检索结果-内蒙古大学图书馆

2nd IEEE International Conference on Trends in Quantum Computing and Emerging Business Technologies, TQCEBT 2024

作者： Anuradha, R. Swathi, B. Kumar, Rakesh Nagpal, Amandeep Kalra, Ravi Abdulaali, Hayder Saadoon Institute of Aeronautical Engineering Dundigal Hyderabad India New Horizon College of Engineering Department of Information Science Engineering Bangalore India Applications Gla University Department of Computer Engineering Mathura India Lovely Professional University Phagwara India Lloyd Institute of Engineering & Technology Knowledge Park Ii Uttar Pradesh Greater Noida201306 India National University of Science and Technology College of Technical Engineering Dhi Qar Iraq

ISBN: (纸本)9798350384277

This research introduces novel methodologies in graph convolutional networks (GCNs) to enhance semantic relationship mining within large-scale ontologies. Traditional approaches to understanding and extracting meaningful patterns from ontological structures often struggle with the complexity and scale of data. The proposed framework leverages advanced GCNs, incorporating a series of innovative mechanisms designed to optimize performance, accuracy, and scalability. Firstly, an enhanced graph convolutional layer is introduced, specifically tailored to capture the nuanced hierarchical and relational data typical of extensive ontological datasets. This layer employs a multidimensional feature extraction technique, significantly improving the depth and quality of semantic relationship identification. Secondly, the paper presents a unique embedding algorithm that efficiently maps semantic and relational data into a lower-dimensional space, facilitating faster computation while retaining critical information. To address the challenges of scalability, a distributed processing architecture is also proposed, enabling the handling of ontologies at an unprecedented scale. Empirical evaluations demonstrate the superiority of the approach in terms of precision, recall, and computational efficiency compared to existing methods. This research contributes to the field by providing a robust tool for experts and practitioners involved in knowledge discovery, data mining, and semantic web technologies, paving the way for more intelligent and efficient ontology management. © 2024 IEEE.

关键词： Scalability

来源：评论

学校读者我要写书评

暂无评论

Optimal Elevators Control for Buildings Based on Associative Memory 8

Optimal Elevators Control for Buildings Based on Associative...

引用

8th International Symposium on Innovative Approaches in Smart Technologies, ISAS 2024

作者： Ahmed, Saadaldeen Rashid Abdullah, Abdulqadir Ismail Aljanabi, Sabah Jebur Tawfeek, Zaki Saeed Radhi, Ahmed Dheyaa Kadhim, Rafad Imad Algburi, Sameer Hashim, Wassan Sdnsn Shin, Jungpil Bayan University Computer Science Department Kurdistan Erbil Iraq Al-Ayen University College of Engineering Artificial Intelligence Engineering Department Thi-Qar Iraq Knowledge University College of Engineering Department of Computer Engineering Kurdistan Region Erbil Iraq Al-Ma'moon University College Al-Washash Electrical Power Techniques Baghdad Iraq AL Hikma University College Engineering Computer Technology Department Baghdad Iraq University of Al-Ameed College of Pharmacy PO Box 198 Karbala Iraq University of Hilla Medical Devices Technology Engineering Babylon Iraq Al-Kitab University Kirkuk36015 Iraq The University of Aizu School of Computer Science and Engineering Aizuwakamatsu965-8580 Japan

ISBN: (纸本)9798331540104

Conventional elevators encounter the issues of energy efficiency, waiting periods, and lack of adaptation under dynamic conditions of the buildings. To this purpose, this paper provides an elevator control optimization model based on associative memory in order to tackle these challenges. To minimize energy usage and waiting time and increase the responsiveness of the entire system to real-time passenger demand. This technology leverages associative memory - specifically Hopfield networks - to effectively learn and reallocate elevator assignments adjusted to past traffic flows. The observed results represent up to 31% energy consumption reductions and 33% waiting time savings that show the function of the proposed system in optimizing traffic and energy consumption patterns at different building sizes and traffic scenarios. This research introduces a new elevator control system employing associative memory, which demonstrates considerable improvement in energy efficiency and lower waiting times for passengers. These findings will lead to additional exploration, notably for real-time application, interaction with IoT and building management systems, and scaling to bigger structures. © 2024 IEEE.

关键词： Associative storage

来源：评论

学校读者我要写书评

暂无评论

Transformer Embeddings for the Implementation of a Semantic MOOC Recommender System 6

Transformer Embeddings for the Implementation of a Semantic ...

