检索结果-内蒙古大学图书馆

International Conference on Applied Soft Computing and Communication Networks, ACN 2023

作者： Mookherji, Srijanee Suresh, Devanapalli Raghavendra Narayan, K.G. Odelu, Vanga Prasath, Rajendra Goutham Reddy, Alavalapati Computer Science and Engineering Indian Institute of Information Technology Sri City Chittoor 630 Gnan Marg Andhra Pradesh Sri City517646 India Department of Mathematics Rajiv Gandhi University of Knowledge Technologies Telangana Basar504107 India Department of Mathematics and Computer Science Fontbonne University St. LouisMO63105 United States

ISBN: (纸本)9789819720033

RFID technologies have been widely used in various applications in recent decades. This includes smart healthcare. Authenticating users is essential in healthcare applications for safety, security, data confidentiality, and patient privacy. Also, computational overheads significantly impact the efficiency of medical service delivery. Numerous RFID-tag authentication protocols exist in the literature to address these challenges. However, a majority of the works fail to meet the necessary security characteristics for e-healthcare applications. This study presents a secure authentication technique using pseudo-identities to safeguard privacy. Additionally, the pseudo-identity technique used in our protocol maintains privacy and prevents traceability. We give a comprehensive security research proving our protocol provides security against various known attacks. This research involves formal security verification using AVISPA tool. Additionally, we evaluate the performance of the proposed protocol and compare it to most related existing methods to show the feasibility of our scheme. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Cognitive Psychology and Blending AI for Emotion-Infused English Translation with Dynamic Vocabulary Growth 2

Cognitive Psychology and Blending AI for Emotion-Infused Eng...

引用

2nd IEEE International Conference on Emerging Research in Computational science, ICERCS 2024

作者： Jawad, Israa Abed Ali, Mariam Fadel Ali, Abdalsalam Taha Hussain Mohammed, Nada Qasim Al-Dabagh, Mustafa Zuhaer Nayef Al-Nisour University College Baghdad Iraq Uruk University Department of Radiology Techniques Baghdad Iraq Al Kitab University Department of Medical Engineering Kirkuk Iraq Al-Nisour D25 College Baghdad Iraq Knowledge University College of Science Department of Computer Science Erbil Iraq

ISBN: (纸本)9798331534950

Machine Neural Translation (MNT) has received a lot of interest in recent years, owing to its simple yet cutting-edge capabilities. Wearable sensors have great promise for research into cognitive development in the MNT processing. The limited semantic knowledge acquired by language learners leads to inaccurate terminology. Many pupils rely on the traditional thesaurus to express their feelings. Previous research has revealed, however, that MNT has a number of restrictions, including source scope requirements, unusual word translation, and restricted speech, whereas Machine Statistical Translation (MST) has additional qualities that adhere to these constraints. Furthermore, it presents a method for determining emotional ratings for students learning English as a second language, with word choice based on contextual awareness. The research offers the Machine Emotional Statistical Vocabulary Language Expansion (MESVLE) approach for protecting a list of words related to emotional information in context. In our case, the MNT decoder improves word prediction reliability by referring to MST word recommendations throughout both the training and testing phases. Patterns are trained to record emotional occurrences, and the rating approach incorporates a variety of word ranking factors. MESVLE was used to create an online review writing program to help students learn to write. Experimental results on translation tasks from Chinese to English and English to German show that the suggested structure will profit from MST words while also continuously developing MNT and MST baseline structures. © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Adaptive Web Crawling Strategies Based on Ontological User Interest Modeling for Personalized Content Retrieval 2

Adaptive Web Crawling Strategies Based on Ontological User I...

引用

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

作者： Durga, Vijaya Anandhi, R.J. Bansal, Saloni Singh, Navdeep Kalra, Ravi Bader, Nabaa M. Institute of Aeronautical Engineering Dundigal Hyderabad India New Horizon College of Engineering Department of Information Science Engineering Bangalore India Gla University Department of Computer Engineering and Applications Mathura India Lovely Professional University Phagwara India Lloyd Institute of Engineering & Technology Knowledge Park IIUttar Pradesh Greater Noida201306 India National University of Science and Technology College of Technical Engineering Dhi Qar Iraq

