检索结果-内蒙古大学图书馆

2023 International Conference on Computer Communication and Informatics, ICCCI 2023

作者： Bhaskaran, S. Bharathiraja, N. Pradeepa, K. Vinoth Kumar, M. Ravindhar, N.V. Marappan, Raja SASTRA Deemed University School of Computing Thanjavur India Chitkara University Institute of Engineering and Technology Chitkara University Punjab India St. Michael College of Engineering and Technology Department of Computer Science and Engineering India Dmi-St.Eugene University Department of Computer Science and Engineering Great North Road Chibombo District Zambia Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350348217

Nowadays, customers can get recommendations for products and services that fit their anticipated needs in the context of a large body of data. Advances in this area provide novel concepts and enable technology for use in e-learning settings. The existing recommendation systems typically focus on improving the item side, but they don't consider the user characteristics in the recommendation. Thus, they're ineffective and hence not a good fit for a virtual classroom setting. This research focuses on applying semantics-based knowledge graph modeling with collaborative filtering (CF) to solve these issues. This proposed framework applies the users' static features to aid in cold start issues for potential new users. The proposed framework significantly outperforms the existing models and helps maintain acceptable performance using better user-item interactions. © 2023 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Long-Term Load Forecasting Based on Hybrid CEEMDAN-SSA-BiGRU-Attention Model

Long-Term Load Forecasting Based on Hybrid CEEMDAN-SSA-BiGRU...

引用

IEEE International Conference on Artificial Intelligence in engineering and technology (IICAIET)

作者： Jiajian Lin Lit Yen Yeo Yuting Sheng Mehran Motamed Ektesabi Jalal Tavalaei Hadi Nabipour Afrouzi Faculty of Engineering Computing and Science Swinburne University of Technology Kuching Malaysia Department of Engineering Management The Eleventh Metallurcial Construction Group CO. LTD Liuzhou China School of Science Computing and Engineering Technologies Swinburne Univerdity of Technology Hawthorn Victoria Australia

ISBN: (数字)9798350389692

ISBN: (纸本)9798350389708

Electric load is characterized by uncertainty, randomness, and volatility, so accurate prediction will be challenging. This paper thus comes up with a hybrid prediction model called CEEMDAN-SSA-BiGRU Attention to predict the load. First, it preprocesses the load data from a selected power grid in Chicago, USA, from 2012 to 2015. Then, the load data is divided into a series of IMF sequences combined with the original data, shaping a new feature set using CEEMDAN (Complete Ensemble Empirical Mode Decomposition with Adaptive Noise). SSA (Sparrow search algorithm) optimized the hyperparameter of the BiGRU Attention network, and the network processed the new feature set to make predictions. The results from the experiments show that the judgment coefficient (R-square, R 2 ) of the model, the root mean square error (RMSE), and the mean absolute error (MAE) are 90.2%, 51618, and 39470, respectively. The three indexes are much better than other models and have a higher forecast precision degree and stable ability, which shows the model's superiority in long-term load forecasting..

关键词： Training Accuracy Uncertainty Load forecasting Time series analysis Predictive models Prediction algorithms Power grids Root mean square Load modeling

来源：评论

学校读者我要写书评

暂无评论

Real-Time Hydraulic Fluid Leak Detection in Heavy Machinery Using Cloud-Integrated Wireless Sensor Networks for Proactive Maintenance 10

Real-Time Hydraulic Fluid Leak Detection in Heavy Machinery ...

引用

10th International Conference on Communication and Signal Processing, ICCSP 2024

作者： Kumaresh, P.S. Sivanantham, E. Shoba, L.K. Priya, W. Deva Mohankumar, N. Elango, B. K.L.N.College of Engineering Department of Electronics and Communication Engineering Tamil Nadu Sivagangai India Rajalakshmi Institute of Technology Department of Electronics and Communication Engineering Tamil Nadu Chennai India Srm Institute of Science and Technology Department of Computing Technologies Chenagalpattu Chennai Tamil Nadu Kattankulathur India Saveetha University Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Tamil Nadu Chennai India Symbiosis Institute of Technology Maharashtra Nagpur India Adhiparasakthi Engineering College Department of Electronics and Communication Engineering Tamil Nadu Melmaruvathur India

