检索结果-内蒙古大学图书馆

7th International Symposium on Multidisciplinary Studies and Innovative Technologies, ISMSIT 2023

作者： Ransinghe, M.R.A.D. Samarakoon, D.S.M.A. Waththaladeniya, M.N. Ihalagedara, B.I.H.U. Samaratunge Arachchilllage, Udara Srimath S. Kodagoda, N. Sri Lanka Institute of Information Technology Department of Computer Science and Software Engineering Malabe Sri Lanka

ISBN: (纸本)9798350342154

Optimizing organic crop rotation and effectively managing pests and diseases remain a significant challenge for farmers. In this research, we propose a Smart System to Optimize Organic Crop Rotation using Precision Agriculture Data. The system leverages Internet of Things (IoT) technology, machine learning (ML) algorithms, and cloud computing to enhance decision-making and improve productivity in organic farming. The proposed system integrates multiple components to provide farmers with informed decisions for optimized crop rotation. Soil sensors collect data on soil health, which is then analyzed using a multi-objective optimization technique to determine the best crop for a given soil sample. Real-time weather data is incorporated to enable climate-resilient farming practices and help farmers make educated choices in selecting crops and implementing rotation plans. Additionally, a cloud computing-based model is developed for pest and disease identification, providing farmers with effective solutions to combat these challenges in organic methodologies. By leveraging IoT, ML, and cloud computing, our system proposes farmers a more efficient and effective approach to managing their crops. The system provides real-time data-driven recommendations on fertilizer selection and crop rotation, leading to improved crop growth, increased yields, and reduced environmental impact. Moreover, by adopting organic farming practices, the system contributes to the sustainable development of the agricultural sector. © 2023 IEEE.

关键词： Crop rotation

来源：评论

学校读者我要写书评

暂无评论

Predictive Modeling for Early Identification of Disease Severity in Acute Respiratory Infections: A Case Study with COVID-19 5

Predictive Modeling for Early Identification of Disease Seve...

引用

5th International Conference on Advancements in Computing, ICAC 2023

作者： Kalapuge, Vindhya Kasthurirathna, Dharshana Sri Lanka Institute of Information Technology Department of Computer Science & Software Engineering Malabe Sri Lanka

ISBN: (纸本)9798350358131

The COVID-19 pandemic, declared a global emergency by WHO in March 2020, has had a profound impact on global health. With millions affected, the pandemic's magnitude became evident. Even advanced healthcare systems grappled with resource shortages, from protective gear to ventilators. Late diagnosis and the inability to adapt to new SARS-CoV-2 variants led to misdiagnoses and high casualties. Overburdened healthcare facilities and the absence of a centralized patient data system hindered swift decision-making. The lack of real-time monitoring meant many didn't receive timely, personalized care, underscoring the need for an integrated healthcare response during global emergencies. To tackle these challenges and improve hospital resource management during pandemics, this study presents a web approach harnessing big data analytics to develop a machine learning predictive model. This model has been developed to enable hospitals to assess patients' severity in real-time, taking into account a wide range of factors such as symptoms, medical history, and demographics. To acquire data regularly, a streaming data pipeline was established using Apache Kafka and Apache Streaming. In predicting the severity levels of patients, both Multinomial Logistic Regression and Multilayer Perceptron (MLP) models were employed. One noteworthy finding was that using datasets with balanced classes yielded significantly higher accuracy for the MLP model compared to unbalanced datasets. Specifically, MLP achieved the highest accuracy of 60.4% when trained on balanced classes. This model's real-time severity insights have the potential to revolutionize decision-making and resource allocation in healthcare. It represents a significant step towards a more effective response to future pandemics and the strengthening of the global healthcare system. © 2023 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

SPRSPS: An Effective Preprocessing Framework to Enhance Vulnerability Detection in Deep Learning Models 24

SPRSPS: An Effective Preprocessing Framework to Enhance Vuln...

