检索结果-内蒙古大学图书馆

26th International Conference on computer and Information technology, ICCIT 2023

作者： Hamza, Golam Ibna Rahman, Mohammad Mushfiqur Roshni, Sanjana Akter Barua, Aishik Reshad, Muhtasim Ferdous Sakib, Mr. Nazmus Ahsanullah University of Science & Technology Department of Computer Science & Engineering Dhaka Bangladesh

ISBN: (纸本)9798350359015

This study is divided into two crucial sections. We first gathered Bangla song names and lyrics using web crawling and a dataset that was only slightly annotated. A comprehensive dataset was then thoroughly annotated across five different genres. Utilizing transformer models to classify the genre of Bangla songs was our main goal. Noteworthy accomplishments are the 94% accuracy and F1-score of csebuetnlp/banglabert. Additionally, we created a text generation system using ritog/bangla-gpt2 and flax-community/gpt2-bengali. This method allows for the development of scenario-based music material, expanding the creative possibilities for the entertainment business, by choosing the genre with the highest F1 score from the classification findings. © 2023 IEEE.

关键词： Bangla lyrics classification generation transformer models

来源：评论

学校读者我要写书评

暂无评论

Skin Cancer Classification using Deep Learning Algorithms

Skin Cancer Classification using Deep Learning Algorithms

引用

2023 International Conference on Data science, Agents and Artificial Intelligence, ICDSAAI 2023

作者： Senthil Murugan, K.R. Jayamaharaja, A.S.V. Vishal, R. Deepalakshmi, R. Balamurugan, P. Velammal College of Engineering and Technology Department of Computer Science and Engineering Madurai India

ISBN: (纸本)9798350348910

Skin cancer detection, acritical facet of dermatology, has witnessed significant advancements through deep learning methodologies. Leveraging the ISIC dataset, this project introduces a potent approach to multi-class skin lesion classification, emphasizing skin cancer identification, which achieves an impressive accuracy rate of 90%. The methodology meticulously selects, preprocesses, and augments the dataset to ensure diversity and data quality. Centered on Convolutional Neural Networks (CNNs), with considerations for transfer learning and strategic dropout integration, the model exhibits robustness. Rigorous evaluations, encompassing diverse performance metrics, provide comprehensive insights. Additionally, potential deployment avenues, such as API development and cloud-based solutions, are explored. This research underscores the substantial accuracy gains attainable with the ISIC dataset and the transformative potential of deep learning in advancing skin cancer diagnosis, offering hope for enhanced patient care and outcomes. © 2023 IEEE.

关键词： Dermatology

来源：评论

学校读者我要写书评

暂无评论

Faster R-CNN for Detection and Classification of Banana Leaf Diseases 1

Faster R-CNN for Detection and Classification of Banana Leaf...

引用

1st International Conference on Advances in Electrical, Electronics and Computational Intelligence, ICAEECI 2023

作者： Bharathi Raja, N. Selvi Rajendran, P. Hindustan Institute of Technology and Science Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350342796

Plant diseases are important factors in reducing the appearance of agricultural commodities. Consequently, it is essential to recognize and diagnose these disorders as early as possible. To this end, the researchers suggest a Deep Learning (DL) technique to categorize diseases of the banana leaf that have been fully automated. In this paper, a transfer learning strategy reorientation of a Faster Region-based Convolutional Neural Network (Faster R-CNN) is proposed to develop an uncertainty detection. Using images acquired from different parts of the Banana plant, six distinct designs were built from 18 different classes. Early results show that the proposed method works even in challenging situations such as poor lighting, a complex environment, and variable resolution, shape, position, and orientation of real-world images. The effectiveness of multiple automated uncertainty disease detection systems is also measured through improvement and verification measures. The proposed FR-CNN model uses a pre-formed disease detection algorithm to create a network that could produce correct estimates through Deep Transfer Learning (DTL). The developed model performed better in terms of accuracy and needed less training time when compared to other deep-learning models. © 2023 IEEE.

关键词： Accuracy Agriculture Deep Transfer Learning (DTL) Faster Region-based Convolutional Neural Network (Faster R-CNN) Plant Disease Detection

来源：评论

学校读者我要写书评

暂无评论

Damaged Image Repair using Masks with computer Vision Inpaint Method 2

Damaged Image Repair using Masks with Computer Vision Inpain...

