检索结果-内蒙古大学图书馆

International Symposium on computer, Consumer and control (IS3C)

作者： Chuan-Kang Liu Chi-Hui Chiang Dept. of Artificial Intelligence and Computer Engineering National Chin-Yi University of Technology Taichung Taiwan Dept. of Information Management Chia Nan University of Parmacy and Science Tainan Taiwan

Federated learning has been regarded as emerging machine learning framework due to its privacy protection. In the IoT trend, federated learning enables edge clients to predict or classify local detected data with a global model that is computed by a FL server through the aggregation of all local models trained by a base FL algorithm. However, meanwhile, its distributed nature also brings several security challenges. Poisoning attacks are the main security risks that can easily and efficiently affect the accuracy of the global learning model. Previous work proposed a voting strategy which can predict the label of the input robustly no matter the attacks the malicious users use. However, its accuracy also easily falls down as the number of malicious user increases while the number of groups is fixed. This paper proposes a new attack defense algorithm against poisoning attacks in federated learning. This paper uses ID-distribution features to group all clients, including normal and malicious ones. The main idea of this proposed scheme is to put those potential malicious clients in specified groups. Hence, the resulting vote output can accurately classify the dataset inputs, regardless of the number of the groups the learning framework has. Our analytical results also show that our scheme exactly perform better compared to original voting scheme.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A statistical analysis on website quality for purchase intention during online shopping 10

A statistical analysis on website quality for purchase inten...

引用

10th IEEE International Conference on Communication Systems and Network Technologies, CSNT 2021

作者： Mittal, Mohit Chauhan, Shaifali Gupta, Swadha Singh, Hardeep CRIStAL INRIA Lille France Dept. of Management Prestige Institute of Management Gwalior India Dept. of Comp. Sci. & Engg. Thapar Institute of Engineering & Technology Patiala India Dept. of Computer Engineering & Technology Guru Nanak Dev University Amritsar India

ISBN: (纸本)9780738105239

According to current scenario, technology play a vital role in the field of communication and services. Internet technology is a big success to interact people virtually. It provide ease to communicate via mail, audio calls and video calls. In the industries point of view raising the business is the main need. For this, website quality is majorly impact on the customers. Therefore, website quality, website reputation are the major parameters to enhance the purchase intention in customer’s perspective. To analyse this we proposed a research model to check the purchase intention over website quality and website reputation based on various statistical algorithms. SPSS Statistics is software to solve the complex problem over the model defined. The simulation results shows remarkable results. © 2021 IEEE.

关键词： Websites

来源：评论

学校读者我要写书评

暂无评论

Satellite Imagery Driven Flood Detection using Deep Learning

Satellite Imagery Driven Flood Detection using Deep Learning

引用

Artificial Intelligence and Quantum Computation-Based Sensor Application (ICAIQSA), International Conference on

作者： Pooja G. Dhawane Pranali Navghare Pranoti Mane Pranali N. Nitnaware Sampada Mashirkar Seema Y. Mendhekar Dept. of Information Technology Yeshwantrao Chavan College of Engg Nagpur India Dept. of Computer Engineering PICT Pune India Dept. of IOT Priyadarshini college of Engg Nagpur India School of Management Ramdeobaba University Nagpur India NC Pharmacy Wanadongri Nagpur India

ISBN: (数字)9798331517953

ISBN: (纸本)9798331517960

Flood detection is crucial for effective dis-aster response and management, enabling early warning systems and targeted relief efforts. This paper proposes a deep learning-oriented approach for flood detection in Convolutional neural networks (CNNs) and transfer learning applied to satellite pictures techniques. Satellite imagery provides wide coverage and high spatial resolution, making it a valuable resource for flood monitoring. However, the complexity of flood patterns requires advanced computational techniques for accurate analysis. CNNs deep learning models have demonstrated impressive achievements in the realm of image classification, showcasing an ability to autonomously acquire significant features from visual data. The proposed methodology aims to train a robust flood detection model capable of discerning flooded and non-flooded regions within satellite images. transfer learning enhances the model's performance by adapting pre-trained models to t Transfer learning uses pre-trained models to improve the performance of the model. he flood detection domain, even in regions with limited historical flood data. the output of this work have the ability make revolution for flood detection systems and improve catastrophe handling techniques, leading to reduced vulnerability in flood-prone areas. by leveraging deep learning methodologies, we can advance our understanding of floods and build more resilient communities to confront this escalating threat. The paper introduces an innovative method for flood detection that combines CNNs and transfer learning in an effort to create a reliable and accurate flood detection model. The work's outcomes contribute to the advancement of flood monitoring systems, improving disaster response and reducing vulnerability in flood-prone areas