引用

6th International Conference on Intelligent Computing in Data sciences, ICDS 2024

作者： Assami, Sara Daoudi, Najima Ajhoun, Rachida Ecole Nationale Supérieure d'Informatique et d'Analyse Des Systèmes of Mohammed v University Department of Computer Science Rabat Morocco Ecole des Sciences de l'Information Department of Data and Knowledge Engineering Rabat Morocco

ISBN: (纸本)9798350351200

Semantic web technologies aim to interconnect objects using descriptors that identify their characteristics and improve information retrieval. In Massive Open Online Courses (MOOCs), the learning contents semantic links and their pertinence for learner needs are essential to motivate learners and reduce dropout rates. This work aims to develop a semantic recommender system prototype that uses external data sources on learners to identify their knowledge, skills, and interests to recommend MOOCs. First, this paper traces the knowledge-based recommendation of MOOCs and its data representation in the literature. Afterward, it explores a dataset of a MOOC platform to extract MOOCs content-related data, and a dataset of a professional social media to extract knowledge-based characteristics of a learner from his/her social profile. For the implementation of the semantic recommender, three different techniques: TF-IDF, GloVe, and USE models are used to compute the semantic similarity of learner needs and MOOCs content. The semantic MOOC recommender system implementation showed the advantages of using different data sources and the increased performance of a MOOC recommender system based on transformer models like the USE model. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Attribution rollout: a new way to interpret visual transformer

引用

Journal of Ambient Intelligence and Humanized Computing 2023年第1期14卷 163-173页

作者： Xu, Li Yan, Xin Ding, Weiyue Liu, Zechao College of Computer Science and Technology Harbin Engineering University Nantong Street Heilongjiang Harbin150001 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Qianjin Street Jilin Changchun130012 China Department of Medicine Harvard Medical School Longwood Avenue BostonMA02115 United States

Transformer-based models are dominating the field of natural language processing and are becoming increasingly popular in the field of computer vision. However, the black box characteristics of transformers seriously hamper their application in certain fields. Prior work relies on the raw attention scores or employs heuristic propagation along with the attention graph. In this work, we propose a new way to visualize model. The method computes attention scores based on attribution and then propagates these attention scores through the layers. This propagation involves attention layers and multi-head attention mechanism. Our method extracts salient dependencies in each layer to visualize prediction results. We benchmark our method on recent visual transformer networks and demonstrate its many advantages over the existing interpretability methods. Our code is available at: https://***/yxheartipp/attr-rollout. © 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Quantitative Evaluation to Detect Crack Depth in Beams Based on CNN-RNN-LSTM Approach

Quantitative Evaluation to Detect Crack Depth in Beams Based...

引用

2023 International Conference on Self Sustainable Artificial Intelligence Systems, ICSSAS 2023

作者： Gandhi, Mohammad Asif Swaminathen, A.N. Patil, Deepak T. Ravitheja, A. Kamali, R. Rajput, Akshay Anjuman-I-Islam's Kalsekar Technical Campus Department of Mechanical Engineering Maharashtra Panvel India Adi Shankara Institute of Engineering and Technology Kerala India Bharati Vidyapeeth College of Architecture Maharashtra Navi Mumbai India Svr Engineering College Department of Civil Engineering Andhra Pradesh Kurnool India Knowledge Institute of Technology Department of Computer Science and Engineering Tamilnadu Salem India Graphic Era Deemed to Be University Department of Computer Science & Engineering Uttarakhand Dehradun India

ISBN: (纸本)9798350300857

In this study, the proposed approach offers a novel hybrid image-based deep learning method for autonomous concrete fracture identification. Cracks are easier to spot and false positives are reduced with hybrid images that include visual and infrared thermography data. In specifically, a Visible and infrared camera as well as a line laser make up a hybrid imaging system for spatially scanning unmanned vehicles can efficiently assess large-scale concrete-made constructions like bridges and dams. Crack detection is a commonplace task in many industrial domains, however the current method of relying on expert judgment is typically laborious, time consuming, and inaccurate. The practical benefits of automated decision-making increase as the size of the target concrete construction grows. Cracks can be automatically identified and seen using the proposed method. Preprocessing, segmentation, feature extraction, and model training are the four components of the proposed method. It performs clever edge recognition, scaling, and greyscale conversion as part of its preparation. Improved K-Means segmentation is used for the separation. It employs GLCM for feature extraction, and CNN-RNN-LSTM for model training. The new method is compared to two established approaches, CNN-RNN and CNN-LSTM, and is found to be superior. © 2023 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Evaluating Energy Consumption for Routing Selection using the Multi-Routing Clustering Protocol using Timeslot Transmission in Dynamic Path Selection in Wireless Sensor Networks 4

Evaluating Energy Consumption for Routing Selection using th...