引用

4th Asia-Pacific Artificial Intelligence and Big Data Forum, AIBDF 2024

作者： Wang, Jiarui Guo, Wensheng Yang, Xia Sun, Haiyong School of Information and Software Engineering University of Electronic Science and Technology of China Sichuan Chengdu China Chengdu Lianan Tech Sichuan Chengdu China

ISBN: (纸本)9798400710865

Current vulnerability detection methods based on deep learning and program slicing techniques are widely used, but the program representations and slicing strategies they employ are not well-suited for this purpose. This paper introduces the SPRSPS (More Suitable Program Representation and Smarter Program Slicing) framework, which standardizes and enhances preprocessing procedures. The approach involves: first, utilizing features of LLVM IR, such as SSA and control/data flow simplification, to construct program representations more suitable for vulnerability detection;second, optimizing graph representations for graph neural networks commonly used in both general and specific vulnerability detection. Compared to previous work, it more clearly defines node and edge features. Finally, it thoroughly investigates the distances between vulnerability manifestation points and root causes, proposing a smarter slicing strategy. Ablation experiments were conducted on the general vulnerability detection model SedSVD and the specific vulnerability detection model GLICE. After replacing their preprocessing methods with the proposed approach, improvements were observed in accuracy and F1 scores. In the SedSVD project, the false positive rate (FPR) decreased by 12%, accuracy increased by 7%, and the F1 score improved by 10%, with a 95% reduction in the number of result lines, indicating more precise vulnerability localization. In the GLICE project, the FPR decreased by 10%, accuracy improved by 3%, and the number of result lines was significantly reduced by 91%. These experiments demonstrate that using the SPRSPS framework allows for more accurate and efficient vulnerability detection. © 2024 Copyright held by the owner/author(s).

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Sinhala Sign Language Translation through Immersive 3D Avatars and Adaptive Learning 5

Sinhala Sign Language Translation through Immersive 3D Avata...

引用

5th International Conference on Advancements in Computing, ICAC 2023

作者： Gamage, B.G.J. Paranagama, R.P.S.D. Ranaweera, R.M.S.H. Dilshan, A.V.R. Weerathunga, Ishara Kasthurirathna, Dharshana Sri Lanka Institute of Information Technology Faculty of Computing Department of Software Engineering Malabe Sri Lanka

ISBN: (纸本)9798350358131

This research paper addresses the challenge of bridging the communication gap between sign language users and non-users through a comprehensive study on sign language translation. The focus is on Sinhala Sign Language (SSL), and the research problem encompasses various innovative components. These include the conversion of Sinhala Sign Language (SSL) into text, emotion recognition and representation, personalized sign language learning, and accurate identification and translation of sign language gestures. By leveraging machine learning, deep learning, 3D modeling, and image/video processing techniques, the system enhances accessibility, communication, and education for the deaf and hard-of-hearing community. The outcomes of this research encompass an accurate and visually appealing sign language translation system, personalized learning interfaces, and the integration of emotions into sign language communication. The research contributes by providing insights into SSL grammar and lexicon, developing a tailored sign language learning curriculum, implementing reinforcement learning algorithms for personalized feedback, utilizing 3D components for enhanced visual quality, and optimizing deployments and models for improved performance. The proposed system has significant implications for improved accessibility, education, and inclusivity, fostering effective communication and understanding between sign language users and non-users. © 2023 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

VECCTO: An Collaborative Task Offloading Framework for UAV-Assisted Vehicular Edge Clusters 4

VECCTO: An Collaborative Task Offloading Framework for UAV-A...

引用

2023 4th International Conference on Computer engineering and Intelligent Control, ICCEIC 2023

作者： Zhang, Zhiyang Zhang, Fengli University of Electronic Science and Technology of China School of Information and Software Engineering Chengdu Sichuan610000 China

ISBN: (纸本)9798350308877

Unmanned Aerial Vehicles (UAVs) provide Vehicle Edge Clusters (VECs) with robust signal coverage and data offloading capabilities, but they have limitations when dealing with heterogeneous cluster environments and dynamic task resource requests. This paper presents VECCTO, a collaborative task offloading framework designed specifically for UAV-assisted VEC that seeks to address the scalability and dynamics challenges in VEC task offloading. VECCTO incorporates the Asynchronous Advantage Actor-Critic (A3C) mechanism, which includes a centralized global Critic in the base station and a distributed local Actor in the UAV. It obtains and trains the global state value function of the entire VEC via the target network and independently updates the task offloading policy parameters of each sub-VEC based on the policy gradient, thus autonomously learning the task offloading policy. We evaluate the efficacy of VECCTO using the modified Google Cluster Usage Tracing (GCT) dataset. The results demonstrate that VECCTO efficiently manages task offloading in UAV-assisted VECs, achieving low latency while assuring load balancing among sub-VECs, which makes it a promising solution for next-generation IoV ecosystems. © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

