检索结果-内蒙古大学图书馆

4th IEEE Asian Conference on Innovation in Technology, ASIANCON 2024

作者： Amrutha, K. Shreekumar, T. Resmi, K.R. Vineetha, K.R. Dept. of Computer Science Bangalore India Mite Dept of Computer Science and Engineering Mangalore India

ISBN: (数字)9798350354218

ISBN: (纸本)9798350354218

Fatigue during driving significantly impairs a driver's reaction time, awareness, and decision-making abilities, leading to an increased risk of accidents. Recognising and mitigating driver fatigue is crucial for enhancing road safety and preventing potential collisions. This research introduces a non-intrusive method to reduce road accidents caused by driver fatigue. Recognising that accidents often occur due to lapses in driver alertness, the system utilises an affordable, high-quality webcam and dashcam. The approach involves extracting essential information through a multi-stage monitoring process to evaluate the driver's state thoroughly. The study includes a detailed analysis of webcam specifications, such as resolution, frame rate, and additional features. It also compares the traditional cascading technique with the advanced MediaPipe method, incorporating facial recognition, eye movement tracking, and head position analysis to detect driver fatigue accurately. © 2024 IEEE.

关键词： Eye movements

来源：评论

学校读者我要写书评

暂无评论

Land Cover Extraction from Satellite Imagery using U-Net Model 18

Land Cover Extraction from Satellite Imagery using U-Net Mod...

引用

18th INDIAcom;11th International Conference on Computing for Sustainable Global Development, INDIACom 2024

作者： Rani, K. Pushpa Sreedevi, Pogula Dastagiriah, C. Rao, K. Srinivas Subbaraju, G.V. Padmavathi, Jasti Mlr Institute of Technology Dept. of Computer Science and Engineering Hyderabad India G. Pulla Reddy Engineering College Dept. of Computer Science and Engineering Kurnool India Anurag University Dept. of Computer Science and Engineering Hyderabad India Scetw Dept. of Computer Science and Engineering Hyderabad India Hyderabad India

ISBN: (纸本)9789380544519

Satellite imagery offers extensive information that can be used for a variety of societal applications, from the number of buildings in a metropolis to the land cover types of a specific area. However, extracting such information is a difficult task. In the past, images were scanned manually by domain experts to extract features like buildings, infrastructure, and vegetation, which would take weeks or even months depending on the image size. To address this challenge, we trained our model using U-Net architecture, a deep learning model, because of its advantages in multiscale feature learning and faster processing. Data augmentation is done on the dataset in order to enhance the amount of data and prevent overfitting artificially. The trained model achieved an F1 score of 92% and an impressive precision score of 95%. This automated method can be scaled to large sets of data, reducing the need for human labeling. © 2024 Bharati Vidyapeeth, New Delhi.

关键词： Data augmentation Deep learning Machine learning Multiscale feature learning U-Net architecture

来源：评论

学校读者我要写书评

暂无评论

AAF-SCM: An Authenticated Framework for Supply Chain Management

AAF-SCM: An Authenticated Framework for Supply Chain Managem...

引用

2024 IEEE International Conference on Intelligent Systems and Advanced Applications, ICISAA 2024

作者： Roy, Prince Kumar, Rajneesh Morshed, Md Neaz Fairleigh Dickinson University Dept. of Applied Computer Science United States Dept. of Computer Science & Engineering India

ISBN: (纸本)9798331539948

The process of a supply chain involves a series of activities that distribute, assemble, and manage products, transferring them from the supplier to the end consumer. It operates as a complex, interconnected network regulated by supply and demand. Security in supply chain management is a crucial aspect of its overall security measures, focusing primarily on maintaining essential end-to-end protection. Without this, several attacks can be used to manipulate data and valuable information from the entire chain of networks. This paper explains how encrypted intermediates can secure the entire SCM by validating each intermediate using public-private key encryption. We also demonstrate and assess how the proposed AAF-SCM model can aid in tracing security breaches or unauthorized data tampering. We also validate this model against nefarious attacks like Fabrication, Assertion, Deletion, and Modification. Finally, we propose opportunities to develop innovative systems that enhance security through intermediary steps. © 2024 IEEE.

关键词： Supply chain management

来源：评论

学校读者我要写书评

暂无评论

Smart Agritech : An Enhanced Solution for Advanced Plant Disease Detection, Remediation, and Data-Driven Agriculture 2

Smart Agritech : An Enhanced Solution for Advanced Plant Dis...

