shenzhen University College of Electronics and Information Engineering Shenzhen518060 China Macau University of Science and Technology Faculty of Humanities and Arts Macau999078 China Beijing University of Posts and Telecommunications College of Information and Communication Engineering Beijing China Huizhou University School of Computer Science and Engineering Huizhou516007 China Nanjing University of Aeronautics and Astronautics College of Astronautics Nanjing210016 China

ISBN: (纸本)9798350384437

In this paper, an electronically reconfigurable reflectarray antenna (RRA) that operates in X-band is developed and simulated. Two P-I-N diodes are integrated in each element to obtain 1-bit phase compensation. The proposed element offers a stable angular response and polarization rotation in X-band. The element is applied to a 19×19 RRA for achieving beam scanning. The simulated result of the proposed RRA shows that the proposed RRA can achievea beam scanning ranging from -30° to 30° and a peak gain of 18.12 dBi. © 2024 IEEE.

关键词： Reflection

来源：评论

学校读者我要写书评

暂无评论

An Uncertainty-Aware Deep Learning-Based Model for COVID-19 Diagnosis 3

An Uncertainty-Aware Deep Learning-Based Model for COVID-19 ...

引用

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

作者： Reddy, L Chandra Sekhar Jayakarthik, R. Kiran, Ajmeera Sharma, Nipun Sharma, Swati Reddy, Pundru Chandra Shaker Hyderabad India Saveetha College of Liberal Arts and Sciences Department of Computer Science Tamil Nadu Chennai India MLR Institute of Technology Dundigal Computer Science and Engineering Telangana Hyderabad India Presidency University Electronics and Communication Engineering Karnataka Bangalore India School of Computer Science Engineering and Information Science Presidency University Karnataka Bangalore India

ISBN: (纸本)9798350317022

The application of deep-learning(DL) to the processing of medical images has been highly successful. A few groundbreaking DL-based works have achieved substantial progress in computerized screening of COVID-19 using chest X-ray( CXR) pictures in the wake of the current epidemic scenario caused by SARS-CoV-2. While DL models have shown promise, they currently lack a crucial component for use in medical image analysis: the ability to communicate uncertainty in the strategies prediction. Therefore, in this paper, we create a design for automatically detecting COVID19 from CXR images using an uncertainty-aware convolutional-neural-network(UACNN) and estimate the uncertainty in its predictions. In the suggested method, an EfficientNetB3 model is tuned using CXR pictures, and then the model is used in conjunction with Monte Carlo (MC) dropout. The posterior predictive distribution has been obtained after M forward passes of inference using MC dropout. The anticipation and design uncertainty are then determined by calculating the mean and entropy of the generated anticipative distribution. The COVID19CXr, XR-pictures, and Kaggle CXR datasets are used to test the suggested approach. Multi-class classification on the COVID19CXr dataset was completed with an accuracy of 99.81% using the proposed UACNN approach. For the purpose of diagnosing COVID-19 cases from CXR pictures, our suggested methodology demonstrates its superiority over the existing methodologies. © 2023 IEEE.

关键词： CNN COVID19 CXR deep-learning transfer-learning uncertainty-quantification

来源：评论

学校读者我要写书评

暂无评论

Creating Realities: An In-Depth Study of AI-Driven Image Generation with Generative Adversarial Networks 15

Creating Realities: An In-Depth Study of AI-Driven Image Gen...

引用

15th International Conference on Computing communication and Networking Technologies, ICCCNT 2024

作者： Dhand, Raman Sidana, Sagar Sinha, Anurag Kumar, Biresh Kumari, Shreya Madhukar Rao, G. Raj, Petheru Al-Khayyat, Ahmed Maheswaran, S. Guru Tegh Bahadur Institute of Technology Department of computer science and engineering India Maharshi Dayanand University Department of computer science and engineering Haryana Rohtak India IGNOU India School of Computing and information Science New Delhi India Amity University Department of computer science and It Jharkhand India Koneru Lakshmaiah Education Foundation Department of computer science and engineering India Reliance Jio Platforms Ltd Bangalore India Islamic University Department of computer science and engineering Iraq Kongu Engineering College Department of Electronics and Communication Engineering Erode Perundurai638060 India