引用

4th International Conference on Evolutionary Computing and Mobile Sustainable Networks, ICECMSN 2024

作者： Prakash, M. Abinesh, J. Malarvizhi, P. Emilyn, J. Jeba Thamburaj, A. Sam Kumar, D. Vinod Department of Computer Science Vinayaka Mission's Kirupananda Variyar Arts and Science College Vinayaka Mission's Research Foundation Deemed to Be University Tamil Nadu Salem636 308 India Department of Computer Science and Engineering Knowledge Institute of Technology Tamil Nadu Salem637504 India Department of Information Technology Sona College of Technology Tamil Nadu Salem India Tamil Nadu Salem India Tamil Nadu Salem India

Wireless sensor networks (WSNs) are cutting-edge technology that can be used in many fields requiring critical information. However, limited resource constraints, contextual connectivity, and lifecycle requirements drive designers to seek more efficient WSN infrastructures. Unbalanced energy utilization of sensor hubs during information steering in Wireless Sensor Networks (WSN). Accordingly, one of the principal configuration difficulties of remote sensor networks is to limit the energy utilization of sensor hubs. Therefore, many routing schemes are designed to efficiently utilize sensor nodes' limited Energy. These schemes generally use low-power paths to transmit data. It turns out that using the same path is suboptimal given the network lifetime. To overcome this problem, a new method is introduced that uses a Multi-Route Clustering Protocol Using Timeslot Transmission (MRCP-TTDPS) with dynamic path selection. It consumes Energy on path selection. In the first step, multipath routing is configured to detect path quality, so this method uses Multipath Optimized Routing (MPRS) to send high-quality path data. The second stage uses Cluster-Based Optimal Path Selection (CORS) to establish the best energy path. The third stage develops energy consumption models. The amount of the hubs with the most noteworthy leftover Energy is chosen as the group top of each round. Every standard hub partakes in a group framed by neigh exhausting bunch heads. Every sensor hub sends identified information to the bunch head in each round. The group head sends the data to the base station. The results show that the model is better than the path model regarding path identifier energy utilization and path quality. © 2025 The Authors.

关键词： Sensor nodes

来源：评论

学校读者我要写书评

暂无评论

Dynamic Resource Allocation in Edge Computing via Deep Deterministic Policy Gradient Reinforcement Learning

Dynamic Resource Allocation in Edge Computing via Deep Deter...

引用

Integrated Circuits and Communication Systems (ICICACS), IEEE International Conference on

作者： Vidhya Gopal U Surendar A Bajulunisha M Tamilselvi V Sathiyapriya N Saranya Department of Computer Science and Engineering Sona College of Technology Salem India Department of Electronics and Communication Engineering SRM institute of Science and Technology Chennai India Department of Computer Science and Engineering Chennai Institute of Technology Kundrathur India Department of Computer Science and Engineering Roever Engineering College Perambalur India Department of Computer Science and Engineering Knowledge Institute of Technology Salem India Department of Artificial Intelligence and Data Science Karpagam College of Engineering Coimbatore India

ISBN: (数字)9798331508456

ISBN: (纸本)9798331508463

The difficulty with dynamic and heterogeneous natured edge computing environments is resource provisioning. Reinforcement Learning (RL) can be promising to solve the problems of resource allocation under conditions of dynamics and complexity. This research work presents a novel DDPG-based (Deep Deterministic Policy Gradient) approach for optimizing the dynamics of resource allocation in edge computing environments by exploiting the CRAWDAD KAIST–WIBRO dataset for the proposed model. This approach implements a neural network that learns the optimal policies of allocations with dynamism towards new changes in workloads and resource availabilities. In order to test the performance of this method, conducted several simulations over real-world workload and resource data, mapping the parameters like rewards and variation in episodes. The simulation results indicate that proposed approach performs superior compared to traditional heuristic-based approaches as well as other RL algorithms for resource usage, response time, and energy efficiency. This proposed approach permits optimized resource utilization along with quality of service, of paramount importance in executing complex and demanding applications at the edge computing environment.

