检索结果-内蒙古大学图书馆

2nd International Conference on Artificial Intelligence, Blockchain, and Internet of Things, AIBThings 2024

作者： Gao, Xian He, Peixiong Zhou, Yi Qin, Xiao Columbus State University Tsys School of Computer Science ColumbusGA United States Auburn University Department of Computer Science and Software Engineering AuburnAL United States

ISBN: (纸本)9798331529529

Deep learning models are widely used in healthcare. Given the large amount of data and the need for real-time processing, running these models on IoT devices is a viable solution. This study examines the impact of deep learning models on the limited resources of IoT devices. We selected three models introduced at the 2023 CVPR conference and executed them on a Raspberry Pi with different dataset sizes to measure CPU utilization, memory utilization, and energy consumption. The results show that for the pruned Yolov5 model, CPU utilization has the strongest positive correlation with energy consumption (5.43 × 10=4 Joules), while memory utilization shows the most significant negative correlation (-4.27 × 10=4 Joules). In the FasterNet-T0 model, dataset size has the strongest positive correlation with energy consumption (2.75 × 10=5 Joules). For the Lite-Mono model, dataset size shows the most significant positive correlation (1.84 × 10=4 Joules), while memory utilization has the strongest negative correlation with energy consumption (- 2.52 × 10=4 Joules). These results highlight the key factors correlated with energy consumption across different models, providing valuable insights for deploying deep learning models on IoT devices. © 2024 IEEE.

关键词： Deep Learning Energy Consumption Hardware Utilization Healthcare IoT

来源：评论

学校读者我要写书评

暂无评论

Empirical Study on Mispronunciation Detection for Tajweed Rules during Quran Recitation 6

Empirical Study on Mispronunciation Detection for Tajweed Ru...

引用

6th International Conference on Computing and Informatics, ICCI 2024

作者： Alsahafí, Yousef S. Asad, Muhammad Department of Information technology Computing and Information technology Khulis College University of Jeddah Jeddah Saudi Arabia Department of Computer and Software Engineering College of Electrical and Mechanical Engineering National University of Science and Technology Islamabad Pakistan

ISBN: (纸本)9798350373875

This paper presents an extensive empirical study aiming to identify the optimal combination of feature extraction techniques and machine learning algorithms, including deep learning, for automated mispronunciation detection during Quran recitation. Three feature extraction methods-Mel-Frequency Cepstral Coefficients (MFCC), Spectrogram, and Kaldi pitch - are systematically evaluated in conjunction with a diverse set of classifiers, including Gradient Boosting (GB), Support Vector Machines (SVM), Logistic Regression (LR), Random Forest (RF), Artificial Neural Network (ANN), Convolutional Neural Networks (CNN), and Long Short-Term Memory (LSTM) networks. The study leverages the QDAT dataset, comprising 1500 audio samples from 150 readers, with metadata specifying age, gender, and three distinct rules for mispronunciation detection. Experimental results demonstrate that the integration of MFCC with deep learning classifiers consistently achieves the highest performance across multiple evaluation metrics. Model robustness is validated using receiver operator characteristic curves (ROC) and accuracy metrics. © 2024 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Tidal-Tree-Mem: Toward Read-Intensive Key-Value Stores With Tidal Structure Based on LSM-Tree

Tidal-Tree-Mem: Toward Read-Intensive Key-Value Stores With ...

引用

作者： Ma, Chenlin Yang, Hao Wu, Shangyu Wang, Yi Mao, Rui Shenzhen University College of Computer Science and Software Engineering Shenzhen518060 China City University of Hong Kong Department of Computer Science Hong Kong Shenzhen University College of Computer Science and Software Engineering The Shenzhen Institute of Computing Sciences Shenzhen518060 China

