检索结果-内蒙古大学图书馆

8th IEEE International Smart Cities Conference, ISC2 2022

作者： Naveed, Muhammad Usman, Syed Muhammad Satti, Muhammad Islam Aleshaiker, Sama Anwar, Aamir Shaheed Zulfikar Ali Bhutto Institute of Science and Technology Department of Computer Science Islamabad Pakistan Ai Air University Faculty of Computing Department of Creative Technologies Islamabad Pakistan Riphah University Faculty of Computer Science and Software Engineering Islamabad Pakistan School of Computing & Engineering University of West London London United Kingdom

ISBN: (数字)9781665485616

ISBN: (纸本)9781665485616

An intrusion Detection System (IDS) is a system that resides inside the network and monitors all incoming and outgoing traffic. It prevents unethical activities from happening over the network. With the use of IoT devices, network traffic is also increased. Intruders and hackers are attracted to this network because of its low processing power and openness. IoT has transformed diagnostic and monitoring systems for patients in the healthcare industry. However, a secure network is needed for these health care devices. This research proposes a hybrid model to secure the IoT network from external intrusions. The proposed method consists of preprocessing data with the help of normalization and feature selection by removing high correlated features with the help of the Pearson correlation coefficient and Support Vector Machine (SVM) for classification. The proposed approach has achieved an accuracy of 99.3%, precision of 99.1% and an F-1 score of 99.25% on the standard dataset. Results have been compared with state-of-the-art, and the proposed method outperforms all performance measures. © 2022 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Approximated Coded Computing: Towards Fast, Private and Secure Distributed Machine Learning

引用

IEEE Transactions on Emerging Topics in Computing 2025年

作者： Qiu, Houming Zhu, Kun Luong, Nguyen Cong Niyato, Dusit Jiangxi University of Finance and Economics School of Software and IoT Engineering Jiangxi 330032 China Nanjing University of Aeronautics and Astronautics College of Computer Science and Technology Nanjing210016 China Phenikaa University Faculty of Computer Science Hanoi12116 Viet Nam Nanyang Technological University School of Computer Science and Engineering 639798 Singapore

In a large-scale distributed machine learning system, coded computing has attracted wide-spread attention since it can effectively alleviate the impact of stragglers. However, several emerging problems greatly limit the performance of coded distributed systems. Firstly, an existence of colluding workers who collude results with each other leads to serious privacy leakage issues. Secondly, there are few existing works considering security issues in data transmission of distributed computing systems/or coded distributed machine learning systems. Thirdly, the number of required results for which need to wait increases with the degree of decoding functions. In this paper, we design a secure and private approximated coded distributed computing (SPACDC) scheme that deals with the above-mentioned problems simultaneously. Our SPACDC scheme guarantees data security during the transmission process using a new encryption algorithm based on elliptic curve cryptography. Especially, the SPACDC scheme does not impose strict constraints on the minimum number of results required to be waited for. An extensive performance analysis is conducted to demonstrate the effectiveness of our SPACDC scheme. Furthermore, we present a secure and private distributed learning algorithm based on the SPACDC scheme, which can provide information-theoretic privacy protection for training data. Our experiments show that the SPACDC-based deep learning algorithm achieves a significant speedup over the baseline approaches. © 2013 IEEE.

关键词： Parallel processing systems

来源：评论

学校读者我要写书评

暂无评论

Scaling down to scale up: benchmarking single-machine graph processing frameworks in a hardware-constrained environment

引用

Computing 2025年第7期107卷 1-25页

作者： Loukil, Mariem Sfaxi, Lilia Robbana, Riadh Software Engineering Department Mediterranean Institute of Technology South Mediterranean University Tunis Tunisia LIPSIC Laboratory Faculty of Science of Tunis (FST) University of Tunis El Manar Tunis Tunisia Department of Computer Science Engineering and Mathematics INSAT University of Carthage Tunis Tunisia

