检索结果-内蒙古大学图书馆

2024 International Conference on Intelligent and Innovative Practices in Engineering and Management, IIPEM 2024

作者： Gupta, Kartavya Rani, Khushi Ajmani, Prerna Sharma, Vandana Alkhayyat, Ahmed Kalinga Institute of Industrial Technology Computer Science and Engineering Bhubaneswar India Vivekananda Institute of Professional Studies-TC India CHRIST University Computer Science Department Bengaluru India The Islamic University College of Technical Engineering Najaf Iraq

ISBN: (纸本)9798350390049

This study establishes a hybrid methodology combining LLM, CNN, and RNN for predicting crop yield, and detailed coverage of each area of the hybrid is set as follows-. In general, traditional methods have great difficulties with analyzing agricultural data presented as complex non-linear data. Our suggested approach utilizes the extraction capabilities of CNN, the temporal sequence modeling of RNN, and the sophisticated data processing of LLM, and this hybrid approach produced high accuracy levels for tested crops including wheat, maize, millet, rice, and barley, as well as significantly better precision, recall and f-score cutoff levels than traditional methods. This research contributes to ongoing developments toward improved food security and agriculture output through the implementation of sophisticated machine learning models. This paper presents a novel hybrid model for predicting crops yields by combining Recurrent Neural Networks (RNNs) and Convolutional Neural Networks (CNNs) with Large Language Models (LLMs). Because agricultural data is challenging to model as traditional algorithms typically struggle with complex, inherently non-linear data, our modeling approach leverages the capabilities of sophisticated LLMs for processing data, temporal sequence modeling capabilities of RNNs, and data extraction capabilities of CNNs. Our hybrid model can produce high accuracy outcomes from the model experimentation using standard measures of output accuracy from a number of crop species, including barley, rice, millet, maize and wheat, and the model also produced significant and meaningful improvements over previous studies with traditional methods. © 2024 IEEE.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

Promoting rigor in blockchain energy and environmental footprint research:A systematic literature review

引用

Blockchain(Research and Applications) 2024年第1期5卷 133-151页

作者： Ashish Rajendra Sai Harald Vranken Department of Computer Science Open UniversiteitHeerlen6419 ATthe Netherlands Department of Advanced Computing Sciences Maastricht UniversityMaastricht6211 LKthe Netherlands Institute for Computing&Information Sciences Radboud UniversityNijmegen6525 XZthe Netherlands

There is a growing interest in understanding the energy and environmental footprint of digital currencies,specifically in cryptocurrencies such as Bitcoin and *** cryptocurrencies are operated by a geographically distributed network of computing nodes,making it hard to estimate their energy consumption *** studies,both in academia and industry,attempt to model cryptocurrency energy consumption often based on a number of assumptions,for instance,about the hardware in use or the geographic distribution of the computing nodes.A number of these studies have already been widely criticized for their design choices and subsequent over-or under-estimation of energy *** this study,we evaluate the reliability of prior models and estimates by leveraging existing scientific literature from fields cognizant of blockchain,such as social energy sciences and information *** first design a quality assessment framework based on existing research,and we then conduct a systematic literature review examining scientific and non-academic literature demonstrating common issues and potential avenues of addressing these *** goal with this article is to advance the field by promoting scientific rigor in studies focusing on blockchain energy *** that end,we provide a novel set of codes of conduct for the five most widely used research methodologies:Quantitative energy modeling,literature reviews,data analysis and statistics,case studies,and *** envision that this code of conduct would assist in standardizing the design and assessment of studies focusing on blockchain-based systems’energy and environmental footprint.

关键词： Blockchain Energy consumption Environmental footprint Scientific rigor Reliability

来源：评论

学校读者我要写书评

暂无评论

Finding the Sweet Spot: An Empirical Study on Dataset Size, Performance, and Efficiency in Relation Extraction

Finding the Sweet Spot: An Empirical Study on Dataset Size, ...

