检索结果-内蒙古大学图书馆

6D Movable Antenna Enhanced Interference Mitigation for Cellular-Connected UAV Communications

IEEE Wireless Communications Letters 2025年第6期14卷 1618-1622页

作者： Ren, Tianshi Zhang, Xianchao Zhu, Lipeng Ma, Wenyan Gao, Xiaozheng Zhang, Rui The School of Information and Electronics Beijing Institute of Technology Beijing100081 China The Department of Electrical and Computer Engineering National University of Singapore Singapore117583 Singapore The Provincial Key Laboratory of Multimodal Perceiving and Intelligent Systems China The Engineering Research Center of Intelligent Human Health Situation Awareness of Zhejiang Province Jiaxing University Jiaxing314001 China School of Science and Engineering Shenzhen Research Institute of Big Data The Chinese University of HongKong Guangdong Shenzhen518172 China

Cellular-connected unmanned aerial vehicle (UAV) communications is an enabling technology to transmit control signaling or payload data for UAVs through cellular networks. Due to the line-of-sight dominant air-to-ground channels, efficient interference mitigation is crucial to UAV communications, while the conventional fixed-position antenna (FPA) arrays have limited degrees of freedom to suppress the interference between the UAV and its non-associated co-channel base stations (BSs). To address this challenge, we propose in this letter a new approach by utilizing the six-dimensional movable antenna (6DMA) arrays to enhance the interference mitigation for the UAV. Specifically, we propose an efficient block coordinate descent algorithm to iteratively optimize the antenna position vector, array rotation vector, receive beamforming vector, and associated BS of the UAV to maximize its signal-to-interference-plus-noise ratio. Numerical results show that the proposed 6DMA enhanced cellular-connected UAV communication can significantly outperform that with the traditional FPA arrays and other benchmark schemes in terms of interference mitigation. © 2025 IEEE. All rights reserved.

关键词： Aircraft communication

来源：评论

学校读者我要写书评

暂无评论

Development of Framework for Embedding Ethical AI in engineering Curriculums

Development of Framework for Embedding Ethical AI in Enginee...

引用

IEEE Education engineering (EDUCON)

作者： King Harold A. Recto Romano Q. Neyra Antipas T. Teologo Department of Electronics Computer and Communications Engineering Ateneo de Manila University Quezon City Philippines Senior Director for Engineering Office FEU Institute of Technology Manila Philippines Electronics Engineering Department FEU Institute of Technology Manila Philippines

ISBN: (数字)9798331539498

ISBN: (纸本)9798331539504

The fast progression of Artificial Intelligence (AI) technology has elicited substantial ethical issues, especially within engineering fields that directly impact society. This study seeks to establish a framework for integrating Ethical AI ideas into engineering curriculum, therefore preparing future engineers to address the moral, social, and legal ramifications of AI. The framework incorporates Ethical AI principles into current course formats, encompassing introductory, enabling, and demonstrative courses, with particular focus on subjects like Science, technology, and Society, Professional engineering Ethics, and thesis/capstone projects. The paper recommends a curriculum update that complies with industry norms and equips students to embrace responsible AI practices, based on a thorough analysis of pertinent Commission on Higher Education (CHED) Memorandum Orders (CMOs) and literature. The research also presents evaluation rubrics to gauge students' comprehension and implementation of Ethical AI concepts in their academic projects. The paper suggests that integrating Ethical AI into engineering education enables universities to cultivate engineers who possess both technical proficiency and a robust ethical framework about AI technology.

关键词： Industries Ethics Law Employment Curriculum development Artificial intelligence engineering education

来源：评论

学校读者我要写书评

暂无评论

Emotion Recognition from Mizo Speech: A Signal Processing Approach

Emotion Recognition from Mizo Speech: A Signal Processing Ap...

引用

2022 IEEE International Conference on Distributed Computing and Electrical Circuits and electronics, ICDCECE 2022

作者： Mangalam, Aditya Raj Singh, Sudeep Lalremtluanga, C. Kumar, Prakash Das, Ranjita Basu, Joyanta Chatterjee, Saibal National Institute of Technology Mizoram Department of Electrical and Electronics Engineering Aizawl India National Institute of Technology Mizoram Department of Computer Science and Engineering Aizawl India Cdac Kolkata Kolkata India