引用

2nd IEEE International Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation, IATMSI 2024

作者： Rekha, K.S. Haridas, Aakash Dept. of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350360523

Plant diseases can have a detrimental effect on crop yield and quality, posing significant challenges to global food security. Early and accurate disease detection is essential for timely intervention and mitigation. In this study, we propose a novel approach for plant disease detection using a deep learning method based on a state-of-the-art convolutional neural network, ResNet9 architecture. The ResNet9 model is trained on a diverse dataset of plant images, including both healthy and diseased plants, representing different plant species and diseases. Our method leverages the power of deep learning to automatically learn discriminative features from plant images, enabling it to distinguish between healthy and diseased plants with a high degree of accuracy. We evaluate the performance of our model on a real-world dataset of plant images, and the results demonstrate its effectiveness in disease detection. The model achieves a high accuracy rate, indicating its potential for field deployment to assist farmers in monitoring and managing plant health. In conclusion, our study presents a promising solution for automated plant disease detection, providing farmers and agronomists with a practical tool to identify and combat plant diseases early, ultimately contributing to improving crop productivity and food security. © 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

Integrated IoT and Machine Learning Solutions for Precision Farming: Crop Recommendation and Leaf Disease Diagnosis 8

Integrated IoT and Machine Learning Solutions for Precision ...

引用

8th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), I-SMAC 2024

作者： Harish, M. Devi, J. Vimala Dept. of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350376425

The digital convergence of the Internet of Things and machine learning has therefore redefined precision agriculture with respect to productivity and sustainability. This work therefore proposes a smart agriculture system via the following IoT sensors: Soil Moisture, DHT, and NPK sensors, along with data storage in ThingSpeak cloud *** Similarly, farmers learn which plants are best to grow based on their projected data from machine learning algorithms. A convolutional neural network named ResNet was used for its control to instantly and correctly identify plant diseases in live mode. For the system's front end, HTML, CSS, and JavaScript were used while Python facilitated creation of the back end that provides users with an easy-to-use interface. It has achieved high accuracy levels in crop recommendation through models like Decision Tree, Naive Bayes, SVM, Logistic Regression, Random Forest and XGBoost among others have attained an accuracy of 90%, 99.09%, 97.95%, 95.27%, 99.09% and 99.31% respectively in crop recommendation. By ResNet model in the identification of leaf disease, a density of 99.2% was achieved. © 2024 IEEE.

关键词： Smart agriculture

来源：评论

学校读者我要写书评

暂无评论

Multiple Cancer Prediction with Image Analysis and Machine Learning 5

Multiple Cancer Prediction with Image Analysis and Machine L...

引用

5th IEEE International Conference on Computing, Power, and Communication Technologies, IC2PCT 2024

作者： Nithya Sree, N. Ramyadevi, R. Dept. of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350383522

Cancer, the second biggest cause of death globally, was recently discovered to pose a risk sickness for humans, despite early discovery not doing much to keep people from dying. Thus, efforts to give an ecologically friendly design with proven cancer-prevention estimations and means during the preliminary stages identification of cancer are critically needed. The growth of learning machine procedures have gotten better the cancer diagnosis sector by beating people in terms of both effectiveness and mistake rate. During the previous period, there certainly has seen a massive shift in the learning from machines supported tactics for separating and identifying separate cancerous tumors. This paper gives an outline of numerous forms of cancer detection processes that utilize learning algorithms alongside deep neural-based computers, in addition to a multitude of strategies, to process diverse data types. for finding illustrates and typical datasets have been employed in recent study. The objective of this endeavor is to put into practice machines instruction and algorithms that use deep learning to assess, rate, and fix the current improvements in cancer diagnosis and recognition for four types of cancer: brain, lung, kidney, and oral cancer. Various new methods were combined, and the results were examined using important performance measures such as accuracy, area under the curve, precision, sensitivity, and Dice score against standard datasets. These results will be discussed in future works. © 2024 IEEE.

关键词： cancer deep learning image processing oncology

来源：评论

学校读者我要写书评

暂无评论

Time Series Forecasting of Sales Data using Hybrid Analysis 5

Time Series Forecasting of Sales Data using Hybrid Analysis

引用

5th IEEE International Conference on Computing, Power, and Communication Technologies, IC2PCT 2024

作者： Rajasree, T. Ramyadevi, R. Dept. of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350383522

Forecasting of sales data based on time for businesses and organizations is absolutely an efficient thing to be done for the successful market trend analysis, and it will be an added advantage for the manufacturing sector to meet the business needs for an organization. Knowing about the future trends will be a crucial thing for sales and production, hence sales forecasting plays a vital role in achieving higher sales rate and thereby improving the efficiency of the businesses. Using machine learning methods like random forest, linear regression, XG-boosting, K Neighbors regression model, and Keras deep neural network regressor to predict sales for future demands with precision. This Forecasting approach is based on the product attributes, customer information, and various necessary parameters such as data related to product sales, past sales performance, customer demands according to time considering all these factors the analysis were done in the trained data. © 2024 IEEE.