ISBN: (纸本)9798350353068

This research introduces unique techniques for improving preventative servicing of heavy equipment using a real-time leak-detecting system for hydraulic fluid. The technology employs a network of sensors across the gear to monitor the hydraulics in real time. These wireless sensors communicate data to a cloud-based platform, where cloud computing analytics are used for real-time analysis. The cloud-integrated sensor network quickly detects hydraulic fluid leakage to address the critical demand for quick maintenance interventions. Preventing possible breakdowns and avoiding downtime are two areas where real-time skills shine. The cloud-based design enables remote monitoring and administration, which is essential for a preventative maintenance approach. Multiple pieces of heavy equipment were used in virtual and real-world tests to evaluate the proposed solution. The results reveal that the system is useful for real-time detection of hydraulic fluid leaks, which can potentially increase heavy equipment's overall dependability and performance. The system is a viable option for a wide range of industrial uses due to the incorporation of cloud computing, which guarantees scalability, flexibility, and accessibility. © 2024 IEEE.

关键词： Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

FedEAT: A Robustness Optimization Framework for Federated LLMs

arXiv

引用

arXiv 2025年

作者： Pang, Yahao Wu, Xingyuan Zhang, Xiaojin Chen, Wei Jin, Hai National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China Huazhong University of Science and Technology Wuhan China

Significant advancements have been made by Large Language Models (LLMs) in the domains of natural language understanding and automated content creation. However, they still face persistent problems, including substantial computational costs and inadequate availability of training data. The combination of Federated Learning (FL) and LLMs (federated LLMs) offers a solution by leveraging distributed data while protecting privacy, which positions it as an ideal choice for sensitive domains. However, Federated LLMs still suffer from robustness challenges, including data heterogeneity, malicious clients, and adversarial attacks, which greatly hinder their applications. We first introduce the robustness problems in federated LLMs, to address these challenges, we propose FedEAT (Federated Embedding space Adversarial Training), a novel framework that applies adversarial training in the embedding space of client LLM and employs a robust aggregation approach, specifically geometric median aggregation, to enhance the robustness of Federated LLMs. Our experiments demonstrate that FedEAT effectively improves the robustness of Federated LLMs with minimal performance loss. © 2025, CC BY.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Monitor and Control of Drug Preparation using Deep Q Neural Network 7

Monitor and Control of Drug Preparation using Deep Q Neural ...

引用

7th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), I-SMAC 2023

作者： Irfan, B.Md. Hemalakshmi, G.R. Prakash, N.B. Kamalesh, S. Pokhariyal, Rajesh Natrayan, L. Nalsar University of Law Department of Information Technology Telangana Hyderabad500101 India Vit Bhopal University School of Computing Science and Engineering Madhya Pradesh 466114 India National Engineering College Department of Electrical and Electronics Engineering Tamil Nadu Kovilpatti628503 India Velammal College of Engineering and Technology Department of Information Technology Tamil Nadu Madurai625009 India Graphic Era Deemed to Be University Department of Computer Science & Engineering Uttarakhand Dehradun248002 India Simats Saveetha School of Engineering Department of Mechanical Engineering Tamil Nadu Chennai602105 India

ISBN: (纸本)9798350341485

In the pharmaceutical industry, an evaporator is used to vaporize the solvent from a solution and prepare the drug for use. Because of its significance, evaporation is often treated as a separate process. If it is being evaporated, the remaining material will dry out and become solid. Evaporation may seem like it would dry up a solution, but in reality, it concentrates it. Keeping the solution's concentration constant is a huge task. Maintaining the proper concentration of the solution is a primary focus of this study. As a first step, we construct the mathematical model of the evaporator. Second, controllers like Model Predictive Controllers (MPC) and Deep Q Network (DQN) controllers are designed. Third, the controllers are evaluated using error measures like Integral Square Error (ISE), Integral Absolute Error (IAE), and Integral Time Square Error (ITSE) by giving the required set-point to the system. The evaluation result shows that the DQN produce minimal error of ISE, IAE, and ITSE and their values are 14.26, 9.45, and 671.82. Additionally, the DQN controller reach the set-point with minimal settling time, and no overshoot and undershoot characteristics. © 2023 IEEE.

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

Bridging Gaps in HCI: Advancing Education, Research, and Careers in Asia

Bridging Gaps in HCI: Advancing Education, Research, and Car...