ISBN: (纸本)9781665483162

As humans, the most natural way for expressing feelings and communicating is verbal speech. Communication with machines is done either by traditional input methods i.e., keyboard, joystick or with the help of speech recognition technology. The speech recognition mostly works on an average input of user but it lags the instant response, based on the mood of the user and the emotional feature of communication. Emotion recognition is one of the most popular and expanding research domain in recent years. The world is moving towards the functioning of machines with less manual input. Human-computer interaction can be improved by emotions recognition, reducing the need for human intervention. The paper presents an emotion recognition system developed by utilizing the different machine learning techniques that helps to process and classify speech signals to detect emotions. The input to the system are speech audios that were recorded in the Mizo language, the native language of Mizoram, India. To develop the emotion recognition system, seven basic emotions i.e., Anger, Disgust, Fear, Happiness, Neutral, Sadness and Surprise, were analyzed from emotional speech signals. Further, to extract the features from audio signals, signal processing methods have been used. In this work twelve features were extracted, those are Autocorrelation, Chroma, Fundamental frequency, Zero-crossing rate, Short-time energy, RMS, Periodogram, LPCC, MFCC etc. The extracted features were used to train four classifiers namely Decision tree, KNN, SVM and Ensemble. At last, a model was prepared with the combination of classifiers that recognizes the emotion of the signal. The emotion recognition system recognizes single emotions as well as mixed types of emotions. The insights gained may be helpful in a wide range of applications. © 2022 IEEE.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Audio-based tissue classification - preliminary investigation for a needle procedure

引用

Current Directions in Biomedical engineering 2023年第1期9卷 347-350页

作者： Serwatka, Witold Heryan, Katarzyna Sorysz, Joanna Illanes, Alfredo Boese, Axel Krombach, Gabrielle A. Friebe, Michael Faculty of Computer Science Electronics and Telecommunications AGH University of Science and Technology al. A. Mickiewicza 30 Kraków Poland Department of Measurement and Electronics AGH University of Science and Technology Kraków Poland Intelligente Katheter Otto-von-Guericke Universtät Magdeburg Germany Department of Diagnostic and Interventional Radiology University Hospital Justus-Liebig-University Giessen Germany Department of Biocybernetics and Biomedical Engineering AGH University of Science and Technology Kraków Poland

Image-guided and minimally invasive procedures still require confirmation on having reached a target. Intraoperative imaging is not always sufficient or conclusive as it comes with artifacts that can come with a certain amount of ambiguity and inaccurate location information. As an alternative to imaging, we want to explore sounds produced by the biopsy needle tip while advancing and interacting with tissue. In this paper, we show that by analyzing vibroacoustic signals acquired at the proximal end of the needle we are able to differentiate the tissue type. In total, 419 audio samples of 5 tissues were acquired and converted to spectrograms used as input to a convolutional neural network. Using this experimental setup we were able to differentiate the tissue types with an F1 score of 71.64%. Based on these results we were able to demonstrate the feasibility of our approach, as well as the importance of further experiments to ensure that vibroacoustic sounds produced by the needle tip can be a new navigation method. © 2023 the author(s), published by Walter de Gruyter Berlin/Boston.

关键词： Needles

来源：评论

学校读者我要写书评

暂无评论

A Superficial Learning Strategy to Identify Email Spams Based on Hybrid Data Filtration and Classification Methodology

A Superficial Learning Strategy to Identify Email Spams Base...

引用

2024 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems, ICSES 2024

作者： Alekhya, A. Tagore Kumar, P. Bharaneedharan, M. Kavitha, S. Geetha, C. Thyagarajan, C. Qis College of Engineering and Technology Department of Electrical and Electronics Engineering Andhra Pradesh Ongole India Qis College of Engineering and Technology Department of Mechanical Engineering AndhraPradesh Ongole India S.A. Engineering College Department of Ece Chennai India Vel Tech High Tech Dr. Rangarajan Dr. Sakunthala Engineering College Department of Cse Chennai India R.M.K. Engineering College Chennai Department of Computer Science and Engineering Chennai India Panimalar Engineering College Department of Cse Chennai India

ISBN: (纸本)9798331543617

Spam email detection is a critical task in improving email security, especially with the increasing volume of spam emails that threaten users' privacy and productivity. In this study, we propose a hybrid approach combining Gated Recurrent Units (GRU) and Support Vector Machine (SVM) to identify spam emails effectively. The GRU component captures temporal dependencies in the email text, while SVM classifies the extracted features into spam or non-spam categories. The model was evaluated using various performance metrics, including accuracy, precision, recall, and F1-score, and compared with other models like standalone GRU, SVM, CNN, and Naive Bayes. The proposed hybrid GRU-SVM model achieved a superior accuracy of 96.8%, outperforming GRU (93.2%), SVM (91.5%), CNN (94.1%), and Naive Bayes (89.4%). Additionally, the model demonstrated a high true positive rate (98.2%) and a low false negative rate (1.8%) on a spam-heavy dataset, indicating its robustness in identifying spam emails. The results suggest that the hybrid model can significantly enhance spam email detection systems by improving classification accuracy and reducing false positives. © 2024 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Approach for Performance Analysis of Secure SDN-Industrial Networks

Deep Learning Approach for Performance Analysis of Secure SD...

