检索结果-内蒙古大学图书馆

Harnessing Deep Learning and Time Series Models for Accurate Global Solar Radiation Prediction

Procedia computer science 2025年 259卷 98-107页

作者： K. Meena A. Vadivel Tanvir Habib Sardar Arnav Kotiyal Guru Prasad M S Utsav Kumar Department of Computer Science and Engineering School of Engineering Dayananda Sagar University Bengaluru - 562112 India Department of Computer Applications Graphic Era (Deemed to be University) Dehradun India

For applications such as weather forecasting, power grid management, and solar energy integration, accurate solar radiation prediction is essential. Using real-time data from the EU science Hub’s Climate Monitoring Satellite Application Facility (CM SAF), this research examines the efficacy of several time series models for hourly solar radiation prediction. The data are subjected to stationarity testing using the Augmented Dickey-Fuller (ADF) test prior to the models being applied. This study uses well-known time series models, including Vector Auto-regression (VAR), Linear Regression, and Autoregressive Integrated Moving Average (ARIMA). The performance of the proposed model is evaluated using Mean Square Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), R-squared, and Mean Absolute Percentage Error (MAPE). It is found that Vector Auto-regression (VAR) is encouraging for predicting solar radiation on hourly basis with least amount of overall error. This analysis has used residual error inspection, error distribution analysis and sample accuracy evaluation using MAPE. This paper highlights the importance of VAR on using time series model for predicting solar radiation.

关键词： Solar Radiation Prediction Time Series Models Autoregressive Integrated Moving Average (ARIMA) Vector Autoregressive (VAR) Regression Error Metrics performance analysis

来源：评论

学校读者我要写书评

暂无评论

VoteBlock - A Decentralized Online Voting Solution with Blockchain

VoteBlock - A Decentralized Online Voting Solution with Bloc...

引用

International Conference on Trends in Electronics and Informatics (ICEI)

作者： Ms. P. Santhiya S. Arshik P. Rajendra Prasanth V. Ramesh Kumar S. Santhosh Department of Computer Science and Engineering Builders Engineering College India

ISBN: (数字)9798331544607

ISBN: (纸本)9798331544614

Traditional voting systems, both paper and electronic, suffer from major security, transparency, and fraud-prevention challenges. Paper ballots are vulnerable to manipulation and logistical concerns, whereas electronic voting machines may be hacked into and manipulated. Centralized systems also create problems of voter anonymity, accessibility, and auditability. VoteBlock, an online voting system built on blockchain technology, takes advantage of the decentralized and immutable features of blockchain. VoteBlock utilizes a distributed ledger to prevent single points of failure, such that no single entity can modify or manage the voting process. Every vote is encrypted and written as a transaction on the blockchain, with real-time verifiability at no cost to voter privacy. Multi-factor authentication is used to protect access and keep unauthorized voting at bay. The open architecture makes it possible for election officials and auditors to validate results cost-effectively and reliably. VoteBlock was prototyped and tested under various conditions to measure performance metrics including transaction speed, network latency, and security scalability. The testing proved that VoteBlock successfully inhibits double voting and tampering with votes, providing an elevated solution that heightens the security, transparency, and credibility of contemporary voting systems.

关键词： Privacy Translation Scalability Smart contracts User interfaces Real-time systems Blockchains Electronic voting Homomorphic encryption Testing

来源：评论

学校读者我要写书评

暂无评论

Towards automated and reliable lung cancer detection in histopathological images using DY-FSPAN: A feature-summarized pyramidal attention network for explainable AI

引用

Computational Biology and Chemistry 2025年 118卷 108500页

作者： Banerjee, Tathagat Department of Computer Science and Engineering Indian Institute of Technology Patna India

