检索结果-内蒙古大学图书馆

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Li, Junfan Wu, Zheshun Xu, Zenglin King, Irwin School of Computer Science and Technology Harbin Institute of Technology Shenzhen China Pengcheng Lab China Institute Fudan University China Shanghai Academy of AI for Science China Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong

We consider online model selection with decentralized data over M clients, and study the necessity of collaboration among clients. Previous work proposed various federated algorithms without demonstrating their necessity, while we answer the question from a novel perspective of computational constraints. We prove lower bounds on the regret, and propose a federated algorithm and analyze the upper bound. Our results show (i) collaboration is unnecessary in the absence of computational constraints on clients;(ii) collaboration is necessary if the computational cost on each client is limited to o(K), where K is the number of candidate hypothesis spaces. We clarify the unnecessary nature of collaboration in previous federated algorithms for distributed online multi-kernel learning, and improve the regret bounds at a smaller computational and communication cost. Our algorithm relies on three new techniques including an improved Bernstein's inequality for martingale, a federated online mirror descent framework, and decoupling model selection and prediction, which might be of independent interest. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Selective Kernel Spatial Feature Extraction based Deep Learning Approach for Identification and Classification of Archaeological Sites

Selective Kernel Spatial Feature Extraction based Deep Learn...

引用

2024 International Conference on Intelligent Algorithms for Computational Intelligence Systems, IACIS 2024

作者： Sajja, Sri Lavanya Alsalami, Zaid Sunil, G. Sunil Kumar, V. Mohamad Ramadan, Ghazi Malla Reddy Engineering College for Women Secunderabad India The Islamic University Engineering College of Technical Engineering Department of Computers Techniques Najaf Iraq Sr University School of Computer Science & Artificial Intelligence Warangal India Nitte Meenakshi Institute of Technology Dept. of Ai and Ml Bengaluru India Ahl Al Bayt University College of Mlt Karbala Iraq

ISBN: (纸本)9798350360660

Deep Learning (DL) based identification and classification of archaeological sites are being used progressively from satellite images obtained from Geographic Information System (GIS). Even though, there were promising results from the existing researches, there is still need to enhance the classification with distinct features of the satellite images. The methods found challenging to accurately or partially identify an archaeological feature especially in a complex landscape due to lack of distinction between archaeological and non-archaeological features. For this, the geo-referenced satellite images are considered in this research, which are pre-processed using min-max normalization for efficient data analysis and to remove unwanted data. The Selective kernel spatial Feature Extraction (SFE) module is used to improve the feature extraction process where the spatial features are extracted. The extracted features are then classified using Fully Convoluted Deep Neural Network (FCDNN) for effective identification and classification of archaeological sites. The results showed that the proposed SFE-FCDNN achieved better classification accuracy with 98.83%, precision of 97.41%, and an error rate of 1.71 when compared to the existing methods such as Neural Network (NN), and Backpropagation Neural Network (BNN). © 2024 IEEE.

关键词： Satellite imagery

来源：评论

学校读者我要写书评

暂无评论

Implementing IoT and Deep Learning-Based Educational Systems for Assessing Practical Learning with Cloud Computing Applications

Implementing IoT and Deep Learning-Based Educational Systems...

引用

Technological Advancements in Computational sciences (ICTACS), International Conference on

作者： Hardeo Kumar Thakur Minal Bafna Jagendra Singh Usikela Naresh Susmi Biswas Saggurthi Kiran School of Computer Science Engineering and Technology Bennett University Greater Noida India Department of Physics Agrawal PG College Jaipur India Department of Computer Science and Engineering(AI&ML) CVR College of Engineering Rangareddy India Department of Management Science Haldia Institute of Management MAKAUT West Bengal India Department of CSE (AI&ML) CMR Technical Campus (Autonomous) Hyderabad India