关键词： Deep learning Adaptation models Accuracy Computational modeling Transfer learning Data models Satellite images Floods Artificial intelligence Monitoring

来源：评论

学校读者我要写书评

暂无评论

Optical Evanescent Field for Direct Observation of Sub-100nm Particle Motion on Glass Surface

Optical Evanescent Field for Direct Observation of Sub-100nm...

引用

Robotics, engineering, Science, and Technology (RESTCON), International Conference on

作者： Panart Khajornrungruang Thitipat Permpatdechakul Keisuke Suzuki Aran Blattler Yutaka Terayama Daiki Goto Pipat Phaisalpanumas Natthaphon Bun-Athuek Amornphun Phunopas Dept. of Intelligent and Control System Faculty of Computer Science and Systems Engineering Mechanical Science and Technology Division Kyushu Institute of Technology Iizuka-Shi Fukuoka Japan Dept. of Interdisciplinary Informatics Graduate School of Computer Science and Systems Engineering Mechanical Information Science and Technology Division Kyushu Institute of Technology Iizuka-Shi Fukuoka Japan Dept. of Production and Robotics Engineering Faculty of Engineering King Mongkut’s University of Technology North Bangkok Bangsue Bangkok Thailand Dept. of Intelligent and Control System Graduate School of Computer Science and Systems Engineering Mechanical Science and Technology Course Kyushu Institute of Technology Iizuka-Shi Fukuoka Japan Dept. of Industiral Engineering Faculty of Engineering King Mongkut’s University of Technology North Bangkok Bangsue Bangkok Thailand Dept. of Mechanical Engineering Technology College of Industrial Technology King Mongkut’s University of Technology North Bangkok Bangsue Bangkok Thailand

To directly investigate the dynamic nanoscale phenomenon on the surface being processed in wet conditions such as precision polishing, and cleaning in semiconductor industrial, an optical method for visualization and observation of each sub-100 nm sized particle that is moving on an interface such as a silica glass surface by applying an evanescent field have been proposing. Subsequently, we developed an experimental apparatus equipped with an optical microscopy system for verifying the moving particle observation method in a laboratory scale. This article introduces some experimentally direct observation results of duplicated wet processes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SSRN

引用

SSRN 2024年

作者： Kang, Hanhoon Jung, Jong-Kyun Dept. of Computer Engineering Sejong University 98 Gunja-ro Gwangjin-gu Seoul05004 Korea Republic of Dept. of IT Policy and Management Soongsil University 369 Sangdo-ro Dongjak-gu Seoul06978 Korea Republic of

Recent advancements in embedding models have brought significant progress in the field of natural language processing (NLP). In particular, embedding models play a critical role in the Retrieval-Augmented Generation (RAG) pipeline by enabling the effective retrieval of similar documents, thus mitigating the hallucination phenomenon in large language models (LLMs). Against this background, the selection of public embedding models and the optimization of their performance through fine-tuning have emerged as pivotal challenges. This study conducts a linguistic evaluation of various publicly available embedding models and addresses performance deficiencies in specific tasks through the application of fine-tuning techniques. The experiments covered five linguistic tasks, and for tasks with poor performance, fine-tuning of the embedding models resulted in an average improvement of 9.4%. The findings of this research are expected to provide valuable insights into the selection and fine-tuning of embedding models for NLP applications and RAG pipelines. © 2024, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Performance analysis of online shopping for customer satisfaction using PLS-SEM 10

Performance analysis of online shopping for customer satisfa...

