检索结果-内蒙古大学图书馆

2025 International Conference on Multi-Agent Systems for Collaborative Intelligence, ICMSCI 2025

作者： Rajan, K. Palanivel Raj, J. Relin Francis Krishnan, R. Santhana Balamuralikrishnan, G. Vidyasree, G. Jothi, J. Nirmal Psna College of Engineering and Technology Department of Electrical and Electronics Engineering Dindigul India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Electronics and Communication Engineering Chennai India Scad College of Engineering and Technology Department of Electronics and Communication Engineering Cheranmahadevi India Velammal College of Engineering and Technology Department of Computer Science and Engineering Madurai India Sri Sai Ranganathan Engineering College Department of Computer Science and Engineering Coimbatore India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Electronics and Communication Engineering Avadi India

ISBN: (纸本)9798331509828

The preservation of biodiversity, particularly the monitoring of rare tree species in dynamic forest ecosystems, presents significant challenges due to the complexities in detecting and analyzing forest changes. This research introduces a novel IoT -assisted AI framework, termed FoLiA-Net (Forest Lightweight Adaptive Network), designed to improve the efficiency and accuracy of monitoring rare trees. The proposed algorithm combines IoT sensor data with machine learning techniques to adaptively detect, classify, and track rare tree species across large and dynamically changing forest areas. The framework utilizes a lightweight neural network structure to ensure real-time processing while minimizing computational resources, making it suitable for deployment in resource-constrained environments. Simulation experiments were conducted to evaluate the performance of FoLiA-Net in comparison with existing algorithms, including Faster R-CNN (F-R-CNN), Random Forest Classifier (RFC), and Gradient Boosting Machines (GBM). The evaluation was based on several key performance metrics such as accuracy, latency and detection efficiency. The results revealed that FoLiA-Net outperformed the existing algorithms in terms of accuracy and computational efficiency, demonstrating a notable improvement in the monitoring of rare tree species in diverse forest ecosystems. The proposed framework is particularly effective in large-scale forest monitoring, providing a valuable tool for biodiversity conservation efforts © 2025 IEEE.

关键词： Biodiversity Forest Ecosystems Machine Learning Rare Trees Simulation Sustainability

来源：评论

学校读者我要写书评

暂无评论

Fast Mesh Generation in Multi-layer Lattice Boltzmann Simulation with Moving Boundaries 41st

Fast Mesh Generation in Multi-layer Lattice Boltzmann Simula...

引用

41st computer Graphics International Conference, CGI 2024

作者： He, Peng Wang, Liangjun Xu, Lei Zhang, Wu Zhu, Wenhao School of Computer Engineering and Science Shanghai University Shanghai200444 China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China School of Mechanics and Engineering Science Shanghai University Shanghai200072 China

ISBN: (纸本)9783031820236

Large-scale computational fluid dynamics methods rely on efficient and accurate mesh generation algorithms, especially when handling complex geometries, as mesh generation in such cases can be time-consuming. This paper presents a new approach to mesh generation, integrating the multi-layer lattice Boltzmann method with moving boundaries. This technique minimizes the impact of machine errors on computational geometry, thereby improving the precision of geometric object recognition within the mesh. Furthermore, it significantly cuts down the time needed for mesh generation. Theoretical analyses and numerical experiments reveal that the time required for mesh generation in this study has been reduced by an order of magnitude, facilitating the rapid creation of multi-layer grid nodes numbering in the tens of millions within seconds. By combining moving grids with moving boundaries, this method verifies airflow around airfoils in various grid setups. Moreover, we have extended its application to three-dimensional space, effectively simulating submarine movements. In scenarios with moving boundaries, where mesh generation is necessary at each time step, this method particularly shines. It requires minimal additional computation time, which is a significant advantage. This makes it a practical solution for mesh generation in large-scale simulations. Such simulations often use the multi-layer lattice Boltzmann method and involve moving boundary flow. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Mesh generation

来源：评论

学校读者我要写书评

暂无评论

Evaluating Artificial Neural Networks and Emerging Machine Learning Methods for Engine Performance and Emissions Prediction: A Review 4

Evaluating Artificial Neural Networks and Emerging Machine L...

