检索结果-内蒙古大学图书馆

5th International Conference on Advancements in Computing, ICAC 2023

作者： Nirasha Jayasiri, K.C. Chandrasiri, Sanjeevi Rupasinghe, Shalini Karunanayake, K.O. Rivindu Uthayachandran, Abineshh Zihara, M.I. Fathima Sri Lanka Institute of Information Technology Dept. of Computer Science and Software Engineering Sri Lanka

ISBN: (纸本)9798350358131

Tomato is one of the most popular crops worldwide. The success of a tomato crop is highly dependent on the health of the plants. Nutrient deficiency surveillance is typically conducted through visual inspections, which can be challenging for inexperienced farmers and home gardeners to work accurately. There is a growing need for a quick, reliable, and accurate nutrient deficiency identification system to address this issue. The proposed method is based on image processing and deep learning technologies that are highly effective for image classification tasks. Two models were trained using a dataset collected from tomato plants in Sri Lanka and evaluated using Mask Region-based Convolutional Neural Network (Mask R-CNN) and, You Only Look Once (YOLO) for deficiency classification, and results obtained 92% and 98% accuracy, respectively. Deficiency dispersion level expressed as a percentage using Mask R-CNN and followed by image processing techniques. Overall, this proposed system offers a convenient and accessible tool for farmers and home gardeners to monitor and maintain the health of their tomato plants, enabling them to achieve optimal yields and ensure profitable returns. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Dynamic Image Deblurring based on Crosshatch Attention Adversarial Network and Hybrid Loss 5

Dynamic Image Deblurring based on Crosshatch Attention Adver...

引用

5th International Conference on Advancements in Computational Sciences, ICACS 2024

作者： Aslam, Ummama Shaukat, Arslan Azam, Basim Dept. of Computer and Software Engineering H-12 Islamabad Pakistan Institute of Integrated and Intelligent Systems Griffith University Brisbane Australia

ISBN: (纸本)9798350394764

Image deblurring techniques that uses deep learning have shown great potential but due to low generalizability, noise immunity and the correlation among different pixels is not addressed in detail that results in unwanted artifact that appears in the deblurred image. To tackle this problem an end-to-end approach is proposed for the recovery of sharp image from blurred one without the estimation of blur kernel. A special type of attention module known as crosshatch attention is used after Residual Block of Generator model for removing noise and for the collection of correlation of different pixels in an image. Hybrid Loss function is defined which focus on different part of image and improve edges and texture details. The performance of the model for deblurring is measured on GoPro dataset. Our proposed model has slightly higher objective and subjective evaluation i-e PSNR, SSIM value and the visual results. © 2024 IEEE.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Work in Progress: Congestion Control in mmWave Fluctuating Scenarios in 5G-A/6G 10

Work in Progress: Congestion Control in mmWave Fluctuating S...

引用

10th IEEE World Forum on Internet of Things, WF-IoT 2024

作者： Sandoval, Jorge Ignacio Cespedes, Sandra University of Chile Department of Electrical Engineering Santiago Chile Concordia University Dept. of Computer Science and Software Eng Montreal Canada

ISBN: (纸本)9798350373011

The development of the next generation of cellular networks, 5G-Advanced and 6G (5G-A/6G), offers higher speeds, sub-millisecond latency, and providing wider coverage, which are key to meeting the requirements of new and demanding applications. As such, there are several challenges in managing and leveraging this opportunity to ensure that channel conditions do not impact the application due to mobility and obstructions. 5G introduces the use of millimeter wave (mmWave), and the commercial deployment of this technology brings to light the issues related to propagation and mobility in high-frequency bands, and their impact on applications has begun to be studied by exploring the response of the congestion control algorithms (CCAs) in representative scenarios. However, the highly variable channel conditions in mmWave require that they be defined as fluctuating bandwidth scenarios. It is necessary to determine how the transport layer can take advantage of the maximum available capacity and not affect the applications, and whether the network promises are fulfilled. This work aims to design and evaluate a CCA capable of efficiently adapting to the fluctuating bandwidth of extreme condition scenarios of 5G-A/6G mobile networks and to compare it with the state-of-the-art algorithms. As a first result, a set of simulation-based evaluation using 5GLENA was discussed. A combination of CCAs and different radio link control (RLC) buffer sizes allows us to highlight the importance of defining appropriate metrics and including convergence times as part of the evaluation performance of the algorithms. Algorithms such as HighSpeed and New Reno are among the slowest to converge, while BBR is the fastest. The analysis and characterization of the algorithms will allow us to define the requirements for designing an Machine Learning (ML) based algorithm with optimal performance and better convergence times. © 2024 IEEE.