引用

10th IEEE International Conference on Communication Systems and Network Technologies, CSNT 2021

作者： Chauhan, Shaifali Banerjee, Richa Mittal, Mohit Singh, Hardeep School of Studies in Management Jiwaji University Prestige Institute of Management Gwalior India Dept. of Management Prestige Institute of Management Gwalior India CRIStAL INRIA Lille France Dept. of Computer Engineering & Technology Guru Nanak Dev University Amritsar India

ISBN: (纸本)9780738105239

Advancement in technology from past few years provide a dyanmic platform to various customers and companies interact virtually. To ease the shopping, various sites are available to buy accessories online such as cloths, electronics, etc. Customer satisfaction is a ***, to consider positive aspect to enhance the business based on companies point-of-view on the other hand ease of availability and satisfaction are main parameters according to users point-of-view. For this, a model is proposed with various hypothesis to find the level of consumer’s satisfaction. The major inputs are hedonic shopping value, website quality and utilitarian shopping value to the proposed model. The model is test with statistical tool such as PLS-SEM 3.3 version. PLS-SEM is efficiently work to solve complex problems. The simulation shows notable results. © 2021 IEEE.

关键词： Customer satisfaction

来源：评论

学校读者我要写书评

暂无评论

Integrating Simulation and Optimization: A Case Study in Pamplona for Self-Collection Delivery Points Network Design 35

Integrating Simulation and Optimization: A Case Study in Pam...

引用

35th European Modeling and Simulation Symposium, EMSS 2023

作者： Izco, Irene Serrano-Hernandez, Adrian Sawik, Bartosz Faulin, Javier GILT-OR Group Institute of Smart Cities Dept. Statitistics Computer Science and Mathematics Public University of Navarra Campus Arrosadia s/n Pamplona31006 Spain Department of Business Informatics and Engineering Management AGH University of Science and Technology Mickiewicza 30 Kraków30059 Poland

ISBN: (纸本)9788885741881

The disruptions experienced by the processes in the last mile delivery during the SARS-CoV-2 pandemic raised the dilemma of up-to-date last mile approaches for Urban Logistics (UL) issues. Self-Collection Delivery Systems (SCDS) have been proved to be an improvement for all the players of the SC, providing flexibility of time-windows and reducing overall mileage, delivery time and, consequently, gas emissions. Differing from previous works involving hybrid modeling for automated parcel lockers (APL) network design, this paper brings a System Dynamics Simulation Model (SDSM) to forecast online shopping demand in the Spanish city of Pamplona. A bi-criteria Facility Location Problem (FLP) is solved by means of an e-constraint method, where e is defined as the level of coverage of the total demand. The experiment run considers 90% of demand coverage, in order to obtain the most complex network possible. The simulation and demand forecast was carried out using Anylogic simulation software and the optimization procedure makes use of the Java-based CPLEX API solver. © 2023 The Authors.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

Optimized ECG Signal Compression and Security for Efficient Cardiac Abnormality Detection 4

Optimized ECG Signal Compression and Security for Efficient ...

引用

4th IEEE International Conference on ICT in Business Industry and Government, ICTBIG 2024

作者： Roy, Vandana Baghel, Abhishek Singh Jain, Sapan Kumar Mohanty, Sribidhya Srinivasarao, G. Bhatt, Anushka Ggits Dept of Elrectronics Communication M.P Jabalpur India Ies Institute of Technology and Management Ies University Department of Computer Science & Engineering M.P Bhopal India Gyan Ganga Institute of Technology & Sciences Dept of Cse MP Jabalpur India Graphic era Deemed to be University India Chalapathi Institute of Technology Dept. of Cse AP Guntur India Ggits MP India

ISBN: (纸本)9798331518981

Protecting biological data during dissemination, this ECG waves, is becoming more important, and this work is relevant to that requirement. It is of the extreme importance to guarantee the security of transferred medical information as the amount of data sent over the web continues to rise. It proposes a watermarking approach for compressing the ECG waves in addition to securing the information. By including subject information in ECG waves in a way that doesn't change their diagnostic usefulness, watermarking makes signal blocking possible. The frequency region and the domain of space are the two primary categories of watermarking methods. Improving signal quality to accept watermarking is also covered in the chapter using the Fourier Decomposition Method (FDM). In a setting with a large amount of ECG information moving around, FDM is used to accomplish realistic data compression as well, which is similar to decoding. This prevents the expansion of storage and bandwidth requirements while yet achieving a viable signal. The proposed technique beats its predecessors in relations of SNR, PRD, and compression coefficient, as shown by simulation results. As a whole, this approach improves the security of ECG signals and data minimisation for hospitals that are handled electronically. © 2024 IEEE.