Medical image classification is critical for accurate disease diagnosis, necessitating models that balance performance and interpretability. This study presents Dilated Y-Block-based Feature Summarized Pyramidal Attention Network (DY-FSPAN), a deep learning framework designed for robust feature extraction and classification. The architecture incorporates Y-blocks and attention mechanisms to enhance spatial feature representation while maintaining receptive field coherence. The proposed model achieves a classification accuracy of 98.5 %, surpassing existing approaches such as convolutional block attention networks, adversarial learning models, and multi-output 3D CNNs. To validate the efficacy of DY-FSPAN, we conduct an extensive experiment, including comparative benchmarking against state-of-the-art methods, robustness assessments, and ablation studies. The model's structural improvements are tested through various configurations to assess the impact of key components, confirming the contribution of attention mechanisms to performance enhancement. Grad-CAM analysis was employed to visualize learned feature maps, highlighting the model's focus on diagnostically relevant regions, thereby improving trust in AI-driven medical decision-making. From an explainable AI perspective, the proposed framework achieves superior classification accuracy and enhances interpretability, addressing a crucial requirement in medical imaging applications. The qualitative and quantitative analyses demonstrate that DY-FSPAN effectively localizes disease-specific features, making it a suitable tool for clinical use. The findings suggest that integrating attention-based architectures with optimized feature selection can significantly advance automated medical diagnosis. The model's ability to improve diagnostic reliability while maintaining transparency underscores its potential for real-world deployment in healthcare settings. © 2025 Elsevier Ltd

关键词： Neuroimaging

来源：评论

学校读者我要写书评

暂无评论

Optimizing Task Allocation in Heterogeneous Agent Manufacturing Systems 25th

Optimizing Task Allocation in Heterogeneous Agent Manufactur...

引用

25th International Conference on Parallel and Distributed Computing, Applications and Technologies, PDCAT 2024

作者： Yu, Qi Di, Kai Jiang, Yichuan Chen, Dan School of Cyber Science and Engineering Southeast University Jiangsu Nanjing211189 China School of Computer Science and Engineering Southeast University Jiangsu Nanjing211189 China College of Electronics and Information Engineering Beibu Gulf University Guangxi Qinzhou535000 China

ISBN: (纸本)9789819642069

With the increasing integration of AGVs (Automated Guided Vehicles) and Robot Arms in manufacturing systems, traditional scheduling approaches that handle them separately often lead to inefficiencies and poor coordination. To overcome these limitations, we proposes a concise method based on temporal logic and hybrid dynamic programming to optimize the scheduling of heterogeneous agent systems. By accurately modeling the state transitions and timing constraints of both AGVs and Robot Arms, and applying a hybrid dynamic programming framework, the method achieves global optimization in task allocation. The results show significant improvements in task completion time over conventional methods, offering a streamlined solution for multi-agent scheduling in intelligent manufacturing environments. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Global optimization

来源：评论

学校读者我要写书评

暂无评论

IOT Based Plant Growth Monitoring and Ideal Condition Detection System

IOT Based Plant Growth Monitoring and Ideal Condition Detect...

引用

Disruptive Technologies (ICDT), International Conference on

作者： Bidur Gupta Abhinav Singh Akash Bansal Anik Agarwal Rekha Baghel Computer Science Ajay Kumar Garg Engineering College Ghaziabad India Computer Science & Engineering Ajay Kumar Garg Engineering College Ghaziabad India

ISBN: (数字)9798331519582

ISBN: (纸本)9798331519599

In recent times, the Internet of Things (IoT) has inched itself as an evolutionary technology in agriculture as it allows for managing and controlling the growth conditions of the plants in an optimal way. This paper demonstrates the features of an IoT based system for effective plant growth monitoring along with ideal condition detection. The set of sensors embedded in the system incorporates measuring devices that capture and send the temperature, humidity, soil moisture content and light intensity to a central processing unit. The system sets and analyzes the data cloud along with AI algorithms for efficient agricultural activities and systems. This study focuses on the system design, its data gathering procedures, and decision processes, and their potential in smart farming and urban gardening. The experiments, conducted within the framework of the given concept showed that the system was able to operate within ideal conditions and therefore when changes occur, it initiates an action that helps avoid resource losses and assist in improving the yield. It reiterates the importance of IoT in world of agriculture and the quest for sustainability in modern farming practices.

关键词： Temperature sensors Temperature measurement Smart agriculture Accuracy Predictive models Sensor systems Internet of Things Reliability Sustainable development Monitoring

来源：评论

学校读者我要写书评

暂无评论

Transfer Learning-Based Fault Classification Methods for Solar Photovoltaic Modules: A Comparative Analysis 6th

Transfer Learning-Based Fault Classification Methods for Sol...

