检索结果-内蒙古大学图书馆

Multimedia University engineering Conference (MECON)

作者： H. Ahmed Tahir Fahad Nabi Muhammad Ziad Tariq Ahmad Fasih Khan Azwan Mahmud Faculty of Engineering Multimedia University Cyberjaya Malaysia Department of Electrical Engineering & Information Technology University of Kiel Kiel Germany Department of Computer Science SZABIST University Islamabad Pakistan Roots School System Islamabad Pakistan

ISBN: (数字)9798331530747

ISBN: (纸本)9798331530754

This paper outlines the merging of Explainable Artificial Intelligence (XAI) with Open Radio Access Network (O-RAN) and space communication systems. The usage of AI drives decision-making in critical domains of telecommunications and space explorations requires transparency and interpretability. However, traditional AI models often operate as “black boxes,” making it difficult to understand their decision-making processes. This lack of explainability poses significant risks, including misinterpretation of signals, undetected anomalies, and erroneous decision-making, which can compromise the integrity of communication systems. Specifically, the challenges include accurately distinguishing between legitimate signals and attacks in anti-jamming scenarios, understanding the behaviour of complex models like LSTM in traffic prediction, and ensuring the reliability of telemetry data despite errors and noise. Integration of XAI techniques within O-RAN architecture and space communication protocols can ensure trust, reliability and safety in AI-enabled systems. This paper investigates the opportunities and challenges of incorporating XAI in O-RAN and space communications. Additionally, it presents the implications of XAI, the need for interpretability in autonomous spacecraft operations, anomaly detection and decision support for mission-critical tasks. By bridging the gap in AI transparency and advanced communication technology, this paper aims to present a detailed analysis of implemented AI and Machine Learning (ML) in the telecommunication domain. It also presents the challenges currently faced in the intersection of XAI and communication. Use cases of XAI in the domain of Open Radio Access Network and Space Communications in light of LIME and SHAP techniques were presented to give a hypothetical modelling for future experimentation to provide local and global interpretation and explanations for the currently employed AI/ML models in the respective domains. Overall, this

关键词： Surveys Space vehicles Explainable AI Space communications Decision making Open RAN Reliability Telemetry Artificial intelligence Virtualization

来源：评论

学校读者我要写书评

暂无评论

Improving Routing Decision Algorithm for RPL Networks 11

Improving Routing Decision Algorithm for RPL Networks

引用

11th International Conference on Information Technology, ICIT 2023

作者： Zaqebah, Abdullah Al Almomani, Omar Almomani, Malek Alsaaidah, Adeeb Abu-Shareha, Ahmad Adel Althunibat, Ahmad The World IslamicSciences and Education University Department of Computer Science Amman Jordan The World Islamic Sciences and Education University Department of Information System and Networks Amman Jordan Software Engineering The World Islamic Sciences and Education University Amman Jordan Al-Ahliyya Amman University Department of Networks and Information Security Amman Jordan Al-Ahliyya Amman University Department of Data Science and Artificial Intelligence Amman Jordan Al-Zaytoonah University of Jordan Department of Software Engineering Amman11733 Jordan

ISBN: (纸本)9798350320060

Low Power Networks are spreading worldwide, seeking to enable small devices to join wireless networks. This requires a routing mechanism that makes it possible and seamless. This research aims to create a Low Power and Lossy Networks (RPL) routing protocol that balances power usage and node dependability. The main emphasis of the algorithm presented here is the choice made by network nodes (Zigbees) regarding which path to deliver the message along. Results for this routing technique seem promising. Utilizing it increased packet transfer reliability while enforcing power conservation. Furthermore, a 10% reduction in the network's overall power consumption was made. © 2023 IEEE.

关键词： Routing protocols

来源：评论

学校读者我要写书评

暂无评论

Transfer Learning Trained LSTM Models for Household Load Profile Forecasting

Transfer Learning Trained LSTM Models for Household Load Pro...

引用

Grid Edge Technologies Conference & Exposition (Grid Edge), IEEE PES

作者： Roshan Klein-Seetharaman Xiangqi Zhu Barry Mather Department of Mathematics Yale University New Haven USA Electrical Engineering and Computer Science Oregon State University Corvallis USA National Renewable Energy Laboratory Power System Engineering Center Golden USA

ISBN: (数字)9798350352528

ISBN: (纸本)9798350352535

Grid edge renewable energy resources, such as rooftop solar photovoltaics, closely interact with consumer load profiles. Therefore, forecasting future electricity demand, ideally at the individual household level, is indispensable. In this paper, we present a transfer learning enhanced household load profile forecasting method. First, we tune a long short-term memory forecasting model to perform day-ahead prediction of household electricity load profiles. Then we improve these individualized models using transfer learning, and we use k-means clustering to create optimal source data sets. We find average improvements of 4.38% (largest improvement of 10.71%) when the entire data set was used to train the source model and 2.45% (largest improvement of 11.57%) in the mean absolute error when households were first clustered and used to train separate source models for each cluster. We find that transfer learning with clustered data can effectively boost the forecasting performance of the LSTM models. We use realistic household power measurements for 148 real residential households in Austin, Texas.