ISBN: (纸本)9798350370249

The field of artificial intelligence has witnessed significant advancements with the advent of Generative Adversarial Networks, revolutionizing image generation techniques. The literature review covers seminal works and recent advancements, highlighting the evolution of image generation techniques. Taxonomy is developed to classify methods based on their underlying principles and applications across various domains including art, fashion, healthcare, and entertainment. Comparative analysis evaluates the effectiveness, efficiency, and applicability of different models, utilizing metrics corresponding Inception Score and Frechet Inception Distance. By conducting a thorough review of existing literature and technologies, we explore the evolution of GAN architectures, from their inception to the latest innovations. We examine various GAN models, including DCGAN, StyleGAN, and CycleGAN, assessing their effectiveness in generating high-fidelity images across diverse applications. In addition to this comprehensive analysis, we present our own implementation of a GAN model tailored for specific image generation tasks. Our model is tested on multiple datasets to evaluate its performance, highlighting improvements in training stability and image quality. We discuss the architectural choices, optimization techniques, and training procedures employed in our implementation. Furthermore, we address the challenges faced in the field, such as mode collapse, training instability, and the need for largescale datasets. Our findings offer valuable insights into optimizing GAN performance and propose potential directions for future research. This comprehensive analysis serves as a foundational reference for researchers and practitioners aiming to leverage GANs for advanced image generation tasks, pushing the boundaries of what is visually conceivable through artificial intelligence. © 2024 IEEE.

关键词： AI computer vision Deep Learning GANs Image generation ML

来源：评论

学校读者我要写书评

暂无评论

Advanced Machine Learning Techniques for Enhancing Data Security in Cloud Computing Systems 5

Advanced Machine Learning Techniques for Enhancing Data Secu...

引用

5th IEEE International Conference on Computing, Power, and communication Technologies, IC2PCT 2024

作者： Dhinakaran, M. Sundhari, M. Ambika, S. Balaji, V. Rajasekaran, R.Thalapathi Galgotias College of Engineering & Technology Department of Electronics and Communication Engineering Uttar Pradesh Greater Noida India Grt Institute of Engineering and Technology Dept. of Computer Science and Engineering Tamil Nadu Tiruttani India E. G. S. Pillay Engineering College Department of Information Technology Tamil Nadu Nagapattinam India Chennai India Saveetha School of Engineering Simats Dept. of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350383522

In the age of cloud computing, data stored and processed in the cloud must be secure. This study examines how powerful machine learning can secure cloud computing data. Three trials assessed different machine learning models in this setting. Experiment 1 used a Random Forest model and achieved 95% accuracy, 0.92 precision, 0.96 recall, and 0.94 F1 Score. This shows that the model can accurately categorize security threats with a good balance of true and false positives. A Deep Neural Network (DNN) improved accuracy to 97% in Experiment 2. Precision, recall, and F1 Score values of 0.94, 0.98, and 0.96 demonstrate the DNN's ability to discriminate threats from normal activity. The model captures complicated patterns well, making it a powerful cloud security tool. Security analysis using reinforcement learning, specifically Q-learning, was introduced in Experiment 3. The model's 88% detection rate showed its capacity to identify threats, but its 0.05 false positive rate created a tradeoff between true and false positives. With the 0.12 false negative rate, one can infer improvements in threat detection accuracy. These results indicate that state-of-the-art machine learning is capable of protecting cloud data. The Random Forest and Deep Neural Network models have very high accuracy balanced with reasonable precision-recall trade-offs, whereas reinforcement learning through Qlearning shows promise but needs modification to improve the model's performance in terms of both accuracy and false positive rates. While rising threats need constant adaptation and learning, the model should also fulfill security needs. This study helps formulate a secure cloud computing infrastructure that can stand threats of change. © 2024 IEEE.