引用

2nd International Conference on Applied Artificial Intelligence and Computing, ICAAIC 2023

作者： Ramakrishna, Doddi Purna Gana Emmanuel, G. S. Michael Selvan, Mercy Paul Sathyabama Institute of Science and Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9781665456302

Image inpainting is the technique used to automatically fix damaged areas using data from sections that have been saved. With the development of deep learning in recent years, image drawing performance has substantially increased. This research study reviews the main methods used for automating image inpainting. This research study provides a brief overview of traditional techniques while concentrating on deep learning-based inpainting techniques, covering model categorization, strengths and drawbacks, scope of application, and performance comparison. Finally, the challenges and trends surrounding automated image inpainting are examined and foreseen. A tool called image inpainting uses the data from the remaining components to repair damaged areas. With the advancement of society, image inpainting has become a vital research area in the field of computer vision. It is extensively used in culture, daily life, and security, including object removal and the preservation of digital cultural assets. Conventional methods build geometric models based on geometric consistency and image content similarity, or they use texture generation to patch up small sections of damaged images. It partially solves the problem of loose coupling between high-level semantics and low-level image properties, enabling deep learning to gradually overtake traditional methods in computer vision. © 2023 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Exploratory Analysis of Methods, Techniques, and Metrics to Handle Class Imbalance Problem 2

Exploratory Analysis of Methods, Techniques, and Metrics to ...

引用

2nd International Conference on Machine Learning and Data engineering, ICMLDE 2023

作者： Sneha, H.R. Annappa, B. Department of Information Science & Engineering Nitte Meenakshi Institute of Technology Bengaluru560064 India Department of Computer Science & Engineering National Institute of Technology Karnataka Surathkal575025 India

Class imbalance a common challenge in machine learning, often results in skewed predictions and misrepresentative model assessments, highlighting the need for effective countermeasures. Our detailed survey dives into three primary techniques for addressing this issue: data-level interventions, algorithmic modifications, and integrated hybrid solutions. We thoroughly dissect each approach, delineating its merits, drawbacks, and ideal use cases. Data-level methods aim to restructure the dataset for class balance, while algorithmic techniques recalibrate the learning process to better detect the minority class. The hybrid strategies merge the benefits of both for a holistic remedy. The study further emphasizes the importance of precise evaluation metrics, elaborating on both conventional metrics and those tailored for imbalanced scenarios. Our objective is to arm professionals with a deep insight into tackling class imbalance, especially within the big data framework. The insights shared aspire to inspire the creation of resilient, equitable machine learning models adapt at navigating imbalanced data, ensuring enhanced prediction fidelity and consistency. © 2024 Elsevier B.V.. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

GRU-Based Winner Subcarrier Detection in Frequency Domain Contention 24

GRU-Based Winner Subcarrier Detection in Frequency Domain Co...

引用

7th International Conference on Information science and Systems, ICISS 2024

作者： Yao, Shumin Zhao, Qinglin Xu, Zezhou Feng, Li Li, Guanghui Tian, Liwei Sun, Yi School of Computer Science and Engineering Macau University of Science and Technology China Department of Broadband Communication Pengcheng Laboratory China School of Artificial Intelligence and Computer Science Jiangnan University China Department of Computer Guangdong University of Science and Technology China Institute of Computing Technology Chinese Academy of Sciences China

ISBN: (纸本)9798400717567

Single-carrier frequency domain contention (S-FDC) is an efficient wireless contention mechanism based on orthogonal frequency-division multiplexing (OFDM). In each round of S-FDC, each node randomly selects and signals on one of the OFDM subcarriers while listening to all subcarriers simultaneously. Each node independently detects the activated subcarrier with the smallest index and regards it as the winner subcarrier. Accurately detecting the winner subcarrier is crucial to ensuring the functionality of the network. However, it is extremely difficult in practice due to power leakage problems that arise from frequency asynchronization among nodes. In this paper, we propose a gated-recurrent-unit (GRU)-based model that incorporates S-FDC’s unique features as domain knowledge to enable accurate winner subcarrier detection. Extensive simulation experiments verify that our DL model is effective and outperforms state of the art. This research highlights the potential of DL in improving wireless communication systems. © 2024 Copyright held by the owner/author(s).

关键词： Frequency domain analysis

来源：评论

学校读者我要写书评

暂无评论

Efficient Regular Expression Matching and Hardware-Accelerated Finite Automata Pattern Recognition in NIDS 6

Efficient Regular Expression Matching and Hardware-Accelerat...

引用

6th International Conference on Recent Trends in Advance Computing, ICRTAC 2023

作者： Thota, Krishna Kishore Retna Raj, R. Jeberson Sathyabama Institute of Science and Technology Department of Computer Science and Engineering Tamilnadu India

ISBN: (纸本)9798350394702

To protect network infrastructure from the ever-changing cyber threats, Intrusion Detection Systems (IDS) perform important duties. This study introduces a sophisticated algorithm aimed at overcoming key challenges in IDS. These challenges include efficient regular expression matching, hardware implementation, and improved pattern recognition. The algorithm employs a unique technique to reduce memory specifications by using controlled faults into the pattern matching process. It builds upon perfect hashing, ensuring precise and efficient regular expression matching, making it ideal for high-speed processing in IDS applications. Additionally, the central component of a hardware-based Network Intrusion Detection System (NIDS), the technique comprises a signature match processor that is based on a field-programmable gate array (FPGA). For effective string matching, this processor makes use of a CAM-based cellular architecture. For multiple signature matches, it generates priority-encoded addresses using a binary tree structure. To enhance IDS capabilities further, the algorithm introduces an efficient method for detecting regular expression matches within network traffic text using Field-Programmable Gate Arrays (FPGAs). It presents a hardware implementation approach based on Deterministic Finite Automata (DFA), enhancing both speed and accuracy in pattern matching. This proposed algorithm provides a comprehensive solution to optimize intrusion detection by integrating innovative techniques in regular expression matching, hardware acceleration, and pattern recognition, thereby enhancing network security against springing cyber threats. © 2023 IEEE.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Park with Ease: Evaluating Usability to Design Intuitive Interfaces for Car Parking Applications 9

Park with Ease: Evaluating Usability to Design Intuitive Int...