MSEs Credit Risk Assessment Model Based on Federated Learning and Feature Selection

引用

Computers, Materials & Continua 2023年第6期75卷 5573-5595页

作者： Zhanyang Xu Jianchun Cheng Luofei Cheng Xiaolong Xu Muhammad Bilal School of Computer and Software Nanjing University of Information Science&TechnologyNanjing210044China State Key Laboratory Novel Software Technology Nanjing UniversityNanjing210023China Department of Computer and Electronics Systems Engineering Hankuk University of Foreign StudiesYongin-siGyeonggi-do17035Korea

Federated learning has been used extensively in business inno-vation scenarios in various *** research adopts the federated learning approach for the first time to address the issue of bank-enterprise information asymmetry in the credit assessment ***,this research designs a credit risk assessment model based on federated learning and feature selection for micro and small enterprises(MSEs)using multi-dimensional enterprise data and multi-perspective enterprise *** proposed model includes four main processes:namely encrypted entity alignment,hybrid feature selection,secure multi-party computation,and global model ***,a two-step feature selection algorithm based on wrapper and filter is designed to construct the optimal feature set in multi-source heterogeneous data,which can provide excellent accuracy and *** addition,a local update screening strategy is proposed to select trustworthy model parameters for aggregation each time to ensure the quality of the global *** results of the study show that the model error rate is reduced by 6.22%and the recall rate is improved by 11.03%compared to the algorithms commonly used in credit risk research,significantly improving the ability to identify ***,the business operations of commercial banks are used to confirm the potential of the proposed model for real-world implementation.

关键词： Federated learning feature selection credit risk assessment MSEs

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Video Object Segmentation via Weak User Interaction and Temporal Modulation

引用

Chinese Journal of Electronics 2023年第3期32卷 507-518页

作者： FAN Jiaqing ZHANG Kaihua ZHAO Yaqian LIU Qingshan College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics College of Computer and Software Nanjing University of Information Science and Technology Engineering Research Center of Digital Forensics Ministry of Education Inspur Suzhou Intelligent Technology Corporation

In unsupervised video object segmentation(UVOS), the whole video might segment the wrong target due to the lack of initial prior information. Also, in semi-supervised video object segmentation(SVOS), the initial video frame with a fine-grained pixel-level mask is essential to good segmentation accuracy. It is expensive and laborious to provide the accurate pixel-level masks for each training sequence. To address this issue, We present a weak user interactive UVOS approach guided by a simple human-made rectangle annotation in the initial frame. We first interactively draw the region of interest by a rectangle, and then we leverage the mask RCNN(region-based convolutional neural networks) method to generate a set of coarse reference labels for subsequent mask propagations. To establish the temporal correspondence between the coherent frames, we further design two novel temporal modulation modules to enhance the target representations. We compute the earth mover's distance(EMD)-based similarity between coherent frames to mine the co-occurrent objects in the two images, which is used to modulate the target representation to highlight the foreground target. We design a cross-squeeze temporal modulation module to emphasize the co-occurrent features across frames, which further helps to enhance the foreground target representation. We augment the temporally modulated representations with the original representation and obtain the compositive spatio-temporal information, producing a more accurate video object segmentation(VOS) model. The experimental results on both UVOS and SVOS datasets including Davis2016,FBMS, Youtube-VOS, and Davis2017, show that our method yields favorable accuracy and complexity. The related code is available.

关键词： Earth Training Codes Annotations Modulation Object segmentation Complexity theory

来源：评论

学校读者我要写书评

暂无评论

Adaptive IoT Decision Making in Uncertain Environments 7

Adaptive IoT Decision Making in Uncertain Environments

引用

7th IEEE International Conference on Smart Internet of Things, SmartIoT 2023

作者： Wang, Yan Zheng, Liwei He, Jingjing Cui, Zhanqi Computer School Software Engineering Research Center Beijing Information Science and Technology University Beijing China