引用

International CSI computer Conference, CSICC

作者： Sohrab Pirhadi Babak Niroomand Ebrahim Ansari Department of Computer Science Institute for Advanced Studies in Basic Sciences (IASBS) Zanjan Iran

ISBN: (数字)9798331523114

ISBN: (纸本)9798331523121

Relation extraction (RE) is a critical task in natural language processing that identifies relationships between entities within text. While increasing the size of annotated datasets generally enhances model performance, the cost and effort associated with human annotation can be prohibitive. This study investigates the impact of dataset size on RE performance using the Semantic Evaluation 2010 Task 8 dataset. Four deep neural models-Attention-Based Convolutional Neural Network, Attention-Based Bidirectional Long Short-Term Memory Network, Relation Bidirectional Encoder Representations from Transformers, and Matching the Blanks-were evaluated across eight subsets of the dataset to simulate size reduction. Performance metrics such as accuracy, precision, recall, and F1-score were analyzed. The results indicate that although larger datasets improve model performance, the benefits diminish beyond a certain size, illustrating the law of diminishing returns. These findings emphasize the importance of balancing dataset size and quality for cost-effective training and suggest strategies such as data augmentation and transfer learning to optimize performance with limited data.

关键词： Training Measurement Annotations Computational modeling Transfer learning Semantics Performance gain Transformers Natural language processing Long short term memory

来源：评论

学校读者我要写书评

暂无评论

Mobile Edge Computing for Multi-Services Digital Twin-Enabled IoT Heterogeneous Networks

引用

IEEE Transactions on Cognitive Communications and Networking 2024年第3期11卷 1845-1853页

作者： Liu, Weiqi Hossain, Mohammad Arif Ansari, Nirwan Auburn University at Montgomery Department of Computer Science and Computer Information Systems MontgomeryAL36117 United States Middle Tennessee State University Department of Engineering Technology MurfreesboroTN37132 United States New Jersey Institute of Technology Advanced Networking Laboratory Department of Electrical and Computing Engineering NewarkNJ07102 United States

A scheme for edge computing-enabled offloading in a digital twin (DT) enabled heterogeneous network (HetNet) of multi-services IoT devices (IDs) is proposed. This scheme optimizes the association and handover of IDs, offloading ratio, and resource allocation considering the number of IDs, deadline requirements, and resource capacities. The objective is to enhance future generation networks by considering the ID movement, diverse ID requests, and network heterogeneity. We formulate the problem as Joint ID assOciatIon, offloadiNg ratio, Wireless bandwidth and computIng reSource allocation, and digital twin placEment (JOINWISE), aiming to minimize the task completion time of all IDs while considering ID movement. Since JOINWISE is a mixed-integer nonlinear problem, we decompose it into two sub-problems: the ID Association (IDA) problem and the offloading Ratio, DT plAcement, bandwiDth and computIng resource allOcation (RADIO) problem. IDA can be solved by mapping it to a multi-dimensional multiple knapsacks problem. Due to the non-convexity, high dimension of decision variables, and dynamic HetNet environment of RADIO, we propose a deep deterministic policy gradient (DDPG) based reinforcement learning method to iteratively solve the two sub-problems. Simulation results have confirmed the effectiveness of our proposed scheme in tackling the JOINWISE problem. © 2015 IEEE.

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

Using NSCTS and DCNN, Rapid Prediction and Forecasting of Breast Cancer 1

Using NSCTS and DCNN, Rapid Prediction and Forecasting of Br...

引用

1st IEEE International Conference on Ambient Intelligence, Knowledge Informatics and Industrial Electronics, AIKIIE 2023

作者： Seethalakshmi, K. Bhagyalakshmi, A. Sangeetha, A. Vijitha, S. Palukuri, P. Suhas Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Tamil Nadu Chennai India R.M.K. College of Engineering and Technology Department of Computer Science and Engineering Tamil Nadu Chennai India Vels Institute of Science Technology & Advanced Studies Department of Computer Science and Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350316469

Utilizing the CAD system, which aids radiologists in various diagnostic procedures, a recent study has been conducted on the early identification of breast cancer. Next to lung cancer, breast cancer ranks among the most deadly diseases. Initially, detection is done based on screening tests done through Magnetic resonance imaging (MRI), subsequently Infrared thermography, and digital mammography (DM). Whenever a suspicion is raised, these tests might be recommended by the specialist. Region-based segmentation is used for the test picture in this work, while NSCTS (Non-subsample Contourlet transform segmentation) is used for preprocessing. ResNet-164 DCNN architecture performs feature extraction and classification between normal and aberrant tumor pictures. The diagnosis system adopts the deep learning technology to increase its performance rate. The approach to prediction starts with screening test photos, then preprocessing to enhance the image quality, ROI detection, ROI segmentation, and classification. The resulting images are examined using a variety of evaluation measures, including performance rate, sensitivity, specificity, and accuracy. When compared to other recent work, the outcome is exceptional. The obtained accuracy, sensitivity of the proposed system is 98.58% and 98.78%. The application takes advantage of the MIAS mammography image dataset. © 2023 IEEE.