引用

9th IEEE International Women in engineering (WIE) Conference on Electrical and computer engineering, WIECON-ECE 2023

作者： Ashraf, Anika Sultana, Zinia Islam, Iyolita Pinky, Amrin Akhter Toma, Sabrina Afrin Zinia, Afrina Islam, Muhammad Nazrul Military Institute of Science and Technology Computer Science and Engineering Department Dhaka Bangladesh

ISBN: (纸本)9798350319651

With a smartphone app or web interface, users with different demographic profiles may book and pay for parking spaces, cutting down on the time and stress involved in locating a place. Hence, such parking systems should be usable and intuitive to end users. Therefore, this research aims to evaluate the usability of existing car parking applications and to propose an intuitive and usable car parking application. To attain these objectives, three smart car parking mobile applications (Parking Koi, ParkWhiz, and SpotHero) were selected and evaluated through heuristic evaluation and a user study. The studies revealed several usability problems such as lack of feedback, instructions, flexibility and adaptability. According to the severity of issues, the Park Whiz application encountered the least number of issues in total, while the SpotHero program experienced the highest number of problems. Comparing with Parking Koi and SpotHero, Parkwhiz's average level of severity is substantially higher. The user study revealed that the three car parking applications' interfaces are poorly designed and provided the suggestions for improvement to enhance user attention. Finally, a prototype of a car parking application with an intuitive UIs is proposed to address the revealed usability problems. © 2023 IEEE.

关键词： User interfaces

来源：评论

学校读者我要写书评

暂无评论

Efficient Fetal Health Monitoring and Classification with Machine Learning 7

Efficient Fetal Health Monitoring and Classification with Ma...

引用

7th International Conference on Intelligent Computing and Control Systems, ICICCS 2023

作者： Singh, Kabir Shyry, Prayla Franklin, Ramya G Sathyabama Institute of Science and Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350397253

The goal of the research on fetal health categorization using machine learning is to create a model that can precisely predict the condition of a fetus during pregnancy. This is crucial because prompt action following early identification of fetal health issues might enhance the pregnancy's outcome. This research study suggests classifying fetal health status using machine learning approaches based on ultrasound images and other clinical parameters. To train and test our model, we will gather a sizable dataset of ultrasound images and clinical characteristics from pregnant women. To categorize the state of fetal health, the proposed model will employ machine learning algorithms and image processing techniques. Our approach should categorize fetal health status with a high degree of accuracy, and it will help obstetricians and gynecologists provide better treatment for pregnant patients. © 2023 IEEE.

关键词： Genetic programming

来源：评论

学校读者我要写书评

暂无评论

Towards intelligent and trustworthy task assignments for 5G-enabled industrial communication systems

引用

Digital Communications and Networks 2025年第1期11卷 246-255页

作者： Mingfeng Huang Anfeng Liu Neal N.Xiong Athanasios V.Vasilakos School of Computer and Communication Engineering Changsha University of Science&TechnologyChangsha410114China School of Electronic Information Central South UniversityChangsha410083China Department of Computer Science and Mathematics Sul Ross State UniversityAlpineTX 79830USA College of Mathematics and Computer Science Fuzhou UniversityFuzhou350116China Center for AI Research University of AgderGrimstad 999026Norway

With the unprecedented prevalence of Industrial Internet of Things(IIoT)and 5G technology,various applications supported by industrial communication systems have generated exponentially increased processing tasks,which makes task assignment inefficient due to insufficient *** this paper,an Intelligent and Trustworthy task assignment method based on Trust and Social relations(ITTS)is proposed for scenarios with many tasks and few ***,ITTS first makes initial assignments based on trust and social influences,thereby transforming the complex large-scale industrial task assignment of the platform into the small-scale task assignment for each ***,an intelligent Q-decision mechanism based on workers'social relation is proposed,which adopts the first-exploration-then-utilization principle to allocate *** when a worker cannot cope with the assigned tasks,it initiates dynamic worker recruitment,thus effectively solving the worker shortage problem as well as the cold start *** importantly,we consider trust and security issues,and evaluate the trust and social circles of workers by accumulating task feedback,to provide the platform a reference for worker recruitment,thereby creating a high-quality worker ***,extensive simulations demonstrate ITTS outperforms two benchmark methods by increasing task completion rates by 56.49%-61.53%and profit by 42.34%-47.19%.

关键词： Industrial Internet of Things Insufficient workers Trust evaluation Social relation Task assignment

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：