The log-structured merge-tree (LSM-tree)-based key-value store has been widely adopted by many large-scale data storage applications for its excellent write performance. However, such write performance gains mainly come from scarifying read performance due to the leveled and log-structured intrinsic characteristics of the LSM-tree. Therefore, the critical challenge of the existing LSM-tree is how to improve the read efficiency by reducing read amplification. This article for the first time proposes Tidal-tree-Mem, a novel data structure where data flow inside the LSM-tree-like Tidal waves. First, a floating strategy is proposed to allow frequently accessed files at the bottom of the LSM-tree to move to higher positions, reducing read amplification. Second, a stretching strategy is proposed to vary the shape of the LSM-tree to adapt to workloads with different characteristics. To evaluate the performance of Tidal-tree-Mem, we conduct a series of experiments using standard benchmarks from YCSB. The experimental results show that Tidal-tree-Mem can effectively reduce read amplification and the overall latency by over 71.94% and 47.34%, respectively, compared with representative schemes. © 1982-2012 IEEE.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Machine learning and deep learning algorithms in detecting COVID-19 utilizing medical images: a comprehensive review

引用

Iran Journal of computer Science 2024年第3期7卷 699-721页

作者： Nurjahan Mahbub-Or-Rashid, Md. Satu, Md. Shahriare Tammim, Sanjana Ruhani Sunny, Farhana Akter Moni, Mohammad Ali Department of IoT and Robotics Engineering Bangabandhu Sheikh Mujibur Rahman Digital University Kaliakair Bangladesh Department of Computer Science and Engineering Bangladesh University of Business and Technology Mirpur Bangladesh Department of Management Information Systems Noakhali Science and Technology University Noakhali Bangladesh Department of Computer Science and Software Engineering Auburn University Auburn AL United States Department of Computer Science and Engineering Green University of Bangladesh Dhaka Bangladesh Faculty of Health and Behavioural Sciences School of Health and Rehabilitation Sciences The University of Queensland St Lucia Australia

The public’s health is seriously at risk from the coronavirus pandemic. Millions of people have already died as a result of this devastating illness, which affects countless people daily worldwide. Unfortunately, no specific therapeutic drugs or vaccines are available to cure patients completely. Therefore, early identification of infected individuals and their isolation can help reduce community transmission of COVID-19. Despite being commonly used, the reverse transcription polymerase chain reaction (RT-PCR) test is costly, time-consuming, and requires suitable kits, which are not always readily available. An alternative solution for the traditional RT-PCR test is machine learning and deep learning-based COVID-19 detection that utilizes clinical features of chest X-rays and computed tomography (CT) images. In this study, we conducted a detailed review of more than 100 recently published works to detect COVID-19-infected patients. Thus, different data preprocessing, data augmentation, image enhancement, feature extraction, machine learning, deep learning, Explainable Artificial Intelligence (AI) methods, etc. were explored to understand how these techniques were used to process images for identifying COVID-19. Additionally, we identified the current challenges in this field and suggested further research directions. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： Chest X-ray Computed tomography COVID-19 Deep learning Machine learning

来源：评论

学校读者我要写书评

暂无评论

SEM-F1: an Automatic Way for Semantic Evaluation of Multi-Narrative Overlap Summaries at Scale

SEM-F1: an Automatic Way for Semantic Evaluation of Multi-Na...

引用

2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022

作者： Bansal, Naman Akter, Mousumi Karmaker, Shubhra Kanti Lab Department of Computer Science and Software Engineering College of Engineering Auburn University United States

Recent work has introduced an important yet relatively under-explored NLP task called Semantic Overlap Summarization (SOS) that entails generating a summary from multiple alternative narratives which conveys the common information provided by those narratives. Previous work also published a benchmark dataset for this task by collecting 2, 925 alternative narrative pairs from the web and manually annotating 411 different reference summaries by engaging human annotators. In this paper, we exclusively focus on the automated evaluation of the SOS task using the benchmark dataset. More specifically, we first use the popular ROUGE metric from text-summarization literature and conduct a systematic study to evaluate the SOS task. Our experiments discover that ROUGE is not suitable for this novel task and therefore, we propose a new sentence-level precision-recall style automated evaluation metric, called SEM-F1 (Semantic F1). It is inspired by the benefits of the sentence-wise annotation technique using overlap labels reported by the previous work. Our experiments show that the proposed SEM-F1 metric yields a higher correlation with human judgment and higher inter-rater agreement compared to the ROUGE metric. © 2022 Association for Computational Linguistics.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