引用

6th International Conference on Intelligent Communication, Control and Devices, ICICCD 2024

作者： Supriya Shukla, Ashutosh Manchanda, Mahesh Department of AI and ML COER University Roorkee247667 India Electrical Cluster School of Engineering UPES Dehradun India Department of Computer Science and Engineering GEHU University Dehradun India

ISBN: (纸本)9789819783281

India’s reliance on fossil fuels to meet its energy generation demands has a negative impact on both the environment and public health. In the present energy transition, photovoltaic (PV) technologies have become more widely accepted for commercial use, achieved significant progress in technology, and have a major role to play in reducing the harmful environmental effects of fossil fuel-based power generation. Soiling research on solar PV has notably increased in recent years due to its critical role in reducing the performance of solar PV cells. Therefore, to guarantee the amount of power yield, efficient monitoring of the soiling is crucial. It is difficult to manually analyse soiling severity on the panel images due to the non-uniformity of the type and amount of soiling faults. Deep learning models have been successfully applied to the analysis of solar panel images and soiling categorization;nevertheless, this approach may require a significant amount of training time and may lead to gradient descent. To tackle these training issues, we propose a comparative study of two pre-trained neural network architectures, namely, MobileNetV3small and RestNet50, on a publicly available dataset of 875 images of six solar PV fault classes, namely, clean, dust, bird-drop, electrical damage, physical damage, and snow-covered. The experimental results show that MobileNetV3small achieved a better performance of 98%. The results show that MobileNetV3small obtained a promising result of 11% higher classification accuracy than ResNet50, with an accuracy of 86.6%. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Electric losses

来源：评论

学校读者我要写书评

暂无评论

Automated Customer Feedback Generation Using Facial Expression Through OpenCV 6th

Automated Customer Feedback Generation Using Facial Expressi...

引用

6th International Conference on Smart Computing and Informatics, SCI 2024

作者： Ayushi Arora, Deepak Department of Computer Science and Engineering Amity School of Engineering and Technology Amity University Uttar Pradesh Lucknow Campus Lucknow India

ISBN: (纸本)9789819619801

A business needs to work on the right problems to be able to grow. These problems can only be provided by the people who are using the product or service made by the business. Accurate customer feedback is what allows a business to set its priorities straight. Thus, in this paper, we have attempted to make a simple and easy-to-use tool from already existing resources that will provide real-time customer reviews to business owners which will help them in improving their service. The result of the model execution includes the performance of various concepts that are face detection, face recognition, emotion detection, storage in the database and calculations to find the positive (happy and surprise), negative emotion (sad, fear, angry, and disgust) and neutral (neither positive nor negative). For understanding the functioning of the model, OpenCV and CNN fundamentals have been explained in detail in the paper. This paper concludes by discussing the future scopes of the tool created. In the past, CCTV cameras were used for security only, but now these can be used to get customers’ real-time reviews also which will be very beneficial to them to improve their services. This will allow them to grow and compete in the future, where survival is going to depend on how well a business uses AI in its day-to-day operations. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

AGRI PREDICT: AI based Crop Advisory System for Intelligent Agriculture

AGRI PREDICT: AI based Crop Advisory System for Intelligent ...

引用

2025 International Conference on Visual Analytics and Data Visualization, ICVADV 2025

作者： Anand, K. Adarsh, R. Akshay Sundar, S. Computer Science and Engineering Rajalakshmi Engineering College Chennai India

ISBN: (数字)9798331521394

ISBN: (纸本)9798331521394

The Agri Predict will enhance the farmer's ability to implement highly informative interpretative agricultural practices. The use of machine learning algorithms gives accurate information regarding the nutrients required, water required and the presence of pests. The state of the soil is defined with reference to factors including acidity, water availability, and nutrients;this direction responds to individual needs of certain crops. By so doing it offers detailed analysis this enables the farmers to address the arising issues in order to improve the general soil health and the yields of crops in the farmland. In addition to providing suggestions, the system also displays forecasts to support decision making in the long run. In a manner of anticipating crop productions and the threats posed by unfavorable climate conditions or diseases, the system enables farmers make an early reaction that results in minimal crop loss and keeps resource utilization to a bare minimum. This is a sustainable farming since the system is able to analyze data relative to history and environment that helps in saving water and fertilizer usage, crop health and costs. In conclusion, this technology can so greatly fit between conventional agriculture and the advanced agriculture of precision agriculture to increases agricultures' sustainability and resilience. © 2025 IEEE.

