检索结果-内蒙古大学图书馆

Mobile Computing and Sustainable Informatics (ICMCSI), International Conference on

作者： K Navya Sree Mancharla Rakesh Reddy Saraswathi. S Department of Computer science and engineering Specialization with AI & ML Sathyabama Institute of Science and Technology Chennai India Department Computer science and engineering Sathyabama Institute of Science and Technology Chennai India

ISBN: (数字)9798331522667

ISBN: (纸本)9798331522674

air pollution is a significant threat to human health and the environment. Accurate air quality forecasting is essential for effective mitigation strategies, including public health advisories, emission control measures, and policy interventions. This research focuses on the development of an advanced air quality forecasting system using machine learning techniques. The system uses historical data on pollutants such as PM2.5, NO2, and O3, along with meteorological parameters, to predict future air quality levels. The model is enhanced with the inclusion of sophisticated machine learning algorithms to better capture the intricate spatiotemporal patterns and enhance the accuracy of forecasting. The system may potentially provide real-time air quality forecasts that enable proactive measures for protecting public health and inform decisions for environmental policy. This research contributes to sustainable and resilient urban environments by providing valuable insights into air quality dynamics and supporting effective air pollution mitigation strategies.

关键词： Accuracy Atmospheric measurements Prevention and mitigation Urban areas Weather forecasting air pollution Pollution measurement Forecasting Public healthcare Diseases

来源：评论

学校读者我要写书评

暂无评论

An Improved Wind Driven Optimization and Factored Conditional Restricted Boltzmann Machine for Electric Load forecasting 2

An Improved Wind Driven Optimization and Factored Conditiona...

引用

2nd IEEE International Conference on Networks, Multimedia and Information Technology, NMITCON 2024

作者： Deepa, N. Adnan, Myasar Mundher Naveen, I.G. Kumar, Gotte Ranjith Palakurthy, Deepthi Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Department of Computer Science and Engineering Chennai India The Islamic University College of Technical Engineering Department of Computers Techniques Engineering Najaf Iraq Nitte Meenakshi Institute of Technology Department of Ece Bengaluru India Sr University School of Computer Science & Artificial Intelligence Warangal India Gokaraju Rangaraju Institute of Engineering and Technology Bachupally Department of Ai & Ml Hyderabad India

ISBN: (纸本)9798350372892

Now-a-days, because of the expanding effects of both human behavior and the environment, the consumption of electric power is increasing rapidly in our century. It is used in decision-making and power grid operation;electric load forecasting is significant. The complex signal that is electric load profile arises from the nonlinear and stochastic behavior of users. The suggested model is a comprehensive framework that includes modules for training, forecasting, feature selection, and data preprocessing and optimization. An enhanced version of the mutual information approach, the Distance-Based Synthetic Minority Oversampling Technique (D-SMOTE) used for data pre-processing and feature selection module. It is used to choose abstractive features from historical data. The Factored Conditional Restricted Boltzmann Machine (FCRBM), a deep learning model enhanced by learning to estimate the future electric load, is used for training and forecasting module. The optimization module used for fine tuning the adjustable parameters of model is based on Improved Wind Driven Optimization (IWDO) algorithm. The evaluation metric used in this research is Mean Absolute Percentage Error (MAPE). The average MAPE value of IWDO algorithm is 0.4125% better than that of existing methods like Temporal Inception Convolution Network using Multi-Head Attention (TICN-Att), Residual Convolutional Neural Network (RCNN) and Multilayered Long Short-Term Memory (ml-LSTM) and Feature Preprocessing, Multi-Layer Perceptron and Genetic Wind-Driven Optimization (FPP-mlP-GWDO) algorithms. © 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

An Alternative Deep Learning Approach for Early Diagnosis of Malaria

An Alternative Deep Learning Approach for Early Diagnosis of...