关键词： Radio links

来源：评论

学校读者我要写书评

暂无评论

Exploring the Potential of Llama Models in Automated Code Refinement: A Replication Study

Exploring the Potential of Llama Models in Automated Code Re...

引用

IEEE International Conference on software Analysis, Evolution and Reengineering (SANER)

作者： Genevieve Caumartin Qiaolin Qin Sharon Chatragadda Janmitsinh Panjrolia Heng Li Diego Elias Costa Dept of Computer Science and Software Engineering Concordia University Montreal Canada Dept of Computer Engineering and Software Engineering Polytechnique Montreal Montreal Canada

ISBN: (数字)9798331535100

ISBN: (纸本)9798331535117

Code reviews are an integral part of software development and have been recognized as a crucial practice for minimizing bugs and favouring higher code quality. They serve as an important checkpoint before committing code and play an essential role in knowledge transfer between developers. However, code reviews can be time-consuming and can stale the development of large software projects. In a recent study, Guo et al. assessed how ChatGPT3.5 can help the code review process. They evaluated the effectiveness of ChatGPT in automating the code refinement tasks, where developers recommend small changes in the submitted code. While Guo et al.'s study showed promising results, proprietary models like ChatGPT pose risks to data privacy and incur extra costs for software projects. In this study, we explore alternatives to ChatGPT in code refinement tasks by including two open-source, smaller-scale large language models: CodeLlama and Llama 2 (7B parameters). Our results show that, if properly tuned, the Llama models, particularly CodeLlama, can achieve reasonable performance, often comparable to ChatGPT in auto-mated code refinement. However, not all code refinement tasks are equally successful: tasks that require changing existing code (e.g., refactoring) are more manageable for models to automate than tasks that demand new code. Our study highlights the potential of open-source models for code refinement, offering cost-effective, privacy-conscious solutions for real-world software development.

关键词： Temperature measurement Data privacy Codes Reviews Large language models Documentation Chatbots software Data models software development management

来源：评论

学校读者我要写书评

暂无评论

Laser-assisted Multidimensional Imaging Modalities for Early Detection of Tumours in Bio Tissues: An In Vitro Study

引用

Lasers in engineering 2025年第4-6期59卷 199-215页

作者： Akhtar, M. Ullah, H. Aslam, K. Siddique, M.A. Akram, A. Majid, M.A. Abdullah-Al-Wadud, M. Aleem, A. Farhan, M. Batool, Z. Biophotonics Imaging Techniques Laboratory Institute of Physics The Islamia University of Bahawalpur 63100 Pakistan Dept. of Software Engineering College of Computer and Information Sciences King Saud University Riyadh11543 Saudi Arabia School of Earth Sciences and Engineering Hohai University Nanjing China

