检索结果-内蒙古大学图书馆

Intelligent Systems for Cybersecurity (ISCS), International Conference on

作者： R. Geetha D Jayakumar S. Rukmani Devi S. Senthurya Akhila Akula R. Karthiga Department of Electrical and Electronics Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai Tamil Nadu India Department of Computer Science and Engineering R.M.D. Engineering College Chennai Tamil Nadu India Department of Computer Science and Engineering Prince Shri Venkateshwara Padmavathy Engineering College Chennai Tamil Nadu India Department of Computer Science Saveetha College of Liberal Arts and Sciences SIMATS Deemed to be University Chennai Tamil Nadu India Department of ECE MLR Institute of Technology Hyderabad India Department of IT R.M.K Engineering College Chennai Tamil Nadu India

ISBN: (数字)9798350375237

ISBN: (纸本)9798350375244

Data security is of the utmost importance in wireless sensor networks due to the massive amounts of data collected and sent between nodes. An improved security method for wireless sensor networks is presented in this paper. This mechanism takes into account the application, the security level, and the bit error rate simultaneously. In order to provide the user with the ability to select between unsecure and secure modes, we made use of reserved bits of the frame control field that are contained within the communication header. The Secured and Intelligent Data Transmission Protocol (SIDTP) is the name of the unified perceptual information transmission model that is established in this research. Its purpose is to compensate for the unequal distribution of cognitive radio users across different wireless LANs. For the purpose of determining whether or not the suggested scheme is effective, the proposed model will be cross-validated with the traditional data transmission model known as Wireless Data Transmission Protocol (WDTP). The approach has the potential to optimize the utilization of spectrum resources in an efficient manner. In addition, to help lessen the risks connected with wireless networks, this study lays out a technique for transmitting data using cyclic delay full diversity sensing information coding. In order to evaluate the performance of the system against a variety of correlation coefficients, we developed a system simulation model. The result of the study showed that cyclic delay diversity systems had overall interference intensity similar to frequency division duplex as well as time division duplex. As an added bonus, this enhances its anti-jamming attack capabilities. The proposed system has been planned and implemented, and significant trials have been carried out in an industrial setting. Additionally, a prototype of the system has been designed. Compared to conventional communication interfaces that are only equipped with a single wireless interf

关键词： Wireless communication Wireless sensor networks Protocols Wireless networks Prototypes Robot sensing systems Data models

来源：评论

学校读者我要写书评

暂无评论

Thai Beef Cattle Recognition for Fattening Farms: An Empirical Study of Cattle Cooperative Practices in Chiang Rai

Thai Beef Cattle Recognition for Fattening Farms: An Empiric...

引用

International ECTI Northern Section Conference on electrical, Electronics, computer and Telecommunications engineering (ECTI-NCON)

作者： Ant Maw Khon Myint Myat Pradorn Sureephong Qing Fan Santichai Wicha School of Applied Digital Technology Mae Fah Luang University Chiang Rai Thailand College of Arts Media and Technology Chiang Mai University Chiang Mai Thailand Key Laboratory of China(Guangxi)-ASEAN CrossBorder Animal Disease Prevention and Control Ministry of Agriculture and Rural Affairs of China Guangxi Veterinary Research Institute Guangxi China Computer and Communication Engineering for Capacity Building (CCC) School of Applied Digital Technology Mae Fah Luang University Chiang Rai Thailand

ISBN: (数字)9798331543273

ISBN: (纸本)9798331543280

This research focuses on developing an automated system to identify the breed and sex of Thai beef cattle using advanced computer vision technology. By using the YOLOv11 (You Only Look Once) model, a state-of-the-art object detection tool, this system can quickly and accurately identify cattle breeds and determine their sex. High-resolution image datasets were collected and augmented, yielding 81.2% accuracy for breed detection and 95.0% for sex classification, with mAP@50 scores of 85.1% and 99.3%, respectively. However, limited data for certain breeds, like Thai Native and Japanese cattle, reduced the model’s performance for those categories. To overcome this, we aim to expand the dataset from CCTV footage in future studies. The system will include user-friendly features, such as real-time alerts and dashboards, making it practical for farmers to use. This project demonstrates how AI can improve cattle farming by saving time, reducing errors, and supporting better decisions. Future improvements will explore applications in disease detection and behavior monitoring.