引用

International Conference on Computing and Networking Technology (ICCNT)

作者： Jayavrinda Vrindavanam E Mary Jasmine Gaurav Kamath Anirudh Narayanan Department of Computer Science and Engineering(AI & ML) Dayananda Sagar University Bengaluru India Department of Computer Science and Engineering Christ University Bengaluru India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

Considering the malaria disease-related moralities prevailing mainly in underdeveloped countries, early detection and treatment of malaria must be an essential strategy for lowering morbidity and fatality rates. Detection of Malaria using traditional investigation methods through blood samples and expert judgments was found to be time-consuming. In this paper, the authors introduced a Machine Learning automated system to eliminate the need for human intervention, which in turn enables early detection of malaria. The study has used various Deep Learning techniques such as traditional Convolutional Neural Network (CNN), VGG19, ConvNeXtXLarge, ConvNeXtBase, ConvNeXtSmall, ConvNeXtTiny, InceptionResnetv2, Xception, DenseNet169, EfficientNetB7, MobileNet, ResNet50, and NasNetLarge as base models. These models have been trained and tested with microscopic blood smear images dataset and observed that ConvNeXtXLarge detects malarial parasites with an accuracy of 96%. The proposed method outperforms the existing approaches in terms of both accuracy and speed. The findings of this work can contribute to the development of more accurate and efficient automated systems for early detection of Malaria.

关键词： Deep learning Accuracy Malaria Microscopy Convolutional neural networks Blood Residual neural networks

来源：评论

学校读者我要写书评

暂无评论

Enhancing Radiology Report Interpretation with Large-Scale Language Models: A Two-Stage Fine-Tuning Approach 27

Enhancing Radiology Report Interpretation with Large-Scale L...

引用

27th International Conference on Advanced Communications Technology, ICACT 2025

作者： Pi, Sun-Woo Park, Myeong-Soo Lee, Byoung-Dai Department of Computer Science Graduate School Kyonggi University Suwon Korea Republic of Division of AI and Computer Engineering Kyonggi University Suwon Korea Republic of

ISBN: (纸本)9791188428137

Radiology reports contain complex medical terminology and specialized knowledge, making them difficult for both patients and medical professionals to interpret. This study aims to address this challenge by developing a large-scale language model specifically designed for interpreting chest radiology reports. We focus on four key natural language processing (NLP) tasks—summarization, paraphrasing, abbreviation interpretation, and question answering—using a synthetic dataset derived from the MIMIC-CXR reports and GPT-3.5 Turbo. To enhance the model’s performance, we propose a two-stage supervised fine-tuning (SFT) process, incorporating real-world medical data from PubMedQA and MedQA, in addition to the synthetic dataset. The resulting models, Model-1 and Model-2, were evaluated based on accuracy, conciseness, and clarity, using test data not seen during training. Experimental results demonstrated that the proposed two-stage SFT method achieved strong performance across all four tasks, providing comparable performance to models such as GPT-3.5, Bard, Llama2, and MedAlpaca in key evaluation metrics, despite using a relatively smaller number of parameters. These findings suggest that synthetic data, when combined with domain-specific datasets, can significantly improve the interpretive capabilities of large-scale language models in the medical domain. Copyright 2025 Global IT Research Institute (GIRI). All rights reserved.

关键词： Radiology

来源：评论

学校读者我要写书评

暂无评论

Hybrid RF-DNN-LSTM Ensemble for Short-Term Solar Energy Forecasting

Hybrid RF-DNN-LSTM Ensemble for Short-Term Solar Energy Fore...

引用

International Conference on Inventive Computation Technologies (ICICT)

作者： Indumathi V V T Ram Pavan Kumar M Srilakshmi Ramya S Ch Harika Divya R Sahith Vellaturi Gopikrishna Department of CSE (AI&ML) B V Raju Institute of Technology Narsapur Medak Telangana India Department of Computer Science Kakaraparti Bhavanarayana College Vijayawada Andhra Pradesh India Department of CSE Koneru Lakshmaiah Education Foundation Vaddeswaram Andhra Pradesh India Department of AI&ML Aditya University Surampalem Dept of CSE CVR College of Engineering Hyderabad Dept of IT MLR Institute of Technology Hyderabad

ISBN: (数字)9798331512248

ISBN: (纸本)9798331512255

Given the drastic shift of global sentiment towards renewable energy, it becomes incredibly important to match supply with demand. However the highly variable nature of weather makes it difficult to accurately predict the output of a solar power plant. In this paper, solved this problem by using an ensemble model consisting of both machine learning and neural networks (NN) as base models to forecast the amount of energy that needs to be produced by a solar plant over a short-term time horizon, which in our case will be 0 minute (immediate), 5 minute, 30 minute and 90 minute. Each base model is fine tuned to encourage high diversity and low correlation to improve prediction accuracy. The expected stability or generalization from RF-DNN combined with the memory retention capability of the LSTM network should provide an ideal predictor for time series forecasting of a stochastic process like weather.

