检索结果-内蒙古大学图书馆

2025 International Workshop on Integrated Nonlinear Microwave and Millimetre-Wave Circuits, INMMiC 2025

作者： Khanehbeygi, Mehran Tatangelo, Giorgio Pantoli, Leonardo Leuzzi, Giorgio University of L'Aquila Dept. of Industrial and Information Engineering & Economics L'Aquila Italy University of L'Aquila Computer Science and Mathematics Dept. of Information Engineering L'Aquila Italy

ISBN: (纸本)9798331519605

This brief presents a Voltage-Controlled Oscillator (VCO) for operation in the mmWave frequency range. The VCO is based on the Colpitts topology, utilising SiGe:C 130 nm bipolar devices. Unlike traditional configurations, the proposed VCO simultaneously provides both a differential output at the fundamental frequency (200 GHz) and a push-push output at the second harmonic (400 GHz). The overall performance is significantly enhanced through the implementation of an innovative Second Harmonic Extraction Network (SHEN), which efficiently captures and utilizes the second harmonic for improved output power and efficiency. © 2025 IEEE.

关键词： Colpitts MMIC mmWave Oscillator SiGe

来源：评论

学校读者我要写书评

暂无评论

Ethical Adaptive Security Algorithm for Cross-Platform IoT-Enabled Metaverse Applications

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Hassan, Mahmood Ul Mahmood, Khalid Khan, Jahangir Altalidi, Askar Javed, Muhammad Wasim Mir, Shamaila Rasheed Najran University Department of Computer Skills Deanship of Preparatory Year 61441 Saudi Arabia Engineering and Technical Specializations Unit Applied College King Khalid University Aseer Muhayil Saudi Arabia University of Hail College of Computer Science and Engineering Dept of Information and Computer Science Saudi Arabia

The prompt expansion of the Metaverse presents challenges for secure and ethical user interactions. Existing security frameworks often lack integration of ethical considerations such as user consent and regulatory compliance. This study develops an Ethical Adaptive Security Algorithm (EASA) that embeds ethical principles into Metaverse security mechanisms. EASA incorporates a dynamic User Consent Management System, modeled as a time-dependent consent function, that gives users control over their data. Integrate ethical parameters into security actions using compliance and transparency functions. The framework employs mathematical constructs, including consent differential equations and optimization problems, to balance user satisfaction and ethical considerations. EASA was evaluated through simulations in MATLAB R2021b and results showed that EASA achieved a detection accuracy of 98.5% in low-traffic scenarios, outperforming existing models by at least 6.2%. © 1975-2011 IEEE.

关键词： MATLAB

来源：评论

学校读者我要写书评

暂无评论

Channel-Aware Domain-Adaptive Generative Adversarial Network for Robust Speech Recognition

Channel-Aware Domain-Adaptive Generative Adversarial Network...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Chien-Chun Wang Li-Wei Chen Cheng-Kang Chou Hung-Shin Lee Berlin Chen Hsin-Min Wang Dept. Computer Science and Information Engineering National Taiwan Normal University Taiwan United-Link Co. Ltd Taiwan Institute of Computer Science Academia Sinica Taiwan

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

While pre-trained automatic speech recognition (ASR) systems demonstrate impressive performance on matched domains, their performance often degrades when confronted with channel mismatch stemming from unseen recording environments and conditions. To mitigate this issue, we propose a novel channel-aware data simulation method for robust ASR training. Our method harnesses the synergistic power of channel-extractive techniques and generative adversarial networks (GANs). We first train a channel encoder capable of extracting embeddings from arbitrary audio. On top of this, channel embeddings are extracted using a minimal amount of target-domain data and used to guide a GAN-based speech synthesizer. This synthesizer generates speech that faithfully preserves the phonetic content of the input while mimicking the channel characteristics of the target domain. We evaluate our method on the challenging Hakka Across Taiwan (HAT) and Taiwanese Across Taiwan (TAT) corpora, achieving relative character error rate (CER) reductions of 20.02% and 9.64%, respectively, compared to the baselines. These results highlight the efficacy of our channel-aware data simulation method for bridging the gap between source- and target-domain acoustics.