引用

Next Generation Communication & Information Processing (INCIP), International Conference on

作者： H. Anwar Basha Sudeshna Chakraborty Kavita Rani Tanu Sharma Sweety Rana Pramod Kumar Department of Computer Science and Engineering Rajalakshmi Institute of Technology Chennai India Department of Computer Science and Engineering Galgotias University Greater Noida India Department of Computer Science and Engineering Panipat Institute of Engineering and Technology Panipat Haryana India Department of Electronics and Communication Engineering Central University of Karnataka Kalaburagi India

ISBN: (数字)9798331528140

ISBN: (纸本)9798331528157

Software Defined Networking, represents a contemporary programming paradigm distinguished by its adaptability, stability, premium performance, and configurability, rendering it exceptionally suitable for contemporary real-time, high-bandwidth applications. NFV involves detaching network functions from hardware, virtualizing them as software on servers/cloud. This brings networking benefits and functionalities from traditional hardware setups, housing these functions as software entities within virtualized environments. While SDN aims to dissociate network control and data forwarding tasks from the underlying hardware, NFV targets the abstraction of network forwarding and other network-related functions from the hardware substrate. In the pursuit of enhancing network efficiency, a novel approach involving a hybrid network architecture driven by machine learning techniques is introduced. In the context of this scholarly investigation, NFV is strategically utilized to deploy stateful firewall services, operating as Virtual Network Functions (VNFs) within an SDN framework. This deployment serves a dual purpose: bolstering network security and augmenting network scalability. Conversely, the responsibility of the SDN controller revolves around the formulation of an ensemble of guidelines and principles aimed at averting potentially perilous network connections. To proactively identify conceivable malevolent links and potential targets for cyberattacks, advanced machine learning algorithms are trained employing conventional data on network vulnerabilities. Employing four widely accepted machine learning algorithms, predictions are made concerning the intended target hosts for imminent assaults, leveraging traditional network data as a basis. The empirical investigation harnesses a substantial dataset originating from 19 honeypot servers, revealing an astounding 22 million login attempts from 154 diverse nations. This onslaught involved the participation of over 6,000 uniqu

关键词： Machine learning algorithms Firewalls (computing) Scalability Rendering (computer graphics) Hardware Software Real-time systems Servers Software defined networking Substrates

来源：评论

学校读者我要写书评

暂无评论

A Novel and Accurate Technique For testing PV Modules - - - -Towards Adaptation In Indian PV Industries

A Novel and Accurate Technique For testing PV Modules - - - ...

引用

2022 IEEE Delhi Section Conference, DELCON 2022

作者： Majumdar, Debashis Pal, Sudipta Basu Ganguly, Rajiv University of Engineering and Management Department of Electronics Engineering Kolkata India University of Engineering and Management Department of Computer Science Technology Kolkata India Dean of Science University of Engineering Management Kolkata India

ISBN: (纸本)9781665458832

There are several methods of V-I characterization for solar cells/modules. With the passage of time earlier laborious and slow analog methods is replaced by smarter and faster digital methods. In this course of development, another approach of V-I characterization using suitable supercacitive load has been established by the researchers. PV modules are known to be the fundamental building block for configuring large size (GW level) PV Arrays which have to be designed with due care and special emphasis on the interlinking power losses. So, reliability analysis in terms of module quality and power loss is considered the most valuable task. So, in this paper authors have shown how a user or researchers easily performed the reliability checks using their own set-up. To judge the accuracy and precision of this method authors have carried out V-I characterization of a solar module at different insolations and also verified the linearity of selected electrical parameters of the characteristics against varying levels of insolation. The V-I curves derived from this method have also been compared in this paper with standard test results obtained at ERTL (electronics Regional Test Laboratory), Government of India, in Kolkata using PASAN solar cell testing machine. © 2022 IEEE.

关键词： Solar panels

来源：评论

学校读者我要写书评

暂无评论

Ripeness Classification of Cacao Using Cepstral-Based Statistical Features and Support Vector Machine 4

Ripeness Classification of Cacao Using Cepstral-Based Statis...