关键词： YOLO Deep learning computer vision Cows Real-time systems Data models Object recognition Monitoring Farming Diseases

来源：评论

学校读者我要写书评

暂无评论

Predicting the Porosity of As-Built Additive Manufactured Samples Based on Machine Learning Method for Small Datasets

SSRN

引用

SSRN 2023年

作者： Pi, Qingyang Li, Rui Han, Bin Yang, Kun Hu, Yang Shi, Yan Qi, Huan Li, Wei Bi, Kedong Sun, Guifang School of Mechanical Engineering Southeast University Nanjing211189 China School of Automation Science and Electrical Engineering Beihang University Beijing100191 China Nanjing Huirui Photoelectric Technology Co. LTD. Nanjing211121 China School of Artificial Intelligence and Computer Science Jiangsu Key Laboratory of Media Design and Software Technology Jiangnan University Jiangsu China

With the widespread application of Machine Learning (ML) to explore the process-structure-property (PSP) relationships in the field of Additive Manufacturing (AM), the accuracy of data is critical to the performance of established ML models for small datasets. In this study, the DBCSCAN algorithm is applied to identify and remove noise points from the porosity dataset of IN718 as-built parts fabricated by quasi-continuous wave (QCW) laser direct metal deposition (DMD), aiming to enhance the dataset's quality and consequently improve the predictive performance of the model. The fitting degree and prediction performance of the ML model were significantly enhanced by appropriately eliminating noise points, as evidenced by the substantial improvement in R2 scores from 0.367 and 0.546 to 0.915 and 0.959 for the training and test sets, respectively. Meanwhile, SVR was applied to generate process parameter maps to reveal the effect of process parameters (such as laser peak power, scanning speed, powder feeding rate and pulse frequency) on the porosity of the components. Experimental validation was carried out using the optimized combinations of process parameters, thereby further demonstrating the enhanced accuracy of the ML model trained with the improved quality dataset. © 2023, The Authors. All rights reserved.

关键词： Porosity

来源：评论

学校读者我要写书评

暂无评论

A Toolbox of Feminist Wonder: Theories and methods that can make a difference 26

A Toolbox of Feminist Wonder: Theories and methods that can ...

引用

26th ACM Conference on computer-Supported Cooperative Work and Social Computing, CSCW 2023

作者： Hansson, Karin Bardzell, Shaowen Bhandari, Aparajita Boulicault, Marion Doyle, Dylan Thomas Erete, Sheena Cerratto Pargman, Teresa Lazem, Shaimaa Muller, Michael Normark, Maria Petterson, Adrian Rosén, Anton Poikolainen Taylor, Alex S. Thomas, Jakita O. Watson, Julia Södertörn University The School of Natural Sciences Technology and Environmental Studies Sweden Georgia Institute of Technology The School of Interactive Computing United States Cornell University Department of Communication United States University of Edinburgh Department of Philosophy United States University of Colorado Boulder Department of Information Science United States University of Maryland College of Information United States Stockholm University The Department of Computer and Systems Sciences Sweden City for Scientific Research and Technological Applications The Informatics Research Institute Egypt Ibm Research Human Centered Ai United States Uppsala University Department of Informatics and Media Sweden University of Toronto Faculty of Information Canada Aalto University The School of Arts Design and Architecture Finland City University of London The Centre for Human Computer Interaction Design United Kingdom Auburn University Department of Computer Science and Software Engineering United States University of Toronto Department of Computer Science Canada

ISBN: (纸本)9798400701290

This one-day hybrid workshop builds on previous feminist CSCW workshops to explore feminist theoretical and methodological approaches that have provided us with useful tools to see things differently and make space for change. Since its inception over a decade ago, feminist HCI has progressed from the margins to mainstream HCI, with numerous references in the literature. Feminist HCI has also evolved to incorporate other critical HCI practices such as Queer HCI, participatory design, and speculative design. While feminist approaches have grown in popularity and become mainstream, it is getting more difficult to distinguish the feminist emancipatory core from other attempts of developing and improving society in various ways. In this workshop, we therefore want to revisit our feminist roots, where theory is a liberatory and creative practice, motivated by affect, curiosity, and wonder. From this standpoint, we consider which of our feminist tools can make a significant difference today, in a highly datafied world. The goal of this workshop is to;1) create an inventory of feminist theories and concepts that have had an impact on our work as designers, educators, researchers, and activists;2) develop a feminist toolbox for the CSCW community to strengthen our feminist literacy. © 2023 Owner/Author.