Graph processing frameworks are pivotal in managing the increasing complexity and size of datasets in numerous computational fields. However, the performance of these frameworks can vary significantly depending on their design and the specific conditions under which they are tested. This paper presents a comprehensive benchmarking study of six single-machine graph processing frameworks: GraphChi, Ligra, X-stream, MMap, GridGraph, and GPOP across a variety of datasets and graph processing algorithms, and on a consumer-level machine. In the evaluation of the frameworks, several performance metrics were used, which are execution time, CPU, and memory usage, as well as qualitative metrics, such as ease of use and comprehensive documentation which contribute to determining each framework’s practical effectiveness. Our findings indicate that no single framework excels in all aspects; instead, each framework demonstrates strengths and weaknesses that are context-dependent. By evaluating frameworks in a unified environment rather than their original setups, the study explores which frameworks perform more effectively under comparable conditions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Ha-Bsn: Hardware Acceleration of Bio-Sfa and Bio-Nica, Biological Neural Networks, on Fpga

SSRN

引用

SSRN 2023年

作者： Ebrahimi, Amirhosein Vafaeisefat, Hoda Asghari, Mohsen Rahmati, Dara School of Computer Science Institute for Research in Fundamental Sciences Farmanieh Campus Tehran Iran Faculty of Computer Science and Software Engineering Concordia University Montreal Canada Faculty of Computer Science and engineering Shahid Beheshti University Tehran Iran

Nowadays, with the ever-growing advancement in neural networks, many of today's needs have been resolved. However, the processing speed of neural network applications might be challenging and take too long to execute. This is especially true for real-time and embedded systems, which must guarantee a response within limited time constraints. It is relatively straightforward to observe the blurred line between the real-time system and biologically inspired applications. For instance, the bio-SFA algorithm learns slow-varying features by inspiration from the human brain, and the bio-NICA algorithm, a biologically plausible neural network for non-negative independent component analysis, separates mixtures of unknown signals into their distinct sources by understanding how the brain solves blind source separation. These algorithms stem from the human brain's functionality;therefore, the processing speed should be reasonable. In this work, we will leverage the high capability of hardware performance by using field-programmable gate arrays (FPGAs) to accelerate both the bio-SFA and bio-NICA algorithms. We have compared our approach with a software implementation running on two popular embedded boards' processors, ARM Cortex-A53 SoC and ARM Cortex-A72. We have run the standard algorithm on both boards and calculated the number of cycles it takes. Generally, the designed accelerator performs around 38x speedup for Bio-SFA and 4x speedup for Bio-NICA over Cortex-A53. Similarly, compared to Cortex-A72, it achieves 9x speedup for Bio-SFA and 2x for Bio-NICA. Moreover, the accelerator consumes only 0.34 Watts for Bio-SFA and 0.85 Watts for Bio-NICA of power. © 2023, The Authors. All rights reserved.

关键词： Field programmable gate arrays (FPGA)

来源：评论

学校读者我要写书评

暂无评论

Multimodal Data Fusion Based on Generative Adversarial Network in University Teaching Evaluation

Journal of Network Intelligence

引用

Journal of Network Intelligence 2025年第2期10卷 845-858页

作者： Liu, Min Teng, Hua Zhang, Hong Li, Hao School of Computer Science and Software Engineering Southwest Petroleum University Nanchong637001 China Department of Computer China West Normal University Nanchong637009 China Faculty of Computer and Information Science SouthWest University Chongqing400700 China Krirk University Bangkok10220 Thailand

With the advancement of educational evaluation reform and the popularization of higher education, university teaching quality evaluation has been a research hotspot in the field of educational evaluation. In response to the issue of multimodal heterogene-ity gap in current university education evaluation data, which makes it tough to integrate evaluation data, this article suggests a Multimodal Data Fusion (MDF) method for university teaching evaluation relied on Generative Adversarial Network (GAN). Firstly, the MDF model is constructed from two aspects: establishing similarity network and designing regularization terms. By designing sparse regularization terms, the feature selection of multimodal samples is carried out to address the issue of large deviation of fusion data. Secondly, BERT pre-training model is adopted to extract the modal embedding features of teaching evaluation text, and Bi-LSTM is adopted to extract the audio and visual modal embedding features of teaching evaluation. Then, on the ground of the constructed MDF model, combined with the GAN and autoencoder, a multi-modal adversarial autoencoder learning model is established to reduce the heterogeneous gap between modes and form a unified representation. At last, the self-attention pretest network is established to achieve the automatic classification of multi-modal university teaching evaluation data. The experimental outcome implies that the accuracy, F1 value and determination coefficient R2 of the suggested method are 92.18%, 93.72% and 90.5%, respectively, which are superior to the comparison method, showing good classification performance. © 2025, J. Network Intell. All rights reserved.

