检索结果-内蒙古大学图书馆

13th International Conference of Information and Communication technology, ICTech 2024

作者： Xiu, Pengfei Fu, Lijun Sun, Yukun Wang, Hongliang Li, Xuerao Shenyang Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences Liaoning Province Human-Computer Interaction System Engineering Research Center Based on Digital Twin Shenyang China Shandong University Big Data Technology and Cognitive Intelligence Laboratory University of Chinese Academy of Sciences Shenyang China Shenyang Institute of Computing Technology Chinese Academy of Sciences Liaoning Province Human-Computer Interaction System Engineering Research Center Based on Digital Twin Shenyang China

ISBN: (纸本)9798350376258

Anaerobic fermentation is the most important link to gas production, this paper solves the current problem with the help of the current complete machine learning technology, combining perception and intelligent processing, intelligent processing of information, and derive a decision-making basis for its control or management [1]. Aiming at the current problems of the anaerobic fermentation process in biogas engineering, the system design was carried out, and the anaerobic fermentation process of biogas and its main influencing factors were investigated, and the monitoring parameters of the system were selected to be temperature, PH value, liquid level and redox potential [2]. Previous studies are mainly based on a single prediction model, which leads to poor generalization ability of the model. In this study, unbalanced samples are handled by Borderline-SMOTE algorithm. Based on the Stacking integrated learning approach, a common single prediction model is used to construct a combined prediction model. The accuracy, precision, recall, F1 score and area under the ROC curve are used to evaluate the advantages and disadvantages of the combined prediction model over the single prediction model. ©2024 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Improved Wide&Deep Recommendation Algorithm for User Behavioural Characteristics 13

Improved Wide&Deep Recommendation Algorithm for User Behavio...

引用

13th International Conference of Information and Communication technology, ICTech 2024

作者： Lin, Huaiyuan Ji, Han Shenyang Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences Beijing China Backend Development Centre Beijing Zhongke Zhihe Digital Technology Co. Ltd Ningxia Western Cloud Data Beijing China

ISBN: (纸本)9798350376258

In today's era of rapid data and information growth, people are exposed to more and more complex information. Recommendation system solves the problem of how to accurately deliver information to users, and also helps companies better understand user needs. According to the user's market demand, constantly improve the product experience. By analysing users' information in different areas, we can recommend products that meet their needs and interests in a multi-dimensional way. By analysing the user's behaviour, personal interests and other relevant information, we can improve the recommendation algorithm to push the items that the user is interested in, thereby improving the user experience and increasing the user's time of *** recent years, many models based on Wide&Deep recommendation algorithms have been *** Wide&Deep model can solve many problems of traditional algorithmic models, but at the same time there are also problems such as large data requirements and complex feature engineering. Based on this, a new Deep&iFFM model is proposed, which cross-fertilises each set of features to achieve the selection of different boosting methods for different attributes. The accuracy can be further improved by the collected dataset of user articles. ©2024 IEEE.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

Examining the Acceptance of a Secure and Systematic Personal Research Management Prototype for Higher Education Researchers 7

Examining the Acceptance of a Secure and Systematic Personal...

引用

7th International Conference on Internet Applications, Protocols, and Services, NETAPPS 2024

作者： Awang, Hapini Mansor, Nur Suhaili Adnan, Muhammad Hazim Shahatha Al-Mashhadani, Abdulrazak F. Ghazali, Osman Khamis, Shakiroh Institute for Advanced and Smart Digital Opportunities School of Computing Universiti Utara Malaysia Sintok Malaysia School of Computing Universiti Utara Malaysia Sintok Malaysia Faculty of Business Sohar University Sohar Oman Faculty of Information and Communication Technology Universiti Tunku Abdul Rahman Kampar Malaysia