关键词： Computation theory

来源：评论

学校读者我要写书评

暂无评论

Telemedicine Platforms with Cloud-Based AI-Driven Diagnostics in Hospitals

Telemedicine Platforms with Cloud-Based AI-Driven Diagnostic...

引用

Visual Analytics and Data Visualization (ICVADV), International Conference on

作者： S. Thangalakshmi N. Mohankumar L.N. Jayanthi Y M Blessy R. Meenakshi M. Rajmohan Faculty – Electrical School of Marine Engineering and Technology Indian Maritime University Chennai Tamil Nadu India Symbiosis Institute of Technology Symbiosis International (Deemed University) Pune India Department of Commerce Saveetha College of Liberal Arts and Sciences Saveetha Institute of Medical and Technical Sciences (SIMATS) Saveetha University Chennai Tamil Nadu India Department of Electronics and Communication and Engineering R.M.K. Engineering College Chennai Tamil Nadu India Department of Computer Science and Engineering Chennai Institute of Technology Chennai Tamil Nadu India Department of Electronics and Communication Engineering Hindustan Institute of Technology and Science Chennai Tamil Nadu India

ISBN: (数字)9798331521394

ISBN: (纸本)9798331521400

Hospitals may benefit greatly from telemedicine technologies, including cloud-based artificial intelligence (AI)-driven diagnostics. Regardless of location, instantaneous access to medical knowledge is made possible by these systems that allow for virtual consultations between patients and healthcare practitioners. Critical patient data is always available during consultations due to these systems' use of cloud computing to safely store and handle massive volumes of data. The use of AI-powered diagnostics improves the precision and effectiveness of diagnoses. To help healthcare providers make informed decisions, machine learning algorithms examine patient data, including medical imaging, test findings, and clinical notes. Faster and more accurate diagnoses are possible with the help of this technology since it can spot patterns and abnormalities that human practitioners may miss. Hospitals can streamline their workflow using telemedicine technologies that use AI for diagnoses. They improve the efficiency of patient triage, the prioritization of critical situations, and the allocation of resources. Better healthcare delivery, shorter wait times, and improved patient outcomes are the effects of this.

关键词： Cloud computing Accuracy Hospitals Telemedicine Visual analytics Streaming media Sensitivity and specificity Resource management Artificial intelligence Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

A Lightweight Controller for Autonomous Following of a Target Platform for Drones

A Lightweight Controller for Autonomous Following of a Targe...

引用

Cybernetics and Innovations (ICCI), International Conference on

作者： Aadil Farooq Sadman Shafi Zahid Ullah Moomal Quresh Narumol Chumuang Dept. of Electrical and Computer Engineering UCY Cyprus Dept. of Electrical Engineering Penn State University United States Dept. of Electronics information and Bioengineering Politecnico di Milano Italy University of Lyon CNRS INSA-Lyon Universite Claude Bernard Lyon 1 France Dept. of Digital Media Technology Muban Chombueng Rajabhat University Thailand

Drones or Unmanned Aerial Vehicles (UAVs) are providing interminable opportunities to capture high-quality video feeds that were previously impossible and have transformed the digital era. Many applications today require computer vision (CV) and machine learning (ML) techniques to extract the useful information captured from the onboard camera, and send it to an embedded controller that can make independent decisions. For instance, maneuvering the drone to follow a target platform by using only the onboard camera feed is critical in target tracking. Therefore, in this paper, we exploit the applicability of a low-computational embedded tracking controller to follow a target platform e.g. a car or pedestrian, and thus, react in real-time, adjusting the drone steering angles and velocity. We developed a system that enables drones to follow a target platform autonomously without requiring continuous human intervention on an embedded state-of-the-art STM32 Nucleo board. The system includes a lightweight controller that controls the drone's movement and enables it to track and follow a target platform accurately. To validate the performance of our embedded controller, we performed a number of experiments in an open-source AirSim simulator. The tracking controller footprint and memory consumption was less than 3%, and was able to reliably track and trail the target platform in different environmental conditions.