ISBN: (数字)9798350387490

ISBN: (纸本)9798350387506

In this study, the practical application of technologies related to IoT and machine learning in the robotics education context is examined based on the use of a robot with two proximity sensors. The trial system was designed to leverage the real-time sensor data and monitor and optimize student interactions with the robot in the course of performing such tasks as object manipulation and palletization. The sensor data is used to critically track the accuracy of student actions and help mentors provide feedback on the issue. The machine learning models used in the study, which are Recurrent Neural Network (RNN), K-Nearest Neighbors (KNN), Support Vector Machine (SVM), and Long Short-Term Memory (LSTM), are applied to analyze the sensor data and predict and classify the student's actions so that corrective measures can be taken in time. The RNN model has the highest accuracy and efficiency for the task, as it reaches the level of 96.7 % compared to 80% for KNN, 71% for SVM, and 75% for LSTM. This advantage is explained by the capability to model temporal dependencies or otherwise capture with its memory the sequences present in the sensor data. The data is transmitted securely and efficiently to the cloud platforms and back due to the implementation of the IoT, which also helps to deploy the model more effectively. Overall, it is concluded that the integration of IoT and machine learning is beneficial and transformative in educational contexts as it provides students with personalized real-time feedback. In this way, the level of proficiency of the students in dealing with robotic and IoT-based systems is significantly enhanced, preparing them to successfully address the future challenges of industry and academia in the sphere.

关键词： Support vector machines Recurrent neural networks Education Machine learning Nearest neighbor methods Robot sensing systems Data models Real-time systems Sensors Long short term memory

来源：评论

学校读者我要写书评

暂无评论

LLM-based Methodology for Expanding 3D Metadata in Point Cloud 27

LLM-based Methodology for Expanding 3D Metadata in Point Clo...

引用

27th International Conference on Advanced Communications Technology, ICACT 2025

作者： Kim, Geon-Woo Kim, Joo-Chang Department of AI Computer Science and Engineering Kyonggi University Suwon16227 Korea Republic of Contents Convergence Software Research Institute Kyonggi University Suwon16227 Korea Republic of

ISBN: (纸本)9791188428137

This paper proposes a method for expanding the metadata of three-dimensional point cloud data using Large Language Models (LLMs). Currently, point cloud data plays a crucial role in various fields such as autonomous driving and medical image reconstruction, necessitating the expansion of metadata for efficient processing. Traditionally, metadata construction has relied on manual input, which is prone to errors. In this study, we propose a method that utilizes LLMs, particularly the Llama 3.1 model, to extract the center points of each class in the point cloud data and expand the metadata by adding these center points to the annotation files. By using center points, computational costs are reduced, and the performance of segmentation and detection models based on this data is improved. Copyright 2025 Global IT Research Institute (GIRI). All rights reserved.

关键词： Data assimilation

来源：评论

学校读者我要写书评

暂无评论

Context-Aware Summarization for PDF Documents using Large Language Models

Context-Aware Summarization for PDF Documents using Large La...

引用

Expert Clouds and Applications (ICOECA), International Conference on

作者： Akshara Ramprasad P. Sivakumar B. Tech Computer Science with specialization in AI & ML School of Computer Science and Engineering Vellore Institute of Technology Chennai India School of Computer Science and Engineering Vellore Institute of Technology Chennai India

ISBN: (数字)9798350385793

ISBN: (纸本)9798350385809

In an era characterized by the overflow of textual information, the demand for effective text summarization techniques has become increasingly evident. This research study presents a novel solution to address this demand: the development of a PDF Summarizer Generative ai Platform for context-aware text and document summarization. The developed platform empowers users to generate informative summaries from lengthy textual documents. It features an interface powered by Gradio for enabling user-friendly accessibility. Equipped with essential components such as Openai's language models for text comprehension, Chroma vector enables document embedding and conversational retrieval chains for contextual understanding, where the platform offers a comprehensive solution. Users can effortlessly upload documents in various formats, including PDFs, and interactively engage with the system to obtain concise summaries tailored to their specific requirements.

关键词： Generative ai Databases Large language models Text summarization Portable document format Vectors Context modeling

来源：评论

学校读者我要写书评

暂无评论

Research on Optimization Algorithm of Real Estate Enterprise Value Evaluation Based on BP Neural Network 2

Research on Optimization Algorithm of Real Estate Enterprise...