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Galat, Umesh Rewatkar, Rajendra Kothare, Chandrakant Datta Meghe Institute of Research and Higher Education Aids Faculty of Engineering and Technology Department of Computer Science and Engineering Maharashtra Wardha India Shri Shankarprasad Agnihotri Collge of Engineering Department of Mechanical Engineering Maharashatra Wardha India

ISBN: (纸本)9798331523923

These due to the shift towards the cleaner energy generation and newer and sophisticated engine technologies the prediction of the performance and emission of engine is of vital importance for the designer for the purpose of ANR as well as the emission control standards. This review also assesses the performance of ANNs and the new machine learning techniques in this area. ANNs especially the single layer and multi-layer networks have shown good levels of predictions of engine performance and emission for ethanol-gasoline, bioethanol and other fuel blends. For example, the models based on Levenberg-Marquardt optimization and the Bayesian regularization have revealed essential correlation coefficients and minimized mean squared errors. Based on comparative analyses, the further improvement of the predictive ability and speed of ANNs is stressed, including applications of ANNs integrated with other approaches like Response Surface Methodology (RSM), and other developing approaches like Extreme Learning Machines (ELM) and Support Vector Regression (SVR). However, challenges are concluded to remains including data quality, model complexities and computational resources. This review reveals that, for tackling these issues and enhancing the progress in developing efficient and sustainable engine solutions, detailed databases and refined mathematical modeling approaches are required. The directions for future research are to obtain better quality data, enhance computational time, and determine more fuel blends and engine settings for the model. © 2025 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Translational Generative Retrieval via Potential Query Generation

Translational Generative Retrieval via Potential Query Gener...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Guo, Yihan Liu, Tingwen Sheng, Jiawei Ma, Duohe Sun, Ming Tian, Ling Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China

ISBN: (纸本)9798350368741

Document retrieval aims to find documents related to the query from all candidate documents. Existing studies develop the Generative Retrieval approach, which assigns a unique DocID to each document, and then measures document-query relevance based on the probability of generating the expected DocID for the given query. However, the generated DocID can have expressive limitation of different semantic topics, leading to semantic gaps in document retrieval. Besides, existing GR models usually suffer from the catastrophic forgetting when memorizing new documents incrementally, which makes real-world application impractical. To overcome these issues, we propose Translational Generative Retrieval, which translates each document into potential queries reflecting different topics, specifically by a sequence of token probability distributions. To better model the semantics of potential queries and effectively decode the target query from the distributions, we propose DirEcted Acyclic Graph Retrieval (DEAR) model, which reforms the distributions from a non-autoregressive generative model into a Directed Acyclic Graph. Experimental results demonstrate that DEAR outperforms existing retrieval models, setting a new state-of-the-art in generative retrieval. © 2025 IEEE.

关键词： Directed Acyclic Graph Generative Retrieval Non-autoregressive Generation Query Generation

来源：评论

学校读者我要写书评

暂无评论

Credit Card Fraud Detection Using Random Forest and K-Nearest Neighbors (KNN) Algorithms 5th

Credit Card Fraud Detection Using Random Forest and K-Neares...

引用

5th International Conference on Computing, Communications, and Cyber Security, IC4S 2023

作者： Alhabib, Abdulaziz Abdulrhman Alasiri, Abdulaziz Fae Alharbi, Mazen Bunayan Ahmad, Sultan Eljialy, A.E.M. Department of Information Systems College of Computer Engineering and Sciences Prince Sattam Bin Abdulaziz University P.O.Box. 151 Alkharj11942 Saudi Arabia Department of Computer Science College of Computer Engineering and Sciences Prince Sattam Bin Abdulaziz University P.O.Box. 151 Alkharj11942 Saudi Arabia Chandigarh University Punjab Mohali Gharuan140413 India