关键词： Training Error analysis Synthesizers Phonetics Generative adversarial networks Acoustics Recording Data mining Speech processing Automatic speech recognition

来源：评论

学校读者我要写书评

暂无评论

Cluster Head Selection Algorithm using Machine Learning 4

Cluster Head Selection Algorithm using Machine Learning

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Nidhya, M.S. Gurumoorthi, E. Babu, M. Charumathi, A.C. Naved, Mohd Maram, Balajee School of Computer Applications Dayananda Sagar University Bangalore India School of Engineering Malla Reddy University India Chennai Institute of Technology College Dept of Ai & Ds Chennai India Sona College of Technology Dept of Information Technology India Jaipuria Institute of Management Dept of Business Analytics Noida India School of Computer Science and Artificial Intelligence Sr University Ananthasagar Hasanparthy Warangal India

ISBN: (纸本)9798331523923

Wireless Sensor Networks (WSNs) find extensive applications in environmental monitoring, healthcare, and smart cities. Energy efficiency, however, continues to be a significant challenge with the limited lifetime of sensor node batteries. The conventional heuristic-based cluster head (CH) selection techniques tend not to adapt dynamically to network changes, resulting in inefficient energy utilization and decreased network lifetime. This research discusses Machine Learning (ML)-oriented CH selection approaches to improve energy efficiency, network lifetime, and data fusion. Using supervised and unsupervised learning methods, ML algorithms are able to learn optimal CHs dynamically based on residual energy, network structure, and data traffic. The comparative analysis show that ML-based CH selection enhances network stability by 95% and lowers energy consumption by 50% compared to traditional methods. The research points to the promise of ML in WSN performance optimization and opens the doors to intelligent, adaptive clustering technologies. © 2025 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

LNPP: Logical Neural Path Planning of Mobile Beacon for Ocean Sensor Networks in Uncertain Environments using Hierarchical Reinforcement Learning

引用

IEEE Transactions on Network science and engineering 2025年

作者： Wang, Weijun Wu, Huafeng Yang, Shenhua Mei, Xiaojun Han, Dezhi Marino, Mario D. Li, Kuan-Ching Jimei University Navigation College Xiamen361021 China Shanghai Maritime University Merchant Marine College Shanghai201306 China Shanghai Maritime University College of Information Engineering Shanghai201306 China Department of Computer Science Oslomet Norway Providence University Dept. of Computer Science and Information Engineering Taichung43301 Taiwan

Localization of sensor nodes is a critical issue in Ocean Sensor Networks (OSNs). A key feature of these methods is the use of GPS-enabled mobile beacons that periodically broadcast their locations through path planning to achieve sensor localization. However, mobile beacons in OSNs are vulnerable to wind, waves, and currents, which prevent them from following pre-planned paths. Additionally, existing path planning algorithms are not suitable for handling uncertain obstacles and disturbances in OSN environments. To address these challenges, this article introduces a novel Logic Neural Path Planning (LNPP) scheme for mobile beacons. LNPP incorporates logical rule knowledge into its neural network in order to enhance learning efficiency and reduce unnecessary explorations. Furthermore, to effectively learn strategies across different time scales, a hierarchical reinforcement learning algorithm is proposed. The experimental results demonstrate that, compared to other methods, the proposed path planning scheme reduces the average localization time and the trajectory length by over 21 percent in obstacle-free OSN environments. Moreover, our scheme effectively operates in OSNs with uncertain obstacles. © 2013 IEEE.