The idea, upon which this research work depends, is the early detection of tumours in different biological soft tissues like bladder, respiratory and thigh tissues. Imaging and spectroscopic technique that were used to study healthy and cancerous tissues were white light microscopy and Fourier-transform infrared radiation (FTIR) spectroscopy. The observation and calculations collected through all these imaging techniques prove as helping tools to differentiate healthy and cancerous body tissues. Soft tissues from patients who had been diagnosed with bladder, respiratory, and thigh cancer were gathered from the Bahawalpur Victoria Hospital, Pakistan while keeping in mind the ethical research perspective. Two-dimensional (2-D) white light microscopy images showed that healthy and cancerous tissues have a different kind of shapes, sizes and structure arrangements. Normal tissues images show a regular pattern of structure arrangement, but cancerous tissues show an irregular shapes, sizes, and structures. Similarly, FTIR spectroscopy graphs represents different peaks of stretching vibrations of C-H, O-H, C-C, N-H, CH2 double and triple bonding of different biological tissues like bladder, respiratory and thigh tissues. This research work will help in the medical field for early detection of tumour which helps to diagnose the tumour and also helpful for better treatment planning in early stage. ©2025 Old City Publishing, Inc.

关键词： Fourier transform infrared spectroscopy

来源：评论

学校读者我要写书评

暂无评论

Integrated Word2Vec-based Speech Annotations for Enhanced EEG Decoding of Speech Intentions 13

Integrated Word2Vec-based Speech Annotations for Enhanced EE...

引用

13th International Winter Conference on Brain-computer Interface, BCI 2025

作者： Jang, Se-Na Park, Hyeong-Yeong Kim, Seong-Wook Yu, Seong-Hyun Lee, Minji Jeong, Ji-Hoon Dept. Computer Science Chungbuk National University Cheongju Korea Republic of Dept. Biomedical Software Engineering The Catholic University of Korea Bucheon Korea Republic of

ISBN: (纸本)9798331521929

Brain-computer interface (BCI) technology has promising applications as an intuitive communication tool and in fields such as language rehabilitation. This study aims to decode human speech intentions by analyzing EEG signals recorded during actual and imagined speech. EEG data were collected using a 64 channels system, with preprocessing to remove artifacts. Automatic speech recognition (ASR) was used to extract precise speech onset times, generating time-specific speech annotations corresponding with EEG data. Pretrained Word2Vec embeddings were integrated to provide semantic context, combining neural signals with high-level linguistic features. Support vector machine (SVM), linear discriminant analysis (LDA) were employed for decoding. The results demonstrate that integrating speech annotations improves decoding accuracy, even for imagined speech, highlighting the potential of BCI technology for advanced applications in communication and rehabilitation. © 2025 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Generative Adversarial Networks for Anomaly Detection: A Systematic Literature Review 4

Generative Adversarial Networks for Anomaly Detection: A Sys...

引用

4th International Conference on Computing, Mathematics and engineering Technologies, iCoMET 2023

作者： Noor, Shah Bazai, Sibghat Ullah Ghafoor, Muhammad Imran Marjan, Shah Akram, Saira Ali, Fatima Dept. Computer Science Quetta Pakistan Pakistan Television Corporation Dept. of Electrical Engineering Superior University Lahore Pakistan Dept. of Software Engineering Quetta Pakistan Dept. of Computer Engineering Quetta Pakistan

ISBN: (纸本)9798350335316

In numerous research areas, anomaly identification is a major problem. Identifying and properly classifying data as anomalous is a challenging task that is resolved in various manners over the years. Different approaches like traditional, supervised, unsupervised, and semi-supervised are used for anomaly detection. In the literature, various machine learning-based anomaly detection algorithms exist. It is challenging to choose one anomaly detection algorithm from the several available algorithms because each algorithm puts forward its good detection performance. In recent years, generative adversarial networks have shown remarkable results for anomaly classification. This paper aims to represent a systematic literature review of generative adversarial network-based approaches for anomaly detection and highlights their pros. © 2023 IEEE.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

SCHC over DtS-IoT: Performance of SCHC Confirmation Modes in Satellite IoT 10

SCHC over DtS-IoT: Performance of SCHC Confirmation Modes in...