ISBN: (纸本)9789819773701

In this paper, we explored the application of both the Random Forest and K-Nearest Neighbors (KNN) algorithms for fraud detection. Fraudulent activities pose significant threats to various industries, making their detection crucial. We reviewed related works on fraud detection, highlighting the effectiveness of both the Random Forest and KNN methods. We proposed a system utilizing a combination of Random Forest and KNN models for credit card fraud detection, detailing its architecture and methodology. The system preprocesses and splits data, trains the models, and evaluates their performance on a testing set. We analyzed the results, demonstrating the accuracy, robustness, and scalability of the proposed system. Additionally, we presented data on the most common hours for fraudulent transactions and the top jobs associated with them. Overall, this study emphasizes the efficacy of utilizing both Random Forest and KNN algorithms in mitigating the risks associated with fraud and offers a valuable tool for safeguarding against financial malfeasance. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Random forests

来源：评论

学校读者我要写书评

暂无评论

Workflow Task Offloading Upon MEC: A Novel Mobility-Aware and Clustering-Based Approach 31st

Workflow Task Offloading Upon MEC: A Novel Mobility-Aware a...

引用

31st International Conference on Web Services, ICWS 2024, Held as Part of the Services Conference Federation, SCF 2024

作者： Wang, Tenghui Feng, Jiafeng Ma, Yong Xia, Yunni Yu, Yang Dong, Yumin Xu, Xifeng Li, Jinpeng Zhao, Han Dai, Mengxuan College of Computer Science Chongqing University Chongqing400030 China China Huadian Corporation Ltd. Guangdong Company Guangzhou510620 China School of Computer and Information Engineering Jiangxi Normal University Jiangxi Nanchang330022 China Guodian Nanjing Automation Co. Ltd. Nanjing210032 China College of Computer and Information Science Chongqing Normal University Chongqing401331 China

ISBN: (纸本)9783031770715

The widespread deployment of intelligent Internet of Things (IoT) devices brings strict latency demands on complex workload patterns such as workflows. In such scenarios, tremendous data is generated and processed in accordance with specific service chains. Mobile Edge Computing (MEC) has proven its feasibility in reducing the traffic in the core network and relieving cloud datacenters of fragmented computational demands. However, existing solutions to multi-workflow scheduling and offloading in MEC are still limited due to the fact that they usually make task dispatching decisions prior to real execution, making it difficult to cope with the dynamicity of the environment and the mobility of users. To address this challenge, we developed a novel computation offloading strategy by synthesizing a Harris Hawks Optimization-based particle filter trajectory prediction algorithm for forecasting future user locations, a clustering-based multi-workflow merging algorithm for identifying redundant tasks and a Lyapunov optimization-based DQN algorithm for yielding computation offloading schedules. Simulation results clearly show that method beats traditional ones across multiple performance metrics. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Computation offloading

来源：评论

学校读者我要写书评

暂无评论

ICA-Net:improving class activation for weakly supervised semantic segmentation via joint contrastive and simulation learning

引用

Optoelectronics Letters 2025年第3期21卷 188-192页

作者： YE Zhuang LIU Ruyu SUN Bo School of Information Engineering Chengdu Aviation Vocational and Technical CollegeChengdu610100China School of Computer Science and Engineering Hangzhou Normal UniversityHangzhou311121China Quanzhou Institute of Equipment Manufacturing Haixi InstitutesChinese Academy of SciencesQuanzhou362200China

In the field of optoelectronics,certain types of data may be difficult to accurately annotate,such as high-resolution optoelectronic imaging or imaging in certain special spectral *** supervised learning can provide a more reliable approach in these *** popular approaches mainly adopt the classification-based class activation maps(CAM)as initial pseudo labels to solve the task.

关键词： high resolution imaging supervised learning class activation maps joint contrastive simulation learning special spectral ranges weakly supervised learning optoelectronics

来源：评论

学校读者我要写书评

暂无评论

CalliSense: An Interactive Educational Tool for Process-based Learning in Chinese Calligraphy 25

CalliSense: An Interactive Educational Tool for Process-base...