关键词： Computational modeling Simulation Markov decision processes Neural networks Reinforcement learning Quality of service Dynamic scheduling Resource management Time factors Edge computing

来源：评论

学校读者我要写书评

暂无评论

The Geography of Temperature Space

The Geography of Temperature Space

引用

2024 Joint Ontology Workshops - Episode X: The Tukker Zomer of Ontology, and Satellite Events, JOWO 2024

作者： Wright, George A. Purver, Matthew School of Electronic Engineering and Computer Science Queen Mary University of London United Kingdom School of Computing and Mathematical Sciences Birkbeck University of London United Kingdom Department of Knowledge Technologies Jožef Stefan Institute Ljubljana Slovenia

This paper takes as its basis, Gärdenfors’ [1] description of conceptual spaces and sketches an initial geography of the conceptual space for temperature. It highlights important differences between the space’s constituents, including: how category membership differs for concepts along different parts of the dimension;how comparatives and compounds are formed;how context affects concept location and behaviour;and how non-literal usage allows concepts to be used outside of their conceptual space or in a different way within their own conceptual space. The purpose of this tour of temperature space is to aid the practical implementation of semantic representations based upon conceptual spaces. © 2024 Copyright for this paper by its authors.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

An Investigational Study of Detecting Acute Lymphoblastic Leukemia using computer Vision

An Investigational Study of Detecting Acute Lymphoblastic Le...

引用

Smart Technologies and Systems for Next Generation Computing (ICSTSN), International Conference on

作者： M Ashok K Tharani S VenkataSriram Kumar Ramasamy Department of Computer Science and Engineering Rajalakshmi Institute of Technology Chennai India Department of Computer Science and Engineering Knowledge Institute of Technology Salem India

Among all divesting cancers, Hematologists predict that the Leukemia is mostly occur on the children, teenagers, and young adults. Moreover 85% of cancer cases are detected younger than the age of 15. Due to a Genetic abnormality in the bone marrow, Acute lymphoblastic leukemia (ALL) is particularly susceptible to life-threatening infections. The laboratory method to detect the ALL is prolonged and slow process. Reviewing prior research on detection methods in ALL is the goal of this study. This review includes (a) the parameters necessary for the ALL detection (b) methods involved in the detection process (c) which algorithms gives the accurate prediction and (d) finally all the necessary context for the detection of the ALL-affected cells. The proposed system possesses the automated machine learning (Chabot) approach used to categorize the infected and healthy cells in the blood smears (microscopic images) in order to detect ALL. The Blood smears are converted into the CMYK color space and separated into clusters using K-means Algorithm. A cell from each cluster is picked and detected whether the cell is affected with ALL or not using the nuclei of the cell using supervised learning algorithm like SVM, XGBoost Classifier, Etc., The proposed system aids in enhancing the acute lymphoblastic leukemia detection system.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Aggregative Dynamics and Revenue Structuring in Energy Internet User-Prosumer Ecosystems

Aggregative Dynamics and Revenue Structuring in Energy Inter...

引用

2024 OPJU International Technology Conference on Smart Computing for Innovation and Advancement in Industry 4.0, OTCON 2024

作者： Singh, Anil Pratap Veena, Ch. Anandhi, R.J. Singla, Atul Parmar, Ashish Alabdely, Haider Ies Insititute of Technology and Management Ies University Department of Computer Science & Engineering M.P Bhopal India Institute of Aeronautical Engineering Hyderabad Dundigal India New Horizon College of Engineering Department of Information Science Engineering Bangalore India Lovely Professional University Phagwara India Lloyd Institute of Engineering & Technology Knowledge Park II Uttar Pradesh Greater Noida201306 India The Islamic University Najaf Iraq

ISBN: (纸本)9798350373783

This study explores income structure and group dynamics in complicated energy internet consumer-prosumer ecosystems.a DRORA (Dynamic Revenue Optimization and Aggregation) is proposed after studying energy consumers and prosumers throughout time. PDPA, EDOA, and RFO are in the system. These boost energy market efficiency, transparency, and fairness. As a way to promote fair pay and customer cost, the PDPA lets prosumers have a say in how prices are set. The EDOA makes sure that resources are used efficiently by distributing power in the best way possible to cut down on costs and improve system performance. With the RFOA's accurate income predictions, stakeholders can make smart decisions that will help them make the most money. Simulations and real-world studies have shown that the suggested model is better than traditional methods at getting stable and fair income sharing in the Energy Internet environment, which is always changing. © 2024 IEEE.

关键词： Signal modulation

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：