关键词： Renewable energy sources Time series analysis Weather forecasting Stochastic processes Solar energy Predictive models Stability analysis Forecasting Long short term memory Random forests

来源：评论

学校读者我要写书评

暂无评论

A Trustworthy Product Rating System Based on the Blockchain with E-Commerce Business Model

A Trustworthy Product Rating System Based on the Blockchain ...

引用

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

作者： Kranthi, Alapati Smitha Ranjith Kumar, Gotte Tejasri, Nimmagari Raviprakash Siddhanti, Prateeksha Koneru Lakshmaiah Education Foundation Department of Computer Science and Engineering Vaadeswaram India Sr University School of Computer Science & Artificial Intelligence Warangal India Malla Reddy Engineering College for Women Dhulapally It Department Hyderabad India Kalpataru Institute of Technology Department of Computer Science and Engineering Tiptur India Nitte Meenakshi Institute of Technology Yelahanka Department of Ai and Ml Bengaluru India

ISBN: (纸本)9798350313413

This article covers the difficulties that customers and retailers encounter while searching for and getting real items at reasonable costs in the internet marketplace. While the development of e-commerce has made it simpler than ever for people to purchase from the comfort of their own homes, it has also resulted in an explosion of phoney reviews and rating manipulation, causing shoppers to lose trust in both the reviews they read and the rating systems themselves. This article offers a method based on blockchain technology to provide e-commerce enterprises with a trustworthy and transparent product rating system. The recommended method for evaluating things in the paper is based on blockchain technology, which the study believes provides e-commerce enterprises with a trustworthy and transparent rating system. According to the outcome analysis, 90% of users thought the blockchain-based grading system was easier to use and more straightforward than prior ones. © 2023 IEEE.

关键词： Blockchain technology Decentralization E-commerce Legitimate products Market disruptions Product Grade System Product quality Smart contract

来源：评论

学校读者我要写书评

暂无评论

An Optimization Model for Logistics Services in E-Commerce Market 2

An Optimization Model for Logistics Services in E-Commerce M...

引用

2nd International Conference on Data science and Information System, ICDSIS 2024

作者： Sivaparthipan, C.B. Alabdeli, Haider Harshitha, P. Nagendar, Y. Kulkarni, Girija G. Tagore Institute Of Engineering And Technology Department Of Cse Salem India The Islamic University College Of Technical Engineering Department Of Computers Techniques Engineering Najaf Iraq Nitte Menashaki Institute Of Technology Department Of Ai Ml Bengaluru India Sr University School Of Computer Science And Engineering Telangana Warangal India SacramentoCA United States

ISBN: (纸本)9798350381665

The E-commerce market is the most hype and growth sector in the economic, and many countries showing interest on e-commerce to develop the economy. In e-commerce the logistic is the key factor to consider for the profitable growth so focus on the reverse logistic for efficient distribution and increase profit. The reverse logistic is highlighted in this study for decrease the distribution cost and increases the distribution efficiency for growth of the e-commerce market. The study proposes the Hierarchical Density-Based Spatial Clustering of Application with noise (HDBSCAN) clustering algorithm for analyzing the customer behavior to solve route optimization problem. Then mathematical programming model was built for reducing the damages cost it includes fixed cost, green cost, cargo cost. Thereafter, the genetic algorithm was used to solve problem of the model and achieved 93.50% accuracy. The proposed method results show the promising results in solving the route optimization problem with consideration of the customer priority. Moreover, the propose method is greatly used for enterprises in reverse logistics to minimize the cost and time. © 2024 IEEE.