关键词： Cloud Computing Data Security Machine learning Q-Learning

来源：评论

学校读者我要写书评

暂无评论

A Broadband Array Antenna Based on E-Shaped Folded Strip Elements for Millimeter-Wave N259/N260 Applications 7

A Broadband Array Antenna Based on E-Shaped Folded Strip Ele...

引用

7th IEEE International Conference on Electronic information and communication Technology, ICEICT 2024

作者： Wu, Xi Feng, Botao Ding, Xiao Gu, Wenzhe Deng, Li Zeng, Qingsheng Shenzhen University College of Electronics and Information Engineering Shenzhen518060 China Macau University of Science and Technology Faculty of Humanities and Arts Macau999078 China Huizhou University School of Computer Science and Engineering Huizhou516007 China Beijing University of Posts and Telecommunications College of Information and Communication Engineering Beijing China Nanjing University of Aeronautics and Astronautics College of Astronautics Nanjing210016 China

ISBN: (纸本)9798350384437

A low-profile, wideband linearly-polarization array antenna based on broadband E-shaped folded strip elements is proposed. The antenna unit consists of a 2×2 array of E-shaped folded strip elements and four metalized through-holes. The microstrip line, located on the underside of an extremely thin dielectric substrate, utilizes a cross-shaped slot for its coupled feeding mechanism. This configuration markedly enhances the compatibility with circuits at millimeter-wave frequencies and also offers the advantage of a low-profile design. The simulated performance of the antenna module shows an impedance bandwidth covering 71%, extending from 21.43 GHz to 45 GHz, along with a peak gain of 5.925 dBi. Moreover, it maintains a cross-polarization discrimination level that is greater than 25 dB. To demonstrate the wideband and high-gain characteristics, a 2 × 2 array of linearly polarized antennas has been crafted, featuring a straightforward microstrip feed system and eliminating the necessity for an extra enclosure made of dielectric material. The simulated data reveal commendable characteristics regarding impedance correlation, gain, and the patterns of radiation, rendering the array well-suited for deployment in millimeter-wave applications designated as N259 and N260. © 2024 IEEE.

关键词： Millimeter waves

来源：评论

学校读者我要写书评

暂无评论

Intelligent personalised learning system based on emotions in e-learning

引用

Personal and Ubiquitous Computing 2023年第6期27卷 2211-2223页

作者： Karthika, R. Jesi, V. Elizabeth Christo, Mary Subaja Deborah, L. Jegatha Sivaraman, Audithan Kumar, Sanjeev Department of Computer Science and Engineering University College of Engineering Tindivanam Tamil Nadu Melpakkam604001 India Department of Networking and Communications School of Computing College of Engineering SRM Institute of Science and Technology Chennai Kattankulathur603203 India Department of Information Technology Netaji Subhas University of Technology New Delhi110078 India Department of Electronics and Communication Engineering Netaji Subhas University of Technology New Delhi110078 India

One of the greatest challenges in the success of a personalised e-learning system lies in the behaviour identification of the learners during the learning and evaluation phase. The content delivery in an e-learning system must be modified and updated periodically according to the preference and behaviour of the learners. Usually, the behaviour of the learners drastically changes according to their affective states during the learning phase. The accurate identification of the learner’s negative emotions and addressing such emotions carefully in a positive sense can greatly provide success to the learners. In this paper, the learner’s emotions especially frustration emotion are automatically and accurately estimated using the information received from learning management systems (LMS) using the Takagi sugeno fuzzy inference engine. Based on this estimation, several motivational messages are distributed according to the identified emotions which had greatly helped them to succeed during e-learning. The motivational messages that are used for sending to the learners are based on regulatory fit theory. Several kinds of statistical tests are used in this paper for deep analysis. Two sets of learners, namely, control and experimental sets, are identified from undergraduate students. Experimental results are shown for these two sets to reveal the increase in their emotional strength after receiving the motivational messages. Statistical analysis t-test is also applied to the two sets, and the experimental results have shown that there is a significant difference between the two groups which shows the dominance of the proposed system. © 2023, The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature.

关键词： E-learning

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：