关键词： deep reinforcement learning logic neural networks mobile beacon Ocean sensor networks path planning

来源：评论

学校读者我要写书评

暂无评论

Automatic Vehicle Detection using DETR: A Transformer-Based Approach for Navigating Treacherous Roads

arXiv

引用

arXiv 2025年

作者： Fahad, Istiaq Ahmed Arean, Abdullah Ibne Hanif Ahmed, Nazmus Sakib Hasan, Mahmudul Institute of Information Technology University of Dhaka Dhaka Bangladesh Dept. of Computer Science and Engineering University of Dhaka Dhaka Bangladesh

Automatic Vehicle Detection (AVD) in diverse driving environments presents unique challenges due to varying lighting conditions, road types, and vehicle types. Traditional methods, such as YOLO and Faster R-CNN, often struggle to cope with these complexities. As computer vision evolves, combining Convolutional Neural Networks (CNNs) with Transformer-based approaches offers promising opportunities for improving detection accuracy and efficiency. This study is the first to experiment with Detection Transformer (DETR) for automatic vehicle detection in complex and varied settings. We employ a Collaborative Hybrid Assignments Training scheme, Co-DETR, to enhance feature learning and attention mechanisms in DETR. By leveraging versatile label assignment strategies and introducing multiple parallel auxiliary heads, we provide more effective supervision during training and extract positive coordinates to boost training efficiency. Through extensive experiments on DETR variants and YOLO models, conducted using the BadODD dataset, we demonstrate the advantages of our approach. Our method achieves superior results, and improved accuracy in diverse conditions, making it practical for real-world deployment. This work significantly advances autonomous navigation technology and opens new research avenues in object detection for autonomous vehicles. By integrating the strengths of CNNs and Transformers, we highlight the potential of DETR for robust and efficient vehicle detection in challenging driving environments. © 2025, CC BY.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Live Audio Recognition and Text Conversion System

Live Audio Recognition and Text Conversion System

引用

Computational Intelligence, Communication Technology and Networking (CICTN), International Conference on

作者： Pratyaksha Sharma Sumita Gupta Boddu Asmitha Bhavya Khushi Sharma Saru Dhir Sapna Gambhir Department of Computer Science & Engineering Amity School of Engineering & Technology Amity University UP Department of Information Technology Amity School of Engineering & Technology Amity University UP Dept. of Computer Science College of Engineering and Computing George Mason University USA

ISBN: (数字)9798331530389

ISBN: (纸本)9798331530396

With the advancement of technologies, different methods are currently being used for converting spoken language into text. These systems offer a hands-free alternative to traditional input methods, especially for individuals with physical disabilities or those requiring efficient documentation of spoken content. The goal of this study is to review recent advancements in this field and highlight gaps in current research, with a focus on accuracy, language adaptability, ease of use, and the integration of various technologies. We also suggest future directions for enhancing and developing this technology further.

关键词： Accuracy Text recognition Reviews Hidden Markov models Speech recognition Machine learning Documentation Natural language processing Communications technology Computational intelligence

来源：评论

学校读者我要写书评

暂无评论

Deepfake Image Detection using Deep Learning

Deepfake Image Detection using Deep Learning

引用

Artificial Intelligence and Data engineering (AIDE), International Conference on

作者： Arun Kumar S Anand Kumar M Robin Rohit Vincent Uttam Upendra Hegde Anusha M S N Nauman Pasha Dept. of Computer Studies Symbiosis Institute of Computer Studies and Research (SICSR) Pune India Dept. of Information Science and Engineering Bio-Intelligence Lab Presidency University Bangaluru India Dept. of Computer Science and Engineering Bio-Intelligence Lab Presidency University Bangaluru India

ISBN: (数字)9798331527518

ISBN: (纸本)9798331527525

Deepfake images are generated by modifying existing visuals and are frequently exploited in harmful ways. When executed proficiently, these images can be almost indistinguishable from authentic ones. The increasing development of deep learning techniques has largely fueled the increase in deepfake content. While numerous techniques are available for creating deepfake images, the most commonly employed are GANs and autoencoders. This paper presents a way to make deepfake detection more accurate by using a combination of the YOLOv8 model and a Recurrent Neural Network (RNN). YOLOv8 extracts spatial details from the images, while the RNN identifies temporal patterns and subtle irregularities across image frames, signaling potential manipulation. This methodology presents an efficient solution for identifying deepfake images and reducing their misuse.