关键词： Electronic commerce

来源：评论

学校读者我要写书评

暂无评论

Improved AO based Classification Framework for Eye Diseases 2

Improved AO based Classification Framework for Eye Diseases

引用

2nd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2024

作者： Saju, Binju Asha, V. Mathew, Jincy C Sangma, Sengcheng Ghosh, Shouvik Sivaguru, K. Adi Shankara Institute of Engineering & Technology Department of Computer Science - AI Engineering Kerala Kalady India New Horizon College of Engineering Master of Computer Applications Bengaluru India

ISBN: (纸本)9798350327533

A sensory organ that reacts to visible light, the human eye is a component of the sensory nervous system. A new approach is needed since, although physical detection of the eye condition is still a possibility, it is challenging and time-consuming. The study recommends a hybrid paradigm to classify various eye illnesses. Prior to further processing, pictures are first reduced in size, made grayscale, and noise-free using a combination of the Weiner and Median filters. Histogram equalization based on a Gaussian Mixture is also used to enhance pictures. Picture features are recovered with the aid of a thick convolutional neural network. An improved Aquila optimized ResNet101 model is used for classification. The effectiveness of the models is contrasted with that of related studies in the literature. A F1 score of 98.18%, accuracy of 99.2%, sensitivity of 98.9%, specificity of 98.91%, and precision of 98% were attained by the suggested model. © 2024 IEEE.

关键词： DCNN Diabetic retinopathy Gaussian Mixture IAO ResNet

来源：评论

学校读者我要写书评

暂无评论

EVA2.0:Investigating Open-domain Chinese Dialogue Systems with Large-scale Pre-training

引用

Machine Intelligence Research 2023年第2期20卷 207-219页

作者： Yuxian Gu Jiaxin Wen Hao Sun Yi Song Pei Ke Chujie Zheng Zheng Zhang Jianzhu Yao Lei Liu Xiaoyan Zhu Minlie Huang The Conversational AI Group Tsinghua UniversityBeijing 100084China Department of Computer Science and Technology Tsinghua UniversityBeijing 100084China Department of Electrical Engineering and Computer Science York UniversityToronto M3J1P3Canada

Large-scale pre-training has shown remarkable performance in building open-domain dialogue ***,previous works mainly focus on showing and evaluating the conversational performance of the released dialogue model,ignoring the discussion of some key factors towards a powerful human-like chatbot,especially in Chinese *** this paper,we conduct extensive experiments to investigate these under-explored factors,including data quality control,model architecture designs,training approaches,and decoding *** propose EVA2.0,a large-scale pre-trained open-domain Chinese dialogue model with 2.8 billion parameters,and will make our models and codes publicly *** and human evaluations show that EVA2.0 significantly outperforms other open-source *** also discuss the limitations of this work by presenting some failure cases and pose some future research directions on large-scale Chinese open-domain dialogue systems.

关键词： Natural language processing deep learning(DL) large-scale pre-training dialogue systems Chinese open-domain conversational model

来源：评论

学校读者我要写书评

暂无评论

Competition on robust deep learning

引用

National science Review 2023年第6期10卷 13-15页

作者： Yinpeng Dong Chang Liu Wenzhao Xiang Hang Su Jun Zhu Department of Computer Science and Technology Institute for AI Tsinghua-Bosch Joint ML Center THBI Lab BNRist Center Tsinghua University Institute of Image Communication and Networks Engineering in the Department of Electronic Engineering (EE) Shanghai Jiao Tong University Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Peng Cheng Laboratory Pazhou Laboratory (Huangpu)

PROBLEM In recent years,the rapid development of artificial intelligence (ai) technology,especially machine learning and deep learning, is profoundly changing human production and *** various fields,such as robotics,face recognition,autonomous driving and healthcare,ai is playing an important ***,although ai is promoting the technological revolution and industrial progress,its security risks are often *** studies have found that the wellperforming deep learning models are extremely vulnerable to adversarial examples [1-3].The adversarial examples are crafted by applying small,humanimperceptible perturbations to natural examples,but can mislead deep learning models to make wrong *** vulnerability of deep learning models to adversarial examples can raise security and safety threats to various realworld applications.

关键词： robustness adversarial example adversarial training deep 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：