ISBN: (纸本)9798331519513

Efficient management of research grants is crucial for academic and scientific progress. However, unsystematic research management always poses risks like failure to meet the deadline or even failure to complete the project. To address the challenges in this domain, a prototype called the Smart Personal Research Grant Management System (SPRGM) was developed. This prototype aims to support sustainable and efficient research grant management by providing accessible, high-quality tools tailored to the needs of researchers and administrators. To evaluate its acceptance among potential users, a survey was conducted involving researchers and grant administrators. The evaluation followed the technology Acceptance Model (TAM), examining Perceived Usefulness (PU), Perceived Ease of Use (PEOU), and Intention to Adopt (ITA) using descriptive statistics and correlation analysis. Results indicate the prototype achieved a high level of PU (mean=4.12), PEOU (mean=4.09), and ITA (mean=4.10). However, no significant correlation was found between PEOU, PU, and ITA, thus rejecting H1 (r = 0.726, p = 0.164), H2 (r = 0.321, p = 0.597), and H3 (r = 0.726, p = 0.164). The qualitative data was analyzed using sentiment and thematic analyses. Sentiment analysis revealed predominantly positive and neutral user perceptions, with an average sentiment score of +0.50 and a magnitude score of 0.51. Furthermore, the thematic analysis indicated that SPRGM is well-received by users, with some suggestions for improvement. This study extends the boundary of knowledge by exploring the role of digital technology in improving research grant management and promoting efficient use of resources in academic and research institutions. © 2024 IEEE.

关键词： Research and development management

来源：评论

学校读者我要写书评

暂无评论

Assessment and Analysis of IoT Protocol Effectiveness in Data Exfiltration Scenario 20

Assessment and Analysis of IoT Protocol Effectiveness in Dat...

引用

20th Annual International Conference on Distributed computing in Smart Systems and the Internet of Things, DCOSS-IoT 2024

作者： Adesanya, Olanrewaju Mueez Moradpoor, Naghmeh Maglaras, Leandros Lim, Ik Soo Amine Ferrag, Mohamed University of Greenwich School of Computing and Mathematical Sciences London United Kingdom Edinburgh Napier University School of Computing Engineering and the Built Environment Edinburgh United Kingdom Technology Innovation Institute Artificial Intelligence and Digital Science Research Center Masdar Abu Dhabi United Arab Emirates

ISBN: (纸本)9798350369441

The rapid growth of Internet of Things technology has introduced an era of numerous interconnected devices, transforming the communication with the physical world. However, the security and privacy of the data generated and stored on these devices have become significant concerns due to the potential risks associated with unauthorized access and data exfiltration. This paper presents a comprehensive study on the characterization and evaluation of IoT protocols for data exfiltration, with a focus on Message Queuing Telemetry Transport versions 3.1.1 and 5.0, Constrained Application Protocol version 1.0, and Websocket, owing to their widespread adoption and diverse characteristics. These protocols are chosen to meet the constraints of IoT devices and networks, where minimal bandwidth utilization and low power consumption are crucial. We employed a multifaceted methodology, incorporating a comprehensive literature review and the Chiton data encapsulation and exfiltration software tool, to assess the security features, vulnerabilities, and performance metrics of these protocols for data exfiltration. Performance evaluations on the three selected protocols were conducted using a live Client-Server network. A laptop served as the server for exfiltrated data collection, while a Raspberry Pi 3 device acted as the IoT Client Publisher. The evaluation included Wireshark as a network protocol analyser and the enhancement of the Chiton Software Tool with custom codes to encapsulate and exfiltrate data within the IoT protocol messages, empirically measuring the selected protocols' performance, including overhead, latency, and throughput for different data exfiltration scenarios, providing a versatile platform for protocol evaluation. Comparative analysis revealed the strengths and weaknesses of MQTT, CoAP, and Websocket in various data exfiltration scenarios, facilitating the selection of MQTT and Websocket over the CoAP protocol for IoT applications. Lastly, ideas and recommend

关键词： Application programs

来源：评论

学校读者我要写书评

暂无评论

Idecomp: imbalance-aware decomposition for class-decomposed classification using conditional GANs

引用

Discover Artificial Intelligence 2023年第1期3卷 31页

作者： Buczek, Patryk Zidan, Usama Gaber, Mohamed Medhat Abdelsamea, Mohammed M. School of Computing and Digital Technology Birmingham City University Birmingham100190 United Kingdom Faculty of Computer Science and Engineering Galala University Suez435611 Egypt Department of Computer Science Faculty of Computers and Information Assiut University Assiut71515 Egypt