引用

2nd International Conference on Smart Technologies for Smart Nation, SmartTechCon 2023

作者： Niranjanamurthy, M. Saravanan, S. Mahaveerakannan, R. Surendran, S. Nakrani, Tulsidas Arun, M.R. Department of AI and ML BMS Institute of Technology and Management Avalahalli Karnataka Bangalore India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai India Tamilnadu Chennai India Department of Computer Science and Engineering Tagore Engineering College Tamil Nadu Chennai India Department of Computer Application Sankalchand Patel College of Engineering Sankalchand Patel University Gujarat Visnagar India Department of ECE Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Avadi Tamilnadu Chennai India

ISBN: (纸本)9798350305418

Because of its professional skills and expertise, it is able to persuade both the buyer and the selling and make the transaction easier. An optimal design scheme for real estate businesses' worth appraisals is proposed here, and it is based on BPNN (BP neural network). A worth appraisal system is developed by doing an analysis of several worth indicators pertaining to real estate companies, and then the system is optimized with the use of BPNN. In the final step, an analysis of the simulation test is performed. According to the findings of the simulation, the arithmetic has a certain accuracy, which is 8.34% higher than the accuracy of traditional arithmetic. On the premise of ensuring the efficient processing of data in batches and finding the rules therein, reduce the impact of human subjectivity, improve the accuracy and scientificity of real estate appraisal, and provide certain reference for the national and local governments to reasonably regulate house prices, so as to promote the stable operation and healthy development of the real estate market. In doing so, you will be able to promote the growth of the real estate market in a healthy manner. © 2023 IEEE.

关键词： BP neural network Enterprise worth appraisal Real estate

来源：评论

学校读者我要写书评

暂无评论

Detection of the Crown of Thorns starfish using YOLOv5 8

Detection of the Crown of Thorns starfish using YOLOv5

引用

8th International Conference on Electronics, Communication and Aerospace Technology, ICECA 2024

作者： Kunekar, Pankaj Patil, Pradnya Vishal Bbhagat, Babeetta Patil, Tejal H. Rajas, Neha Sawant, Pratiksha Yuvraj Vishwakarma Institute of Technology Department of Information Technology Maharashtra Pune India Pillai Hoc College of Engineering Computer Engineering Rasayani India Mit School of Computing Maharashtra Pune India Sinhgad College of Engineering Department of Ai&ds Maharashtra Pune India Vishwakarma Institute of Technology Department of Ai&ds Maharashtra Pune India PVG's College of Science and Commerce Department of Computer Science Maharashtra Pune India

ISBN: (纸本)9798350367904

The invasive Crown-of-Thorns starfish (COTS) poses a significant threat to coral reef ecosystems. Early detection and removal are crucial to mitigating their impact. This research proposes a YOLOv5-based object detection system to accurately identify and locate COTS in underwater images. By fine-tuning the YOLOv5 model with a dataset of COTS images, the system can effectively detect and classify COTS with high precision and recall. The output of the system includes bounding boxes and confidence scores for each detected COTS, enabling timely intervention and removal efforts. This research contributes to the conservation of coral reefs by providing a valuable tool for monitoring and controlling COTS populations. The proposed system can be integrated into underwater drones or diveroperated devices to facilitate efficient and accurate COTS detection and removal. © 2024 IEEE.

关键词： Reefs

来源：评论

学校读者我要写书评

暂无评论

Enhancing Cloud Image Retrieval Efficiency through Secure Optimization

Enhancing Cloud Image Retrieval Efficiency through Secure Op...

引用

2024 International Conference on Knowledge engineering and Communication Systems, ICKECS 2024

作者： Balakrishna, N. Sakthivel, M. Ushasri, G.Sai Thanmai, J.Naga Kumar, K.Bharath Swamy, G.Venkaiah Mohan Babu University School of Computing Department of AI/ML Data Science AndhraPradesh Tirupati India Sri Shanmugha College of Engineering and Technology Department of Artificial Intelligence Salem Tamilnadu Sankari637304 India Sree Vidyanikethan Engineering College Department of Cse Sree Andhra pradesh Tirupati India

ISBN: (纸本)9798350359688

There is a growing trend of using public clouds for image search outsourcing. However, privacy issues arise when image datasets are directly outsourced to untrusted clouds. Recently, a number of secure image retrieval techniques have been put forth. Nevertheless, the majority of them demand input from image owners in order to create secure indexes, wasting a significant amount of their computational power. Numerous approaches are put forth to address this issue;however, their search accuracy is poor when applied to large datasets. We present the first secure image retrieval scheme in this paper that addresses these two issues at the same time to achieve more precise search results. To reduce search time and image owner costs, we allow cloud servers to locally build a reliable hierarchical index graph using the encrypted image features. Moreover, parallel construction and updating of the secure index is possible. We offer a security analysis of the suggested plan. © 2024 IEEE.