引用

2025 CHI Conference on Human Factors in computing Systems, CHI EA 2025

作者： Gamage, Dilrukshi Cheng, Shiwei Mudliar, Preeti Lu, Zhicong Zhao, Shengdong Ahmed, Nova Ma, Xiaojuan Lee, Uichin Wang, Ding Department of Computation and Intelligent Systems University of Colombo School of Computing Colombo Sri Lanka Zhejiang University of Technology Hangzhou China International Institute of Information Technology Bangalore Bangalore India Department of Computer Science City University of Hong Kong Hong Kong School of Creative Media City University of Hong Kong Hong Kong Design Inclusion and Access Lab. Department of Electrical and Computer Engineering North South University Dhaka Dhaka Bangladesh Hong Kong University of Science and Technology Hong Kong Hong Kong School of Computing KAIST Daejeon Korea Republic of Google AtlantaGA United States

ISBN: (纸本)9798400713958

Asia’s Human-Computer Interaction (HCI) landscape is rapidly evolving, yet it faces distinct challenges in curriculum development, research establishment, and career navigation. This panel discussion, hosted by Asia SIGCHI Committee (ASC) at CHI2025, will bring together distinguished experts to address these challenges and explore strategies for fostering a robust and inclusive HCI community in Asia. Panelists will discuss the integration of culturally relevant content in HCI education, approaches to enhancing research visibility on international platforms, and initiatives to bridge gaps between academic training and industry expectations. Through an engaging discussion and audience interaction, the panel aims to identify actionable solutions, promote collaboration, and inspire future initiatives that strengthen HCI’s growth across the region. Participants will gain valuable insights into overcoming systemic barriers while building sustainable and impactful HCI programs tailored to Asia’s unique sociocultural dynamics. This panel seeks to advance the global relevance and contributions of HCI in Asia. © 2025 Copyright held by the owner/author(s).

关键词： Curricula

来源：评论

学校读者我要写书评

暂无评论

Exponential Time Differencing Schemes for the Peng-Robinson Equation of State with Preservation of Maximum Bound Principle

引用

Advances in Applied Mathematics and Mechanics 2022年第2期14卷 494-527页

作者： Qiumei Huang Kun Jiang Jingwei Li College of Mathematics Faculty of ScienceBeijing University of TechnologyBeijing 100124China Beijing Institute for Scientific and Engineering Computing Beijing University of TechnologyBeijing 100124China Laboratory of Mathematics and Complex Systems and School of Mathematical Science Beijing Normal UniversityBeijing 100875China

The Peng-Robison equation of state,one of the most extensively applied equations of state in the petroleum industry and chemical engineering,has an excel-lent appearance in predicting the thermodynamic properties of a wide variety of *** has been a great challenge on how to design numerical schemes with preser-vation of mass conservation and energy dissipation *** on the exponential time difference combined with the stabilizing technique and added Lagrange multi-plier enforcing the mass conservation,we develop the efﬁcientﬁrst-and second-order numerical schemes with preservation of maximum bound principle(MBP)to solve the single-component two-phase diffuse interface model with Peng-Robison equation of *** analyses as well as energy stability are also *** two-dimensional and three-dimensional experiments are performed to verify these theo-retical results.

关键词： Peng-Robinson equation of state diffuse interface model maximum bound principle exponential time differencing Lagrange multiplier

来源：评论

学校读者我要写书评

暂无评论

Multi-View Graph Embedding Learning for Image Co-Segmentation and Co-Localization

引用

IEEE Transactions on Circuits and Systems for Video technology 2024年第6期34卷 4942-4956页

作者： Huang, Aiping Li, Lijian Zhang, Le Niu, Yuzhen Zhao, Tiesong Lin, Chia-Wen Fuzhou University Fujian Key Laboratory for Intelligent Processing and Wireless Transmission of Media Information College of Physics and Information Engineering Fuzhou350108 China Fuzhou University Fujian Key Laboratory of Network Computing and Intelligent Information Processing College of Computer and Data Science Fuzhou350108 China University of Electronic Science and Technology of China School of Information and Communication Engineering Chengdu611731 China Fuzhou University Fujian Key Laboratory for Intelligent Processing and Wireless Transmission of Media Information College of Physics and Information Engineering The Fujian Science and Technology Innovation Laboratory for Optoelectronic Information Fuzhou350108 China Institute of Communications Engineering National Tsing Hua University Department of Electrical Engineering Hsinchu30013 Taiwan