关键词： Technological innovation Target tracking Military computing Memory management Cameras Real-time systems Feeds

来源：评论

学校读者我要写书评

暂无评论

A Privacy-Preserving Framework with Multi-Modal Data for Cross-Domain Recommendation

arXiv

引用

arXiv 2024年

作者： Wang, Li Sang, Lei Zhang, Quangui Wu, Qiang Xu, Min School of Electrical and Data Engineering University of Technology Sydney 15 Broadway Ultimo SydneyNSW2000 Australia School of Computer Science and Technology Anhui University 111 Jiulong Road Economic and Technological Development District Hefei230601 China School of Artificial Intelligence Chongqing University of Arts and Sciences 319 Honghe Avenue Yongchuan District Chongqing402160 China

Cross-domain recommendation (CDR) aims to enhance recommendation accuracy in a target domain with sparse data by leveraging rich information in a source domain, thereby addressing the data-sparsity problem. Some existing CDR methods highlight the advantages of extracting domain-common and domain-specific features to learn comprehensive user and item representations. However, these methods can't effectively disentangle these components as they often rely on simple user-item historical interaction information (such as ratings, clicks, and browsing), neglecting the rich multi-modal features. Additionally, they don't protect user-sensitive data from potential leakage during knowledge transfer between domains. To address these challenges, we propose a Privacy-Preserving Framework with Multi-Modal Data for Cross-Domain Recommendation, called P2M2-CDR. Specifically, we first design a multi-modal disentangled encoder that utilizes multi-modal information to disentangle more informative domain-common and domain-specific embeddings. Furthermore, we introduce a privacy-preserving decoder to mitigate user privacy leakage during knowledge transfer. Local differential privacy (LDP) is utilized to obfuscate the disentangled embeddings before inter-domain exchange, thereby enhancing privacy protection. To ensure both consistency and differentiation among these obfuscated disentangled embeddings, we incorporate contrastive learning-based domain-inter and domain-intra losses. Extensive Experiments conducted on four real-world datasets demonstrate that P2M2-CDR outperforms other state-of-the-art single-domain and cross-domain baselines. © 2024, CC BY.

关键词： Sensitive data

来源：评论

学校读者我要写书评

暂无评论

BCIM: Budget and capacity constrained influence maximization in multilayer networks

arXiv

引用

arXiv 2024年

作者： Zhang, Su-Su Liu, Chuang Wang, Huijuan Chen, Yang Zhan, Xiu-Xiu Research Center for Complexity Sciences Hangzhou Normal University Hangzhou311121 China College of Media and International Culture Zhejiang University Hangzhou310058 China Faculty of Electrical Engineering Mathematics and Computer Science Delft University of Technology Mekelweg 4 Delft2628 CD Netherlands Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai200433 China

Influence maximization (IM), which aims to select a set of seed nodes that can maximize their influence within a network, can be applied to various domains, such as viral marketing, disease control, and political campaigns. One of the extended IM problems, i.e., budgeted Influence Maximization (BIM), adds a budgeted constraint, which considers that different nodes may have different costs. However, the definition of the current BIM problem has limitations, as it only imposes a budget constraint. This may lead to solutions with a large number of low-cost nodes that are not applicable to real-world scenarios. Furthermore, since users can transmit information on multiple social networking platforms, solving the BIM problem across different platforms could better optimize resource usage. To address these issues, we propose a Budget and Capacity Constrained Influence Maximization (BCIM) problem in multilayer networks and design a Multilayer Multi-Population Genetic Algorithm (MMGA) to solve it. In MMGA, a repair module addresses budget constraints, while a multi-population parallel module handles capacity (seed size) constraints. Additionally, the initialization module, which considers multilayer network properties, and the multi-population parallel module significantly enhance the algorithm's efficiency. Extensive experiments upon various synthetic and empirical multilayer networks indicate that MMGA achieves at least a 10% improvement in spreading performance under budget and capacity constraints compared to baseline methods extended from various classical IM problems. The proposed BCIM problem opens up a new direction in influence maximization, and the proposed method offers an effective and efficient framework to the problem. Copyright © 2024, The Authors. All rights reserved.