关键词： Accuracy prediction Comparison Customer Needs Data analysis Machine learning methods Market Trend Analysis Model analysis Sales forecasting

来源：评论

学校读者我要写书评

暂无评论

Tail Optimality of the Nudge-M Scheduling Algorithm

引用

Performance Evaluation Review 2024年第2期52卷 21-23页

作者： Charlet, Nils Van Houdt, Benny Dept. Computer Science University of Antwerp Antwerp Belgium

Recently it was shown that the response time of First-Come- First-Served (FCFS) scheduling can be stochastically and asymptotically improved upon by the Nudge scheduling algorithm in case of light-tailed job size distributions. Such improvements are feasible even when the jobs are partitioned into two types and the scheduler only has information about the type of incoming jobs (but not their size). In this paper we introduce Nudge-M scheduling, where basically any incoming type-1 job is allowed to pass any type-2 job that is still waiting in the queue given that it arrived as one of the last M jobs. We prove that Nudge- M has an asymptotically optimal response time within a large family of Nudge scheduling algorithms when job sizes are light-tailed. Simple explicit results for the the prefactor of Nudge-M are derived as well as explicit results for the optimal parameter M. An expression for the prefactor that only depends on the type-1 and type-2 mean job sizes and the fraction of type-1 jobs is presented in the heavy traffic setting. © 2024 Copyright is held by the owner/author(s).

关键词： Scheduling algorithms

来源：评论

学校读者我要写书评

暂无评论

NLP based Text Summarization Techniques for News Articles 2

NLP based Text Summarization Techniques for News Articles

引用

2nd IEEE International Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation, IATMSI 2024

作者： Kumaran, B. Logesh Ravindran, N.V. Dept. of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350360523

This defines a news summarization web application using Streamlit, allowing users to access and read news articles from various sources. Here's an abstract of what the project does the necessary Python libraries are imported, including Streamlit for the web application, BeautifulSoup for web scraping, PIL for image processing, and Newspaper for article extraction. Three functions are defined for fetching news based on different criteria: fetch-news-search-topic for searching news based on a topic, fetch-top-news for fetching the top news, and fetch-category-news for fetching news based on a specific category. A function, fetch-news-poster, is defined to fetch and display the image associated with each news article. The display-news function is defined to present the news articles on the Streamlit web application, along with their associated images, summaries, and publication dates. The run function configures the Streamlit application layout and functionality, including options for selecting news categories, displaying trending news, choosing favorite topics, and searching for specific topics. The application displays a title, logo, and various news categories, allowing users to select their preferred category and view the corresponding news articles. Overall, this application provides a convenient way for users to access and read summarized news articles based on their preferences. © 2024 IEEE.

关键词： Image processing

来源：评论

学校读者我要写书评

暂无评论

A Semi-Supervised Approach For Detecting Agricultural Land Reduction In Bangladesh Using Satellite Images

A Semi-Supervised Approach For Detecting Agricultural Land R...

引用

2024 IEEE International Conference on Computing, Applications and Systems, COMPAS 2024

作者： Shafin, Wahid Mahmood Ahsan, Sk. Md. Masudul Dept. of Computer Science and Engineering Khulna Bangladesh

ISBN: (纸本)9798331529765

Recently, remote sensing change detection has significantly improved because of greater access to global satellite images and developments in satellite technology. Several CNN-based techniques have demonstrated exceptional precision. Detecting the amount of agricultural area that has been reduced is a type of change detection problem that can easily be solved using deep learning methods on satellite data. But the majority of deep learning methods have been specifically created for high-resolution images. This data lacks global coverage, consists of at most 3 to 4 bands, and is costly. The Sentinel-2 satellite, which was launched in 2015, offers medium-resolution multi-spectral image data consisting of 14 bands and provides free global coverage. Having more bands enhances the capabilities for model analysis. But there is a lack of labeled satellite data. This research proposes a semi-supervised method for generating ground truth by employing a multi-step procedure. This technique began with semi-supervised classification to label the images, followed by a sequence of refinement processes to enhance the accuracy of the ground truth mask. The mask was created using the XGBoost machine learning technique. The dataset was assessed using the output images generated by the trained model. Detecting changes in low-resolution image may be difficult, but proposed method will greatly streamline the procedure. Applying this approach revealed an approximately 8.35% decrease in agricultural land area inside the test image area between 2018 and 2022. In the test area of 237.77 square kilometers, the reduced area measures approximately 19.861 square kilometers. © 2024 IEEE.

关键词： Self-supervised learning

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：