Medical image classification tasks frequently encounter challenges associated with class imbalance, resulting in biased model training and suboptimal classification performance. To address this issue, the combination of class decomposition and transfer learning has proven to be effective in classifying imbalanced medical imaging datasets. Nevertheless, in order to further augment the performance gains achieved through the utilisation of class decomposition within deep learning frameworks, we propose a novel model coined imbalance-Aware Decomposition for Class-Decomposed Classification (iDeComp) model. By incorporating a conditional Generative Adversarial Network (GAN) model, iDeComp is capable of generating additional samples specifically tailored to underrepresented decomposed subclasses. This paper investigates the application of iDeComp using two different medical imaging datasets. iDeComp selects underrepresented samples from the training set of the sublevel classes within each dataset, which are then employed to train separate conditional Deep Convolutional GAN (DCGAN) models and verification models. The conditional DCGAN model is responsible for generating additional samples, while the verification model critically evaluates the appropriateness of the synthesised images. Subsequently, the resulting augmented samples are utilized to train the classification model. To assess the effectiveness of iDeComp, we employ various evaluation metrics including accuracy, precision, recall, and F1 score. The results obtained from our experiments clearly indicate that iDeComp outperforms existing approaches in terms of classifying both imbalanced datasets. © The Author(s) 2023.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Prism: Privacy-Preserving Inter-Site MRI Harmonization via Disentangled Representation Learning 22

Prism: Privacy-Preserving Inter-Site MRI Harmonization via D...

引用

22nd IEEE International Symposium on Biomedical Imaging, ISBI 2025

作者： Galada, Sarang Halder, Tanurima Deo, Kunal Krish, Ram P. Jadhav, Kshitij Indian Institute of Technology Trust Lab Bombay India School of Computing and Data Science Sai University Chennai India Koita Centre for Digital Health Indian Institute of Technology Bombay India

ISBN: (纸本)9798331520526

Multi-site MRI studies often suffer from site-specific variations arising from differences in methodology, hardware, and acquisition protocols, thereby compromising accuracy and reliability in clinical AI/ML tasks. We present PRISM (Privacy-preserving Inter-Site MRI Harmonization), a novel Deep Learning framework for harmonizing structural brain MRI across multiple sites while preserving data privacy. PRISM employs a dual-branch autoencoder with contrastive learning and variational inference to disentangle anatomical features from style and site-specific variations, enabling unpaired image translation without traveling subjects or multiple MRI modalities. Our modular design allows harmonization to any target site and seamless integration of new sites without the need for retraining or fine-tuning. Using multi-site structural MRI data, we demonstrate PRISM's effectiveness in downstream tasks such as brain tissue segmentation and validate its harmonization performance through multiple experiments. Our framework addresses key challenges in medical AI/ML, including data privacy, distribution shifts, model generalizability and interpretability. Code is available at https://***/saranggalada/PRISM. © 2025 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Four Challenges for IML Designers: Lessons of an Interactive Customer Segmentation Prototype in a Global Manufacturing Company

Four Challenges for IML Designers: Lessons of an Interactive...

引用

Extended Abstracts of the 2023 CHI Conference on Human Factors in computing Systems, CHI EA 2023

作者： Raees, Muhammad Khan, Vassilis-Javed Papangelis, Konstantinos Golisano College of Computing and Information Sciences Rochester Institute of Technology RochesterNY United States Digital Transformation Team Sappi Europe Belgium Rochester Institute of Technology RochesterNY United States

ISBN: (纸本)9781450394222

Interactive Machine Learning (IML) apps permeate all aspects of businesses, including sales. Customer segmentation is integral for sales, to identify customer groups to serve them appropriately. However, the novelty of such apps in a sales context raises the question: what challenges designers of such apps will face, in a sales context? To explore this question, we report our reflections on an IML study for customer clustering. We used data from a global manufacturing company to cluster customers using the Recency, Frequency, and Monetary (RFM) method. We applied a machine learning clustering model (K-Means) and discussed with seven seasoned sales managers the interaction with clusters. We report four challenges and foresee that designers of such systems will face, in the context of sales operations. © 2023 Owner/Author.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

Visual Analysis of Multi-source Temporal Data for Online Learning

Visual Analysis of Multi-source Temporal Data for Online Lea...