关键词： Costs

来源：评论

学校读者我要写书评

暂无评论

Role of Wireless Communications in Digital Economy in the Present Context 6

Role of Wireless Communications in Digital Economy in the Pr...

引用

6th International Conference on Trends in Electronics and Informatics, ICOEI 2022

作者： Revathi, S. Shrivastava, Arpan Yussupova, Ardak Hidayatulloh, A. Nururrochman Saltanat, Daurbekova Mishra, Arpana Sri Ramakrishna Institute of Technology Department of Computer Science and Engineering Coimbatore India Management Devi Ahilya Vishva Vidyalaya Madhya Pradesh India Kazakh National University of Arts Department of Art Studies Nur-Sultan Kazakhstan Universitas Gadjah Mada Leadership and Policy Innovation Program Indonesia International Education Corporation Department of Construction Almaty050042 Kazakhstan Sharda University Electrical Electronics and Communication Engineering Greater Noida India

ISBN: (纸本)9781665483285

Wireless communication has connected millions of people across the world to internet to enable them to reap benefits of digital economy in present scenario. Almost all the sectors of economy including healthcare, agriculture and transportation nowadays rely largely upon wireless communications. In the present context, the sudden outbreak of Covid-19 has caused governments to impose restrictions on various activities and employees have been directed to work from their homes to ensure safety. In such a situation, wireless communication has made it possible to connect with each other via the internet. Apart from this, Smart healthcare-system has been developed through utilisation of wireless communication systems. During this pandemic situation, delivery of healthcare services in remote areas has gained huge momentum and wireless communication plays a vital role in this regard. Aim of current critical assessment is to provide an in-depth analysis of the role played by wireless communication in establishment of a well-structured digital economy in present scenario. In literature-review, different applications of wireless technology via ICT in various sectors and aspects of life have been discussed through a conceptual and a theoretical framework. The Method section of current study has provided an in-depth insight into the ways required information have been collected in this study. As found in the results and discussion section, a positive relation exists between wireless-communication and establishment of digital economy in current situation. This study has concluded that there are certain challenges associated with wireless communication;however, it has significant influence in making processes smarter and faster as compared to earlier. © 2022 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Cloud-Powered Smart Rehabilitation and Assistive Robotics for Stroke Recovery with Recurrent Neural Networks

Cloud-Powered Smart Rehabilitation and Assistive Robotics fo...

引用

Data Intelligence and Cognitive Informatics (ICDICI), International Conference on

作者： M Maria Sampoornam Mothiram Rajasekaran Visumathi J Balachandra Pattanaik S. Kalaichelvi S. Sujatha Department of Information Technology J.J College of Engineering and Technology Tiruchirappalli Tamil Nadu India Pine Candle Way Saint Augustine Florida USA Department of Information Technology Veltech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu India Department of Electrical and Computer Engineering Wollega University Nekemte Ethiopia PG and Research Department of Computer Science and Applications Vivekanandha College of Arts and Sciences for Women (Autonomous) Elayampalayam Tiruchengode Tamil Nadu India Department of Biomedical Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai Tamil Nadu India

ISBN: (数字)9798350389609

ISBN: (纸本)9798350389616

Innovative rehabilitation treatments are needed since stroke is a major cause of long-term impairment globally. In this paper, it presents a smart robotics-assisted rehabilitation system for stroke patients that uses cloud computing and is enhanced using Recurrent Neural Networks (RNNs). The system utilizes a combination of wearable sensors, robotic equipment, and cloud computing to create individualized rehabilitation plans for each patient. To quickly evaluate patients' progress and adjust rehabilitation programs, RNNs are used for real-time processing of continuous sensor data streams. Cloud computing allows for easy scaling, universal accessibility, and compatibility with preexisting healthcare systems. Initial results show promise in enhancing stroke recovery outcomes, highlighting the potential of the proposed method to transform rehabilitation techniques in the smart healthcare realm. The urgent need for effective and tailored stroke rehabilitation programs is something this framework intends to solve, which should lead to better results and a higher quality of life for patients.

关键词： Cloud computing Technological innovation Recurrent neural networks Transforms Stroke (medical condition) Robot sensing systems Real-time systems Wearable sensors Streams Research and development

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：