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

DM-Net for Colorectal Polyp Detection Using Dual Feature and Multi-Layer Aggregation

DM-Net for Colorectal Polyp Detection Using Dual Feature and...

引用

International Conference on Advanced Cloud and Big Data (CBD)

作者： Jingjing Wan Ling Wang Wenjie Zhu Bolun Chen Department of Gastroenterology The Second People's Hospital of Huai'an Huaian China Faculty of Computer and Software Engineering Huaiyin Institute of Technology Huaian China

ISBN: (数字)9798331511074

ISBN: (纸本)9798331511081

Early detection of colorectal polyps is crucial for preventing colorectal cancer. Although endoscopy is the current standard diagnostic method, it still faces challenges in terms of accuracy, efficiency, and patient comfort. To address these issues, this paper proposes a colorectal polyp detection model named DM-Net. This model utilizes the Dual Feature Integration Block (DFIB) to integrate channel and spatial features, enhancing feature extraction efficiency. Additionally, the model incorporates the Multi-Layer Path Aggregation Network (MLPAN) to handle the multi-scale variations of polyps. Experimental results demon-strate that DM-Net significantly outperforms existing methods in terms of accuracy and efficiency, offering high clinical applica-bility.

关键词： YOLO Accuracy Endoscopes Colorectal cancer Big Data Feature extraction Real-time systems Standards Faces

来源：评论

学校读者我要写书评

暂无评论

Vehicle type recognition based on audio data 58

Vehicle type recognition based on audio data

引用

58th Hawaii International Conference on System Sciences, HICSS 2025

作者： Kobiela, Dariusz Hajdasz, Michal Erezman, Mateusz Nurzyńska, Karolina Zaporowski, Szymon Kurowski, Adam Weichbroth, Pawel Department of Software Engineering Faculty of Electronics Telecommunication and Informatics Gdańsk University of Technology Gabriela Narutowicza 11/12 Gdańsk80-233 Poland Department of Multimedia Systems Faculty of Electronics Telecommunication and Informatics Gdańsk University of Technology Gabriela Narutowicza 11/12 Gdańsk80-233 Poland Department of Algorithmics and Software Faculty of Automatic Control Electronics and Computer Science Silesian University of Technology Akademicka 16 Gliwice44-100 Poland

ISBN: (纸本)9780998133188

Identifying different vehicle types can help manage traffic more efficiently, reduce congestion, and improve public safety. This study aims to create a classification model that can recognize vehicle types based on the sound of passing vehicles. To achieve this, a database of raw audio files containing 1763 samples from two sources was assembled. The time-domain signals were converted to a time-frequency representation using the short-time Fourier transform to generate Mel Spectrograms. Mel-frequency Cepstral Coefficients (MFCCs) were also generated using the discrete cosine transform. In our experiments we compared these approaches. Since the data was imbalanced we applied online augmentation. Based on the literature review, we chose a Convolutional Neural Network (CNN) classifier because it is particularly well suited for analyzing large datasets due to its automatic feature extraction, parameter sharing and sparsity. The results showed that Mel Spectrograms were more effective for audio data preprocessing in this particular use case, achieving the highest accuracy of 0.875 and the highest f1-score of 0.877 compared to MFCCs. © 2025 IEEE computer Society. All rights reserved.

关键词： Image coding

来源：评论

学校读者我要写书评

暂无评论

Towards a Deep Learning Pain-Level Detection Deployment at UAE for Patient-Centric-Pain Management and Diagnosis Support: Framework and Performance Evaluation 14

Towards a Deep Learning Pain-Level Detection Deployment at U...