引用

Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems

作者： Xinya Gong Wenhui Tao Yuxin Ma Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen Guangdong China

来源：评论

学校读者我要写书评

暂无评论

Using Blue Whale Technology: An ML Edge Self-Adaptable Vehicle Slowdown Earliest Warning Information System 8th

Using Blue Whale Technology: An ML Edge Self-Adaptable Vehic...

引用

8th International Conference on Microelectronics Electromagnetics and Telecommunications, ICMEET 2023

作者： Murali, N. David, D. Beulah Research Scholar Department of Computer Science and Engineering Saveetha School of Engineering SIMATS Tamilnadu Chennai India Department of Data Analytics Institute of Information Technology Saveetha School of Engineering SIMATS Tamilnadu Chennai India

ISBN: (纸本)9789819784219

Human life is challenged by this main work’s ultimate goal of reducing accidents and ensuring life safety due to the enormous growth of vehicles and those based on safety. Here, cases of suspected drunk driving, reckless driving, etc., are present. In this scenario, vehicles are traveling at full speed and irresponsibly using technology on all roads. An early warning system is used to stop auto accidents. In order to accommodate the city's steadily increasing automobile population, intelligent traffic systems must be designed in a resourceful and sustainable manner using all available technology in both light and dark. The advanced ML's work on unexpected traffic flow and all road conditions resulted in significant real-time changes in the flow of traffic for every significant issue that arose. Here, the Blue Whale technology makes use of clever intelligence to quickly identify, detect, and modify warning systems. The primary objective of the study was to train CNN/BWT on the collected data sets in order to operationalize the unsupervised approach for the prediction of critical situations. Additionally, it makes an effort to clarify the situation so that guests can feel more at ease and help them decide on transfers in time-sensitive situations. IOT is a practical way to locate the nearest object using machine learning methods that are accurate and apply received data sets, resulting in significant findings that support object recognition. The paperwork fully focuses on improving driving knowledge and offering new approaches for quick object recognition. The Fast Warning System Initiative, which aims to increase daytime safety and security, is providing a prior warning system. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Backward wave tubes

来源：评论

学校读者我要写书评

暂无评论

Secure Data Embedding in Digital Images: Enhancing Covert Communication with LSB-Based Techniques

引用

Procedia computer science 2025年 258卷 2091-2100页

作者： Tina Babu Rekha R Nair Rajesh T M Kishore S Department of Computer Science and Engineering School of Advanced Computing Alliance University Bengaluru India Department of Computer Science and Engineering Dayananda Sagar University Bengaluru India Department of Computer Applications Nitte (Deemed to be University) Nitte Institute of Professional Education Mangalore Karnataka India

Information security and the ability to convey secret messages have been necessities since the dawn of civilization. Various media forms, such as photos, audio files, and videos, offer a conducive environment for concealing information that is invisible to the human eye in the current digital era by taking advantage of superfluous or unused data bits. This hidden information can be used for secret communication or as a way to include more messages into a single file, which will minimize the quantity of data that needs to be sent. In order to encode and store messages within the RGB pixels of a cover image (canvas image) without causing visual distortion, two methods are shown in this study. Both approaches split the message into separate segments, which are then translated into 8-bit binary values. These values are then encrypted using a straightforward symmetric exclusive OR (XOR) encryption key, and the message is encoded in the canvas image by changing the pixel value’s least significant bit (LSB). The first approach encodes the secret message from top to bottom and left to right by sequentially storing it beginning with the top-left pixel. By encoding the message bits into the cover image pixels at random, the second technique reduces the susceptibility of the concealment to analysis. By using redundant data in digital media, these approaches can hide information while preserving the original visual integrity. This makes them an effective and safe way to communicate covertly or embed data into a single file, which maximizes data transmission.

关键词： Steganography Least Significant Bit (LSB) Data Encryption Covert Communication Digital Media XOR Encryption

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：