引用

International Conference on Artificial Intelligence and Communication technology, ICAICT 2023

作者： Li, Xian Gao, Cen Li, Meng Li, Xu Shenyang Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Shandong Artificial Intelligence Association Jinan China Beijing Zhongke Zhihe Digital Technology Co. Ltd Beijing China

ISBN: (纸本)9789819966400

Nowadays with the rapid development of education information, distance education is gradually popularized in People’s Daily life and has attracted more and more attention. As the online learning platform using scale expands increasingly, learners and online learning platform of interaction in the process of multi-source temporal data, through analyzing the multi-source temporal data mining, can know more about students’ online learning situation, found that students learning rule, etc., this approach will assist the teacher to students in the learning process timely intervention, targeted guidance, and thus, the goal of personalized training can be achieved. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Voxelization Algorithm Based on Octree Spatial Averaging 13

Voxelization Algorithm Based on Octree Spatial Averaging

引用

13th International Conference of Information and Communication technology, ICTech 2024

作者： Lv, HongChao Wang, Jun Wang, HongLiang Zhou, XingYu Shenyang University of Chemical Technology Shandong China Shenyang Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences Liaoning Province Human-Computer Interaction System Engineering Research Center Based on Digital Twin Shenyang China

ISBN: (纸本)9798350376258

This paper proposes a high-precision and efficient voxelization algorithm for the development of voxelization in the preprocessing stage of industrial simulation. The main idea is to establish an octree data structure to evenly divide the three-dimensional mesh model space into voxel sets. By using the separation axis method and the improved scan line method, the position relationship between voxels and triangles can be directly determined by skipping the calculation of intersection between voxels and triangles. The innovation of this article lies in the use of the separation axis algorithm and the improved scanning line method for voxelization, and the simplification of the algorithm's operations through the octree data structure, thereby reducing the time and spatial complexity of the algorithm. ©2024 IEEE.

关键词： Consensus algorithm

来源：评论

学校读者我要写书评

暂无评论

POINT TO POINT PROPAGATION OVER PERIODIC ROUGH BOUNDARIES 10

POINT TO POINT PROPAGATION OVER PERIODIC ROUGH BOUNDARIES

引用

10th Convention of the European Acoustics Association, EAA 2023

作者： Attenborough, Keith Mellish, Steve Taherzadeh, Shahram Bashir, Imran Stronach, Alex School of Engineering and Innovation The Open University United Kingdom School of Computing Engineering and Digital Technology Teeside University United Kingdom RPS Group Manchester United Kingdom

ISBN: (纸本)9788888942674

A rough surface formed by regularly spaced acoustically hard parallel strips or grooves gives rise to non-specular diffracted modes and surface waves. Surface waves result in values greater than +6 dB in spectra of the sound field relative to the direct field (excess attenuation). As well as surface wave generation, measurements of excess attenuation over regularly spaced parallel strips show effects of the finite array dimensions. Numerical predictions of pressure contours at the frequency of main surface wave energy show that the surface waves are created by overlapping, interacting, quarter wavelength resonances in the gaps between roughness elements or within grooves. Additional peaks in EA spectra result from interference between surface waves and diffracted components travelling towards the source. The surface waves are reduced if the roughness elements resonate near the surface wave frequencies. Predictions of propagation over periodic rectangular grooves with the same width but depths varied to create a phase change of 2π over each period show non-specular behaviour associated with both surface wave generation and the diversion of energy into diffracted modes. Calculations are made of potential traffic noise insertion loss due to a periodic surface consisting of rectangular grooves with different depths. © 2023 Keith Attenborough et al. This is an open-access article distributed under the terms of the Creative Commons Attribution 3.0 Unported License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

关键词： Surface roughness

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：