Image co-segmentation and co-localization exploit inter-image information to identify and extract foreground objects with a batch mode. However, they remain challenging when confronted with large object variations or complex backgrounds. This paper proposes a multi-view graph embedding (MV-Gem) learning scheme which integrates diversity, robustness and discernibility of object features to alleviate this phenomenon. To encourage the diversity, the deep co-information containing both low-layer general representations and high-layer semantic information is generated to form a multi-view feature pool for comprehensive co-object description. To enhance the robustness, a multi-view adaptive weighted learning is formulated to fuse the deep co-information for feature complementation. To ensure the discernibility, the graph embedding and sparse constraint are embedded into the fusion formulation for feature selection. The former aims to inherit important structures from multiple views, and the latter further selects important features to restrain irrelevant backgrounds. With these techniques, MV-Gem gradually recovers all co-objects through optimization iterations. Extensive experimental results on real-world datasets demonstrate that MV-Gem is capable of locating and delineating co-objects in an image group. © 1991-2012 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Deep Fake Detection Based on Hybrid Approach Involving Residual Network Deep Learning Architecture

Deep Fake Detection Based on Hybrid Approach Involving Resid...

引用

IEEE International Conference on System, Computation, Automation and Networking (ICSCAN)

作者： N.V. Shibu R. Muthunagai S. Prabu Department of Computing Technologies SRM Institute of Science and Technology Chengalpattu India Department of Electrical & Electronics Engineering Manakula Vinayagar Institute of Technology Puducherry India Department of Computing Technologies School of computing SRM Institute of Science and Technologies Chennai India

ISBN: (数字)9798331510022

ISBN: (纸本)9798331510039

This Deep fake technology aims at generating synthetic video content or morphed video content which is very realistic to the naked eye. It involves the use of deep learning algorithms in the domain of video processing. In most cases, such artificially generated video contents are very difficult to get differentiated from naturally captured video signals. The existing methodologies of detection involved image tamper detection and digital forensics algorithms. These algorithms are ineffective in detecting videos tampered using deep fake technology. The proposed technique involves training and building of deep learning models that works like a black box to detect the artefacts crucial in the detection of video tampering. This paper presents an overview of the technology advancements in the field of deep fake video detection techniques over recent years. This paper also performs a comparative analysis on the performance of hybrid algorithms involving residual network deep learning architecture in the detection of video signals morphed using deep fake technology. The training datasets are obtained from Face forensics to build the model. The algorithm is augmented with image quality assessment, temporal consistency analysis and facial landmarks analysis to improve the detection algorithm. The performance metrics involve the generation of confusion matrix and generation of accuracy measures. The results provide a promising direction towards the construction of better detection models to safeguard against current and future threats.

关键词： Training Deep learning Measurement Image quality Deepfakes Current measurement Digital forensics Detection algorithms Faces Residual neural networks

来源：评论

学校读者我要写书评

暂无评论

Optimized Flame Detection Using a YOLOv5 Neural Network

Optimized Flame Detection Using a YOLOv5 Neural Network

引用

2024 International Conference on computing, Robotics and System Sciences, ICRSS 2024

作者： Karim, Shahid Ibrar, Muhammad Bilal, Anas Qadir, Akeel Bibi, Irfana School of Information Engineering Xi'an Eurasia University Xi'an710065 China Software College Shenyang Normal University Shenyang China College of Information Science and Technology Hainan Normal University Haikou571158 China Faculty of Computing and Information Technology University of Punjab Department of Computer Science Punjab Lahore Pakistan

ISBN: (纸本)9798331511296

With the rising prevalence of smart homes, there's an increasing demand for comprehensive automation solutions to mitigate fire risks, especially when homeowners are absent or in homes with elderly residents. This study focuses on enhancing flame detection techniques, particularly for smaller, hard-to-detect fire sources. A customized Yolov5 neural network was developed to improve detection precision. This enhancement was facilitated using a dataset of over 2,000 images from lab camera observations and online platforms. These images were then manually labeled and clustered for anchor dimensions using the K-means++ algorithm. The CIOU and diou - nms techniques were integrated to optimize the network's performance. Upon training, the refined model was tested on the Jet Nano, revealing its high efficacy in flame detection. © 2024 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：