关键词： Cloud security

来源：评论

学校读者我要写书评

暂无评论

Semantic Segmentation and YOLO Detector over Aerial Vehicle Images

引用

computers, Materials & Continua 2024年第8期80卷 3315-3332页

作者： Asifa Mehmood Qureshi Abdul Haleem Butt Abdulwahab Alazeb Naif Al Mudawi Mohammad Alonazi Nouf Abdullah Almujally Ahmad Jalal Hui Liu Faculty of Computing and AI Air UniversityIslamabad44000Pakistan Department of Computer Science College of Computer Science and Information SystemNajran UniversityNajran55461Saudi Arabia Department of Information Systems College of Computer Engineering and SciencesPrince Sattam bin Abdulaziz UniversityAl-Kharj16273Saudi Arabia Department of Information Technology College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Cognitive Systems Lab University of BremenBremen28359Germany

Intelligent vehicle tracking and detection are crucial tasks in the realm of highway ***,vehicles come in a range of sizes,which is challenging to detect,affecting the traffic monitoring system’s overall *** learning is considered to be an efficient method for object detection in vision-based *** this paper,we proposed a vision-based vehicle detection and tracking system based on a You Look Only Once version 5(YOLOv5)detector combined with a segmentation *** model consists of six *** the first step,all the extracted traffic sequence images are subjected to pre-processing to remove noise and enhance the contrast level of the *** pre-processed images are segmented by labelling each pixel to extract the uniform regions to aid the detection phase.A single-stage detector YOLOv5 is used to detect and locate vehicles in *** detection was exposed to Speeded Up Robust Feature(SURF)feature extraction to track multiple *** on this,a unique number is assigned to each vehicle to easily locate them in the succeeding image frames by extracting them using the feature-matching ***,we implemented a Kalman filter to track multiple *** the end,the vehicle path is estimated by using the centroid points of the rectangular bounding box predicted by the tracking *** experimental results and comparison reveal that our proposed vehicle detection and tracking system outperformed other state-of-the-art *** proposed implemented system provided 94.1%detection precision for Roundabout and 96.1%detection precision for Vehicle Aerial Imaging from Drone(VaiD)datasets,respectively.

关键词： Semantic segmentation YOLOv5 vehicle detection and tracking Kalman filter SURF

来源：评论

学校读者我要写书评

暂无评论

An Analytical Study of Reading Habits of Undergraduate Students

An Analytical Study of Reading Habits of Undergraduate Stude...

引用

Communication & Computing (WCONF), World Conference on

作者： Shanmukha Priya Sreenidhi Appalabatla Dept. of Computer Science and Engineering (AI & ML) Malla Reddy University Hyderabad India

Reading habit opens up the door to succeed in learning. It is the soul of education. It is therefore essential to explore the reading habits of professional students to access their interest in reading in turn their personality, communication skills. The practice of reading does not mirror the lifestyle of most undergraduates in Academics and Universities. It is assumed that quite handful of professional students are aware of how to read, what to read, when to read and where to read. Basically, reading for refreshment or relieving stress is quite common among the educated *** study is a concise survey on “Reading Habits of Professional Students.” Data is collected using a validated online questionnaire. It is analysed using Pandas – a Python library for analysis and manipulation of data. Further matplotlib – a popular python package for data visualisation is used to showcase the results in the form of plots and graphs. Interpretations are drawn based on the varied responses from the respondents. The findings disclosed that nearly all the respondents understand the importance of reading. The study revealed that 91.95% love to read from their various fields while 8.05% showed their unwillingness towards book reading. 43.34% of the student population likes reading fiction books, whereas only 1.24% of professional students go with non-fictional books besides 55.42% showed interest to read both. It is observed that reading habit among professional students pursuing their engineering stream is encouraging. It is recommended that students should develop and show curiosity towards book reading. Parents should function as catalysts encouraging their children by supplementing them with needed reading resources besides creating a conducive atmosphere for them.

关键词：

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：