关键词： Agricultural robots

来源：评论

学校读者我要写书评

暂无评论

Forecasting land use changes in crop classification and drought using remote sensing

引用

Journal of Arid Land 2025年第5期17卷 575-589页

作者： Mashael MAASHI Nada ALZABEN Noha NEGM Venkatesan VEERAMANI Sabarunisha Sheik BEGUM Geetha PALANIAPPAN Department of Software Engineering College of Computer and Information SciencesKing Saud UniversityRiyadh 11451Saudi Arabia Department of Computer Sciences College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityRiyadh 11671Saudi Arabia Department of Computer Science Applied College at MahayilKing Khalid UniversityAbha 61421Saudi Arabia Department of Civil Engineering University College of EngineeringAnna UniversityAriyalur 621731India Department of Biotechnology P.S.R.Engineering CollegeSivakasi 626140India Department of Electronics and Communication Engineering School of Engineering and TechnologyDhanalakshmi Srinivasan UniversitySamayapuram 621112India

Challenges in land use and land cover(LULC)include rapid urbanization encroaching on agricultural land,leading to fragmentation and loss of natural ***,the effects of urbanization on LULC of different crop types are less *** study assessed the impacts of LULC changes on agriculture and drought vulnerability in the Aguascalientes region,Mexico,from 1994 to 2024,and predicted the LULC in 2034 using remote sensing data,with the goals of sustainable land management and climate resilience *** increasing urbanization and drought,the integration of satellite imagery and machine learning models in LULC analysis has been underutilized in this *** Landsat imagery,we assessed crop attributes through indices such as normalized difference vegetation index(NDVI),normalized difference water index(NDWI),normalized difference moisture index(NDMI),and vegetation condition index(VCI),alongside watershed delineation and spectral *** random forest model was applied to classify LULC,providing insights into both historical and future *** indicated a significant decline in vegetation cover(109.13 km^(2))from 1994 to 2024,accompanied by an increase in built-up land(75.11 km^(2))and bare land(67.13 km^(2)).Projections suggested a further decline in vegetation cover(41.51 km^(2))and continued urban land expansion by *** study found that paddy crops exhibited the highest values,while common bean and maize performed *** analysis revealed that mildly dry areas in 2004 became severely dry in 2024,highlighting the increasing vulnerability of agriculture to climate *** study concludes that sustainable land management,improved water resource practices,and advanced monitoring techniques are essential to mitigate the adverse effects of LULC changes on agricultural productivity and drought resilience in the *** findings contribute to the understanding of how remote sensing can be effectively used for long-t

关键词： land use and land cover(LULC) crop attributes drought vulnerability machine learning models remote sensing

来源：评论

学校读者我要写书评

暂无评论

A Systematic Review: Development of AI Based computer Vision Scrap Sorting System for Metal Scrap

A Systematic Review: Development of AI Based Computer Vision...

引用

2025 International Conference on Multi-Agent Systems for Collaborative Intelligence, ICMSCI 2025

作者： Gedam, Pragati B. Khan, Atiya Purohit, Neha Jha, V.K. G H Raisoni College of Engineering Department of Computer Science and Engineering Nagpur India Jawaharlal Nehru Aluminium Research Development and Design Centre Department of Aluminium Electrolysum Nagpur India

ISBN: (纸本)9798331509828

The metals recycling industry has undergone a revolution thanks to the quick development of computer vision and artificial intelligence (AI), which have made it possible to sort metal trash using efficient and automated techniques. The existence of pollutants, the requirement for high-speed processing without sacrificing precision, and variations in scrap form, size, and texture are some of the ongoing difficulties. Though they provide strong feature extraction capabilities, current methods like Convolutional Neural Networks (CNNs), Scale-Invariant Feature Transform (SIFT), and Histogram of Oriented Gradients (HOG) frequently necessitate substantial preprocessing and sizable, precisely labeled datasets in order to integrate them with classification models like Support Vector Machines (SVM) and Artificial Neural Networks (ANN). Furthermore, scalability and resilience in real-world scenarios continue to be major challenges. An AI-driven computer vision system is proposed in this work for identifying and sorting different kinds of metal trash, such as alloys made of copper, iron, and aluminium. Utilizing sophisticated feature extraction techniques and combining SVM and ANN models, the system seeks to maximize classification performance while tackling issues with operational effectiveness and dataset variability. YOLO LabelImg makes annotations easier by producing accurate bounding boxes, which are essential for tasks involving object identification and categorization. The study emphasizes the value of integrating models to increase accuracy and investigates how AI-powered solutions might raise the efficiency, dependability, and affordability of applications for sorting metal waste. © 2025 IEEE.

关键词： Convolutional neural networks

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：