引用

10th IEEE World Forum on Internet of Things, WF-IoT 2024

作者： Munoz-Lara, Rodrigo Cespedes, Sandra Diaz, Marcos University of Chile Dept.of Electrical Engineering Santiago Chile Concordia University Dept. of Computer Science and Software Eng. MontrealQC Canada

ISBN: (纸本)9798350373011

Static Context Header Compression and Fragmentation (SCHC) is a standard defined as an adaptation layer for supporting IPv6, UDP, and CoAP protocols in low power wide area network (LPWAN) technologies. SCHC has fragmentation modes that use confirmation mechanisms to deliver reliable communications. Direct-to-satellite Internet of Things (DtS-IoT) directly communicates between end devices and the satellite in an IoT environment. If SCHC is implemented in a DtSIoT environment, applications using IPv6 could have global coverage through the Internet of Things (IoT). Unfortunately, it is not known whether SCHC can operate with the current acknowledgement mechanisms in a DtS-IoT environment, and if so, it is not known which one performs better. This work evaluates SCHC acknowledgement modes for ACK-on-Error fragmentation mode, including the new SCHC Compound ACK mode. It determines which mode has the lowest transfer delay for different LoRa data rates and frame error rates in a DtS-IoT environment with LEO satellites. © 2024 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Development of AI-Based Diagnostic Systems for Wound Images 15

Development of AI-Based Diagnostic Systems for Wound Images

引用

15th International Conference on Information and Communication Technology Convergence, ICTC 2024

作者： Jeong, Seoyeon Kim, Jaeho Choi, Kyusung Cho, Young-Rae Yonsei University Dept. of Computer and Telecommunications Engineering Wonju26493 Korea Republic of Yonsei University Dept. of Software Wonju26493 Korea Republic of

ISBN: (纸本)9798350364637

Recent advancements in AI technology are revolutionizing the medical field by enhancing diagnostic accuracy, optimizing treatment plans, and providing personalized medical services. AI-based algorithms are particularly effective in analyzing medical images to detect diseases early. Telemedicine, which allows remote medical consultations, benefits from these techniques by improving access to healthcare and enabling accurate diagnoses through efficient data exchange. This work developed an AI-based diagnostic system using a Convolutional Neural Network (CNN) model to analyze wound images. The wound dataset from Kaggle, consisting of 377 images across seven categories, was augmented 25 times to improve model performance. The app allows users to take or upload wound images, which are then classified by the model, providing treatment and aftercare information. This app achieved a high accuracy of 95.716% in classifying wounds and provides basic treatment suggestions. Despite challenges like limited dataset size, the project successfully demonstrated the potential for real-time wound analysis in telemedicine and healthcare. Future improvements should include a more diverse dataset and advanced treatment recommendations to enhance the app's utility. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

IoT Security: A Deep Learning-Based Approach for Intrusion Detection and Prevention

IoT Security: A Deep Learning-Based Approach for Intrusion D...

引用

2023 International Conference on Evolutionary Algorithms and Soft Computing Techniques, EASCT 2023

作者： Kauhsik, Bhanu Nandanwar, Himanshu Katarya, Rahul Delhi Technological University Dept. of Software Engineering Delhi India Delhi Technological University Dept. of Computer Science and Engineering Delhi India

ISBN: (纸本)9798350313413

The size and market worth of the Internet of Things (IoT) have expanded, but unfortunately, the likelihood of user data being compromised has also risen. This presents a notable danger that has the potential to create disorder. Consequently, the main aim of this paper is to recognize any weaknesses within existing security solutions and suggest an innovative approach to address them. In order to accomplish this, the paper puts forth four research inquiries concerning IoT security that leverage Machine Learning and Deep Learning techniques. Additionally, it conducts an extensive review of the latest publications and concludes that a combination of specific techniques can provide a potential solution to the security problems in IoT. Overall, the findings of this study suggest that this systematic literature review could help in significantly enhancing the security of IoT devices and applications, safeguarding user data from unauthorized access and potential misuse. © 2023 IEEE.

关键词： Cyberattack Deep Learning Internet of Things (IOT) Intrusion Detection System (IDS) Network Security

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：