关键词： Photovoltaic systems Renewable energy sources Power measurement Electricity Transfer learning Predictive models Data models Forecasting Long short term memory Load modeling

来源：评论

学校读者我要写书评

暂无评论

Manufacturing A Low-Cost Telegram and Optical Character Recognition-Based Indoor Air Quality Monitoring Data Logger 8

Manufacturing A Low-Cost Telegram and Optical Character Reco...

引用

8th International Conference on Information Management and Technology, ICIMTech 2023

作者： Pramono, Andi Budiman, Satrio Arif Farchan, Muchammad Mappaturi, Andi Baso School of Design Bina Nusantara University Interior Design Department Jakarta11480 Indonesia Brawijaya University Information System Computer Science Faculty Malang65145 Indonesia Institut Teknologi Sepuluh Nopember Faculty of Intelligent Electrical and Informatics Technology Department of Electrical Engineering Surabaya60111 Indonesia Islamic State University of Maulana Malik Ibrahim Faculty of Science and Technology Architecture Department Malang Indonesia

ISBN: (纸本)9798350326093

Urban air is frequently contaminated with CO, CO2, VOC, HCHO, PM 2.5, and PM 10. Rural regions are at a lower risk than those near roads and industrial areas that produce emissions. Air pollutants negatively affect its inhabitants' health, particularly the respiratory system. Most people will spend more time indoors, requiring a method for monitoring indoor air quality (IAQ). Urban communities need IAQ monitoring instruments as an early warning system for their health. This research seeks to produce inexpensive IAQ that can be utilized by all levels of society, particularly urban communities. This research utilizes a qualitative, design-thinking-based methodology. The research diverged from Empatize, which asserts that urban communities require a method for determining the local air quality. Moreover, it is determined at the define stage that IAQ monitoring, which includes a data log feature, is still comparatively expensive, so a solution is developed at the ideate stage. Creating a prototype is the next step in realizing the specified solution. In this investigation, they decided to use IAQ monitoring, which is relatively inexpensive but lacks log data storage. The author uses the ESP32-cam microcontroller to capture the screen display device, and the resulting image is sent to a telegram and processed with optical character recognition (OCR) to generate a data log. The results of prototype testing are utilized for prototype development. © 2023 IEEE.

关键词： Industrial emissions

来源：评论

学校读者我要写书评

暂无评论

DPN: decoupling partition and navigation for neural solvers of min-max vehicle routing problems 24

DPN: decoupling partition and navigation for neural solvers ...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Zhi Zheng Shunyu Yao Zhenkun Wang Xialiang Tong Mingxuan Yuan Ke Tang Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China Department of Computer Science City University of Hong Kong Hong Kong SAR and School of System Design and Intelligent Manufacturing Southern University of Science and Technology Shenzhen China School of System Design and Intelligent Manufacturing Southern University of Science and Technology Shenzhen China China Huawei Noah's Ark Lab Shenzhen China

The min-max vehicle routing problem (min-max VRP) traverses all given customers by assigning several routes and aims to minimize the length of the longest route. Recently, reinforcement learning (RL)-based sequential planning methods have exhibited advantages in solving efficiency and optimality. However, these methods fail to exploit the problem-specific properties in learning representations, resulting in less effective features for decoding optimal routes. This paper considers the sequential planning process of min-max VRPs as two coupled optimization tasks: customer partition for different routes and customer navigation in each route (i.e., partition and navigation). To effectively process min-max VRP instances, we present a novel attention-based Partition-and-Navigation encoder (P&N Encoder) that learns distinct embeddings for partition and navigation. Furthermore, we utilize an inherent symmetry in decoding routes and develop an effective agent-permutation-symmetric (APS) loss function. Experimental results demonstrate that the proposed Decoupling-Partition-Navigation (DPN) method significantly surpasses existing learning-based methods in both single-depot and multi-depot minmax VRPs. Our code is available at.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Range-Agnostic Multi-View Depth Estimation with Keyframe Selection

Range-Agnostic Multi-View Depth Estimation with Keyframe Sel...