关键词： Breast cancer contourlet segmentation DCNN Digital mammograms Image preprocessing MRI ResNet

来源：评论

学校读者我要写书评

暂无评论

NTFS: Introduction and Analysis from Forensics Point of View 2

NTFS: Introduction and Analysis from Forensics Point of View

引用

2nd International Conference for Advancement in Technology, ICONAT 2023

作者： Hermon, Rahul Singh, Upasna Singh, Bhupendra Defense Institute of Advanced Technology School of Computer Engineering and Mathematical Sciences Pune India Indian Institute of Information Technology Computer Science and Engineering Department Pune India

ISBN: (纸本)9781665475174

New Technology File System (NTFS) is a file system being used by Windows Operating Systems since 1993. NTFS is a file system used by the Windows Operating Systems for storing, cataloguing and discovering/finding files. In this work we will learn about the basics of NTFS to include its file structure and other important attributes. Then carry out analysis of NTFS file system using WinHex and Active@ Disk Editor tools from a forensics point of view, compare the results of both tools. Lastly, we carried out comparison of NTFS in Windows 10 and 11 Operating System to include forensics analysis using WinHex and Active@ Disk Editor tools. © 2023 IEEE.

关键词： Windows operating system

来源：评论

学校读者我要写书评

暂无评论

X-ClusterLink: An Efficient Cross-Cluster Communication Framework in Multi-Kubernetes Clusters 25

X-ClusterLink: An Efficient Cross-Cluster Communication Fram...

引用

34th ACM Web Conference, WWW 2025

作者： Wang, Pengbo Zhao, Gongming Wu, Yuantao Xu, Hongli Wang, Haibo School of Computer Science and Technology University of Science and Technology of China Hefei China Suzhou Institute for Advanced Research University of Science and Technology of China Suzhou China University of Kentucky Department of Computer Science Lexington United States

ISBN: (纸本)9798400712746

Kubernetes is widely adopted by enterprises to enhance service availability for applications such as web services and large-scale model training, due to its advantages in managing containerized applications. As service demands increase, a single Kubernetes cluster often becomes insufficient, leading to the trend of using multiple clusters to improve service scalability. However, achieving efficient cross-cluster communication poses significant challenges due to the need for low latency, high throughput, and strong robustness. Existing methods for cross-cluster communication either employ a centralized control plane, which becomes a communication bottleneck, or use numerous service-bound proxies, leading to increased management complexity and possibly compromised robustness in cross-cluster communication. To address the above challenges, we introduce X-ClusterLink, a framework designed for efficient cross-cluster communication in multi-Kubernetes clusters. X-ClusterLink first employs broker clusters to ensure low-latency cross-cluster synchronization. Then, it aggregates multiple containerized gateways to enhance throughput and leverages eXpress Data Path (XDP) for advanced packet processing, thereby accelerating traffic forwarding. Finally, it incorporates Bucket-Based Consistent ECMP to facilitate seamless failover and enhance robustness. Experimental results demonstrate that X-ClusterLink significantly improves cross-cluster communication efficiency, increasing cross-cluster forwarding bandwidth by 3.1 × compared to existing solutions. © 2025 Copyright held by the owner/author(s).

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Leveraging Artificial Intelligence in computer science to Manage Stress and Anxiety: Applications and Innovations 2

Leveraging Artificial Intelligence in Computer Science to Ma...