引用

14th International Conference on Ambient Systems, Networks and Technologies Networks, ANT 2023 and The 6th International Conference on Emerging Data and Industry 4.0, EDI40 2023

作者： Ismail, Leila Waseem, Muhammad Danish Lab School of Computing and Information Systems Faculty of Engineering and Information Technology The University of Melbourne Australia Research Laboratory Department of Computer Science and Software Engineering College of Information Technology United Arab Emirates University United Arab Emirates National Water and Energy Center United Arab Emirates University United Arab Emirates

The outbreak of the COVID-19 pandemic revealed the criticality of timely intervention in a situation exacerbated by a shortage in medical staff and equipment. Pain-level screening is the initial step toward identifying the severity of patient conditions. Automatic recognition of state and feelings help in identifying patient symptoms to take immediate adequate action and providing a patient-centric medical plan tailored to a patient's state. In this paper, we propose a framework for pain-level detection for deployment in the United Arab Emirates and assess its performance using the most used approaches in the literature. Our results show that a deployment of a pain-level deep learning detection framework is promising in identifying the pain level accurately. © 2023 Elsevier B.V.. All rights reserved.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Design and Simulation of a Network Infrastructure for a Multi-Branch Organization Using Cisco Packet Tracer 25

Design and Simulation of a Network Infrastructure for a Mult...

引用

25th International Arab Conference on Information Technology, ACIT 2024

作者： Aljamal, Osama S. Aljamal, Mahmoud Alsarhan, Ayoub Aljaidi, Mohammad Okour, Saif Al-Aiash, Issa Al-Qerem, Ahmad Daoud, Essam Al Elrashidi, Ali Al Hussein Technical University Department of Computer Science Amman Jordan Irbid National University Faculty of Science and Information Technology Department of Cybersecurity Irbid21110 Jordan The Hashemite University Department of Information Technology Zarqa Jordan Zarqa University Department of Computer Science Zarqa Jordan Irbid National University Department of Software Engineering Irbid Jordan Zarqa University Department of Cybersecurity Zarqa Jordan University of Business and Technology Department of Electrical Engineering Jeddah21432 Saudi Arabia

ISBN: (纸本)9798331540012

Designing and simulating a network infrastructure for multi-branch organizations is essential for ensuring seamless connectivity and efficient operations. This paper addresses the challenges faced by organizations in maintaining consistent and reliable network connectivity across multiple locations, including managing network traffic, ensuring security, and optimizing resource allocation while keeping costs under control. The study presents a comprehensive methodology involving the conceptualization of network ideas, designing the network architecture, adding necessary devices and tools, configuring these devices according to the network topology, and troubleshooting to ensure optimal performance. Key elements such as VLANs, routers, switches, and routing protocols like RIP, OSPF, and EIGRP are incorporated, with the entire design and simulation conducted using Cisco Packet Tracer. The findings demonstrate that full connectivity between headquarters and branch sites can be achieved within a budget of $40,000. This paper provides a practical guide for implementing similar network projects, emphasizing the importance of detailed configurations and troubleshooting steps, and recommends adopting this methodology to enhance network infrastructure efficiently and cost-effectively. © 2024 IEEE.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

Electrocoagulation-based AZO DYE (P4R) Removal Rate Prediction Model using Deep Learning

Electrocoagulation-based AZO DYE (P4R) Removal Rate Predicti...

引用

2023 International Symposium on Green Technologies and Applications, ISGTA 2023

作者： Akoulih, Meryem Tigani, Smail Byoud, Fouzia Rharib, Meryem El Saadane, Rachid Pierre, Samuel Chehri, Abdellah Ghachtouli, Sanae El IME Lab Faculty of Science Hassan 2 University Casablanca20250 Morocco Research and Development Unit Accsellium LLC Fez Morocco Electrical Engineering Department SIRC-LaGeS Hassania School of Public Labors Casablanca20250 Morocco Department of Computer and Software Engineering Polytechnique Montréal MontréalQC Canada Department of Mathematics and Computer Science Royal Military College of Canada KingstonON11 K7K 7B4 Canada

This article presents a study on the effectiveness of electrocoagulation (EC) for the removal of azo dyes from wastewater. The analysis was performed using a combination of statistical methods, including density estimation, correlation analysis, and deep learning for electrocoagulation performance prediction. The results showed that electrocoagulation was able to effectively remove azo dyes from the wastewater, considering the energy consumption and the mass of flocs being important factors in the process. Deep Learning (DL) is used to build our predictive model using the datasets collected during the experimentation stage. Overall, the findings suggest that electrocoagulation is a promising technique for the treatment of wastewater containing azo dyes, and that the use of statistical and machine learning methods can aid in the optimization of the process. © 2024 The Authors. Published by ELSEVIER B.V.

关键词： Azo dyes

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：