引用

International Conference on 3D Imaging, Modeling, Processing, Visualization and Transmission (3DIMPVT)

作者： Andrea Conti Matteo Poggi Valerio Cambareri Stefano Mattoccia Department of Computer Science and Engineering University of Bologna Italy Advanced Research Center on Electronic System (ARCES) Brussels Belgium Sony Depthsensing Solutions University of Bologna Italy

ISBN: (数字)9798350362459

ISBN: (纸本)9798350362466

Methods for 3D reconstruction from posed frames require prior knowledge about the scene metric range, usually to recover matching cues along the epipolar lines and narrow the search range. However, such prior might not be directly available or estimated inaccurately in real scenarios – e.g., outdoor 3D reconstruction from video sequences – therefore heavily hampering performance. In this paper, we focus on multi-view depth estimation without requiring prior knowledge about the metric range of the scene by proposing RAMDepth, an efficient and purely 2D framework that reverses the depth estimation and matching steps order. Moreover, we demonstrate the capability of our framework to provide rich insights about the quality of the views used for prediction. Additional material can be found on our project page.

关键词： Measurement Three-dimensional displays Correlation Video sequences Memory management Estimation Cameras

来源：评论

学校读者我要写书评

暂无评论

Bioimaging of Dissolvable Microneedle Arrays: Challenges and Opportunities

引用

Research 2022年第4期2022卷 633-655页

作者： Yanni Wang Gehua Ma Guangzhi Gao Ji Tao Wenzhao Cao Haohao Sun Fengsen Ma Yilong Zhang Yen Wei Mei Tian Laboratory of Biologics and Biomaterials Collge of PharmacyZhejiang University of TechnologyHangzhou 310014China Cllge of Computer Science and Technology Zhejiang UniversityHangzhou 310027China Human Phenome Institute Fudan UniversityShanghai 201203China College of Information Engineering Zhejiang University of TechnologyHangzhou 310023China Life Science Research Center Frontier Crossing InstituteZhejiang University of TechnologyHangzhou 310023China Engineering Research Center of Intelligent Sensing and System Ministry of EducationHangzhou 310023China College of Computer Science and Technology Zhejiang University of TechnologyHangzhou 310023China Department of Chemistry and the Tsinghua Center for Frontier Polymer Research Tsinghua UniversityBeijing 100084China

The emergence of microneedle arrays(MNAs)as a novel,simple,and minimally invasive administration approach largely addresses the challenges of traditional drug *** particular,the dissolvable MNAs act as a promising,multifarious,and well-controlled platform for micro-nanotransport in medical research and cosmetic formulation *** effective delivery mostly depends on the behavior of the MNAs penetrated into the body,and accurate assessment is urgently *** imaging technologies offer high sensitivity and resolution visualization of cross-scale,multidimensional,and multiparameter information,which can be used as an important aid for the evaluation and development of new *** combination of MNA technology and imaging can generate considerable new knowledge in a cost-effective manner with regards to the pharmacokinetics and bioavailability of active substances for the treatment of various *** addition,noninvasive imaging techniques allow rapid,receptive assessment of transdermal penetration and drug deposition in various tissues,which could greatly facilitate the translation of experimental MNAs into clinical *** on the recent promising development of bioimaging,this review is aimed at summarizing the current status,challenges,and future perspective on in vivo assessment of MNA drug delivery by various imaging technologies.

关键词： needle mostly formulation

来源：评论

学校读者我要写书评

暂无评论

Dart Games Optimizer with Deep Learning-Based Computational Linguistics Named Entity Recognition

引用

Intelligent Automation & Soft Computing 2023年第9期37卷 2549-2566页

作者： Mesfer Al Duhayyim Hala J.Alshahrani Khaled Tarmissi Heyam H.Al-Baity Abdullah Mohamed Ishfaq Yaseen Amgad Atta Abdelmageed Mohamed IEldesouki Department of Computer Science College of Sciences and Humanities-AflajPrince Sattam bin Abdulaziz UniversityAl Aflaj16828Saudi Arabia Department of Applied Linguistics College of LanguagesPrincess Nourah Bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Computer Sciences College of Computing and Information SystemUmm Al-Qura UniversityMakkah24211Saudi Arabia Department of Information Technology College of Computer and Information SciencesKing Saud UniversityP.O.Box 145111Riyadh4545Saudi Arabia Research Centre Future University in EgyptNew Cairo11845Egypt Department of Computer and Self Development Preparatory Year DeanshipPrince Sattam bin Abdulaziz UniversityAlKharjSaudi Arabia Department of Information System College of Computer Engineering and SciencesPrince Sattam bin Abdulaziz UniversityAlKharjSaudi Arabia