ISBN: (纸本)9798350316575

The rapid growth of the Internet of Things (IoT) has led to widespread deployment of IoT systems in domains such as smart homes, healthcare, and transportation. However, IoT systems often operate under uncertainty, making it difficult to predict and control their behavior. In this paper, we propose an adaptive decision making approach for IoT systems in uncertain, dynamic environments. We present a framework with perception, decision and execution layers to handle uncertainty in IoT systems. The perception layer senses the environment and system state. The decision layer employs an optimized deep Q-network algorithm (Ad-DQN) specifically designed to handle uncertain environments, enabling it to make informed decisions based on learned experiences. The execution layer implements the actions. We demonstrate the framework on an intelligent air conditioning system as a case study of an IoT system operating under uncertainty. The Ad-DQN based decision layer adapts the air conditioning control policy to maximize comfort while minimizing energy usage. Experiments show our method outperforms traditional DQN method in uncertain environments. © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

TESRGAN: Transformer Enhanced Super-Resolution Generative Adversarial Networks 4

TESRGAN: Transformer Enhanced Super-Resolution Generative Ad...

引用

4th International Conference on Neural Networks, information and Communication engineering, NNICE 2024

作者： Sun, Bohang Chen, Bo Tian, Yi Chen, Weiqin University of Electronic Science and Technology of China School of Information and Software Engineering Chengdu China University of Electronic Science and Technology of China Yibin Park Yibin China

ISBN: (纸本)9798350394375

With the rapid advancement of deep learning in image processing, Image Super-Resolution (ISR) has garnered extensive attention as a key technology. Recently, Transformer architectures have demonstrated immense potential across various domains, owing to their excellent ability to capture long-range dependencies. This paper explores a novel approach to incorporating Transformer architecture into the task of image super-resolution. We propose a new super-resolution model that fuses traditional Convolutional Neural Networks (CNNs) with Transformer architecture, particularly in the feature extraction and image reconstruction phases. The model includes a Residual in Residual Dense Block Network (RRDBNet) for initial feature extraction, followed by a novel module named DenseResidualTransformer for further enhancement of feature *** DenseResidualTransformer module combines the self-attention mechanism of Transformers with densely connected MLPs to capture global dependencies and complex textures in images. This module significantly enhances the expressiveness of feature maps through its multi-layered attention and MLP structure, while preserving the fine details of the original image. Despite the additional computational and memory overhead introduced by Transformers, our experimental results demonstrate superior image super-resolution performance on multiple standard datasets, with 31.67db of PSNR and 0.88 of SSIM, particularly in reconstructing high-frequency details and complex ***, we provide a detailed analysis of the application of Transformers in image super-resolution tasks, discussing the benefits and challenges it brings. The results show that incorporating Transformer architecture offers an effective way to enhance the performance of super-resolution models, especially in handling images with complex structures and textures. Our work not only demonstrates the potential of applying cutting-edge deep learning technologies to image s

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

Microcontroller Home-Based Security Reporting System using GPS-enabled technology 2

Microcontroller Home-Based Security Reporting System using G...

引用

2nd International Conference on Multidisciplinary engineering and Applied Science, ICMEAS 2023

作者： Ikwuazom, Callistus Tochukwu Onyeabor, Grace Amina Uche, Timothy Mustapha, Atiku Muhammad-Bello, Bilkisu Anunuso, Justice Chikezie Federal University of Technology Department of Information Technology Minna Nigeria Federal University of Technology Department of Information and Media Technology Minna Nigeria Nile University Department of Software Engineering and Information Technology Abuja Nigeria Federal University of Technology Department of Mechatronics Engineering Minna Nigeria

ISBN: (纸本)9798350358834

This study addresses the rising threat of theft and burglary by proposing a microcontroller-based security system utilizing GPS technology for enhanced home safety. Comprising a microcontroller unit, Neo-6M GPS module, and SIM800L communication module, the system enables real-time breach tracking and reporting with a user-friendly single-button activation. It ensures swift reporting of precise coordinates and nearby locations to a designated recipient without compromising security. Affordability, adaptability, and effectiveness distinguish this solution, overcoming existing security limitations. The results demonstrate accurate location tracking, rapid message transmission, and timely alerts. Future recommendations include solar panel integration and alternative coordinate conversion methods. In essence, this GPS-based Arduino microcontroller system strengthens home security, ensuring prompt response and homeowner safety. © 2023 IEEE.

关键词： Microcontrollers

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：