关键词： Electrocardiography

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence Oriented User Sentiment Evaluation System on Social Networks using Modified Deep Learning Principles 5

Artificial Intelligence Oriented User Sentiment Evaluation S...

引用

5th International Conference on Mobile Computing and Sustainable Informatics, ICMCSI 2024

作者： Thangamayan, S. Jagdale, Sandip Nivrutti Lakshmi, T. R. Kalai Gopal Thatipudi, Jayendra Penyameen, K. Khan, Bhola Saveetha Institute of Medical and Technical Sciences Saveetha School of Law Department of Research and Development Chennai77 India Yashwantrao Mohite Institute of Management Karad India Sathyabama Institute Of Science And Technology School Of Management Studies Chennai India University of North Texas Dept. of Computer Science United States Velammal College Of Engineering And Technology Madurai India MJP Rohilkhand University Department of Regional Economics Bareilly India

ISBN: (纸本)9798350395235

Sentiment analysis, a pivotal aspect of natural language processing, is vital for deciphering the emotional nuances embedded in textual data. This project introduces an innovative workflow that amalgamates various techniques to elevate sentiment analysis performance. The workflow encompasses Fuzzy C-means (FCM) clustering for pattern identification, Differential Multi-layer Whale Optimization (DWO) for feature extraction, and a classification phase utilizing diverse deep learning models, including Long Short-Term Memory (LSTM) and Convolutional Neural Networks (CNN). Additionally, Ant Lion Optimization (ALO) ensures system optimization, fostering robustness and adaptability. The proposed system is evaluated against eight distinct deep learning models, each offering unique architectures or configurations. Remarkably, the proposed workflow achieves an impressive accuracy of 96%, underscoring its efficacy in discerning complex sentiments. This high level of accuracy positions the system as a powerful tool for real-world applications where nuanced understanding of human sentiment is paramount. The project contributes to the evolving landscape of sentiment analysis, providing a comprehensive framework for extracting valuable insights from diverse textual datasets. © 2024 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Improving the Efficiency of a Multistage Evaporator Station for Sugar Production Using Neural Networks 4

Improving the Efficiency of a Multistage Evaporator Station ...

引用

4th IEEE International Conference on Modern Electrical and Energy System, MEES 2022

作者： Zaiets, Nataliia Lutska, Nataliia Vlasenko, Lidiia National University of Life and Environmental Sciences of Ukraine Det. of Automation and Robotic Systems Kyiv Ukraine National University of Food Technologies Dept. of Automation and Computer Technologies of Control Systems Kyiv Ukraine State University of Trade and Economics Dept. of Software Engineering and Cyber Security Kyiv Ukraine

ISBN: (纸本)9798350346831

The paper shows the process of developing a model of multistage evaporator station of a sugar factory based on a neural network. The neural network predicts the main performance indicators of the multistage evaporator station, such as the concentration of syrup at the output of the evaporator and the amount of evaporated water at the station. Unlike existing solutions, forecasting is performed in real time based on a set of indicators of the automation system (temperatures, flow rates, levels, pressure, density in the apparatus) and industrial laboratory (concentration of solids at the inlet to the evaporation station). The proposed neural network model has an MLP structure with 27 inputs, 2 outputs and one hidden layer with 20 neurons and predicts these indicators with an error of less than 5%. This allows to increase the informative support of the operator-technologist on the quality indicators of the enterprise without additional load on the industrial laboratory and without additional cost automatic quality devices, as well as to perform timely adjustment of the technological mode of the department. © 2022 IEEE.

关键词： Evaporation

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：