Computational linguistics is an engineering-based scientific *** deals with understanding written and spoken language from a computational ***,the domain also helps construct the artefacts that are useful in processing and producing a language either in bulk or in a dialogue *** Entity Recognition(NER)is a fundamental task in the data extraction *** concentrates on identifying and labelling the atomic components from several texts grouped under different entities,such as organizations,people,places,and ***,the NER mechanism identifies and removes more types of entities as per the *** significance of the NER mechanism has been well-established in Natural Language Processing(NLP)tasks,and various research investigations have been conducted to develop novel NER *** conventional ways of managing the tasks range from rule-related and hand-crafted feature-related Machine Learning(ML)techniques to Deep Learning(DL)*** this aspect,the current study introduces a novel Dart Games Optimizer with Hybrid Deep Learning-Driven Computational Linguistics(DGOHDL-CL)model for *** presented DGOHDL-CL technique aims to determine and label the atomic components from several texts as a collection of the named *** the presented DGOHDL-CL technique,the word embed-ding process is executed at the initial stage with the help of the word2vec *** the NER mechanism,the Convolutional Gated Recurrent Unit(CGRU)model is employed in this *** last,the DGO technique is used as a hyperparameter tuning strategy for the CGRU algorithm to boost the NER’s *** earlier studies integrated the DGO mechanism with the CGRU model for *** exhibit the superiority of the proposed DGOHDL-CL technique,a widespread simulation analysis was executed on two datasets,CoNLL-2003 and OntoNotes *** experimental outcomes establish the promising performance of the DGOHDL-CL technique over other models.

关键词： Named entity recognition deep learning natural language processing computational linguistics dart games optimizer

来源：评论

学校读者我要写书评

暂无评论

Task sequencing in heterogeneous device for improved offloading decision using optimization technique

引用

Measurement: Sensors 2022年 24卷

作者： Saranya, G. Sasikala, E. Department of Computer Science and Engineering SRM Institute of Science and Technology Chennai India Department of Data Science and Business System SRM Institute of Science and Technology Chennai India

Edge Computing (EC) has made decisions regarding offloading tasks. Also, it might be a challenging task for a gadget of the multi-hop cause of competing network models due to the limited bandwidth available. The literature provides several studies on the issue of the multi-hop cloud environment. Moreover, partial offloading of multi-hop computing and dynamic network management leads to network problems. And inefficient performance measured in terms of task completion time has not been factored into current studies. To reduce the average finishing time of all jobs, this article proposed joint multi-task complete unloading and a network that supports the scheduling issue. Several variable decision factors such as the partial systematic ratio of offloading, Offloading remote devices, task start time, path of routing & dynamic network start time were optimized by the formulated problem. To manage tasks, we use the features inherent in multiple processors with various CPU frequencies. Under the restrictions of power & latency, we determine the appropriate quantity of task data to be handled immediately or distributed to the preferred nodes on the clouds remotely. Our objective is to solve the issue of optimization of task scheduling on a limited quasi-quadratic function. We offer an Improved Offloading and Heuristic Flow Optimization (IOHFO) solution effectively to solve these problems by using semi-definite relaxation. Finally, a simulator can be used to evaluate our proposed unloading system to reduce the (optimal) cost of unloading profiles for various parameters. © 2022 The Author(s)

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Enhanced Classification method for Large-Scale Medical Data

Enhanced Classification method for Large-Scale Medical Data

引用

Mobile, Intelligent, and Ubiquitous Computing Conference (MIUCC), International

作者： Ahmed Hassan Khaled M Fouad Alaa Eldin Abdalla Yassin Somia Mohamed ElSewedy University of Technology Cairo Egypt Faculty of computer science and engineering New Mansoura University Mansoura Egypt Information System department Benha University Benha Egypt

ISBN: (数字)9798350367775

ISBN: (纸本)9798350367782

The medical community has been concerned about how to increase the accuracy of different classification methods with large data that are being generated every day. The traditional KNN method has many limitations, such as dealing with large-scale data, handling uncertain data, and also determining the k parameter for KNN that gives the best result. In this research, three limitations are solved. By using optimized feature selection methods, optimal features are chosen from many irrelevant features. Then, uncertain data that has a conflict with the class label is handled. Finally, the optimal number of k in the KNN method that gives better accuracy is chosen using the ROC curve. The prime objective of this paper is to develop a hybrid optimal model for medical data classification that handles these challenges. The results are evaluated using the accuracy metric. Experimental results show that the enhanced KNN method outperforms the previously used KNN method in used medical datasets

关键词： Training Measurement Accuracy Computational modeling Data handling Nearest neighbor methods Ubiquitous computing Feature extraction Data models Testing

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：