RoSe: Rotation-Invariant Sequence-Aware Consensus for Robust Correspondence Pruning 24

RoSe: Rotation-Invariant Sequence-Aware Consensus for Robust...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Liu, Yizhang Zhou, Weiwei Li, Yanping Zhao, Shengjie School of Software Engineering Tongji University Shanghai China College of Computer and Data Science Fuzhou University Fuzhou China Department of Computer Science and Technology Tongji University Shanghai China Engineering Research Center of Key Software Technologies for Smart City Perception and Planning Ministry of Education Shanghai China

ISBN: (纸本)9798400706868

Correspondence pruning has recently drawn considerable attention as a crucial step in image matching. Existing methods typically achieve this by constructing neighborhoods for each feature point and imposing neighborhood consistency. However, the nearest-neighbor matching strategy often results in numerous many-to-one correspondences, thereby reducing the reliability of neighborhood information. Furthermore, the smoothness constraint fails in cases of large-scale rotations, leading to misjudgments. To address the above issues, this paper proposes a novel robust correspondence pruning method termed RoSe, which is based on rotation-invariant sequence-aware consensus. We formulate the correspondence pruning problem as a mathematical optimization problem and derive a closed-form solution. Specifically, we devise a rectified local neighborhood construction strategy that effectively enlarges the distribution between inliers and outliers. Meanwhile, to accommodate large-scale rotation, we propose a relative sequence-aware consistency as an alternative to existing smoothness constraints, which can better characterize the topological structure of inliers. Experimental results on image matching and registration tasks demonstrate the effectiveness of our method. Robustness analysis involving diverse feature descriptors and varying rotation degrees further showcases the efficacy of our method. © 2024 ACM.

关键词： correspondence pruning

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of a Web-Based Application for Managing Agricultural Health Products 4

Design and Implementation of a Web-Based Application for Man...

引用

4th International Conference on Emerging Trends in Networks and computer Communications, ETNCC 2024

作者： Oluwagbemi, Olugbenga O. Onyeka, Emebo Ishieka, Ikashi S. Wieclaw, Anna Azeta, Ambrose A. Middlesex University Department of Computer Science London United Kingdom Virginia Tech University Department of Computer Science Blacksburg United States Namibia University of Science and Technology Department of Software Engineering Windhoek Namibia

ISBN: (纸本)9798350353266

Caring for the health of food crops and plants can help boost food production and eradicate hunger according to the second United Nations (UN) Sustainable Development Goal (SDG). The procurement of agricultural health products such as fertilizers, fungicides, pesticides, and herbicides are a major problem for an average Nigerian farmer. This results in low crop yield and negatively impacts on food production which eventually causes hunger in the land. Existing methods of procuring these health products have majorly been through offline platforms such as agricultural stores and other relevant stores. This has its disadvantages such as inaccessible roads to stores where such products can be obtained, varying prices, health products out of stock, ignorance in the application of such products. These barriers deter farmers from procuring these health products. In this paper, a survey was conducted on the needs and problems of farmers. The results of the survey informed the design and implementation of an agricultural health Informatics web application for health product management for food crops. The application was designed using unified modelling language class diagram and implemented using Python. SQLite3 serves as the backend database. The agricultural informatics solution will help farmers in Nigeria to easily procure health products for food crops and get the products delivered without stress and worry when fully deployed. This will boost food production, thus eradicating hunger;it will also help in exporting food crops to other countries. © 2024 IEEE.

关键词： Agriculture AI Application Chatbot Farmers Health Informatics

来源：评论

学校读者我要写书评

暂无评论

Semantic Overlap Summarization among Multiple Alternative Narratives: an Exploratory Study 29

Semantic Overlap Summarization among Multiple Alternative Na...