ISBN: (纸本)9798350384277

The exponential growth of web content necessitates efficient and personalized methods for information retrieval. This research introduces an innovative approach to web crawling, centered on adaptive strategies guided by ontological user interest modeling, aiming to enhance the precision of personalized content retrieval. The proposed method employs a dynamic user interest model, constructed, and continually refined through user interactions, leveraging ontology to represent and understand the complex and evolving nature of user interests. In contrast to traditional web crawlers that operate on fixed algorithms, the adaptive crawler anticipates changes in user interests and adjusts its strategies, accordingly, ensuring relevance and timeliness of the retrieved content. The system architecture integrates a multi-faceted profiling mechanism that captures and evolves with user preferences, combined with an intelligent crawling algorithm that prioritizes content based on predicted user interest levels. Empirical results demonstrate a significant improvement in retrieval precision and efficiency, highlighting the crawler's ability to discern and adapt to the nuanced shifts in user interests. Furthermore, the research delves into the implications of such personalized crawling on user privacy and web dynamics, offering insights and recommendations for a balanced approach. This work contributes to the fields of semantic web, personalized content retrieval, and adaptive systems, proposing a novel pathway for the next generation of intelligent web crawlers. © 2024 IEEE.

关键词： Web crawler

来源：评论

学校读者我要写书评

暂无评论

Development of Resistive-type IoT-Based Methane Gas Concentration Transmitter Using SnO2 Material

引用

Journal of The Institution of Engineers (India): Series D 2023年第2期104卷 515-529页

作者： Ghosh, Animesh Mondal, Bikas Mondal, Santu Hazra, Tanmoy Biswas, Arindam Department of Electrical Engineering Techno Polytechnic Durgapur West Bengal Panagarh India Department of Applied Electronics and Instrumentation Engineering Asansol Engineering College West Bengal Asansol India Department of Computer Science and Engineering NSHM Knowledge Campus West Bengal Durgapur India Department of Mining Engineering Kazi Nazrul University West Bengal Asansol India Centre of IoT and AI Integration with Education-Industry-Agriculture and School of Mines and Metallurgy Kazi Nazrul University West Bengal Asansol India

Many conventional sensors are used in industries since industrial methane sensing is critical. In the present case, a SnO2 layer is the sensing medium for methane that decreases its electrical resistance with increase in methane concentration. A Wheatstone bridge detects the decrease in resistance, thereby converting it to a suitable voltage. Since the environment where methane gas would be present is hazardous, electrical communication is impossible through a physical network. Instead, the authors have taken the help of the Internet of Things (IoT) for data communication purpose which has become much more feasible nowadays for communicating data in a hazardous environment. The mathematical relationship of the methane concentration with the transmitted current and voltage is found by theoretically analyzing the proposed methane sensor. The authors have tested the proposed system of methane concentration measurement experimentally. The paper presents the experimental results with reasonable accuracy, sensitivity, and linearity. [Figure not available: see fulltext.]. © 2022, The Institution of Engineers (India).

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Fostering Sustainable Development through Distributed Intelligence Applications

Fostering Sustainable Development through Distributed Intell...

引用

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

作者： Durga, C.S.L. Vijaya Agrawal, Shruti Anandhi, R.J. Singh, Navdeep Kalra, Ravi Adnan, Myasar Mundher Institute of Aeronautical Engineering Hyderabad Dundigal India Ies College of Technology Department of Computer Science & Engineering Ma. P Bhopal 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

SDODI, which stands for Sustainable Development Optimization using Distributed Intelligence, advances sustainable development. SDODI is the first to examine environmental, social, and economic challenges together using EcoOpt, InclusNet, and ResilienceHub. Environmental optimization program EcoOpt increases the total effect while ensuring resource efficiency and environmentally friendly behavior. InclusNet uses math to include everyone and make communities more active, varied, and accessible. The ResilienceHub algorithm prioritizes financial stability, flexibility, and economic power. Sustainable initiatives are typically divided by traditional approaches. SDODI utilizes information to better allocate resources, engage the community, and strengthen the economy. SDODI is unique because it adapts to changing situations, giving it a comprehensive sustainable growth solution. SDODI is new because it supports and improves sustainability ideals. © 2024 IEEE.

关键词： Sustainable development goals

来源：评论

学校读者我要写书评

暂无评论

Advanced Graph Convolutional Networks for Semantic Relationship Mining in Large-Scale Ontologies 2

Advanced Graph Convolutional Networks for Semantic Relations...

引用

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

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：