引用

2nd International Conference on Advances in Computation, Communication and Information Technology, ICAICCIT 2024

作者： Mittal, Ketan Shikha Sharma, Ronak Attri, Jeevesh Kumar Taneja, Kritika Department of Computer Science and Engineering Manav Rachna International Institute of Research and Studies Faridabad India Department of electrical and electronics engineering Manav Rachna International Institute of Research and Studies Faridabad India

ISBN: (纸本)9798331541217

This study explores the effectiveness, ethical considerations, and demographic influences of AI-based interventions in managing stress and anxiety. AI technologies, including Machine Learning, Natural Language Processing (NLP), and Biometric Monitoring, have shown promising results in reducing stress and anxiety across diverse populations. Machine Learning algorithms excel in predictive analytics, enabling early detection and intervention, while NLP tools offer real-time cognitive-behavioural therapy (CBT) and emotional support through AI-powered chatbots. Biometric Monitoring provides objective physiological data, further enhancing the precision of stress management strategies. However, the effectiveness of these interventions is influenced by demographic variables such as age, gender, socio-economic status, and cultural background, with younger, tech-savvy users and those of higher socio-economic status showing greater engagement and benefit. Also, the mobile application named "sahayya" has been discussed along with its merits. Discussing how technology can be put to better use. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Software Reliability Assessment Using Hybrid Neuro-Fuzzy Model

引用

computer Systems science & Engineering 2022年第6期41卷 891-902页

作者： Parul Gandhi Mohammad Zubair Khan Ravi Kumar Sharma Omar H.Alhazmi Surbhi Bhatia Chinmay Chakraborty Department of Computer Applications Manav Rachna International Institute of Research and StudiesFaridabad121006India Department of Computer Science College of Computer Science and EngineeringTaibah UniversityMadinahSaudi Arabia Department of Computer Applications Chandigarh Group of CollegesLandran140307India College of Computer Sciences and Information Technology King Faisal UniversitySaudi Arabia Department of Electronics&Communication Engineering Birla Institute of TechnologyMesra JharkhandIndia

Software reliability is the primary concern of software developmentorganizations, and the exponentially increasing demand for reliable softwarerequires modeling techniques to be developed in the present era. Small unnoticeable drifts in the software can culminate into a disaster. Early removal of theseerrors helps the organization improve and enhance the software’s reliability andsave money, time, and effort. Many soft computing techniques are available toget solutions for critical problems but selecting the appropriate technique is abig challenge. This paper proposed an efficient algorithm that can be used forthe prediction of software reliability. The proposed algorithm is implementedusing a hybrid approach named Neuro-Fuzzy Inference System and has also beenapplied to test data. In this work, a comparison among different techniques of softcomputing has been performed. After testing and training the real time data withthe reliability prediction in terms of mean relative error and mean absolute relativeerror as 0.0060 and 0.0121, respectively, the claim has been verified. The resultsclaim that the proposed algorithm predicts attractive outcomes in terms of meanabsolute relative error plus mean relative error compared to the other existingmodels that justify the reliability prediction of the proposed model. Thus, thisnovel technique intends to make this model as simple as possible to improvethe software reliability.

关键词： Software quality reliability neural networks fuzzy logic neuro-fuzzy inference system

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of YOLO versions for Real-time Pothole Detection

引用

Procedia computer science 2025年 257卷 77-84页

作者： Leonhel V. Fortin Orven E. Llantos Department of Computer Applications College of Computer Studies MSU-Iligan Institute of Technology Tibanga Iligan City 9200 Philippines Department of Computer Science

The integration of lightweight computer vision models emerges as a promising solution for automating road inspection processes. The evolution of YOLO architectures, particularly their lightweight variants, enables significant improvements in both detection accuracy and computational efficiency. Recent iterations through YOLOv9-tiny, YOLOv10-nano, and YOLOv11-nano enhance real-time performance capabilities while maintaining acceptable accuracy through optimized network architectures. The implementation of these lightweight YOLO variants presents a compelling approach to automated pothole detection. Previous studies utilizing limited datasets of approximately 1,388 images established initial feasibility but left significant room for improvement in model robustness and generalization. This research addresses these limitations by employing an expanded dataset of 16,054 images, encompassing diverse environmental conditions and road surface characteristics. The comparative analysis establishes new benchmarks for pothole detection in resource-constrained environments, demonstrating the viability of nano/tiny models for practical applications.

关键词： Lightweight computer Vision YOLO Pothole Detection Real-time Object Detection Road Surface Inspection

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：