引用

4th IEEE International Conference on Artificial Intelligence in engineering and technology, IICAIET 2022

作者： Galindo, Juvy Amor M. Rosal, Jamie Eduardo C. Villaverde, Jocelyn Flores College of Engineering and Technology Cor Jesu College Inc. Digos City Philippines School of Electrical Electronics and Computer Engineering Mapua University Manila Philippines

ISBN: (数字)9781665468374

ISBN: (纸本)9781665468374

High quality fine cocoa beans come from farms on which the cacao is grown, harvested and processed properly. Harvesting under-ripe cacao pods would result in poor-quality yield because it won't have developed all its flavors and aromas and it will not continue to ripen after harvest and not suitable for fermentation. On the other hand, over-ripe cacao pods may germinate and possibly will lead to fungal-infective, defective and generate poor quality yields. The best way of harvesting cacao pods is when it is about to ripe. The conventional way of determining the ripeness of a cacao pod is by manual tapping to get a hollow sound. Hollow sound will indicate ripeness because the cacao beans are no longer tightly packed inside the pod. This paper recommends an approach to classify the ripeness of cacao using the acoustic sensing technology. The device will generate an acoustic signal from cacao pods which was recorded for acoustic signal analysis. Cepstral-based technique was used for feature extraction and Support Vector Machine (SVM) algorithm model and tested using nested cross validation resulted in 94% mean test score. © 2022 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Energy-efficient routing to prevent void holes in heterogeneous 5G wireless sensor network using game theory

Energy-efficient routing to prevent void holes in heterogene...

引用

2023 International Conference on Smart Computing and Application, ICSCA 2023

作者： Mateen, Abdul Ahad, Abdul Zia, Salam Shayea, Ibraheem Ali, Sawsan University of Management and Technology Sialkot Pakistan Istanbul Technical University of Turkey Turkey University of Sialkot Department of Computer Science Sialkot Pakistan Istanbul Technical University Department of Electronics and Communication Engineering Turkey University of Ha'il Department of Computer Science and Engineering Ha'il Saudi Arabia

ISBN: (纸本)9798350347050

Heterogenous 5G wireless Sensor Networks face several constraints throughout the routing process. Reduced costs, minimal energy use, and reliable data transmission between nodes are the primary problems of a heterogenous 5G wireless sensors network. During the transmission process of nodes, vacant holes use the most energy. The two most problematic aspects of heterogenous 5G WSNs are the location mentioned above mistake and the battery drain on individual nodes. However, the network's performance suffers significantly due to data packet loss and excessive energy consumption. Thus, many routing protocols incorporate various energy-saving techniques. In contrast, a routing strategy is suggested in this research to prevent void holes and maximize network stability. In addition, the scalability and efficacy of the proposed protocol are demonstrated by comparing it with state-of-the-art protocols. This study also introduces the idea of location error to increase the network's efficiency. In addition, a scalability study of the suggested systems has been conducted. Extensive simulations were also conducted to evaluate the effectiveness of the proposed technique. The findings confirm that the recommended routing strategy outperforms the competing schemes. © 2023 IEEE.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

Machine Learning for Predicting Energy Consumption in Smart Buildings Using Artificial Adaptive Systems

Machine Learning for Predicting Energy Consumption in Smart ...

引用

2025 International Conference on Multi-Agent Systems for Collaborative Intelligence, ICMSCI 2025

作者： Kocherla, Raviteja Jency, C. Mohan, T. Mani Mallala, Balasubbareddy Manikandaprabu, P. Kanth, Tatiraju V. Rajani Mallareddy University Department of Computer Science & Engineering Telangana Hyderabad500043 India Dr. N.G.P. Institute of Technology Department of Artificial Intelligence and Data Science Coimbatore641048 India Annamacharya University Department of Mechanical Engineering Rajampet516126 India ChaitanyaBharathi Institute of Technology Department of Electrical and Electronics Engineering Telangana Hyderabad500075 India Sona College of Technology Department of Mechanical Engineering Salem636005 India Tvr Consulting Services Private Limited Telangana Hyderabad500040 India

ISBN: (纸本)9798331509828

This study investigates the use of Artificial Adaptive (AA) systems for predicting energy consumption in Smart Buildings, focusing on optimizing energy usage with sensors, actuators, and intelligent systems. Using the CRISP-DM methodology, the research incorporated statistical techniques like PCA and ARIMA models to extract relevant features and identify temporal relationships. Long Short-Term Memory (LSTM) networks were employed to refine prediction models, balancing neurons and training epochs to prevent overfitting or underfitting. The best model, utilizing the first Principal Component, achieved 74% precision. The findings highlight AA systems' potential in energy management, emphasizing the challenges of model precision and resource availability, while offering a foundation for future improvements in predictive modeling. © 2025 IEEE.

关键词： Smart homes

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：