关键词： YOLO Deep learning Deepfakes Adaptation models Analytical models Visualization Recurrent neural networks Accuracy Computational modeling Faces

来源：评论

学校读者我要写书评

暂无评论

Detection of Brain Tumor Using a Deep Learning Approach

Detection of Brain Tumor Using a Deep Learning Approach

引用

Artificial Intelligence and Data engineering (AIDE), International Conference on

作者： Arun Kumar S Anand Kumar M Robin Rohit Vincent Anusha M S Uttam Upendra Hegde N Nauman Pasha Dept. of Computer Studies Symbiosis Institute of Computer Studies and Research (SICSR) Pune India Dept. of Information Science and Engineering Networks & IoT Lab Presidency University Bangaluru India Dept. of Computer Science and Engineering Bio-Intelligence Lab Presidency University Bangaluru India

ISBN: (数字)9798331527518

ISBN: (纸本)9798331527525

This study introduces a deep learning-based method for classifying brain tumors using a pre-trained VGG19 convolutional neural network (CNN). By leveraging transfer learning, we adapted the VGG19 model with custom fully connected layers and trained it on MRI images to differentiate between tumor and non-tumor cases. The model’s architecture includes dropout layers to minimize overfitting and enhance generalization while maintaining the robust feature extraction capabilities of the VGG19 base. We developed a Flask web application interface to make the model accessible via web-based user input, allowing users to upload MRI images and receive immediate predictions on tumor presence. Preliminary results show that proposed model can accurately classify brain tumor images with high accuracy, highlighting the potential of deep learning in automating brain tumor diagnostics. This tool could significantly aid clinicians in making rapid and accurate diagnoses, ultimately improving patient outcomes.

关键词： Deep learning Adaptation models Accuracy Magnetic resonance imaging Transfer learning Brain tumors Predictive models Brain modeling Convolutional neural networks Reliability

来源：评论

学校读者我要写书评

暂无评论

Automated Traffic Light Control System for Ambulance Using Laser Signals and Raspberry Pi

Automated Traffic Light Control System for Ambulance Using L...

引用

Artificial Intelligence and Data engineering (AIDE), International Conference on

作者： Arun Kumar S Anand Kumar M Robin Rohit Vincent Anusha M S Uttam Upendra Hegde N Nauman Pasha Dept. of Computer Studies Symbiosis Institute of Computer Studies and Research (SICSR) Pune India Dept. of Information Science and Engineering Networks & IoT Lab Presidency University Bangaluru India Dept. of Computer Science and Engineering Networks & IoT Lab Presidency University Bangaluru India

ISBN: (数字)9798331527518

ISBN: (纸本)9798331527525

Urban traffic congestion poses a major challenge, particularly for emergency services like ambulances, where delays can have life-threatening consequences. This paper proposes a novel, cost-efficient Automated Traffic Light Control System aimed at prioritizing ambulances at busy intersections, thereby reducing delays and ensuring faster response times. The system utilizes Raspberry Pi Zero 2W, Laser Diodes (KY-008), and Light Dependent Resistors (LDRs) to detect ambulances and dynamically control traffic lights. Unlike traditional systems relying on GPS or RFID technologies, this laser-based approach offers greater precision and affordability through the use of modulated laser signals. Experimental results reveal that this system reduces ambulance response times by 35%. The tests were conducted under simulated urban conditions, highlighting the system's capability to outperform conventional solutions. The simplicity of integration and real-time responsiveness underscore its potential for widespread urban adoption.

关键词： Resistors Semiconductor lasers Traffic control Emergency services Road safety Real-time systems Delays Time factors Traffic congestion Radiofrequency identification

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：