引用

29th International Conference on Computational Linguistics, COLING 2022

作者： Bansal, Naman Akter, Mousumi Karmaker, Shubhra Kanti Lab Department of Computer Science and Software Engineering College of Engineering Auburn University United States

In this paper, we introduce an important yet relatively unexplored NLP task called Semantic Overlap Summarization (SOS), which entails generating a single summary from multiple alternative narratives which can convey the common information provided by those narratives. As no benchmark dataset is readily available for this task, we created one by collecting 2, 925 alternative narrative pairs from the web and then, went through the tedious process of manually creating 411 different reference summaries by engaging human annotators. As a way to evaluate this novel task, we first conducted a systematic study by borrowing the popular ROUGE metric from text-summarization literature and discovered that ROUGE is not suitable for our task. Subsequently, we conducted further human annotations to create 200 document-level and 1, 518 sentence-level ground-truth overlap labels. Our experiments show that the sentence-wise annotation technique with three overlap labels, i.e., {Absent (A), Partially-Present (PP), and Present (P)}, yields a higher correlation with human judgment and higher inter-rater agreement compared to the ROUGE metric. © 2022 Proceedings - International Conference on Computational Linguistics, COLING. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Improving multi-class opinion classification in social networks by combining Fuzzy SVM and CNN 28th

Improving multi-class opinion classification in social netwo...

引用

28th International Conference on Knowledge Based and Intelligent information and engineering Systems, KES 2024

作者： Ghezaiel Hammouda, Nadia Toujani, Radhia College of Computer Science and Software Engineering University of Hail Hail Saudi Arabia ESTMOD Department Higher Institute of management University of Tunis Tunisia

Machine learning techniques, particularly fuzzy Support Vector Machines (fuzzy SVM), have demonstrated effectiveness in sentiment classification within social networks. However, the evolving complexity of social networks content and the necessity to handle diverse opinions prompt ongoing advancements in sentiment analysis methodologies. In this study, we propose an innovative approach by integrating a Convolutional Neural Network (CNN) model with fuzzy SVM. Our key contribution lies in the fusion of these two methodologies, capitalizing on the strengths of fuzzy SVM for opinion mining and CNN for extracting intricate features. Additionally, we extend this method to enable multi-class opinion classification, allowing for a finer understanding of nuances in expressed sentiments. Through evaluation on benchmark datasets, we highlight a notable improvement in performance compared to baseline methods. The results underscore the enhanced generalization capabilities and increased accuracy in opinion classification offered by our hybrid model, rendering it a promising asset for decision-making applications based on multi-opinion analysis. © 2024 The Authors.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Analysis of Techniques for Detection and Removal of Zero-Day Attacks (ZDA) 2nd

Analysis of Techniques for Detection and Removal of Zero-Day...

引用

2nd International Conference on Ubiquitous Security, UbiSec 2022

作者： Hamid, Khalid Iqbal, Muhammad Waseem Aqeel, Muhammad Liu, Xiangyong Arif, Muhammad Department of Software Engineering The Superior University Lahore54000 Pakistan Department of Computer Science The Superior University Lahore54000 Pakistan School of Computer Science and Cyber Engineering Guangzhou University Guangzhou510006 China

ISBN: (纸本)9789819902712

Zero-day attacks (ZDAs) are previously unknown flaws and errors in operating systems, networks, and general-purpose software. ZDAs are the cause to open security breach holes for external users or hackers for illegal operations before patches. ZDAs are different from viruses, worms and Trojans. They are very difficult to detect and remove because they are unknown to users and even programmers. Conventional defense systems are useless against such types of attacks. This paper investigates the zero-day attacks, their vulnerabilities, the intensity of these attacks and the reasons in a real-time environment. Different techniques are compared to investigate ZDAs. The hybrid technique has been used to check the behavior of data traffic coming from outside the world in the virtual environment for zero-day attacks. Static check tools (MD5 Checksum, AV-Suite, and SOPHOS) and behavioral check tools (SANDBOX) have been used for the verification and validation of results. The second comparatively best technique is Machine Learning-Based Technique which showed the best results. The results show how to choose the best solution against zero-day attacks in the real-time environment of the software. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Zero-day attack

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：